From da142f3d373a6ddaca0119615a8db2175ddc4121 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 5 Dec 2025 15:26:55 -0800
Subject: KVM: Remove subtle "struct kvm_stats_desc" pseudo-overlay

Remove KVM's internal pseudo-overlay of kvm_stats_desc, which subtly
aliases the flexible name[] in the uAPI definition with a fixed-size array
of the same name.  The unusual embedded structure results in compiler
warnings due to -Wflex-array-member-not-at-end, and also necessitates an
extra level of dereferencing in KVM.  To avoid the "overlay", define the
uAPI structure to have a fixed-size name when building for the kernel.

Opportunistically clean up the indentation for the stats macros, and
replace spaces with tabs.

No functional change intended.

Reported-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Closes: https://lore.kernel.org/all/aPfNKRpLfhmhYqfP@kspp
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
[..]
Acked-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Bibo Mao <maobibo@loongson.cn>
Acked-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/20251205232655.445294-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/guest.c    |  4 +--
 arch/loongarch/kvm/vcpu.c |  2 +-
 arch/loongarch/kvm/vm.c   |  2 +-
 arch/mips/kvm/mips.c      |  4 +--
 arch/powerpc/kvm/book3s.c |  4 +--
 arch/powerpc/kvm/booke.c  |  4 +--
 arch/riscv/kvm/vcpu.c     |  2 +-
 arch/riscv/kvm/vm.c       |  2 +-
 arch/s390/kvm/kvm-s390.c  |  4 +--
 arch/x86/kvm/x86.c        |  4 +--
 include/linux/kvm_host.h  | 83 ++++++++++++++++++++---------------------------
 include/uapi/linux/kvm.h  |  8 +++++
 virt/kvm/binary_stats.c   |  2 +-
 virt/kvm/kvm_main.c       | 20 ++++++------
 14 files changed, 70 insertions(+), 75 deletions(-)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 1c87699fd886..332c453b87cf 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -29,7 +29,7 @@
 
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 
@@ -42,7 +42,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, hvc_exit_stat),
 	STATS_DESC_COUNTER(VCPU, wfe_exit_stat),
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 656b954c1134..b3547bd41d21 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -14,7 +14,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, int_exits),
 	STATS_DESC_COUNTER(VCPU, idle_exits),
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 194ccbcdc3b3..7deff56e0e1a 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -10,7 +10,7 @@
 #include <asm/kvm_eiointc.h>
 #include <asm/kvm_pch_pic.h>
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, pages),
 	STATS_DESC_ICOUNTER(VM, hugepages),
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index b0fb92fda4d4..23e69baad453 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -38,7 +38,7 @@
 #define VECTORSPACING 0x100	/* for EI/VI mode */
 #endif
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 
@@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, wait_exits),
 	STATS_DESC_COUNTER(VCPU, cache_exits),
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d79c5d1098c0..2efbe05caed7 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -38,7 +38,7 @@
 
 /* #define EXIT_DEBUG */
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, num_2M_pages),
 	STATS_DESC_ICOUNTER(VM, num_1G_pages)
@@ -53,7 +53,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, sum_exits),
 	STATS_DESC_COUNTER(VCPU, mmio_exits),
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 3401b96be475..f3ddb24ece74 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -36,7 +36,7 @@
 
 unsigned long kvmppc_booke_handlers;
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_ICOUNTER(VM, num_2M_pages),
 	STATS_DESC_ICOUNTER(VM, num_1G_pages)
@@ -51,7 +51,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, sum_exits),
 	STATS_DESC_COUNTER(VCPU, mmio_exits),
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index a55a95da54d0..fdd99ac1e714 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -24,7 +24,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, ecall_exit_stat),
 	STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 66d91ae6e9b2..715a06ae8c13 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -13,7 +13,7 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_mmu.h>
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS()
 };
 static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 56a50524b3ee..495141bf0398 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -64,7 +64,7 @@
 #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
 			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, inject_io),
 	STATS_DESC_COUNTER(VM, inject_float_mchk),
@@ -90,7 +90,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, exit_userspace),
 	STATS_DESC_COUNTER(VCPU, exit_null),
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ff8812f3a129..69e0a033e4ac 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -237,7 +237,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_ipiv);
 bool __read_mostly enable_device_posted_irqs = true;
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_device_posted_irqs);
 
-const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+const struct kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
 	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
 	STATS_DESC_COUNTER(VM, mmu_pte_write),
@@ -263,7 +263,7 @@ const struct kvm_stats_header kvm_vm_stats_header = {
 		       sizeof(kvm_vm_stats_desc),
 };
 
-const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
+const struct kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	KVM_GENERIC_VCPU_STATS(),
 	STATS_DESC_COUNTER(VCPU, pf_taken),
 	STATS_DESC_COUNTER(VCPU, pf_fixed),
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d93f75b05ae2..7428d9949382 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1927,56 +1927,43 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	struct kvm *kvm;
-	const struct _kvm_stats_desc *desc;
+	const struct kvm_stats_desc *desc;
 	enum kvm_stat_kind kind;
 };
 
-struct _kvm_stats_desc {
-	struct kvm_stats_desc desc;
-	char name[KVM_STATS_NAME_SIZE];
-};
-
-#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		       \
-	.flags = type | unit | base |					       \
-		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	       \
-		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	       \
-	.exponent = exp,						       \
-	.size = sz,							       \
+#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz)		\
+	.flags = type | unit | base |					\
+		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |       \
+		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	\
+		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	\
+	.exponent = exp,						\
+	.size = sz,							\
 	.bucket_size = bsz
 
-#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, generic.stat)   \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vm_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
-#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		       \
-	{								       \
-		{							       \
-			STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),     \
-			.offset = offsetof(struct kvm_vcpu_stat, stat)	       \
-		},							       \
-		.name = #stat,						       \
-	}
+#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, generic.stat),		\
+	.name = #stat,							\
+}
+#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vm_stat, stat),			\
+	.name = #stat,							\
+}
+#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz)		\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = offsetof(struct kvm_vcpu_stat, stat),			\
+	.name = #stat,							\
+}
 /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
 #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz)		       \
 	SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
@@ -2053,7 +2040,7 @@ struct _kvm_stats_desc {
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
-		       const struct _kvm_stats_desc *desc,
+		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset);
 
@@ -2098,9 +2085,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
 
 
 extern const struct kvm_stats_header kvm_vm_stats_header;
-extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
+extern const struct kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
-extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
+extern const struct kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index dddb781b0507..76bd54848b11 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -14,6 +14,10 @@
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
+#ifdef __KERNEL__
+#include <linux/kvm_types.h>
+#endif
+
 #define KVM_API_VERSION 12
 
 /*
@@ -1579,7 +1583,11 @@ struct kvm_stats_desc {
 	__u16 size;
 	__u32 offset;
 	__u32 bucket_size;
+#ifdef __KERNEL__
+	char name[KVM_STATS_NAME_SIZE];
+#else
 	char name[];
+#endif
 };
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c
index eefca6c69f51..76ce697c773b 100644
--- a/virt/kvm/binary_stats.c
+++ b/virt/kvm/binary_stats.c
@@ -50,7 +50,7 @@
  * Return: the number of bytes that has been successfully read
  */
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
-		       const struct _kvm_stats_desc *desc,
+		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5b5b69c97665..cf65fd82d36d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -983,9 +983,9 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
 		kvm_free_memslot(kvm, memslot);
 }
 
-static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
+static umode_t kvm_stats_debugfs_mode(const struct kvm_stats_desc *desc)
 {
-	switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
+	switch (desc->flags & KVM_STATS_TYPE_MASK) {
 	case KVM_STATS_TYPE_INSTANT:
 		return 0444;
 	case KVM_STATS_TYPE_CUMULATIVE:
@@ -1020,7 +1020,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 	struct dentry *dent;
 	char dir_name[ITOA_MAX_LEN * 2];
 	struct kvm_stat_data *stat_data;
-	const struct _kvm_stats_desc *pdesc;
+	const struct kvm_stats_desc *pdesc;
 	int i, ret = -ENOMEM;
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
@@ -6186,11 +6186,11 @@ static int kvm_stat_data_get(void *data, u64 *val)
 	switch (stat_data->kind) {
 	case KVM_STAT_VM:
 		r = kvm_get_stat_per_vm(stat_data->kvm,
-					stat_data->desc->desc.offset, val);
+					stat_data->desc->offset, val);
 		break;
 	case KVM_STAT_VCPU:
 		r = kvm_get_stat_per_vcpu(stat_data->kvm,
-					  stat_data->desc->desc.offset, val);
+					  stat_data->desc->offset, val);
 		break;
 	}
 
@@ -6208,11 +6208,11 @@ static int kvm_stat_data_clear(void *data, u64 val)
 	switch (stat_data->kind) {
 	case KVM_STAT_VM:
 		r = kvm_clear_stat_per_vm(stat_data->kvm,
-					  stat_data->desc->desc.offset);
+					  stat_data->desc->offset);
 		break;
 	case KVM_STAT_VCPU:
 		r = kvm_clear_stat_per_vcpu(stat_data->kvm,
-					    stat_data->desc->desc.offset);
+					    stat_data->desc->offset);
 		break;
 	}
 
@@ -6360,7 +6360,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 static void kvm_init_debug(void)
 {
 	const struct file_operations *fops;
-	const struct _kvm_stats_desc *pdesc;
+	const struct kvm_stats_desc *pdesc;
 	int i;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
@@ -6373,7 +6373,7 @@ static void kvm_init_debug(void)
 			fops = &vm_stat_readonly_fops;
 		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
 				kvm_debugfs_dir,
-				(void *)(long)pdesc->desc.offset, fops);
+				(void *)(long)pdesc->offset, fops);
 	}
 
 	for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
@@ -6384,7 +6384,7 @@ static void kvm_init_debug(void)
 			fops = &vcpu_stat_readonly_fops;
 		debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
 				kvm_debugfs_dir,
-				(void *)(long)pdesc->desc.offset, fops);
+				(void *)(long)pdesc->offset, fops);
 	}
 }
 
-- 
cgit v1.2.3


From f947d9e77b26238b821b5227afb4fee8c7ea0d5a Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Mon, 12 Jan 2026 09:39:03 +1000
Subject: nvme/host: fixup some typos

Fix up some minor typos in the nvme host driver and a comment
style to conform to the standard kernel style.

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 69cb04406b47..74cbbf48a981 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -25,7 +25,8 @@
 
 struct nvme_tcp_queue;
 
-/* Define the socket priority to use for connections were it is desirable
+/*
+ * Define the socket priority to use for connections where it is desirable
  * that the NIC consider performing optimized packet processing or filtering.
  * A non-zero value being sufficient to indicate general consideration of any
  * possible optimization.  Making it a module param allows for alternative
@@ -926,7 +927,7 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 			req->curr_bio = req->curr_bio->bi_next;
 
 			/*
-			 * If we don`t have any bios it means that controller
+			 * If we don't have any bios it means the controller
 			 * sent more data than we requested, hence error
 			 */
 			if (!req->curr_bio) {
-- 
cgit v1.2.3


From ddfb8b322bbd8ae996f4ac0192f0190feb0a01ce Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 3 Nov 2025 15:44:06 +0100
Subject: nvme: expose active quirks in sysfs

Currently, there is no straightforward way for a user to inspect
which quirks are active for a given device from userspace.

Add a new "quirks" sysfs attribute to the nvme controller device.

Reading this file will display a human-readable list
of all active quirks, with each quirk name on a new line.
If no quirks are active, it will display "none".

Tested-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/nvme.h  | 54 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/sysfs.c | 23 ++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9a5f28c5103c..523015ae2add 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -180,6 +180,60 @@ enum nvme_quirks {
 	NVME_QUIRK_DMAPOOL_ALIGN_512		= (1 << 22),
 };
 
+static inline char *nvme_quirk_name(enum nvme_quirks q)
+{
+	switch (q) {
+	case NVME_QUIRK_STRIPE_SIZE:
+		return "stripe_size";
+	case NVME_QUIRK_IDENTIFY_CNS:
+		return "identify_cns";
+	case NVME_QUIRK_DEALLOCATE_ZEROES:
+		return "deallocate_zeroes";
+	case NVME_QUIRK_DELAY_BEFORE_CHK_RDY:
+		return "delay_before_chk_rdy";
+	case NVME_QUIRK_NO_APST:
+		return "no_apst";
+	case NVME_QUIRK_NO_DEEPEST_PS:
+		return "no_deepest_ps";
+	case NVME_QUIRK_QDEPTH_ONE:
+		return "qdepth_one";
+	case NVME_QUIRK_MEDIUM_PRIO_SQ:
+		return "medium_prio_sq";
+	case NVME_QUIRK_IGNORE_DEV_SUBNQN:
+		return "ignore_dev_subnqn";
+	case NVME_QUIRK_DISABLE_WRITE_ZEROES:
+		return "disable_write_zeroes";
+	case NVME_QUIRK_SIMPLE_SUSPEND:
+		return "simple_suspend";
+	case NVME_QUIRK_SINGLE_VECTOR:
+		return "single_vector";
+	case NVME_QUIRK_128_BYTES_SQES:
+		return "128_bytes_sqes";
+	case NVME_QUIRK_SHARED_TAGS:
+		return "shared_tags";
+	case NVME_QUIRK_NO_TEMP_THRESH_CHANGE:
+		return "no_temp_thresh_change";
+	case NVME_QUIRK_NO_NS_DESC_LIST:
+		return "no_ns_desc_list";
+	case NVME_QUIRK_DMA_ADDRESS_BITS_48:
+		return "dma_address_bits_48";
+	case NVME_QUIRK_SKIP_CID_GEN:
+		return "skip_cid_gen";
+	case NVME_QUIRK_BOGUS_NID:
+		return "bogus_nid";
+	case NVME_QUIRK_NO_SECONDARY_TEMP_THRESH:
+		return "no_secondary_temp_thresh";
+	case NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND:
+		return "force_no_simple_suspend";
+	case NVME_QUIRK_BROKEN_MSI:
+		return "broken_msi";
+	case NVME_QUIRK_DMAPOOL_ALIGN_512:
+		return "dmapool_align_512";
+	}
+
+	return "unknown";
+}
+
 /*
  * Common request structure for NVMe passthrough.  All drivers must have
  * this structure as the first member of their request-private data.
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 29430949ce2f..16c6fea4b2db 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -601,6 +601,28 @@ static ssize_t dctype_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(dctype);
 
+static ssize_t quirks_show(struct device *dev, struct device_attribute *attr,
+                char *buf)
+{
+	int count = 0, i;
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned long quirks = ctrl->quirks;
+
+	if (!quirks)
+		return sysfs_emit(buf, "none\n");
+
+	for (i = 0; quirks; ++i) {
+		if (quirks & 1) {
+			count += sysfs_emit_at(buf, count, "%s\n",
+					nvme_quirk_name(BIT(i)));
+		}
+		quirks >>= 1;
+	}
+
+	return count;
+}
+static DEVICE_ATTR_RO(quirks);
+
 #ifdef CONFIG_NVME_HOST_AUTH
 static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -742,6 +764,7 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_kato.attr,
 	&dev_attr_cntrltype.attr,
 	&dev_attr_dctype.attr,
+	&dev_attr_quirks.attr,
 #ifdef CONFIG_NVME_HOST_AUTH
 	&dev_attr_dhchap_secret.attr,
 	&dev_attr_dhchap_ctrl_secret.attr,
-- 
cgit v1.2.3


From 5a741f8cc6fe62542f955cd8d24933a1b6589cbd Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Sun, 28 Dec 2025 12:48:36 +0000
Subject: soc: microchip: mpfs: Fix memory leak in mpfs_sys_controller_probe()

In mpfs_sys_controller_probe(), if of_get_mtd_device_by_node() fails,
the function returns immediately without freeing the allocated memory
for sys_controller, leading to a memory leak.

Fix this by jumping to the out_free label to ensure the memory is
properly freed.

Also, consolidate the error handling for the mbox_request_channel()
failure case to use the same label.

Fixes: 742aa6c563d2 ("soc: microchip: mpfs: enable access to the system controller's flash")
Co-developed-by: Jianhao Xu <jianhao.xu@seu.edu.cn>
Signed-off-by: Jianhao Xu <jianhao.xu@seu.edu.cn>
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/soc/microchip/mpfs-sys-controller.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/soc/microchip/mpfs-sys-controller.c b/drivers/soc/microchip/mpfs-sys-controller.c
index 30bc45d17d34..81636cfecd37 100644
--- a/drivers/soc/microchip/mpfs-sys-controller.c
+++ b/drivers/soc/microchip/mpfs-sys-controller.c
@@ -142,8 +142,10 @@ static int mpfs_sys_controller_probe(struct platform_device *pdev)
 
 	sys_controller->flash = of_get_mtd_device_by_node(np);
 	of_node_put(np);
-	if (IS_ERR(sys_controller->flash))
-		return dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n");
+	if (IS_ERR(sys_controller->flash)) {
+		ret = dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n");
+		goto out_free;
+	}
 
 no_flash:
 	sys_controller->client.dev = dev;
@@ -155,8 +157,7 @@ no_flash:
 	if (IS_ERR(sys_controller->chan)) {
 		ret = dev_err_probe(dev, PTR_ERR(sys_controller->chan),
 				    "Failed to get mbox channel\n");
-		kfree(sys_controller);
-		return ret;
+		goto out_free;
 	}
 
 	init_completion(&sys_controller->c);
@@ -174,6 +175,10 @@ no_flash:
 	dev_info(&pdev->dev, "Registered MPFS system controller\n");
 
 	return 0;
+
+out_free:
+	kfree(sys_controller);
+	return ret;
 }
 
 static void mpfs_sys_controller_remove(struct platform_device *pdev)
-- 
cgit v1.2.3


From ac30cd304347f2daeece6998bb5f0ae2db64e397 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Wed, 28 Jan 2026 08:26:23 +0000
Subject: nvme: stop using AWUPF

As described at [0], much of the atomic write parts of the specification
are lacking.

For now, there is nothing which we can do in software about the lack of
a dedicated NVMe write atomic command.

As for reading the atomic write limits, it is felt that the per-namespace
values are mostly properly specified and it is assumed that they are
properly implemented.

The specification of NAWUPF is quite clear. However the specification of
NABSPF is less clear. The lack of clarity in NABSPF comes from deciding
whether NABSPF applies when NSABP is 0 - it is assumed that NSABPF does
not apply when NSABP is 0.

As for the per-controller AWUPF, how this value applies to shared
namespaces is missing in the specification. Furthermore, the value is in
terms of logical blocks, which is an NS entity.

Since AWUPF is so poorly defined, stop using it already together.
Hopefully this will force vendors to implement NAWUPF support always.

Note that AWUPF not only effects atomic write support, but also the
physical block size reported for the device.

To help users know this restriction, log an info message per NS.

[0] https://lore.kernel.org/linux-nvme/20250707141834.GA30198@lst.de/

Tested-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 14 +++++---------
 drivers/nvme/host/nvme.h |  3 ++-
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7bf228df6001..83efc88ac0f9 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2045,14 +2045,10 @@ static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
 		if (id->nabspf)
 			boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
 	} else {
-		/*
-		 * Use the controller wide atomic write unit.  This sucks
-		 * because the limit is defined in terms of logical blocks while
-		 * namespaces can have different formats, and because there is
-		 * no clear language in the specification prohibiting different
-		 * values for different controllers in the subsystem.
-		 */
-		atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
+		if (ns->ctrl->awupf)
+			dev_info_once(ns->ctrl->device,
+				"AWUPF ignored, only NAWUPF accepted\n");
+		atomic_bs = bs;
 	}
 
 	lim->atomic_write_hw_max = atomic_bs;
@@ -3221,7 +3217,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
-	subsys->awupf = le16_to_cpu(id->awupf);
 
 	/* Versions prior to 1.4 don't necessarily report a valid type */
 	if (id->cntrltype == NVME_CTRL_DISC ||
@@ -3654,6 +3649,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
+	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 523015ae2add..9971045dbc05 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -464,6 +464,8 @@ struct nvme_ctrl {
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
+
+	u16			awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -496,7 +498,6 @@ struct nvme_subsystem {
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
-	u16			awupf; /* 0's based value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;
-- 
cgit v1.2.3


From 1799d8abeabc68ec05679292aaf6cba93b343c05 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Tue, 27 Jan 2026 19:38:44 +0800
Subject: xfrm6: fix uninitialized saddr in xfrm6_get_saddr()

xfrm6_get_saddr() does not check the return value of
ipv6_dev_get_saddr(). When ipv6_dev_get_saddr() fails to find a suitable
source address (returns -EADDRNOTAVAIL), saddr->in6 is left
uninitialized, but xfrm6_get_saddr() still returns 0 (success).

This causes the caller xfrm_tmpl_resolve_one() to use the uninitialized
address in xfrm_state_find(), triggering KMSAN warning:

=====================================================
BUG: KMSAN: uninit-value in xfrm_state_find+0x2424/0xa940
 xfrm_state_find+0x2424/0xa940
 xfrm_resolve_and_create_bundle+0x906/0x5a20
 xfrm_lookup_with_ifid+0xcc0/0x3770
 xfrm_lookup_route+0x63/0x2b0
 ip_route_output_flow+0x1ce/0x270
 udp_sendmsg+0x2ce1/0x3400
 inet_sendmsg+0x1ef/0x2a0
 __sock_sendmsg+0x278/0x3d0
 __sys_sendto+0x593/0x720
 __x64_sys_sendto+0x130/0x200
 x64_sys_call+0x332b/0x3e70
 do_syscall_64+0xd3/0xf80
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable tmp.i.i created at:
 xfrm_resolve_and_create_bundle+0x3e3/0x5a20
 xfrm_lookup_with_ifid+0xcc0/0x3770
=====================================================

Fix by checking the return value of ipv6_dev_get_saddr() and propagating
the error.

Fixes: a1e59abf8249 ("[XFRM]: Fix wildcard as tunnel source")
Reported-by: syzbot+e136d86d34b42399a8b1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68bf1024.a70a0220.7a912.02c2.GAE@google.com/T/
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv6/xfrm6_policy.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 1f19b6f14484..125ea9a5b8a0 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -57,6 +57,7 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr,
 	struct dst_entry *dst;
 	struct net_device *dev;
 	struct inet6_dev *idev;
+	int err;
 
 	dst = xfrm6_dst_lookup(params);
 	if (IS_ERR(dst))
@@ -68,9 +69,11 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr,
 		return -EHOSTUNREACH;
 	}
 	dev = idev->dev;
-	ipv6_dev_get_saddr(dev_net(dev), dev, &params->daddr->in6, 0,
-			   &saddr->in6);
+	err = ipv6_dev_get_saddr(dev_net(dev), dev, &params->daddr->in6, 0,
+				 &saddr->in6);
 	dst_release(dst);
+	if (err)
+		return -EHOSTUNREACH;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 0a4524bc69882a4ddb235bb6b279597721bda197 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 27 Jan 2026 14:49:23 +0200
Subject: xfrm: skip templates check for packet offload tunnel mode

In packet offload, hardware is responsible to check templates. The
result of its operation is forwarded through secpath by relevant
drivers. That secpath is actually removed in __xfrm_policy_check2().

In case packet is forwarded, this secpath is reset in RX, but pushed
again to TX where policy is rechecked again against dummy secpath
in xfrm_policy_ok().

Such situation causes to unexpected XfrmInTmplMismatch increase.

As a solution, simply skip template mismatch check.

Fixes: 600258d555f0 ("xfrm: delete intermediate secpath entry in packet offload mode")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 62486f866975..5428185196a1 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3801,8 +3801,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		struct xfrm_tmpl *tp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl *stp[XFRM_MAX_DEPTH];
 		struct xfrm_tmpl **tpp = tp;
+		int i, k = 0;
 		int ti = 0;
-		int i, k;
 
 		sp = skb_sec_path(skb);
 		if (!sp)
@@ -3828,6 +3828,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			tpp = stp;
 		}
 
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET && sp == &dummy)
+			/* This policy template was already checked by HW
+			 * and secpath was removed in __xfrm_policy_check2.
+			 */
+			goto out;
+
 		/* For each tunnel xfrm, find the first matching tmpl.
 		 * For each tmpl before that, find corresponding xfrm.
 		 * Order is _important_. Later we will implement
@@ -3837,7 +3843,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		 * verified to allow them to be skipped in future policy
 		 * checks (e.g. nested tunnels).
 		 */
-		for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
+		for (i = xfrm_nr - 1; i >= 0; i--) {
 			k = xfrm_policy_ok(tpp[i], sp, k, family, if_id);
 			if (k < 0) {
 				if (k < -1)
@@ -3853,6 +3859,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 			goto reject;
 		}
 
+out:
 		xfrm_pols_put(pols, npols);
 		sp->verified_cnt = k;
 
-- 
cgit v1.2.3


From 0a1fc2f301529ac75aec0ce80d5ab9d9e4dc4b16 Mon Sep 17 00:00:00 2001
From: Daniel Hodges <hodgesd@meta.com>
Date: Sat, 31 Jan 2026 19:08:40 -0800
Subject: nvme-fabrics: use kfree_sensitive() for DHCHAP secrets

The DHCHAP secrets (dhchap_secret and dhchap_ctrl_secret) contain
authentication key material for NVMe-oF. Use kfree_sensitive() instead
of kfree() in nvmf_free_options() to ensure secrets are zeroed before
the memory is freed, preventing recovery from freed pages.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Daniel Hodges <hodgesd@meta.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fabrics.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 55a8afd2efd5..d37cb140d832 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -1290,8 +1290,8 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts)
 	kfree(opts->subsysnqn);
 	kfree(opts->host_traddr);
 	kfree(opts->host_iface);
-	kfree(opts->dhchap_secret);
-	kfree(opts->dhchap_ctrl_secret);
+	kfree_sensitive(opts->dhchap_secret);
+	kfree_sensitive(opts->dhchap_ctrl_secret);
 	kfree(opts);
 }
 EXPORT_SYMBOL_GPL(nvmf_free_options);
-- 
cgit v1.2.3


From b84bb7bd913d8ca2f976ee6faf4a174f91c02b8d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 31 Jan 2026 22:48:08 +0800
Subject: nvme: fix admin queue leak on controller reset

When nvme_alloc_admin_tag_set() is called during a controller reset,
a previous admin queue may still exist. Release it properly before
allocating a new one to avoid orphaning the old queue.

This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix
admin request_queue lifetime").

Cc: Keith Busch <kbusch@kernel.org>
Fixes: 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").
Reported-and-tested-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs9wv3SdPo+N01Fw2SHBYDs9tj2M_e1-GdQOkRy=DsBB1w@mail.gmail.com/
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 83efc88ac0f9..c12986495e71 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4860,6 +4860,13 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ret)
 		return ret;
 
+	/*
+	 * If a previous admin queue exists (e.g., from before a reset),
+	 * put it now before allocating a new one to avoid orphaning it.
+	 */
+	if (ctrl->admin_q)
+		blk_put_queue(ctrl->admin_q);
+
 	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
-- 
cgit v1.2.3


From 594c11d0e1d445f580898a2b8c850f2e3f099368 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Tue, 27 Jan 2026 07:22:35 -0600
Subject: ipmi: Fix use-after-free and list corruption on sender error

The analysis from Breno:

When the SMI sender returns an error, smi_work() delivers an error
response but then jumps back to restart without cleaning up properly:

1. intf->curr_msg is not cleared, so no new message is pulled
2. newmsg still points to the message, causing sender() to be called
   again with the same message
3. If sender() fails again, deliver_err_response() is called with
   the same recv_msg that was already queued for delivery

This causes list_add corruption ("list_add double add") because the
recv_msg is added to the user_msgs list twice. Subsequently, the
corrupted list leads to use-after-free when the memory is freed and
reused, and eventually a NULL pointer dereference when accessing
recv_msg->done.

The buggy sequence:

  sender() fails
    -> deliver_err_response(recv_msg)  // recv_msg queued for delivery
    -> goto restart                    // curr_msg not cleared!
  sender() fails again (same message!)
    -> deliver_err_response(recv_msg)  // tries to queue same recv_msg
    -> LIST CORRUPTION

Fix this by freeing the message and setting it to NULL on a send error.
Also, always free the newmsg on a send error, otherwise it will leak.

Reported-by: Breno Leitao <leitao@debian.org>
Closes: https://lore.kernel.org/lkml/20260127-ipmi-v1-0-ba5cc90f516f@debian.org/
Fixes: 9cf93a8fa9513 ("ipmi: Allow an SMI sender to return an error")
Cc: stable@vger.kernel.org # 4.18
Reviewed-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_msghandler.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 3f48fc6ab596..a590a67294e2 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -4852,8 +4852,15 @@ restart:
 			if (newmsg->recv_msg)
 				deliver_err_response(intf,
 						     newmsg->recv_msg, cc);
-			else
-				ipmi_free_smi_msg(newmsg);
+			if (!run_to_completion)
+				spin_lock_irqsave(&intf->xmit_msgs_lock,
+						  flags);
+			intf->curr_msg = NULL;
+			if (!run_to_completion)
+				spin_unlock_irqrestore(&intf->xmit_msgs_lock,
+						       flags);
+			ipmi_free_smi_msg(newmsg);
+			newmsg = NULL;
 			goto restart;
 		}
 	}
-- 
cgit v1.2.3


From 1d90e6c1a56f6ab83e5c9d30ded19e7ac8155713 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Tue, 27 Jan 2026 07:35:02 -0600
Subject: ipmi: Consolidate the run to completion checking for xmit msgs lock

It made things hard to read, move the check to a function.

Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Breno Leitao <leitao@debian.org>
---
 drivers/char/ipmi/ipmi_msghandler.c | 42 +++++++++++++++++++++----------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a590a67294e2..a042b1596933 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -602,6 +602,22 @@ static int __ipmi_bmc_register(struct ipmi_smi *intf,
 static int __scan_channels(struct ipmi_smi *intf,
 				struct ipmi_device_id *id, bool rescan);
 
+static void ipmi_lock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion,
+				unsigned long *flags)
+{
+	if (run_to_completion)
+		return;
+	spin_lock_irqsave(&intf->xmit_msgs_lock, *flags);
+}
+
+static void ipmi_unlock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion,
+				  unsigned long *flags)
+{
+	if (run_to_completion)
+		return;
+	spin_unlock_irqrestore(&intf->xmit_msgs_lock, *flags);
+}
+
 static void free_ipmi_user(struct kref *ref)
 {
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
@@ -1878,11 +1894,9 @@ static void smi_send(struct ipmi_smi *intf,
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	unsigned long flags = 0;
 
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	smi_msg = smi_add_send_msg(intf, smi_msg, priority);
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (smi_msg)
 		handlers->sender(intf->send_info, smi_msg);
@@ -4826,8 +4840,7 @@ static void smi_work(struct work_struct *t)
 	 * message delivery.
 	 */
 restart:
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	if (intf->curr_msg == NULL && !intf->in_shutdown) {
 		struct list_head *entry = NULL;
 
@@ -4843,8 +4856,7 @@ restart:
 			intf->curr_msg = newmsg;
 		}
 	}
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (newmsg) {
 		cc = intf->handlers->sender(intf->send_info, newmsg);
@@ -4852,13 +4864,9 @@ restart:
 			if (newmsg->recv_msg)
 				deliver_err_response(intf,
 						     newmsg->recv_msg, cc);
-			if (!run_to_completion)
-				spin_lock_irqsave(&intf->xmit_msgs_lock,
-						  flags);
+			ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 			intf->curr_msg = NULL;
-			if (!run_to_completion)
-				spin_unlock_irqrestore(&intf->xmit_msgs_lock,
-						       flags);
+			ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 			ipmi_free_smi_msg(newmsg);
 			newmsg = NULL;
 			goto restart;
@@ -4928,16 +4936,14 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf,
 		spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock,
 				       flags);
 
-	if (!run_to_completion)
-		spin_lock_irqsave(&intf->xmit_msgs_lock, flags);
+	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	/*
 	 * We can get an asynchronous event or receive message in addition
 	 * to commands we send.
 	 */
 	if (msg == intf->curr_msg)
 		intf->curr_msg = NULL;
-	if (!run_to_completion)
-		spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags);
+	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
 	if (run_to_completion)
 		smi_work(&intf->smi_work);
-- 
cgit v1.2.3


From 9f235ccecd03c436cb1683eac16b12f119e54aa9 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Tue, 13 Jan 2026 17:41:34 +0800
Subject: ipmi: ipmb: initialise event handler read bytes

IPMB doesn't use i2c reads, but the handler needs to set a value.
Otherwise an i2c read will return an uninitialised value from the bus
driver.

Fixes: 63c4eb347164 ("ipmi:ipmb: Add initial support for IPMI over IPMB")
Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Message-ID: <20260113-ipmb-read-init-v1-1-a9cbce7b94e3@codeconstruct.com.au>
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_ipmb.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/char/ipmi/ipmi_ipmb.c b/drivers/char/ipmi/ipmi_ipmb.c
index 3a51e58b2487..28818952a7a4 100644
--- a/drivers/char/ipmi/ipmi_ipmb.c
+++ b/drivers/char/ipmi/ipmi_ipmb.c
@@ -202,11 +202,16 @@ static int ipmi_ipmb_slave_cb(struct i2c_client *client,
 		break;
 
 	case I2C_SLAVE_READ_REQUESTED:
+		*val = 0xff;
+		ipmi_ipmb_check_msg_done(iidev);
+		break;
+
 	case I2C_SLAVE_STOP:
 		ipmi_ipmb_check_msg_done(iidev);
 		break;
 
 	case I2C_SLAVE_READ_PROCESSED:
+		*val = 0xff;
 		break;
 	}
 
-- 
cgit v1.2.3


From 6b157b408d0c7d125e4d7c62e11e7d9376a5d150 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 16 Jan 2026 17:22:01 -0600
Subject: ipmi:ls2k: Make ipmi_ls2k_platform_driver static

No need for it to be global.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601170753.3zDBerGP-lkp@intel.com/
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_ls2k.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_ls2k.c b/drivers/char/ipmi/ipmi_si_ls2k.c
index 45442c257efd..4c1da80f256c 100644
--- a/drivers/char/ipmi/ipmi_si_ls2k.c
+++ b/drivers/char/ipmi/ipmi_si_ls2k.c
@@ -168,7 +168,7 @@ static void ipmi_ls2k_remove(struct platform_device *pdev)
 	ipmi_si_remove_by_dev(&pdev->dev);
 }
 
-struct platform_driver ipmi_ls2k_platform_driver = {
+static struct platform_driver ipmi_ls2k_platform_driver = {
 	.driver = {
 		.name = "ls2k-ipmi-si",
 	},
-- 
cgit v1.2.3


From 7bb8c40f5ad88392bbabb719ebfd5e3354ce0428 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 4 Feb 2026 11:55:55 +0100
Subject: nvme: add support for dynamic quirk configuration via module
 parameter

Introduce support for enabling or disabling specific NVMe quirks at module
load time through the `quirks` module parameter.
This mechanism allows users to apply known quirks dynamically based on the
device's PCI vendor and device IDs, without requiring to add hardcoded
entries in the driver and recompiling the kernel.

While the generic PCI new_id sysfs interface exists for dynamic
configuration, it is insufficient for scenarios where the system fails
to boot (for example, this has been reported to happen because of the
bogus_nid quirk). The new_id attribute is writable only after the system
has booted and sysfs is mounted.

The `quirks` parameter accepts a list of quirk specifications separated by
a '-' character in the following format:

<VID>:<DID>:<quirk_names>[-<VID>:<DID>:<quirk_names>-..]

Each quirk is represented by its name and can be prefixed with `^` to
indicate that the quirk should be disabled; quirk names are separated by
a ',' character.

Example: enable BOGUS_NID and BROKEN_MSI, disable DEALLOCATE_ZEROES:

   $ modprobe nvme quirks=7170:2210:bogus_nid,broken_msi,^deallocate_zeroes

Tested-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  13 ++
 drivers/nvme/host/pci.c                         | 162 ++++++++++++++++++++++++
 2 files changed, 175 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a8d0afde7f85..f0b286c2dfc1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -74,6 +74,7 @@
 	TPM	TPM drivers are enabled.
 	UMS	USB Mass Storage support is enabled.
 	USB	USB support is enabled.
+	NVME	NVMe support is enabled
 	USBHID	USB Human Interface Device support is enabled.
 	V4L	Video For Linux support is enabled.
 	VGA	The VGA console has been enabled.
@@ -4671,6 +4672,18 @@ Kernel parameters
 			This can be set from sysctl after boot.
 			See Documentation/admin-guide/sysctl/vm.rst for details.
 
+	nvme.quirks=    [NVME] A list of quirk entries to augment the built-in
+			nvme quirk list. List entries are separated by a
+			'-' character.
+			Each entry has the form VendorID:ProductID:quirk_names.
+			The IDs are 4-digits hex numbers and quirk_names is a
+			list of quirk names separated by commas. A quirk name
+			can be prefixed by '^', meaning that the specified
+			quirk must be disabled.
+
+			Example:
+			nvme.quirks=7710:2267:bogus_nid,^identify_cns-9900:7711:broken_msi
+
 	ohci1394_dma=early	[HW,EARLY] enable debugging via the ohci1394 driver.
 			See Documentation/core-api/debugging-via-ohci1394.rst for more
 			info.
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9fc4a60280a0..bd884e294600 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -72,6 +72,13 @@
 static_assert(MAX_PRP_RANGE / NVME_CTRL_PAGE_SIZE <=
 	(1 /* prp1 */ + NVME_MAX_NR_DESCRIPTORS * PRPS_PER_PAGE));
 
+struct quirk_entry {
+	u16 vendor_id;
+	u16 dev_id;
+	u32 enabled_quirks;
+	u32 disabled_quirks;
+};
+
 static int use_threaded_interrupts;
 module_param(use_threaded_interrupts, int, 0444);
 
@@ -102,6 +109,142 @@ static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2 and < 4096");
 
+static struct quirk_entry *nvme_pci_quirk_list;
+static unsigned int nvme_pci_quirk_count;
+
+/* Helper to parse individual quirk names */
+static int nvme_parse_quirk_names(char *quirk_str, struct quirk_entry *entry)
+{
+	int i;
+	size_t field_len;
+	bool disabled, found;
+	char *p = quirk_str, *field;
+
+	while ((field = strsep(&p, ",")) && *field) {
+		disabled = false;
+		found = false;
+
+		if (*field == '^') {
+			/* Skip the '^' character */
+			disabled = true;
+			field++;
+		}
+
+		field_len = strlen(field);
+		for (i = 0; i < 32; i++) {
+			unsigned int bit = 1U << i;
+			char *q_name = nvme_quirk_name(bit);
+			size_t q_len = strlen(q_name);
+
+			if (!strcmp(q_name, "unknown"))
+				break;
+
+			if (!strcmp(q_name, field) &&
+				    q_len == field_len) {
+				if (disabled)
+					entry->disabled_quirks |= bit;
+				else
+					entry->enabled_quirks |= bit;
+				found = true;
+				break;
+			}
+		}
+
+		if (!found) {
+			pr_err("nvme: unrecognized quirk %s\n", field);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+/* Helper to parse a single VID:DID:quirk_names entry */
+static int nvme_parse_quirk_entry(char *s, struct quirk_entry *entry)
+{
+	char *field;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->vendor_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field || kstrtou16(field, 16, &entry->dev_id))
+		return -EINVAL;
+
+	field = strsep(&s, ":");
+	if (!field)
+		return -EINVAL;
+
+	return nvme_parse_quirk_names(field, entry);
+}
+
+static int quirks_param_set(const char *value, const struct kernel_param *kp)
+{
+	int count, err, i;
+	struct quirk_entry *qlist;
+	char *field, *val, *sep_ptr;
+
+	err = param_set_copystring(value, kp);
+	if (err)
+		return err;
+
+	val = kstrdup(value, GFP_KERNEL);
+	if (!val)
+		return -ENOMEM;
+
+	if (!*val)
+		goto out_free_val;
+
+	count = 1;
+	for (i = 0; val[i]; i++) {
+		if (val[i] == '-')
+			count++;
+	}
+
+	qlist = kcalloc(count, sizeof(*qlist), GFP_KERNEL);
+	if (!qlist) {
+		err = -ENOMEM;
+		goto out_free_val;
+	}
+
+	i = 0;
+	sep_ptr = val;
+	while ((field = strsep(&sep_ptr, "-"))) {
+		if (nvme_parse_quirk_entry(field, &qlist[i])) {
+			pr_err("nvme: failed to parse quirk string %s\n",
+				value);
+			goto out_free_qlist;
+		}
+
+		i++;
+	}
+
+	nvme_pci_quirk_count = count;
+	nvme_pci_quirk_list  = qlist;
+	goto out_free_val;
+
+out_free_qlist:
+	kfree(qlist);
+out_free_val:
+	kfree(val);
+	return err;
+}
+
+static char quirks_param[128];
+static const struct kernel_param_ops quirks_param_ops = {
+	.set = quirks_param_set,
+	.get = param_get_string,
+};
+
+static struct kparam_string quirks_param_string = {
+	.maxlen = sizeof(quirks_param),
+	.string = quirks_param,
+};
+
+module_param_cb(quirks, &quirks_param_ops, &quirks_param_string, 0444);
+MODULE_PARM_DESC(quirks, "Enable/disable NVMe quirks by specifying "
+						"quirks=VID:DID:quirk_names");
+
 static int io_queue_count_set(const char *val, const struct kernel_param *kp)
 {
 	unsigned int n;
@@ -3439,12 +3582,25 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 	return 0;
 }
 
+static struct quirk_entry *detect_dynamic_quirks(struct pci_dev *pdev)
+{
+	int i;
+
+	for (i = 0; i < nvme_pci_quirk_count; i++)
+		if (pdev->vendor == nvme_pci_quirk_list[i].vendor_id &&
+		    pdev->device == nvme_pci_quirk_list[i].dev_id)
+			return &nvme_pci_quirk_list[i];
+
+	return NULL;
+}
+
 static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 		const struct pci_device_id *id)
 {
 	unsigned long quirks = id->driver_data;
 	int node = dev_to_node(&pdev->dev);
 	struct nvme_dev *dev;
+	struct quirk_entry *qentry;
 	int ret = -ENOMEM;
 
 	dev = kzalloc_node(struct_size(dev, descriptor_pools, nr_node_ids),
@@ -3476,6 +3632,11 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev,
 			 "platform quirk: setting simple suspend\n");
 		quirks |= NVME_QUIRK_SIMPLE_SUSPEND;
 	}
+	qentry = detect_dynamic_quirks(pdev);
+	if (qentry) {
+		quirks |= qentry->enabled_quirks;
+		quirks &= ~qentry->disabled_quirks;
+	}
 	ret = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
 			     quirks);
 	if (ret)
@@ -4074,6 +4235,7 @@ static int __init nvme_init(void)
 
 static void __exit nvme_exit(void)
 {
+	kfree(nvme_pci_quirk_list);
 	pci_unregister_driver(&nvme_driver);
 	flush_workqueue(nvme_wq);
 }
-- 
cgit v1.2.3


From 63059500b124254c2630b2f8c46cb3555e726f52 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 5 Feb 2026 17:11:15 +0000
Subject: nvme: stop setting namespace gendisk device driver data

Since commit 1f4137e882c6 ("nvme: move passthrough logging attribute to
head"), we stopped using the namespace to hold the passthrough logging
enabled attribute. There is now nowhere now which looks up the gendisk dev
driver data, so stop setting it.

Incidentally, it would have been better to set this before adding the
disk.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c12986495e71..3a2126584a23 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4181,13 +4181,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	nvme_mpath_add_disk(ns, info->anagrpid);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
 
-	/*
-	 * Set ns->disk->device->driver_data to ns so we can access
-	 * ns->head->passthru_err_log_enabled in
-	 * nvme_io_passthru_err_log_enabled_[store | show]().
-	 */
-	dev_set_drvdata(disk_to_dev(ns->disk), ns);
-
 	return;
 
  out_cleanup_ns_from_list:
-- 
cgit v1.2.3


From 3ddfbfbc78ac1d3d9e95098fb6a32b57b8a0dcae Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Thu, 5 Feb 2026 17:11:14 +0000
Subject: nvme: correct comment about nvme_ns_remove()

The comment in nvme_mpath_remove_disk() references nvme_remove_ns(), which
should be nvme_ns_remove().

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/multipath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 174027d1cc19..bfcc5904e6a2 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1300,7 +1300,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	mutex_lock(&head->subsys->lock);
 	/*
 	 * We are called when all paths have been removed, and at that point
-	 * head->list is expected to be empty. However, nvme_remove_ns() and
+	 * head->list is expected to be empty. However, nvme_ns_remove() and
 	 * nvme_init_ns_head() can run concurrently and so if head->delayed_
 	 * removal_secs is configured, it is possible that by the time we reach
 	 * this point, head->list may no longer be empty. Therefore, we recheck
-- 
cgit v1.2.3


From 52c9ee202edd21d0599ac3b5a6fe1da2a2f053e5 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 6 Feb 2026 09:59:32 -0600
Subject: ipmi:si: Handle waiting messages when BMC failure detected

If a BMC failure is detected, the current message is returned with an
error.  However, if there was a waiting message, it would not be
handled.

Add a check for the waiting message after handling the current message.

Suggested-by: Guenter Roeck <linux@roeck-us.net>
Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Closes: https://lore.kernel.org/linux-acpi/CAK8fFZ58fidGUCHi5WFX0uoTPzveUUDzT=k=AAm4yWo3bAuCFg@mail.gmail.com/
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_intf.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 5459ffdde8dc..ff159b1162b9 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -809,6 +809,12 @@ restart:
 			 */
 			return_hosed_msg(smi_info, IPMI_BUS_ERR);
 		}
+		if (smi_info->waiting_msg != NULL) {
+			/* Also handle if there was a message waiting. */
+			smi_info->curr_msg = smi_info->waiting_msg;
+			smi_info->waiting_msg = NULL;
+			return_hosed_msg(smi_info, IPMI_BUS_ERR);
+		}
 		smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_HOSED);
 		goto out;
 	}
-- 
cgit v1.2.3


From c3bb3295637cc9bf514f690941ca9a385bf30113 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 6 Feb 2026 10:33:52 -0600
Subject: ipmi:si: Use a long timeout when the BMC is misbehaving

If the driver goes into HOSED state, don't reset the timeout to the
short timeout in the timeout handler.

Reported-by: Igor Raits <igor@gooddata.com>
Closes: https://lore.kernel.org/linux-acpi/CAK8fFZ58fidGUCHi5WFX0uoTPzveUUDzT=k=AAm4yWo3bAuCFg@mail.gmail.com/
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
---
 drivers/char/ipmi/ipmi_si_intf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index ff159b1162b9..0049e3792ba1 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1119,7 +1119,9 @@ static void smi_timeout(struct timer_list *t)
 		     * SI_USEC_PER_JIFFY);
 	smi_result = smi_event_handler(smi_info, time_diff);
 
-	if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
+	if (smi_info->si_state == SI_HOSED) {
+		timeout = jiffies + SI_TIMEOUT_HOSED;
+	} else if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
 		/* Running with interrupts, only do long timeouts. */
 		timeout = jiffies + SI_TIMEOUT_JIFFIES;
 		smi_inc_stat(smi_info, long_timeouts);
-- 
cgit v1.2.3


From ff4b6bf7eef4f5b921eed78f2816abcc55bcdd68 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Wed, 28 Jan 2026 20:50:33 +0000
Subject: riscv: dts: microchip: add can resets to mpfs

The can IP on PolarFire SoC requires the use of the blocks reset
during normal operation, and the property is therefore required by the
binding, causing a warning on the m100pfsevp board where it is default
enabled:
mpfs-m100pfsevp.dtb: can@2010c000 (microchip,mpfs-can): 'resets' is a required property
Add the reset to both can nodes.

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 arch/riscv/boot/dts/microchip/mpfs.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi
index 9883ca3554c5..bd658f3a8b1d 100644
--- a/arch/riscv/boot/dts/microchip/mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi
@@ -425,6 +425,7 @@
 			clocks = <&clkcfg CLK_CAN0>, <&clkcfg CLK_MSSPLL3>;
 			interrupt-parent = <&plic>;
 			interrupts = <56>;
+			resets = <&mss_top_sysreg CLK_CAN0>;
 			status = "disabled";
 		};
 
@@ -434,6 +435,7 @@
 			clocks = <&clkcfg CLK_CAN1>, <&clkcfg CLK_MSSPLL3>;
 			interrupt-parent = <&plic>;
 			interrupts = <57>;
+			resets = <&mss_top_sysreg CLK_CAN1>;
 			status = "disabled";
 		};
 
-- 
cgit v1.2.3


From 3c85234b979af71cb9db5eb976ea08a468415767 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sat, 31 Jan 2026 01:13:45 +0800
Subject: cache: starfive: fix device node leak in starlink_cache_init()

of_find_matching_node() returns a device_node with refcount incremented.

Use __free(device_node) attribute to automatically call of_node_put()
when the variable goes out of scope, preventing the refcount leak.

Fixes: cabff60ca77d ("cache: Add StarFive StarLink cache management")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/cache/starfive_starlink_cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cache/starfive_starlink_cache.c b/drivers/cache/starfive_starlink_cache.c
index 24c7d078ca22..3a25d2d7c70c 100644
--- a/drivers/cache/starfive_starlink_cache.c
+++ b/drivers/cache/starfive_starlink_cache.c
@@ -102,11 +102,11 @@ static const struct of_device_id starlink_cache_ids[] = {
 
 static int __init starlink_cache_init(void)
 {
-	struct device_node *np;
 	u32 block_size;
 	int ret;
 
-	np = of_find_matching_node(NULL, starlink_cache_ids);
+	struct device_node *np __free(device_node) =
+		of_find_matching_node(NULL, starlink_cache_ids);
 	if (!of_device_is_available(np))
 		return -ENODEV;
 
-- 
cgit v1.2.3


From 0528a348b04b327a4611e29589beb4c9ae81304a Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sat, 31 Jan 2026 01:49:09 +0800
Subject: cache: ax45mp: Fix device node reference leak in ax45mp_cache_init()

In ax45mp_cache_init(), of_find_matching_node() returns a device node
with an incremented reference count that must be released with
of_node_put(). The current code fails to call of_node_put() which
causes a reference leak.

Use the __free(device_node) attribute to ensure automatic cleanup when
the variable goes out of scope.

Fixes: d34599bcd2e4 ("cache: Add L2 cache management for Andes AX45MP RISC-V core")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/cache/ax45mp_cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cache/ax45mp_cache.c b/drivers/cache/ax45mp_cache.c
index 1d7dd3d2c101..934c5087ec2b 100644
--- a/drivers/cache/ax45mp_cache.c
+++ b/drivers/cache/ax45mp_cache.c
@@ -178,11 +178,11 @@ static const struct of_device_id ax45mp_cache_ids[] = {
 
 static int __init ax45mp_cache_init(void)
 {
-	struct device_node *np;
 	struct resource res;
 	int ret;
 
-	np = of_find_matching_node(NULL, ax45mp_cache_ids);
+	struct device_node *np __free(device_node) =
+		of_find_matching_node(NULL, ax45mp_cache_ids);
 	if (!of_device_is_available(np))
 		return -ENODEV;
 
-- 
cgit v1.2.3


From 4efa91a28576054aae0e6dad9cba8fed8293aef8 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Fri, 30 Jan 2026 19:42:47 +0900
Subject: xfrm: always flush state and policy upon NETDEV_UNREGISTER event

syzbot is reporting that "struct xfrm_state" refcount is leaking.

  unregister_netdevice: waiting for netdevsim0 to become free. Usage count = 2
  ref_tracker: netdev@ffff888052f24618 has 1/1 users at
       __netdev_tracker_alloc include/linux/netdevice.h:4400 [inline]
       netdev_tracker_alloc include/linux/netdevice.h:4412 [inline]
       xfrm_dev_state_add+0x3a5/0x1080 net/xfrm/xfrm_device.c:316
       xfrm_state_construct net/xfrm/xfrm_user.c:986 [inline]
       xfrm_add_sa+0x34ff/0x5fa0 net/xfrm/xfrm_user.c:1022
       xfrm_user_rcv_msg+0x58e/0xc00 net/xfrm/xfrm_user.c:3507
       netlink_rcv_skb+0x158/0x420 net/netlink/af_netlink.c:2550
       xfrm_netlink_rcv+0x71/0x90 net/xfrm/xfrm_user.c:3529
       netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
       netlink_unicast+0x5aa/0x870 net/netlink/af_netlink.c:1344
       netlink_sendmsg+0x8c8/0xdd0 net/netlink/af_netlink.c:1894
       sock_sendmsg_nosec net/socket.c:727 [inline]
       __sock_sendmsg net/socket.c:742 [inline]
       ____sys_sendmsg+0xa5d/0xc30 net/socket.c:2592
       ___sys_sendmsg+0x134/0x1d0 net/socket.c:2646
       __sys_sendmsg+0x16d/0x220 net/socket.c:2678
       do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
       do_syscall_64+0xcd/0xf80 arch/x86/entry/syscall_64.c:94
       entry_SYSCALL_64_after_hwframe+0x77/0x7f

This is because commit d77e38e612a0 ("xfrm: Add an IPsec hardware
offloading API") implemented xfrm_dev_unregister() as no-op despite
xfrm_dev_state_add() from xfrm_state_construct() acquires a reference
to "struct net_device".
I guess that that commit expected that NETDEV_DOWN event is fired before
NETDEV_UNREGISTER event fires, and also assumed that xfrm_dev_state_add()
is called only if (dev->features & NETIF_F_HW_ESP) != 0.

Sabrina Dubroca identified steps to reproduce the same symptoms as below.

  echo 0 > /sys/bus/netdevsim/new_device
  dev=$(ls -1 /sys/bus/netdevsim/devices/netdevsim0/net/)
  ip xfrm state add src 192.168.13.1 dst 192.168.13.2 proto esp \
     spi 0x1000 mode tunnel aead 'rfc4106(gcm(aes))' $key 128   \
     offload crypto dev $dev dir out
  ethtool -K $dev esp-hw-offload off
  echo 0 > /sys/bus/netdevsim/del_device

Like these steps indicate, the NETIF_F_HW_ESP bit can be cleared after
xfrm_dev_state_add() acquired a reference to "struct net_device".
Also, xfrm_dev_state_add() does not check for the NETIF_F_HW_ESP bit
when acquiring a reference to "struct net_device".

Commit 03891f820c21 ("xfrm: handle NETDEV_UNREGISTER for xfrm device")
re-introduced the NETDEV_UNREGISTER event to xfrm_dev_event(), but that
commit for unknown reason chose to share xfrm_dev_down() between the
NETDEV_DOWN event and the NETDEV_UNREGISTER event.
I guess that that commit missed the behavior in the previous paragraph.

Therefore, we need to re-introduce xfrm_dev_unregister() in order to
release the reference to "struct net_device" by unconditionally flushing
state and policy.

Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API")
Cc: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_device.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 52ae0e034d29..550457e4c4f0 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -544,6 +544,14 @@ static int xfrm_dev_down(struct net_device *dev)
 	return NOTIFY_DONE;
 }
 
+static int xfrm_dev_unregister(struct net_device *dev)
+{
+	xfrm_dev_state_flush(dev_net(dev), dev, true);
+	xfrm_dev_policy_flush(dev_net(dev), dev, true);
+
+	return NOTIFY_DONE;
+}
+
 static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
@@ -556,8 +564,10 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 		return xfrm_api_check(dev);
 
 	case NETDEV_DOWN:
-	case NETDEV_UNREGISTER:
 		return xfrm_dev_down(dev);
+
+	case NETDEV_UNREGISTER:
+		return xfrm_dev_unregister(dev);
 	}
 	return NOTIFY_DONE;
 }
-- 
cgit v1.2.3


From fd3634312a04f336dcbfb481060219f0cd320738 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Sat, 7 Feb 2026 14:27:05 +0100
Subject: debugobject: Make it work with deferred page initialization - again

debugobjects uses __GFP_HIGH for allocations as it might be invoked
within locked regions. That worked perfectly fine until v6.18. It still
works correctly when deferred page initialization is disabled and works
by chance when no page allocation is required before deferred page
initialization has completed.

Since v6.18 allocations w/o a reclaim flag cause new_slab() to end up in
alloc_frozen_pages_nolock_noprof(), which returns early when deferred
page initialization has not yet completed. As the deferred page
initialization takes quite a while the debugobject pool is depleted and
debugobjects are disabled.

This can be worked around when PREEMPT_COUNT is enabled as that allows
debugobjects to add __GFP_KSWAPD_RECLAIM to the GFP flags when the context
is preemtible. When PREEMPT_COUNT is disabled the context is unknown and
the reclaim bit can't be set because the caller might hold locks which
might deadlock in the allocator.

In preemptible context the reclaim bit is harmless and not a performance
issue as that's usually invoked from slow path initialization context.

That makes debugobjects depend on PREEMPT_COUNT || !DEFERRED_STRUCT_PAGE_INIT.

Fixes: af92793e52c3 ("slab: Introduce kmalloc_nolock() and kfree_nolock().")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://patch.msgid.link/87pl6gznti.ffs@tglx
---
 lib/Kconfig.debug  |  1 +
 lib/debugobjects.c | 19 ++++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ba36939fda79..a874146ad828 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -723,6 +723,7 @@ source "mm/Kconfig.debug"
 
 config DEBUG_OBJECTS
 	bool "Debug object operations"
+	depends on PREEMPT_COUNT || !DEFERRED_STRUCT_PAGE_INIT
 	depends on DEBUG_KERNEL
 	help
 	  If you say Y here, additional code will be inserted into the
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 89a1d6745dc2..12f50de85b62 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -398,9 +398,26 @@ static void fill_pool(void)
 
 	atomic_inc(&cpus_allocating);
 	while (pool_should_refill(&pool_global)) {
+		gfp_t gfp = __GFP_HIGH | __GFP_NOWARN;
 		HLIST_HEAD(head);
 
-		if (!kmem_alloc_batch(&head, obj_cache, __GFP_HIGH | __GFP_NOWARN))
+		/*
+		 * Allow reclaim only in preemptible context and during
+		 * early boot. If not preemptible, the caller might hold
+		 * locks causing a deadlock in the allocator.
+		 *
+		 * If the reclaim flag is not set during early boot then
+		 * allocations, which happen before deferred page
+		 * initialization has completed, will fail.
+		 *
+		 * In preemptible context the flag is harmless and not a
+		 * performance issue as that's usually invoked from slow
+		 * path initialization context.
+		 */
+		if (preemptible() || system_state < SYSTEM_SCHEDULING)
+			gfp |= __GFP_KSWAPD_RECLAIM;
+
+		if (!kmem_alloc_batch(&head, obj_cache, gfp))
 			break;
 
 		guard(raw_spinlock_irqsave)(&pool_lock);
-- 
cgit v1.2.3


From b777b5e09eabeefc6ba80f4296366a4742701103 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 10 Feb 2026 17:02:25 +0000
Subject: time/jiffies: Inline jiffies_to_msecs() and jiffies_to_usecs()

For common cases (HZ=100, 250 or 1000), these helpers are at most one
multiply, so there is no point calling a tiny function.

Keep them out of line for HZ=300 and others.

This saves cycles in TCP fast path, among other things.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux.new
add/remove: 0/8 grow/shrink: 25/89 up/down: 530/-3474 (-2944)
...
nla_put_msecs                                193       -    -193
message_stats_print                         2131     920   -1211
Total: Before=25365208, After=25362264, chg -0.01%

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260210170226.57209-1-edumazet@google.com
---
 include/linux/jiffies.h | 40 ++++++++++++++++++++++++++++++++++++++--
 kernel/time/time.c      | 19 +++++++------------
 2 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fdef2c155c27..d1c3d4941854 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -434,8 +434,44 @@ extern unsigned long preset_lpj;
 /*
  * Convert various time units to each other:
  */
-extern unsigned int jiffies_to_msecs(const unsigned long j);
-extern unsigned int jiffies_to_usecs(const unsigned long j);
+
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+/**
+ * jiffies_to_msecs - Convert jiffies to milliseconds
+ * @j: jiffies value
+ *
+ * This inline version takes care of HZ in {100,250,1000}.
+ *
+ * Return: milliseconds value
+ */
+static inline unsigned int jiffies_to_msecs(const unsigned long j)
+{
+	return (MSEC_PER_SEC / HZ) * j;
+}
+#else
+unsigned int jiffies_to_msecs(const unsigned long j);
+#endif
+
+#if !(USEC_PER_SEC % HZ)
+/**
+ * jiffies_to_usecs - Convert jiffies to microseconds
+ * @j: jiffies value
+ *
+ * Return: microseconds value
+ */
+static inline unsigned int jiffies_to_usecs(const unsigned long j)
+{
+	/*
+	 * Hz usually doesn't go much further MSEC_PER_SEC.
+	 * jiffies_to_usecs() and usecs_to_jiffies() depend on that.
+	 */
+	BUILD_BUG_ON(HZ > USEC_PER_SEC);
+
+	return (USEC_PER_SEC / HZ) * j;
+}
+#else
+unsigned int jiffies_to_usecs(const unsigned long j);
+#endif
 
 /**
  * jiffies_to_nsecs - Convert jiffies to nanoseconds
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 0ba8e3c50d62..36fd2313ae7e 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -365,20 +365,16 @@ SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp)
 }
 #endif
 
+#if HZ > MSEC_PER_SEC || (MSEC_PER_SEC % HZ)
 /**
  * jiffies_to_msecs - Convert jiffies to milliseconds
  * @j: jiffies value
  *
- * Avoid unnecessary multiplications/divisions in the
- * two most common HZ cases.
- *
  * Return: milliseconds value
  */
 unsigned int jiffies_to_msecs(const unsigned long j)
 {
-#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
-	return (MSEC_PER_SEC / HZ) * j;
-#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
+#if HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
 	return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
 #else
 # if BITS_PER_LONG == 32
@@ -390,7 +386,9 @@ unsigned int jiffies_to_msecs(const unsigned long j)
 #endif
 }
 EXPORT_SYMBOL(jiffies_to_msecs);
+#endif
 
+#if (USEC_PER_SEC % HZ)
 /**
  * jiffies_to_usecs - Convert jiffies to microseconds
  * @j: jiffies value
@@ -405,17 +403,14 @@ unsigned int jiffies_to_usecs(const unsigned long j)
 	 */
 	BUILD_BUG_ON(HZ > USEC_PER_SEC);
 
-#if !(USEC_PER_SEC % HZ)
-	return (USEC_PER_SEC / HZ) * j;
-#else
-# if BITS_PER_LONG == 32
+#if BITS_PER_LONG == 32
 	return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
-# else
+#else
 	return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
-# endif
 #endif
 }
 EXPORT_SYMBOL(jiffies_to_usecs);
+#endif
 
 /**
  * mktime64 - Converts date to seconds.
-- 
cgit v1.2.3


From bbdaa8c17cae18b977f4509911d7a390aa8a6597 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 11 Feb 2026 17:30:28 +0100
Subject: nvme: fix memory leak in quirks_param_set()

When loading the nvme module, if the 'quirks' parameter is specified
via both the kernel command line (e.g., nvme.quirks=...) and the
modprobe command line (e.g., modprobe nvme quirks=...), the
quirks_param_set() callback is invoked twice.

Currently, in the double-invocation scenario, the second call
overwrites the nvme_pci_quirk_list pointer, causing the memory
allocated in the first call to leak.

Fix this by freeing the existing list before assigning the new one.

Fixes: b4247c8317c5 ("nvme: add support for dynamic quirk configuration via module parameter")
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bd884e294600..c0f2104326ab 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -219,6 +219,7 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 		i++;
 	}
 
+	kfree(nvme_pci_quirk_list);
 	nvme_pci_quirk_count = count;
 	nvme_pci_quirk_list  = qlist;
 	goto out_free_val;
-- 
cgit v1.2.3


From 5ee01f1a7343d6a3547b6802ca2d4cdce0edacb1 Mon Sep 17 00:00:00 2001
From: Qingye Zhao <zhaoqingye@honor.com>
Date: Wed, 11 Feb 2026 09:24:04 +0000
Subject: cgroup: fix race between task migration and iteration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a task is migrated out of a css_set, cgroup_migrate_add_task()
first moves it from cset->tasks to cset->mg_tasks via:

    list_move_tail(&task->cg_list, &cset->mg_tasks);

If a css_task_iter currently has it->task_pos pointing to this task,
css_set_move_task() calls css_task_iter_skip() to keep the iterator
valid. However, since the task has already been moved to ->mg_tasks,
the iterator is advanced relative to the mg_tasks list instead of the
original tasks list. As a result, remaining tasks on cset->tasks, as
well as tasks queued on cset->mg_tasks, can be skipped by iteration.

Fix this by calling css_set_skip_task_iters() before unlinking
task->cg_list from cset->tasks. This advances all active iterators to
the next task on cset->tasks, so iteration continues correctly even
when a task is concurrently being migrated.

This race is hard to hit in practice without instrumentation, but it
can be reproduced by artificially slowing down cgroup_procs_show().
For example, on an Android device a temporary
/sys/kernel/cgroup/cgroup_test knob can be added to inject a delay
into cgroup_procs_show(), and then:

  1) Spawn three long-running tasks (PIDs 101, 102, 103).
  2) Create a test cgroup and move the tasks into it.
  3) Enable a large delay via /sys/kernel/cgroup/cgroup_test.
  4) In one shell, read cgroup.procs from the test cgroup.
  5) Within the delay window, in another shell migrate PID 102 by
     writing it to a different cgroup.procs file.

Under this setup, cgroup.procs can intermittently show only PID 101
while skipping PID 103. Once the migration completes, reading the
file again shows all tasks as expected.

Note that this change does not allow removing the existing
css_set_skip_task_iters() call in css_set_move_task(). The new call
in cgroup_migrate_add_task() only handles iterators that are racing
with migration while the task is still on cset->tasks. Iterators may
also start after the task has been moved to cset->mg_tasks. If we
dropped css_set_skip_task_iters() from css_set_move_task(), such
iterators could keep task_pos pointing to a migrating task, causing
css_task_iter_advance() to malfunction on the destination css_set,
up to and including crashes or infinite loops.

The race window between migration and iteration is very small, and
css_task_iter is not on a hot path. In the worst case, when an
iterator is positioned on the first thread of the migrating process,
cgroup_migrate_add_task() may have to skip multiple tasks via
css_set_skip_task_iters(). However, this only happens when migration
and iteration actually race, so the performance impact is negligible
compared to the correctness fix provided here.

Fixes: b636fd38dc40 ("cgroup: Implement css_task_iter_skip()")
Cc: stable@vger.kernel.org # v5.2+
Signed-off-by: Qingye Zhao <zhaoqingye@honor.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cgroup.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 8af4351536cf..49da0874a023 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 
 	mgctx->tset.nr_tasks++;
 
+	css_set_skip_task_iters(cset, task);
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,
-- 
cgit v1.2.3


From 166e31d7dbf6aa44829b98aa446bda5c9580f12a Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 09:26:54 -0800
Subject: nvme-pci: ensure we're polling a polled queue

A user can change the polled queue count at run time. There's a brief
window during a reset where a hipri task may try to poll that queue
before the block layer has updated the queue maps, which would race with
the now interrupt driven queue and may cause double completions.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0f2104326ab..4ee4d7ead5a9 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1627,7 +1627,8 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	struct nvme_queue *nvmeq = hctx->driver_data;
 	bool found;
 
-	if (!nvme_cqe_pending(nvmeq))
+	if (!test_bit(NVMEQ_POLLED, &nvmeq->flags) ||
+	    !nvme_cqe_pending(nvmeq))
 		return 0;
 
 	spin_lock(&nvmeq->cq_poll_lock);
-- 
cgit v1.2.3


From 4735b510a00fb2d4ac9e8d21a8c9552cb281f585 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 11:00:12 -0800
Subject: nvme-pci: cap queue creation to used queues

If the user reduces the special queue count at runtime and resets the
controller, we need to reduce the number of queues and interrupts
requested accordingly rather than start with the pre-allocated queue
count.

Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4ee4d7ead5a9..c63efa49132f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2902,7 +2902,13 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->nr_write_queues = write_queues;
 	dev->nr_poll_queues = poll_queues;
 
-	nr_io_queues = dev->nr_allocated_queues - 1;
+	/*
+	 * The initial number of allocated queue slots may be too large if the
+	 * user reduced the special queue parameters. Cap the value to the
+	 * number we need for this round.
+	 */
+	nr_io_queues = min(nvme_max_io_queues(dev),
+			   dev->nr_allocated_queues - 1);
 	result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
 	if (result < 0)
 		return result;
-- 
cgit v1.2.3


From baa47c4f89eb2e7614e6a06dd5957632e38c4e74 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 10 Feb 2026 10:38:09 -0800
Subject: nvme-pci: do not try to add queue maps at runtime

The block layer allocates the set's maps once. We can't add special
purpose queues at runtime if they weren't allocated at initialization
time.

Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c63efa49132f..0c1a8d7aa1c0 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2902,6 +2902,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	dev->nr_write_queues = write_queues;
 	dev->nr_poll_queues = poll_queues;
 
+	if (dev->ctrl.tagset) {
+		/*
+		 * The set's maps are allocated only once at initialization
+		 * time. We can't add special queues later if their mq_map
+		 * wasn't preallocated.
+		 */
+		if (dev->ctrl.tagset->nr_maps < 3)
+			dev->nr_poll_queues = 0;
+		if (dev->ctrl.tagset->nr_maps < 2)
+			dev->nr_write_queues = 0;
+	}
+
 	/*
 	 * The initial number of allocated queue slots may be too large if the
 	 * user reduced the special queue parameters. Cap the value to the
-- 
cgit v1.2.3


From f66857bafd4f151c5cc6856e47be2e12c1721e43 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:12 +0000
Subject: KVM: arm64: Hide S1POE from guests when not supported by the host

When CONFIG_ARM64_POE is disabled, KVM does not save/restore POR_EL1.
However, ID_AA64MMFR3_EL1 sanitisation currently exposes the feature to
guests whenever the hardware supports it, ignoring the host kernel
configuration.

If a guest detects this feature and attempts to use it, the host will
fail to context-switch POR_EL1, potentially leading to state corruption.

Fix this by masking ID_AA64MMFR3_EL1.S1POE in the sanitised system
registers, preventing KVM from advertising the feature when the host
does not support it (i.e. system_supports_poe() is false).

Fixes: 70ed7238297f ("KVM: arm64: Sanitise ID_AA64MMFR3_EL1")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-2-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/sys_regs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a7cd0badc20c..1b4cacb6e918 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1816,6 +1816,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		       ID_AA64MMFR3_EL1_SCTLRX |
 		       ID_AA64MMFR3_EL1_S1POE |
 		       ID_AA64MMFR3_EL1_S1PIE;
+
+		if (!system_supports_poe())
+			val &= ~ID_AA64MMFR3_EL1_S1POE;
 		break;
 	case SYS_ID_MMFR4_EL1:
 		val &= ~ID_MMFR4_EL1_CCIDX;
-- 
cgit v1.2.3


From 9cb0468d0b335ccf769bd8e161cc96195e82d8b1 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:13 +0000
Subject: KVM: arm64: Optimise away S1POE handling when not supported by host

Although ID register sanitisation prevents guests from seeing the
feature, adding this check to the helper allows the compiler to entirely
eliminate S1POE-specific code paths (such as context switching POR_EL1)
when the host kernel is compiled without support (CONFIG_ARM64_POE is
disabled).

This aligns with the pattern used for other optional features like SVE
(kvm_has_sve()) and FPMR (kvm_has_fpmr()), ensuring no POE logic if the
host lacks support, regardless of the guest configuration state.

Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-3-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5d5a3bbdb95e..2ca264b3db5f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1616,7 +1616,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP))
 
 #define kvm_has_s1poe(k)				\
-	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+	(system_supports_poe() &&			\
+	 kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
 #define kvm_has_ras(k)					\
 	(kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP))
-- 
cgit v1.2.3


From 7e7c2cf0024d89443a7af52e09e47b1fe634ab17 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:14 +0000
Subject: KVM: arm64: Fix ID register initialization for non-protected pKVM
 guests

In protected mode, the hypervisor maintains a separate instance of
the `kvm` structure for each VM. For non-protected VMs, this structure is
initialized from the host's `kvm` state.

Currently, `pkvm_init_features_from_host()` copies the
`KVM_ARCH_FLAG_ID_REGS_INITIALIZED` flag from the host without the
underlying `id_regs` data being initialized. This results in the
hypervisor seeing the flag as set while the ID registers remain zeroed.

Consequently, `kvm_has_feat()` checks at EL2 fail (return 0) for
non-protected VMs. This breaks logic that relies on feature detection,
such as `ctxt_has_tcrx()` for TCR2_EL1 support. As a result, certain
system registers (e.g., TCR2_EL1, PIR_EL1, POR_EL1) are not
saved/restored during the world switch, which could lead to state
corruption.

Fix this by explicitly copying the ID registers from the host `kvm` to
the hypervisor `kvm` for non-protected VMs during initialization, since
we trust the host with its non-protected guests' features. Also ensure
`KVM_ARCH_FLAG_ID_REGS_INITIALIZED` is cleared initially in
`pkvm_init_features_from_host` so that `vm_copy_id_regs` can properly
initialize them and set the flag once done.

Fixes: 41d6028e28bd ("KVM: arm64: Convert the SVE guest vcpu flag to a vm flag")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-4-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/pkvm.c | 35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 8e29d7734a15..f3c1c6955163 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -342,6 +342,7 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 	/* No restrictions for non-protected VMs. */
 	if (!kvm_vm_is_protected(kvm)) {
 		hyp_vm->kvm.arch.flags = host_arch_flags;
+		hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED);
 
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
@@ -471,6 +472,35 @@ err:
 	return ret;
 }
 
+static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
+	const struct kvm *host_kvm = hyp_vm->host_kvm;
+	struct kvm *kvm = &hyp_vm->kvm;
+
+	if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags))
+		return -EINVAL;
+
+	if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))
+		return 0;
+
+	memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs));
+
+	return 0;
+}
+
+static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	int ret = 0;
+
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	else
+		ret = vm_copy_id_regs(hyp_vcpu);
+
+	return ret;
+}
+
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 			      struct pkvm_hyp_vm *hyp_vm,
 			      struct kvm_vcpu *host_vcpu)
@@ -490,8 +520,9 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
 	hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 
-	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
-		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+	ret = pkvm_vcpu_init_sysregs(hyp_vcpu);
+	if (ret)
+		goto done;
 
 	ret = pkvm_vcpu_init_traps(hyp_vcpu);
 	if (ret)
-- 
cgit v1.2.3


From 02471a78a052b631204aed051ab718e4d14ae687 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Fri, 13 Feb 2026 14:38:15 +0000
Subject: KVM: arm64: Remove redundant kern_hyp_va() in unpin_host_sve_state()

The `sve_state` pointer in `hyp_vcpu->vcpu.arch` is initialized as a
hypervisor virtual address during vCPU initialization in
`pkvm_vcpu_init_sve()`.

`unpin_host_sve_state()` calls `kern_hyp_va()` on this address. Since
`kern_hyp_va()` is idempotent, it's not a bug. However, it is
unnecessary and potentially confusing. Remove the redundant conversion.

Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260213143815.1732675-5-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/pkvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index f3c1c6955163..2f029bfe4755 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -392,7 +392,7 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu)
 	if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE))
 		return;
 
-	sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state);
+	sve_state = hyp_vcpu->vcpu.arch.sve_state;
 	hyp_unpin_shared_mem(sve_state,
 			     sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu));
 }
-- 
cgit v1.2.3


From ee5c38a8d31e5dea52299c43c2ec3213351ab6e1 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 6 Feb 2026 14:30:23 -0800
Subject: KVM: arm64: vgic: Handle const qualifier from gic_kvm_info allocation
 type

In preparation for making the kmalloc family of allocators type aware,
we need to make sure that the returned type from the allocation matches
the type of the variable being assigned. (Before, the allocator would
always return "void *", which can be implicitly cast to any pointer type.)

The assigned type is "struct gic_kvm_info", but the returned type,
while matching, is const qualified. To get them exactly matching, just
use the dereferenced pointer for the sizeof().

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20260206223022.it.052-kees@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 86c149537493..a53f93546aa0 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -654,7 +654,7 @@ static struct gic_kvm_info *gic_kvm_info;
 void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
 {
 	BUG_ON(gic_kvm_info != NULL);
-	gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL);
+	gic_kvm_info = kmalloc(sizeof(*gic_kvm_info), GFP_KERNEL);
 	if (gic_kvm_info)
 		*gic_kvm_info = *info;
 }
-- 
cgit v1.2.3


From cb184dd19154fc486fa3d9e02afe70a97e54e055 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Fri, 6 Feb 2026 14:20:28 +0800
Subject: fs: init flags_valid before calling vfs_fileattr_get

syzbot reported a uninit-value bug in [1].

Similar to the "*get" context where the kernel's internal file_kattr
structure is initialized before calling vfs_fileattr_get(), we should
use the same mechanism when using fa.

[1]
BUG: KMSAN: uninit-value in fuse_fileattr_get+0xeb4/0x1450 fs/fuse/ioctl.c:517
 fuse_fileattr_get+0xeb4/0x1450 fs/fuse/ioctl.c:517
 vfs_fileattr_get fs/file_attr.c:94 [inline]
 __do_sys_file_getattr fs/file_attr.c:416 [inline]

Local variable fa.i created at:
 __do_sys_file_getattr fs/file_attr.c:380 [inline]
 __se_sys_file_getattr+0x8c/0xbd0 fs/file_attr.c:372

Reported-by: syzbot+7c31755f2cea07838b0c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7c31755f2cea07838b0c
Tested-by: syzbot+7c31755f2cea07838b0c@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Link: https://patch.msgid.link/tencent_B6C4583771D76766D71362A368696EC3B605@qq.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/file_attr.c b/fs/file_attr.c
index 42721427245a..0e9b4f737546 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -376,7 +376,7 @@ SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
 	struct path filepath __free(path_put) = {};
 	unsigned int lookup_flags = 0;
 	struct file_attr fattr;
-	struct file_kattr fa;
+	struct file_kattr fa = { .flags_valid = true }; /* hint only */
 	int error;
 
 	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);
-- 
cgit v1.2.3


From 9eed043d10f17301c1b5141e16bb98a85a8fd07e Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 3 Feb 2026 17:40:14 +0800
Subject: writeback: Fix wakeup and logging timeouts for !DETECT_HUNG_TASK

Recent changes of fs-writeback cause such warnings if DETECT_HUNG_TASK
is not enabled:

INFO: The task sync:1342 has been waiting for writeback completion for more than 1 seconds.

The reason is sysctl_hung_task_timeout_secs is 0 when DETECT_HUNG_TASK
is not enabled, then it causes the warning message even if the writeback
lasts for only one second.

Guard the wakeup and logging with "#ifdef CONFIG_DETECT_HUNG_TASK" can
eliminate the warning messages. But on the other hand, it is possible
that sysctl_hung_task_timeout_secs be also 0 when DETECT_HUNG_TASK is
enabled. So let's just check the value of sysctl_hung_task_timeout_secs
to decide whether do wakeup and logging.

Fixes: 1888635532fb ("writeback: Wake up waiting tasks when finishing the writeback of a chunk.")
Fixes: d6e621590764 ("writeback: Add logging for slow writeback (exceeds sysctl_hung_task_timeout_secs)")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://patch.msgid.link/20260203094014.2273240-1-chenhuacai@loongson.cn
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs-writeback.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 68228bf89b82..eb1ca86bf30a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -198,10 +198,11 @@ static void wb_queue_work(struct bdi_writeback *wb,
 
 static bool wb_wait_for_completion_cb(struct wb_completion *done)
 {
+	unsigned long timeout = sysctl_hung_task_timeout_secs;
 	unsigned long waited_secs = (jiffies - done->wait_start) / HZ;
 
 	done->progress_stamp = jiffies;
-	if (waited_secs > sysctl_hung_task_timeout_secs)
+	if (timeout && (waited_secs > timeout))
 		pr_info("INFO: The task %s:%d has been waiting for writeback "
 			"completion for more than %lu seconds.",
 			current->comm, current->pid, waited_secs);
@@ -1955,6 +1956,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 		.range_end		= LLONG_MAX,
 	};
 	unsigned long start_time = jiffies;
+	unsigned long timeout = sysctl_hung_task_timeout_secs;
 	long write_chunk;
 	long total_wrote = 0;  /* count both pages and inodes */
 	unsigned long dirtied_before = jiffies;
@@ -2041,9 +2043,8 @@ static long writeback_sb_inodes(struct super_block *sb,
 		__writeback_single_inode(inode, &wbc);
 
 		/* Report progress to inform the hung task detector of the progress. */
-		if (work->done && work->done->progress_stamp &&
-		   (jiffies - work->done->progress_stamp) > HZ *
-		   sysctl_hung_task_timeout_secs / 2)
+		if (work->done && work->done->progress_stamp && timeout &&
+		   (jiffies - work->done->progress_stamp) > HZ * timeout / 2)
 			wake_up_all(work->done->waitq);
 
 		wbc_detach_inode(&wbc);
-- 
cgit v1.2.3


From 81f16c9778d730f573d0d565706bb7227e2405f4 Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Fri, 13 Feb 2026 18:30:06 +0800
Subject: statmount: Fix the null-ptr-deref in do_statmount()

If the mount is internal, it's mnt_ns will be MNT_NS_INTERNAL, which is
defined as ERR_PTR(-EINVAL). So, in the do_statmount(), need to check ns
of mount by IS_ERR() and return.

Fixes: 0e5032237ee5 ("statmount: accept fd as a parameter")
Reported-by: syzbot+9e03a9535ea65f687a44@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698e287a.a70a0220.2c38d7.009e.GAE@google.com/
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Link: https://patch.msgid.link/20260213103006.2472569-1-wangqing7171@gmail.com
Reviewed-by: Bhavik Sachdev <b.sachdev1904@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/namespace.c b/fs/namespace.c
index a67cbe42746d..90700df65f0d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5678,6 +5678,8 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 
 		s->mnt = mnt_file->f_path.mnt;
 		ns = real_mount(s->mnt)->mnt_ns;
+		if (IS_ERR(ns))
+			return PTR_ERR(ns);
 		if (!ns)
 			/*
 			 * We can't set mount point and mnt_ns_id since we don't have a
-- 
cgit v1.2.3


From ac83896172798cf82ebc643cf555aa4cdd3a07da Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Fri, 13 Feb 2026 02:28:12 +0000
Subject: iomap: Describe @private in iomap_readahead()

The kernel test rebot reports the kernel-doc warning:

```
Warning: fs/iomap/buffered-io.c:624 function parameter 'private'
 not described in 'iomap_readahead'
```

The former commit in "iomap: stash iomap read ctx in the private
field of iomap_iter" has added a new parameter @private to
iomap_readahead(), so let's describe the parameter.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601261111.vIL9rhgD-lkp@intel.com/
Fixes: 8806f279244b ("iomap: stash iomap read ctx in the private field of iomap_iter")
Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20260213022812.766187-1-lihongbo22@huawei.com
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1fe19b4ee2f4..58887513b894 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -625,6 +625,7 @@ static int iomap_readahead_iter(struct iomap_iter *iter,
  * iomap_readahead - Attempt to read pages from a file.
  * @ops: The operations vector for the filesystem.
  * @ctx: The ctx used for issuing readahead.
+ * @private: The filesystem-specific information for issuing iomap_iter.
  *
  * This function is for filesystems to call to implement their readahead
  * address_space operation.
-- 
cgit v1.2.3


From 1cb968a2013ffa8112d52ebe605009ea1c6a582c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Sat, 24 Jan 2026 04:18:40 +0000
Subject: nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit().

syzbot reported memory leak of struct cred. [0]

nfsd_nl_threads_set_doit() passes get_current_cred() to
nfsd_svc(), but put_cred() is not called after that.

The cred is finally passed down to _svc_xprt_create(),
which calls get_cred() with the cred for struct svc_xprt.

The ownership of the refcount by get_current_cred() is not
transferred to anywhere and is just leaked.

nfsd_svc() is also called from write_threads(), but it does
not bump file->f_cred there.

nfsd_nl_threads_set_doit() is called from sendmsg() and
current->cred does not go away.

Let's use current_cred() in nfsd_nl_threads_set_doit().

[0]:
BUG: memory leak
unreferenced object 0xffff888108b89480 (size 184):
  comm "syz-executor", pid 5994, jiffies 4294943386
  hex dump (first 32 bytes):
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 369454a7):
    kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline]
    slab_post_alloc_hook mm/slub.c:4958 [inline]
    slab_alloc_node mm/slub.c:5263 [inline]
    kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270
    prepare_creds+0x22/0x600 kernel/cred.c:185
    copy_creds+0x44/0x290 kernel/cred.c:286
    copy_process+0x7a7/0x2870 kernel/fork.c:2086
    kernel_clone+0xac/0x6e0 kernel/fork.c:2651
    __do_sys_clone+0x7f/0xb0 kernel/fork.c:2792
    do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
    do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94
    entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 924f4fb003ba ("NFSD: convert write_threads to netlink command")
Cc: stable@vger.kernel.org
Reported-by: syzbot+dd3b43aa0204089217ee@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69744674.a00a0220.33ccc7.0000.GAE@google.com/
Tested-by: syzbot+dd3b43aa0204089217ee@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 89fe2c0e8d44..43ced6b0e197 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1647,7 +1647,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 	if (attr)
 		nn->min_threads = nla_get_u32(attr);
 
-	ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope);
+	ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope);
 	if (ret > 0)
 		ret = 0;
 out_unlock:
-- 
cgit v1.2.3


From 92978c83bb4eef55d02a6c990c01c423131eefa7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Sat, 24 Jan 2026 04:18:41 +0000
Subject: nfsd: Fix cred ref leak in nfsd_nl_listener_set_doit().

nfsd_nl_listener_set_doit() uses get_current_cred() without
put_cred().

As we can see from other callers, svc_xprt_create_from_sa()
does not require the extra refcount.

nfsd_nl_listener_set_doit() is always in the process context,
sendmsg(), and current->cred does not go away.

Let's use current_cred() in nfsd_nl_listener_set_doit().

Fixes: 16a471177496 ("NFSD: add listener-{set,get} netlink command")
Cc: stable@vger.kernel.org
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 43ced6b0e197..b06adb5d5a2e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2000,7 +2000,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
-					      get_current_cred());
+					      current_cred());
 		/* always save the latest error */
 		if (ret < 0)
 			err = ret;
-- 
cgit v1.2.3


From 1072020685f4b81f6efad3b412cdae0bd62bb043 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 12 Feb 2026 12:41:25 +0100
Subject: irqchip/sifive-plic: Fix frozen interrupt due to affinity setting

PLIC ignores interrupt completion message for disabled interrupt, explained
by the specification:

    The PLIC signals it has completed executing an interrupt handler by
    writing the interrupt ID it received from the claim to the
    claim/complete register. The PLIC does not check whether the completion
    ID is the same as the last claim ID for that target. If the completion
    ID does not match an interrupt source that is currently enabled for
    the target, the completion is silently ignored.

This caused problems in the past, because an interrupt can be disabled
while still being handled and plic_irq_eoi() had no effect. That was fixed
by checking if the interrupt is disabled, and if so enable it, before
sending the completion message. That check is done with irqd_irq_disabled().

However, that is not sufficient because the enable bit for the handling
hart can be zero despite irqd_irq_disabled(d) being false. This can happen
when affinity setting is changed while a hart is still handling the
interrupt.

This problem is easily reproducible by dumping a large file to uart (which
generates lots of interrupts) and at the same time keep changing the uart
interrupt's affinity setting. The uart port becomes frozen almost
instantaneously.

Fix this by checking PLIC's enable bit instead of irqd_irq_disabled().

Fixes: cc9f04f9a84f ("irqchip/sifive-plic: Implement irq_set_affinity() for SMP host")
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260212114125.3148067-1-namcao@linutronix.de
---
 drivers/irqchip/irq-sifive-plic.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index 60fd8f91762b..70058871d2fb 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -172,8 +172,13 @@ static void plic_irq_disable(struct irq_data *d)
 static void plic_irq_eoi(struct irq_data *d)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+	u32 __iomem *reg;
+	bool enabled;
+
+	reg = handler->enable_base + (d->hwirq / 32) * sizeof(u32);
+	enabled = readl(reg) & BIT(d->hwirq % 32);
 
-	if (unlikely(irqd_irq_disabled(d))) {
+	if (unlikely(!enabled)) {
 		plic_toggle(handler, d->hwirq, 1);
 		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
 		plic_toggle(handler, d->hwirq, 0);
-- 
cgit v1.2.3


From ce9e40a9a5e5cff0b1b0d2fa582b3d71a8ce68e8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 6 Feb 2026 15:48:16 +0000
Subject: irqchip/gic-v3-its: Limit number of per-device MSIs to the range the
 ITS supports

The ITS driver blindly assumes that EventIDs are in abundant supply, to the
point where it never checks how many the hardware actually supports.

It turns out that some pretty esoteric integrations make it so that only a
few bits are available, all the way down to a single bit.

Enforce the advertised limitation at the point of allocating the device
structure, and hope that the endpoint driver can deal with such limitation.

Fixes: 84a6a2e7fc18d ("irqchip: GICv3: ITS: device allocation and configuration")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Zenghui Yu <zenghui.yu@linux.dev>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260206154816.3582887-1-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c   | 4 ++++
 include/linux/irqchip/arm-gic-v3.h | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2988def30972..a51e8e6a8181 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3475,6 +3475,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	int lpi_base;
 	int nr_lpis;
 	int nr_ites;
+	int id_bits;
 	int sz;
 
 	if (!its_alloc_device_table(its, dev_id))
@@ -3486,7 +3487,10 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	/*
 	 * Even if the device wants a single LPI, the ITT must be
 	 * sized as a power of two (and you need at least one bit...).
+	 * Also honor the ITS's own EID limit.
 	 */
+	id_bits = FIELD_GET(GITS_TYPER_IDBITS, its->typer) + 1;
+	nvecs = min_t(unsigned int, nvecs, BIT(id_bits));
 	nr_ites = max(2, nvecs);
 	sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
 	sz = max(sz, ITS_ITT_ALIGN);
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 70c0948f978e..0225121f3013 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -394,6 +394,7 @@
 #define GITS_TYPER_VLPIS		(1UL << 1)
 #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT	4
 #define GITS_TYPER_ITT_ENTRY_SIZE	GENMASK_ULL(7, 4)
+#define GITS_TYPER_IDBITS		GENMASK_ULL(12, 8)
 #define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS		GENMASK_ULL(17, 13)
-- 
cgit v1.2.3


From f0617176be5e497b67b3c87bac35b26ebccac499 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 12:04:50 +0100
Subject: irqchip/mmp: Make icu_irq_chip variable static const

File-scope 'icu_irq_chip' is not used outside of this unit and is not
modified anywhere, so make it static const to silence sparse warning:

  irq-mmp.c:139:17: warning: symbol 'icu_irq_chip' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260216110449.160277-2-krzysztof.kozlowski@oss.qualcomm.com
---
 drivers/irqchip/irq-mmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 09e640430208..8e210cb451be 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -136,7 +136,7 @@ static void icu_unmask_irq(struct irq_data *d)
 	}
 }
 
-struct irq_chip icu_irq_chip = {
+static const struct irq_chip icu_irq_chip = {
 	.name		= "icu_irq",
 	.irq_mask	= icu_mask_irq,
 	.irq_mask_ack	= icu_mask_ack_irq,
-- 
cgit v1.2.3


From bffda93a51b40afd67c11bf558dc5aae83ca0943 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Thu, 12 Feb 2026 11:23:27 -0800
Subject: scsi: lpfc: Properly set WC for DPP mapping

Using set_memory_wc() to enable write-combining for the DPP portion of
the MMIO mapping is wrong as set_memory_*() is meant to operate on RAM
only, not MMIO mappings. In fact, as used currently triggers a BUG_ON()
with enabled CONFIG_DEBUG_VIRTUAL.

Simply map the DPP region separately and in addition to the already
existing mappings, avoiding any possible negative side effects for
these.

Fixes: 1351e69fc6db ("scsi: lpfc: Add push-to-adapter support to sli4")
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Reviewed-by: Mathias Krause <minipli@grsecurity.net>
Link: https://patch.msgid.link/20260212192327.141104-1-justintee8345@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_init.c |  2 ++
 drivers/scsi/lpfc/lpfc_sli.c  | 36 ++++++++++++++++++++++++++++++------
 drivers/scsi/lpfc/lpfc_sli4.h |  3 +++
 3 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index a116a16c4a6f..b5e53c7d33e7 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -12039,6 +12039,8 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba)
 		iounmap(phba->sli4_hba.conf_regs_memmap_p);
 		if (phba->sli4_hba.dpp_regs_memmap_p)
 			iounmap(phba->sli4_hba.dpp_regs_memmap_p);
+		if (phba->sli4_hba.dpp_regs_memmap_wc_p)
+			iounmap(phba->sli4_hba.dpp_regs_memmap_wc_p);
 		break;
 	case LPFC_SLI_INTF_IF_TYPE_1:
 		break;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 734af3d039f8..690763e0aa55 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -15981,6 +15981,32 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset)
 	return NULL;
 }
 
+static __maybe_unused void __iomem *
+lpfc_dpp_wc_map(struct lpfc_hba *phba, uint8_t dpp_barset)
+{
+
+	/* DPP region is supposed to cover 64-bit BAR2 */
+	if (dpp_barset != WQ_PCI_BAR_4_AND_5) {
+		lpfc_log_msg(phba, KERN_WARNING, LOG_INIT,
+			     "3273 dpp_barset x%x != WQ_PCI_BAR_4_AND_5\n",
+			     dpp_barset);
+		return NULL;
+	}
+
+	if (!phba->sli4_hba.dpp_regs_memmap_wc_p) {
+		void __iomem *dpp_map;
+
+		dpp_map = ioremap_wc(phba->pci_bar2_map,
+				     pci_resource_len(phba->pcidev,
+						      PCI_64BIT_BAR4));
+
+		if (dpp_map)
+			phba->sli4_hba.dpp_regs_memmap_wc_p = dpp_map;
+	}
+
+	return phba->sli4_hba.dpp_regs_memmap_wc_p;
+}
+
 /**
  * lpfc_modify_hba_eq_delay - Modify Delay Multiplier on EQs
  * @phba: HBA structure that EQs are on.
@@ -16944,9 +16970,6 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 	uint8_t dpp_barset;
 	uint32_t dpp_offset;
 	uint8_t wq_create_version;
-#ifdef CONFIG_X86
-	unsigned long pg_addr;
-#endif
 
 	/* sanity check on queue memory */
 	if (!wq || !cq)
@@ -17132,14 +17155,15 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
 
 #ifdef CONFIG_X86
 			/* Enable combined writes for DPP aperture */
-			pg_addr = (unsigned long)(wq->dpp_regaddr) & PAGE_MASK;
-			rc = set_memory_wc(pg_addr, 1);
-			if (rc) {
+			bar_memmap_p = lpfc_dpp_wc_map(phba, dpp_barset);
+			if (!bar_memmap_p) {
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 					"3272 Cannot setup Combined "
 					"Write on WQ[%d] - disable DPP\n",
 					wq->queue_id);
 				phba->cfg_enable_dpp = 0;
+			} else {
+				wq->dpp_regaddr = bar_memmap_p + dpp_offset;
 			}
 #else
 			phba->cfg_enable_dpp = 0;
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index ee58383492b2..b6d90604bb61 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -785,6 +785,9 @@ struct lpfc_sli4_hba {
 	void __iomem *dpp_regs_memmap_p;  /* Kernel memory mapped address for
 					   * dpp registers
 					   */
+	void __iomem *dpp_regs_memmap_wc_p;/* Kernel memory mapped address for
+					    * dpp registers with write combining
+					    */
 	union {
 		struct {
 			/* IF Type 0, BAR 0 PCI cfg space reg mem map */
-- 
cgit v1.2.3


From 57297736c08233987e5d29ce6584c6ca2a831b12 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Thu, 29 Jan 2026 15:30:39 +0100
Subject: scsi: storvsc: Fix scheduling while atomic on PREEMPT_RT

This resolves the follow splat and lock-up when running with PREEMPT_RT
enabled on Hyper-V:

[  415.140818] BUG: scheduling while atomic: stress-ng-iomix/1048/0x00000002
[  415.140822] INFO: lockdep is turned off.
[  415.140823] Modules linked in: intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_discovery pmt_class intel_pmc_ssram_telemetry intel_vsec ghash_clmulni_intel aesni_intel rapl binfmt_misc nls_ascii nls_cp437 vfat fat snd_pcm hyperv_drm snd_timer drm_client_lib drm_shmem_helper snd sg soundcore drm_kms_helper pcspkr hv_balloon hv_utils evdev joydev drm configfs efi_pstore nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vsock vmw_vmci efivarfs autofs4 ext4 crc16 mbcache jbd2 sr_mod sd_mod cdrom hv_storvsc serio_raw hid_generic scsi_transport_fc hid_hyperv scsi_mod hid hv_netvsc hyperv_keyboard scsi_common
[  415.140846] Preemption disabled at:
[  415.140847] [<ffffffffc0656171>] storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[  415.140854] CPU: 8 UID: 0 PID: 1048 Comm: stress-ng-iomix Not tainted 6.19.0-rc7 #30 PREEMPT_{RT,(full)}
[  415.140856] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/04/2024
[  415.140857] Call Trace:
[  415.140861]  <TASK>
[  415.140861]  ? storvsc_queuecommand+0x2e1/0xbe0 [hv_storvsc]
[  415.140863]  dump_stack_lvl+0x91/0xb0
[  415.140870]  __schedule_bug+0x9c/0xc0
[  415.140875]  __schedule+0xdf6/0x1300
[  415.140877]  ? rtlock_slowlock_locked+0x56c/0x1980
[  415.140879]  ? rcu_is_watching+0x12/0x60
[  415.140883]  schedule_rtlock+0x21/0x40
[  415.140885]  rtlock_slowlock_locked+0x502/0x1980
[  415.140891]  rt_spin_lock+0x89/0x1e0
[  415.140893]  hv_ringbuffer_write+0x87/0x2a0
[  415.140899]  vmbus_sendpacket_mpb_desc+0xb6/0xe0
[  415.140900]  ? rcu_is_watching+0x12/0x60
[  415.140902]  storvsc_queuecommand+0x669/0xbe0 [hv_storvsc]
[  415.140904]  ? HARDIRQ_verbose+0x10/0x10
[  415.140908]  ? __rq_qos_issue+0x28/0x40
[  415.140911]  scsi_queue_rq+0x760/0xd80 [scsi_mod]
[  415.140926]  __blk_mq_issue_directly+0x4a/0xc0
[  415.140928]  blk_mq_issue_direct+0x87/0x2b0
[  415.140931]  blk_mq_dispatch_queue_requests+0x120/0x440
[  415.140933]  blk_mq_flush_plug_list+0x7a/0x1a0
[  415.140935]  __blk_flush_plug+0xf4/0x150
[  415.140940]  __submit_bio+0x2b2/0x5c0
[  415.140944]  ? submit_bio_noacct_nocheck+0x272/0x360
[  415.140946]  submit_bio_noacct_nocheck+0x272/0x360
[  415.140951]  ext4_read_bh_lock+0x3e/0x60 [ext4]
[  415.140995]  ext4_block_write_begin+0x396/0x650 [ext4]
[  415.141018]  ? __pfx_ext4_da_get_block_prep+0x10/0x10 [ext4]
[  415.141038]  ext4_da_write_begin+0x1c4/0x350 [ext4]
[  415.141060]  generic_perform_write+0x14e/0x2c0
[  415.141065]  ext4_buffered_write_iter+0x6b/0x120 [ext4]
[  415.141083]  vfs_write+0x2ca/0x570
[  415.141087]  ksys_write+0x76/0xf0
[  415.141089]  do_syscall_64+0x99/0x1490
[  415.141093]  ? rcu_is_watching+0x12/0x60
[  415.141095]  ? finish_task_switch.isra.0+0xdf/0x3d0
[  415.141097]  ? rcu_is_watching+0x12/0x60
[  415.141098]  ? lock_release+0x1f0/0x2a0
[  415.141100]  ? rcu_is_watching+0x12/0x60
[  415.141101]  ? finish_task_switch.isra.0+0xe4/0x3d0
[  415.141103]  ? rcu_is_watching+0x12/0x60
[  415.141104]  ? __schedule+0xb34/0x1300
[  415.141106]  ? hrtimer_try_to_cancel+0x1d/0x170
[  415.141109]  ? do_nanosleep+0x8b/0x160
[  415.141111]  ? hrtimer_nanosleep+0x89/0x100
[  415.141114]  ? __pfx_hrtimer_wakeup+0x10/0x10
[  415.141116]  ? xfd_validate_state+0x26/0x90
[  415.141118]  ? rcu_is_watching+0x12/0x60
[  415.141120]  ? do_syscall_64+0x1e0/0x1490
[  415.141121]  ? do_syscall_64+0x1e0/0x1490
[  415.141123]  ? rcu_is_watching+0x12/0x60
[  415.141124]  ? do_syscall_64+0x1e0/0x1490
[  415.141125]  ? do_syscall_64+0x1e0/0x1490
[  415.141127]  ? irqentry_exit+0x140/0x7e0
[  415.141129]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

get_cpu() disables preemption while the spinlock hv_ringbuffer_write is
using is converted to an rt-mutex under PREEMPT_RT.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-by: Florian Bezdeka <florian.bezdeka@siemens.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://patch.msgid.link/0c7fb5cd-fb21-4760-8593-e04bade84744@siemens.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/storvsc_drv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 19e18939d3a5..19ff0004e259 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1855,8 +1855,9 @@ static enum scsi_qc_status storvsc_queuecommand(struct Scsi_Host *host,
 	cmd_request->payload_sz = payload_sz;
 
 	/* Invokes the vsc to start an IO */
-	ret = storvsc_do_io(dev, cmd_request, get_cpu());
-	put_cpu();
+	migrate_disable();
+	ret = storvsc_do_io(dev, cmd_request, smp_processor_id());
+	migrate_enable();
 
 	if (ret)
 		scsi_dma_unmap(scmnd);
-- 
cgit v1.2.3


From 2e6b5cd6a4b37a95b78cf8c39a979b58c915c8ed Mon Sep 17 00:00:00 2001
From: Alexey Charkov <alchark@flipper.net>
Date: Mon, 9 Feb 2026 19:17:34 +0400
Subject: scsi: ufs: core: Fix RPMB region size detection for UFS 2.2

Older UFS spec devices (2.2 and earlier) do not expose per-region RPMB
sizes, as only one RPMB region is supported. In such cases, the size of the
single RPMB region can be deduced from the Logical Block Count and Logical
Block Size fields in the RPMB Unit Descriptor.

Add a fallback mechanism to calculate the RPMB region size from these
fields if the device implements an older spec, so that the RPMB driver can
work with such devices - otherwise it silently skips the whole RPMB.

        Section 14.1.4.6 (RPMB Unit Descriptor)

Link: https://www.jedec.org/system/files/docs/JESD220C-2_2.pdf
Cc: stable@vger.kernel.org
Fixes: b06b8c421485 ("scsi: ufs: core: Add OP-TEE based RPMB driver for UFS devices")
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Alexey Charkov <alchark@flipper.net>
Link: https://patch.msgid.link/20260209-ufs-rpmb-v3-1-b1804e71bd38@flipper.net
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8349fe2090db..12f1bdc70587 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -23,6 +23,7 @@
 #include <linux/pm_opp.h>
 #include <linux/regulator/consumer.h>
 #include <linux/sched/clock.h>
+#include <linux/sizes.h>
 #include <linux/iopoll.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_dbg.h>
@@ -5248,6 +5249,25 @@ static void ufshcd_lu_init(struct ufs_hba *hba, struct scsi_device *sdev)
 		hba->dev_info.rpmb_region_size[1] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION1_SIZE];
 		hba->dev_info.rpmb_region_size[2] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION2_SIZE];
 		hba->dev_info.rpmb_region_size[3] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION3_SIZE];
+
+		if (hba->dev_info.wspecversion <= 0x0220) {
+			/*
+			 * These older spec chips have only one RPMB region,
+			 * sized between 128 kB minimum and 16 MB maximum.
+			 * No per region size fields are provided (respective
+			 * REGIONX_SIZE fields always contain zeros), so get
+			 * it from the logical block count and size fields for
+			 * compatibility
+			 *
+			 * (See JESD220C-2_2 Section 14.1.4.6
+			 * RPMB Unit Descriptor,* offset 13h, 4 bytes)
+			 */
+			hba->dev_info.rpmb_region_size[0] =
+				(get_unaligned_be64(desc_buf
+					+ RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_COUNT)
+				<< desc_buf[RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_SIZE])
+				/ SZ_128K;
+		}
 	}
 
 
-- 
cgit v1.2.3


From 70ca8caa96ce473647054f5c7b9dab5423902402 Mon Sep 17 00:00:00 2001
From: Tomas Henzl <thenzl@redhat.com>
Date: Tue, 10 Feb 2026 20:18:50 +0100
Subject: scsi: ses: Fix devices attaching to different hosts

On a multipath SAS system some devices don't end up with correct symlinks
from the SCSI device to its enclosure. Some devices even have enclosure
links pointing to enclosures attached to different SCSI hosts.

ses_match_to_enclosure() calls enclosure_for_each_device() which iterates
over all enclosures on the system, not just enclosures attached to the
current SCSI host.

Replace the iteration with a direct call to ses_enclosure_find_by_addr().

Reviewed-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Tomas Henzl <thenzl@redhat.com>
Link: https://patch.msgid.link/20260210191850.36784-1-thenzl@redhat.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ses.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 789b170da652..98a7367d2f20 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -528,9 +528,8 @@ struct efd {
 };
 
 static int ses_enclosure_find_by_addr(struct enclosure_device *edev,
-				      void *data)
+				      struct efd *efd)
 {
-	struct efd *efd = data;
 	int i;
 	struct ses_component *scomp;
 
@@ -683,7 +682,7 @@ static void ses_match_to_enclosure(struct enclosure_device *edev,
 	if (efd.addr) {
 		efd.dev = &sdev->sdev_gendev;
 
-		enclosure_for_each_device(ses_enclosure_find_by_addr, &efd);
+		ses_enclosure_find_by_addr(edev, &efd);
 	}
 }
 
-- 
cgit v1.2.3


From 5b313760059c9df7d60aba7832279bcb81b4aec0 Mon Sep 17 00:00:00 2001
From: Won Jung <wone.jung@samsung.com>
Date: Wed, 11 Feb 2026 15:01:05 +0900
Subject: scsi: ufs: core: Reset urgent_bkops_lvl to allow runtime PM power
 mode

Ensures that UFS Runtime PM can achieve power saving after System PM
suspend by resetting hba->urgent_bkops_lvl. Also modify the
ufshcd_bkops_exception_event_handler to avoid setting urgent_bkops_lvl when
status is 0, which helps maintain optimal power management.

On UFS devices supporting UFSHCD_CAP_AUTO_BKOPS_SUSPEND, a BKOPS exception
event can lead to a situation where UFS Runtime PM can't enter low-power
mode states even after the BKOPS exception has been resolved.

BKOPS exception with bkops status 0 occurs, the driver logs:

 "ufshcd_bkops_exception_event_handler: device raised urgent BKOPS exception for bkops status 0"

When a BKOPS exception occurs, ufshcd_bkops_exception_event_handler() reads
the BKOPS status and sets hba->urgent_bkops_lvl to BKOPS_STATUS_NO_OP(0).
This allows the device to perform Runtime PM without changing the UFS power
mode.  (__ufshcd_wl_suspend(hba, UFS_RUNTIME_PM))

During system PM suspend, ufshcd_disable_auto_bkops() is called, disabling
auto bkops. After UFS System PM Resume, when runtime PM attempts to suspend
again, ufshcd_urgent_bkops() is invoked. Since hba->urgent_bkops_lvl
remains at BKOPS_STATUS_NO_OP(0), ufshcd_enable_auto_bkops() is triggered.

However, in ufshcd_bkops_ctrl(), the driver compares the current BKOPS
status with hba->urgent_bkops_lvl, and only enables auto bkops if
curr_status >= hba->urgent_bkops_lvl.  Since both values are 0, the
condition is met

As a result, __ufshcd_wl_suspend(hba, UFS_RUNTIME_PM) skips power mode
transitions and remains in an active state, preventing power saving even
though no urgent BKOPS condition exists.

Signed-off-by: Won Jung <wone.jung@samsung.com>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Link: https://patch.msgid.link/1891546521.01770806581968.JavaMail.epsvc@epcpadp2new
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 12f1bdc70587..3bbc2b51c87b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5982,6 +5982,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 
 	hba->auto_bkops_enabled = false;
 	trace_ufshcd_auto_bkops_state(hba, "Disabled");
+	hba->urgent_bkops_lvl = BKOPS_STATUS_PERF_IMPACT;
 	hba->is_urgent_bkops_lvl_checked = false;
 out:
 	return err;
@@ -6085,7 +6086,7 @@ static void ufshcd_bkops_exception_event_handler(struct ufs_hba *hba)
 	 * impacted or critical. Handle these device by determining their urgent
 	 * bkops status at runtime.
 	 */
-	if (curr_status < BKOPS_STATUS_PERF_IMPACT) {
+	if ((curr_status > BKOPS_STATUS_NO_OP) && (curr_status < BKOPS_STATUS_PERF_IMPACT)) {
 		dev_err(hba->dev, "%s: device raised urgent BKOPS exception for bkops status %d\n",
 				__func__, curr_status);
 		/* update the current status as the urgent bkops level */
-- 
cgit v1.2.3


From fa96392ebebc8fade2b878acb14cce0f71016503 Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Thu, 12 Feb 2026 12:30:26 +0530
Subject: scsi: mpi3mr: Add NULL checks when resetting request and reply queues

The driver encountered a crash during resource cleanup when the reply and
request queues were NULL due to freed memory.  This issue occurred when the
creation of reply or request queues failed, and the driver freed the memory
first, but attempted to mem set the content of the freed memory, leading to
a system crash.

Add NULL pointer checks for reply and request queues before accessing the
reply/request memory during cleanup

Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://patch.msgid.link/20260212070026.30263-1-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr_fw.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 1cfbdb773353..04d4a2aea7d7 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -4806,21 +4806,25 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc)
 	}
 
 	for (i = 0; i < mrioc->num_queues; i++) {
-		mrioc->op_reply_qinfo[i].qid = 0;
-		mrioc->op_reply_qinfo[i].ci = 0;
-		mrioc->op_reply_qinfo[i].num_replies = 0;
-		mrioc->op_reply_qinfo[i].ephase = 0;
-		atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0);
-		atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0);
-		mpi3mr_memset_op_reply_q_buffers(mrioc, i);
-
-		mrioc->req_qinfo[i].ci = 0;
-		mrioc->req_qinfo[i].pi = 0;
-		mrioc->req_qinfo[i].num_requests = 0;
-		mrioc->req_qinfo[i].qid = 0;
-		mrioc->req_qinfo[i].reply_qid = 0;
-		spin_lock_init(&mrioc->req_qinfo[i].q_lock);
-		mpi3mr_memset_op_req_q_buffers(mrioc, i);
+		if (mrioc->op_reply_qinfo) {
+			mrioc->op_reply_qinfo[i].qid = 0;
+			mrioc->op_reply_qinfo[i].ci = 0;
+			mrioc->op_reply_qinfo[i].num_replies = 0;
+			mrioc->op_reply_qinfo[i].ephase = 0;
+			atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0);
+			atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0);
+			mpi3mr_memset_op_reply_q_buffers(mrioc, i);
+		}
+
+		if (mrioc->req_qinfo) {
+			mrioc->req_qinfo[i].ci = 0;
+			mrioc->req_qinfo[i].pi = 0;
+			mrioc->req_qinfo[i].num_requests = 0;
+			mrioc->req_qinfo[i].qid = 0;
+			mrioc->req_qinfo[i].reply_qid = 0;
+			spin_lock_init(&mrioc->req_qinfo[i].q_lock);
+			mpi3mr_memset_op_req_q_buffers(mrioc, i);
+		}
 	}
 
 	atomic_set(&mrioc->pend_large_data_sz, 0);
-- 
cgit v1.2.3


From 38353c26db28efd984f51d426eac2396d299cca7 Mon Sep 17 00:00:00 2001
From: Salomon Dushimirimana <salomondush@google.com>
Date: Fri, 13 Feb 2026 19:28:06 +0000
Subject: scsi: pm8001: Fix use-after-free in pm8001_queue_command()

Commit e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()") refactors
pm8001_queue_command(), however it introduces a potential cause of a double
free scenario when it changes the function to return -ENODEV in case of phy
down/device gone state.

In this path, pm8001_queue_command() updates task status and calls
task_done to indicate to upper layer that the task has been handled.
However, this also frees the underlying SAS task. A -ENODEV is then
returned to the caller. When libsas sas_ata_qc_issue() receives this error
value, it assumes the task wasn't handled/queued by LLDD and proceeds to
clean up and free the task again, resulting in a double free.

Since pm8001_queue_command() handles the SAS task in this case, it should
return 0 to the caller indicating that the task has been handled.

Fixes: e29c47fe8946 ("scsi: pm8001: Simplify pm8001_task_exec()")
Signed-off-by: Salomon Dushimirimana <salomondush@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://patch.msgid.link/20260213192806.439432-1-salomondush@google.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/pm8001/pm8001_sas.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index 6a8d35aea93a..645524f3fe2d 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -525,8 +525,9 @@ int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags)
 		} else {
 			task->task_done(task);
 		}
-		rc = -ENODEV;
-		goto err_out;
+		spin_unlock_irqrestore(&pm8001_ha->lock, flags);
+		pm8001_dbg(pm8001_ha, IO, "pm8001_task_exec device gone\n");
+		return 0;
 	}
 
 	ccb = pm8001_ccb_alloc(pm8001_ha, pm8001_dev, task);
-- 
cgit v1.2.3


From af3973e7b4fd91e6884b312526168869fb013d68 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Mon, 16 Feb 2026 15:10:55 +0100
Subject: scsi: snic: Remove unused linkstatus

The (struct vnic_dev).linkstatus buffer is freed in svnic_dev_unregister()
and referenced in svnic_dev_link_status() but never alloc'd. This means
(struct vnic_dev).linkstatus is always null and the dealloc the reference
in svnic_dev_link_status() is dead code.

Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Acked-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://patch.msgid.link/20260216141056.59429-2-fourier.thomas@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/snic/vnic_dev.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/scsi/snic/vnic_dev.c b/drivers/scsi/snic/vnic_dev.c
index 760f3f22095c..c4df0b17c86c 100644
--- a/drivers/scsi/snic/vnic_dev.c
+++ b/drivers/scsi/snic/vnic_dev.c
@@ -42,8 +42,6 @@ struct vnic_dev {
 	struct vnic_devcmd_notify *notify;
 	struct vnic_devcmd_notify notify_copy;
 	dma_addr_t notify_pa;
-	u32 *linkstatus;
-	dma_addr_t linkstatus_pa;
 	struct vnic_stats *stats;
 	dma_addr_t stats_pa;
 	struct vnic_devcmd_fw_info *fw_info;
@@ -650,8 +648,6 @@ int svnic_dev_init(struct vnic_dev *vdev, int arg)
 
 int svnic_dev_link_status(struct vnic_dev *vdev)
 {
-	if (vdev->linkstatus)
-		return *vdev->linkstatus;
 
 	if (!vnic_dev_notify_ready(vdev))
 		return 0;
@@ -686,11 +682,6 @@ void svnic_dev_unregister(struct vnic_dev *vdev)
 				sizeof(struct vnic_devcmd_notify),
 				vdev->notify,
 				vdev->notify_pa);
-		if (vdev->linkstatus)
-			dma_free_coherent(&vdev->pdev->dev,
-				sizeof(u32),
-				vdev->linkstatus,
-				vdev->linkstatus_pa);
 		if (vdev->stats)
 			dma_free_coherent(&vdev->pdev->dev,
 				sizeof(struct vnic_stats),
-- 
cgit v1.2.3


From 97af85787c1964a7e7b146c5d4e021f089af47ea Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Feb 2026 12:46:58 -0800
Subject: scsi: snic: MAINTAINERS: Update snic maintainers

Update snic maintainers.

Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://patch.msgid.link/20260217204658.5465-1-kartilak@cisco.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 70292bd3ed71..0900af786cce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6115,6 +6115,7 @@ F:	drivers/scsi/fnic/
 
 CISCO SCSI HBA DRIVER
 M:	Karan Tilak Kumar <kartilak@cisco.com>
+M:	Narsimhulu Musini <nmusini@cisco.com>
 M:	Sesidhar Baddela <sebaddel@cisco.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported
-- 
cgit v1.2.3


From a41dbf5e004edbe1260883c43a8bd134d9cb0c1c Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Sat, 14 Feb 2026 16:22:13 +0100
Subject: mount: hold namespace_sem across copy in create_new_namespace()

Fix an oversight when creating a new mount namespace. If someone had the
bright idea to make the real rootfs a shared or dependent mount and it
is later copied the copy will become a peer of the old real rootfs mount
or a dependent mount of it. The namespace semaphore is dropped and we
use mount lock exact to lock the new real root mount. If that fails or
the subsequent do_loopback() fails we rely on the copy of the real root
mount to be cleaned up by path_put(). The problem is that this doesn't
deal with mount propagation and will leave the mounts linked in the
propagation lists.

When creating a new mount namespace create_new_namespace() first
acquires namespace_sem to clone the nullfs root, drops it, then
reacquires it via LOCK_MOUNT_EXACT which takes inode_lock first to
respect the inode_lock -> namespace_sem lock ordering. This
drop-and-reacquire pattern is fragile and was the source of the
propagation cleanup bug fixed in the preceding commit.

Extend lock_mount_exact() with a copy_mount mode that clones the mount
under the locks atomically. When copy_mount is true, path_overmounted()
is skipped since we're copying the mount, not mounting on top of it -
the nullfs root always has rootfs mounted on top so the check would
always fail. If clone_mnt() fails after get_mountpoint() has pinned the
mountpoint, __unlock_mount() is used to properly unpin the mountpoint
and release both locks.

This allows create_new_namespace() to use LOCK_MOUNT_EXACT_COPY which
takes inode_lock and namespace_sem once and holds them throughout the
clone and subsequent mount operations, eliminating the
drop-and-reacquire pattern entirely.

Reported-by: syzbot+a89f9434fb5a001ccd58@syzkaller.appspotmail.com
Fixes: 9b8a0ba68246 ("mount: add OPEN_TREE_NAMESPACE") # mainline only
Link: https://lore.kernel.org/699047f6.050a0220.2757fb.0024.GAE@google.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 111 +++++++++++++++++++++++++++++----------------------------
 1 file changed, 57 insertions(+), 54 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 90700df65f0d..022e59afcb5e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2791,7 +2791,8 @@ static inline void unlock_mount(struct pinned_mountpoint *m)
 }
 
 static void lock_mount_exact(const struct path *path,
-			     struct pinned_mountpoint *mp);
+			     struct pinned_mountpoint *mp, bool copy_mount,
+			     unsigned int copy_flags);
 
 #define LOCK_MOUNT_MAYBE_BENEATH(mp, path, beneath) \
 	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
@@ -2799,7 +2800,10 @@ static void lock_mount_exact(const struct path *path,
 #define LOCK_MOUNT(mp, path) LOCK_MOUNT_MAYBE_BENEATH(mp, (path), false)
 #define LOCK_MOUNT_EXACT(mp, path) \
 	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
-	lock_mount_exact((path), &mp)
+	lock_mount_exact((path), &mp, false, 0)
+#define LOCK_MOUNT_EXACT_COPY(mp, path, copy_flags) \
+	struct pinned_mountpoint mp __cleanup(unlock_mount) = {}; \
+	lock_mount_exact((path), &mp, true, (copy_flags))
 
 static int graft_tree(struct mount *mnt, const struct pinned_mountpoint *mp)
 {
@@ -3073,16 +3077,13 @@ static struct file *open_detached_copy(struct path *path, unsigned int flags)
 	return file;
 }
 
-DEFINE_FREE(put_empty_mnt_ns, struct mnt_namespace *,
-	    if (!IS_ERR_OR_NULL(_T)) free_mnt_ns(_T))
-
 static struct mnt_namespace *create_new_namespace(struct path *path, unsigned int flags)
 {
-	struct mnt_namespace *new_ns __free(put_empty_mnt_ns) = NULL;
-	struct path to_path __free(path_put) = {};
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct user_namespace *user_ns = current_user_ns();
-	struct mount *new_ns_root;
+	struct mnt_namespace *new_ns;
+	struct mount *new_ns_root, *old_ns_root;
+	struct path to_path;
 	struct mount *mnt;
 	unsigned int copy_flags = 0;
 	bool locked = false;
@@ -3094,71 +3095,63 @@ static struct mnt_namespace *create_new_namespace(struct path *path, unsigned in
 	if (IS_ERR(new_ns))
 		return ERR_CAST(new_ns);
 
-	scoped_guard(namespace_excl) {
-		new_ns_root = clone_mnt(ns->root, ns->root->mnt.mnt_root, copy_flags);
-		if (IS_ERR(new_ns_root))
-			return ERR_CAST(new_ns_root);
+	old_ns_root = ns->root;
+	to_path.mnt = &old_ns_root->mnt;
+	to_path.dentry = old_ns_root->mnt.mnt_root;
 
-		/*
-		 * If the real rootfs had a locked mount on top of it somewhere
-		 * in the stack, lock the new mount tree as well so it can't be
-		 * exposed.
-		 */
-		mnt = ns->root;
-		while (mnt->overmount) {
-			mnt = mnt->overmount;
-			if (mnt->mnt.mnt_flags & MNT_LOCKED)
-				locked = true;
-		}
+	VFS_WARN_ON_ONCE(old_ns_root->mnt.mnt_sb->s_type != &nullfs_fs_type);
+
+	LOCK_MOUNT_EXACT_COPY(mp, &to_path, copy_flags);
+	if (IS_ERR(mp.parent)) {
+		free_mnt_ns(new_ns);
+		return ERR_CAST(mp.parent);
 	}
+	new_ns_root = mp.parent;
 
 	/*
-	 * We dropped the namespace semaphore so we can actually lock
-	 * the copy for mounting. The copied mount isn't attached to any
-	 * mount namespace and it is thus excluded from any propagation.
-	 * So realistically we're isolated and the mount can't be
-	 * overmounted.
+	 * If the real rootfs had a locked mount on top of it somewhere
+	 * in the stack, lock the new mount tree as well so it can't be
+	 * exposed.
 	 */
-
-	/* Borrow the reference from clone_mnt(). */
-	to_path.mnt = &new_ns_root->mnt;
-	to_path.dentry = dget(new_ns_root->mnt.mnt_root);
-
-	/* Now lock for actual mounting. */
-	LOCK_MOUNT_EXACT(mp, &to_path);
-	if (unlikely(IS_ERR(mp.parent)))
-		return ERR_CAST(mp.parent);
+	mnt = old_ns_root;
+	while (mnt->overmount) {
+		mnt = mnt->overmount;
+		if (mnt->mnt.mnt_flags & MNT_LOCKED)
+			locked = true;
+	}
 
 	/*
-	 * We don't emulate unshare()ing a mount namespace. We stick to the
-	 * restrictions of creating detached bind-mounts. It has a lot
-	 * saner and simpler semantics.
+	 * We don't emulate unshare()ing a mount namespace. We stick
+	 * to the restrictions of creating detached bind-mounts. It
+	 * has a lot saner and simpler semantics.
 	 */
 	mnt = __do_loopback(path, flags, copy_flags);
-	if (IS_ERR(mnt))
-		return ERR_CAST(mnt);
-
 	scoped_guard(mount_writer) {
+		if (IS_ERR(mnt)) {
+			emptied_ns = new_ns;
+			umount_tree(new_ns_root, 0);
+			return ERR_CAST(mnt);
+		}
+
 		if (locked)
 			mnt->mnt.mnt_flags |= MNT_LOCKED;
 		/*
-		 * Now mount the detached tree on top of the copy of the
-		 * real rootfs we created.
+		 * now mount the detached tree on top of the copy
+		 * of the real rootfs we created.
 		 */
 		attach_mnt(mnt, new_ns_root, mp.mp);
 		if (user_ns != ns->user_ns)
 			lock_mnt_tree(new_ns_root);
 	}
 
-	/* Add all mounts to the new namespace. */
-	for (struct mount *p = new_ns_root; p; p = next_mnt(p, new_ns_root)) {
-		mnt_add_to_ns(new_ns, p);
+	for (mnt = new_ns_root; mnt; mnt = next_mnt(mnt, new_ns_root)) {
+		mnt_add_to_ns(new_ns, mnt);
 		new_ns->nr_mounts++;
 	}
 
-	new_ns->root = real_mount(no_free_ptr(to_path.mnt));
+	new_ns->root = new_ns_root;
 	ns_tree_add_raw(new_ns);
-	return no_free_ptr(new_ns);
+	return new_ns;
 }
 
 static struct file *open_new_namespace(struct path *path, unsigned int flags)
@@ -3840,16 +3833,20 @@ static int do_new_mount(const struct path *path, const char *fstype,
 }
 
 static void lock_mount_exact(const struct path *path,
-			     struct pinned_mountpoint *mp)
+			     struct pinned_mountpoint *mp, bool copy_mount,
+			     unsigned int copy_flags)
 {
 	struct dentry *dentry = path->dentry;
 	int err;
 
+	/* Assert that inode_lock() locked the correct inode. */
+	VFS_WARN_ON_ONCE(copy_mount && !path_mounted(path));
+
 	inode_lock(dentry->d_inode);
 	namespace_lock();
 	if (unlikely(cant_mount(dentry)))
 		err = -ENOENT;
-	else if (path_overmounted(path))
+	else if (!copy_mount && path_overmounted(path))
 		err = -EBUSY;
 	else
 		err = get_mountpoint(dentry, mp);
@@ -3857,9 +3854,15 @@ static void lock_mount_exact(const struct path *path,
 		namespace_unlock();
 		inode_unlock(dentry->d_inode);
 		mp->parent = ERR_PTR(err);
-	} else {
-		mp->parent = real_mount(path->mnt);
+		return;
 	}
+
+	if (copy_mount)
+		mp->parent = clone_mnt(real_mount(path->mnt), dentry, copy_flags);
+	else
+		mp->parent = real_mount(path->mnt);
+	if (unlikely(IS_ERR(mp->parent)))
+		__unlock_mount(mp);
 }
 
 int finish_automount(struct vfsmount *__m, const struct path *path)
-- 
cgit v1.2.3


From 4a403d7aa9074f527f064ef0806aaab38d14b07c Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 29 Jan 2026 14:52:22 +0100
Subject: namespace: fix proc mount iteration

The m->index isn't updated when m->show() overflows and retains its
value before the current mount causing a restart to start at the same
value. If that happens in short order to due a quickly expanding mount
table this would cause the same mount to be shown again and again.

Ensure that *pos always equals the mount id of the mount that was
returned by start/next. On restart after overflow mnt_find_id_at(*pos)
finds the exact mount. This should avoid duplicates, avoid skips and
should handle concurrent modification just fine.

Cc: <stable@vger.kernel.org>
Fixed: 2eea9ce4310d8 ("mounts: keep list of mounts in an rbtree")
Link: https://patch.msgid.link/20260129-geleckt-treuhand-4bb940acacd9@brauner
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 022e59afcb5e..31483c66ace8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1531,23 +1531,33 @@ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct mount *mnt;
 
 	down_read(&namespace_sem);
 
-	return mnt_find_id_at(p->ns, *pos);
+	mnt = mnt_find_id_at(p->ns, *pos);
+	if (mnt)
+		*pos = mnt->mnt_id_unique;
+	return mnt;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct mount *next = NULL, *mnt = v;
+	struct mount *mnt = v;
 	struct rb_node *node = rb_next(&mnt->mnt_node);
 
-	++*pos;
 	if (node) {
-		next = node_to_mount(node);
+		struct mount *next = node_to_mount(node);
 		*pos = next->mnt_id_unique;
+		return next;
 	}
-	return next;
+
+	/*
+	 * No more mounts. Set pos past current mount's ID so that if
+	 * iteration restarts, mnt_find_id_at() returns NULL.
+	 */
+	*pos = mnt->mnt_id_unique + 1;
+	return NULL;
 }
 
 static void m_stop(struct seq_file *m, void *v)
-- 
cgit v1.2.3


From ef0b64741a53e47ce8022c973099e969094aa536 Mon Sep 17 00:00:00 2001
From: Jori Koolstra <jkoolstra@xs4all.nl>
Date: Mon, 1 Dec 2025 13:23:38 +0100
Subject: minix: Correct errno in minix_new_inode

The cases (!j || j > sbi->s_ninodes) can never occur unless the
filesystem is broken, so this should not return ENOSPC, but
EFSCORRUPTED.

Signed-off-by: Jori Koolstra <jkoolstra@xs4all.nl>
Link: https://patch.msgid.link/20251201122338.90568-1-jkoolstra@xs4all.nl
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/minix/bitmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c
index 7da66ca184f4..abec438330a7 100644
--- a/fs/minix/bitmap.c
+++ b/fs/minix/bitmap.c
@@ -247,7 +247,7 @@ struct inode *minix_new_inode(const struct inode *dir, umode_t mode)
 	j += i * bits_per_zone;
 	if (!j || j > sbi->s_ninodes) {
 		iput(inode);
-		return ERR_PTR(-ENOSPC);
+		return ERR_PTR(-EFSCORRUPTED);
 	}
 	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
 	inode->i_ino = j;
-- 
cgit v1.2.3


From 6c4b2243cb6c0755159bd567130d5e12e7b10d9f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 7 Feb 2026 08:25:24 +0000
Subject: unshare: fix unshare_fs() handling

There's an unpleasant corner case in unshare(2), when we have a
CLONE_NEWNS in flags and current->fs hadn't been shared at all; in that
case copy_mnt_ns() gets passed current->fs instead of a private copy,
which causes interesting warts in proof of correctness]

> I guess if private means fs->users == 1, the condition could still be true.

Unfortunately, it's worse than just a convoluted proof of correctness.
Consider the case when we have CLONE_NEWCGROUP in addition to CLONE_NEWNS
(and current->fs->users == 1).

We pass current->fs to copy_mnt_ns(), all right.  Suppose it succeeds and
flips current->fs->{pwd,root} to corresponding locations in the new namespace.
Now we proceed to copy_cgroup_ns(), which fails (e.g. with -ENOMEM).
We call put_mnt_ns() on the namespace created by copy_mnt_ns(), it's
destroyed and its mount tree is dissolved, but...  current->fs->root and
current->fs->pwd are both left pointing to now detached mounts.

They are pinning those, so it's not a UAF, but it leaves the calling
process with unshare(2) failing with -ENOMEM _and_ leaving it with
pwd and root on detached isolated mounts.  The last part is clearly a bug.

There is other fun related to that mess (races with pivot_root(), including
the one between pivot_root() and fork(), of all things), but this one
is easy to isolate and fix - treat CLONE_NEWNS as "allocate a new
fs_struct even if it hadn't been shared in the first place".  Sure, we could
go for something like "if both CLONE_NEWNS *and* one of the things that might
end up failing after copy_mnt_ns() call in create_new_namespaces() are set,
force allocation of new fs_struct", but let's keep it simple - the cost
of copy_fs_struct() is trivial.

Another benefit is that copy_mnt_ns() with CLONE_NEWNS *always* gets
a freshly allocated fs_struct, yet to be attached to anything.  That
seriously simplifies the analysis...

FWIW, that bug had been there since the introduction of unshare(2) ;-/

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://patch.msgid.link/20260207082524.GE3183987@ZenIV
Tested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/fork.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index e832da9d15a4..65113a304518 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3085,7 +3085,7 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 		return 0;
 
 	/* don't need lock here; in the worst case we'll do useless copy */
-	if (fs->users == 1)
+	if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1)
 		return 0;
 
 	*new_fsp = copy_fs_struct(fs);
-- 
cgit v1.2.3


From fc1e8a6f129d87c64ac8e58b50d9dfa66217cfda Mon Sep 17 00:00:00 2001
From: Liam Mitchell <mitchell.liam@gmail.com>
Date: Wed, 18 Feb 2026 14:21:35 -0800
Subject: Input: bcm5974 - recover from failed mode switch

Mode switches sent before control response are ignored. This results in
an unresponsive trackpad and "bcm5974: bad trackpad package, length: 8"
repeated in logs.

On receiving unknown 8-byte packets, assume that mode switch was ignored
and schedule an asynchronous mode reset. The reset will switch the
device to normal mode, wait, then switch back to wellspring mode.

Signed-off-by: Liam Mitchell <mitchell.liam@gmail.com>
Link: https://lore.kernel.org/linux-input/CAOQ1CL4+DP1TuLAGNsz5GdFBTHvnTg=5q=Dr2Z1OQc6RXydSYA@mail.gmail.com/
Acked-by: Henrik Rydberg <rydberg@bitmath.org>
Link: https://patch.msgid.link/20260213-bcm5974-reset-v2-1-1837851336b0@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/bcm5974.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index dfdfb59cc8b5..fe52f15c0c10 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -286,6 +286,8 @@ struct bcm5974 {
 	const struct tp_finger *index[MAX_FINGERS];	/* finger index data */
 	struct input_mt_pos pos[MAX_FINGERS];		/* position array */
 	int slots[MAX_FINGERS];				/* slot assignments */
+	struct work_struct mode_reset_work;
+	unsigned long last_mode_reset;
 };
 
 /* trackpad finger block data, le16-aligned */
@@ -696,6 +698,32 @@ static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 	return retval;
 }
 
+/*
+ * Mode switches sent before the control response are ignored.
+ * Fixing this state requires switching to normal mode and waiting
+ * about 1ms before switching back to wellspring mode.
+ */
+static void bcm5974_mode_reset_work(struct work_struct *work)
+{
+	struct bcm5974 *dev = container_of(work, struct bcm5974, mode_reset_work);
+	int error;
+
+	guard(mutex)(&dev->pm_mutex);
+	dev->last_mode_reset = jiffies;
+
+	error = bcm5974_wellspring_mode(dev, false);
+	if (error) {
+		dev_err(&dev->intf->dev, "reset to normal mode failed\n");
+		return;
+	}
+
+	fsleep(1000);
+
+	error = bcm5974_wellspring_mode(dev, true);
+	if (error)
+		dev_err(&dev->intf->dev, "mode switch after reset failed\n");
+}
+
 static void bcm5974_irq_button(struct urb *urb)
 {
 	struct bcm5974 *dev = urb->context;
@@ -752,10 +780,20 @@ static void bcm5974_irq_trackpad(struct urb *urb)
 	if (dev->tp_urb->actual_length == 2)
 		goto exit;
 
-	if (report_tp_state(dev, dev->tp_urb->actual_length))
+	if (report_tp_state(dev, dev->tp_urb->actual_length)) {
 		dprintk(1, "bcm5974: bad trackpad package, length: %d\n",
 			dev->tp_urb->actual_length);
 
+		/*
+		 * Receiving a HID packet means we aren't in wellspring mode.
+		 * If we haven't tried a reset in the last second, try now.
+		 */
+		if (dev->tp_urb->actual_length == 8 &&
+		    time_after(jiffies, dev->last_mode_reset + msecs_to_jiffies(1000))) {
+			schedule_work(&dev->mode_reset_work);
+		}
+	}
+
 exit:
 	error = usb_submit_urb(dev->tp_urb, GFP_ATOMIC);
 	if (error)
@@ -906,6 +944,7 @@ static int bcm5974_probe(struct usb_interface *iface,
 	dev->intf = iface;
 	dev->input = input_dev;
 	dev->cfg = *cfg;
+	INIT_WORK(&dev->mode_reset_work, bcm5974_mode_reset_work);
 	mutex_init(&dev->pm_mutex);
 
 	/* setup urbs */
@@ -998,6 +1037,7 @@ static void bcm5974_disconnect(struct usb_interface *iface)
 {
 	struct bcm5974 *dev = usb_get_intfdata(iface);
 
+	disable_work_sync(&dev->mode_reset_work);
 	usb_set_intfdata(iface, NULL);
 
 	input_unregister_device(dev->input);
-- 
cgit v1.2.3


From 249013e673fce3506c61063c7cbedd75b4c668d8 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 22:09:21 -0800
Subject: fsnotify: drop unused helper

Remove this helper now that all users have been converted to
fserror_report_metadata as of 7.0-rc1.

Cc: jack@suse.cz
Cc: amir73il@gmail.com
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/177148129543.716249.980530449513340111.stgit@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 28a9cb13fbfa..079c18bcdbde 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -495,19 +495,6 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
-static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
-				    int error)
-{
-	struct fs_error_report report = {
-		.error = error,
-		.inode = inode,
-		.sb = sb,
-	};
-
-	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
-			NULL, NULL, NULL, 0);
-}
-
 static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt)
 {
 	fsnotify_mnt(FS_MNT_ATTACH, ns, mnt);
-- 
cgit v1.2.3


From 294f54f849d846f4643a67db9b41b63867dc8bfe Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 22:09:37 -0800
Subject: fserror: fix lockdep complaint when igrabbing inode

Christoph Hellwig reported a lockdep splat in generic/108:

 ================================
 WARNING: inconsistent lock state
 6.19.0+ #4827 Tainted: G                 N
 --------------------------------
 inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
 swapper/1/0 [HC1[1]:SC0[0]:HE0:SE1] takes:
 ffff88811ed1b140 (&sb->s_type->i_lock_key#33){?.+.}-{3:3}, at: igrab+0x1a/0xb0
 {HARDIRQ-ON-W} state was registered at:
   lock_acquire+0xca/0x2c0
   _raw_spin_lock+0x2e/0x40
   unlock_new_inode+0x2c/0xc0
   xfs_iget+0xcf4/0x1080
   xfs_trans_metafile_iget+0x3d/0x100
   xfs_metafile_iget+0x2b/0x50
   xfs_mount_setup_metadir+0x20/0x60
   xfs_mountfs+0x457/0xa60
   xfs_fs_fill_super+0x6b3/0xa90
   get_tree_bdev_flags+0x13c/0x1e0
   vfs_get_tree+0x27/0xe0
   vfs_cmd_create+0x54/0xe0
   __do_sys_fsconfig+0x309/0x620
   do_syscall_64+0x8b/0xf80
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
 irq event stamp: 139080
 hardirqs last  enabled at (139079): [<ffffffff813a923c>] do_idle+0x1ec/0x270
 hardirqs last disabled at (139080): [<ffffffff828a8d09>] common_interrupt+0x19/0xe0
 softirqs last  enabled at (139032): [<ffffffff8134a853>] __irq_exit_rcu+0xc3/0x120
 softirqs last disabled at (139025): [<ffffffff8134a853>] __irq_exit_rcu+0xc3/0x120

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&sb->s_type->i_lock_key#33);
   <Interrupt>
     lock(&sb->s_type->i_lock_key#33);

  *** DEADLOCK ***

 1 lock held by swapper/1/0:
  #0: ffff8881052c81a0 (&vblk->vqs[i].lock){-.-.}-{3:3}, at: virtblk_done+0x4b/0x110

 stack backtrace:
 CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Tainted: G                 N  6.19.0+ #4827 PREEMPT(full)
 Tainted: [N]=TEST
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x5b/0x80
  print_usage_bug.part.0+0x22c/0x2c0
  mark_lock+0xa6f/0xe90
  __lock_acquire+0x10b6/0x25e0
  lock_acquire+0xca/0x2c0
  _raw_spin_lock+0x2e/0x40
  igrab+0x1a/0xb0
  fserror_report+0x135/0x260
  iomap_finish_ioend_buffered+0x170/0x210
  clone_endio+0x8f/0x1c0
  blk_update_request+0x1e4/0x4d0
  blk_mq_end_request+0x1b/0x100
  virtblk_done+0x6f/0x110
  vring_interrupt+0x59/0x80
  __handle_irq_event_percpu+0x8a/0x2e0
  handle_irq_event+0x33/0x70
  handle_edge_irq+0xdd/0x1e0
  __common_interrupt+0x6f/0x180
  common_interrupt+0xb7/0xe0
  </IRQ>

It looks like the concern here is that inode::i_lock is sometimes taken
in IRQ context, and sometimes it is held when going to IRQ context,
though it's a little difficult to tell since I think this is a kernel
from after the actual 6.19 release but before 7.0-rc1.

Either way, we don't need to take i_lock, because filesystems should
not report files to fserror if they're about to be freed or have not
yet been exposed to other threads, because the resulting fsnotify report
will be meaningless.

Therefore, bump inode::i_count directly and clarify the preconditions on
the inode being passed in.

Link: https://lore.kernel.org/linux-fsdevel/aY7BndIgQg3ci_6s@infradead.org/
Reported-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/177148129564.716249.3069780698231701540.stgit@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/ioend.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index e4d57cb969f1..4d1ef8a2cee9 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -69,11 +69,57 @@ static u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
 	return folio_count;
 }
 
+static DEFINE_SPINLOCK(failed_ioend_lock);
+static LIST_HEAD(failed_ioend_list);
+
+static void
+iomap_fail_ioends(
+	struct work_struct	*work)
+{
+	struct iomap_ioend	*ioend;
+	struct list_head	tmp;
+	unsigned long		flags;
+
+	spin_lock_irqsave(&failed_ioend_lock, flags);
+	list_replace_init(&failed_ioend_list, &tmp);
+	spin_unlock_irqrestore(&failed_ioend_lock, flags);
+
+	while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
+			io_list))) {
+		list_del_init(&ioend->io_list);
+		iomap_finish_ioend_buffered(ioend);
+		cond_resched();
+	}
+}
+
+static DECLARE_WORK(failed_ioend_work, iomap_fail_ioends);
+
+static void iomap_fail_ioend_buffered(struct iomap_ioend *ioend)
+{
+	unsigned long flags;
+
+	/*
+	 * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions
+	 * in the fserror code.  The caller no longer owns the ioend reference
+	 * after the spinlock drops.
+	 */
+	spin_lock_irqsave(&failed_ioend_lock, flags);
+	if (list_empty(&failed_ioend_list))
+		WARN_ON_ONCE(!schedule_work(&failed_ioend_work));
+	list_add_tail(&ioend->io_list, &failed_ioend_list);
+	spin_unlock_irqrestore(&failed_ioend_lock, flags);
+}
+
 static void ioend_writeback_end_bio(struct bio *bio)
 {
 	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
 
 	ioend->io_error = blk_status_to_errno(bio->bi_status);
+	if (ioend->io_error) {
+		iomap_fail_ioend_buffered(ioend);
+		return;
+	}
+
 	iomap_finish_ioend_buffered(ioend);
 }
 
-- 
cgit v1.2.3


From 023cd6d90f8aa2ef7b72d84be84a18e61ecebd64 Mon Sep 17 00:00:00 2001
From: Piotr Mazek <pmazek@outlook.com>
Date: Thu, 5 Feb 2026 23:05:02 +0100
Subject: ACPI: PM: Save NVS memory on Lenovo G70-35

[821d6f0359b0614792ab8e2fb93b503e25a65079] prevented machines
produced later than 2012 from saving NVS region to accelerate S3.

Despite being made after 2012, Lenovo G70-35 still needs NVS memory
saving during S3. A quirk is introduced for this platform.

Signed-off-by: Piotr Mazek <pmazek@outlook.com>
[ rjw: Subject adjustment ]
Link: https://patch.msgid.link/GV2PPF3CD5B63CC2442EE3F76F8443EAD90D499A@GV2PPF3CD5B63CC.EURP251.PROD.OUTLOOK.COM
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 66ec81e306d4..132a9df98471 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -386,6 +386,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "80E1"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Lenovo G70-35",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "80Q5"),
+		},
+	},
 	/*
 	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
 	 * the Low Power S0 Idle firmware interface (see
-- 
cgit v1.2.3


From ab140365fb62c0bdab22b2f516aff563b2559e3b Mon Sep 17 00:00:00 2001
From: Lars Ellenberg <lars.ellenberg@linbit.com>
Date: Thu, 19 Feb 2026 15:20:12 +0100
Subject: drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even though we check that we "should" be able to do lc_get_cumulative()
while holding the device->al_lock spinlock, it may still fail,
if some other code path decided to do lc_try_lock() with bad timing.

If that happened, we logged "LOGIC BUG for enr=...",
but still did not return an error.

The rest of the code now assumed that this request has references
for the relevant activity log extents.

The implcations are that during an active resync, mutual exclusivity of
resync versus application IO is not guaranteed. And a potential crash
at this point may not realizs that these extents could have been target
of in-flight IO and would need to be resynced just in case.

Also, once the request completes, it will give up activity log references it
does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put().

Fix:

Do not crash the kernel for a condition that is harmless during normal
operation: also catch "e->refcnt == 0", not only "e == NULL"
when being noisy about "al_complete_io() called on inactive extent %u\n".

And do not try to be smart and "guess" whether something will work, then
be surprised when it does not.
Deal with the fact that it may or may not work.  If it does not, remember a
possible "partially in activity log" state (only possible for requests that
cross extent boundaries), and return an error code from
drbd_al_begin_io_nonblock().

A latter call for the same request will then resume from where we left off.

Cc: stable@vger.kernel.org
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_actlog.c   | 53 +++++++++++++++++---------------------
 drivers/block/drbd/drbd_interval.h |  5 +++-
 2 files changed, 27 insertions(+), 31 deletions(-)

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 742b2908ff68..b3dbf6c76e98 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -483,38 +483,20 @@ void drbd_al_begin_io(struct drbd_device *device, struct drbd_interval *i)
 
 int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *i)
 {
-	struct lru_cache *al = device->act_log;
 	/* for bios crossing activity log extent boundaries,
 	 * we may need to activate two extents in one go */
 	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
 	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
-	unsigned nr_al_extents;
-	unsigned available_update_slots;
 	unsigned enr;
 
-	D_ASSERT(device, first <= last);
-
-	nr_al_extents = 1 + last - first; /* worst case: all touched extends are cold. */
-	available_update_slots = min(al->nr_elements - al->used,
-				al->max_pending_changes - al->pending_changes);
-
-	/* We want all necessary updates for a given request within the same transaction
-	 * We could first check how many updates are *actually* needed,
-	 * and use that instead of the worst-case nr_al_extents */
-	if (available_update_slots < nr_al_extents) {
-		/* Too many activity log extents are currently "hot".
-		 *
-		 * If we have accumulated pending changes already,
-		 * we made progress.
-		 *
-		 * If we cannot get even a single pending change through,
-		 * stop the fast path until we made some progress,
-		 * or requests to "cold" extents could be starved. */
-		if (!al->pending_changes)
-			__set_bit(__LC_STARVING, &device->act_log->flags);
-		return -ENOBUFS;
+	if (i->partially_in_al_next_enr) {
+		D_ASSERT(device, first < i->partially_in_al_next_enr);
+		D_ASSERT(device, last >= i->partially_in_al_next_enr);
+		first = i->partially_in_al_next_enr;
 	}
 
+	D_ASSERT(device, first <= last);
+
 	/* Is resync active in this area? */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *tmp;
@@ -529,14 +511,21 @@ int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *
 		}
 	}
 
-	/* Checkout the refcounts.
-	 * Given that we checked for available elements and update slots above,
-	 * this has to be successful. */
+	/* Try to checkout the refcounts. */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *al_ext;
 		al_ext = lc_get_cumulative(device->act_log, enr);
-		if (!al_ext)
-			drbd_info(device, "LOGIC BUG for enr=%u\n", enr);
+
+		if (!al_ext) {
+			/* Did not work. We may have exhausted the possible
+			 * changes per transaction. Or raced with someone
+			 * "locking" it against changes.
+			 * Remember where to continue from.
+			 */
+			if (enr > first)
+				i->partially_in_al_next_enr = enr;
+			return -ENOBUFS;
+		}
 	}
 	return 0;
 }
@@ -556,7 +545,11 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i)
 
 	for (enr = first; enr <= last; enr++) {
 		extent = lc_find(device->act_log, enr);
-		if (!extent) {
+		/* Yes, this masks a bug elsewhere.  However, during normal
+		 * operation this is harmless, so no need to crash the kernel
+		 * by the BUG_ON(refcount == 0) in lc_put().
+		 */
+		if (!extent || extent->refcnt == 0) {
 			drbd_err(device, "al_complete_io() called on inactive extent %u\n", enr);
 			continue;
 		}
diff --git a/drivers/block/drbd/drbd_interval.h b/drivers/block/drbd/drbd_interval.h
index 366489b72fe9..5d3213b81eed 100644
--- a/drivers/block/drbd/drbd_interval.h
+++ b/drivers/block/drbd/drbd_interval.h
@@ -8,12 +8,15 @@
 struct drbd_interval {
 	struct rb_node rb;
 	sector_t sector;		/* start sector of the interval */
-	unsigned int size;		/* size in bytes */
 	sector_t end;			/* highest interval end in subtree */
+	unsigned int size;		/* size in bytes */
 	unsigned int local:1		/* local or remote request? */;
 	unsigned int waiting:1;		/* someone is waiting for completion */
 	unsigned int completed:1;	/* this has been completed already;
 					 * ignore for conflict detection */
+
+	/* to resume a partially successful drbd_al_begin_io_nonblock(); */
+	unsigned int partially_in_al_next_enr;
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)
-- 
cgit v1.2.3


From 81b1f046ff8a5ad5da2c970cff354b61dfa1d6b1 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 12 Jan 2026 18:04:12 +0100
Subject: drbd: Replace deprecated strcpy with strscpy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

strcpy() has been deprecated [1] because it performs no bounds checking
on the destination buffer, which can lead to buffer overflows. Replace
it with the safer strscpy().  No functional changes.

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_main.c     | 14 +++++++++-----
 drivers/block/drbd/drbd_receiver.c |  4 ++--
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 1f6ac9202b66..ba00b5f21a49 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -32,6 +32,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/random.h>
 #include <linux/reboot.h>
 #include <linux/notifier.h>
@@ -732,9 +733,9 @@ int drbd_send_sync_param(struct drbd_peer_device *peer_device)
 	}
 
 	if (apv >= 88)
-		strcpy(p->verify_alg, nc->verify_alg);
+		strscpy(p->verify_alg, nc->verify_alg);
 	if (apv >= 89)
-		strcpy(p->csums_alg, nc->csums_alg);
+		strscpy(p->csums_alg, nc->csums_alg);
 	rcu_read_unlock();
 
 	return drbd_send_command(peer_device, sock, cmd, size, NULL, 0);
@@ -745,6 +746,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	struct drbd_socket *sock;
 	struct p_protocol *p;
 	struct net_conf *nc;
+	size_t integrity_alg_len;
 	int size, cf;
 
 	sock = &connection->data;
@@ -762,8 +764,10 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	}
 
 	size = sizeof(*p);
-	if (connection->agreed_pro_version >= 87)
-		size += strlen(nc->integrity_alg) + 1;
+	if (connection->agreed_pro_version >= 87) {
+		integrity_alg_len = strlen(nc->integrity_alg) + 1;
+		size += integrity_alg_len;
+	}
 
 	p->protocol      = cpu_to_be32(nc->wire_protocol);
 	p->after_sb_0p   = cpu_to_be32(nc->after_sb_0p);
@@ -778,7 +782,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 	p->conn_flags    = cpu_to_be32(cf);
 
 	if (connection->agreed_pro_version >= 87)
-		strcpy(p->integrity_alg, nc->integrity_alg);
+		strscpy(p->integrity_alg, nc->integrity_alg, integrity_alg_len);
 	rcu_read_unlock();
 
 	return __conn_send_command(connection, sock, cmd, size, NULL, 0);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 3de919b6f0e1..3d0a061b6c40 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3801,14 +3801,14 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i
 			*new_net_conf = *old_net_conf;
 
 			if (verify_tfm) {
-				strcpy(new_net_conf->verify_alg, p->verify_alg);
+				strscpy(new_net_conf->verify_alg, p->verify_alg);
 				new_net_conf->verify_alg_len = strlen(p->verify_alg) + 1;
 				crypto_free_shash(peer_device->connection->verify_tfm);
 				peer_device->connection->verify_tfm = verify_tfm;
 				drbd_info(device, "using verify-alg: \"%s\"\n", p->verify_alg);
 			}
 			if (csums_tfm) {
-				strcpy(new_net_conf->csums_alg, p->csums_alg);
+				strscpy(new_net_conf->csums_alg, p->csums_alg);
 				new_net_conf->csums_alg_len = strlen(p->csums_alg) + 1;
 				crypto_free_shash(peer_device->connection->csums_tfm);
 				peer_device->connection->csums_tfm = csums_tfm;
-- 
cgit v1.2.3


From 6b3e458806e34f1142592f786d3eb0ebac209cc2 Mon Sep 17 00:00:00 2001
From: Günther Noack <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:35 +0100
Subject: HID: Document memory allocation properties of report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The memory pointer returned by the report_fixup() hook does not get
freed by the caller.  Instead, report_fixup() must return (in return
value and *rsize) a memory buffer with at least the same lifetime as
the input buffer (defined by rdesc and original *rsize).

This is usually achieved using one of the following techniques:

* Returning a pointer and size to a sub-portion of the input buffer
* Returning a pointer to a static buffer
* Allocating a buffer with a devm_*() function,
  which will automatically get freed when the device is removed.

Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 include/linux/hid.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/hid.h b/include/linux/hid.h
index dce862cafbbd..2990b9f94cb5 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -836,6 +836,12 @@ struct hid_usage_id {
  * raw_event and event should return negative on error, any other value will
  * pass the event on to .event() typically return 0 for success.
  *
+ * report_fixup must return a report descriptor pointer whose lifetime is at
+ * least that of the input rdesc.  This is usually done by mutating the input
+ * rdesc and returning it or a sub-portion of it.  In case a new buffer is
+ * allocated and returned, the implementation of report_fixup is responsible for
+ * freeing it later.
+ *
  * input_mapping shall return a negative value to completely ignore this usage
  * (e.g. doubled or invalid usage), zero to continue with parsing of this
  * usage by generic code (no special handling needed) or positive to skip
-- 
cgit v1.2.3


From 239c15116d80f67d32f00acc34575f1a6b699613 Mon Sep 17 00:00:00 2001
From: Günther Noack <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:36 +0100
Subject: HID: apple: avoid memory leak in apple_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The apple_report_fixup() function was returning a
newly kmemdup()-allocated buffer, but never freeing it.

The caller of report_fixup() does not take ownership of the returned
pointer, but it *is* permitted to return a sub-portion of the input
rdesc, whose lifetime is managed by the caller.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-apple.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 233e367cce1d..894adc23367b 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -686,9 +686,7 @@ static const __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			 "fixing up Magic Keyboard battery report descriptor\n");
 		*rsize = *rsize - 1;
-		rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL);
-		if (!rdesc)
-			return NULL;
+		rdesc = rdesc + 1;
 
 		rdesc[0] = 0x05;
 		rdesc[1] = 0x01;
-- 
cgit v1.2.3


From 91e8c6e601bdc1ccdf886479b6513c01c7e51c2c Mon Sep 17 00:00:00 2001
From: Günther Noack <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:37 +0100
Subject: HID: magicmouse: avoid memory leak in magicmouse_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The magicmouse_report_fixup() function was returning a
newly kmemdup()-allocated buffer, but never freeing it.

The caller of report_fixup() does not take ownership of the returned
pointer, but it *is* permitted to return a sub-portion of the input
rdesc, whose lifetime is managed by the caller.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-magicmouse.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 91f621ceb924..17908d52c027 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -994,9 +994,7 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			 "fixing up magicmouse battery report descriptor\n");
 		*rsize = *rsize - 1;
-		rdesc = kmemdup(rdesc + 1, *rsize, GFP_KERNEL);
-		if (!rdesc)
-			return NULL;
+		rdesc = rdesc + 1;
 
 		rdesc[0] = 0x05;
 		rdesc[1] = 0x01;
-- 
cgit v1.2.3


From 2bad24c17742fc88973d6aea526ce1353f5334a3 Mon Sep 17 00:00:00 2001
From: Günther Noack <gnoack@google.com>
Date: Thu, 19 Feb 2026 16:43:38 +0100
Subject: HID: asus: avoid memory leak in asus_report_fixup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The asus_report_fixup() function was returning a newly allocated
kmemdup()-allocated buffer, but never freeing it.  Switch to
devm_kzalloc() to ensure the memory is managed and freed automatically
when the device is removed.

The caller of report_fixup() does not take ownership of the returned
pointer, but it is permitted to return a pointer whose lifetime is at
least that of the input buffer.

Also fix a harmless out-of-bounds read by copying only the original
descriptor size.

Assisted-by: Gemini-CLI:Google Gemini 3
Signed-off-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-asus.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 8ffcd12038e8..7a08e964b9cc 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1399,14 +1399,21 @@ static const __u8 *asus_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 */
 		if (*rsize == rsize_orig &&
 			rdesc[offs] == 0x09 && rdesc[offs + 1] == 0x76) {
-			*rsize = rsize_orig + 1;
-			rdesc = kmemdup(rdesc, *rsize, GFP_KERNEL);
-			if (!rdesc)
-				return NULL;
+			__u8 *new_rdesc;
+
+			new_rdesc = devm_kzalloc(&hdev->dev, rsize_orig + 1,
+						 GFP_KERNEL);
+			if (!new_rdesc)
+				return rdesc;
 
 			hid_info(hdev, "Fixing up %s keyb report descriptor\n",
 				drvdata->quirks & QUIRK_T100CHI ?
 				"T100CHI" : "T90CHI");
+
+			memcpy(new_rdesc, rdesc, rsize_orig);
+			*rsize = rsize_orig + 1;
+			rdesc = new_rdesc;
+
 			memmove(rdesc + offs + 4, rdesc + offs + 2, 12);
 			rdesc[offs] = 0x19;
 			rdesc[offs + 1] = 0x00;
-- 
cgit v1.2.3


From ecfa6f34492c493a9a1dc2900f3edeb01c79946b Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 19 Feb 2026 15:33:54 +0100
Subject: HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them

In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at
raw event handle"), we handle the fact that raw event callbacks
can happen even for a HID device that has not been "claimed" causing a
crash if a broken device were attempted to be connected to the system.

Fix up the remaining in-tree HID drivers that forgot to add this same
check to resolve the same issue.

Cc: Jiri Kosina <jikos@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Bastien Nocera <hadess@hadess.net>
Cc: linux-input@vger.kernel.org
Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-cmedia.c          | 2 +-
 drivers/hid/hid-creative-sb0540.c | 2 +-
 drivers/hid/hid-zydacron.c        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-cmedia.c b/drivers/hid/hid-cmedia.c
index 528d7f361215..8bf5649b0c79 100644
--- a/drivers/hid/hid-cmedia.c
+++ b/drivers/hid/hid-cmedia.c
@@ -99,7 +99,7 @@ static int cmhid_raw_event(struct hid_device *hid, struct hid_report *report,
 {
 	struct cmhid *cm = hid_get_drvdata(hid);
 
-	if (len != CM6533_JD_RAWEV_LEN)
+	if (len != CM6533_JD_RAWEV_LEN || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 	if (memcmp(data+CM6533_JD_SFX_OFFSET, ji_sfx, sizeof(ji_sfx)))
 		goto out;
diff --git a/drivers/hid/hid-creative-sb0540.c b/drivers/hid/hid-creative-sb0540.c
index b4c8e7a5d3e0..dfd6add353d1 100644
--- a/drivers/hid/hid-creative-sb0540.c
+++ b/drivers/hid/hid-creative-sb0540.c
@@ -153,7 +153,7 @@ static int creative_sb0540_raw_event(struct hid_device *hid,
 	u64 code, main_code;
 	int key;
 
-	if (len != 6)
+	if (len != 6 || !(hid->claimed & HID_CLAIMED_INPUT))
 		return 0;
 
 	/* From daemons/hw_hiddev.c sb0540_rec() in lirc */
diff --git a/drivers/hid/hid-zydacron.c b/drivers/hid/hid-zydacron.c
index 3bdb26f45592..1aae80f848f5 100644
--- a/drivers/hid/hid-zydacron.c
+++ b/drivers/hid/hid-zydacron.c
@@ -114,7 +114,7 @@ static int zc_raw_event(struct hid_device *hdev, struct hid_report *report,
 	unsigned key;
 	unsigned short index;
 
-	if (report->id == data[0]) {
+	if (report->id == data[0] && (hdev->claimed & HID_CLAIMED_INPUT)) {
 
 		/* break keys */
 		for (index = 0; index < 4; index++) {
-- 
cgit v1.2.3


From 858d2a4f67ff69e645a43487ef7ea7f28f06deae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Feb 2026 16:12:05 +0000
Subject: tcp: fix potential race in tcp_v6_syn_recv_sock()

Code in tcp_v6_syn_recv_sock() after the call to tcp_v4_syn_recv_sock()
is done too late.

After tcp_v4_syn_recv_sock(), the child socket is already visible
from TCP ehash table and other cpus might use it.

Since newinet->pinet6 is still pointing to the listener ipv6_pinfo
bad things can happen as syzbot found.

Move the problematic code in tcp_v6_mapped_child_init()
and call this new helper from tcp_v4_syn_recv_sock() before
the ehash insertion.

This allows the removal of one tcp_sync_mss(), since
tcp_v4_syn_recv_sock() will call it with the correct
context.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+937b5bbb6a815b3e5d0b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69949275.050a0220.2eeac1.0145.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260217161205.2079883-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_connection_sock.h |  4 +-
 include/net/tcp.h                  |  4 +-
 net/ipv4/syncookies.c              |  2 +-
 net/ipv4/tcp_fastopen.c            |  2 +-
 net/ipv4/tcp_ipv4.c                |  8 +++-
 net/ipv4/tcp_minisocks.c           |  2 +-
 net/ipv6/tcp_ipv6.c                | 98 ++++++++++++++++----------------------
 net/mptcp/subflow.c                |  6 ++-
 net/smc/af_smc.c                   |  6 ++-
 9 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ecb362025c4e..5cb3056d6ddc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -42,7 +42,9 @@ struct inet_connection_sock_af_ops {
 				      struct request_sock *req,
 				      struct dst_entry *dst,
 				      struct request_sock *req_unhash,
-				      bool *own_req);
+				      bool *own_req,
+				      void (*opt_child_init)(struct sock *newsk,
+							     const struct sock *sk));
 	u16	    net_header_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  sockptr_t optval, unsigned int optlen);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 40e72b9cb85f..eb8bf63fdafc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -544,7 +544,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req);
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk));
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 569befcf021b..061751aabc8e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -203,7 +203,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	bool own_req;
 
 	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						 NULL, &own_req);
+						 NULL, &own_req, NULL);
 	if (child) {
 		refcount_set(&req->rsk_refcnt, 1);
 		sock_rps_save_rxhash(child, skb);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index b30090cff3cf..df803f088f45 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -333,7 +333,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	bool own_req;
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 NULL, &own_req);
+							 NULL, &own_req, NULL);
 	if (!child)
 		return NULL;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6264fc0b2be5..2980c175d326 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1705,7 +1705,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req)
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk))
 {
 	struct inet_request_sock *ireq;
 	bool found_dup_sk = false;
@@ -1757,6 +1759,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
+#if IS_ENABLED(CONFIG_IPV6)
+	if (opt_child_init)
+		opt_child_init(newsk, sk);
+#endif
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ec128865f5c0..d9c5a43bd281 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -925,7 +925,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * socket is created, wait for troubles.
 	 */
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 req, &own_req);
+							 req, &own_req, NULL);
 	if (!child)
 		goto listen_overflow;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d10487b4e5bf..e46a0efae012 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1312,11 +1312,48 @@ static void tcp_v6_restore_cb(struct sk_buff *skb)
 		sizeof(struct inet6_skb_parm));
 }
 
+/* Called from tcp_v4_syn_recv_sock() for v6_mapped children. */
+static void tcp_v6_mapped_child_init(struct sock *newsk, const struct sock *sk)
+{
+	struct inet_sock *newinet = inet_sk(newsk);
+	struct ipv6_pinfo *newnp;
+
+	newinet->pinet6 = newnp = tcp_inet6_sk(newsk);
+	newinet->ipv6_fl_list = NULL;
+
+	memcpy(newnp, tcp_inet6_sk(sk), sizeof(struct ipv6_pinfo));
+
+	newnp->saddr = newsk->sk_v6_rcv_saddr;
+
+	inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
+	if (sk_is_mptcp(newsk))
+		mptcpv6_handle_mapped(newsk, true);
+	newsk->sk_backlog_rcv = tcp_v4_do_rcv;
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
+	tcp_sk(newsk)->af_specific = &tcp_sock_ipv6_mapped_specific;
+#endif
+
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->pktoptions  = NULL;
+	newnp->opt	   = NULL;
+
+	/* tcp_v4_syn_recv_sock() has initialized newinet->mc_{index,ttl} */
+	newnp->mcast_oif   = newinet->mc_index;
+	newnp->mcast_hops  = newinet->mc_ttl;
+
+	newnp->rcv_flowinfo = 0;
+	if (inet6_test_bit(REPFLOW, sk))
+		newnp->flow_label = 0;
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
 					 struct request_sock *req_unhash,
-					 bool *own_req)
+					 bool *own_req,
+					 void (*opt_child_init)(struct sock *newsk,
+								const struct sock *sk))
 {
 	const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct inet_request_sock *ireq;
@@ -1332,61 +1369,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 #endif
 	struct flowi6 fl6;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		/*
-		 *	v6 mapped
-		 */
-
-		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst,
-					     req_unhash, own_req);
-
-		if (!newsk)
-			return NULL;
-
-		newinet = inet_sk(newsk);
-		newinet->pinet6 = tcp_inet6_sk(newsk);
-		newinet->ipv6_fl_list = NULL;
-
-		newnp = tcp_inet6_sk(newsk);
-		newtp = tcp_sk(newsk);
-
-		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
-
-		newnp->saddr = newsk->sk_v6_rcv_saddr;
-
-		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
-		if (sk_is_mptcp(newsk))
-			mptcpv6_handle_mapped(newsk, true);
-		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
-#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
-		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
-#endif
-
-		newnp->ipv6_mc_list = NULL;
-		newnp->ipv6_ac_list = NULL;
-		newnp->pktoptions  = NULL;
-		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet_iif(skb);
-		newnp->mcast_hops  = ip_hdr(skb)->ttl;
-		newnp->rcv_flowinfo = 0;
-		if (inet6_test_bit(REPFLOW, sk))
-			newnp->flow_label = 0;
-
-		/*
-		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-		 * here, tcp_create_openreq_child now does this for us, see the comment in
-		 * that function for the gory details. -acme
-		 */
-
-		/* It is tricky place. Until this moment IPv4 tcp
-		   worked with IPv6 icsk.icsk_af_ops.
-		   Sync it now.
-		 */
-		tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
-
-		return newsk;
-	}
-
+	if (skb->protocol == htons(ETH_P_IP))
+		return tcp_v4_syn_recv_sock(sk, skb, req, dst,
+					    req_unhash, own_req,
+					    tcp_v6_mapped_child_init);
 	ireq = inet_rsk(req);
 
 	if (sk_acceptq_is_full(sk))
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index f66129f1e649..8b25dd86ffeb 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -808,7 +808,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
@@ -855,7 +857,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 create_child:
 	child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						     req_unhash, own_req);
+						     req_unhash, own_req, opt_child_init);
 
 	if (child && *own_req) {
 		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d8201eb3ac5f..18c56b0d7ad5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -124,7 +124,9 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct smc_sock *smc;
 	struct sock *child;
@@ -142,7 +144,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 
 	/* passthrough to original syn recv sock fct */
 	child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash,
-					       own_req);
+					       own_req, opt_child_init);
 	/* child must not inherit smc or its ops */
 	if (child) {
 		rcu_assign_sk_user_data(child, NULL);
-- 
cgit v1.2.3


From f891007ab1c77436950d10e09eae54507f1865ff Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Feb 2026 14:13:37 +0000
Subject: psp: use sk->sk_hash in psp_write_headers()

udp_flow_src_port() is indirectly using sk->sk_txhash as a base,
because __tcp_transmit_skb() uses skb_set_hash_from_sk().

This is problematic because this field can change over the
lifetime of a TCP flow, thanks to calls to sk_rethink_txhash().

Problem is that some NIC might (ab)use the PSP UDP source port in their
RSS computation, and PSP packets for a given flow could jump
from one queue to another.

In order to avoid surprises, it is safer to let Protective Load
Balancing (PLB) get its entropy from the IPv6 flowlabel,
and change psp_write_headers() to use sk->sk_hash which
does not change for the duration of the flow.

We might add a sysctl to select the behavior, if there
is a need for it.

Fixes: fc724515741a ("psp: provide encapsulation helper for drivers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-By: Daniel Zahka <daniel.zahka@gmail.com>
Link: https://patch.msgid.link/20260218141337.999945-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/psp/psp_main.c | 39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/net/psp/psp_main.c b/net/psp/psp_main.c
index a8534124f626..066222eb56c4 100644
--- a/net/psp/psp_main.c
+++ b/net/psp/psp_main.c
@@ -166,9 +166,46 @@ static void psp_write_headers(struct net *net, struct sk_buff *skb, __be32 spi,
 {
 	struct udphdr *uh = udp_hdr(skb);
 	struct psphdr *psph = (struct psphdr *)(uh + 1);
+	const struct sock *sk = skb->sk;
 
 	uh->dest = htons(PSP_DEFAULT_UDP_PORT);
-	uh->source = udp_flow_src_port(net, skb, 0, 0, false);
+
+	/* A bit of theory: Selection of the source port.
+	 *
+	 * We need some entropy, so that multiple flows use different
+	 * source ports for better RSS spreading at the receiver.
+	 *
+	 * We also need that all packets belonging to one TCP flow
+	 * use the same source port through their duration,
+	 * so that all these packets land in the same receive queue.
+	 *
+	 * udp_flow_src_port() is using sk_txhash, inherited from
+	 * skb_set_hash_from_sk() call in __tcp_transmit_skb().
+	 * This field is subject to reshuffling, thanks to
+	 * sk_rethink_txhash() calls in various TCP functions.
+	 *
+	 * Instead, use sk->sk_hash which is constant through
+	 * the whole flow duration.
+	 */
+	if (likely(sk)) {
+		u32 hash = sk->sk_hash;
+		int min, max;
+
+		/* These operations are cheap, no need to cache the result
+		 * in another socket field.
+		 */
+		inet_get_local_port_range(net, &min, &max);
+		/* Since this is being sent on the wire obfuscate hash a bit
+		 * to minimize possibility that any useful information to an
+		 * attacker is leaked. Only upper 16 bits are relevant in the
+		 * computation for 16 bit port value because we use a
+		 * reciprocal divide.
+		 */
+		hash ^= hash << 16;
+		uh->source = htons((((u64)hash * (max - min)) >> 32) + min);
+	} else {
+		uh->source = udp_flow_src_port(net, skb, 0, 0, false);
+	}
 	uh->check = 0;
 	uh->len = htons(udp_len);
 
-- 
cgit v1.2.3


From e1512c1db9e8794d8d130addd2615ec27231d994 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Wed, 18 Feb 2026 02:16:43 +0900
Subject: espintcp: Fix race condition in espintcp_close()

This issue was discovered during a code audit.

After cancel_work_sync() is called from espintcp_close(),
espintcp_tx_work() can still be scheduled from paths such as
the Delayed ACK handler or ksoftirqd.
As a result, the espintcp_tx_work() worker may dereference a
freed espintcp ctx or sk.

The following is a simple race scenario:

           cpu0                             cpu1

  espintcp_close()
    cancel_work_sync(&ctx->work);
                                     espintcp_write_space()
                                       schedule_work(&ctx->work);

To prevent this race condition, cancel_work_sync() is
replaced with disable_work_sync().

Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/aZSie7rEdh9Nu0eM@v4bel
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xfrm/espintcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index bf744ac9d5a7..8709df716e98 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -536,7 +536,7 @@ static void espintcp_close(struct sock *sk, long timeout)
 	sk->sk_prot = &tcp_prot;
 	barrier();
 
-	cancel_work_sync(&ctx->work);
+	disable_work_sync(&ctx->work);
 	strp_done(&ctx->strp);
 
 	skb_queue_purge(&ctx->out_queue);
-- 
cgit v1.2.3


From 64868f5ecadeb359a49bc4485bfa7c497047f13a Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Tue, 17 Feb 2026 17:50:12 +0000
Subject: net: usb: kaweth: remove TX queue manipulation in kaweth_set_rx_mode

kaweth_set_rx_mode(), the ndo_set_rx_mode callback, calls
netif_stop_queue() and netif_wake_queue(). These are TX queue flow
control functions unrelated to RX multicast configuration.

The premature netif_wake_queue() can re-enable TX while tx_urb is still
in-flight, leading to a double usb_submit_urb() on the same URB:

kaweth_start_xmit() {
    netif_stop_queue();
    usb_submit_urb(kaweth->tx_urb);
}

kaweth_set_rx_mode() {
    netif_stop_queue();
    netif_wake_queue();             // wakes TX queue before URB is done
}

kaweth_start_xmit() {
    netif_stop_queue();
    usb_submit_urb(kaweth->tx_urb); // URB submitted while active
}

This triggers the WARN in usb_submit_urb():

  "URB submitted while active"

This is a similar class of bug fixed in rtl8150 by

- commit 958baf5eaee3 ("net: usb: Remove disruptive netif_wake_queue in rtl8150_set_multicast").

Also kaweth_set_rx_mode() is already functionally broken, the
real set_rx_mode action is performed by kaweth_async_set_rx_mode(),
which in turn is not a no-op only at ndo_open() time.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Link: https://patch.msgid.link/20260217175012.1234494-1-n7l8m4@u.northwestern.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kaweth.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index c9efb7df892e..e01d14f6c366 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -765,7 +765,6 @@ static void kaweth_set_rx_mode(struct net_device *net)
 
 	netdev_dbg(net, "Setting Rx mode to %d\n", packet_filter_bitmap);
 
-	netif_stop_queue(net);
 
 	if (net->flags & IFF_PROMISC) {
 		packet_filter_bitmap |= KAWETH_PACKET_FILTER_PROMISCUOUS;
@@ -775,7 +774,6 @@ static void kaweth_set_rx_mode(struct net_device *net)
 	}
 
 	kaweth->packet_filter_bitmap = packet_filter_bitmap;
-	netif_wake_queue(net);
 }
 
 /****************************************************************
-- 
cgit v1.2.3


From f1e2f0ce704e4a14e3f367d3b97d3dd2d8e183b7 Mon Sep 17 00:00:00 2001
From: Martin Pålsson <martin@poleshift.se>
Date: Wed, 18 Feb 2026 05:28:22 +0000
Subject: net: usb: lan78xx: scan all MDIO addresses on LAN7801
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The LAN7801 is designed exclusively for external PHYs (unlike the
LAN7800/LAN7850 which have internal PHYs), but lan78xx_mdio_init()
restricts PHY scanning to MDIO addresses 0-7 by setting phy_mask to
~(0xFF). This prevents discovery of external PHYs wired to addresses
outside that range.

One such case is the DP83TC814 100BASE-T1 PHY, which is typically
configured at MDIO address 10 via PHYAD bootstrap pins and goes
undetected with the current mask.

Remove the restrictive phy_mask assignment for the LAN7801 so that the
default mask of 0 applies, allowing all 32 MDIO addresses to be
scanned during bus registration.

Fixes: 02dc1f3d613d ("lan78xx: add LAN7801 MAC only support")
Signed-off-by: Martin Pålsson <martin@poleshift.se>
Link: https://patch.msgid.link/0110019c6f388aff-98d99cf0-4425-4fff-b16b-dea5ad8fafe0-000000@eu-north-1.amazonses.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 00397a807393..065588c9cfa6 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2094,8 +2094,6 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev)
 		dev->mdiobus->phy_mask = ~(1 << 1);
 		break;
 	case ID_REV_CHIP_ID_7801_:
-		/* scan thru PHYAD[2..0] */
-		dev->mdiobus->phy_mask = ~(0xFF);
 		break;
 	}
 
-- 
cgit v1.2.3


From bfd264fbbbca7a39ea430d7bc2baf8ee2ea958e4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 18 Feb 2026 18:05:51 +0200
Subject: net: dsa: sja1105: protect link replay helpers against NULL phylink
 instance

There is a crash when unbinding the sja1105 driver under special
circumstances:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030
Call trace:
phylink_run_resolve_and_disable+0x10/0x90
sja1105_static_config_reload+0xc0/0x410
sja1105_vlan_filtering+0x100/0x140
dsa_port_vlan_filtering+0x13c/0x368
dsa_port_reset_vlan_filtering.isra.0+0xe8/0x198
dsa_port_bridge_leave+0x130/0x248
dsa_user_changeupper.part.0+0x74/0x158
dsa_user_netdevice_event+0x50c/0xa50
notifier_call_chain+0x78/0x148
raw_notifier_call_chain+0x20/0x38
call_netdevice_notifiers_info+0x58/0xa8
__netdev_upper_dev_unlink+0xac/0x220
netdev_upper_dev_unlink+0x38/0x70
del_nbp+0x1a4/0x320
br_del_if+0x3c/0xd8
br_device_event+0xf8/0x2d8
notifier_call_chain+0x78/0x148
raw_notifier_call_chain+0x20/0x38
call_netdevice_notifiers_info+0x58/0xa8
unregister_netdevice_many_notify+0x314/0x848
unregister_netdevice_queue+0xe8/0xf8
dsa_user_destroy+0x50/0xa8
dsa_port_teardown+0x80/0x98
dsa_switch_teardown_ports+0x4c/0xb8
dsa_switch_deinit+0x94/0xb8
dsa_switch_put_tree+0x2c/0xc0
dsa_unregister_switch+0x38/0x60
sja1105_remove+0x24/0x40
spi_remove+0x38/0x60
device_remove+0x54/0x90
device_release_driver_internal+0x1d4/0x230
device_driver_detach+0x20/0x38
unbind_store+0xbc/0xc8
---[ end trace 0000000000000000 ]---

which requires an explanation.

When a port offloads a bridge, the switch must be reset to change
the VLAN awareness state (the SJA1105_VLAN_FILTERING reason for
sja1105_static_config_reload()). When the port leaves a VLAN-aware
bridge, it must also be reset for the same reason: it is returning
to operation as a VLAN-unaware standalone port.

sja1105_static_config_reload() triggers the phylink link replay helpers.

Because sja1105 is a switch, it has multiple user ports. During unbind,
ports are torn down one by one in dsa_switch_teardown_ports() ->
dsa_port_teardown() -> dsa_user_destroy().

The crash happens when the first user port is not part of the VLAN-aware
bridge, but any other user port is.

Tearing down the first user port causes phylink_destroy() to be called
on dp->pl, and this pointer to be set to NULL. Then, when the second
user port is torn down, this was offloading a VLAN-aware bridge port, so
indirectly it will trigger sja1105_static_config_reload().

The latter function iterates using dsa_switch_for_each_available_port(),
and unconditionally dereferences dp->pl, including for the
aforementioned torn down previous port, and passes that to phylink.
This is where the NULL pointer is coming from.

There are multiple levels at which this could be avoided:
- add an "if (dp->pl)" in sja1105_static_config_reload()
- make the phylink replay helpers NULL-tolerant
- mark ports as DSA_PORT_TYPE_UNUSED after dsa_port_phylink_destroy()
  has run, such that subsequent dsa_switch_for_each_available_port()
  iterations skip them
- disconnect the entire switch at once from switchdev and
  NETDEV_CHANGEUPPER events while unbinding, not just port by port,
  likely using a "ds->unbinding = true" mechanism or similar

however options 3 and 4 are quite heavy and might have side effects.
Although 2 allows to keep the driver simpler, the phylink API it not
NULL-tolerant in general and is not responsible for the NULL pointer
(this is something done by dsa_port_phylink_destroy()). So I went
with 1.

Functionally speaking, skipping the replay helpers for ports without
a phylink instance is fine, because that only happens during driver
removal (an operation which cannot be cancelled). The ports are not
required to work (although they probably still will - untested
assumption - as long as we don't overwrite the last port speed with
SJA1105_SPEED_AUTO).

Fixes: 0b2edc531e0b ("net: dsa: sja1105: let phylink help with the replay of link callbacks")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260218160551.194782-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 71a817c07a90..94d17b06da40 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2278,6 +2278,12 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	 * change it through the dynamic interface later.
 	 */
 	dsa_switch_for_each_available_port(dp, ds) {
+		/* May be called during unbind when we unoffload a VLAN-aware
+		 * bridge from port 1 while port 0 was already torn down
+		 */
+		if (!dp->pl)
+			continue;
+
 		phylink_replay_link_begin(dp->pl);
 		mac[dp->index].speed = priv->info->port_speed[SJA1105_SPEED_AUTO];
 	}
@@ -2334,7 +2340,8 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 	}
 
 	dsa_switch_for_each_available_port(dp, ds)
-		phylink_replay_link_end(dp->pl);
+		if (dp->pl)
+			phylink_replay_link_end(dp->pl);
 
 	rc = sja1105_reload_cbs(priv);
 	if (rc < 0)
-- 
cgit v1.2.3


From f6a495484a27150fb85f943e1a7464da88c2a797 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Thu, 19 Feb 2026 16:10:01 -0600
Subject: proc: Fix pointer error dereference

The function try_lookup_noperm() can return an error pointer. Add check
for error pointer.

Detected by Smatch:
fs/proc/base.c:2148 proc_fill_cache() error:
'child' dereferencing possible ERR_PTR()

Fixes: 1df98b8bbcca ("proc_fill_cache(): clean up, get rid of pointless find_inode_number() use")
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Link: https://patch.msgid.link/20260219221001.1117135-1-ethantidmore06@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/proc/base.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4eec684baca9..4c863d17dfb4 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2128,6 +2128,9 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 	ino_t ino = 1;
 
 	child = try_lookup_noperm(&qname, dir);
+	if (IS_ERR(child))
+		goto end_instantiate;
+
 	if (!child) {
 		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);
-- 
cgit v1.2.3


From 0d195d3b205ca90db30d70d09d7bb6909aac178f Mon Sep 17 00:00:00 2001
From: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Date: Fri, 20 Feb 2026 12:39:37 +0100
Subject: drbd: fix null-pointer dereference on local read error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to
__req_mod() with a NULL peer_device:

  __req_mod(req, what, NULL, &m);

The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this
NULL peer_device to drbd_set_out_of_sync(), which dereferences it,
causing a null-pointer dereference.

Fix this by obtaining the peer_device via first_peer_device(device),
matching how drbd_req_destroy() handles the same situation.

Cc: stable@vger.kernel.org
Reported-by: Tuo Li <islituo@gmail.com>
Link: https://lore.kernel.org/linux-block/20260104165355.151864-1-islituo@gmail.com
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_req.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d15826f6ee81..70f75ef07945 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -621,7 +621,8 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		break;
 
 	case READ_COMPLETED_WITH_ERROR:
-		drbd_set_out_of_sync(peer_device, req->i.sector, req->i.size);
+		drbd_set_out_of_sync(first_peer_device(device),
+				req->i.sector, req->i.size);
 		drbd_report_io_error(device, req);
 		__drbd_chk_io_error(device, DRBD_READ_ERROR);
 		fallthrough;
-- 
cgit v1.2.3


From 9b8eeccd7110d10f9c1b1aa456f5efac23e4e383 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Thu, 19 Feb 2026 11:24:00 -0800
Subject: MAINTAINERS: update enic and usnic maintainers

Remove Christian Benvenuti from the enic/usnic maintainer lists because he
is no longer working on the drivers and the email address is no longer valid.
Keep Satish Kharat as the enic maintainer and the usnic co-maintainer.

Signed-off-by: Satish Kharat <satishkh@cisco.com>
Acked-by: Leon Romanovsky <leon@kernel.org>
Link: https://patch.msgid.link/20260219-enic-maintainers-update-v2-v1-1-c58aa11c2ea8@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index b8d8a5c41597..c00b5f5d4203 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6219,14 +6219,13 @@ S:	Supported
 F:	drivers/scsi/snic/
 
 CISCO VIC ETHERNET NIC DRIVER
-M:	Christian Benvenuti <benve@cisco.com>
 M:	Satish Kharat <satishkh@cisco.com>
 S:	Maintained
 F:	drivers/net/ethernet/cisco/enic/
 
 CISCO VIC LOW LATENCY NIC DRIVER
-M:	Christian Benvenuti <benve@cisco.com>
 M:	Nelson Escobar <neescoba@cisco.com>
+M:	Satish Kharat <satishkh@cisco.com>
 S:	Supported
 F:	drivers/infiniband/hw/usnic/
 
-- 
cgit v1.2.3


From 2bb995e6155cb4f254574598cbd6fe1dcc99766a Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 18 Feb 2026 16:56:00 -0800
Subject: net: phy: qcom: qca807x: normalize return value of gpio_get

The GPIO get callback is expected to return 0 or 1 (or a negative error
code). Ensure that the value returned by qca807x_gpio_get() is
normalized to the [0, 1] range.

Fixes: 86ef402d805d ("gpiolib: sanitize the return value of gpio_chip::get()")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/aZZeyr2ysqqk2GqA@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index d8f1ce5a7128..6004da5741af 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -375,7 +375,7 @@ static int qca807x_gpio_get(struct gpio_chip *gc, unsigned int offset)
 	reg = QCA807X_MMD7_LED_FORCE_CTRL(offset);
 	val = phy_read_mmd(priv->phy, MDIO_MMD_AN, reg);
 
-	return FIELD_GET(QCA807X_GPIO_FORCE_MODE_MASK, val);
+	return !!FIELD_GET(QCA807X_GPIO_FORCE_MODE_MASK, val);
 }
 
 static int qca807x_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)
-- 
cgit v1.2.3


From 594163ea88a03bdb412063af50fc7177ef3cbeae Mon Sep 17 00:00:00 2001
From: Linus Walleij <linusw@kernel.org>
Date: Thu, 19 Feb 2026 12:38:50 +0100
Subject: net: ethernet: xscale: Check for PTP support properly

In ixp4xx_get_ts_info() ixp46x_ptp_find() is called
unconditionally despite this feature only existing on
ixp46x, leading to the following splat from tcpdump:

root@OpenWrt:~# tcpdump -vv -X -i eth0
(...)
Unable to handle kernel NULL pointer dereference at virtual address
  00000238 when read
(...)
Call trace:
 ptp_clock_index from ixp46x_ptp_find+0x1c/0x38
 ixp46x_ptp_find from ixp4xx_get_ts_info+0x4c/0x64
 ixp4xx_get_ts_info from __ethtool_get_ts_info+0x90/0x108
 __ethtool_get_ts_info from __dev_ethtool+0xa00/0x2648
 __dev_ethtool from dev_ethtool+0x160/0x234
 dev_ethtool from dev_ioctl+0x2cc/0x460
 dev_ioctl from sock_ioctl+0x1ec/0x524
 sock_ioctl from sys_ioctl+0x51c/0xa94
 sys_ioctl from ret_fast_syscall+0x0/0x44
 (...)
Segmentation fault

Check for ixp46x in ixp46x_ptp_find() before trying to set up
PTP to avoid this.

To avoid altering the returned error code from ixp4xx_hwtstamp_set()
which before this patch was -EOPNOTSUPP, we return -EOPNOTSUPP
from ixp4xx_hwtstamp_set() if ixp46x_ptp_find() fails no matter
the error code. The helper function ixp46x_ptp_find() helper
returns -ENODEV.

Fixes: 9055a2f59162 ("ixp4xx_eth: make ptp support a platform driver")
Signed-off-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260219-ixp4xx-fix-ethernet-v3-1-f235ccc3cd46@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xscale/ixp4xx_eth.c | 5 +----
 drivers/net/ethernet/xscale/ptp_ixp46x.c | 3 +++
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index e1e7f65553e7..b0faa0f1780d 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -403,15 +403,12 @@ static int ixp4xx_hwtstamp_set(struct net_device *netdev,
 	int ret;
 	int ch;
 
-	if (!cpu_is_ixp46x())
-		return -EOPNOTSUPP;
-
 	if (!netif_running(netdev))
 		return -EINVAL;
 
 	ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index);
 	if (ret)
-		return ret;
+		return -EOPNOTSUPP;
 
 	ch = PORT2CHANNEL(port);
 	regs = port->timesync_regs;
diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c
index 94203eb46e6b..93c64db22a69 100644
--- a/drivers/net/ethernet/xscale/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@@ -232,6 +232,9 @@ static struct ixp_clock ixp_clock;
 
 int ixp46x_ptp_find(struct ixp46x_ts_regs *__iomem *regs, int *phc_index)
 {
+	if (!cpu_is_ixp46x())
+		return -ENODEV;
+
 	*regs = ixp_clock.regs;
 	*phc_index = ptp_clock_index(ixp_clock.ptp_clock);
 
-- 
cgit v1.2.3


From 470c7ca2b4c3e3a51feeb952b7f97a775b5c49cd Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Thu, 19 Feb 2026 17:31:31 +0000
Subject: udplite: Fix null-ptr-deref in __udp_enqueue_schedule_skb().

syzbot reported null-ptr-deref of udp_sk(sk)->udp_prod_queue. [0]

Since the cited commit, udp_lib_init_sock() can fail, as can
udp_init_sock() and udpv6_init_sock().

Let's handle the error in udplite_sk_init() and udplitev6_sk_init().

[0]:
BUG: KASAN: null-ptr-deref in instrument_atomic_read include/linux/instrumented.h:82 [inline]
BUG: KASAN: null-ptr-deref in atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
BUG: KASAN: null-ptr-deref in __udp_enqueue_schedule_skb+0x151/0x1480 net/ipv4/udp.c:1719
Read of size 4 at addr 0000000000000008 by task syz.2.18/2944

CPU: 1 UID: 0 PID: 2944 Comm: syz.2.18 Not tainted syzkaller #0 PREEMPTLAZY
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
Call Trace:
 <IRQ>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 kasan_report+0xa2/0xe0 mm/kasan/report.c:595
 check_region_inline mm/kasan/generic.c:-1 [inline]
 kasan_check_range+0x264/0x2c0 mm/kasan/generic.c:200
 instrument_atomic_read include/linux/instrumented.h:82 [inline]
 atomic_read include/linux/atomic/atomic-instrumented.h:32 [inline]
 __udp_enqueue_schedule_skb+0x151/0x1480 net/ipv4/udp.c:1719
 __udpv6_queue_rcv_skb net/ipv6/udp.c:795 [inline]
 udpv6_queue_rcv_one_skb+0xa2e/0x1ad0 net/ipv6/udp.c:906
 udp6_unicast_rcv_skb+0x227/0x380 net/ipv6/udp.c:1064
 ip6_protocol_deliver_rcu+0xe17/0x1540 net/ipv6/ip6_input.c:438
 ip6_input_finish+0x191/0x350 net/ipv6/ip6_input.c:489
 NF_HOOK+0x354/0x3f0 include/linux/netfilter.h:318
 ip6_input+0x16c/0x2b0 net/ipv6/ip6_input.c:500
 NF_HOOK+0x354/0x3f0 include/linux/netfilter.h:318
 __netif_receive_skb_one_core net/core/dev.c:6149 [inline]
 __netif_receive_skb+0xd3/0x370 net/core/dev.c:6262
 process_backlog+0x4d6/0x1160 net/core/dev.c:6614
 __napi_poll+0xae/0x320 net/core/dev.c:7678
 napi_poll net/core/dev.c:7741 [inline]
 net_rx_action+0x60d/0xdc0 net/core/dev.c:7893
 handle_softirqs+0x209/0x8d0 kernel/softirq.c:622
 do_softirq+0x52/0x90 kernel/softirq.c:523
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0xe7/0x120 kernel/softirq.c:450
 local_bh_enable include/linux/bottom_half.h:33 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:924 [inline]
 __dev_queue_xmit+0x109c/0x2dc0 net/core/dev.c:4856
 __ip6_finish_output net/ipv6/ip6_output.c:-1 [inline]
 ip6_finish_output+0x158/0x4e0 net/ipv6/ip6_output.c:219
 NF_HOOK_COND include/linux/netfilter.h:307 [inline]
 ip6_output+0x342/0x580 net/ipv6/ip6_output.c:246
 ip6_send_skb+0x1d7/0x3c0 net/ipv6/ip6_output.c:1984
 udp_v6_send_skb+0x9a5/0x1770 net/ipv6/udp.c:1442
 udp_v6_push_pending_frames+0xa2/0x140 net/ipv6/udp.c:1469
 udpv6_sendmsg+0xfe0/0x2830 net/ipv6/udp.c:1759
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg+0xe5/0x270 net/socket.c:742
 __sys_sendto+0x3eb/0x580 net/socket.c:2206
 __do_sys_sendto net/socket.c:2213 [inline]
 __se_sys_sendto net/socket.c:2209 [inline]
 __x64_sys_sendto+0xde/0x100 net/socket.c:2209
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd2/0xf20 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f67b4d9c629
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f67b5c98028 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f67b5015fa0 RCX: 00007f67b4d9c629
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007f67b4e32b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000040000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f67b5016038 R14: 00007f67b5015fa0 R15: 00007ffe3cb66dd8
 </TASK>

Fixes: b650bf0977d3 ("udp: remove busylock and add per NUMA queues")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260219173142.310741-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udplite.c | 3 +--
 net/ipv6/udplite.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index d3e621a11a1a..826e9e79eb19 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -20,10 +20,9 @@ EXPORT_SYMBOL(udplite_table);
 /* Designate sk as UDP-Lite socket */
 static int udplite_sk_init(struct sock *sk)
 {
-	udp_init_sock(sk);
 	pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
 		     "please contact the netdev mailing list\n");
-	return 0;
+	return udp_init_sock(sk);
 }
 
 static int udplite_rcv(struct sk_buff *skb)
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 2cec542437f7..e867721cda4d 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -16,10 +16,9 @@
 
 static int udplitev6_sk_init(struct sock *sk)
 {
-	udpv6_init_sock(sk);
 	pr_warn_once("UDP-Lite is deprecated and scheduled to be removed in 2025, "
 		     "please contact the netdev mailing list\n");
-	return 0;
+	return udpv6_init_sock(sk);
 }
 
 static int udplitev6_rcv(struct sk_buff *skb)
-- 
cgit v1.2.3


From e123d9302d223767bd910bfbcfe607bae909f8ac Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:11 -0800
Subject: bnxt_en: Fix RSS context delete logic

We need to free the corresponding RSS context VNIC
in FW everytime an RSS context is deleted in driver.
Commit 667ac333dbb7 added a check to delete the VNIC
in FW only when netif_running() is true to help delete
RSS contexts with interface down.

Having that condition will make the driver leak VNICs
in FW whenever close() happens with active RSS contexts.
On the subsequent open(), as part of RSS context restoration,
we will end up trying to create extra VNICs for which we
did not make any reservation. FW can fail this request,
thereby making us lose active RSS contexts.

Suppose an RSS context is deleted already and we try to
process a delete request again, then the HWRM functions
will check for validity of the request and they simply
return if the resource is already freed. So, even for
delete-when-down cases, netif_running() check is not
necessary.

Remove the netif_running() condition check when deleting
an RSS context.

Reported-by: Jakub Kicinski <kicinski@meta.com>
Fixes: 667ac333dbb7 ("eth: bnxt: allow deleting RSS contexts when the device is down")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fb45e1dd1dd7..7768d9753e2d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10889,12 +10889,10 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	struct bnxt_ntuple_filter *ntp_fltr;
 	int i;
 
-	if (netif_running(bp->dev)) {
-		bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
-		for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
-			if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
-				bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
-		}
+	bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
+	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
+		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
+			bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
 	}
 	if (!all)
 		return;
-- 
cgit v1.2.3


From c1bbd9900d65ac65b9fce9f129e3369a04871570 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:12 -0800
Subject: bnxt_en: Fix deleting of Ntuple filters

Ntuple filters can be deleted when the interface
is down. The current code blindly sends the filter
delete command to FW. When the interface is down, all
the VNICs are deleted in the FW. When the VNIC is
freed in the FW, all the associated filters are also
freed. We need not send the free command explicitly.
Sending such command will generate FW error in the
dmesg.

In order to fix this, we can safely return from
bnxt_hwrm_cfa_ntuple_filter_free() when BNXT_STATE_OPEN
is not true which confirms the VNICs have been deleted.

Fixes: 8336a974f37d ("bnxt_en: Save user configured filters in a lookup list")
Suggested-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7768d9753e2d..8c73a723d23f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6240,6 +6240,9 @@ int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 	int rc;
 
 	set_bit(BNXT_FLTR_FW_DELETED, &fltr->base.state);
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state))
+		return 0;
+
 	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
 	if (rc)
 		return rc;
-- 
cgit v1.2.3


From ce5a0f4612dbacc805fe16719f9f6bd18352b70d Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Thu, 19 Feb 2026 10:53:13 -0800
Subject: selftests: drv-net: rss_ctx: test RSS contexts persist after
 ifdown/up

Add a test to verify that RSS contexts persist across interface
down/up along with their associated Ntuple filters. Another test
that creates contexts/rules keeping interface down and test their
persistence is also added.

Tested on bnxt_en:

 TAP version 13
 1..1
 # timeout set to 0
 # selftests: drivers/net/hw: rss_ctx.py
 # TAP version 13
 # 1..2
 # ok 1 rss_ctx.test_rss_context_persist_create_and_ifdown
 # ok 2 rss_ctx.test_rss_context_persist_ifdown_and_create # SKIP Create context not supported with interface down
 # # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:1 error:0

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260219185313.2682148-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 100 +++++++++++++++++++++-
 1 file changed, 98 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ed7e405682f0..b9b7527c2c6b 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -4,13 +4,15 @@
 import datetime
 import random
 import re
+import time
 from lib.py import ksft_run, ksft_pr, ksft_exit
 from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import ksft_disruptive
 from lib.py import rand_port
-from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
+from lib.py import cmd, ethtool, ip, defer, GenerateTraffic, CmdExitFailure, wait_file
 
 
 def _rss_key_str(key):
@@ -809,6 +811,98 @@ def test_rss_default_context_rule(cfg):
                           'noise' : (0, 1) })
 
 
+@ksft_disruptive
+def test_rss_context_persist_ifupdown(cfg, pre_down=False):
+    """
+    Test that RSS contexts and their associated ntuple filters persist across
+    an interface down/up cycle.
+
+    """
+
+    require_ntuple(cfg)
+
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 6:
+        try:
+            ethtool(f"-L {cfg.ifname} combined 6")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except Exception as exc:
+            raise KsftSkipEx("Not enough queues for the test") from exc
+
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    ifup = defer(ip, f"link set dev {cfg.ifname} up")
+    if pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+
+    try:
+        ctx1_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+        defer(ethtool, f"-X {cfg.ifname} context {ctx1_id} delete")
+    except CmdExitFailure as exc:
+        raise KsftSkipEx("Create context not supported with interface down") from exc
+
+    ctx2_id = ethtool_create(cfg, "-X", "context new start 4 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx2_id} delete")
+
+    port_ctx2 = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_ctx2} context {ctx2_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    if not pre_down:
+        ip(f"link set dev {cfg.ifname} down")
+    ifup.exec()
+
+    wait_file(f"/sys/class/net/{cfg.ifname}/carrier",
+        lambda x: x.strip() == "1", deadline=20)
+
+    remote_addr = cfg.remote_addr_v[cfg.addr_ipver]
+    for _ in range(10):
+        if cmd(f"ping -c 1 -W 1 {remote_addr}", fail=False).ret == 0:
+            break
+        time.sleep(1)
+    else:
+        raise KsftSkipEx("Cannot reach remote host after interface up")
+
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True)
+
+    data1 = [c for c in ctxs if c.get('context') == ctx1_id]
+    ksft_eq(len(data1), 1, f"Context {ctx1_id} should persist after ifup")
+
+    data2 = [c for c in ctxs if c.get('context') == ctx2_id]
+    ksft_eq(len(data2), 1, f"Context {ctx2_id} should persist after ifup")
+
+    _ntuple_rule_check(cfg, ntuple_id, ctx2_id)
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    main_traffic = sum(cnts[0:2])
+    ksft_ge(main_traffic, 18000, f"Main context traffic distribution: {cnts}")
+    ksft_lt(sum(cnts[2:6]), 500, f"Other context queues should be mostly empty: {cnts}")
+
+    _send_traffic_check(cfg, port_ctx2, f"context {ctx2_id}",
+                        {'target': (4, 5),
+                         'noise': (0, 1),
+                         'empty': (2, 3)})
+
+
+def test_rss_context_persist_create_and_ifdown(cfg):
+    """
+    Create RSS contexts then cycle the interface down and up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=False)
+
+
+def test_rss_context_persist_ifdown_and_create(cfg):
+    """
+    Bring interface down first, then create RSS contexts and bring up.
+    """
+    test_rss_context_persist_ifupdown(cfg, pre_down=True)
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.context_cnt = None
@@ -823,7 +917,9 @@ def main() -> None:
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
                   test_flow_add_context_missing,
                   test_delete_rss_context_busy, test_rss_ntuple_addition,
-                  test_rss_default_context_rule],
+                  test_rss_default_context_rule,
+                  test_rss_context_persist_create_and_ifdown,
+                  test_rss_context_persist_ifdown_and_create],
                  args=(cfg, ))
     ksft_exit()
 
-- 
cgit v1.2.3


From d4f687fbbce45b5e88438e89b5e26c0c15847992 Mon Sep 17 00:00:00 2001
From: Ralf Lici <ralf@mandelbit.com>
Date: Wed, 18 Feb 2026 21:08:26 +0100
Subject: ovpn: tcp - fix packet extraction from stream

When processing TCP stream data in ovpn_tcp_recv, we receive large
cloned skbs from __strp_rcv that may contain multiple coalesced packets.
The current implementation has two bugs:

1. Header offset overflow: Using pskb_pull with large offsets on
   coalesced skbs causes skb->data - skb->head to exceed the u16 storage
   of skb->network_header. This causes skb_reset_network_header to fail
   on the inner decapsulated packet, resulting in packet drops.

2. Unaligned protocol headers: Extracting packets from arbitrary
   positions within the coalesced TCP stream provides no alignment
   guarantees for the packet data causing performance penalties on
   architectures without efficient unaligned access. Additionally,
   openvpn's 2-byte length prefix on TCP packets causes the subsequent
   4-byte opcode and packet ID fields to be inherently misaligned.

Fix both issues by allocating a new skb for each openvpn packet and
using skb_copy_bits to extract only the packet content into the new
buffer, skipping the 2-byte length prefix. Also, check the length before
invoking the function that performs the allocation to avoid creating an
invalid skb.

If the packet has to be forwarded to userspace the 2-byte prefix can be
pushed to the head safely, without misalignment.

As a side effect, this approach also avoids the expensive linearization
that pskb_pull triggers on cloned skbs with page fragments. In testing,
this resulted in TCP throughput improvements of up to 74%.

Fixes: 11851cbd60ea ("ovpn: implement TCP transport")
Signed-off-by: Ralf Lici <ralf@mandelbit.com>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ovpn/tcp.c | 53 ++++++++++++++++++++++++++++++++++----------------
 1 file changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
index ec2bbc28c196..5499c1572f3e 100644
--- a/drivers/net/ovpn/tcp.c
+++ b/drivers/net/ovpn/tcp.c
@@ -70,37 +70,56 @@ static void ovpn_tcp_to_userspace(struct ovpn_peer *peer, struct sock *sk,
 	peer->tcp.sk_cb.sk_data_ready(sk);
 }
 
-static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
+static struct sk_buff *ovpn_tcp_skb_packet(const struct ovpn_peer *peer,
+					   struct sk_buff *orig_skb,
+					   const int pkt_len, const int pkt_off)
 {
-	struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp);
-	struct strp_msg *msg = strp_msg(skb);
-	size_t pkt_len = msg->full_len - 2;
-	size_t off = msg->offset + 2;
-	u8 opcode;
+	struct sk_buff *ovpn_skb;
+	int err;
 
-	/* ensure skb->data points to the beginning of the openvpn packet */
-	if (!pskb_pull(skb, off)) {
-		net_warn_ratelimited("%s: packet too small for peer %u\n",
-				     netdev_name(peer->ovpn->dev), peer->id);
+	/* create a new skb with only the content of the current packet */
+	ovpn_skb = netdev_alloc_skb(peer->ovpn->dev, pkt_len);
+	if (unlikely(!ovpn_skb))
 		goto err;
-	}
 
-	/* strparser does not trim the skb for us, therefore we do it now */
-	if (pskb_trim(skb, pkt_len) != 0) {
-		net_warn_ratelimited("%s: trimming skb failed for peer %u\n",
+	skb_copy_header(ovpn_skb, orig_skb);
+	err = skb_copy_bits(orig_skb, pkt_off, skb_put(ovpn_skb, pkt_len),
+			    pkt_len);
+	if (unlikely(err)) {
+		net_warn_ratelimited("%s: skb_copy_bits failed for peer %u\n",
 				     netdev_name(peer->ovpn->dev), peer->id);
+		kfree_skb(ovpn_skb);
 		goto err;
 	}
 
-	/* we need the first 4 bytes of data to be accessible
+	consume_skb(orig_skb);
+	return ovpn_skb;
+err:
+	kfree_skb(orig_skb);
+	return NULL;
+}
+
+static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp);
+	struct strp_msg *msg = strp_msg(skb);
+	int pkt_len = msg->full_len - 2;
+	u8 opcode;
+
+	/* we need at least 4 bytes of data in the packet
 	 * to extract the opcode and the key ID later on
 	 */
-	if (!pskb_may_pull(skb, OVPN_OPCODE_SIZE)) {
+	if (unlikely(pkt_len < OVPN_OPCODE_SIZE)) {
 		net_warn_ratelimited("%s: packet too small to fetch opcode for peer %u\n",
 				     netdev_name(peer->ovpn->dev), peer->id);
 		goto err;
 	}
 
+	/* extract the packet into a new skb */
+	skb = ovpn_tcp_skb_packet(peer, skb, pkt_len, msg->offset + 2);
+	if (unlikely(!skb))
+		goto err;
+
 	/* DATA_V2 packets are handled in kernel, the rest goes to user space */
 	opcode = ovpn_opcode_from_skb(skb, 0);
 	if (unlikely(opcode != OVPN_DATA_V2)) {
@@ -113,7 +132,7 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
 		/* The packet size header must be there when sending the packet
 		 * to userspace, therefore we put it back
 		 */
-		skb_push(skb, 2);
+		*(__be16 *)__skb_push(skb, sizeof(u16)) = htons(pkt_len);
 		ovpn_tcp_to_userspace(peer, strp->sk, skb);
 		return;
 	}
-- 
cgit v1.2.3


From 97d5c8f5c09a604c4873c8348f58de3cea69a7df Mon Sep 17 00:00:00 2001
From: Tomasz Pakuła <tomasz.pakula.oficjalny@gmail.com>
Date: Wed, 4 Feb 2026 22:44:55 +0100
Subject: HID: pidff: Fix condition effect bit clearing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As reported by MPDarkGuy on discord, NULL pointer dereferences were
happening because not all the conditional effects bits were cleared.

Properly clear all conditional effect bits from ffbit

Fixes: 7f3d7bc0df4b ("HID: pidff: Better quirk assigment when searching for fields")
Cc: stable@vger.kernel.org # 6.18.x
Signed-off-by: Tomasz Pakuła <tomasz.pakula.oficjalny@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/usbhid/hid-pidff.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c
index a4e700b40ba9..56d6af39ba81 100644
--- a/drivers/hid/usbhid/hid-pidff.c
+++ b/drivers/hid/usbhid/hid-pidff.c
@@ -1452,10 +1452,13 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 		hid_warn(pidff->hid, "unknown ramp effect layout\n");
 
 	if (PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) {
-		if (test_and_clear_bit(FF_SPRING, dev->ffbit)   ||
-		    test_and_clear_bit(FF_DAMPER, dev->ffbit)   ||
-		    test_and_clear_bit(FF_FRICTION, dev->ffbit) ||
-		    test_and_clear_bit(FF_INERTIA, dev->ffbit))
+		bool test = false;
+
+		test |= test_and_clear_bit(FF_SPRING, dev->ffbit);
+		test |= test_and_clear_bit(FF_DAMPER, dev->ffbit);
+		test |= test_and_clear_bit(FF_FRICTION, dev->ffbit);
+		test |= test_and_clear_bit(FF_INERTIA, dev->ffbit);
+		if (test)
 			hid_warn(pidff->hid, "unknown condition effect layout\n");
 	}
 
-- 
cgit v1.2.3


From cfc83a3c71517b59c1047db57da31e26a9dc2f33 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Mon, 16 Feb 2026 11:20:29 +0100
Subject: batman-adv: Avoid double-rtnl_lock ELP metric worker
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

batadv_v_elp_get_throughput() might be called when the RTNL lock is already
held. This could be problematic when the work queue item is cancelled via
cancel_delayed_work_sync() in batadv_v_elp_iface_disable(). In this case,
an rtnl_lock() would cause a deadlock.

To avoid this, rtnl_trylock() was used in this function to skip the
retrieval of the ethtool information in case the RTNL lock was already
held.

But for cfg80211 interfaces, batadv_get_real_netdev() was called - which
also uses rtnl_lock(). The approach for __ethtool_get_link_ksettings() must
also be used instead and the lockless version __batadv_get_real_netdev()
has to be called.

Cc: stable@vger.kernel.org
Fixes: 8c8ecc98f5c6 ("batman-adv: Drop unmanaged ELP metric worker")
Reported-by: Christian Schmidbauer <github@grische.xyz>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Tested-by: Sören Skaarup <freifunk_nordm4nn@gmx.de>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_v_elp.c      | 10 +++++++++-
 net/batman-adv/hard-interface.c |  8 ++++----
 net/batman-adv/hard-interface.h |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index cb16c1ed2a58..fe832093d421 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh,
 			/* unsupported WiFi driver version */
 			goto default_throughput;
 
-		real_netdev = batadv_get_real_netdev(hard_iface->net_dev);
+		/* only use rtnl_trylock because the elp worker will be cancelled while
+		 * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise
+		 * wait forever when the elp work_item was started and it is then also
+		 * trying to rtnl_lock
+		 */
+		if (!rtnl_trylock())
+			return false;
+		real_netdev = __batadv_get_real_netdev(hard_iface->net_dev);
+		rtnl_unlock();
 		if (!real_netdev)
 			goto default_throughput;
 
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 5113f879736b..1c488049d554 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev)
 }
 
 /**
- * batadv_get_real_netdevice() - check if the given netdev struct is a virtual
+ * __batadv_get_real_netdev() - check if the given netdev struct is a virtual
  *  interface on top of another 'real' interface
  * @netdev: the device to check
  *
@@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev)
  * Return: the 'real' net device or the original net device and NULL in case
  *  of an error.
  */
-static struct net_device *batadv_get_real_netdevice(struct net_device *netdev)
+struct net_device *__batadv_get_real_netdev(struct net_device *netdev)
 {
 	struct batadv_hard_iface *hard_iface = NULL;
 	struct net_device *real_netdev = NULL;
@@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device)
 	struct net_device *real_netdev;
 
 	rtnl_lock();
-	real_netdev = batadv_get_real_netdevice(net_device);
+	real_netdev = __batadv_get_real_netdev(net_device);
 	rtnl_unlock();
 
 	return real_netdev;
@@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device)
 	if (batadv_is_cfg80211_netdev(net_device))
 		wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT;
 
-	real_netdev = batadv_get_real_netdevice(net_device);
+	real_netdev = __batadv_get_real_netdev(net_device);
 	if (!real_netdev)
 		return wifi_flags;
 
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 9db8a310961e..9ba8fb2bdceb 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -67,6 +67,7 @@ enum batadv_hard_if_bcast {
 
 extern struct notifier_block batadv_hard_if_notifier;
 
+struct net_device *__batadv_get_real_netdev(struct net_device *net_device);
 struct net_device *batadv_get_real_netdev(struct net_device *net_device);
 bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface);
 bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface);
-- 
cgit v1.2.3


From 08f97454b7fa39bfcf82524955c771d2d693d6fe Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 22 Feb 2026 13:35:13 +0000
Subject: KVM: arm64: Fix protected mode handling of pages larger than 4kB

Since 3669ddd8fa8b5 ("KVM: arm64: Add a range to pkvm_mappings"),
pKVM tracks the memory that has been mapped into a guest in a
side data structure. Crucially, it uses it to find out whether
a page has already been mapped, and therefore refuses to map it
twice. So far, so good.

However, this very patch completely breaks non-4kB page support,
with guests being unable to boot. The most obvious symptom is that
we take the same fault repeatedly, and not making forward progress.
A quick investigation shows that this is because of the above
rejection code.

As it turns out, there are multiple issues at play:

- while the HPFAR_EL2 register gives you the faulting IPA minus
  the bottom 12 bits, it will still give you the extra bits that
  are part of the page offset for anything larger than 4kB,
  even for a level-3 mapping

- pkvm_pgtable_stage2_map() assumes that the address passed as
  a parameter is aligned to the size of the intended mapping

- the faulting address is only aligned for a non-page mapping

When the planets are suitably aligned (pun intended), the guest
faults on a page by accessing it past the bottom 4kB, and extra bits
get set in the HPFAR_EL2 register. If this results in a page mapping
(which is likely with large granule sizes), nothing aligns it further
down, and pkvm_mapping_iter_first() finds an intersection that
doesn't really exist. We assume this is a spurious fault and return
-EAGAIN. And again...

This doesn't hit outside of the protected code, as the page table
code always aligns the IPA down to a page boundary, hiding the issue
for everyone else.

Fix it by always forcing the alignment on vma_pagesize, irrespective
of the value of vma_pagesize.

Fixes: 3669ddd8fa8b5 ("KVM: arm64: Add a range to pkvm_mappings")
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://https://patch.msgid.link/20260222141000.3084258-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/kvm/mmu.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8c5d259810b2..3952415c4f83 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1753,14 +1753,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	/*
-	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
-	 * ensure we find the right PFN and lay down the mapping in the right
-	 * place.
+	 * Both the canonical IPA and fault IPA must be aligned to the
+	 * mapping size to ensure we find the right PFN and lay down the
+	 * mapping in the right place.
 	 */
-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
-		fault_ipa &= ~(vma_pagesize - 1);
-		ipa &= ~(vma_pagesize - 1);
-	}
+	fault_ipa = ALIGN_DOWN(fault_ipa, vma_pagesize);
+	ipa = ALIGN_DOWN(ipa, vma_pagesize);
 
 	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);
-- 
cgit v1.2.3


From 24ed11ee5bacf9a9aca18fc6b47667c7f38d578b Mon Sep 17 00:00:00 2001
From: Shawn Lin <shawn.lin@rock-chips.com>
Date: Wed, 11 Feb 2026 21:02:37 +0800
Subject: soc: rockchip: grf: Add missing of_node_put() when returning

Fix the smatch checking:
drivers/soc/rockchip/grf.c:249 rockchip_grf_init()
warn: inconsistent refcounting 'np->kobj.kref.refcount.refs.counter':

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: 75fb63ae0312 ("soc: rockchip: grf: Support multiple grf to be handled")
Closes: https://lore.kernel.org/all/aYXvgTcUJWQL2can@stanley.mountain/
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Link: https://patch.msgid.link/1770814957-17762-1-git-send-email-shawn.lin@rock-chips.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/soc/rockchip/grf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/soc/rockchip/grf.c b/drivers/soc/rockchip/grf.c
index 04937c40da47..b459607c118a 100644
--- a/drivers/soc/rockchip/grf.c
+++ b/drivers/soc/rockchip/grf.c
@@ -231,6 +231,7 @@ static int __init rockchip_grf_init(void)
 		grf = syscon_node_to_regmap(np);
 		if (IS_ERR(grf)) {
 			pr_err("%s: could not get grf syscon\n", __func__);
+			of_node_put(np);
 			return PTR_ERR(grf);
 		}
 
-- 
cgit v1.2.3


From 29d1f56c4f3001b7f547123e0a307c009ac717f8 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Tue, 10 Feb 2026 13:01:42 +0100
Subject: Revert "arm64: dts: rockchip: Further describe the WiFi for the
 Pinebook Pro"

This reverts commit 6d54d935062e2d4a7d3f779ceb9eeff108d0535d.

It seems there are different variants of the Wifi chipset in use on the
Pinebook Pro. And according to the reported regression - see Closes
below, the reverted change causes issues with one Wifi chipset.

The original commit message indicates a "further description" only and
does not indicate this would fix an actual problem, so a revert should
not cause further problems.

Fixes: 6d54d935062e ("arm64: dts: rockchip: Further describe the WiFi for the Pinebook Pro")
Cc: Jan Palus <jpalus@fastmail.com>
Cc: Peter Robinson <pbrobinson@gmail.com>
Cc: Thorsten Leemhuis <regressions@leemhuis.info>
Cc: stable@vger.kernel.org
Closes: https://lore.kernel.org/r/aUKOlj-RvTYlrpiS@rock.grzadka/
Tested-by: Jan Palus <jpalus@fastmail.com>
Reviewed-by: Dragan Simic <dsimic@manjaro.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20260210120142.698512-1-heiko@sntech.de
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
index 753d51344954..ae937a3afa11 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
@@ -879,12 +879,6 @@
 		};
 	};
 
-	wifi {
-		wifi_host_wake_l: wifi-host-wake-l {
-			rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>;
-		};
-	};
-
 	wireless-bluetooth {
 		bt_wake_pin: bt-wake-pin {
 			rockchip,pins = <2 RK_PD3 RK_FUNC_GPIO &pcfg_pull_none>;
@@ -942,19 +936,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdio0_bus4 &sdio0_cmd &sdio0_clk>;
 	sd-uhs-sdr104;
-	#address-cells = <1>;
-	#size-cells = <0>;
 	status = "okay";
-
-	brcmf: wifi@1 {
-		compatible = "brcm,bcm4329-fmac";
-		reg = <1>;
-		interrupt-parent = <&gpio0>;
-		interrupts = <RK_PA3 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-names = "host-wake";
-		pinctrl-names = "default";
-		pinctrl-0 = <&wifi_host_wake_l>;
-	};
 };
 
 &sdhci {
-- 
cgit v1.2.3


From 663c28469d3274d6456f206a6671c91493d85ff1 Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Sat, 21 Feb 2026 01:59:44 -0300
Subject: smb: client: fix cifs_pick_channel when channels are equally loaded

cifs_pick_channel uses (start % chan_count) when channels are equally
loaded, but that can return a channel that failed the eligibility
checks.

Drop the fallback and return the scan-selected channel instead. If none
is eligible, keep the existing behavior of using the primary channel.

Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Acked-by: Meetakshi Setiya <msetiya@microsoft.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/transport.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 75697f6d2566..05f8099047e1 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -807,16 +807,21 @@ cifs_cancelled_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 }
 
 /*
- * Return a channel (master if none) of @ses that can be used to send
- * regular requests.
+ * cifs_pick_channel - pick an eligible channel for network operations
  *
- * If we are currently binding a new channel (negprot/sess.setup),
- * return the new incomplete channel.
+ * @ses: session reference
+ *
+ * Select an eligible channel (not terminating and not marked as needing
+ * reconnect), preferring the least loaded one. If no eligible channel is
+ * found, fall back to the primary channel (index 0).
+ *
+ * Return: TCP_Server_Info pointer for the chosen channel, or NULL if @ses is
+ * NULL.
  */
 struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 {
 	uint index = 0;
-	unsigned int min_in_flight = UINT_MAX, max_in_flight = 0;
+	unsigned int min_in_flight = UINT_MAX;
 	struct TCP_Server_Info *server = NULL;
 	int i, start, cur;
 
@@ -846,14 +851,8 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 			min_in_flight = server->in_flight;
 			index = cur;
 		}
-		if (server->in_flight > max_in_flight)
-			max_in_flight = server->in_flight;
 	}
 
-	/* if all channels are equally loaded, fall back to round-robin */
-	if (min_in_flight == max_in_flight)
-		index = (uint)start % ses->chan_count;
-
 	server = ses->chans[index].server;
 	spin_unlock(&ses->chan_lock);
 
-- 
cgit v1.2.3


From 2692c614f8f05929d692b3dbfd3faef1f00fbaf0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 10 Feb 2026 14:58:22 +0100
Subject: device property: Allow secondary lookup in
 fwnode_get_next_child_node()

When device_get_child_node_count() got split to the fwnode and device
respective APIs, the fwnode didn't inherit the ability to traverse over
the secondary fwnode. Hence any user, that switches from device to fwnode
API misses this feature. In particular, this was revealed by the commit
1490cbb9dbfd ("device property: Split fwnode_get_child_node_count()")
that effectively broke the GPIO enumeration on Intel Galileo boards.
Fix this by moving the secondary lookup from device to fwnode API.

Note, in general no device_*() API should go into the depth of the fwnode
implementation.

Fixes: 114dbb4fa7c4 ("drivers property: When no children in primary, try secondary")
Cc: stable@vger.kernel.org
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Link: https://patch.msgid.link/20260210135822.47335-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/property.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 6a63860579dd..8d9a34be57fb 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -797,7 +797,18 @@ struct fwnode_handle *
 fwnode_get_next_child_node(const struct fwnode_handle *fwnode,
 			   struct fwnode_handle *child)
 {
-	return fwnode_call_ptr_op(fwnode, get_next_child_node, child);
+	struct fwnode_handle *next;
+
+	if (IS_ERR_OR_NULL(fwnode))
+		return NULL;
+
+	/* Try to find a child in primary fwnode */
+	next = fwnode_call_ptr_op(fwnode, get_next_child_node, child);
+	if (next)
+		return next;
+
+	/* When no more children in primary, continue with secondary */
+	return fwnode_call_ptr_op(fwnode->secondary, get_next_child_node, child);
 }
 EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
 
@@ -841,19 +852,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node);
 struct fwnode_handle *device_get_next_child_node(const struct device *dev,
 						 struct fwnode_handle *child)
 {
-	const struct fwnode_handle *fwnode = dev_fwnode(dev);
-	struct fwnode_handle *next;
-
-	if (IS_ERR_OR_NULL(fwnode))
-		return NULL;
-
-	/* Try to find a child in primary fwnode */
-	next = fwnode_get_next_child_node(fwnode, child);
-	if (next)
-		return next;
-
-	/* When no more children in primary, continue with secondary */
-	return fwnode_get_next_child_node(fwnode->secondary, child);
+	return fwnode_get_next_child_node(dev_fwnode(dev), child);
 }
 EXPORT_SYMBOL_GPL(device_get_next_child_node);
 
-- 
cgit v1.2.3


From 7ec1bd3d9be671d04325b9e06149b8813f6a4836 Mon Sep 17 00:00:00 2001
From: Potin Lai <potin.lai.pt@gmail.com>
Date: Thu, 22 Jan 2026 16:37:56 +0800
Subject: soc: aspeed: socinfo: Mask table entries for accurate SoC ID matching

The siliconid_to_name() function currently masks the input silicon ID
with 0xff00ffff, but compares it against unmasked table entries. This
causes matching to fail if the table entries contain non-zero values in
the bits covered by the mask (bits 16-23).

Update the logic to apply the 0xff00ffff mask to the table entries
during comparison. This ensures that only the relevant model and
revision bits are considered, providing a consistent match across
different manufacturing batches.

[arj: Add Fixes: tag, fix 'soninfo' typo, clarify function reference]

Fixes: e0218dca5787 ("soc: aspeed: Add soc info driver")
Signed-off-by: Potin Lai <potin.lai.pt@gmail.com>
Link: https://patch.msgid.link/20260122-soc_aspeed_name_fix-v1-1-33a847f2581c@gmail.com
Signed-off-by: Andrew Jeffery <andrew@codeconstruct.com.au>
---
 drivers/soc/aspeed/aspeed-socinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/aspeed/aspeed-socinfo.c b/drivers/soc/aspeed/aspeed-socinfo.c
index 5e34e01ad26d..fb8fde94b651 100644
--- a/drivers/soc/aspeed/aspeed-socinfo.c
+++ b/drivers/soc/aspeed/aspeed-socinfo.c
@@ -39,7 +39,7 @@ static const char *siliconid_to_name(u32 siliconid)
 	unsigned int i;
 
 	for (i = 0 ; i < ARRAY_SIZE(rev_table) ; ++i) {
-		if (rev_table[i].id == id)
+		if ((rev_table[i].id & 0xff00ffff) == id)
 			return rev_table[i].name;
 	}
 
-- 
cgit v1.2.3


From 5dd69b864911ae3847365e8bafe7854e79fbeecb Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 29 Jan 2026 09:51:10 -0800
Subject: hwmon: (macsmc) Fix regressions in Apple Silicon SMC hwmon driver

The recently added macsmc-hwmon driver contained several critical
bugs in its sensor population logic and float conversion routines.

Specifically:
- The voltage sensor population loop used the wrong prefix ("volt-"
  instead of "voltage-") and incorrectly assigned sensors to the
  temperature sensor array (hwmon->temp.sensors) instead of the
  voltage sensor array (hwmon->volt.sensors). This would lead to
  out-of-bounds memory access or data corruption when both temperature
  and voltage sensors were present.
- The float conversion in macsmc_hwmon_write_f32() had flawed exponent
  logic for values >= 2^24 and lacked masking for the mantissa, which
  could lead to incorrect values being written to the SMC.

Fix these issues to ensure correct sensor registration and reliable
manual fan control.

Confirm that the reported overflow in FIELD_PREP is fixed by declaring
macsmc_hwmon_write_f32() as __always_inline for a compile test.

Fixes: 785205fd8139 ("hwmon: Add Apple Silicon SMC hwmon driver")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://lore.kernel.org/linux-hwmon/20260119195817.GA1035354@ax162/
Cc: James Calligeros <jcalligeros99@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Neal Gompa <neal@gompa.dev>
Cc: Janne Grunau <j@jannau.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Link: https://lore.kernel.org/r/20260129175112.3751907-2-linux@roeck-us.net
Reviewed-by: James Calligeros <jcalligeros99@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/macsmc-hwmon.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c
index 1c0bbec7e8eb..40d25c81b443 100644
--- a/drivers/hwmon/macsmc-hwmon.c
+++ b/drivers/hwmon/macsmc-hwmon.c
@@ -228,25 +228,22 @@ static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value)
 {
 	u64 val;
 	u32 fval = 0;
-	int exp = 0, neg;
+	int exp, neg;
 
+	neg = value < 0;
 	val = abs(value);
-	neg = val != value;
 
 	if (val) {
-		int msb = __fls(val) - exp;
-
-		if (msb > 23) {
-			val >>= msb - FLT_MANT_BIAS;
-			exp -= msb - FLT_MANT_BIAS;
-		} else if (msb < 23) {
-			val <<= FLT_MANT_BIAS - msb;
-			exp += msb;
-		}
+		exp = __fls(val);
+
+		if (exp > 23)
+			val >>= exp - 23;
+		else
+			val <<= 23 - exp;
 
 		fval = FIELD_PREP(FLT_SIGN_MASK, neg) |
 		       FIELD_PREP(FLT_EXP_MASK, exp + FLT_EXP_BIAS) |
-		       FIELD_PREP(FLT_MANT_MASK, val);
+		       FIELD_PREP(FLT_MANT_MASK, val & FLT_MANT_MASK);
 	}
 
 	return apple_smc_write_u32(smc, key, fval);
@@ -663,8 +660,8 @@ static int macsmc_hwmon_populate_sensors(struct macsmc_hwmon *hwmon,
 		if (!hwmon->volt.sensors)
 			return -ENOMEM;
 
-		for_each_child_of_node_with_prefix(hwmon_node, key_node, "volt-") {
-			sensor = &hwmon->temp.sensors[hwmon->temp.count];
+		for_each_child_of_node_with_prefix(hwmon_node, key_node, "voltage-") {
+			sensor = &hwmon->volt.sensors[hwmon->volt.count];
 			if (!macsmc_hwmon_create_sensor(hwmon->dev, hwmon->smc, key_node, sensor)) {
 				sensor->attrs = HWMON_I_INPUT;
 
-- 
cgit v1.2.3


From 579b86f3c26fee97996e68c1cbfb7461711f3de3 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 29 Jan 2026 09:51:11 -0800
Subject: hwmon: (macsmc) Fix overflows, underflows, and sign extension

The macsmc-hwmon driver experienced several issues related to value
scaling and type conversion:

1. macsmc_hwmon_read_f32_scaled() clipped values to INT_MAX/INT_MIN.
   On 64-bit systems, hwmon supports long values, so clipping to
   32-bit range was premature and caused loss of range for high-power
   sensors. Changed it to use long and clip to LONG_MAX/LONG_MIN.
2. The overflow check in macsmc_hwmon_read_f32_scaled() used 1UL,
   which is 32-bit on some platforms. Switched to 1ULL.
3. macsmc_hwmon_read_key() used a u32 temporary variable for f32
   values. When assigned to a 64-bit long, negative values were
   zero-extended instead of sign-extended, resulting in large
   positive numbers.
4. macsmc_hwmon_read_ioft_scaled() used mult_frac() which could
   overflow during intermediate multiplication. Switched to
   mul_u64_u32_div() to handle the 64-bit multiplication safely.
5. ioft values (unsigned 48.16) could overflow long when scaled
   by 1,000,000. Added explicit clipping to LONG_MAX in the caller.
6. macsmc_hwmon_write_f32() truncated its long argument to int,
   potentially causing issues for large values.

Fix these issues by using appropriate types and helper functions.

Fixes: 785205fd8139 ("hwmon: Add Apple Silicon SMC hwmon driver")
Cc: James Calligeros <jcalligeros99@gmail.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Neal Gompa <neal@gompa.dev>
Cc: Janne Grunau <j@jannau.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20260129175112.3751907-3-linux@roeck-us.net
Reviewed-by: James Calligeros <jcalligeros99@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/macsmc-hwmon.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/hwmon/macsmc-hwmon.c b/drivers/hwmon/macsmc-hwmon.c
index 40d25c81b443..1500ec2cc9f8 100644
--- a/drivers/hwmon/macsmc-hwmon.c
+++ b/drivers/hwmon/macsmc-hwmon.c
@@ -22,6 +22,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/hwmon.h>
+#include <linux/math64.h>
 #include <linux/mfd/macsmc.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -130,7 +131,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key,
 	if (ret < 0)
 		return ret;
 
-	*p = mult_frac(val, scale, 65536);
+	*p = mul_u64_u32_div(val, scale, 65536);
 
 	return 0;
 }
@@ -140,7 +141,7 @@ static int macsmc_hwmon_read_ioft_scaled(struct apple_smc *smc, smc_key key,
  * them.
  */
 static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key,
-					int *p, int scale)
+					long *p, int scale)
 {
 	u32 fval;
 	u64 val;
@@ -162,21 +163,21 @@ static int macsmc_hwmon_read_f32_scaled(struct apple_smc *smc, smc_key key,
 		val = 0;
 	else if (exp < 0)
 		val >>= -exp;
-	else if (exp != 0 && (val & ~((1UL << (64 - exp)) - 1))) /* overflow */
+	else if (exp != 0 && (val & ~((1ULL << (64 - exp)) - 1))) /* overflow */
 		val = U64_MAX;
 	else
 		val <<= exp;
 
 	if (fval & FLT_SIGN_MASK) {
-		if (val > (-(s64)INT_MIN))
-			*p = INT_MIN;
+		if (val > (u64)LONG_MAX + 1)
+			*p = LONG_MIN;
 		else
-			*p = -val;
+			*p = -(long)val;
 	} else {
-		if (val > INT_MAX)
-			*p = INT_MAX;
+		if (val > (u64)LONG_MAX)
+			*p = LONG_MAX;
 		else
-			*p = val;
+			*p = (long)val;
 	}
 
 	return 0;
@@ -195,7 +196,7 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 	switch (sensor->info.type_code) {
 	/* 32-bit IEEE 754 float */
 	case __SMC_KEY('f', 'l', 't', ' '): {
-		u32 flt_ = 0;
+		long flt_ = 0;
 
 		ret = macsmc_hwmon_read_f32_scaled(smc, sensor->macsmc_key,
 						   &flt_, scale);
@@ -214,7 +215,10 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 		if (ret)
 			return ret;
 
-		*val = (long)ioft;
+		if (ioft > LONG_MAX)
+			*val = LONG_MAX;
+		else
+			*val = (long)ioft;
 		break;
 	}
 	default:
@@ -224,7 +228,7 @@ static int macsmc_hwmon_read_key(struct apple_smc *smc,
 	return 0;
 }
 
-static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, int value)
+static int macsmc_hwmon_write_f32(struct apple_smc *smc, smc_key key, long value)
 {
 	u64 val;
 	u32 fval = 0;
-- 
cgit v1.2.3


From ac209a7d816d918582d0d6387e93d02679f9c8ed Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 14 Feb 2026 17:03:27 -0800
Subject: hwmon: (emc1403) correct a malformed email address

Add a closing '>' to Kalhan's emaill address.

line 60:  Kalhan Trisal <kalhan.trisal@intel.com

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20260215010327.1687304-1-rdunlap@infradead.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/emc1403.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/hwmon/emc1403.rst b/Documentation/hwmon/emc1403.rst
index 57f833b1a800..77060d515323 100644
--- a/Documentation/hwmon/emc1403.rst
+++ b/Documentation/hwmon/emc1403.rst
@@ -57,7 +57,7 @@ Supported chips:
 	- https://ww1.microchip.com/downloads/en/DeviceDoc/EMC1438%20DS%20Rev.%201.0%20(04-29-10).pdf
 
 Author:
-    Kalhan Trisal <kalhan.trisal@intel.com
+    Kalhan Trisal <kalhan.trisal@intel.com>
 
 
 Description
-- 
cgit v1.2.3


From b7497b5a99f54ab8dcda5b14a308385b2fb03d8d Mon Sep 17 00:00:00 2001
From: Hao Yu <haoyufine@gmail.com>
Date: Mon, 23 Feb 2026 01:03:31 +0800
Subject: hwmon: (aht10) Fix initialization commands for AHT20

According to the AHT20 datasheet (updated to V1.0 after the 2023.09
version), the initialization command for AHT20 is 0b10111110 (0xBE).
The previous sequence (0xE1) used in earlier versions is no longer
compatible with newer AHT20 sensors. Update the initialization
command to ensure the sensor is properly initialized.

While at it, use binary notation for DHT20_CMD_INIT to match the notation
used in the datasheet.

Fixes: d2abcb5cc885 ("hwmon: (aht10) Add support for compatible aht20")
Signed-off-by: Hao Yu <haoyufine@gmail.com>
Link: https://lore.kernel.org/r/20260222170332.1616-3-haoyufine@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/aht10.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/aht10.c b/drivers/hwmon/aht10.c
index 007befdba977..4ce019d2cc80 100644
--- a/drivers/hwmon/aht10.c
+++ b/drivers/hwmon/aht10.c
@@ -37,7 +37,9 @@
 #define AHT10_CMD_MEAS	0b10101100
 #define AHT10_CMD_RST	0b10111010
 
-#define DHT20_CMD_INIT	0x71
+#define AHT20_CMD_INIT	0b10111110
+
+#define DHT20_CMD_INIT	0b01110001
 
 /*
  * Flags in the answer byte/command
@@ -341,7 +343,7 @@ static int aht10_probe(struct i2c_client *client)
 		data->meas_size = AHT20_MEAS_SIZE;
 		data->crc8 = true;
 		crc8_populate_msb(crc8_table, AHT20_CRC8_POLY);
-		data->init_cmd = AHT10_CMD_INIT;
+		data->init_cmd = AHT20_CMD_INIT;
 		break;
 	case dht20:
 		data->meas_size = AHT20_MEAS_SIZE;
-- 
cgit v1.2.3


From be704107e79696e855aa41e901a926039b6d2410 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Thu, 19 Feb 2026 16:55:30 -0600
Subject: regulator: dt-bindings: mt6359: make regulator names unique

Update the example devicetree with unique regulator names for all
regulators. This reflects the same change made to the actual .dtsi file.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260219-mtk-mt6359-fix-regulator-names-v1-2-ee0fcebfe1d9@baylibre.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
index d6b3b5a5c0b3..fe4ac9350ba0 100644
--- a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml
@@ -287,7 +287,7 @@ examples:
           regulator-max-microvolt = <1700000>;
         };
         mt6359_vrfck_1_ldo_reg: ldo_vrfck_1 {
-          regulator-name = "vrfck";
+          regulator-name = "vrfck_1";
           regulator-min-microvolt = <1240000>;
           regulator-max-microvolt = <1600000>;
         };
@@ -309,7 +309,7 @@ examples:
           regulator-max-microvolt = <3300000>;
         };
         mt6359_vemc_1_ldo_reg: ldo_vemc_1 {
-          regulator-name = "vemc";
+          regulator-name = "vemc_1";
           regulator-min-microvolt = <2500000>;
           regulator-max-microvolt = <3300000>;
         };
-- 
cgit v1.2.3


From bfcaf4e8ae9b4f52b97fb04ce03be3a01d41cdd0 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 16 Feb 2026 14:14:33 +0100
Subject: rust: io: macro_export io_define_read!() and io_define_write!()

Currently, the define_read!() and define_write!() I/O macros are crate
public. The only user outside of the I/O module is PCI (for the
configurations space I/O backend). Consequently, when CONFIG_PCI=n this
causes a compile time warning [1].

In order to fix this, rename the macros to io_define_read!() and
io_define_write!() and use #[macro_export] to export them.

This is better than making the crate public visibility conditional, as
eventually subsystems will have their own crate.

Also, I/O backends are valid to be implemented by drivers as well. For
instance, there are devices (such as GPUs) that run firmware which
allows to program other devices only accessible through the primary
device through indirect I/O.

Since the macros are now public, also add the corresponding
documentation.

Fixes: 121d87b28e1d ("rust: io: separate generic I/O helpers from MMIO implementation")
Reported-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Closes: https://lore.kernel.org/driver-core/CANiq72khOYkt6t5zwMvSiyZvWWHMZuNCMERXu=7K=_5tT-8Pgg@mail.gmail.com/ [1]
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Link: https://patch.msgid.link/20260216131534.65008-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/io.rs     | 131 ++++++++++++++++++++++++++++++++++----------------
 rust/kernel/pci/io.rs |  24 ++++-----
 2 files changed, 101 insertions(+), 54 deletions(-)

diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs
index c1cca7b438c3..e5fba6bf6db0 100644
--- a/rust/kernel/io.rs
+++ b/rust/kernel/io.rs
@@ -139,9 +139,9 @@ pub struct Mmio<const SIZE: usize = 0>(MmioRaw<SIZE>);
 
 /// Internal helper macros used to invoke C MMIO read functions.
 ///
-/// This macro is intended to be used by higher-level MMIO access macros (define_read) and provides
-/// a unified expansion for infallible vs. fallible read semantics. It emits a direct call into the
-/// corresponding C helper and performs the required cast to the Rust return type.
+/// This macro is intended to be used by higher-level MMIO access macros (io_define_read) and
+/// provides a unified expansion for infallible vs. fallible read semantics. It emits a direct call
+/// into the corresponding C helper and performs the required cast to the Rust return type.
 ///
 /// # Parameters
 ///
@@ -166,9 +166,9 @@ macro_rules! call_mmio_read {
 
 /// Internal helper macros used to invoke C MMIO write functions.
 ///
-/// This macro is intended to be used by higher-level MMIO access macros (define_write) and provides
-/// a unified expansion for infallible vs. fallible write semantics. It emits a direct call into the
-/// corresponding C helper and performs the required cast to the Rust return type.
+/// This macro is intended to be used by higher-level MMIO access macros (io_define_write) and
+/// provides a unified expansion for infallible vs. fallible write semantics. It emits a direct call
+/// into the corresponding C helper and performs the required cast to the Rust return type.
 ///
 /// # Parameters
 ///
@@ -193,7 +193,30 @@ macro_rules! call_mmio_write {
     }};
 }
 
-macro_rules! define_read {
+/// Generates an accessor method for reading from an I/O backend.
+///
+/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
+/// (infallible) or runtime bounds-checked (fallible) read methods. It abstracts the address
+/// calculation and bounds checking, and delegates the actual I/O read operation to a specified
+/// helper macro, making it generic over different I/O backends.
+///
+/// # Parameters
+///
+/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
+///   `IoKnownSize` for compile-time checks and returns the value directly. `fallible` performs
+///   runtime checks against `maxsize()` and returns a `Result<T>`.
+/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
+///   `#[cfg(CONFIG_64BIT)]` or inline directives).
+/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
+/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `read32`,
+///   `try_read8`).
+/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
+///   (e.g., `call_mmio_read`).
+/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
+///   `$call_macro`.
+/// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`).
+#[macro_export]
+macro_rules! io_define_read {
     (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) ->
      $type_name:ty) => {
         /// Read IO data from a given offset known at compile time.
@@ -226,9 +249,33 @@ macro_rules! define_read {
         }
     };
 }
-pub(crate) use define_read;
+pub use io_define_read;
 
-macro_rules! define_write {
+/// Generates an accessor method for writing to an I/O backend.
+///
+/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
+/// (infallible) or runtime bounds-checked (fallible) write methods. It abstracts the address
+/// calculation and bounds checking, and delegates the actual I/O write operation to a specified
+/// helper macro, making it generic over different I/O backends.
+///
+/// # Parameters
+///
+/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
+///   `IoKnownSize` for compile-time checks and returns `()`. `fallible` performs runtime checks
+///   against `maxsize()` and returns a `Result`.
+/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
+///   `#[cfg(CONFIG_64BIT)]` or inline directives).
+/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
+/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `write32`,
+///   `try_write8`).
+/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
+///   (e.g., `call_mmio_write`).
+/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
+///   `$call_macro`.
+/// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use
+///   of `<-` before the type to denote a write operation.
+#[macro_export]
+macro_rules! io_define_write {
     (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <-
      $type_name:ty) => {
         /// Write IO data from a given offset known at compile time.
@@ -259,7 +306,7 @@ macro_rules! define_write {
         }
     };
 }
-pub(crate) use define_write;
+pub use io_define_write;
 
 /// Checks whether an access of type `U` at the given `offset`
 /// is valid within this region.
@@ -509,40 +556,40 @@ impl<const SIZE: usize> Io for Mmio<SIZE> {
         self.0.maxsize()
     }
 
-    define_read!(fallible, try_read8, call_mmio_read(readb) -> u8);
-    define_read!(fallible, try_read16, call_mmio_read(readw) -> u16);
-    define_read!(fallible, try_read32, call_mmio_read(readl) -> u32);
-    define_read!(
+    io_define_read!(fallible, try_read8, call_mmio_read(readb) -> u8);
+    io_define_read!(fallible, try_read16, call_mmio_read(readw) -> u16);
+    io_define_read!(fallible, try_read32, call_mmio_read(readl) -> u32);
+    io_define_read!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         try_read64,
         call_mmio_read(readq) -> u64
     );
 
-    define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8);
-    define_write!(fallible, try_write16, call_mmio_write(writew) <- u16);
-    define_write!(fallible, try_write32, call_mmio_write(writel) <- u32);
-    define_write!(
+    io_define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8);
+    io_define_write!(fallible, try_write16, call_mmio_write(writew) <- u16);
+    io_define_write!(fallible, try_write32, call_mmio_write(writel) <- u32);
+    io_define_write!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         try_write64,
         call_mmio_write(writeq) <- u64
     );
 
-    define_read!(infallible, read8, call_mmio_read(readb) -> u8);
-    define_read!(infallible, read16, call_mmio_read(readw) -> u16);
-    define_read!(infallible, read32, call_mmio_read(readl) -> u32);
-    define_read!(
+    io_define_read!(infallible, read8, call_mmio_read(readb) -> u8);
+    io_define_read!(infallible, read16, call_mmio_read(readw) -> u16);
+    io_define_read!(infallible, read32, call_mmio_read(readl) -> u32);
+    io_define_read!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         read64,
         call_mmio_read(readq) -> u64
     );
 
-    define_write!(infallible, write8, call_mmio_write(writeb) <- u8);
-    define_write!(infallible, write16, call_mmio_write(writew) <- u16);
-    define_write!(infallible, write32, call_mmio_write(writel) <- u32);
-    define_write!(
+    io_define_write!(infallible, write8, call_mmio_write(writeb) <- u8);
+    io_define_write!(infallible, write16, call_mmio_write(writew) <- u16);
+    io_define_write!(infallible, write32, call_mmio_write(writel) <- u32);
+    io_define_write!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         write64,
@@ -566,40 +613,40 @@ impl<const SIZE: usize> Mmio<SIZE> {
         unsafe { &*core::ptr::from_ref(raw).cast() }
     }
 
-    define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    define_read!(
+    io_define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
+    io_define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
+    io_define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
+    io_define_read!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         pub read64_relaxed,
         call_mmio_read(readq_relaxed) -> u64
     );
 
-    define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    define_read!(
+    io_define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
+    io_define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
+    io_define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
+    io_define_read!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         pub try_read64_relaxed,
         call_mmio_read(readq_relaxed) -> u64
     );
 
-    define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    define_write!(
+    io_define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
+    io_define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
+    io_define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
+    io_define_write!(
         infallible,
         #[cfg(CONFIG_64BIT)]
         pub write64_relaxed,
         call_mmio_write(writeq_relaxed) <- u64
     );
 
-    define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    define_write!(
+    io_define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
+    io_define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
+    io_define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
+    io_define_write!(
         fallible,
         #[cfg(CONFIG_64BIT)]
         pub try_write64_relaxed,
diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs
index 6ca4cf75594c..fb6edab2aea7 100644
--- a/rust/kernel/pci/io.rs
+++ b/rust/kernel/pci/io.rs
@@ -8,8 +8,8 @@ use crate::{
     device,
     devres::Devres,
     io::{
-        define_read,
-        define_write,
+        io_define_read,
+        io_define_write,
         Io,
         IoCapable,
         IoKnownSize,
@@ -88,7 +88,7 @@ pub struct ConfigSpace<'a, S: ConfigSpaceKind = Extended> {
 /// Internal helper macros used to invoke C PCI configuration space read functions.
 ///
 /// This macro is intended to be used by higher-level PCI configuration space access macros
-/// (define_read) and provides a unified expansion for infallible vs. fallible read semantics. It
+/// (io_define_read) and provides a unified expansion for infallible vs. fallible read semantics. It
 /// emits a direct call into the corresponding C helper and performs the required cast to the Rust
 /// return type.
 ///
@@ -117,9 +117,9 @@ macro_rules! call_config_read {
 /// Internal helper macros used to invoke C PCI configuration space write functions.
 ///
 /// This macro is intended to be used by higher-level PCI configuration space access macros
-/// (define_write) and provides a unified expansion for infallible vs. fallible read semantics. It
-/// emits a direct call into the corresponding C helper and performs the required cast to the Rust
-/// return type.
+/// (io_define_write) and provides a unified expansion for infallible vs. fallible read semantics.
+/// It emits a direct call into the corresponding C helper and performs the required cast to the
+/// Rust return type.
 ///
 /// # Parameters
 ///
@@ -163,13 +163,13 @@ impl<'a, S: ConfigSpaceKind> Io for ConfigSpace<'a, S> {
     // PCI configuration space does not support fallible operations.
     // The default implementations from the Io trait are not used.
 
-    define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8);
-    define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16);
-    define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32);
+    io_define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8);
+    io_define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16);
+    io_define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32);
 
-    define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8);
-    define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16);
-    define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32);
+    io_define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8);
+    io_define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16);
+    io_define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32);
 }
 
 impl<'a, S: ConfigSpaceKind> IoKnownSize for ConfigSpace<'a, S> {
-- 
cgit v1.2.3


From c5794709bc9105935dbedef8b9cf9c06f2b559fa Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Tue, 17 Feb 2026 20:28:29 -0800
Subject: ksmbd: Compare MACs in constant time

To prevent timing attacks, MAC comparisons need to be constant-time.
Replace the memcmp() with the correct function, crypto_memneq().

Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/Kconfig   | 1 +
 fs/smb/server/auth.c    | 4 +++-
 fs/smb/server/smb2pdu.c | 5 +++--
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig
index 2775162c535c..12594879cb64 100644
--- a/fs/smb/server/Kconfig
+++ b/fs/smb/server/Kconfig
@@ -13,6 +13,7 @@ config SMB_SERVER
 	select CRYPTO_LIB_MD5
 	select CRYPTO_LIB_SHA256
 	select CRYPTO_LIB_SHA512
+	select CRYPTO_LIB_UTILS
 	select CRYPTO_CMAC
 	select CRYPTO_AEAD2
 	select CRYPTO_CCM
diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 580c4d303dc3..5fe8c667c6b1 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -15,6 +15,7 @@
 #include <crypto/aead.h>
 #include <crypto/md5.h>
 #include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include <linux/random.h>
 #include <linux/scatterlist.h>
 
@@ -165,7 +166,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess,
 			     ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE,
 			     sess->sess_key);
 
-	if (memcmp(ntlmv2->ntlmv2_hash, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE) != 0)
+	if (crypto_memneq(ntlmv2->ntlmv2_hash, ntlmv2_rsp,
+			  CIFS_HMAC_MD5_HASH_SIZE))
 		return -EINVAL;
 	return 0;
 }
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 95901a78951c..743c629fe7ec 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4,6 +4,7 @@
  *   Copyright (C) 2018 Samsung Electronics Co., Ltd.
  */
 
+#include <crypto/utils.h>
 #include <linux/inetdevice.h>
 #include <net/addrconf.h>
 #include <linux/syscalls.h>
@@ -8880,7 +8881,7 @@ int smb2_check_sign_req(struct ksmbd_work *work)
 	ksmbd_sign_smb2_pdu(work->conn, work->sess->sess_key, iov, 1,
 			    signature);
 
-	if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
 		pr_err("bad smb2 signature\n");
 		return 0;
 	}
@@ -8968,7 +8969,7 @@ int smb3_check_sign_req(struct ksmbd_work *work)
 	if (ksmbd_sign_smb3_pdu(conn, signing_key, iov, 1, signature))
 		return 0;
 
-	if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) {
 		pr_err("bad smb2 signature\n");
 		return 0;
 	}
-- 
cgit v1.2.3


From 6b4f875aac344cdd52a1f34cc70ed2f874a65757 Mon Sep 17 00:00:00 2001
From: Nicholas Carlini <nicholas@carlini.com>
Date: Thu, 19 Feb 2026 20:58:57 +0900
Subject: ksmbd: fix signededness bug in smb_direct_prepare_negotiation()

smb_direct_prepare_negotiation() casts an unsigned __u32 value
from sp->max_recv_size and req->preferred_send_size to a signed
int before computing min_t(int, ...). A maliciously provided
preferred_send_size of 0x80000000 will return as smaller than
max_recv_size, and then be used to set the maximum allowed
alowed receive size for the next message.

By sending a second message with a large value (>1420 bytes)
the attacker can then achieve a heap buffer overflow.

This fix replaces min_t(int, ...) with min_t(u32)

Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Signed-off-by: Nicholas Carlini <nicholas@carlini.com>
Reviewed-by: Stefan Metzmacher <metze@samba.org>
Acked-by: Stefan Metzmacher <metze@samba.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_rdma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 7c53b78b818e..188572491d53 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2540,9 +2540,9 @@ static int smb_direct_prepare(struct ksmbd_transport *t)
 		goto put;
 
 	req = (struct smbdirect_negotiate_req *)recvmsg->packet;
-	sp->max_recv_size = min_t(int, sp->max_recv_size,
+	sp->max_recv_size = min_t(u32, sp->max_recv_size,
 				  le32_to_cpu(req->preferred_send_size));
-	sp->max_send_size = min_t(int, sp->max_send_size,
+	sp->max_send_size = min_t(u32, sp->max_send_size,
 				  le32_to_cpu(req->max_receive_size));
 	sp->max_fragmented_send_size =
 		le32_to_cpu(req->max_fragmented_size);
-- 
cgit v1.2.3


From 47322c469d4a63ac45b705ca83680671ff71c975 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 9 Feb 2026 16:38:05 +0100
Subject: dma-mapping: avoid random addr value print out on error path

dma_addr is unitialized in dma_direct_map_phys() when swiotlb is forced
and DMA_ATTR_MMIO is set which leads to random value print out in
warning. Fix that by just returning DMA_MAPPING_ERROR.

Fixes: e53d29f957b3 ("dma-mapping: convert dma_direct_*map_page to be phys_addr_t based")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260209153809.250835-2-jiri@resnulli.us
---
 kernel/dma/direct.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index f476c63b668c..e89f175e9c2d 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -85,7 +85,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 
 	if (is_swiotlb_force_bounce(dev)) {
 		if (attrs & DMA_ATTR_MMIO)
-			goto err_overflow;
+			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
-- 
cgit v1.2.3


From d5b5e8149af0f5efed58653cbebf1cb3258ce49a Mon Sep 17 00:00:00 2001
From: Stian Halseth <stian@itx.no>
Date: Wed, 18 Feb 2026 13:00:24 +0100
Subject: sparc: Fix page alignment in dma mapping

'phys' may include an offset within the page, while previously used
'base_paddr' was already page-aligned. This caused incorrect DMA mapping
in dma_4u_map_phys and dma_4v_map_phys.

Fix both functions by masking 'phys' with IO_PAGE_MASK, covering both
generic SPARC code and sun4v.

Fixes: 38c0d0ebf520 ("sparc: Use physical address DMA mapping")
Reported-by: Stian Halseth <stian@itx.no>
Closes: https://github.com/sparclinux/issues/issues/75
Suggested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Stian Halseth <stian@itx.no>
Tested-by: Nathaniel Roach <nroach44@nroach44.id.au>
Tested-by: Han Gao <gaohan@iscas.ac.cn> # on SPARC Enterprise T5220
[mszyprow: adjusted commit description a bit]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260218120056.3366-2-stian@itx.no
---
 arch/sparc/kernel/iommu.c     | 2 ++
 arch/sparc/kernel/pci_sun4v.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 46ef88bc9c26..7613ab0ffb89 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys,
 	if (direction != DMA_TO_DEVICE)
 		iopte_protection |= IOPTE_WRITE;
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE)
 		iopte_val(*base) = iopte_protection | phys;
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 440284cc804e..61f14b4c8f90 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys,
 
 	iommu_batch_start(dev, prot, entry);
 
+	phys &= IO_PAGE_MASK;
+
 	for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) {
 		long err = iommu_batch_add(phys, mask);
 		if (unlikely(err < 0L))
-- 
cgit v1.2.3


From c8d7f21ead727485ebf965e2b4d42d4a4f0840f6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 9 Feb 2026 19:12:20 +0100
Subject: wifi: cfg80211: wext: fix IGTK key ID off-by-one

The IGTK key ID must be 4 or 5, but the code checks against
key ID + 1, so must check against 5/6 rather than 4/5. Fix
that.

Reported-by: Jouni Malinen <j@w1.fi>
Fixes: 08645126dd24 ("cfg80211: implement wext key handling")
Link: https://patch.msgid.link/20260209181220.362205-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/wext-compat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 1241fda78a68..680500fa57cf 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -684,7 +684,7 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev,
 
 	idx = erq->flags & IW_ENCODE_INDEX;
 	if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) {
-		if (idx < 4 || idx > 5) {
+		if (idx < 5 || idx > 6) {
 			idx = wdev->wext.default_mgmt_key;
 			if (idx < 0)
 				return -EINVAL;
-- 
cgit v1.2.3


From 767d23ade706d5fa51c36168e92a9c5533c351a1 Mon Sep 17 00:00:00 2001
From: Daniil Dulov <d.dulov@aladdin.ru>
Date: Wed, 11 Feb 2026 11:20:24 +0300
Subject: wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()

There is a use-after-free error in cfg80211_shutdown_all_interfaces found
by syzkaller:

BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x116/0x1f0
 print_report+0xcd/0x630
 kasan_report+0xe0/0x110
 cfg80211_shutdown_all_interfaces+0x213/0x220
 cfg80211_rfkill_block_work+0x1e/0x30
 process_one_work+0x9cf/0x1b70
 worker_thread+0x6c8/0xf10
 kthread+0x3c5/0x780
 ret_from_fork+0x56d/0x700
 ret_from_fork_asm+0x1a/0x30
 </TASK>

The problem arises due to the rfkill_block work is not cancelled when wiphy
is being unregistered. In order to fix the issue cancel the corresponding
work in wiphy_unregister().

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 1f87f7d3a3b4 ("cfg80211: add rfkill support")
Cc: stable@vger.kernel.org
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
Link: https://patch.msgid.link/20260211082024.1967588-1-d.dulov@aladdin.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 9af85d655027..d35cf04cbc81 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1212,6 +1212,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	/* this has nothing to do now but make sure it's gone */
 	cancel_work_sync(&rdev->wiphy_work);
 
+	cancel_work_sync(&rdev->rfkill_block);
 	cancel_work_sync(&rdev->conn_work);
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
-- 
cgit v1.2.3


From c854758abe0b8d86f9c43dc060ff56a0ee5b31e0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 17 Feb 2026 13:05:26 +0100
Subject: wifi: radiotap: reject radiotap with unknown bits

The radiotap parser is currently only used with the radiotap
namespace (not with vendor namespaces), but if the undefined
field 18 is used, the alignment/size is unknown as well. In
this case, iterator->_next_ns_data isn't initialized (it's
only set for skipping vendor namespaces), and syzbot points
out that we later compare against this uninitialized value.

Fix this by moving the rejection of unknown radiotap fields
down to after the in-namespace lookup, so it will really use
iterator->_next_ns_data only for vendor namespaces, even in
case undefined fields are present.

Cc: stable@vger.kernel.org
Fixes: 33e5a2f776e3 ("wireless: update radiotap parser")
Reported-by: syzbot+b09c1af8764c0097bb19@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/69944a91.a70a0220.2c38d7.00fc.GAE@google.com
Link: https://patch.msgid.link/20260217120526.162647-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/radiotap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 326faea38ca3..c85eaa583a46 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -239,14 +239,14 @@ int ieee80211_radiotap_iterator_next(
 		default:
 			if (!iterator->current_namespace ||
 			    iterator->_arg_index >= iterator->current_namespace->n_bits) {
-				if (iterator->current_namespace == &radiotap_ns)
-					return -ENOENT;
 				align = 0;
 			} else {
 				align = iterator->current_namespace->align_size[iterator->_arg_index].align;
 				size = iterator->current_namespace->align_size[iterator->_arg_index].size;
 			}
 			if (!align) {
+				if (iterator->current_namespace == &radiotap_ns)
+					return -ENOENT;
 				/* skip all subsequent data */
 				iterator->_arg = iterator->_next_ns_data;
 				/* give up on this namespace */
-- 
cgit v1.2.3


From 243307a0d1b0d01538e202c00454c28b21d4432e Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Tue, 3 Feb 2026 11:21:33 +0100
Subject: wifi: brcmfmac: Fix potential kernel oops when probe fails

When probe of the sdio brcmfmac device fails for some reasons (i.e.
missing firmware), the sdiodev->bus is set to error instead of NULL, thus
the cleanup later in brcmf_sdio_remove() tries to free resources via
invalid bus pointer. This happens because sdiodev->bus is set 2 times:
first in brcmf_sdio_probe() and second time in brcmf_sdiod_probe(). Fix
this by chaning the brcmf_sdio_probe() function to return the error code
and set sdio->bus only there.

Fixes: 0ff0843310b7 ("wifi: brcmfmac: Add optional lpo clock enable support")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Arend van Spriel<arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20260203102133.1478331-1-m.szyprowski@samsung.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 7 +++----
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c   | 7 ++++---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h   | 2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 6a3f187320fc..13952dfeb3e3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -951,11 +951,10 @@ int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev)
 		goto out;
 
 	/* try to attach to the target device */
-	sdiodev->bus = brcmf_sdio_probe(sdiodev);
-	if (IS_ERR(sdiodev->bus)) {
-		ret = PTR_ERR(sdiodev->bus);
+	ret = brcmf_sdio_probe(sdiodev);
+	if (ret)
 		goto out;
-	}
+
 	brcmf_sdiod_host_fixup(sdiodev->func2->card->host);
 out:
 	if (ret)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index 8cf9d7e7c3f7..4e6ed02c1591 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4445,7 +4445,7 @@ brcmf_sdio_prepare_fw_request(struct brcmf_sdio *bus)
 	return fwreq;
 }
 
-struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
+int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 {
 	int ret;
 	struct brcmf_sdio *bus;
@@ -4551,11 +4551,12 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 		goto fail;
 	}
 
-	return bus;
+	return 0;
 
 fail:
 	brcmf_sdio_remove(bus);
-	return ERR_PTR(ret);
+	sdiodev->bus = NULL;
+	return ret;
 }
 
 /* Detach and free everything */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
index 0d18ed15b403..80180d5c6c87 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -358,7 +358,7 @@ void brcmf_sdiod_freezer_uncount(struct brcmf_sdio_dev *sdiodev);
 int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev);
 int brcmf_sdiod_remove(struct brcmf_sdio_dev *sdiodev);
 
-struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
+int brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
 void brcmf_sdio_remove(struct brcmf_sdio *bus);
 void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr);
 
-- 
cgit v1.2.3


From c9f3a593137d862d424130343e77d4b5260a4f5a Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Fri, 30 Jan 2026 16:38:47 +0100
Subject: iio: imu: inv_icm42600: fix odr switch to the same value

ODR switch is done in 2 steps when FIFO is on : change the ODR register
value and acknowledge change when reading the FIFO ODR change flag.
When we are switching to the same odr value, we end up waiting for a
FIFO ODR flag that is never happening.

Fix the issue by doing nothing and exiting properly when we are
switching to the same ODR value.

Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c | 2 ++
 drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c  | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index 54760d8f92a2..0ab6eddf0543 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -651,6 +651,8 @@ static int inv_icm42600_accel_write_odr(struct iio_dev *indio_dev,
 		return -EINVAL;
 
 	conf.odr = inv_icm42600_accel_odr_conv[idx / 2];
+	if (conf.odr == st->conf.accel.odr)
+		return 0;
 
 	pm_runtime_get_sync(dev);
 	mutex_lock(&st->lock);
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index 7ef0a25ec74f..11339ddf1da3 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -358,6 +358,8 @@ static int inv_icm42600_gyro_write_odr(struct iio_dev *indio_dev,
 		return -EINVAL;
 
 	conf.odr = inv_icm42600_gyro_odr_conv[idx / 2];
+	if (conf.odr == st->conf.gyro.odr)
+		return 0;
 
 	pm_runtime_get_sync(dev);
 	mutex_lock(&st->lock);
-- 
cgit v1.2.3


From ffd32db8263d2d785a2c419486a450dc80693235 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Fri, 30 Jan 2026 17:10:23 +0100
Subject: iio: imu: inv_icm42600: fix odr switch when turning buffer off

ODR switch is done in 2 steps when FIFO is on : change the ODR register
value and acknowledge change when reading the FIFO ODR change flag.
When we are switching odr and turning buffer off just afterward, we are
losing the FIFO ODR change flag and ODR switch is blocked.

Fix the issue by force applying any waiting ODR change when turning
buffer off.

Fixes: ec74ae9fd37c ("iio: imu: inv_icm42600: add accurate timestamping")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
index ada968be954d..68a395758031 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c
@@ -371,6 +371,8 @@ static int inv_icm42600_buffer_predisable(struct iio_dev *indio_dev)
 static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev)
 {
 	struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev);
+	struct inv_icm42600_sensor_state *sensor_st = iio_priv(indio_dev);
+	struct inv_sensors_timestamp *ts = &sensor_st->ts;
 	struct device *dev = regmap_get_device(st->map);
 	unsigned int sensor;
 	unsigned int *watermark;
@@ -392,6 +394,8 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev)
 
 	mutex_lock(&st->lock);
 
+	inv_sensors_timestamp_apply_odr(ts, 0, 0, 0);
+
 	ret = inv_icm42600_buffer_set_fifo_en(st, st->fifo.en & ~sensor);
 	if (ret)
 		goto out_unlock;
-- 
cgit v1.2.3


From dd72e6c3cdea05cad24e99710939086f7a113fb5 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 30 Jan 2026 13:30:20 +0200
Subject: iio: light: bh1780: fix PM runtime leak on error path

Move pm_runtime_put_autosuspend() before the error check to ensure
the PM runtime reference count is always decremented after
pm_runtime_get_sync(), regardless of whether the read operation
succeeds or fails.

Fixes: 1f0477f18306 ("iio: light: new driver for the ROHM BH1780")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/bh1780.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/light/bh1780.c b/drivers/iio/light/bh1780.c
index 5d3c6d5276ba..a740d1f992a8 100644
--- a/drivers/iio/light/bh1780.c
+++ b/drivers/iio/light/bh1780.c
@@ -109,9 +109,9 @@ static int bh1780_read_raw(struct iio_dev *indio_dev,
 		case IIO_LIGHT:
 			pm_runtime_get_sync(&bh1780->client->dev);
 			value = bh1780_read_word(bh1780, BH1780_REG_DLOW);
+			pm_runtime_put_autosuspend(&bh1780->client->dev);
 			if (value < 0)
 				return value;
-			pm_runtime_put_autosuspend(&bh1780->client->dev);
 			*val = value;
 
 			return IIO_VAL_INT;
-- 
cgit v1.2.3


From 6c8bf4b604a8a6346ca71f1c027fa01c2c2e04cb Mon Sep 17 00:00:00 2001
From: SeungJu Cheon <suunj1331@gmail.com>
Date: Sat, 24 Jan 2026 04:47:58 +0900
Subject: iio: frequency: adf4377: Fix duplicated soft reset mask

The regmap_read_poll_timeout() uses ADF4377_0000_SOFT_RESET_R_MSK
twice instead of checking both SOFT_RESET_MSK (bit 0) and
SOFT_RESET_R_MSK (bit 7). This causes an incomplete reset status check.

The code first sets both SOFT_RESET and SOFT_RESET_R bits to 1 via
regmap_update_bits(), then polls for them to be cleared. Since we set
both bits before polling, we should be waiting for both to clear.

Fix by using both masks as done in regmap_update_bits() above.

Fixes: eda549e2e524 ("iio: frequency: adf4377: add support for ADF4377")
Signed-off-by: SeungJu Cheon <suunj1331@gmail.com>
Cc: Stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/frequency/adf4377.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/frequency/adf4377.c b/drivers/iio/frequency/adf4377.c
index fa686f785fa4..8e2da218d48a 100644
--- a/drivers/iio/frequency/adf4377.c
+++ b/drivers/iio/frequency/adf4377.c
@@ -508,7 +508,7 @@ static int adf4377_soft_reset(struct adf4377_state *st)
 		return ret;
 
 	return regmap_read_poll_timeout(st->regmap, 0x0, read_val,
-					!(read_val & (ADF4377_0000_SOFT_RESET_R_MSK |
+					!(read_val & (ADF4377_0000_SOFT_RESET_MSK |
 					ADF4377_0000_SOFT_RESET_R_MSK)), 200, 200 * 100);
 }
 
-- 
cgit v1.2.3


From d23d763e00ace4e9c59f8d33e0713d401133ba88 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Wed, 31 Dec 2025 22:14:16 +0100
Subject: iio: imu: inv-mpu9150: fix irq ack preventing irq storms

IRQ needs to be acked. for some odd reasons, reading from irq status does
not reliable help, enable acking from any register to be on the safe side
and read the irq status register. Comments in the code indicate a known
unreliability with that register.
The blamed commit was tested with mpu6050 in lg,p895 and lg,p880 according
to Tested-bys. But with the MPU9150 in the Epson Moverio BT-200 this leads
to irq storms without properly acking the irq.

Fixes: 0a3b517c8089 ("iio: imu: inv_mpu6050: fix interrupt status read for old buggy chips")
Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Acked-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_mpu6050/inv_mpu_core.c    | 8 ++++++++
 drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h     | 2 ++
 drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c | 5 ++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index b2fa1f4957a5..5796896d54cd 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -1943,6 +1943,14 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name,
 			irq_type);
 		return -EINVAL;
 	}
+
+	/*
+	 * Acking interrupts by status register does not work reliably
+	 * but seem to work when this bit is set.
+	 */
+	if (st->chip_type == INV_MPU9150)
+		st->irq_mask |= INV_MPU6050_INT_RD_CLEAR;
+
 	device_set_wakeup_capable(dev, true);
 
 	st->vdd_supply = devm_regulator_get(dev, "vdd");
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
index 211901f8b8eb..6239b1a803f7 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
@@ -390,6 +390,8 @@ struct inv_mpu6050_state {
 /* enable level triggering */
 #define INV_MPU6050_LATCH_INT_EN	0x20
 #define INV_MPU6050_BIT_BYPASS_EN	0x2
+/* allow acking interrupts by any register read */
+#define INV_MPU6050_INT_RD_CLEAR	0x10
 
 /* Allowed timestamp period jitter in percent */
 #define INV_MPU6050_TS_PERIOD_JITTER	4
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 10a473342075..22c1ce66f99e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -248,7 +248,6 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
 	switch (st->chip_type) {
 	case INV_MPU6000:
 	case INV_MPU6050:
-	case INV_MPU9150:
 		/*
 		 * WoM is not supported and interrupt status read seems to be broken for
 		 * some chips. Since data ready is the only interrupt, bypass interrupt
@@ -257,6 +256,10 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
 		wom_bits = 0;
 		int_status = INV_MPU6050_BIT_RAW_DATA_RDY_INT;
 		goto data_ready_interrupt;
+	case INV_MPU9150:
+		/* IRQ needs to be acked */
+		wom_bits = 0;
+		break;
 	case INV_MPU6500:
 	case INV_MPU6515:
 	case INV_MPU6880:
-- 
cgit v1.2.3


From 85e4614524dca6c0a43874f475a17de2b9725648 Mon Sep 17 00:00:00 2001
From: Lukas Schmid <lukas.schmid@netcube.li>
Date: Mon, 2 Feb 2026 21:15:35 +0100
Subject: iio: potentiometer: mcp4131: fix double application of wiper shift

The MCP4131 wiper address is shifted twice when preparing the SPI
command in mcp4131_write_raw().

The address is already shifted when assigned to the local variable
"address", but is then shifted again when written to data->buf[0].
This results in an incorrect command being sent to the device and
breaks wiper writes to the second channel.

Remove the second shift and use the pre-shifted address directly
when composing the SPI transfer.

Fixes: 22d199a53910 ("iio: potentiometer: add driver for Microchip MCP413X/414X/415X/416X/423X/424X/425X/426X")
Signed-off-by: Lukas Schmid <lukas.schmid@netcube.li>#
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/potentiometer/mcp4131.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/potentiometer/mcp4131.c b/drivers/iio/potentiometer/mcp4131.c
index ad082827aad5..56c9111ef5e8 100644
--- a/drivers/iio/potentiometer/mcp4131.c
+++ b/drivers/iio/potentiometer/mcp4131.c
@@ -221,7 +221,7 @@ static int mcp4131_write_raw(struct iio_dev *indio_dev,
 
 	mutex_lock(&data->lock);
 
-	data->buf[0] = address << MCP4131_WIPER_SHIFT;
+	data->buf[0] = address;
 	data->buf[0] |= MCP4131_WRITE | (val >> 8);
 	data->buf[1] = val & 0xFF; /* 8 bits here */
 
-- 
cgit v1.2.3


From 7ef74d961d1ad6ec72b50887ca119d7f98f07717 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Thu, 5 Feb 2026 17:59:14 +0100
Subject: iio: imu: inv_icm45600: fix INT1 drive bit inverted

Drive bit must be set for open-drain mode and be cleared for push-pull
mode.

Referring to datasheet DS-000576_ICM-45605.pdf section 17.23
INT1_CONFIG2.

Fixes: 06674a72cf7a ("iio: imu: inv_icm45600: add buffer support in iio devices")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm45600/inv_icm45600.h      | 2 +-
 drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600.h b/drivers/iio/imu/inv_icm45600/inv_icm45600.h
index c5b5446f6c3b..1c796d4b2a40 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600.h
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600.h
@@ -205,7 +205,7 @@ struct inv_icm45600_sensor_state {
 #define INV_ICM45600_SPI_SLEW_RATE_38NS			0
 
 #define INV_ICM45600_REG_INT1_CONFIG2			0x0018
-#define INV_ICM45600_INT1_CONFIG2_PUSH_PULL		BIT(2)
+#define INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN		BIT(2)
 #define INV_ICM45600_INT1_CONFIG2_LATCHED		BIT(1)
 #define INV_ICM45600_INT1_CONFIG2_ACTIVE_HIGH		BIT(0)
 #define INV_ICM45600_INT1_CONFIG2_ACTIVE_LOW		0x00
diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
index 25bd9757a594..e4638926a10c 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
@@ -637,8 +637,8 @@ static int inv_icm45600_irq_init(struct inv_icm45600_state *st, int irq,
 		break;
 	}
 
-	if (!open_drain)
-		val |= INV_ICM45600_INT1_CONFIG2_PUSH_PULL;
+	if (open_drain)
+		val |= INV_ICM45600_INT1_CONFIG2_OPEN_DRAIN;
 
 	ret = regmap_write(st->map, INV_ICM45600_REG_INT1_CONFIG2, val);
 	if (ret)
-- 
cgit v1.2.3


From 5187e03b817c26c1c3bcb2645a612ea935c4be89 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 4 Feb 2026 15:00:33 +0100
Subject: iio: dac: ds4424: reject -128 RAW value

The DS442x DAC uses sign-magnitude encoding, so -128 cannot be represented
in hardware (7-bit magnitude).

Previously, passing -128 resulted in a truncated value that programmed
0mA (magnitude 0) instead of the expected maximum negative current,
effectively failing silently.

Reject -128 to avoid producing the wrong current.

Fixes: d632a2bd8ffc ("iio: dac: ds4422/ds4424 dac driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ds4424.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ds4424.c b/drivers/iio/dac/ds4424.c
index 6dda8918975a..c61868f2de31 100644
--- a/drivers/iio/dac/ds4424.c
+++ b/drivers/iio/dac/ds4424.c
@@ -140,7 +140,7 @@ static int ds4424_write_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		if (val < S8_MIN || val > S8_MAX)
+		if (val <= S8_MIN || val > S8_MAX)
 			return -EINVAL;
 
 		if (val > 0) {
-- 
cgit v1.2.3


From f55b9510cd9437da3a0efa08b089caeb47595ff1 Mon Sep 17 00:00:00 2001
From: Chris Spencer <spencercw@gmail.com>
Date: Thu, 5 Feb 2026 14:55:45 +0000
Subject: iio: chemical: bme680: Fix measurement wait duration calculation

This function refers to the Bosch BME680 API as the source of the
calculation, but one of the constants does not match the Bosch
implementation. This appears to be a simple transposition of two digits,
resulting in a wait time that is too short. This can cause the following
'device measurement cycle incomplete' check to occasionally fail, returning
EBUSY to user space.

Adjust the constant to match the Bosch implementation and resolve the EBUSY
errors.

Fixes: 4241665e6ea0 ("iio: chemical: bme680: Fix sensor data read operation")
Link: https://github.com/boschsensortec/BME68x_SensorAPI/blob/v4.4.8/bme68x.c#L521
Signed-off-by: Chris Spencer <spencercw@gmail.com>
Acked-by: Vasileios Amoiridis <vassilisamir@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/bme680_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c
index 70f81c4a96ba..24e0b59e2fdf 100644
--- a/drivers/iio/chemical/bme680_core.c
+++ b/drivers/iio/chemical/bme680_core.c
@@ -613,7 +613,7 @@ static int bme680_wait_for_eoc(struct bme680_data *data)
 	 * + heater duration
 	 */
 	int wait_eoc_us = ((data->oversampling_temp + data->oversampling_press +
-			   data->oversampling_humid) * 1936) + (477 * 4) +
+			   data->oversampling_humid) * 1963) + (477 * 4) +
 			   (477 * 5) + 1000 + (data->heater_dur * 1000);
 
 	fsleep(wait_eoc_us);
-- 
cgit v1.2.3


From 585b90c0161ab77416fe3acdbdc55b978e33e16c Mon Sep 17 00:00:00 2001
From: Yasin Lee <yasin.lee.x@gmail.com>
Date: Fri, 13 Feb 2026 23:14:43 +0800
Subject: iio: proximity: hx9023s: fix assignment order for __counted_by

Initialize fw_size before copying firmware data into the flexible
array member to match the __counted_by() annotation. This fixes the
incorrect assignment order that triggers runtime safety checks.

Fixes: e9ed97be4fcc ("iio: proximity: hx9023s: Added firmware file parsing functionality")
Signed-off-by: Yasin Lee <yasin.lee.x@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/hx9023s.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index 2918dfc0df54..ad839db6b326 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -1034,9 +1034,8 @@ static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data
 	if (!bin)
 		return -ENOMEM;
 
-	memcpy(bin->data, fw->data, fw->size);
-
 	bin->fw_size = fw->size;
+	memcpy(bin->data, fw->data, bin->fw_size);
 	bin->fw_ver = bin->data[FW_VER_OFFSET];
 	bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET);
 
-- 
cgit v1.2.3


From a318cfc0853706f1d6ce682dba660bc455d674ef Mon Sep 17 00:00:00 2001
From: Yasin Lee <yasin.lee.x@gmail.com>
Date: Fri, 13 Feb 2026 23:14:44 +0800
Subject: iio: proximity: hx9023s: Protect against division by zero in
 set_samp_freq

Avoid division by zero when sampling frequency is unspecified.

Fixes: 60df548277b7 ("iio: proximity: Add driver support for TYHX's HX9023S capacitive proximity sensor")
Signed-off-by: Yasin Lee <yasin.lee.x@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/hx9023s.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index ad839db6b326..17e00ee2b6f8 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -719,6 +719,9 @@ static int hx9023s_set_samp_freq(struct hx9023s_data *data, int val, int val2)
 	struct device *dev = regmap_get_device(data->regmap);
 	unsigned int i, period_ms;
 
+	if (!val && !val2)
+		return -EINVAL;
+
 	period_ms = div_u64(NANO, (val * MEGA + val2));
 
 	for (i = 0; i < ARRAY_SIZE(hx9023s_samp_freq_table); i++) {
-- 
cgit v1.2.3


From 82ee91d6b15f06b6094eea2c26afe0032fe8e177 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Tue, 10 Feb 2026 18:49:50 +0200
Subject: iio: magnetometer: tlv493d: remove erroneous shift in X-axis data

TLV493D_BX2_MAG_X_AXIS_LSB is defined as GENMASK(7, 4). FIELD_GET()
already right-shifts bits [7:4] to [3:0], so the additional >> 4
discards most of the X-axis low nibble. The Y and Z axes correctly
omit this extra shift. Remove it.

Fixes: 106511d280c7 ("iio: magnetometer: add support for Infineon TLV493D 3D Magentic sensor")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/magnetometer/tlv493d.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/magnetometer/tlv493d.c b/drivers/iio/magnetometer/tlv493d.c
index ec53fd40277b..e5e050af2b74 100644
--- a/drivers/iio/magnetometer/tlv493d.c
+++ b/drivers/iio/magnetometer/tlv493d.c
@@ -171,7 +171,7 @@ static s16 tlv493d_get_channel_data(u8 *b, enum tlv493d_channels ch)
 	switch (ch) {
 	case TLV493D_AXIS_X:
 		val = FIELD_GET(TLV493D_BX_MAG_X_AXIS_MSB, b[TLV493D_RD_REG_BX]) << 4 |
-		      FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]) >> 4;
+		      FIELD_GET(TLV493D_BX2_MAG_X_AXIS_LSB, b[TLV493D_RD_REG_BX2]);
 		break;
 	case TLV493D_AXIS_Y:
 		val = FIELD_GET(TLV493D_BY_MAG_Y_AXIS_MSB, b[TLV493D_RD_REG_BY]) << 4 |
-- 
cgit v1.2.3


From 216345f98cae7fcc84f49728c67478ac00321c87 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Feb 2026 14:46:07 +0200
Subject: iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas()

sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead
of the intended __be32 element size (4 bytes). Use sizeof(*meas) to
correctly match the buffer element type.

Fixes: 8f3f13085278 ("iio: sps30: separate core and interface specific code")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Acked-by: Tomasz Duszynski <tduszyns@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/sps30_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c
index f692c089d17b..c92f04990c34 100644
--- a/drivers/iio/chemical/sps30_i2c.c
+++ b/drivers/iio/chemical/sps30_i2c.c
@@ -171,7 +171,7 @@ static int sps30_i2c_read_meas(struct sps30_state *state, __be32 *meas, size_t n
 	if (!sps30_i2c_meas_ready(state))
 		return -ETIMEDOUT;
 
-	return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(num) * num);
+	return sps30_i2c_command(state, SPS30_I2C_READ_MEAS, NULL, 0, meas, sizeof(*meas) * num);
 }
 
 static int sps30_i2c_clean_fan(struct sps30_state *state)
-- 
cgit v1.2.3


From c3914ce1963c4db25e186112c90fa5d2361e9e0a Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Feb 2026 14:46:08 +0200
Subject: iio: chemical: sps30_serial: fix buffer size in
 sps30_serial_read_meas()

sizeof(num) evaluates to sizeof(size_t) which is 8 bytes on 64-bit,
but the buffer elements are only 4 bytes. The same function already
uses sizeof(*meas) on line 312, making the mismatch evident. Use
sizeof(*meas) consistently.

Fixes: b2e171f5a5c6 ("iio: sps30: add support for serial interface")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Acked-by: Tomasz Duszynski <tduszyns@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/chemical/sps30_serial.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c
index 008bc88590f3..a5e6bc08d5fd 100644
--- a/drivers/iio/chemical/sps30_serial.c
+++ b/drivers/iio/chemical/sps30_serial.c
@@ -303,7 +303,7 @@ static int sps30_serial_read_meas(struct sps30_state *state, __be32 *meas, size_
 	if (msleep_interruptible(1000))
 		return -EINTR;
 
-	ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(num));
+	ret = sps30_serial_command(state, SPS30_SERIAL_READ_MEAS, NULL, 0, meas, num * sizeof(*meas));
 	if (ret < 0)
 		return ret;
 	/* if measurements aren't ready sensor returns empty frame */
-- 
cgit v1.2.3


From dd6183e42719cc54057579b8e6be5348cecfeda7 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Sat, 14 Feb 2026 12:46:37 -0600
Subject: iio: adc: ad7768-1: Fix ERR_PTR dereference in ad7768_fill_scale_tbl

The function iio_get_current_scan_type() can return an error pointer,
the return value scan_type is not checked for this and immediately
dereferenced which can cause a kernel panic.

Add check for IS_ERR() and propagate the error back.

Fixes: ff085189cb17 ("iio: adc: ad7768-1: add support for ADAQ776x-1 ADC Family")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202602051234.5gArzLyZ-lkp@intel.com/
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7768-1.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index fcd8aea7152e..e16dede687d3 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -531,7 +531,7 @@ static int ad7768_reg_access(struct iio_dev *indio_dev,
 	return ret;
 }
 
-static void ad7768_fill_scale_tbl(struct iio_dev *dev)
+static int ad7768_fill_scale_tbl(struct iio_dev *dev)
 {
 	struct ad7768_state *st = iio_priv(dev);
 	const struct iio_scan_type *scan_type;
@@ -541,6 +541,11 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev)
 	u64 tmp2;
 
 	scan_type = iio_get_current_scan_type(dev, &dev->channels[0]);
+	if (IS_ERR(scan_type)) {
+		dev_err(&st->spi->dev, "Failed to get scan type.\n");
+		return PTR_ERR(scan_type);
+	}
+
 	if (scan_type->sign == 's')
 		val2 = scan_type->realbits - 1;
 	else
@@ -565,6 +570,8 @@ static void ad7768_fill_scale_tbl(struct iio_dev *dev)
 		st->scale_tbl[i][0] = tmp0; /* Integer part */
 		st->scale_tbl[i][1] = abs(tmp1); /* Fractional part */
 	}
+
+	return 0;
 }
 
 static int ad7768_set_sinc3_dec_rate(struct ad7768_state *st,
@@ -669,7 +676,9 @@ static int ad7768_configure_dig_fil(struct iio_dev *dev,
 	}
 
 	/* Update scale table: scale values vary according to the precision */
-	ad7768_fill_scale_tbl(dev);
+	ret = ad7768_fill_scale_tbl(dev);
+	if (ret)
+		return ret;
 
 	ad7768_fill_samp_freq_tbl(st);
 
-- 
cgit v1.2.3


From 91f950b4cbb1aa9ea4eb3999f1463e8044b717fb Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 16 Feb 2026 11:57:55 +0200
Subject: iio: gyro: mpu3050-i2c: fix pm_runtime error handling

The return value of pm_runtime_get_sync() is not checked, and the
function always returns success. This allows I2C mux operations to
proceed even when the device fails to resume.

Use pm_runtime_resume_and_get() and propagate its return value to
properly handle resume failures.

Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-i2c.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/gyro/mpu3050-i2c.c b/drivers/iio/gyro/mpu3050-i2c.c
index 092878f2c886..6549b22e643d 100644
--- a/drivers/iio/gyro/mpu3050-i2c.c
+++ b/drivers/iio/gyro/mpu3050-i2c.c
@@ -19,8 +19,7 @@ static int mpu3050_i2c_bypass_select(struct i2c_mux_core *mux, u32 chan_id)
 	struct mpu3050 *mpu3050 = i2c_mux_priv(mux);
 
 	/* Just power up the device, that is all that is needed */
-	pm_runtime_get_sync(mpu3050->dev);
-	return 0;
+	return pm_runtime_resume_and_get(mpu3050->dev);
 }
 
 static int mpu3050_i2c_bypass_deselect(struct i2c_mux_core *mux, u32 chan_id)
-- 
cgit v1.2.3


From acc3949aab3e8094641a9c7c2768de1958c88378 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Mon, 16 Feb 2026 11:57:56 +0200
Subject: iio: gyro: mpu3050-core: fix pm_runtime error handling

The return value of pm_runtime_get_sync() is not checked, allowing
the driver to access hardware that may fail to resume. The device
usage count is also unconditionally incremented. Use
pm_runtime_resume_and_get() which propagates errors and avoids
incrementing the usage count on failure.

In preenable, add pm_runtime_put_autosuspend() on set_8khz_samplerate()
failure since postdisable does not run when preenable fails.

Fixes: 3904b28efb2c ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index ee2fcd20545d..317e7b217ec6 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -322,7 +322,9 @@ static int mpu3050_read_raw(struct iio_dev *indio_dev,
 		}
 	case IIO_CHAN_INFO_RAW:
 		/* Resume device */
-		pm_runtime_get_sync(mpu3050->dev);
+		ret = pm_runtime_resume_and_get(mpu3050->dev);
+		if (ret)
+			return ret;
 		mutex_lock(&mpu3050->lock);
 
 		ret = mpu3050_set_8khz_samplerate(mpu3050);
@@ -647,14 +649,20 @@ out_trigger_unlock:
 static int mpu3050_buffer_preenable(struct iio_dev *indio_dev)
 {
 	struct mpu3050 *mpu3050 = iio_priv(indio_dev);
+	int ret;
 
-	pm_runtime_get_sync(mpu3050->dev);
+	ret = pm_runtime_resume_and_get(mpu3050->dev);
+	if (ret)
+		return ret;
 
 	/* Unless we have OUR trigger active, run at full speed */
-	if (!mpu3050->hw_irq_trigger)
-		return mpu3050_set_8khz_samplerate(mpu3050);
+	if (!mpu3050->hw_irq_trigger) {
+		ret = mpu3050_set_8khz_samplerate(mpu3050);
+		if (ret)
+			pm_runtime_put_autosuspend(mpu3050->dev);
+	}
 
-	return 0;
+	return ret;
 }
 
 static int mpu3050_buffer_postdisable(struct iio_dev *indio_dev)
-- 
cgit v1.2.3


From 064234044056c93a3719d6893e6e5a26a94a61b6 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Mon, 16 Feb 2026 13:24:27 +0000
Subject: iio: buffer: Fix wait_queue not being removed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the edge case where the IIO device is unregistered while we're
buffering, we were directly returning an error without removing the wait
queue. Instead, set 'ret' and break out of the loop.

Fixes: 9eeee3b0bf19 ("iio: Add output buffer support")
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-buffer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index f15a180dc49e..46f36a6ed271 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -228,8 +228,10 @@ static ssize_t iio_buffer_write(struct file *filp, const char __user *buf,
 	written = 0;
 	add_wait_queue(&rb->pollq, &wait);
 	do {
-		if (!indio_dev->info)
-			return -ENODEV;
+		if (!indio_dev->info) {
+			ret = -ENODEV;
+			break;
+		}
 
 		if (!iio_buffer_space_available(rb)) {
 			if (signal_pending(current)) {
-- 
cgit v1.2.3


From 2617595538be8a2f270ad13fccb9f56007b292d7 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Tue, 17 Feb 2026 11:44:50 +0100
Subject: iio: imu: inv_icm45600: fix regulator put warning when probe fails

When the driver probe fails we encounter a regulator put warning
because vddio regulator is not stopped before release. The issue
comes from pm_runtime not already setup when core probe fails and
the vddio regulator disable callback is called.

Fix the issue by setting pm_runtime active early before vddio
regulator resource cleanup. This requires to cut pm_runtime
set_active and enable in 2 function calls.

Fixes: 7ff021a3faca ("iio: imu: inv_icm45600: add new inv_icm45600 driver")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm45600/inv_icm45600_core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
index e4638926a10c..d49053161a65 100644
--- a/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
+++ b/drivers/iio/imu/inv_icm45600/inv_icm45600_core.c
@@ -744,6 +744,11 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi
 	 */
 	fsleep(5 * USEC_PER_MSEC);
 
+	/* set pm_runtime active early for disable vddio resource cleanup */
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		return ret;
+
 	ret = inv_icm45600_enable_regulator_vddio(st);
 	if (ret)
 		return ret;
@@ -776,7 +781,7 @@ int inv_icm45600_core_probe(struct regmap *regmap, const struct inv_icm45600_chi
 	if (ret)
 		return ret;
 
-	ret = devm_pm_runtime_set_active_enabled(dev);
+	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 9990cd4f8827bd1ae3fb6eb7407630d8d463c430 Mon Sep 17 00:00:00 2001
From: Radu Sabau <radu.sabau@analog.com>
Date: Fri, 20 Feb 2026 16:16:41 +0200
Subject: iio: imu: adis: Fix NULL pointer dereference in adis_init

The adis_init() function dereferences adis->ops to check if the
individual function pointers (write, read, reset) are NULL, but does
not first check if adis->ops itself is NULL.

Drivers like adis16480, adis16490, adis16545 and others do not set
custom ops and rely on adis_init() assigning the defaults. Since struct
adis is zero-initialized by devm_iio_device_alloc(), adis->ops is NULL
when adis_init() is called, causing a NULL pointer dereference:

    Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
    pc : adis_init+0xc0/0x118
    Call trace:
     adis_init+0xc0/0x118
     adis16480_probe+0xe0/0x670

Fix this by checking if adis->ops is NULL before dereferencing it,
falling through to assign the default ops in that case.

Fixes: 3b29bcee8f6f ("iio: imu: adis: Add custom ops struct")
Signed-off-by: Radu Sabau <radu.sabau@analog.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c
index d160147cce0b..a2bc1d14ed91 100644
--- a/drivers/iio/imu/adis.c
+++ b/drivers/iio/imu/adis.c
@@ -526,7 +526,7 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev,
 
 	adis->spi = spi;
 	adis->data = data;
-	if (!adis->ops->write && !adis->ops->read && !adis->ops->reset)
+	if (!adis->ops)
 		adis->ops = &adis_default_ops;
 	else if (!adis->ops->write || !adis->ops->read || !adis->ops->reset)
 		return -EINVAL;
-- 
cgit v1.2.3


From 25723454f67980712234a42caca606b6710fd1e1 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wenst@chromium.org>
Date: Tue, 10 Feb 2026 18:03:34 +0800
Subject: wifi: mwifiex: Fix dev_alloc_name() return value check

dev_alloc_name() returns the allocated ID on success, which could be
over 0.

Fix the return value check to check for negative error codes.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/aYmsQfujoAe5qO02@stanley.mountain/
Fixes: 7bab5bdb81e3 ("wifi: mwifiex: Allocate dev name earlier for interface workqueue name")
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://patch.msgid.link/20260210100337.1131279-1-wenst@chromium.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index a66d18e380fc..bc0a946e8e6e 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -3148,7 +3148,7 @@ struct wireless_dev *mwifiex_add_virtual_intf(struct wiphy *wiphy,
 	SET_NETDEV_DEV(dev, adapter->dev);
 
 	ret = dev_alloc_name(dev, name);
-	if (ret)
+	if (ret < 0)
 		goto err_alloc_name;
 
 	priv->dfs_cac_workqueue = alloc_workqueue("MWIFIEX_DFS_CAC-%s",
-- 
cgit v1.2.3


From 03cc8f90d0537fcd4985c3319b4fafbf2e3fb1f0 Mon Sep 17 00:00:00 2001
From: Daniel Hodges <git@danielhodges.dev>
Date: Fri, 6 Feb 2026 14:53:56 -0500
Subject: wifi: libertas: fix use-after-free in lbs_free_adapter()

The lbs_free_adapter() function uses timer_delete() (non-synchronous)
for both command_timer and tx_lockup_timer before the structure is
freed. This is incorrect because timer_delete() does not wait for
any running timer callback to complete.

If a timer callback is executing when lbs_free_adapter() is called,
the callback will access freed memory since lbs_cfg_free() frees the
containing structure immediately after lbs_free_adapter() returns.

Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler)
access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields,
which would all be use-after-free violations.

Use timer_delete_sync() instead to ensure any running timer callback
has completed before returning.

This bug was introduced in commit 8f641d93c38a ("libertas: detect TX
lockups and reset hardware") where del_timer() was used instead of
del_timer_sync() in the cleanup path. The command_timer has had the
same issue since the driver was first written.

Fixes: 8f641d93c38a ("libertas: detect TX lockups and reset hardware")
Fixes: 954ee164f4f4 ("[PATCH] libertas: reorganize and simplify init sequence")
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Hodges <git@danielhodges.dev>
Link: https://patch.msgid.link/20260206195356.15647-1-git@danielhodges.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/libertas/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c
index d44e02c6fe38..dd97f1b61f4d 100644
--- a/drivers/net/wireless/marvell/libertas/main.c
+++ b/drivers/net/wireless/marvell/libertas/main.c
@@ -799,8 +799,8 @@ static void lbs_free_adapter(struct lbs_private *priv)
 {
 	lbs_free_cmd_buffer(priv);
 	kfifo_free(&priv->event_fifo);
-	timer_delete(&priv->command_timer);
-	timer_delete(&priv->tx_lockup_timer);
+	timer_delete_sync(&priv->command_timer);
+	timer_delete_sync(&priv->tx_lockup_timer);
 }
 
 static const struct net_device_ops lbs_netdev_ops = {
-- 
cgit v1.2.3


From 2259d14499d16b115ef8d5d2ddc867e2be7cb5b5 Mon Sep 17 00:00:00 2001
From: Ramanathan Choodamani <quic_rchoodam@quicinc.com>
Date: Thu, 5 Feb 2026 15:12:16 +0530
Subject: wifi: mac80211: set default WMM parameters on all links

Currently, mac80211 only initializes default WMM parameters
on the deflink during do_open(). For MLO cases, this
leaves the additional links without proper WMM defaults
if hostapd does not supply per-link WMM parameters, leading
to inconsistent QoS behavior across links.

Set default WMM parameters for each link during
ieee80211_vif_update_links(), because this ensures all
individual links in an MLD have valid WMM settings during
bring-up and behave consistently across different BSS.

Signed-off-by: Ramanathan Choodamani <quic_rchoodam@quicinc.com>
Signed-off-by: Aishwarya R <aishwarya.r@oss.qualcomm.com>
Link: https://patch.msgid.link/20260205094216.3093542-1-aishwarya.r@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/link.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 17bf55dabd31..a1f67bab8ba1 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -281,6 +281,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS];
 	struct ieee80211_link_data *old_data[IEEE80211_MLD_MAX_NUM_LINKS];
 	bool use_deflink = old_links == 0; /* set for error case */
+	bool non_sta = sdata->vif.type != NL80211_IFTYPE_STATION;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
@@ -337,6 +338,7 @@ static int ieee80211_vif_update_links(struct ieee80211_sub_if_data *sdata,
 		link = links[link_id];
 		ieee80211_link_init(sdata, link_id, &link->data, &link->conf);
 		ieee80211_link_setup(&link->data);
+		ieee80211_set_wmm_default(&link->data, true, non_sta);
 	}
 
 	if (new_links == 0)
-- 
cgit v1.2.3


From 1cb3c20688fc8380c9b365d03aea7e84faf6a9fd Mon Sep 17 00:00:00 2001
From: Sean Rhodes <sean@starlabs.systems>
Date: Thu, 19 Feb 2026 20:14:26 +0000
Subject: ALSA: hda/realtek: Fix speaker pop on Star Labs StarFighter

On Star Labs StarFighter (Realtek ALC233/235), the internal speakers can
emit an audible pop when entering or leaving runtime suspend.

Mute the speaker output paths via snd_hda_gen_shutup_speakers() in the
Realtek shutup callback before the codec is powered down.

This is enough to avoid the pop without special EAPD handling.

Test results:
- runtime PM pop fixed
- still reaches D3 (PCI 0000:00:1f.3 power_state=D3hot)
- does not address pops on cold boot (G3 exit) or around display manager
  start/shutdown

journalctl -k (boot):
- snd_hda_codec_alc269 hdaudioC0D0: ALC233: picked fixup for PCI SSID
  7017:2014
- snd_hda_codec_alc269 hdaudioC0D0: autoconfig for ALC233: line_outs=1
  (0x1b/0x0/0x0/0x0/0x0) type:speaker

Suggested-by: Takashi Iwai <tiwai@suse.com>
Tested-by: Sean Rhodes <sean@starlabs.systems>
Signed-off-by: Sean Rhodes <sean@starlabs.systems>
Link: https://patch.msgid.link/4d5fb71b132bb283fd41c622b8413770b2065242.1771532060.git.sean@starlabs.systems
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 36053042ca77..9f64bb97c3f9 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -1017,6 +1017,24 @@ static int alc269_resume(struct hda_codec *codec)
 	return 0;
 }
 
+#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS	30
+
+static void starlabs_starfighter_shutup(struct hda_codec *codec)
+{
+	if (snd_hda_gen_shutup_speakers(codec))
+		msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS);
+}
+
+static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec,
+					      const struct hda_fixup *fix,
+					      int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->shutup = starlabs_starfighter_shutup;
+}
+
 static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec,
 						 const struct hda_fixup *fix, int action)
 {
@@ -4040,6 +4058,7 @@ enum {
 	ALC245_FIXUP_CLEVO_NOISY_MIC,
 	ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE,
 	ALC233_FIXUP_MEDION_MTL_SPK,
+	ALC233_FIXUP_STARLABS_STARFIGHTER,
 	ALC294_FIXUP_BASS_SPEAKER_15,
 	ALC283_FIXUP_DELL_HP_RESUME,
 	ALC294_FIXUP_ASUS_CS35L41_SPI_2,
@@ -6499,6 +6518,10 @@ static const struct hda_fixup alc269_fixups[] = {
 			{ }
 		},
 	},
+	[ALC233_FIXUP_STARLABS_STARFIGHTER] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_starlabs_starfighter,
+	},
 	[ALC294_FIXUP_BASS_SPEAKER_15] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc294_fixup_bass_speaker_15,
@@ -7651,6 +7674,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x2782, 0x4900, "MEDION E15443", ALC233_FIXUP_MEDION_MTL_SPK),
+	SND_PCI_QUIRK(0x7017, 0x2014, "Star Labs StarFighter", ALC233_FIXUP_STARLABS_STARFIGHTER),
 	SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC),
 	SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED),
 	SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10),
@@ -7747,6 +7771,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"},
 	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
+	{.id = ALC233_FIXUP_STARLABS_STARFIGHTER, .name = "starlabs-starfighter"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
 	{.id = ALC269_FIXUP_SONY_VAIO, .name = "vaio"},
 	{.id = ALC269_FIXUP_DELL_M101Z, .name = "dell-m101z"},
-- 
cgit v1.2.3


From 1d241483368f2fd87fbaba64d6aec6bad3a1e12e Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Fri, 20 Feb 2026 21:58:48 +1030
Subject: ALSA: scarlett2: Fix DSP filter control array handling

scarlett2_add_dsp_ctls() was incorrectly storing the precomp and PEQ
filter coefficient control pointers into the precomp_flt_switch_ctls
and peq_flt_switch_ctls arrays instead of the intended targets
precomp_flt_ctls and peq_flt_ctls. Pass NULL instead, as the filter
coefficient control pointers are not used, and remove the unused
precomp_flt_ctls and peq_flt_ctls arrays from struct scarlett2_data.

Additionally, scarlett2_update_filter_values() was reading
dsp_input_count * peq_flt_count values for
SCARLETT2_CONFIG_PEQ_FLT_SWITCH, but the peq_flt_switch array is
indexed only by dsp_input_count (one switch per DSP input, not per
filter). Fix the read count.

Fixes: b64678eb4e70 ("ALSA: scarlett2: Add DSP controls")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://patch.msgid.link/86497b71db060677d97c38a6ce5f89bb3b25361b.1771581197.git.g@b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_scarlett2.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index 85a0316889d4..ef3150581eab 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -1328,8 +1328,6 @@ struct scarlett2_data {
 	struct snd_kcontrol *mux_ctls[SCARLETT2_MUX_MAX];
 	struct snd_kcontrol *mix_ctls[SCARLETT2_MIX_MAX];
 	struct snd_kcontrol *compressor_ctls[SCARLETT2_COMPRESSOR_CTLS_MAX];
-	struct snd_kcontrol *precomp_flt_ctls[SCARLETT2_PRECOMP_FLT_CTLS_MAX];
-	struct snd_kcontrol *peq_flt_ctls[SCARLETT2_PEQ_FLT_CTLS_MAX];
 	struct snd_kcontrol *precomp_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX];
 	struct snd_kcontrol *peq_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX];
 	struct snd_kcontrol *direct_monitor_ctl;
@@ -3447,7 +3445,6 @@ static int scarlett2_update_autogain(struct usb_mixer_interface *mixer)
 			private->autogain_status[i] =
 				private->num_autogain_status_texts - 1;
 
-
 	for (i = 0; i < SCARLETT2_AG_TARGET_COUNT; i++)
 		if (scarlett2_has_config_item(private,
 					      scarlett2_ag_target_configs[i])) {
@@ -5372,8 +5369,7 @@ static int scarlett2_update_filter_values(struct usb_mixer_interface *mixer)
 
 	err = scarlett2_usb_get_config(
 		mixer, SCARLETT2_CONFIG_PEQ_FLT_SWITCH,
-		info->dsp_input_count * info->peq_flt_count,
-		private->peq_flt_switch);
+		info->dsp_input_count, private->peq_flt_switch);
 	if (err < 0)
 		return err;
 
@@ -6546,7 +6542,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i)
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_precomp_flt_ctl,
 			i * info->precomp_flt_count + j,
-			1, s, &private->precomp_flt_switch_ctls[j]);
+			1, s, NULL);
 		if (err < 0)
 			return err;
 	}
@@ -6556,7 +6552,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i)
 		err = scarlett2_add_new_ctl(
 			mixer, &scarlett2_peq_flt_ctl,
 			i * info->peq_flt_count + j,
-			1, s, &private->peq_flt_switch_ctls[j]);
+			1, s, NULL);
 		if (err < 0)
 			return err;
 	}
-- 
cgit v1.2.3


From cbddd303416456db5ceeedaf9e262096f079e861 Mon Sep 17 00:00:00 2001
From: Panagiotis Foliadis <pfoliadis@posteo.net>
Date: Sat, 21 Feb 2026 19:40:58 +0000
Subject: ALSA: hda/realtek: Add quirk for Acer Aspire V3-572G

The Acer Aspire V3-572G has a combo jack (ALC283) but the BIOS
sets pin 0x19 to 0x411111f0 (not connected), so the headset mic
is not detected.

Add a quirk to override pin 0x19 as a headset mic and enable
headset mode.

Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221075
Suggested-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Panagiotis Foliadis <pfoliadis@posteo.net>
Reviewed-by: Charalampos Mitrodimas <charmitro@posteo.net>
Link: https://patch.msgid.link/20260221-fix-detect-mic-v1-1-b6e427b5275d@posteo.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 9f64bb97c3f9..bba173645b1f 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6614,6 +6614,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
+	SND_PCI_QUIRK(0x1025, 0x0943, "Acer Aspire V3-572G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
-- 
cgit v1.2.3


From 43a44fb7f2fa163926b23149805e989ba2395db1 Mon Sep 17 00:00:00 2001
From: Juhyung Park <qkrwngud825@gmail.com>
Date: Sun, 22 Feb 2026 21:26:08 +0900
Subject: ALSA: hda/realtek: fix model name typo for Samsung Galaxy Book Flex
 (NT950QCG-X716)

There's no product named "Samsung Galaxy Flex Book".
Use the correct "Samsung Galaxy Book Flex" name.

Link: https://www.samsung.com/sec/support/model/NT950QCG-X716
Link: https://www.samsung.com/us/computing/galaxy-books/galaxy-book-flex/galaxy-book-flex-15-6-qled-512gb-storage-s-pen-included-np950qcg-k01us
Cc: <stable@vger.kernel.org>
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Link: https://patch.msgid.link/20260222122609.281191-1-qkrwngud825@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index bba173645b1f..7166cbeb0925 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7335,7 +7335,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
-	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),
-- 
cgit v1.2.3


From 9fb16a5c5ff93058851099a2b80a899b0c53fe3f Mon Sep 17 00:00:00 2001
From: Juhyung Park <qkrwngud825@gmail.com>
Date: Sun, 22 Feb 2026 21:26:09 +0900
Subject: ALSA: hda/realtek: add quirk for Samsung Galaxy Book Flex
 (NT950QCT-A38A)

Similar to other Samsung laptops, NT950QCT also requires the
ALC298_FIXUP_SAMSUNG_AMP quirk applied.

Cc: <stable@vger.kernel.org>
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Link: https://patch.msgid.link/20260222122609.281191-2-qkrwngud825@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 7166cbeb0925..43ecfc63ef87 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7335,6 +7335,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
-- 
cgit v1.2.3


From 24d2d3c5f94007a5a0554065ab7349bb69e28bcb Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:33:45 +1030
Subject: ALSA: usb-audio: Improve Focusrite sample rate filtering

Replace the bLength == 10 max_rate check in
focusrite_valid_sample_rate() with filtering that also examines the
bmControls VAL_ALT_SETTINGS bit.

When VAL_ALT_SETTINGS is readable, the device uses strict
per-altsetting rate filtering (only the highest rate pair for that
altsetting is valid). When it is not readable, all rates up to
max_rate are valid.

For devices without the bLength == 10 Format Type descriptor extension
but with VAL_ALT_SETTINGS readable and multiple altsettings (only seen
in Scarlett 18i8 3rd Gen playback), fall back to the Focusrite
convention: alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.

This produces correct rate tables for all tested Focusrite devices
(all Scarlett 2nd, 3rd, and 4th Gen, Clarett+, and Vocaster) using
only USB descriptors, allowing QUIRK_FLAG_VALIDATE_RATES to be removed
for Focusrite in the next commit.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/7e18c1f393a6ecb6fc75dd867a2c4dbe135e3e22.1771594828.git.g@b4.vu
---
 sound/usb/format.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 65 insertions(+), 5 deletions(-)

diff --git a/sound/usb/format.c b/sound/usb/format.c
index 64cfe4a9d8cd..1207c507882a 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -305,17 +305,48 @@ static bool s1810c_valid_sample_rate(struct audioformat *fp,
 }
 
 /*
- * Many Focusrite devices supports a limited set of sampling rates per
- * altsetting. Maximum rate is exposed in the last 4 bytes of Format Type
- * descriptor which has a non-standard bLength = 10.
+ * Focusrite devices use rate pairs: 44100/48000, 88200/96000, and
+ * 176400/192000. Return true if rate is in the pair for max_rate.
+ */
+static bool focusrite_rate_pair(unsigned int rate,
+				unsigned int max_rate)
+{
+	switch (max_rate) {
+	case 48000:  return rate == 44100 || rate == 48000;
+	case 96000:  return rate == 88200 || rate == 96000;
+	case 192000: return rate == 176400 || rate == 192000;
+	default:     return true;
+	}
+}
+
+/*
+ * Focusrite devices report all supported rates in a single clock
+ * source but only a subset is valid per altsetting.
+ *
+ * Detection uses two descriptor features:
+ *
+ * 1. Format Type descriptor bLength == 10: non-standard extension
+ *    with max sample rate in bytes 6..9.
+ *
+ * 2. bmControls VAL_ALT_SETTINGS readable bit: when set, the device
+ *    only supports the highest rate pair for that altsetting, and when
+ *    clear, all rates up to max_rate are valid.
+ *
+ * For devices without the bLength == 10 extension but with
+ * VAL_ALT_SETTINGS readable and multiple altsettings (only seen in
+ * Scarlett 18i8 3rd Gen playback), fall back to the Focusrite
+ * convention: alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.
  */
 static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 					struct audioformat *fp,
 					unsigned int rate)
 {
+	struct usb_interface *iface;
 	struct usb_host_interface *alts;
+	struct uac2_as_header_descriptor *as;
 	unsigned char *fmt;
 	unsigned int max_rate;
+	bool val_alt;
 
 	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
 	if (!alts)
@@ -326,9 +357,21 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 	if (!fmt)
 		return true;
 
+	as = snd_usb_find_csint_desc(alts->extra, alts->extralen,
+				     NULL, UAC_AS_GENERAL);
+	if (!as)
+		return true;
+
+	val_alt = uac_v2v3_control_is_readable(as->bmControls,
+					       UAC2_AS_VAL_ALT_SETTINGS);
+
 	if (fmt[0] == 10) { /* bLength */
 		max_rate = combine_quad(&fmt[6]);
 
+		if (val_alt)
+			return focusrite_rate_pair(rate, max_rate);
+
+		/* No val_alt: rates fall through from higher */
 		switch (max_rate) {
 		case 192000:
 			if (rate == 176400 || rate == 192000)
@@ -344,12 +387,29 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 			usb_audio_info(chip,
 				"%u:%d : unexpected max rate: %u\n",
 				fp->iface, fp->altsetting, max_rate);
-
 			return true;
 		}
 	}
 
-	return true;
+	if (!val_alt)
+		return true;
+
+	/* Multi-altsetting device with val_alt but no max_rate
+	 * in the format descriptor. Use Focusrite convention:
+	 * alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz.
+	 */
+	iface = usb_ifnum_to_if(chip->dev, fp->iface);
+	if (!iface || iface->num_altsetting <= 2)
+		return true;
+
+	switch (fp->altsetting) {
+	case 1:		max_rate = 48000; break;
+	case 2:		max_rate = 96000; break;
+	case 3:		max_rate = 192000; break;
+	default:	return true;
+	}
+
+	return focusrite_rate_pair(rate, max_rate);
 }
 
 /*
-- 
cgit v1.2.3


From a8cc55bf81a45772cad44c83ea7bb0e98431094a Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:34:48 +1030
Subject: ALSA: usb-audio: Remove VALIDATE_RATES quirk for Focusrite devices

Remove QUIRK_FLAG_VALIDATE_RATES for Focusrite. With the previous
commit, focusrite_valid_sample_rate() produces correct rate tables
without USB probing.

QUIRK_FLAG_VALIDATE_RATES sends SET_CUR requests for each rate (~25ms
each) and leaves the device at 192kHz. This is a problem because that
rate: 1) disables the internal mixer, so outputs are silent until an
application opens the PCM and sets a lower rate, and 2) the Air and
Safe modes get disabled.

Fixes: 5963e5262180 ("ALSA: usb-audio: Enable rate validation for Scarlett devices")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/09b9c012024c998c4ca14bd876ef0dce0d0b6101.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 4cac0dfb0094..3164c9431d29 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,7 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
-		   QUIRK_FLAG_VALIDATE_RATES),
+		   0),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),
 	VENDOR_FLG(0x152a, /* Thesycon devices */
-- 
cgit v1.2.3


From 38c322068a26a01d7ff64da92179e68cdde9860b Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:36:35 +1030
Subject: ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP

Add a quirk flag to skip the usb_set_interface(),
snd_usb_init_pitch(), and snd_usb_init_sample_rate() calls in
__snd_usb_parse_audio_interface(). These are redundant with
snd_usb_endpoint_prepare() at stream-open time.

Enable the quirk for Focusrite devices, as init_sample_rate(rate_max)
sets 192kHz during probing, which disables the internal mixer and Air
and Safe modes.

Fixes: 16f1f838442d ("Revert "ALSA: usb-audio: Drop superfluous interface setup at parsing"")
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/65a7909b15f9feb76c2a6f4f8814c240ddc50737.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c   | 3 ++-
 sound/usb/stream.c   | 3 +++
 sound/usb/usbaudio.h | 6 ++++++
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3164c9431d29..b13d0f4d25ac 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,7 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
-		   0),
+		   QUIRK_FLAG_SKIP_IFACE_SETUP),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),
 	VENDOR_FLG(0x152a, /* Thesycon devices */
@@ -2506,6 +2506,7 @@ static const char *const snd_usb_audio_quirk_flag_names[] = {
 	QUIRK_STRING_ENTRY(MIC_RES_384),
 	QUIRK_STRING_ENTRY(MIXER_PLAYBACK_MIN_MUTE),
 	QUIRK_STRING_ENTRY(MIXER_CAPTURE_MIN_MUTE),
+	QUIRK_STRING_ENTRY(SKIP_IFACE_SETUP),
 	NULL
 };
 
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index ac4d92065dd9..d38c39e28f38 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -1259,6 +1259,9 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip,
 			set_iface_first = true;
 
 		/* try to set the interface... */
+		if (chip->quirk_flags & QUIRK_FLAG_SKIP_IFACE_SETUP)
+			continue;
+
 		usb_set_interface(chip->dev, iface_no, 0);
 		if (set_iface_first)
 			usb_set_interface(chip->dev, iface_no, altno);
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 79978cae9799..085530cf62d9 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -224,6 +224,10 @@ extern bool snd_usb_skip_validation;
  *  playback value represents muted state instead of minimum audible volume
  * QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE
  *  Similar to QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE, but for capture streams
+ * QUIRK_FLAG_SKIP_IFACE_SETUP
+ *  Skip the probe-time interface setup (usb_set_interface,
+ *  init_pitch, init_sample_rate); redundant with
+ *  snd_usb_endpoint_prepare() at stream-open time
  */
 
 enum {
@@ -253,6 +257,7 @@ enum {
 	QUIRK_TYPE_MIC_RES_384			= 23,
 	QUIRK_TYPE_MIXER_PLAYBACK_MIN_MUTE	= 24,
 	QUIRK_TYPE_MIXER_CAPTURE_MIN_MUTE	= 25,
+	QUIRK_TYPE_SKIP_IFACE_SETUP		= 26,
 /* Please also edit snd_usb_audio_quirk_flag_names */
 };
 
@@ -284,5 +289,6 @@ enum {
 #define QUIRK_FLAG_MIC_RES_384			QUIRK_FLAG(MIC_RES_384)
 #define QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE	QUIRK_FLAG(MIXER_PLAYBACK_MIN_MUTE)
 #define QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE	QUIRK_FLAG(MIXER_CAPTURE_MIN_MUTE)
+#define QUIRK_FLAG_SKIP_IFACE_SETUP		QUIRK_FLAG(SKIP_IFACE_SETUP)
 
 #endif /* __USBAUDIO_H */
-- 
cgit v1.2.3


From 0d58273be0b9c3cec3be5488ca37f6ddbaf13cf0 Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Sat, 21 Feb 2026 02:36:56 +1030
Subject: ALSA: usb-audio: Skip clock selector for Focusrite devices

Add QUIRK_FLAG_SKIP_CLOCK_SELECTOR for Focusrite devices.

During interface parsing, snd_usb_clock_find_source() reads the clock
selector value then writes it back unchanged. On Focusrite devices
this redundant write results in a ~300ms delay per altsetting, adding
~1.8s to probe time on a typical device with 6 altsettings.

Enabling SKIP_CLOCK_SELECTOR skips the redundant write-back.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/00e53ae0a508b41516b41833daa17823381a649c.1771594828.git.g@b4.vu
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index b13d0f4d25ac..fbceed8e8d36 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2424,6 +2424,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
+		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),
 	VENDOR_FLG(0x1511, /* AURALiC */
 		   QUIRK_FLAG_DSD_RAW),
-- 
cgit v1.2.3


From 1f96b84835eafb3e6f366dc3a66c0e69504cec9d Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Thu, 5 Feb 2026 13:55:45 +0100
Subject: pinctrl: equilibrium: rename irq_chip function callbacks

Renaming of the irq_chip callback functions to improve clarity.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 48b55c5bf8d4..49c8232b525a 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -23,7 +23,7 @@
 #define PIN_NAME_LEN	10
 #define PAD_REG_OFF	0x100
 
-static void eqbr_gpio_disable_irq(struct irq_data *d)
+static void eqbr_irq_mask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d)
 	gpiochip_disable_irq(gc, offset);
 }
 
-static void eqbr_gpio_enable_irq(struct irq_data *d)
+static void eqbr_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_ack_irq(struct irq_data *d)
+static void eqbr_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -62,10 +62,10 @@ static void eqbr_gpio_ack_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_mask_ack_irq(struct irq_data *d)
+static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_gpio_disable_irq(d);
-	eqbr_gpio_ack_irq(d);
+	eqbr_irq_mask(d);
+	eqbr_irq_ack(d);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
@@ -92,7 +92,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type,
 	return 0;
 }
 
-static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+static int eqbr_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -166,11 +166,11 @@ static void eqbr_irq_handler(struct irq_desc *desc)
 
 static const struct irq_chip eqbr_irq_chip = {
 	.name = "gpio_irq",
-	.irq_mask = eqbr_gpio_disable_irq,
-	.irq_unmask = eqbr_gpio_enable_irq,
-	.irq_ack = eqbr_gpio_ack_irq,
-	.irq_mask_ack = eqbr_gpio_mask_ack_irq,
-	.irq_set_type = eqbr_gpio_set_irq_type,
+	.irq_ack = eqbr_irq_ack,
+	.irq_mask = eqbr_irq_mask,
+	.irq_mask_ack = eqbr_irq_mask_ack,
+	.irq_unmask = eqbr_irq_unmask,
+	.irq_set_type = eqbr_irq_set_type,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
-- 
cgit v1.2.3


From 3e00b1b332e54ba50cca6691f628b9c06574024f Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Thu, 5 Feb 2026 13:55:46 +0100
Subject: pinctrl: equilibrium: fix warning trace on load

The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also
called in the callback function 'eqbr_irq_mask_ack()'. This is done to
avoid source code duplication. The problem, is that in the function
'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()'

This generates the following warning trace in the log for every gpio on
load.

[    6.088111] ------------[ cut here ]------------
[    6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50
[    6.097847] Modules linked in:
[    6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G        W          6.12.59+ #0
[    6.097847] Tainted: [W]=WARN
[    6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50
[    6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40
[    6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046
[    6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008
[    6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0
[    6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000
[    6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514
[    6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000
[    6.097847] FS:  0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000
[    6.097847] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0
[    6.097847] Call Trace:
[    6.097847]  <TASK>
[    6.097847]  ? eqbr_irq_mask+0x63/0x70
[    6.097847]  ? no_action+0x10/0x10
[    6.097847]  eqbr_irq_mask_ack+0x11/0x60

In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the
interrupt is not disabled here.

To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()'
function. Implement instead this directly without disabling the interrupts.

Fixes: 52066a53bd11 ("pinctrl: equilibrium: Convert to immutable irq_chip")
Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-equilibrium.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c
index 49c8232b525a..ba1c867b7b89 100644
--- a/drivers/pinctrl/pinctrl-equilibrium.c
+++ b/drivers/pinctrl/pinctrl-equilibrium.c
@@ -64,8 +64,15 @@ static void eqbr_irq_ack(struct irq_data *d)
 
 static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_irq_mask(d);
-	eqbr_irq_ack(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
+	unsigned int offset = irqd_to_hwirq(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&gctrl->lock, flags);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNCR);
+	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
-- 
cgit v1.2.3


From 09a30b7a035f9f4ac918c8a9af89d70e43462152 Mon Sep 17 00:00:00 2001
From: Maulik Shah <maulik.shah@oss.qualcomm.com>
Date: Mon, 9 Feb 2026 09:33:44 +0530
Subject: pinctrl: qcom: qcs615: Add missing dual edge GPIO IRQ errata flag

Wakeup capable GPIOs uses PDC as parent IRQ chip and PDC on qcs615 do not
support dual edge IRQs. Add missing wakeirq_dual_edge_errata configuration
to enable workaround for dual edge GPIO IRQs.

Fixes: b698f36a9d40 ("pinctrl: qcom: add the tlmm driver for QCS615 platform")
Signed-off-by: Maulik Shah <maulik.shah@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/qcom/pinctrl-qcs615.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
index 4dfa820d4e77..f1c827ddbfbf 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs615.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = {
 	.ntiles = ARRAY_SIZE(qcs615_tiles),
 	.wakeirq_map = qcs615_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static const struct of_device_id qcs615_tlmm_of_match[] = {
-- 
cgit v1.2.3


From 32e0a7ad9c841f46549ccac0f1cca347a40d8685 Mon Sep 17 00:00:00 2001
From: Daniel J Blueman <daniel@quora.org>
Date: Fri, 20 Feb 2026 17:34:51 +0800
Subject: gpio: shared: fix memory leaks

On a Snapdragon X1 Elite laptop (Lenovo Yoga Slim 7x), kmemleak reports
three sets of:

unreferenced object 0xffff00080187f400 (size 1024):
  comm "swapper/0", pid 1, jiffies 4294667327
  hex dump (first 32 bytes):
    58 bd 70 01 08 00 ff ff 58 bd 70 01 08 00 ff ff  X.p.....X.p.....
    00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00  ................
  backtrace (crc 1665d1f8):
    kmemleak_alloc+0xf4/0x12c
    __kmalloc_cache_noprof+0x370/0x49c
    gpio_shared_make_ref+0x70/0x16c
    gpio_shared_of_traverse+0x4e8/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_init+0x34/0x1c4
    do_one_initcall+0x50/0x280
    kernel_init_freeable+0x290/0x33c
    kernel_init+0x28/0x14c
    ret_from_fork+0x10/0x20

unreferenced object 0xffff00080170c140 (size 8):
  comm "swapper/0", pid 1, jiffies 4294667327
  hex dump (first 8 bytes):
    72 65 73 65 74 00 00 00                          reset...
  backtrace (crc fc24536):
    kmemleak_alloc+0xf4/0x12c
    __kmalloc_node_track_caller_noprof+0x3c4/0x584
    kstrdup+0x4c/0xcc
    gpio_shared_make_ref+0x8c/0x16c
    gpio_shared_of_traverse+0x4e8/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_of_traverse+0x200/0x5f4
    gpio_shared_init+0x34/0x1c4
    do_one_initcall+0x50/0x280
    kernel_init_freeable+0x290/0x33c
    kernel_init+0x28/0x14c
    ret_from_fork+0x10/0x20

Fix this by decrementing the reference count of each list entry rather than
only the first.

Fix verified on the same laptop.

Fixes: a060b8c511abb gpiolib: implement low-level, shared GPIO support
Signed-off-by: Daniel J Blueman <daniel@quora.org>
Link: https://patch.msgid.link/20260220093452.101655-1-daniel@quora.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib-shared.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c
index d2614ace4de1..17a7128b6bd9 100644
--- a/drivers/gpio/gpiolib-shared.c
+++ b/drivers/gpio/gpiolib-shared.c
@@ -748,14 +748,14 @@ static bool gpio_shared_entry_is_really_shared(struct gpio_shared_entry *entry)
 static void gpio_shared_free_exclusive(void)
 {
 	struct gpio_shared_entry *entry, *epos;
+	struct gpio_shared_ref *ref, *rpos;
 
 	list_for_each_entry_safe(entry, epos, &gpio_shared_list, list) {
 		if (gpio_shared_entry_is_really_shared(entry))
 			continue;
 
-		gpio_shared_drop_ref(list_first_entry(&entry->refs,
-						      struct gpio_shared_ref,
-						      list));
+		list_for_each_entry_safe(ref, rpos, &entry->refs, list)
+			gpio_shared_drop_ref(ref);
 		gpio_shared_drop_entry(entry);
 	}
 }
-- 
cgit v1.2.3


From 03c0d030f5874eec6ce22750b2b8751d6d4303b5 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Sat, 14 Feb 2026 03:02:48 +0000
Subject: erofs: allow sharing page cache with the same aops only

Inode with identical data but different @aops cannot be mixed
because the page cache is managed by different subsystems (e.g.,
@aops for compressed on-disk inodes cannot handle plain on-disk
inodes).

In this patch, we never allow inodes to share the page cache
among plain, compressed, and fileio cases. When a shared inode
is created, we initialize @aops that is the same as the initial
real inode, and subsequent inodes cannot share the page cache
if the inferred @aops differ from the corresponding shared inode.

This is reasonable as a first step because, in typical use cases,
if an inode is compressible, it will fall into compressed
inodes across different filesystem images unless users use plain
filesystems. However, in that cases, users will use plain
filesystems all the time.

Fixes: 5ef3208e3be5 ("erofs: introduce the page cache share feature")
Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/inode.c    |  7 ++++++-
 fs/erofs/internal.h | 16 +++++++---------
 fs/erofs/ishare.c   | 14 +++++++++-----
 3 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 4f86169c23f1..4b3d21402e10 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -222,6 +222,7 @@ err_out:
 
 static int erofs_fill_inode(struct inode *inode)
 {
+	const struct address_space_operations *aops;
 	int err;
 
 	trace_erofs_fill_inode(inode);
@@ -254,7 +255,11 @@ static int erofs_fill_inode(struct inode *inode)
 	}
 
 	mapping_set_large_folios(inode->i_mapping);
-	return erofs_inode_set_aops(inode, inode, false);
+	aops = erofs_get_aops(inode, false);
+	if (IS_ERR(aops))
+		return PTR_ERR(aops);
+	inode->i_mapping->a_ops = aops;
+	return 0;
 }
 
 /*
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index d1634455e389..a4f0a42cf8c3 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -471,26 +471,24 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
 	return NULL;
 }
 
-static inline int erofs_inode_set_aops(struct inode *inode,
-				       struct inode *realinode, bool no_fscache)
+static inline const struct address_space_operations *
+erofs_get_aops(struct inode *realinode, bool no_fscache)
 {
 	if (erofs_inode_is_data_compressed(EROFS_I(realinode)->datalayout)) {
 		if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP))
-			return -EOPNOTSUPP;
+			return ERR_PTR(-EOPNOTSUPP);
 		DO_ONCE_LITE_IF(realinode->i_blkbits != PAGE_SHIFT,
 			  erofs_info, realinode->i_sb,
 			  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
-		inode->i_mapping->a_ops = &z_erofs_aops;
-		return 0;
+		return &z_erofs_aops;
 	}
-	inode->i_mapping->a_ops = &erofs_aops;
 	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && !no_fscache &&
 	    erofs_is_fscache_mode(realinode->i_sb))
-		inode->i_mapping->a_ops = &erofs_fscache_access_aops;
+		return &erofs_fscache_access_aops;
 	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) &&
 	    erofs_is_fileio_mode(EROFS_SB(realinode->i_sb)))
-		inode->i_mapping->a_ops = &erofs_fileio_aops;
-	return 0;
+		return &erofs_fileio_aops;
+	return &erofs_aops;
 }
 
 int erofs_register_sysfs(struct super_block *sb);
diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c
index ce980320a8b9..829d50d5c717 100644
--- a/fs/erofs/ishare.c
+++ b/fs/erofs/ishare.c
@@ -40,10 +40,14 @@ bool erofs_ishare_fill_inode(struct inode *inode)
 {
 	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
 	struct erofs_inode *vi = EROFS_I(inode);
+	const struct address_space_operations *aops;
 	struct erofs_inode_fingerprint fp;
 	struct inode *sharedinode;
 	unsigned long hash;
 
+	aops = erofs_get_aops(inode, true);
+	if (IS_ERR(aops))
+		return false;
 	if (erofs_xattr_fill_inode_fingerprint(&fp, inode, sbi->domain_id))
 		return false;
 	hash = xxh32(fp.opaque, fp.size, 0);
@@ -56,15 +60,15 @@ bool erofs_ishare_fill_inode(struct inode *inode)
 	}
 
 	if (inode_state_read_once(sharedinode) & I_NEW) {
-		if (erofs_inode_set_aops(sharedinode, inode, true)) {
-			iget_failed(sharedinode);
-			kfree(fp.opaque);
-			return false;
-		}
+		sharedinode->i_mapping->a_ops = aops;
 		sharedinode->i_size = vi->vfs_inode.i_size;
 		unlock_new_inode(sharedinode);
 	} else {
 		kfree(fp.opaque);
+		if (aops != sharedinode->i_mapping->a_ops) {
+			iput(sharedinode);
+			return false;
+		}
 		if (sharedinode->i_size != vi->vfs_inode.i_size) {
 			_erofs_printk(inode->i_sb, KERN_WARNING
 				"size(%lld:%lld) not matches for the same fingerprint\n",
-- 
cgit v1.2.3


From aa280a08e7d8fae58557acc345b36b3dc329d595 Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Tue, 6 Jan 2026 13:15:04 +0000
Subject: x86/fred: Correct speculative safety in fred_extint()

array_index_nospec() is no use if the result gets spilled to the stack, as
it makes the believed safe-under-speculation value subject to memory
predictions.

For all practical purposes, this means array_index_nospec() must be used in
the expression that accesses the array.

As the code currently stands, it's the wrong side of irqentry_enter(), and
'index' is put into %ebp across the function call.

Remove the index variable and reposition array_index_nospec(), so it's
calculated immediately before the array access.

Fixes: 14619d912b65 ("x86/fred: FRED entry/exit and dispatch code")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260106131504.679932-1-andrew.cooper3@citrix.com
---
 arch/x86/entry/entry_fred.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index a9b72997103d..88c757ac8ccd 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -160,8 +160,6 @@ void __init fred_complete_exception_setup(void)
 static noinstr void fred_extint(struct pt_regs *regs)
 {
 	unsigned int vector = regs->fred_ss.vector;
-	unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR,
-						NR_SYSTEM_VECTORS);
 
 	if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR))
 		return;
@@ -170,7 +168,8 @@ static noinstr void fred_extint(struct pt_regs *regs)
 		irqentry_state_t state = irqentry_enter(regs);
 
 		instrumentation_begin();
-		sysvec_table[index](regs);
+		sysvec_table[array_index_nospec(vector - FIRST_SYSTEM_VECTOR,
+						NR_SYSTEM_VECTORS)](regs);
 		instrumentation_end();
 		irqentry_exit(regs, state);
 	} else {
-- 
cgit v1.2.3


From a0cb371b521dde44f32cfe954b6ef6f82b407393 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Sat, 10 Jan 2026 11:47:37 +0800
Subject: x86/bug: Handle __WARN_printf() trap in early_fixup_exception()

The commit 5b472b6e5bd9 ("x86_64/bug: Implement __WARN_printf()")
implemented __WARN_printf(), which changed the mechanism to use UD1
instead of UD2. However, it only handles the trap in the runtime IDT
handler, while the early booting IDT handler lacks this handling. As a
result, the usage of WARN() before the runtime IDT setup can lead to
kernel crashes. Since KMSAN is enabled after the runtime IDT setup, it
is safe to use handle_bug() directly in early_fixup_exception() to
address this issue.

Fixes: 5b472b6e5bd9 ("x86_64/bug: Implement __WARN_printf()")
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/c4fb3645f60d3a78629d9870e8fcc8535281c24f.1768016713.git.houwenlong.hwl@antgroup.com
---
 arch/x86/include/asm/traps.h | 2 ++
 arch/x86/kernel/traps.c      | 2 +-
 arch/x86/mm/extable.c        | 7 ++-----
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 869b88061801..3f24cc472ce9 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -25,6 +25,8 @@ extern int ibt_selftest_noendbr(void);
 void handle_invalid_op(struct pt_regs *regs);
 #endif
 
+noinstr bool handle_bug(struct pt_regs *regs);
+
 static inline int get_si_code(unsigned long condition)
 {
 	if (condition & DR_STEP)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 5a6a772e0a6c..4dbff8ef9b1c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -397,7 +397,7 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
-static noinstr bool handle_bug(struct pt_regs *regs)
+noinstr bool handle_bug(struct pt_regs *regs)
 {
 	unsigned long addr = regs->ip;
 	bool handled = false;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 2fdc1f1f5adb..6b9ff1c6cafa 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -411,14 +411,11 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 		return;
 
 	if (trapnr == X86_TRAP_UD) {
-		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
+		if (handle_bug(regs))
 			return;
-		}
 
 		/*
-		 * If this was a BUG and report_bug returns or if this
+		 * If this was a BUG and handle_bug returns or if this
 		 * was just a normal #UD, we want to continue onward and
 		 * crash.
 		 */
-- 
cgit v1.2.3


From 24c8147abb39618d74fcc36e325765e8fe7bdd7a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Feb 2026 13:59:43 +0100
Subject: x86/cfi: Fix CFI rewrite for odd alignments

Rustam reported his clang builds did not boot properly; turns out his
.config has: CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B=y set.

Fix up the FineIBT code to deal with this unusual alignment.

Fixes: 931ab63664f0 ("x86/ibt: Implement FineIBT")
Reported-by: Rustam Kovhaev <rkovhaev@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Rustam Kovhaev <rkovhaev@gmail.com>
---
 arch/x86/include/asm/cfi.h     | 12 ++++++++----
 arch/x86/include/asm/linkage.h |  4 ++--
 arch/x86/kernel/alternative.c  | 29 ++++++++++++++++++++++-------
 arch/x86/net/bpf_jit_comp.c    | 13 ++-----------
 4 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index c40b9ebc1fb4..ab3fbbd947ed 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -111,6 +111,12 @@ extern bhi_thunk __bhi_args_end[];
 
 struct pt_regs;
 
+#ifdef CONFIG_CALL_PADDING
+#define CFI_OFFSET (CONFIG_FUNCTION_PADDING_CFI+5)
+#else
+#define CFI_OFFSET 5
+#endif
+
 #ifdef CONFIG_CFI
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
 #define __bpfcall
@@ -119,11 +125,9 @@ static inline int cfi_get_offset(void)
 {
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		return 16;
+		return /* fineibt_prefix_size */ 16;
 	case CFI_KCFI:
-		if (IS_ENABLED(CONFIG_CALL_PADDING))
-			return 16;
-		return 5;
+		return CFI_OFFSET;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 9d38ae744a2e..a7294656ad90 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -68,7 +68,7 @@
  * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the
  * CFI symbol layout changes.
  *
- * Without CALL_THUNKS:
+ * Without CALL_PADDING:
  *
  * 	.align	FUNCTION_ALIGNMENT
  * __cfi_##name:
@@ -77,7 +77,7 @@
  * 	.long	__kcfi_typeid_##name
  * name:
  *
- * With CALL_THUNKS:
+ * With CALL_PADDING:
  *
  * 	.align FUNCTION_ALIGNMENT
  * __cfi_##name:
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a888ae0f01fb..e87da25d1236 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1182,7 +1182,7 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 
 		poison_endbr(addr);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16);
+			poison_cfi(addr - CFI_OFFSET);
 	}
 }
 
@@ -1389,6 +1389,8 @@ extern u8 fineibt_preamble_end[];
 #define fineibt_preamble_ud   0x13
 #define fineibt_preamble_hash 5
 
+#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE)
+
 /*
  * <fineibt_caller_start>:
  *  0:   b8 78 56 34 12          mov    $0x12345678, %eax
@@ -1634,7 +1636,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 		 * have determined there are no indirect calls to it and we
 		 * don't need no CFI either.
 		 */
-		if (!is_endbr(addr + 16))
+		if (!is_endbr(addr + CFI_OFFSET))
 			continue;
 
 		hash = decode_preamble_hash(addr, &arity);
@@ -1642,6 +1644,15 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end)
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
+		/*
+		 * FineIBT relies on being at func-16, so if the preamble is
+		 * actually larger than that, place it the tail end.
+		 *
+		 * NOTE: this is possible with things like DEBUG_CALL_THUNKS
+		 * and DEBUG_FORCE_FUNCTION_ALIGN_64B.
+		 */
+		addr += CFI_OFFSET - fineibt_prefix_size;
+
 		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
 		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
 		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
@@ -1664,10 +1675,10 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end)
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
 
-		if (!exact_endbr(addr + 16))
+		if (!exact_endbr(addr + CFI_OFFSET))
 			continue;
 
-		poison_endbr(addr + 16);
+		poison_endbr(addr + CFI_OFFSET);
 	}
 }
 
@@ -1772,7 +1783,8 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	if (FINEIBT_WARN(fineibt_preamble_size, 20)			||
 	    FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20)	||
 	    FINEIBT_WARN(fineibt_caller_size, 14)			||
-	    FINEIBT_WARN(fineibt_paranoid_size, 20))
+	    FINEIBT_WARN(fineibt_paranoid_size, 20)			||
+	    WARN_ON_ONCE(CFI_OFFSET < fineibt_prefix_size))
 		return;
 
 	if (cfi_mode == CFI_AUTO) {
@@ -1885,6 +1897,11 @@ static void poison_cfi(void *addr)
 	 */
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
+		/*
+		 * FineIBT preamble is at func-16.
+		 */
+		addr += CFI_OFFSET - fineibt_prefix_size;
+
 		/*
 		 * FineIBT prefix should start with an ENDBR.
 		 */
@@ -1923,8 +1940,6 @@ static void poison_cfi(void *addr)
 	}
 }
 
-#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE)
-
 /*
  * When regs->ip points to a 0xD6 byte in the FineIBT preamble,
  * return true and fill out target and type.
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8f10080e6fe3..e9b78040d703 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -438,17 +438,8 @@ static void emit_kcfi(u8 **pprog, u32 hash)
 
 	EMIT1_off32(0xb8, hash);			/* movl $hash, %eax	*/
 #ifdef CONFIG_CALL_PADDING
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
-	EMIT1(0x90);
+	for (int i = 0; i < CONFIG_FUNCTION_PADDING_CFI; i++)
+		EMIT1(0x90);
 #endif
 	EMIT_ENDBR();
 
-- 
cgit v1.2.3


From 237dc6a054f6787c2a8f61c59086030267e5e1c5 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 18 Dec 2025 19:20:29 +0100
Subject: x86/headers: Replace __ASSEMBLY__ stragglers with __ASSEMBLER__

After converting the __ASSEMBLY__ statements to __ASSEMBLER__ in
commit 24a295e4ef1ca ("x86/headers: Replace __ASSEMBLY__ with
__ASSEMBLER__ in non-UAPI headers"), some new code has been
added that uses __ASSEMBLY__ again. Convert these stragglers, too.

This is a mechanical patch, done with a simple "sed -i" command.

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251218182029.166993-1-thuth@redhat.com
---
 arch/x86/include/asm/bug.h           | 6 +++---
 arch/x86/include/asm/irqflags.h      | 4 ++--
 arch/x86/include/asm/percpu.h        | 2 +-
 arch/x86/include/asm/runtime-const.h | 6 +++---
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 9b4e04690e1a..80c1696d8d59 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -7,7 +7,7 @@
 #include <linux/objtool.h>
 #include <asm/asm.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct bug_entry;
 extern void __WARN_trap(struct bug_entry *bug, ...);
 #endif
@@ -137,7 +137,7 @@ do {									\
 
 #ifdef HAVE_ARCH_BUG_FORMAT_ARGS
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/static_call_types.h>
 DECLARE_STATIC_CALL(WARN_trap, __WARN_trap);
 
@@ -153,7 +153,7 @@ struct arch_va_list {
 	struct sysv_va_list args;
 };
 extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs);
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define __WARN_bug_entry(flags, format) ({				\
 	struct bug_entry *bug;						\
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index a1193e9d65f2..462754b0bf8a 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -77,7 +77,7 @@ static __always_inline void native_local_irq_restore(unsigned long flags)
 #endif
 
 #ifndef CONFIG_PARAVIRT
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Used in the idle loop; sti takes one instruction cycle
  * to complete:
@@ -95,7 +95,7 @@ static __always_inline void halt(void)
 {
 	native_halt();
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_PARAVIRT */
 
 #ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index c55058f3d75e..409981468cba 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,7 +20,7 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#else /* !__ASSEMBLY__: */
+#else /* !__ASSEMBLER__: */
 
 #include <linux/args.h>
 #include <linux/bits.h>
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index e5a13dc8816e..4cd94fdcb45e 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -6,7 +6,7 @@
   #error "Cannot use runtime-const infrastructure from modules"
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro RUNTIME_CONST_PTR sym reg
 	movq	$0x0123456789abcdef, %\reg
@@ -16,7 +16,7 @@
 	.popsection
 .endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define runtime_const_ptr(sym) ({				\
 	typeof(sym) __ret;					\
@@ -74,5 +74,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 	}
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif
-- 
cgit v1.2.3


From b3d99f43c72b56cf7a104a364e7fb34b0702828b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 9 Feb 2026 15:28:16 +0100
Subject: sched/fair: Fix zero_vruntime tracking

It turns out that zero_vruntime tracking is broken when there is but a single
task running. Current update paths are through __{en,de}queue_entity(), and
when there is but a single task, pick_next_task() will always return that one
task, and put_prev_set_next_task() will end up in neither function.

This can cause entity_key() to grow indefinitely large and cause overflows,
leading to much pain and suffering.

Furtermore, doing update_zero_vruntime() from __{de,en}queue_entity(), which
are called from {set_next,put_prev}_entity() has problems because:

 - set_next_entity() calls __dequeue_entity() before it does cfs_rq->curr = se.
   This means the avg_vruntime() will see the removal but not current, missing
   the entity for accounting.

 - put_prev_entity() calls __enqueue_entity() before it does cfs_rq->curr =
   NULL. This means the avg_vruntime() will see the addition *and* current,
   leading to double accounting.

Both cases are incorrect/inconsistent.

Noting that avg_vruntime is already called on each {en,de}queue, remove the
explicit avg_vruntime() calls (which removes an extra 64bit division for each
{en,de}queue) and have avg_vruntime() update zero_vruntime itself.

Additionally, have the tick call avg_vruntime() -- discarding the result, but
for the side-effect of updating zero_vruntime.

While there, optimize avg_vruntime() by noting that the average of one value is
rather trivial to compute.

Test case:
  # taskset -c -p 1 $$
  # taskset -c 2 bash -c 'while :; do :; done&'
  # cat /sys/kernel/debug/sched/debug | awk '/^cpu#/ {P=0} /^cpu#2,/ {P=1} {if (P) print $0}' | grep -e zero_vruntime -e "^>"

PRE:
    .zero_vruntime                 : 31316.407903
  >R            bash   487     50787.345112   E       50789.145972           2.800000     50780.298364        16     120         0.000000         0.000000         0.000000        /
    .zero_vruntime                 : 382548.253179
  >R            bash   487    427275.204288   E      427276.003584           2.800000    427268.157540        23     120         0.000000         0.000000         0.000000        /

POST:
    .zero_vruntime                 : 17259.709467
  >R            bash   526     17259.709467   E       17262.509467           2.800000     16915.031624         9     120         0.000000         0.000000         0.000000        /
    .zero_vruntime                 : 18702.723356
  >R            bash   526     18702.723356   E       18705.523356           2.800000     18358.045513         9     120         0.000000         0.000000         0.000000        /

Fixes: 79f3f9bedd14 ("sched/eevdf: Fix min_vruntime vs avg_vruntime")
Reported-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260219080624.438854780%40infradead.org
---
 kernel/sched/fair.c | 84 ++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 57 insertions(+), 27 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index eea99ec01a3f..56dddd4fd208 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -589,6 +589,21 @@ static inline bool entity_before(const struct sched_entity *a,
 	return vruntime_cmp(a->deadline, "<", b->deadline);
 }
 
+/*
+ * Per avg_vruntime() below, cfs_rq::zero_vruntime is only slightly stale
+ * and this value should be no more than two lag bounds. Which puts it in the
+ * general order of:
+ *
+ *	(slice + TICK_NSEC) << NICE_0_LOAD_SHIFT
+ *
+ * which is around 44 bits in size (on 64bit); that is 20 for
+ * NICE_0_LOAD_SHIFT, another 20 for NSEC_PER_MSEC and then a handful for
+ * however many msec the actual slice+tick ends up begin.
+ *
+ * (disregarding the actual divide-by-weight part makes for the worst case
+ * weight of 2, which nicely cancels vs the fuzz in zero_vruntime not actually
+ * being the zero-lag point).
+ */
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	return vruntime_op(se->vruntime, "-", cfs_rq->zero_vruntime);
@@ -676,39 +691,61 @@ sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static inline
-void sum_w_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta)
 {
 	/*
-	 * v' = v + d ==> sum_w_vruntime' = sum_runtime - d*sum_weight
+	 * v' = v + d ==> sum_w_vruntime' = sum_w_vruntime - d*sum_weight
 	 */
 	cfs_rq->sum_w_vruntime -= cfs_rq->sum_weight * delta;
+	cfs_rq->zero_vruntime += delta;
 }
 
 /*
- * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * Specifically: avg_vruntime() + 0 must result in entity_eligible() := true
  * For this to be so, the result of this function must have a left bias.
+ *
+ * Called in:
+ *  - place_entity()      -- before enqueue
+ *  - update_entity_lag() -- before dequeue
+ *  - entity_tick()
+ *
+ * This means it is one entry 'behind' but that puts it close enough to where
+ * the bound on entity_key() is at most two lag bounds.
  */
 u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	s64 avg = cfs_rq->sum_w_vruntime;
-	long load = cfs_rq->sum_weight;
+	long weight = cfs_rq->sum_weight;
+	s64 delta = 0;
 
-	if (curr && curr->on_rq) {
-		unsigned long weight = scale_load_down(curr->load.weight);
+	if (curr && !curr->on_rq)
+		curr = NULL;
 
-		avg += entity_key(cfs_rq, curr) * weight;
-		load += weight;
-	}
+	if (weight) {
+		s64 runtime = cfs_rq->sum_w_vruntime;
+
+		if (curr) {
+			unsigned long w = scale_load_down(curr->load.weight);
+
+			runtime += entity_key(cfs_rq, curr) * w;
+			weight += w;
+		}
 
-	if (load) {
 		/* sign flips effective floor / ceiling */
-		if (avg < 0)
-			avg -= (load - 1);
-		avg = div_s64(avg, load);
+		if (runtime < 0)
+			runtime -= (weight - 1);
+
+		delta = div_s64(runtime, weight);
+	} else if (curr) {
+		/*
+		 * When there is but one element, it is the average.
+		 */
+		delta = curr->vruntime - cfs_rq->zero_vruntime;
 	}
 
-	return cfs_rq->zero_vruntime + avg;
+	update_zero_vruntime(cfs_rq, delta);
+
+	return cfs_rq->zero_vruntime;
 }
 
 /*
@@ -777,16 +814,6 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return vruntime_eligible(cfs_rq, se->vruntime);
 }
 
-static void update_zero_vruntime(struct cfs_rq *cfs_rq)
-{
-	u64 vruntime = avg_vruntime(cfs_rq);
-	s64 delta = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime);
-
-	sum_w_vruntime_update(cfs_rq, delta);
-
-	cfs_rq->zero_vruntime = vruntime;
-}
-
 static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *root = __pick_root_entity(cfs_rq);
@@ -856,7 +883,6 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	sum_w_vruntime_add(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 	se->min_vruntime = se->vruntime;
 	se->min_slice = se->slice;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
@@ -868,7 +894,6 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
 				  &min_vruntime_cb);
 	sum_w_vruntime_sub(cfs_rq, se);
-	update_zero_vruntime(cfs_rq);
 }
 
 struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
@@ -5524,6 +5549,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	update_load_avg(cfs_rq, curr, UPDATE_TG);
 	update_cfs_group(curr);
 
+	/*
+	 * Pulls along cfs_rq::zero_vruntime.
+	 */
+	avg_vruntime(cfs_rq);
+
 #ifdef CONFIG_SCHED_HRTICK
 	/*
 	 * queued ticks are scheduled to match the slice, so don't bother
-- 
cgit v1.2.3


From bcd74b2ffdd0a2233adbf26b65c62fc69a809c8e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 23 Jan 2026 16:49:09 +0100
Subject: sched/fair: Only set slice protection at pick time

We should not (re)set slice protection in the sched_change pattern
which calls put_prev_task() / set_next_task().

Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260219080624.561421378%40infradead.org
---
 kernel/sched/fair.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 56dddd4fd208..f2b46c33a8c5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5445,7 +5445,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 }
 
 static void
-set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
+set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first)
 {
 	clear_buddies(cfs_rq, se);
 
@@ -5460,7 +5460,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		__dequeue_entity(cfs_rq, se);
 		update_load_avg(cfs_rq, se, UPDATE_TG);
 
-		set_protect_slice(cfs_rq, se);
+		if (first)
+			set_protect_slice(cfs_rq, se);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -8978,13 +8979,13 @@ again:
 				pse = parent_entity(pse);
 			}
 			if (se_depth >= pse_depth) {
-				set_next_entity(cfs_rq_of(se), se);
+				set_next_entity(cfs_rq_of(se), se, true);
 				se = parent_entity(se);
 			}
 		}
 
 		put_prev_entity(cfs_rq, pse);
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, true);
 
 		__set_next_task_fair(rq, p, true);
 	}
@@ -13598,7 +13599,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-		set_next_entity(cfs_rq, se);
+		set_next_entity(cfs_rq, se, first);
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		account_cfs_rq_runtime(cfs_rq, 0);
 	}
-- 
cgit v1.2.3


From ff38424030f98976150e42ca35f4b00e6ab8fa23 Mon Sep 17 00:00:00 2001
From: Wang Tao <wangtao554@huawei.com>
Date: Tue, 20 Jan 2026 12:31:13 +0000
Subject: sched/eevdf: Update se->vprot in reweight_entity()

In the EEVDF framework with Run-to-Parity protection, `se->vprot` is an
independent variable defining the virtual protection timestamp.

When `reweight_entity()` is called (e.g., via nice/renice), it performs
the following actions to preserve Lag consistency:
 1. Scales `se->vlag` based on the new weight.
 2. Calls `place_entity()`, which recalculates `se->vruntime` based on
    the new weight and scaled lag.

However, the current implementation fails to update `se->vprot`, leading
to mismatches between the task's actual runtime and its expected duration.

Fixes: 63304558ba5d ("sched/eevdf: Curb wakeup-preemption")
Suggested-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Wang Tao <wangtao554@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20260120123113.3518950-1-wangtao554@huawei.com
---
 kernel/sched/fair.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f2b46c33a8c5..93fa5b8313e4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3815,6 +3815,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
 	bool curr = cfs_rq->curr == se;
+	bool rel_vprot = false;
+	u64 vprot;
 
 	if (se->on_rq) {
 		/* commit outstanding execution time */
@@ -3822,6 +3824,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		update_entity_lag(cfs_rq, se);
 		se->deadline -= se->vruntime;
 		se->rel_deadline = 1;
+		if (curr && protect_slice(se)) {
+			vprot = se->vprot - se->vruntime;
+			rel_vprot = true;
+		}
+
 		cfs_rq->nr_queued--;
 		if (!curr)
 			__dequeue_entity(cfs_rq, se);
@@ -3837,6 +3844,9 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	if (se->rel_deadline)
 		se->deadline = div_s64(se->deadline * se->load.weight, weight);
 
+	if (rel_vprot)
+		vprot = div_s64(vprot * se->load.weight, weight);
+
 	update_load_set(&se->load, weight);
 
 	do {
@@ -3848,6 +3858,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
 		place_entity(cfs_rq, se, 0);
+		if (rel_vprot)
+			se->vprot = se->vruntime + vprot;
 		update_load_add(&cfs_rq->load, se->load.weight);
 		if (!curr)
 			__enqueue_entity(cfs_rq, se);
-- 
cgit v1.2.3


From 6e3c0a4e1ad1e0455b7880fad02b3ee179f56c09 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 22 Apr 2025 12:16:28 +0200
Subject: sched/fair: Fix lag clamp

Vincent reported that he was seeing undue lag clamping in a mixed
slice workload. Implement the max_slice tracking as per the todo
comment.

Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
Reported-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com>
Link: https://patch.msgid.link/20250422101628.GA33555@noisy.programming.kicks-ass.net
---
 include/linux/sched.h |  1 +
 kernel/sched/fair.c   | 39 +++++++++++++++++++++++++++++++++++----
 2 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 074ad4ef3d81..a7b4a980eb2f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -579,6 +579,7 @@ struct sched_entity {
 	u64				deadline;
 	u64				min_vruntime;
 	u64				min_slice;
+	u64				max_slice;
 
 	struct list_head		group_node;
 	unsigned char			on_rq;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 93fa5b8313e4..f4446cbe8ffa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -748,6 +748,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 	return cfs_rq->zero_vruntime;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
+
 /*
  * lag_i = S - s_i = w_i * (V - v_i)
  *
@@ -761,17 +763,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
  * EEVDF gives the following limit for a steady state system:
  *
  *   -r_max < lag < max(r_max, q)
- *
- * XXX could add max_slice to the augmented data to track this.
  */
 static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
+	u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
 	s64 vlag, limit;
 
 	WARN_ON_ONCE(!se->on_rq);
 
 	vlag = avg_vruntime(cfs_rq) - se->vruntime;
-	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+	limit = calc_delta_fair(max_slice, se);
 
 	se->vlag = clamp(vlag, -limit, limit);
 }
@@ -829,6 +830,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
 	return min_slice;
 }
 
+static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *root = __pick_root_entity(cfs_rq);
+	struct sched_entity *curr = cfs_rq->curr;
+	u64 max_slice = 0ULL;
+
+	if (curr && curr->on_rq)
+		max_slice = curr->slice;
+
+	if (root)
+		max_slice = max(max_slice, root->max_slice);
+
+	return max_slice;
+}
+
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 {
 	return entity_before(__node_2_se(a), __node_2_se(b));
@@ -853,6 +869,15 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n
 	}
 }
 
+static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (rse->max_slice > se->max_slice)
+			se->max_slice = rse->max_slice;
+	}
+}
+
 /*
  * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
@@ -860,6 +885,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
 	u64 old_min_vruntime = se->min_vruntime;
 	u64 old_min_slice = se->min_slice;
+	u64 old_max_slice = se->max_slice;
 	struct rb_node *node = &se->run_node;
 
 	se->min_vruntime = se->vruntime;
@@ -870,8 +896,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 	__min_slice_update(se, node->rb_right);
 	__min_slice_update(se, node->rb_left);
 
+	se->max_slice = se->slice;
+	__max_slice_update(se, node->rb_right);
+	__max_slice_update(se, node->rb_left);
+
 	return se->min_vruntime == old_min_vruntime &&
-	       se->min_slice == old_min_slice;
+	       se->min_slice == old_min_slice &&
+	       se->max_slice == old_max_slice;
 }
 
 RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
-- 
cgit v1.2.3


From 4c652a47722f69c6f2685f05b17490ea97f643a8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Feb 2026 08:41:13 +0100
Subject: rseq: Mark rseq_arm_slice_extension_timer() __always_inline

objtool warns about this function being called inside of a uaccess
section:

kernel/entry/common.o: warning: objtool: irqentry_exit+0x1dc: call to rseq_arm_slice_extension_timer() with UACCESS enabled

Interestingly, this happens with CONFIG_RSEQ_SLICE_EXTENSION disabled,
so this is an empty function, as the normal implementation is
already marked __always_inline.

I could reproduce this multiple times with gcc-11 but not with gcc-15,
so the compiler probably got better at identifying the trivial function.

Mark all the empty helpers for !RSEQ_SLICE_EXTENSION as __always_inline
for consistency, avoiding this warning.

Fixes: 0ac3b5c3dc45 ("rseq: Implement time slice extension enforcement timer")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260206074122.709580-1-arnd@kernel.org
---
 include/linux/rseq_entry.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index cbc4a791618b..c6831c93cd6e 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -216,10 +216,10 @@ efault:
 }
 
 #else /* CONFIG_RSEQ_SLICE_EXTENSION */
-static inline bool rseq_slice_extension_enabled(void) { return false; }
-static inline bool rseq_arm_slice_extension_timer(void) { return false; }
-static inline void rseq_slice_clear_grant(struct task_struct *t) { }
-static inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
+static __always_inline bool rseq_slice_extension_enabled(void) { return false; }
+static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
+static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
+static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; }
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
-- 
cgit v1.2.3


From 5324953c06bd929c135d9e04be391ee2c11b5a19 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 18 Feb 2026 17:33:29 +0100
Subject: sched/core: Fix wakeup_preempt's next_class tracking

Kernel test robot reported that
tools/testing/selftests/kvm/hardware_disable_test was failing due to
commit 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt()
and rq_modified_*()")

It turns out there were two related problems that could lead to a
missed preemption:

 - when hitting newidle balance from the idle thread, it would elevate
   rb->next_class from &idle_sched_class to &fair_sched_class, causing
   later wakeup_preempt() calls to not hit the sched_class_above()
   case, and not issue resched_curr().

   Notably, this modification pattern should only lower the
   next_class, and never raise it. Create two new helper functions to
   wrap this.

 - when doing schedule_idle(), it was possible to miss (re)setting
   rq->next_class to &idle_sched_class, leading to the very same
   problem.

Cc: Sean Christopherson <seanjc@google.com>
Fixes: 704069649b5b ("sched/core: Rework sched_class::wakeup_preempt() and rq_modified_*()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202602122157.4e861298-lkp@intel.com
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260218163329.GQ1395416@noisy.programming.kicks-ass.net
---
 kernel/sched/core.c  |  1 +
 kernel/sched/ext.c   |  4 ++--
 kernel/sched/fair.c  |  4 ++--
 kernel/sched/sched.h | 11 +++++++++++
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 759777694c78..b7f77c165a6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6830,6 +6830,7 @@ static void __sched notrace __schedule(int sched_mode)
 		/* SCX must consult the BPF scheduler to tell if rq is empty */
 		if (!rq->nr_running && !scx_enabled()) {
 			next = prev;
+			rq->next_class = &idle_sched_class;
 			goto picked;
 		}
 	} else if (!preempt && prev_state) {
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 62b1f3ac5630..06cc0a4aec66 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2460,7 +2460,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	/* see kick_cpus_irq_workfn() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
-	rq->next_class = &ext_sched_class;
+	rq_modified_begin(rq, &ext_sched_class);
 
 	rq_unpin_lock(rq, rf);
 	balance_one(rq, prev);
@@ -2475,7 +2475,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	 * If @force_scx is true, always try to pick a SCHED_EXT task,
 	 * regardless of any higher-priority sched classes activity.
 	 */
-	if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class))
+	if (!force_scx && rq_modified_above(rq, &ext_sched_class))
 		return RETRY_TASK;
 
 	keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f4446cbe8ffa..bf948db905ed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12982,7 +12982,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 	t0 = sched_clock_cpu(this_cpu);
 	__sched_balance_update_blocked_averages(this_rq);
 
-	this_rq->next_class = &fair_sched_class;
+	rq_modified_begin(this_rq, &fair_sched_class);
 	raw_spin_rq_unlock(this_rq);
 
 	for_each_domain(this_cpu, sd) {
@@ -13049,7 +13049,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 		pulled_task = 1;
 
 	/* If a higher prio class was modified, restart the pick */
-	if (sched_class_above(this_rq->next_class, &fair_sched_class))
+	if (rq_modified_above(this_rq, &fair_sched_class))
 		pulled_task = -1;
 
 out:
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b82fb70a9d54..43bbf0693cca 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2748,6 +2748,17 @@ static inline const struct sched_class *next_active_class(const struct sched_cla
 
 #define sched_class_above(_a, _b)	((_a) < (_b))
 
+static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class)
+{
+	if (sched_class_above(rq->next_class, class))
+		rq->next_class = class;
+}
+
+static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class)
+{
+	return sched_class_above(rq->next_class, class);
+}
+
 static inline bool sched_stop_runnable(struct rq *rq)
 {
 	return rq->stop && task_on_rq_queued(rq->stop);
-- 
cgit v1.2.3


From 26d43a90be81fc90e26688a51d3ec83188602731 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Fri, 20 Feb 2026 15:06:40 -0500
Subject: rseq: Clarify rseq registration rseq_size bound check comment

The rseq registration validates that the rseq_size argument is greater
or equal to 32 (the original rseq size), but the comment associated with
this check does not clearly state this.

Clarify the comment to that effect.

Fixes: ee3e3ac05c26 ("rseq: Introduce extensible rseq ABI")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260220200642.1317826-2-mathieu.desnoyers@efficios.com
---
 kernel/rseq.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index b0973d19f366..e349f86cc945 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -449,8 +449,9 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32
 	 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq
 	 * size, the required alignment is the original struct rseq alignment.
 	 *
-	 * In order to be valid, rseq_len is either the original rseq size, or
-	 * large enough to contain all supported fields, as communicated to
+	 * The rseq_len is required to be greater or equal to the original rseq
+	 * size. In order to be valid, rseq_len is either the original rseq size,
+	 * or large enough to contain all supported fields, as communicated to
 	 * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE.
 	 */
 	if (rseq_len < ORIG_RSEQ_SIZE ||
-- 
cgit v1.2.3


From 3b68df978133ac3d46d570af065a73debbb68248 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Fri, 20 Feb 2026 15:06:41 -0500
Subject: rseq: slice ext: Ensure rseq feature size differs from original rseq
 size

Before rseq became extensible, its original size was 32 bytes even
though the active rseq area was only 20 bytes. This had the following
impact in terms of userspace ecosystem evolution:

* The GNU libc between 2.35 and 2.39 expose a __rseq_size symbol set
  to 32, even though the size of the active rseq area is really 20.
* The GNU libc 2.40 changes this __rseq_size to 20, thus making it
  express the active rseq area.
* Starting from glibc 2.41, __rseq_size corresponds to the
  AT_RSEQ_FEATURE_SIZE from getauxval(3).

This means that users of __rseq_size can always expect it to
correspond to the active rseq area, except for the value 32, for
which the active rseq area is 20 bytes.

Exposing a 32 bytes feature size would make life needlessly painful
for userspace. Therefore, add a reserved field at the end of the
rseq area to bump the feature size to 33 bytes. This reserved field
is expected to be replaced with whatever field will come next,
expecting that this field will be larger than 1 byte.

The effect of this change is to increase the size from 32 to 64 bytes
before we actually have fields using that memory.

Clarify the allocation size and alignment requirements in the struct
rseq uapi comment.

Change the value returned by getauxval(AT_RSEQ_ALIGN) to return the
value of the active rseq area size rounded up to next power of 2, which
guarantees that the rseq structure will always be aligned on the nearest
power of two large enough to contain it, even as it grows. Change the
alignment check in the rseq registration accordingly.

This will minimize the amount of ABI corner-cases we need to document
and require userspace to play games with. The rule stays simple when
__rseq_size != 32:

  #define rseq_field_available(field)	(__rseq_size >= offsetofend(struct rseq_abi, field))

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260220200642.1317826-3-mathieu.desnoyers@efficios.com
---
 fs/binfmt_elf.c           |  3 ++-
 include/linux/rseq.h      | 12 ++++++++++++
 include/uapi/linux/rseq.h | 26 ++++++++++++++++++++++----
 kernel/rseq.c             |  3 ++-
 4 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 8e89cc5b2820..fb857faaf0d6 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -47,6 +47,7 @@
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <uapi/linux/rseq.h>
+#include <linux/rseq.h>
 #include <asm/param.h>
 #include <asm/page.h>
 
@@ -286,7 +287,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	}
 #ifdef CONFIG_RSEQ
 	NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end));
-	NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq));
+	NEW_AUX_ENT(AT_RSEQ_ALIGN, rseq_alloc_align());
 #endif
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index 7a01a0760405..b9d62fc2140d 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags)
 		t->rseq = current->rseq;
 }
 
+/*
+ * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq
+ * registration. This is the active rseq area size rounded up to next
+ * power of 2, which guarantees that the rseq structure will always be
+ * aligned on the nearest power of two large enough to contain it, even
+ * as it grows.
+ */
+static inline unsigned int rseq_alloc_align(void)
+{
+	return 1U << get_count_order(offsetof(struct rseq, end));
+}
+
 #else /* CONFIG_RSEQ */
 static inline void rseq_handle_slowpath(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index 863c4a00a66b..f69344fe6c08 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -87,10 +87,17 @@ struct rseq_slice_ctrl {
 };
 
 /*
- * struct rseq is aligned on 4 * 8 bytes to ensure it is always
- * contained within a single cache-line.
+ * The original size and alignment of the allocation for struct rseq is
+ * 32 bytes.
  *
- * A single struct rseq per thread is allowed.
+ * The allocation size needs to be greater or equal to
+ * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to
+ * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32).
+ *
+ * As an alternative, userspace is allowed to use both the original size
+ * and alignment of 32 bytes for backward compatibility.
+ *
+ * A single active struct rseq registration per thread is allowed.
  */
 struct rseq {
 	/*
@@ -180,10 +187,21 @@ struct rseq {
 	 */
 	struct rseq_slice_ctrl slice_ctrl;
 
+	/*
+	 * Before rseq became extensible, its original size was 32 bytes even
+	 * though the active rseq area was only 20 bytes.
+	 * Exposing a 32 bytes feature size would make life needlessly painful
+	 * for userspace. Therefore, add a reserved byte after byte 32
+	 * to bump the rseq feature size from 32 to 33.
+	 * The next field to be added to the rseq area will be larger
+	 * than one byte, and will replace this reserved byte.
+	 */
+	__u8 __reserved;
+
 	/*
 	 * Flexible array member at end of structure, after last feature field.
 	 */
 	char end[];
-} __attribute__((aligned(4 * sizeof(__u64))));
+} __attribute__((aligned(32)));
 
 #endif /* _UAPI_LINUX_RSEQ_H */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index e349f86cc945..38d3ef540760 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -80,6 +80,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/types.h>
+#include <linux/rseq.h>
 #include <asm/ptrace.h>
 
 #define CREATE_TRACE_POINTS
@@ -456,7 +457,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32
 	 */
 	if (rseq_len < ORIG_RSEQ_SIZE ||
 	    (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) ||
-	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) ||
+	    (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) ||
 					    rseq_len < offsetof(struct rseq, end))))
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
-- 
cgit v1.2.3


From 486ff5ad49bc50315bcaf6d45f04a33ef0a45ced Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 2 Jun 2025 21:51:05 -0700
Subject: perf/core: Fix invalid wait context in ctx_sched_in()

Lockdep found a bug in the event scheduling when a pinned event was
failed and wakes up the threads in the ring buffer like below.

It seems it should not grab a wait-queue lock under perf-context lock.
Let's do it with irq_work.

  [   39.913691] =============================
  [   39.914157] [ BUG: Invalid wait context ]
  [   39.914623] 6.15.0-next-20250530-next-2025053 #1 Not tainted
  [   39.915271] -----------------------------
  [   39.915731] repro/837 is trying to lock:
  [   39.916191] ffff88801acfabd8 (&event->waitq){....}-{3:3}, at: __wake_up+0x26/0x60
  [   39.917182] other info that might help us debug this:
  [   39.917761] context-{5:5}
  [   39.918079] 4 locks held by repro/837:
  [   39.918530]  #0: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: __perf_event_task_sched_in+0xd1/0xbc0
  [   39.919612]  #1: ffff88806ca3c6f8 (&cpuctx_lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1a7/0xbc0
  [   39.920748]  #2: ffff88800d91fc18 (&ctx->lock){....}-{2:2}, at: __perf_event_task_sched_in+0x1f9/0xbc0
  [   39.921819]  #3: ffffffff8725cd00 (rcu_read_lock){....}-{1:3}, at: perf_event_wakeup+0x6c/0x470

Fixes: f4b07fd62d4d ("perf/core: Use POLLHUP for a pinned event in error")
Closes: https://lore.kernel.org/lkml/aD2w50VDvGIH95Pf@ly-workstation
Reported-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Link: https://patch.msgid.link/20250603045105.1731451-1-namhyung@kernel.org
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ac70d68217b6..4f86d22f281a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4138,7 +4138,8 @@ static int merge_sched_in(struct perf_event *event, void *data)
 			if (*perf_event_fasync(event))
 				event->pending_kill = POLL_ERR;
 
-			perf_event_wakeup(event);
+			event->pending_wakeup = 1;
+			irq_work_queue(&event->pending_irq);
 		} else {
 			struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu);
 
-- 
cgit v1.2.3


From 6a8a48644c4b804123e59dbfc5d6cd29a0194046 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Mon, 9 Feb 2026 16:52:25 -0800
Subject: perf/x86/intel/uncore: Add per-scheduler IMC CAS count events

IMC on SPR and EMR does not support sub-channels.  In contrast, CPUs
that use gnr_uncores[] (e.g. Granite Rapids and Sierra Forest)
implement two command schedulers (SCH0/SCH1) per memory channel,
providing logically independent command and data paths.

Do not reuse the spr_uncore_imc[] configuration for these CPUs.
Instead, introduce a dedicated gnr_uncore_imc[] with per-scheduler
events, so userspace can monitor SCH0 and SCH1 independently.

On these CPUs, replace cas_count_{read,write} with
cas_count_{read,write}_sch{0,1}.  This may break existing userspace
that relies on cas_count_{read,write}, prompting it to switch to the
per-scheduler events, as the legacy event reports only partial
traffic (SCH0).

Fixes: 632c4bf6d007 ("perf/x86/intel/uncore: Support Granite Rapids")
Fixes: cb4a6ccf3583 ("perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge")
Reported-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260210005225.20311-1-zide.chen@intel.com
---
 arch/x86/events/intel/uncore_snbep.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 5ed6e0b7e715..0a1d08136cc1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6497,6 +6497,32 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct uncore_event_desc gnr_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x01,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0,  "event=0x05,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1,  "event=0x06,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type gnr_uncore_imc = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "imc",
+	.fixed_ctr_bits		= 48,
+	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
+	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
+	.event_descs		= gnr_uncore_imc_events,
+};
+
 static struct intel_uncore_type gnr_uncore_pciex8 = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "pciex8",
@@ -6544,7 +6570,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	NULL,
 	&spr_uncore_pcu,
 	&gnr_uncore_ubox,
-	&spr_uncore_imc,
+	&gnr_uncore_imc,
 	NULL,
 	&gnr_uncore_upi,
 	NULL,
-- 
cgit v1.2.3


From 77de62ad3de3967818c3dbe656b7336ebee461d2 Mon Sep 17 00:00:00 2001
From: Haocheng Yu <yuhaocheng035@gmail.com>
Date: Tue, 3 Feb 2026 00:20:56 +0800
Subject: perf/core: Fix refcount bug and potential UAF in perf_mmap

Syzkaller reported a refcount_t: addition on 0; use-after-free warning
in perf_mmap.

The issue is caused by a race condition between a failing mmap() setup
and a concurrent mmap() on a dependent event (e.g., using output
redirection).

In perf_mmap(), the ring_buffer (rb) is allocated and assigned to
event->rb with the mmap_mutex held. The mutex is then released to
perform map_range().

If map_range() fails, perf_mmap_close() is called to clean up.
However, since the mutex was dropped, another thread attaching to
this event (via inherited events or output redirection) can acquire
the mutex, observe the valid event->rb pointer, and attempt to
increment its reference count. If the cleanup path has already
dropped the reference count to zero, this results in a
use-after-free or refcount saturation warning.

Fix this by extending the scope of mmap_mutex to cover the
map_range() call. This ensures that the ring buffer initialization
and mapping (or cleanup on failure) happens atomically effectively,
preventing other threads from accessing a half-initialized or
dying ring buffer.

Closes: https://lore.kernel.org/oe-kbuild-all/202602020208.m7KIjdzW-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Haocheng Yu <yuhaocheng035@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260202162057.7237-1-yuhaocheng035@gmail.com
---
 kernel/events/core.c | 38 +++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4f86d22f281a..22a0f405585b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7465,28 +7465,28 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			ret = perf_mmap_aux(vma, event, nr_pages);
 		if (ret)
 			return ret;
-	}
 
-	/*
-	 * Since pinned accounting is per vm we cannot allow fork() to copy our
-	 * vma.
-	 */
-	vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
-	vma->vm_ops = &perf_mmap_vmops;
+		/*
+		 * Since pinned accounting is per vm we cannot allow fork() to copy our
+		 * vma.
+		 */
+		vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP);
+		vma->vm_ops = &perf_mmap_vmops;
 
-	mapped = get_mapped(event, event_mapped);
-	if (mapped)
-		mapped(event, vma->vm_mm);
+		mapped = get_mapped(event, event_mapped);
+		if (mapped)
+			mapped(event, vma->vm_mm);
 
-	/*
-	 * Try to map it into the page table. On fail, invoke
-	 * perf_mmap_close() to undo the above, as the callsite expects
-	 * full cleanup in this case and therefore does not invoke
-	 * vmops::close().
-	 */
-	ret = map_range(event->rb, vma);
-	if (ret)
-		perf_mmap_close(vma);
+		/*
+		 * Try to map it into the page table. On fail, invoke
+		 * perf_mmap_close() to undo the above, as the callsite expects
+		 * full cleanup in this case and therefore does not invoke
+		 * vmops::close().
+		 */
+		ret = map_range(event->rb, vma);
+		if (ret)
+			perf_mmap_close(vma);
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From eb4a7139e97374f42b7242cc754e77f1623fbcd5 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Thu, 12 Feb 2026 08:27:31 +0200
Subject: drm/i915/alpm: ALPM disable fixes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PORT_ALPM_CTL is supposed to be written only before link training. Remove
writing it from ALPM disable.

Also clearing ALPM_CTL_ALPM_AUX_LESS_ENABLE and is not about disabling ALPM
but switching to AUX-Wake ALPM. Stop touching this bit on ALPM disable.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7153
Fixes: 1ccbf135862b ("drm/i915/psr: Enable ALPM on source side for eDP Panel replay")
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Michał Grzelak <michal.grzelak@intel.com>
Link: https://patch.msgid.link/20260212062731.397801-1-jouni.hogander@intel.com
(cherry picked from commit 008304c9ae75c772d3460040de56e12112cdf5e6)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index 7ce8c674bb03..07ffee38974b 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -562,12 +562,7 @@ void intel_alpm_disable(struct intel_dp *intel_dp)
 	mutex_lock(&intel_dp->alpm.lock);
 
 	intel_de_rmw(display, ALPM_CTL(display, cpu_transcoder),
-		     ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE |
-		     ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0);
-
-	intel_de_rmw(display,
-		     PORT_ALPM_CTL(cpu_transcoder),
-		     PORT_ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0);
+		     ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE, 0);
 
 	drm_dbg_kms(display->drm, "Disabling ALPM\n");
 	mutex_unlock(&intel_dp->alpm.lock);
-- 
cgit v1.2.3


From ec2cceadfae72304ca19650f9cac4b2a97b8a2fc Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Date: Thu, 19 Feb 2026 10:51:33 +0100
Subject: gpiolib: normalize the return value of gc->get() on behalf of buggy
 drivers

Commit 86ef402d805d ("gpiolib: sanitize the return value of
gpio_chip::get()") started checking the return value of the .get()
callback in struct gpio_chip. Now - almost a year later - it turns out
that there are quite a few drivers in tree that can break with this
change. Partially revert it: normalize the return value in GPIO core but
also emit a warning.

Cc: stable@vger.kernel.org
Fixes: 86ef402d805d ("gpiolib: sanitize the return value of gpio_chip::get()")
Reported-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Closes: https://lore.kernel.org/all/aZSkqGTqMp_57qC7@google.com/
Reviewed-by: Linus Walleij <linusw@kernel.org>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Link: https://patch.msgid.link/20260219-gpiolib-set-normalize-v2-1-f84630e45796@oss.qualcomm.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86a171e96b0e..ada572aaebd6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3267,8 +3267,12 @@ static int gpiochip_get(struct gpio_chip *gc, unsigned int offset)
 
 	/* Make sure this is called after checking for gc->get(). */
 	ret = gc->get(gc, offset);
-	if (ret > 1)
-		ret = -EBADE;
+	if (ret > 1) {
+		gpiochip_warn(gc,
+			"invalid return value from gc->get(): %d, consider fixing the driver\n",
+			ret);
+		ret = !!ret;
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From af12e64ae0661546e8b4f5d30d55c5f53a11efe7 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 20 Jan 2026 22:26:46 +0800
Subject: mmc: mmci: Fix device_node reference leak in of_get_dml_pipe_index()

When calling of_parse_phandle_with_args(), the caller is responsible
to call of_node_put() to release the reference of device node.
In of_get_dml_pipe_index(), it does not release the reference.

Fixes: 9cb15142d0e3 ("mmc: mmci: Add qcom dml support to the driver.")
Signed-off-by: Felix Gu <gu_0233@qq.com>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mmci_qcom_dml.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mmc/host/mmci_qcom_dml.c b/drivers/mmc/host/mmci_qcom_dml.c
index 3da6112fbe39..67371389cc33 100644
--- a/drivers/mmc/host/mmci_qcom_dml.c
+++ b/drivers/mmc/host/mmci_qcom_dml.c
@@ -109,6 +109,7 @@ static int of_get_dml_pipe_index(struct device_node *np, const char *name)
 				       &dma_spec))
 		return -ENODEV;
 
+	of_node_put(dma_spec.np);
 	if (dma_spec.args_count)
 		return dma_spec.args[0];
 
-- 
cgit v1.2.3


From 6465a8bbb0f6ad98aeb66dc9ea19c32c193a610b Mon Sep 17 00:00:00 2001
From: Shawn Lin <shawn.lin@rock-chips.com>
Date: Fri, 16 Jan 2026 08:55:30 +0800
Subject: mmc: dw_mmc-rockchip: Fix runtime PM support for internal phase
 support

RK3576 is the first platform to introduce internal phase support, and
subsequent platforms are expected to adopt a similar design. In this
architecture, runtime suspend powers off the attached power domain, which
resets registers, including vendor-specific ones such as SDMMC_TIMING_CON0,
SDMMC_TIMING_CON1, and SDMMC_MISC_CON. These registers must be saved and
restored, a requirement that falls outside the scope of the dw_mmc core.

Fixes: 59903441f5e4 ("mmc: dw_mmc-rockchip: Add internal phase support")
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Tested-by: Marco Schirrmeister <mschirrmeister@gmail.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc-rockchip.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 4e3423a19bdf..ac069d0c42b2 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -36,6 +36,8 @@ struct dw_mci_rockchip_priv_data {
 	int			default_sample_phase;
 	int			num_phases;
 	bool			internal_phase;
+	int                     sample_phase;
+	int                     drv_phase;
 };
 
 /*
@@ -573,9 +575,43 @@ static void dw_mci_rockchip_remove(struct platform_device *pdev)
 	dw_mci_pltfm_remove(pdev);
 }
 
+static int dw_mci_rockchip_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dw_mci *host = platform_get_drvdata(pdev);
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
+
+	if (priv->internal_phase) {
+		priv->sample_phase = rockchip_mmc_get_phase(host, true);
+		priv->drv_phase = rockchip_mmc_get_phase(host, false);
+	}
+
+	return dw_mci_runtime_suspend(dev);
+}
+
+static int dw_mci_rockchip_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dw_mci *host = platform_get_drvdata(pdev);
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
+	int ret;
+
+	ret = dw_mci_runtime_resume(dev);
+	if (ret)
+		return ret;
+
+	if (priv->internal_phase) {
+		rockchip_mmc_set_phase(host, true, priv->sample_phase);
+		rockchip_mmc_set_phase(host, false, priv->drv_phase);
+		mci_writel(host, MISC_CON, MEM_CLK_AUTOGATE_ENABLE);
+	}
+
+	return ret;
+}
+
 static const struct dev_pm_ops dw_mci_rockchip_dev_pm_ops = {
 	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
-	RUNTIME_PM_OPS(dw_mci_runtime_suspend, dw_mci_runtime_resume, NULL)
+	RUNTIME_PM_OPS(dw_mci_rockchip_runtime_suspend, dw_mci_rockchip_runtime_resume, NULL)
 };
 
 static struct platform_driver dw_mci_rockchip_pltfm_driver = {
-- 
cgit v1.2.3


From 79ad471530e0baef0dce991816013df55e401d9c Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Mon, 16 Feb 2026 14:15:43 -0500
Subject: mmc: sdhci-brcmstb: use correct register offset for V1 pin_sel
 restore

The restore path for SDIO_CFG_CORE_V1 was incorrectly using
SDIO_CFG_SD_PIN_SEL (offset 0x44) instead of SDIO_CFG_V1_SD_PIN_SEL
(offset 0x54), causing the wrong register to be written on resume.
The save path already uses the correct V1-specific offset. This
affects BCM7445 and BCM72116 platforms which use the V1 config core.

Fixes: b7e614802e3f ("mmc: sdhci-brcmstb: save and restore registers during PM")
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Cc: stable@vger.kernel.org
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-brcmstb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index c9442499876c..57e45951644e 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -116,7 +116,7 @@ static void sdhci_brcmstb_restore_regs(struct mmc_host *mmc, enum cfg_core_ver v
 		writel(sr->boot_main_ctl, priv->boot_regs + SDIO_BOOT_MAIN_CTL);
 
 	if (ver == SDIO_CFG_CORE_V1) {
-		writel(sr->sd_pin_sel, cr + SDIO_CFG_SD_PIN_SEL);
+		writel(sr->sd_pin_sel, cr + SDIO_CFG_V1_SD_PIN_SEL);
 		return;
 	}
 
-- 
cgit v1.2.3


From 162d331d833dc73a3e905a24c44dd33732af1fc5 Mon Sep 17 00:00:00 2001
From: Ariel Silver <arielsilver77@gmail.com>
Date: Fri, 20 Feb 2026 10:11:29 +0000
Subject: wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration

link_id is taken from the ML Reconfiguration element (control & 0x000f),
so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS
(15) elements, so index 15 is out-of-bounds. Skip subelements with
link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds
write.

Fixes: 8eb8dd2ffbbb ("wifi: mac80211: Support link removal using Reconfiguration ML element")
Reported-by: Ariel Silver <arielsilver77@gmail.com>
Signed-off-by: Ariel Silver <arielsilver77@gmail.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260220101129.1202657-1-Ariel.Silver@cybereason.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index e83582b2c377..d43204ee330e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7085,6 +7085,9 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 		control = le16_to_cpu(prof->control);
 		link_id = control & IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID;
 
+		if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS)
+			continue;
+
 		removed_links |= BIT(link_id);
 
 		/* the MAC address should not be included, but handle it */
-- 
cgit v1.2.3


From 6510e1324bcdc8caf21f6d17efe27604c48f0d64 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 23 Feb 2026 09:36:16 +0000
Subject: ASoC: cs42l43: Report insert for exotic peripherals

For some exotic peripherals the type detect can return a reserved value
of 0x4. This will currently return an error and not report anything to
user-space, update this to report the insert normally.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260223093616.3800350-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43-jack.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index b83bc4de1301..3e04e6897b14 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -699,6 +699,7 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv)
 	switch (type & CS42L43_HSDET_TYPE_STS_MASK) {
 	case 0x0: // CTIA
 	case 0x1: // OMTP
+	case 0x4:
 		return cs42l43_run_load_detect(priv, true);
 	case 0x2: // 3-pole
 		return cs42l43_run_load_detect(priv, false);
-- 
cgit v1.2.3


From 901084c51a0a8fb42a3f37d2e9c62083c495f824 Mon Sep 17 00:00:00 2001
From: Penghe Geng <pgeng@nvidia.com>
Date: Thu, 19 Feb 2026 15:29:54 -0500
Subject: mmc: core: Avoid bitfield RMW for claim/retune flags

Move claimed and retune control flags out of the bitfield word to
avoid unrelated RMW side effects in asynchronous contexts.

The host->claimed bit shared a word with retune flags. Writes to claimed
in __mmc_claim_host() or retune_now in mmc_mq_queue_rq() can overwrite
other bits when concurrent updates happen in other contexts, triggering
spurious WARN_ON(!host->claimed). Convert claimed, can_retune,
retune_now and retune_paused to bool to remove shared-word coupling.

Fixes: 6c0cedd1ef952 ("mmc: core: Introduce host claiming by context")
Fixes: 1e8e55b67030c ("mmc: block: Add CQE support")
Cc: stable@vger.kernel.org
Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Penghe Geng <pgeng@nvidia.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/host.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index e0e2c265e5d1..ba84f02c2a10 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -486,14 +486,12 @@ struct mmc_host {
 
 	struct mmc_ios		ios;		/* current io bus settings */
 
+	bool			claimed;	/* host exclusively claimed */
+
 	/* group bitfields together to minimize padding */
 	unsigned int		use_spi_crc:1;
-	unsigned int		claimed:1;	/* host exclusively claimed */
 	unsigned int		doing_init_tune:1; /* initial tuning in progress */
-	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
-	unsigned int		retune_now:1;	/* do re-tuning at next req */
-	unsigned int		retune_paused:1; /* re-tuning is temporarily disabled */
 	unsigned int		retune_crc_disable:1; /* don't trigger retune upon crc */
 	unsigned int		can_dma_map_merge:1; /* merging can be used */
 	unsigned int		vqmmc_enabled:1; /* vqmmc regulator is enabled */
@@ -508,6 +506,9 @@ struct mmc_host {
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
+	bool			can_retune;	/* re-tuning can be used */
+	bool			retune_now;	/* do re-tuning at next req */
+	bool			retune_paused;	/* re-tuning is temporarily disabled */
 	int			need_retune;	/* re-tuning is needed */
 	int			hold_retune;	/* hold off re-tuning */
 	unsigned int		retune_period;	/* re-tuning period in secs */
-- 
cgit v1.2.3


From 7a73801fdaf8aee90d23ba77976082a48d156a21 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 22 Dec 2025 21:29:41 +0100
Subject: pmdomain: imx: gpcv2: Discard pm_runtime_put() return value

Passing pm_runtime_put() return value to the callers is not particularly
useful.

Returning an error code from pm_runtime_put() merely means that it has
not queued up a work item to check whether or not the device can be
suspended and there are many perfectly valid situations in which that
can happen, like after writing "on" to the devices' runtime PM "control"
attribute in sysfs for one example.

Accordingly, update imx_pgc_domain_suspend() to simply discard the
return value of pm_runtime_put() and always return success to the
caller.

This will facilitate a planned change of the pm_runtime_put() return
type to void in the future.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peng Fan <peng.fan@nxp.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/15658107.tv2OnDr8pf@rafael.j.wysocki
---
 drivers/pmdomain/imx/gpcv2.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c
index cff738e4d546..a829f8da5be7 100644
--- a/drivers/pmdomain/imx/gpcv2.c
+++ b/drivers/pmdomain/imx/gpcv2.c
@@ -1416,7 +1416,9 @@ static int imx_pgc_domain_suspend(struct device *dev)
 
 static int imx_pgc_domain_resume(struct device *dev)
 {
-	return pm_runtime_put(dev);
+	pm_runtime_put(dev);
+
+	return 0;
 }
 #endif
 
-- 
cgit v1.2.3


From 3afd8df024339c7da1a5a0302f3987866dd16e40 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 22 Dec 2025 21:36:25 +0100
Subject: PM: runtime: Change pm_runtime_put() return type to void

The primary role of pm_runtime_put() is to decrement the runtime PM
usage counter of the given device.  It always does that regardless of
the value returned by it later.

In addition, if the runtime PM usage counter after decrementation turns
out to be zero, a work item is queued up to check whether or not the
device can be suspended.  This is not guaranteed to succeed though and
even if it is successful, the device may still not be suspended going
forward.

There are multiple valid reasons why pm_runtime_put() may not decide to
queue up the work item mentioned above, including, but not limited to,
the case when user space has written "on" to the device's runtime PM
"control" file in sysfs.  In all of those cases, pm_runtime_put()
returns a negative error code (even though the device's runtime PM
usage counter has been successfully decremented by it) which is very
confusing.  In fact, its return value should only be used for debug
purposes and care should be taken when doing it even in that case.

Accordingly, to avoid the confusion mentioned above, change the return
type of pm_runtime_put() to void.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Link: https://patch.msgid.link/14387202.RDIVbhacDa@rafael.j.wysocki
---
 include/linux/pm_runtime.h | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 41037c513f06..64921b10ac74 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev)
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_idle().
- *
- * Return:
- * * 1: Success. Usage counter dropped to zero, but device was already suspended.
- * * 0: Success.
- * * -EINVAL: Runtime PM error.
- * * -EACCES: Runtime PM disabled.
- * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status
- *            change ongoing.
- * * -EBUSY: Runtime PM child_count non-zero.
- * * -EPERM: Device PM QoS resume latency 0.
- * * -EINPROGRESS: Suspend already in progress.
- * * -ENOSYS: CONFIG_PM not enabled.
  */
-static inline int pm_runtime_put(struct device *dev)
+static inline void pm_runtime_put(struct device *dev)
 {
-	return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
+	__pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC);
 }
 
 /**
-- 
cgit v1.2.3


From 014077044e874e270ec480515edbc1cadb976cf2 Mon Sep 17 00:00:00 2001
From: Richard Genoud <richard.genoud@bootlin.com>
Date: Tue, 23 Dec 2025 08:25:49 +0100
Subject: soc: fsl: qbman: fix race condition in qman_destroy_fq

When QMAN_FQ_FLAG_DYNAMIC_FQID is set, there's a race condition between
fq_table[fq->idx] state and freeing/allocating from the pool and
WARN_ON(fq_table[fq->idx]) in qman_create_fq() gets triggered.

Indeed, we can have:
         Thread A                             Thread B
    qman_destroy_fq()                    qman_create_fq()
      qman_release_fqid()
        qman_shutdown_fq()
        gen_pool_free()
           -- At this point, the fqid is available again --
                                           qman_alloc_fqid()
           -- so, we can get the just-freed fqid in thread B --
                                           fq->fqid = fqid;
                                           fq->idx = fqid * 2;
                                           WARN_ON(fq_table[fq->idx]);
                                           fq_table[fq->idx] = fq;
     fq_table[fq->idx] = NULL;

And adding some logs between qman_release_fqid() and
fq_table[fq->idx] = NULL makes the WARN_ON() trigger a lot more.

To prevent that, ensure that fq_table[fq->idx] is set to NULL before
gen_pool_free() is called by using smp_wmb().

Fixes: c535e923bb97 ("soc/fsl: Introduce DPAA 1.x QMan device driver")
Signed-off-by: Richard Genoud <richard.genoud@bootlin.com>
Tested-by: CHAMPSEIX Thomas <thomas.champseix@alstomgroup.com>
Link: https://lore.kernel.org/r/20251223072549.397625-1-richard.genoud@bootlin.com
Signed-off-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
---
 drivers/soc/fsl/qbman/qman.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index 411381f1a1c4..9ddafcb18f1c 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -1827,6 +1827,8 @@ EXPORT_SYMBOL(qman_create_fq);
 
 void qman_destroy_fq(struct qman_fq *fq)
 {
+	int leaked;
+
 	/*
 	 * We don't need to lock the FQ as it is a pre-condition that the FQ be
 	 * quiesced. Instead, run some checks.
@@ -1834,11 +1836,29 @@ void qman_destroy_fq(struct qman_fq *fq)
 	switch (fq->state) {
 	case qman_fq_state_parked:
 	case qman_fq_state_oos:
-		if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID))
-			qman_release_fqid(fq->fqid);
+		/*
+		 * There's a race condition here on releasing the fqid,
+		 * setting the fq_table to NULL, and freeing the fqid.
+		 * To prevent it, this order should be respected:
+		 */
+		if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID)) {
+			leaked = qman_shutdown_fq(fq->fqid);
+			if (leaked)
+				pr_debug("FQID %d leaked\n", fq->fqid);
+		}
 
 		DPAA_ASSERT(fq_table[fq->idx]);
 		fq_table[fq->idx] = NULL;
+
+		if (fq_isset(fq, QMAN_FQ_FLAG_DYNAMIC_FQID) && !leaked) {
+			/*
+			 * fq_table[fq->idx] should be set to null before
+			 * freeing fq->fqid otherwise it could by allocated by
+			 * qman_alloc_fqid() while still being !NULL
+			 */
+			smp_wmb();
+			gen_pool_free(qm_fqalloc, fq->fqid | DPAA_GENALLOC_OFF, 1);
+		}
 		return;
 	default:
 		break;
-- 
cgit v1.2.3


From 3f4e403304186d79fddace860360540fc3af97f9 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Mon, 9 Feb 2026 09:59:04 +0800
Subject: soc: fsl: cpm1: qmc: Fix error check for devm_ioremap_resource() in
 qmc_qe_init_resources()

Fix wrong variable used for error checking after devm_ioremap_resource()
call. The function checks qmc->scc_pram instead of qmc->dpram, which
could lead to incorrect error handling.

Fixes: eb680d563089 ("soc: fsl: cpm1: qmc: Add support for QUICC Engine (QE) implementation")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Acked-by: Herve Codina <herve.codina@bootlin.com>
Link: https://lore.kernel.org/r/20260209015904.871269-1-nichen@iscas.ac.cn
Signed-off-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
---
 drivers/soc/fsl/qe/qmc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index c4587b32a59b..672adff8e35f 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -1790,8 +1790,8 @@ static int qmc_qe_init_resources(struct qmc *qmc, struct platform_device *pdev)
 		return -EINVAL;
 	qmc->dpram_offset = res->start - qe_muram_dma(qe_muram_addr(0));
 	qmc->dpram = devm_ioremap_resource(qmc->dev, res);
-	if (IS_ERR(qmc->scc_pram))
-		return PTR_ERR(qmc->scc_pram);
+	if (IS_ERR(qmc->dpram))
+		return PTR_ERR(qmc->dpram);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 3c99a545b372c77b5d39715968a141f523eccbf2 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Wed, 18 Feb 2026 10:32:35 +0530
Subject: platform/x86: hp-wmi: Add Omen 16-xd0xxx fan and thermal support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-xd0xxx (board ID: 8BCD) has the same WMI interface as
other Victus S boards, but requires quirks for correctly switching
thermal profile (similar to HP Omen 16-wf1xxx, board ID: 8C78).

Add the DMI board name to victus_s_thermal_profile_boards[] table and
map it to omen_v1_thermal_params.

Testing on HP Omen 16-xd0xxx confirmed that platform profile is
registered successfully and fan RPMs are readable and controllable.

Tested-by: Varad Amol Pisale <varadpisale.work@gmail.com>
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260218050235.94687-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 304d9ac63c8a..b91965117edd 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -177,6 +177,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") },
 		.driver_data = (void *)&victus_s_thermal_params,
 	},
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD4") },
 		.driver_data = (void *)&victus_s_thermal_params,
-- 
cgit v1.2.3


From 7d87ed70fc95482c12edf9493c249b6413be485e Mon Sep 17 00:00:00 2001
From: Hans de Goede <johannes.goede@oss.qualcomm.com>
Date: Tue, 17 Feb 2026 14:23:46 +0100
Subject: platform/x86: touchscreen_dmi: Add quirk for y-inverted Goodix
 touchscreen on SUPI S10
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The touchscreen on the SUPI S10 tablet reports inverted Y coordinates,
causing touch input to be mirrored vertically relative to the display.

Add a quirk to set the "touchscreen-inverted-y" boolean device-property
on the touchscreen device, so that the goodix_ts driver will fixup
the coordinates.

Reported-by: Yajat Kumar <yajatapps3@gmail.com>
Closes: https://lore.kernel.org/linux-input/20251230221639.582406-1-yajatapps3@gmail.com/
Tested-by: Yajat Kumar <yajatapps3@gmail.com>
Signed-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260217132346.34535-1-johannes.goede@oss.qualcomm.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/touchscreen_dmi.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index bdc19cd8d3ed..d83c387821ea 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -410,6 +410,16 @@ static const struct ts_dmi_data gdix1002_upside_down_data = {
 	.properties	= gdix1001_upside_down_props,
 };
 
+static const struct property_entry gdix1001_y_inverted_props[] = {
+	PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+	{ }
+};
+
+static const struct ts_dmi_data gdix1001_y_inverted_data = {
+	.acpi_name	= "GDIX1001",
+	.properties	= gdix1001_y_inverted_props,
+};
+
 static const struct property_entry gp_electronic_t701_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-size-x", 960),
 	PROPERTY_ENTRY_U32("touchscreen-size-y", 640),
@@ -1658,6 +1668,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_SKU, "PN20170413488"),
 		},
 	},
+	{
+		/* SUPI S10 */
+		.driver_data = (void *)&gdix1001_y_inverted_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SUPI"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "S10"),
+		},
+	},
 	{
 		/* Techbite Arc 11.6 */
 		.driver_data = (void *)&techbite_arc_11_6_data,
-- 
cgit v1.2.3


From 13fa3aaf02edaad9b41fc61d7f6326d2b6a4bf80 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Mon, 16 Feb 2026 12:50:03 +0530
Subject: platform/x86: hp-wmi: Add Omen 16-wf0xxx fan and thermal support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-wf0xxx (board ID: 8BAB) has the same WMI interface as
other Victus S boards, but requires quirks for correctly switching
thermal profile (similar to HP Omen 16-wf1xxx, board ID: 8C78).

Add the DMI board name to victus_s_thermal_profile_boards[] table and
map it to omen_v1_thermal_params.

Testing on HP Omen 16-wf0xxx confirmed that platform profile is
registered successfully and fan RPMs are readable and controllable.

Suggested-by: Noah Provenzano <noahpro@gmail.com>
Tested-by: Juan Martin Morales <juanm4morales@gmail.com>
Reported-by: Juan Martin Morales <juanm4morales@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220639
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260216072003.90151-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index b91965117edd..bde74a02ccb3 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -173,6 +173,10 @@ static const char * const victus_thermal_profile_boards[] = {
 
 /* DMI Board names of Victus 16-r and Victus 16-s laptops */
 static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = {
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") },
 		.driver_data = (void *)&victus_s_thermal_params,
-- 
cgit v1.2.3


From 53e977b1d50c46f2c4ec3865cd13a822f58ad3cd Mon Sep 17 00:00:00 2001
From: Jonathan Teh <jonathan.teh@outlook.com>
Date: Mon, 16 Feb 2026 01:01:29 +0000
Subject: platform/x86: thinkpad_acpi: Fix errors reading battery thresholds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Check whether the battery supports the relevant charge threshold before
reading the value to silence these errors:

thinkpad_acpi: acpi_evalf(BCTG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCTG: evaluate failed
thinkpad_acpi: acpi_evalf(BCSG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCSG: evaluate failed

when reading the charge thresholds via sysfs on platforms that do not
support them such as the ThinkPad T400.

Fixes: 2801b9683f74 ("thinkpad_acpi: Add support for battery thresholds")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=202619
Signed-off-by: Jonathan Teh <jonathan.teh@outlook.com>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://patch.msgid.link/MI0P293MB01967B206E1CA6F337EBFB12926CA@MI0P293MB0196.ITAP293.PROD.OUTLOOK.COM
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/lenovo/thinkpad_acpi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/lenovo/thinkpad_acpi.c b/drivers/platform/x86/lenovo/thinkpad_acpi.c
index f9c736777908..8982d92dfd97 100644
--- a/drivers/platform/x86/lenovo/thinkpad_acpi.c
+++ b/drivers/platform/x86/lenovo/thinkpad_acpi.c
@@ -9525,14 +9525,16 @@ static int tpacpi_battery_get(int what, int battery, int *ret)
 {
 	switch (what) {
 	case THRESHOLD_START:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery))
+		if (!battery_info.batteries[battery].start_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery)))
 			return -ENODEV;
 
 		/* The value is in the low 8 bits of the response */
 		*ret = *ret & 0xFF;
 		return 0;
 	case THRESHOLD_STOP:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery))
+		if (!battery_info.batteries[battery].stop_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery)))
 			return -ENODEV;
 		/* Value is in lower 8 bits */
 		*ret = *ret & 0xFF;
-- 
cgit v1.2.3


From 6b3fa0615cd8432148581de62a52f83847af3d70 Mon Sep 17 00:00:00 2001
From: Peter Metz <peter.metz@unarin.com>
Date: Thu, 12 Feb 2026 23:46:27 -0500
Subject: platform/x86: intel-hid: Add Dell 14 Plus 2-in-1 to
 dmi_vgbs_allow_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Dell 14 Plus 2-in-1 (model DB04250) requires the VGBS allow list
entry to correctly enable the tablet mode switch. Without this, the
chassis state is not reported, and the hinge rotation only emits
unknown scancodes.

Verified on Dell 14 Plus 2-in-1 DB04250.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221090
Signed-off-by: Peter Metz <peter.metz@unarin.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260213044627.203638-1-peter.metz@unarin.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 0f8684f4464b..60ce32f591ff 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -189,6 +189,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell Pro Rugged 12 Tablet RA02260"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 14 Plus 2-in-1 DB04250"),
+		},
+	},
 	{ }
 };
 
-- 
cgit v1.2.3


From 857f5036f8fd729e097efbe3ba421b75e27346cb Mon Sep 17 00:00:00 2001
From: Peter Metz <peter.metz@unarin.com>
Date: Fri, 13 Feb 2026 17:58:02 -0500
Subject: platform/x86: intel-hid: Add Dell 16 Plus 2-in-1 to
 dmi_vgbs_allow_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Dell 16 Plus 2-in-1 (model DB06250) requires the VGBS allow list
entry to correctly enable the tablet mode switch. Without this, the
chassis state is not reported, and the hinge rotation only emits
unknown scancodes.

Link: https://lore.kernel.org/platform-driver-x86/CAP3yi-BWm0LqkhfzTrGy5n-KQ=3+T8eRMoR+Z+7Ke2VJB43kTA@mail.gmail.com/
Signed-off-by: Peter Metz <peter.metz@unarin.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260213230310.299974-1-peter.metz@unarin.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 60ce32f591ff..a8ae2dba7ffd 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -195,6 +195,12 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 14 Plus 2-in-1 DB04250"),
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell 16 Plus 2-in-1 DB06250"),
+		},
+	},
 	{ }
 };
 
-- 
cgit v1.2.3


From 37da69dbaa60a778ffa67a066b77d287d704c659 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Wed, 11 Feb 2026 22:26:59 +0100
Subject: platform/x86: asus-armoury: add support for G733QS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model G733QS.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260211212659.16542-1-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 6e9703bd5017..001c011fdd56 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1708,6 +1708,20 @@ static const struct dmi_system_id power_limits[] = {
 			.requires_fan_curve = true,
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "G733QS"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 15,
+				.ppt_pl2_sppt_max = 80,
+			},
+			.requires_fan_curve = false,
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G814J"),
-- 
cgit v1.2.3


From 32fc4168fa56f6301d858c778a3d712774e9657e Mon Sep 17 00:00:00 2001
From: Azamat Almazbek uulu <almazbek1608@gmail.com>
Date: Sat, 21 Feb 2026 12:48:13 +0100
Subject: ASoC: amd: yc: Add ASUS EXPERTBOOK BM1503CDA to quirk table

The ASUS ExpertBook BM1503CDA (Ryzen 5 7535U, Barcelo-R) has an
internal DMIC connected through the AMD ACP (Audio CoProcessor)
but is missing from the DMI quirk table, so the acp6x machine
driver probe returns -ENODEV and no DMIC capture device is created.

Add the DMI entry so the internal microphone works out of the box.

Signed-off-by: Azamat Almazbek uulu <almazbek1608@gmail.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://patch.msgid.link/20260221114813.5610-1-almazbek1608@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index f1a63475100d..7af4daeb4c6f 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -703,6 +703,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 				DMI_MATCH(DMI_PRODUCT_NAME, "Vivobook_ASUSLaptop M6501RR_M6501RR"),
 			}
 		},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"),
+		}
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 4b73231b2a61c4142a027613d277a19c484dfcc3 Mon Sep 17 00:00:00 2001
From: Yufan Chen <ericterminal@gmail.com>
Date: Sun, 22 Feb 2026 18:40:35 +0800
Subject: regulator: tps65185: check devm_kzalloc() result in probe

tps65185_probe() dereferences the allocation result immediately by using data->regmap. If devm_kzalloc() returns NULL under memory pressure, this leads to a NULL pointer dereference.

Add the missing allocation check and return -ENOMEM on failure.

Signed-off-by: Yufan Chen <ericterminal@gmail.com>
Link: https://patch.msgid.link/20260222104035.90790-1-ericterminal@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps65185.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/regulator/tps65185.c b/drivers/regulator/tps65185.c
index 3286c9ab33d0..786622d8d598 100644
--- a/drivers/regulator/tps65185.c
+++ b/drivers/regulator/tps65185.c
@@ -332,6 +332,9 @@ static int tps65185_probe(struct i2c_client *client)
 	int i;
 
 	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
 	data->regmap = devm_regmap_init_i2c(client, &regmap_config);
 	if (IS_ERR(data->regmap))
 		return dev_err_probe(&client->dev, PTR_ERR(data->regmap),
-- 
cgit v1.2.3


From f895e5df80316a308c2f7d64d13a78494630ea05 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Thu, 12 Feb 2026 21:52:48 -0600
Subject: ipmi:si: Don't block module unload if the BMC is messed up

If the BMC is in a bad state, don't bother waiting for queues messages
since there can't be any.  Otherwise the unload is blocked until the
BMC is back in a good state.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_si_intf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 0049e3792ba1..3667033fcc51 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2234,7 +2234,8 @@ static void wait_msg_processed(struct smi_info *smi_info)
 	unsigned long jiffies_now;
 	long time_diff;
 
-	while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) {
+	while (smi_info->si_state != SI_HOSED &&
+		    (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL))) {
 		jiffies_now = jiffies;
 		time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies)
 		     * SI_USEC_PER_JIFFY);
-- 
cgit v1.2.3


From 62cd145453d577113f993efd025f258dd86aa183 Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Thu, 12 Feb 2026 21:56:54 -0600
Subject: ipmi:msghandler: Handle error returns from the SMI sender

It used to be, until recently, that the sender operation on the low
level interfaces would not fail.  That's not the case any more with
recent changes.

So check the return value from the sender operation, and propagate it
back up from there and handle the errors in all places.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_msghandler.c | 100 ++++++++++++++++++++++++------------
 1 file changed, 68 insertions(+), 32 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index a042b1596933..f8c3c1e44520 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -1887,19 +1887,32 @@ static struct ipmi_smi_msg *smi_add_send_msg(struct ipmi_smi *intf,
 	return smi_msg;
 }
 
-static void smi_send(struct ipmi_smi *intf,
+static int smi_send(struct ipmi_smi *intf,
 		     const struct ipmi_smi_handlers *handlers,
 		     struct ipmi_smi_msg *smi_msg, int priority)
 {
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	unsigned long flags = 0;
+	int rv = 0;
 
 	ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
 	smi_msg = smi_add_send_msg(intf, smi_msg, priority);
 	ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
 
-	if (smi_msg)
-		handlers->sender(intf->send_info, smi_msg);
+	if (smi_msg) {
+		rv = handlers->sender(intf->send_info, smi_msg);
+		if (rv) {
+			ipmi_lock_xmit_msgs(intf, run_to_completion, &flags);
+			intf->curr_msg = NULL;
+			ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags);
+			/*
+			 * Something may have been added to the transmit
+			 * queue, so schedule a check for that.
+			 */
+			queue_work(system_wq, &intf->smi_work);
+		}
+	}
+	return rv;
 }
 
 static bool is_maintenance_mode_cmd(struct kernel_ipmi_msg *msg)
@@ -2312,6 +2325,7 @@ static int i_ipmi_request(struct ipmi_user     *user,
 	struct ipmi_recv_msg *recv_msg;
 	int run_to_completion = READ_ONCE(intf->run_to_completion);
 	int rv = 0;
+	bool in_seq_table = false;
 
 	if (supplied_recv) {
 		recv_msg = supplied_recv;
@@ -2365,33 +2379,50 @@ static int i_ipmi_request(struct ipmi_user     *user,
 		rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg,
 				     source_address, source_lun,
 				     retries, retry_time_ms);
+		in_seq_table = true;
 	} else if (is_ipmb_direct_addr(addr)) {
 		rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg,
 					    recv_msg, source_lun);
 	} else if (is_lan_addr(addr)) {
 		rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg,
 				    source_lun, retries, retry_time_ms);
+		in_seq_table = true;
 	} else {
-	    /* Unknown address type. */
+		/* Unknown address type. */
 		ipmi_inc_stat(intf, sent_invalid_commands);
 		rv = -EINVAL;
 	}
 
-	if (rv) {
-out_err:
-		if (!supplied_smi)
-			ipmi_free_smi_msg(smi_msg);
-		if (!supplied_recv)
-			ipmi_free_recv_msg(recv_msg);
-	} else {
+	if (!rv) {
 		dev_dbg(intf->si_dev, "Send: %*ph\n",
 			smi_msg->data_size, smi_msg->data);
 
-		smi_send(intf, intf->handlers, smi_msg, priority);
+		rv = smi_send(intf, intf->handlers, smi_msg, priority);
+		if (rv != IPMI_CC_NO_ERROR)
+			/* smi_send() returns an IPMI err, return a Linux one. */
+			rv = -EIO;
+		if (rv && in_seq_table) {
+			/*
+			 * If it's in the sequence table, it will be
+			 * retried later, so ignore errors.
+			 */
+			rv = 0;
+			/* But we need to fix the timeout. */
+			intf_start_seq_timer(intf, smi_msg->msgid);
+			ipmi_free_smi_msg(smi_msg);
+			smi_msg = NULL;
+		}
 	}
+out_err:
 	if (!run_to_completion)
 		mutex_unlock(&intf->users_mutex);
 
+	if (rv) {
+		if (!supplied_smi)
+			ipmi_free_smi_msg(smi_msg);
+		if (!supplied_recv)
+			ipmi_free_recv_msg(recv_msg);
+	}
 	return rv;
 }
 
@@ -3965,12 +3996,12 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf,
 		dev_dbg(intf->si_dev, "Invalid command: %*ph\n",
 			msg->data_size, msg->data);
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		ipmb_addr = (struct ipmi_ipmb_addr *) &recv_msg->addr;
@@ -4044,12 +4075,12 @@ static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf,
 		msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE;
 		msg->data_size = 5;
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr;
@@ -4189,7 +4220,7 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf,
 				  struct ipmi_smi_msg *msg)
 {
 	struct cmd_rcvr          *rcvr;
-	int                      rv = 0;
+	int                      rv = 0; /* Free by default */
 	unsigned char            netfn;
 	unsigned char            cmd;
 	unsigned char            chan;
@@ -4242,12 +4273,12 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf,
 		dev_dbg(intf->si_dev, "Invalid command: %*ph\n",
 			msg->data_size, msg->data);
 
-		smi_send(intf, intf->handlers, msg, 0);
-		/*
-		 * We used the message, so return the value that
-		 * causes it to not be freed or queued.
-		 */
-		rv = -1;
+		if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR)
+			/*
+			 * We used the message, so return the value that
+			 * causes it to not be freed or queued.
+			 */
+			rv = -1;
 	} else if (!IS_ERR(recv_msg)) {
 		/* Extract the source address from the data. */
 		lan_addr = (struct ipmi_lan_addr *) &recv_msg->addr;
@@ -5056,7 +5087,12 @@ static void check_msg_timeout(struct ipmi_smi *intf, struct seq_table *ent,
 				ipmi_inc_stat(intf,
 					      retransmitted_ipmb_commands);
 
-			smi_send(intf, intf->handlers, smi_msg, 0);
+			/* If this fails we'll retry later or timeout. */
+			if (smi_send(intf, intf->handlers, smi_msg, 0) != IPMI_CC_NO_ERROR) {
+				/* But fix the timeout. */
+				intf_start_seq_timer(intf, smi_msg->msgid);
+				ipmi_free_smi_msg(smi_msg);
+			}
 		} else
 			ipmi_free_smi_msg(smi_msg);
 
-- 
cgit v1.2.3


From cae66f1a1dcd23e17da5a015ef9d731129f9d2dd Mon Sep 17 00:00:00 2001
From: Corey Minyard <corey@minyard.net>
Date: Fri, 13 Feb 2026 00:15:04 -0600
Subject: ipmi:si: Fix check for a misbehaving BMC

There is a race on checking the state in the sender, it needs to be
checked under a lock.  But you also need a check to avoid issues with
a misbehaving BMC for run to completion mode.  So leave the check at
the beginning for run to completion, and add a check under the lock
to avoid the race.

Reported-by: Rafael J. Wysocki <rafael@kernel.org>
Fixes: bc3a9d217755 ("ipmi:si: Gracefully handle if the BMC is non-functional")
Cc: stable@vger.kernel.org # 4.18
Signed-off-by: Corey Minyard <corey@minyard.net>
Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
---
 drivers/char/ipmi/ipmi_si_intf.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 3667033fcc51..6eda61664aaa 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -924,9 +924,14 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg)
 {
 	struct smi_info   *smi_info = send_info;
 	unsigned long     flags;
+	int rv = IPMI_CC_NO_ERROR;
 
 	debug_timestamp(smi_info, "Enqueue");
 
+	/*
+	 * Check here for run to completion mode.  A check under lock is
+	 * later.
+	 */
 	if (smi_info->si_state == SI_HOSED)
 		return IPMI_BUS_ERR;
 
@@ -940,18 +945,15 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg)
 	}
 
 	spin_lock_irqsave(&smi_info->si_lock, flags);
-	/*
-	 * The following two lines don't need to be under the lock for
-	 * the lock's sake, but they do need SMP memory barriers to
-	 * avoid getting things out of order.  We are already claiming
-	 * the lock, anyway, so just do it under the lock to avoid the
-	 * ordering problem.
-	 */
-	BUG_ON(smi_info->waiting_msg);
-	smi_info->waiting_msg = msg;
-	check_start_timer_thread(smi_info);
+	if (smi_info->si_state == SI_HOSED) {
+		rv = IPMI_BUS_ERR;
+	} else {
+		BUG_ON(smi_info->waiting_msg);
+		smi_info->waiting_msg = msg;
+		check_start_timer_thread(smi_info);
+	}
 	spin_unlock_irqrestore(&smi_info->si_lock, flags);
-	return IPMI_CC_NO_ERROR;
+	return rv;
 }
 
 static void set_run_to_completion(void *send_info, bool i_run_to_completion)
-- 
cgit v1.2.3


From 8225489ddb900656cc21573b4e1b00c9181fd777 Mon Sep 17 00:00:00 2001
From: Artem Lytkin <iprintercanon@gmail.com>
Date: Mon, 16 Feb 2026 20:20:38 +0000
Subject: staging: sm750fb: add missing pci_release_region on error and removal

hw_sm750_map() calls pci_request_region() but never releases the
region on error paths or in lynxfb_pci_remove(). This causes a
resource leak that prevents the PCI region from being mapped again
after driver removal or a failed probe. A TODO comment in the code
acknowledges this missing cleanup.

Restructure the error handling in hw_sm750_map() to properly release
the PCI region on ioremap failures, and add pci_release_region() to
lynxfb_pci_remove().

Signed-off-by: Artem Lytkin <iprintercanon@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260216202038.1828-1-iprintercanon@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/sm750fb/sm750.c    |  1 +
 drivers/staging/sm750fb/sm750_hw.c | 22 +++++++++++-----------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/staging/sm750fb/sm750.c b/drivers/staging/sm750fb/sm750.c
index dec1f6b88a7d..62f6e0cdff4d 100644
--- a/drivers/staging/sm750fb/sm750.c
+++ b/drivers/staging/sm750fb/sm750.c
@@ -1123,6 +1123,7 @@ static void lynxfb_pci_remove(struct pci_dev *pdev)
 
 	iounmap(sm750_dev->pvReg);
 	iounmap(sm750_dev->pvMem);
+	pci_release_region(pdev, 1);
 	kfree(g_settings);
 }
 
diff --git a/drivers/staging/sm750fb/sm750_hw.c b/drivers/staging/sm750fb/sm750_hw.c
index a29faee91c78..f60b152a647d 100644
--- a/drivers/staging/sm750fb/sm750_hw.c
+++ b/drivers/staging/sm750fb/sm750_hw.c
@@ -36,16 +36,11 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 
 	pr_info("mmio phyAddr = %lx\n", sm750_dev->vidreg_start);
 
-	/*
-	 * reserve the vidreg space of smi adaptor
-	 * if you do this, you need to add release region code
-	 * in lynxfb_remove, or memory will not be mapped again
-	 * successfully
-	 */
+	/* reserve the vidreg space of smi adaptor */
 	ret = pci_request_region(pdev, 1, "sm750fb");
 	if (ret) {
 		pr_err("Can not request PCI regions.\n");
-		goto exit;
+		return ret;
 	}
 
 	/* now map mmio and vidmem */
@@ -54,7 +49,7 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 	if (!sm750_dev->pvReg) {
 		pr_err("mmio failed\n");
 		ret = -EFAULT;
-		goto exit;
+		goto err_release_region;
 	}
 	pr_info("mmio virtual addr = %p\n", sm750_dev->pvReg);
 
@@ -79,13 +74,18 @@ int hw_sm750_map(struct sm750_dev *sm750_dev, struct pci_dev *pdev)
 	sm750_dev->pvMem =
 		ioremap_wc(sm750_dev->vidmem_start, sm750_dev->vidmem_size);
 	if (!sm750_dev->pvMem) {
-		iounmap(sm750_dev->pvReg);
 		pr_err("Map video memory failed\n");
 		ret = -EFAULT;
-		goto exit;
+		goto err_unmap_reg;
 	}
 	pr_info("video memory vaddr = %p\n", sm750_dev->pvMem);
-exit:
+
+	return 0;
+
+err_unmap_reg:
+	iounmap(sm750_dev->pvReg);
+err_release_region:
+	pci_release_region(pdev, 1);
 	return ret;
 }
 
-- 
cgit v1.2.3


From f0109b9d3e1e455429279d602f6276e34689750a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 14:31:35 +0100
Subject: staging: rtl8723bs: properly validate the data in rtw_get_ie_ex()

Just like in commit 154828bf9559 ("staging: rtl8723bs: fix out-of-bounds
read in rtw_get_ie() parser"), we don't trust the data in the frame so
we should check the length better before acting on it

Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Tested-by: Navaneeth K <knavaneeth786@gmail.com>
Reviewed-by: Navaneeth K <knavaneeth786@gmail.com>
Link: https://patch.msgid.link/2026022336-arrange-footwork-6e54@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8723bs/core/rtw_ieee80211.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
index 6cf217e21593..3e2b5e6b07f9 100644
--- a/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
+++ b/drivers/staging/rtl8723bs/core/rtw_ieee80211.c
@@ -186,20 +186,25 @@ u8 *rtw_get_ie_ex(u8 *in_ie, uint in_len, u8 eid, u8 *oui, u8 oui_len, u8 *ie, u
 
 	cnt = 0;
 
-	while (cnt < in_len) {
+	while (cnt + 2 <= in_len) {
+		u8 ie_len = in_ie[cnt + 1];
+
+		if (cnt + 2 + ie_len > in_len)
+			break;
+
 		if (eid == in_ie[cnt]
-			&& (!oui || !memcmp(&in_ie[cnt+2], oui, oui_len))) {
+			&& (!oui || (ie_len >= oui_len && !memcmp(&in_ie[cnt + 2], oui, oui_len)))) {
 			target_ie = &in_ie[cnt];
 
 			if (ie)
-				memcpy(ie, &in_ie[cnt], in_ie[cnt+1]+2);
+				memcpy(ie, &in_ie[cnt], ie_len + 2);
 
 			if (ielen)
-				*ielen = in_ie[cnt+1]+2;
+				*ielen = ie_len + 2;
 
 			break;
 		}
-		cnt += in_ie[cnt+1]+2; /* goto next */
+		cnt += ie_len + 2; /* goto next */
 	}
 
 	return target_ie;
-- 
cgit v1.2.3


From 3ecea84d2b90bbf934d5ca75514fa902fd71e03f Mon Sep 17 00:00:00 2001
From: Daniel J Blueman <daniel@quora.org>
Date: Fri, 20 Feb 2026 20:44:58 +0800
Subject: arm64: dts: qcom: hamoa/x1: fix idle exit latency

Designs based on the Qualcomm X1 Hamoa reference platform report:
driver: Idle state 1 target residency too low

This is because the declared X1 idle entry plus exit latency of 680us
exceeds the declared minimum 600us residency time:
  entry-latency-us = <180>;
  exit-latency-us = <500>;
  min-residency-us = <600>;

Fix this to be 320us so the sum of the entry and exit latencies matches
the downstream 500us exit latency, as directed by Maulik.

Tested on a Lenovo Yoga Slim 7x with Qualcomm X1E-80-100.

Fixes: 2e65616ef07f ("arm64: dts: qcom: x1e80100: Update C4/C5 residency/exit numbers")
Signed-off-by: Daniel J Blueman <daniel@quora.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260220124626.8611-1-daniel@quora.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/hamoa.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/qcom/hamoa.dtsi b/arch/arm64/boot/dts/qcom/hamoa.dtsi
index db65c392e618..4b0784af4bd3 100644
--- a/arch/arm64/boot/dts/qcom/hamoa.dtsi
+++ b/arch/arm64/boot/dts/qcom/hamoa.dtsi
@@ -269,7 +269,7 @@
 				idle-state-name = "ret";
 				arm,psci-suspend-param = <0x00000004>;
 				entry-latency-us = <180>;
-				exit-latency-us = <500>;
+				exit-latency-us = <320>;
 				min-residency-us = <600>;
 			};
 		};
-- 
cgit v1.2.3


From 2a7b7652b1bb3fadc3bd47d622bfb127a93ab6b0 Mon Sep 17 00:00:00 2001
From: Leif Skunberg <diamondback@cohunt.app>
Date: Tue, 10 Feb 2026 14:21:29 +0100
Subject: platform/x86: int3472: Handle GPIO type 0x10 (DOVDD)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Lenovo ThinkPad X1 Fold 16 Gen 1 has an OV5675 sensor (ACPI HID
OVTI5675) behind an INT3472 discrete PMIC controller. The INT3472
_DSM returns GPIO type 0x10 for one of the pins, which controls the
DOVDD (digital I/O power) regulator enable.

Type 0x10 is not currently handled by the driver, causing the GPIO to
be ignored with a warning. Add INT3472_GPIO_TYPE_DOVDD (0x10) and
handle it as a regulator with con_id "dovdd" to match the supply name
used by sensor drivers (e.g. ov5675).

Also increase GPIO_SUPPLY_NAME_LENGTH from 5 to 6 to accommodate
the "dovdd" name (5 chars + null terminator).

Signed-off-by: Leif Skunberg <diamondback@cohunt.app>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260210132129.17943-1-diamondback@cohunt.app
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/int3472/discrete.c | 7 +++++++
 include/linux/platform_data/x86/int3472.h     | 5 +++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 1455d9a7afca..1c65ce87cde0 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -223,6 +223,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
 		*con_id = "avdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
+	case INT3472_GPIO_TYPE_DOVDD:
+		*con_id = "dovdd";
+		*gpio_flags = GPIO_ACTIVE_HIGH;
+		break;
 	case INT3472_GPIO_TYPE_HANDSHAKE:
 		*con_id = "dvdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
@@ -251,6 +255,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
  * 0x0b Power enable
  * 0x0c Clock enable
  * 0x0d Privacy LED
+ * 0x10 DOVDD (digital I/O voltage)
  * 0x13 Hotplug detect
  *
  * There are some known platform specific quirks where that does not quite
@@ -332,6 +337,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	case INT3472_GPIO_TYPE_CLK_ENABLE:
 	case INT3472_GPIO_TYPE_PRIVACY_LED:
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
+	case INT3472_GPIO_TYPE_DOVDD:
 	case INT3472_GPIO_TYPE_HANDSHAKE:
 		gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, con_id, gpio_flags);
 		if (IS_ERR(gpio)) {
@@ -356,6 +362,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 		case INT3472_GPIO_TYPE_POWER_ENABLE:
 			second_sensor = int3472->quirks.avdd_second_sensor;
 			fallthrough;
+		case INT3472_GPIO_TYPE_DOVDD:
 		case INT3472_GPIO_TYPE_HANDSHAKE:
 			ret = skl_int3472_register_regulator(int3472, gpio, enable_time_us,
 							     con_id, second_sensor);
diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h
index b1b837583d54..dbe745dc88d5 100644
--- a/include/linux/platform_data/x86/int3472.h
+++ b/include/linux/platform_data/x86/int3472.h
@@ -26,6 +26,7 @@
 #define INT3472_GPIO_TYPE_POWER_ENABLE				0x0b
 #define INT3472_GPIO_TYPE_CLK_ENABLE				0x0c
 #define INT3472_GPIO_TYPE_PRIVACY_LED				0x0d
+#define INT3472_GPIO_TYPE_DOVDD					0x10
 #define INT3472_GPIO_TYPE_HANDSHAKE				0x12
 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT			0x13
 
@@ -33,8 +34,8 @@
 #define INT3472_MAX_SENSOR_GPIOS				3
 #define INT3472_MAX_REGULATORS					3
 
-/* E.g. "avdd\0" */
-#define GPIO_SUPPLY_NAME_LENGTH				5
+/* E.g. "dovdd\0" */
+#define GPIO_SUPPLY_NAME_LENGTH				6
 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */
 #define GPIO_REGULATOR_NAME_LENGTH				(12 + GPIO_SUPPLY_NAME_LENGTH)
 /* lower- and upper-case mapping */
-- 
cgit v1.2.3


From b38d478dad79e61e8a65931021bdfd7a71741212 Mon Sep 17 00:00:00 2001
From: Leif Skunberg <diamondback@cohunt.app>
Date: Tue, 10 Feb 2026 09:56:25 +0100
Subject: platform/x86: intel-hid: Enable 5-button array on ThinkPad X1 Fold 16
 Gen 1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Lenovo ThinkPad X1 Fold 16 Gen 1 has physical volume up/down
buttons that are handled through the intel-hid 5-button array
interface. The firmware does not advertise 5-button array support via
HEBC, so the driver relies on a DMI allowlist to enable it.

Add the ThinkPad X1 Fold 16 Gen 1 to the button_array_table so the
volume buttons work out of the box.

Signed-off-by: Leif Skunberg <diamondback@cohunt.app>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260210085625.34380-1-diamondback@cohunt.app
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index a8ae2dba7ffd..95c405c8bac0 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -135,6 +135,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
 		},
 	},
+	{
+		.ident = "Lenovo ThinkPad X1 Fold 16 Gen 1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Fold 16 Gen 1"),
+		},
+	},
 	{
 		.ident = "Microsoft Surface Go 3",
 		.matches = {
-- 
cgit v1.2.3


From 249f05e625c6e6c14b27fd34a2f06a1afb9b456d Mon Sep 17 00:00:00 2001
From: Victor Lattaro Volpini <victorlattaro@proton.me>
Date: Tue, 10 Feb 2026 00:00:52 +0000
Subject: platform/x86: hp-wmi: Add Victus 16-d0xxx support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch enables Victus thermal profile support for the HP
Victus 16-d0xxx. It does so by adding model's DMI board name 88F8 to
victus_thermal_profile_boards.

Tested on a Victus 16-d0xxx:
  - Victus thermal profile choices available (quiet, balanced, performance)
    instead of the default ones (cool, quiet, balanced, performance);
  - Profile switching works correctly;
  - About 4% increase in FPS using benchmark Cyberpunk 2077 on
  performance profile;
  - No noticeable regressions.

Signed-off-by: Victor Lattaro Volpini <victorlattaro@proton.me>
Link: https://patch.msgid.link/20260210000048.250280-1-victorlattaro@proton.me
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index bde74a02ccb3..40165138cfbd 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -166,8 +166,9 @@ static const char * const omen_timed_thermal_profile_boards[] = {
 	"8BAD",
 };
 
-/* DMI Board names of Victus 16-d1xxx laptops */
+/* DMI Board names of Victus 16-d laptops */
 static const char * const victus_thermal_profile_boards[] = {
+	"88F8",
 	"8A25",
 };
 
-- 
cgit v1.2.3


From 26a7601471f62b95d56a81c3a8ccb551b5a6630f Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Sat, 7 Feb 2026 12:16:34 -0500
Subject: platform/x86: dell-wmi: Add audio/mic mute key codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add audio/mic mute key codes found in Alienware m18 r1 AMD.

Cc: stable@vger.kernel.org
Tested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Suggested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Acked-by: Pali Rohár <pali@kernel.org>
Link: https://patch.msgid.link/20260207-mute-keys-v2-1-c55e5471c9c1@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-wmi-base.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c
index 4eefbade2f5e..e7a411ae9ca1 100644
--- a/drivers/platform/x86/dell/dell-wmi-base.c
+++ b/drivers/platform/x86/dell/dell-wmi-base.c
@@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = {
 static const struct key_entry dell_wmi_keymap_type_0000[] = {
 	{ KE_IGNORE, 0x003a, { KEY_CAPSLOCK } },
 
+	/* Audio mute toggle */
+	{ KE_KEY,    0x0109, { KEY_MUTE } },
+
+	/* Mic mute toggle */
+	{ KE_KEY,    0x0150, { KEY_MICMUTE } },
+
 	/* Meta key lock */
 	{ KE_IGNORE, 0xe000, { KEY_RIGHTMETA } },
 
-- 
cgit v1.2.3


From 729ffcffa73069cb066fd54a2bc7b09e5f782d48 Mon Sep 17 00:00:00 2001
From: Anton Plotnikov <plotnikovanton@gmail.com>
Date: Tue, 3 Feb 2026 18:48:32 +0200
Subject: platform/x86: hp-wmi: add Omen 14-fb1xxx (board 8E41) support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reverse engineering of the HP Omen Windows utility shows that for performance
mode it uses the same codes listed in hp_thermal_profile_omen_v1. Therefore it
seems sufficient to add the board model name to omen_thermal_profile_boards.

Tested on Omen 14-fb1xxx: CPU power in performance profile reaches the Windows
limit (65W), instead of 45W in automatic BIOS mode. Max fan speed was reached
as well.

Link: https://patch.msgid.link/20260203164832.40514-1-plotnikovanton@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 40165138cfbd..68ede7e5757a 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -146,6 +146,7 @@ static const char * const omen_thermal_profile_boards[] = {
 	"8900", "8901", "8902", "8912", "8917", "8918", "8949", "894A", "89EB",
 	"8A15", "8A42",
 	"8BAD",
+	"8E41",
 };
 
 /* DMI Board names of Omen laptops that are specifically set to be thermal
-- 
cgit v1.2.3


From bd5914caeb4b2de233992c31babccda88041b035 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Thu, 29 Jan 2026 12:19:24 -0500
Subject: platform/x86: alienware-wmi-wmax: Add G-Mode support to m18 laptops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Alienware m18 laptops support G-Mode. Therefore, match them with
G-Series quirks.

Cc: stable@vger.kernel.org
Tested-by: Olexa Bilaniuk <obilaniu@gmail.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://patch.msgid.link/20260129-m18-gmode-v1-1-48be521487b9@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/alienware-wmi-wmax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index e69b50162bb1..d1b4df91401b 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -175,7 +175,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18"),
 		},
-		.driver_data = &generic_quirks,
+		.driver_data = &g_series_quirks,
 	},
 	{
 		.ident = "Alienware x15",
-- 
cgit v1.2.3


From e3aa6feaf0cc30a3c941d15ff04bc1005a8aa315 Mon Sep 17 00:00:00 2001
From: Jesse Guo <JesseGuoTech@outlook.com>
Date: Mon, 26 Jan 2026 04:48:26 +0800
Subject: platform/x86: redmi-wmi: Add more hotkey mappings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds more Fn hotkeys (like Refresh rate toggle).
Additionally, remap the setup key from KEY_SETUP to KEY_CONFIG.
As KEY_CONFIG is supported by Desktop Environments for launching
system settings, whereas KEY_SETUP is often ignored by userspace.

Signed-off-by: Jesse Guo <JesseGuoTech@outlook.com>
Reviewed-by: Gladyshev Ilya <foxido@foxido.dev>
Link: https://patch.msgid.link/TYCPR01MB6851636256C39B170F2312E5D192A@TYCPR01MB6851.jpnprd01.prod.outlook.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/redmi-wmi.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/redmi-wmi.c b/drivers/platform/x86/redmi-wmi.c
index 949236b93a32..e5cb348e3a39 100644
--- a/drivers/platform/x86/redmi-wmi.c
+++ b/drivers/platform/x86/redmi-wmi.c
@@ -20,7 +20,10 @@
 static const struct key_entry redmi_wmi_keymap[] = {
 	{KE_KEY, 0x00000201,	{KEY_SELECTIVE_SCREENSHOT}},
 	{KE_KEY, 0x00000301,	{KEY_ALL_APPLICATIONS}},
-	{KE_KEY, 0x00001b01,	{KEY_SETUP}},
+	{KE_KEY, 0x00001b01,	{KEY_CONFIG}},
+	{KE_KEY, 0x00011b01,	{KEY_CONFIG}},
+	{KE_KEY, 0x00010101,	{KEY_SWITCHVIDEOMODE}},
+	{KE_KEY, 0x00001a01,	{KEY_REFRESH_RATE_TOGGLE}},
 
 	/* AI button has code for each position */
 	{KE_KEY, 0x00011801,	{KEY_ASSISTANT}},
@@ -32,6 +35,26 @@ static const struct key_entry redmi_wmi_keymap[] = {
 	{KE_IGNORE, 0x00050501, {}},
 	{KE_IGNORE, 0x000a0501, {}},
 
+	/* Xiaomi G Command Center */
+	{KE_KEY, 0x00010a01,	{KEY_VENDOR}},
+
+	/* OEM preset power mode */
+	{KE_IGNORE, 0x00011601, {}},
+	{KE_IGNORE, 0x00021601, {}},
+	{KE_IGNORE, 0x00031601, {}},
+	{KE_IGNORE, 0x00041601, {}},
+
+	/* Fn Lock state */
+	{KE_IGNORE, 0x00000701, {}},
+	{KE_IGNORE, 0x00010701, {}},
+
+	/* Fn+`/1/2/3/4 */
+	{KE_KEY, 0x00011101, {KEY_F13}},
+	{KE_KEY, 0x00011201, {KEY_F14}},
+	{KE_KEY, 0x00011301, {KEY_F15}},
+	{KE_KEY, 0x00011401, {KEY_F16}},
+	{KE_KEY, 0x00011501, {KEY_F17}},
+
 	{KE_END}
 };
 
-- 
cgit v1.2.3


From e0cf84109bc6c6768337123f1de24ff56b41c91b Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Wed, 4 Feb 2026 15:34:27 +0200
Subject: reset: rzg2l-usbphy-ctrl: Check pwrrdy is valid before using it

The pwrrdy regmap_filed is allocated in rzg2l_usbphy_ctrl_pwrrdy_init()
only if the driver data is set to RZG2L_USBPHY_CTRL_PWRRDY. Check that
pwrrdy is valid before using it to avoid "Unable to handle kernel NULL
pointer dereference at virtual address" errors.

Fixes: c5b7cd9adefc ("reset: rzg2l-usbphy-ctrl: Add suspend/resume support")
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/reset-rzg2l-usbphy-ctrl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
index 32bc268c9149..05dd9b4a02df 100644
--- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c
+++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
@@ -136,6 +136,9 @@ static int rzg2l_usbphy_ctrl_set_pwrrdy(struct regmap_field *pwrrdy,
 {
 	u32 val = power_on ? 0 : 1;
 
+	if (!pwrrdy)
+		return 0;
+
 	/* The initialization path guarantees that the mask is 1 bit long. */
 	return regmap_field_update_bits(pwrrdy, 1, val);
 }
-- 
cgit v1.2.3


From 318c58852e686c009825ae8c071080b9ccdd2af0 Mon Sep 17 00:00:00 2001
From: Gregory Price <gourry@gourry.net>
Date: Wed, 11 Feb 2026 14:22:27 -0500
Subject: cxl/memdev: fix deadlock in cxl_memdev_autoremove() on attach failure

cxl_memdev_autoremove() takes device_lock(&cxlmd->dev) via guard(device)
and then calls cxl_memdev_unregister() when the attach callback was
provided but cxl_mem_probe() failed to bind.

cxl_memdev_unregister() calls
  cdev_device_del()
    device_del()
      bus_remove_device()
        device_release_driver()

This path is reached when a driver uses the @attach parameter to
devm_cxl_add_memdev() and the CXL topology fails to enumerate (e.g.
DVSEC range registers decode outside platform-defined CXL ranges,
causing the endpoint port probe to fail).

Add cxl_memdev_attach_failed() to set the scope of the check correctly.

Reported-by: kreview-c94b85d6d2
Fixes: 29317f8dc6ed ("cxl/mem: Introduce cxl_memdev_attach for CXL-dependent operation")
Signed-off-by: Gregory Price <gourry@gourry.net>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Link: https://patch.msgid.link/20260211192228.2148713-1-gourry@gourry.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/memdev.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index f547d8ac34c7..273c22118d3d 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -1089,10 +1089,8 @@ static int cxlmd_add(struct cxl_memdev *cxlmd, struct cxl_dev_state *cxlds)
 DEFINE_FREE(put_cxlmd, struct cxl_memdev *,
 	    if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev))
 
-static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
+static bool cxl_memdev_attach_failed(struct cxl_memdev *cxlmd)
 {
-	int rc;
-
 	/*
 	 * If @attach is provided fail if the driver is not attached upon
 	 * return. Note that failure here could be the result of a race to
@@ -1100,7 +1098,14 @@ static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
 	 * succeeded and then cxl_mem unbound before the lock is acquired.
 	 */
 	guard(device)(&cxlmd->dev);
-	if (cxlmd->attach && !cxlmd->dev.driver) {
+	return (cxlmd->attach && !cxlmd->dev.driver);
+}
+
+static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd)
+{
+	int rc;
+
+	if (cxl_memdev_attach_failed(cxlmd)) {
 		cxl_memdev_unregister(cxlmd);
 		return ERR_PTR(-ENXIO);
 	}
-- 
cgit v1.2.3


From 2d53dfacf067968a9ff90c03700fb9b28049f4c6 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:50:58 +0100
Subject: platform/x86: uniwill-laptop: Rename FN lock and super key lock attrs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that both sysfs attributes actually directly control
the FN lock status/super key enable status, rather than the
triggering of the associated events. This behavior was first observed
on a Tuxedo notebook and was belived to be a hardware quirk.
However, it seems that i simply misunderstood the manual of the
OEM software for Intel NUC devices. The correct behavior is:

- fn_lock_toggle_enable enables/disables FN lock mode
- super_key_toggle_enable enables/disables the super key

Rename both sysfs attributes to avoid confusing users.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-2-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../ABI/testing/sysfs-driver-uniwill-laptop        | 10 ++--
 .../admin-guide/laptops/uniwill-laptop.rst         |  2 +-
 drivers/platform/x86/uniwill/uniwill-acpi.c        | 58 +++++++++++-----------
 drivers/platform/x86/uniwill/uniwill-wmi.h         |  6 +--
 4 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
index eaeb659793d2..2df70792968f 100644
--- a/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
+++ b/Documentation/ABI/testing/sysfs-driver-uniwill-laptop
@@ -1,4 +1,4 @@
-What:		/sys/bus/platform/devices/INOU0000:XX/fn_lock_toggle_enable
+What:		/sys/bus/platform/devices/INOU0000:XX/fn_lock
 Date:		November 2025
 KernelVersion:	6.19
 Contact:	Armin Wolf <W_Armin@gmx.de>
@@ -8,15 +8,15 @@ Description:
 
 		Reading this file returns the current enable status of the FN lock functionality.
 
-What:		/sys/bus/platform/devices/INOU0000:XX/super_key_toggle_enable
+What:		/sys/bus/platform/devices/INOU0000:XX/super_key_enable
 Date:		November 2025
 KernelVersion:	6.19
 Contact:	Armin Wolf <W_Armin@gmx.de>
 Description:
-                Allows userspace applications to enable/disable the super key functionality
-                of the integrated keyboard by writing "1"/"0" into this file.
+		Allows userspace applications to enable/disable the super key of the integrated
+		keyboard by writing "1"/"0" into this file.
 
-		Reading this file returns the current enable status of the super key functionality.
+		Reading this file returns the current enable status of the super key.
 
 What:		/sys/bus/platform/devices/INOU0000:XX/touchpad_toggle_enable
 Date:		November 2025
diff --git a/Documentation/admin-guide/laptops/uniwill-laptop.rst b/Documentation/admin-guide/laptops/uniwill-laptop.rst
index a16baf15516b..aff5f57a6bd4 100644
--- a/Documentation/admin-guide/laptops/uniwill-laptop.rst
+++ b/Documentation/admin-guide/laptops/uniwill-laptop.rst
@@ -24,7 +24,7 @@ Keyboard settings
 
 The ``uniwill-laptop`` driver allows the user to enable/disable:
 
- - the FN and super key lock functionality of the integrated keyboard
+ - the FN lock and super key of the integrated keyboard
  - the touchpad toggle functionality of the integrated touchpad
 
 See Documentation/ABI/testing/sysfs-driver-uniwill-laptop for details.
diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index fee93537aa43..440724016885 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -314,8 +314,8 @@
 #define LED_CHANNELS		3
 #define LED_MAX_BRIGHTNESS	200
 
-#define UNIWILL_FEATURE_FN_LOCK_TOGGLE		BIT(0)
-#define UNIWILL_FEATURE_SUPER_KEY_TOGGLE	BIT(1)
+#define UNIWILL_FEATURE_FN_LOCK			BIT(0)
+#define UNIWILL_FEATURE_SUPER_KEY		BIT(1)
 #define UNIWILL_FEATURE_TOUCHPAD_TOGGLE		BIT(2)
 #define UNIWILL_FEATURE_LIGHTBAR		BIT(3)
 #define UNIWILL_FEATURE_BATTERY			BIT(4)
@@ -377,11 +377,15 @@ static const struct key_entry uniwill_keymap[] = {
 	{ KE_IGNORE,    UNIWILL_OSD_CAPSLOCK,                   { KEY_CAPSLOCK }},
 	{ KE_IGNORE,    UNIWILL_OSD_NUMLOCK,                    { KEY_NUMLOCK }},
 
-	/* Reported when the user locks/unlocks the super key */
-	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE,      { KEY_UNKNOWN }},
-	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE,     { KEY_UNKNOWN }},
+	/*
+	 * Reported when the user enables/disables the super key.
+	 * Those events might even be reported when the change was done
+	 * using the sysfs attribute!
+	 */
+	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_DISABLE,		{ KEY_UNKNOWN }},
+	{ KE_IGNORE,    UNIWILL_OSD_SUPER_KEY_ENABLE,		{ KEY_UNKNOWN }},
 	/* Optional, might not be reported by all devices */
-	{ KE_IGNORE,	UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED,	{ KEY_UNKNOWN }},
+	{ KE_IGNORE,	UNIWILL_OSD_SUPER_KEY_STATE_CHANGED,	{ KEY_UNKNOWN }},
 
 	/* Reported in manual mode when toggling the airplane mode status */
 	{ KE_KEY,       UNIWILL_OSD_RFKILL,                     { KEY_RFKILL }},
@@ -600,8 +604,8 @@ static const struct regmap_config uniwill_ec_config = {
 	.use_single_write = true,
 };
 
-static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_attribute *attr,
-					   const char *buf, size_t count)
+static ssize_t fn_lock_store(struct device *dev, struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -624,8 +628,7 @@ static ssize_t fn_lock_toggle_enable_store(struct device *dev, struct device_att
 	return count;
 }
 
-static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attribute *attr,
-					  char *buf)
+static ssize_t fn_lock_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -638,10 +641,10 @@ static ssize_t fn_lock_toggle_enable_show(struct device *dev, struct device_attr
 	return sysfs_emit(buf, "%d\n", !!(value & FN_LOCK_STATUS));
 }
 
-static DEVICE_ATTR_RW(fn_lock_toggle_enable);
+static DEVICE_ATTR_RW(fn_lock);
 
-static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_attribute *attr,
-					     const char *buf, size_t count)
+static ssize_t super_key_enable_store(struct device *dev, struct device_attribute *attr,
+				      const char *buf, size_t count)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -673,8 +676,7 @@ static ssize_t super_key_toggle_enable_store(struct device *dev, struct device_a
 	return count;
 }
 
-static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_attribute *attr,
-					    char *buf)
+static ssize_t super_key_enable_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	unsigned int value;
@@ -687,7 +689,7 @@ static ssize_t super_key_toggle_enable_show(struct device *dev, struct device_at
 	return sysfs_emit(buf, "%d\n", !(value & SUPER_KEY_LOCK_STATUS));
 }
 
-static DEVICE_ATTR_RW(super_key_toggle_enable);
+static DEVICE_ATTR_RW(super_key_enable);
 
 static ssize_t touchpad_toggle_enable_store(struct device *dev, struct device_attribute *attr,
 					    const char *buf, size_t count)
@@ -881,8 +883,8 @@ static int uniwill_nvidia_ctgp_init(struct uniwill_data *data)
 
 static struct attribute *uniwill_attrs[] = {
 	/* Keyboard-related */
-	&dev_attr_fn_lock_toggle_enable.attr,
-	&dev_attr_super_key_toggle_enable.attr,
+	&dev_attr_fn_lock.attr,
+	&dev_attr_super_key_enable.attr,
 	&dev_attr_touchpad_toggle_enable.attr,
 	/* Lightbar-related */
 	&dev_attr_rainbow_animation.attr,
@@ -897,13 +899,13 @@ static umode_t uniwill_attr_is_visible(struct kobject *kobj, struct attribute *a
 	struct device *dev = kobj_to_dev(kobj);
 	struct uniwill_data *data = dev_get_drvdata(dev);
 
-	if (attr == &dev_attr_fn_lock_toggle_enable.attr) {
-		if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK_TOGGLE))
+	if (attr == &dev_attr_fn_lock.attr) {
+		if (uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
 			return attr->mode;
 	}
 
-	if (attr == &dev_attr_super_key_toggle_enable.attr) {
-		if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (attr == &dev_attr_super_key_enable.attr) {
+		if (uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 			return attr->mode;
 	}
 
@@ -1505,7 +1507,7 @@ static void uniwill_shutdown(struct platform_device *pdev)
 
 static int uniwill_suspend_keyboard(struct uniwill_data *data)
 {
-	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
 
 	/*
@@ -1565,7 +1567,7 @@ static int uniwill_resume_keyboard(struct uniwill_data *data)
 	unsigned int value;
 	int ret;
 
-	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY_TOGGLE))
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
 
 	ret = regmap_read(data->regmap, EC_ADDR_SWITCH_STATUS, &value);
@@ -1643,16 +1645,16 @@ static struct platform_driver uniwill_driver = {
 };
 
 static struct uniwill_device_descriptor lapac71h_descriptor __initdata = {
-	.features = UNIWILL_FEATURE_FN_LOCK_TOGGLE |
-		    UNIWILL_FEATURE_SUPER_KEY_TOGGLE |
+	.features = UNIWILL_FEATURE_FN_LOCK |
+		    UNIWILL_FEATURE_SUPER_KEY |
 		    UNIWILL_FEATURE_TOUCHPAD_TOGGLE |
 		    UNIWILL_FEATURE_BATTERY |
 		    UNIWILL_FEATURE_HWMON,
 };
 
 static struct uniwill_device_descriptor lapkc71f_descriptor __initdata = {
-	.features = UNIWILL_FEATURE_FN_LOCK_TOGGLE |
-		    UNIWILL_FEATURE_SUPER_KEY_TOGGLE |
+	.features = UNIWILL_FEATURE_FN_LOCK |
+		    UNIWILL_FEATURE_SUPER_KEY |
 		    UNIWILL_FEATURE_TOUCHPAD_TOGGLE |
 		    UNIWILL_FEATURE_LIGHTBAR |
 		    UNIWILL_FEATURE_BATTERY |
diff --git a/drivers/platform/x86/uniwill/uniwill-wmi.h b/drivers/platform/x86/uniwill/uniwill-wmi.h
index 48783b2e9ffb..fb1910c0f741 100644
--- a/drivers/platform/x86/uniwill/uniwill-wmi.h
+++ b/drivers/platform/x86/uniwill/uniwill-wmi.h
@@ -64,8 +64,8 @@
 #define UNIWILL_OSD_KB_LED_LEVEL3		0x3E
 #define UNIWILL_OSD_KB_LED_LEVEL4		0x3F
 
-#define UNIWILL_OSD_SUPER_KEY_LOCK_ENABLE	0x40
-#define UNIWILL_OSD_SUPER_KEY_LOCK_DISABLE	0x41
+#define UNIWILL_OSD_SUPER_KEY_DISABLE		0x40
+#define UNIWILL_OSD_SUPER_KEY_ENABLE		0x41
 
 #define UNIWILL_OSD_MENU_JP			0x42
 
@@ -74,7 +74,7 @@
 
 #define UNIWILL_OSD_RFKILL			0xA4
 
-#define UNIWILL_OSD_SUPER_KEY_LOCK_CHANGED	0xA5
+#define UNIWILL_OSD_SUPER_KEY_STATE_CHANGED	0xA5
 
 #define UNIWILL_OSD_LIGHTBAR_STATE_CHANGED	0xA6
 
-- 
cgit v1.2.3


From 67e7eb4c130a74c5da9ab43316e00ed3186d1811 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:50:59 +0100
Subject: platform/x86: uniwill-laptop: Fix crash on unexpected battery event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On devices that have not UNIWILL_FEATURE_BATTERY set, the underlying
hardware might still send the UNIWILL_OSD_BATTERY_ALERT event. In such
a situation, the driver will access uninitialized data structures when
handling said event.

Prevent this by only handling the UNIWILL_OSD_BATTERY_ALERT event when
UNIWILL_FEATURE_BATTERY is set.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-3-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index 440724016885..e0f3740a6d3a 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -1359,6 +1359,9 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action
 
 	switch (action) {
 	case UNIWILL_OSD_BATTERY_ALERT:
+		if (!uniwill_device_supports(data, UNIWILL_FEATURE_BATTERY))
+			return NOTIFY_DONE;
+
 		mutex_lock(&data->battery_lock);
 		list_for_each_entry(entry, &data->batteries, head) {
 			power_supply_changed(entry->battery);
-- 
cgit v1.2.3


From 2be519d94544e226636c185e28ec1a72d01aab87 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:51:00 +0100
Subject: platform/x86: uniwill-laptop: Mark FN lock status as being volatile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that the FN lock status can be changed by the underlying
hardware when the user presses a special key combination. Mark the
associated register as volatile to prevent regmap from caching said
value. Also add the necessary suspend/resume handling.

Fixes: d050479693bb ("platform/x86: Add Uniwill laptop driver")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-4-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 39 ++++++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index e0f3740a6d3a..73b3d909e2b0 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -330,6 +330,7 @@ struct uniwill_data {
 	struct acpi_battery_hook hook;
 	unsigned int last_charge_ctrl;
 	struct mutex battery_lock;	/* Protects the list of currently registered batteries */
+	unsigned int last_status;
 	unsigned int last_switch_status;
 	struct mutex super_key_lock;	/* Protects the toggling of the super key lock state */
 	struct list_head batteries;
@@ -580,6 +581,7 @@ static bool uniwill_volatile_reg(struct device *dev, unsigned int reg)
 	case EC_ADDR_SECOND_FAN_RPM_1:
 	case EC_ADDR_SECOND_FAN_RPM_2:
 	case EC_ADDR_BAT_ALERT:
+	case EC_ADDR_BIOS_OEM:
 	case EC_ADDR_PWM_1:
 	case EC_ADDR_PWM_2:
 	case EC_ADDR_TRIGGER:
@@ -1508,7 +1510,19 @@ static void uniwill_shutdown(struct platform_device *pdev)
 	regmap_clear_bits(data->regmap, EC_ADDR_AP_OEM, ENABLE_MANUAL_CTRL);
 }
 
-static int uniwill_suspend_keyboard(struct uniwill_data *data)
+static int uniwill_suspend_fn_lock(struct uniwill_data *data)
+{
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+		return 0;
+
+	/*
+	 * The EC_ADDR_BIOS_OEM is marked as volatile, so we have to restore it
+	 * ourselves.
+	 */
+	return regmap_read(data->regmap, EC_ADDR_BIOS_OEM, &data->last_status);
+}
+
+static int uniwill_suspend_super_key(struct uniwill_data *data)
 {
 	if (!uniwill_device_supports(data, UNIWILL_FEATURE_SUPER_KEY))
 		return 0;
@@ -1547,7 +1561,11 @@ static int uniwill_suspend(struct device *dev)
 	struct uniwill_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	ret = uniwill_suspend_keyboard(data);
+	ret = uniwill_suspend_fn_lock(data);
+	if (ret < 0)
+		return ret;
+
+	ret = uniwill_suspend_super_key(data);
 	if (ret < 0)
 		return ret;
 
@@ -1565,7 +1583,16 @@ static int uniwill_suspend(struct device *dev)
 	return 0;
 }
 
-static int uniwill_resume_keyboard(struct uniwill_data *data)
+static int uniwill_resume_fn_lock(struct uniwill_data *data)
+{
+	if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+		return 0;
+
+	return regmap_update_bits(data->regmap, EC_ADDR_BIOS_OEM, FN_LOCK_STATUS,
+				  data->last_status);
+}
+
+static int uniwill_resume_super_key(struct uniwill_data *data)
 {
 	unsigned int value;
 	int ret;
@@ -1613,7 +1640,11 @@ static int uniwill_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	ret = uniwill_resume_keyboard(data);
+	ret = uniwill_resume_fn_lock(data);
+	if (ret < 0)
+		return ret;
+
+	ret = uniwill_resume_super_key(data);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 9836feedcf559449e82eb0f741084086780104e5 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Wed, 18 Feb 2026 01:51:01 +0100
Subject: platform/x86: uniwill-laptop: Handle FN lock event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On many devices, the user can toggle the Fn lock state by
pressing Fn + Esc. Forward the associated event to the fn_lock
sysfs attribute as a poll notification.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20260218005101.73680-5-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/uniwill/uniwill-acpi.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/uniwill/uniwill-acpi.c b/drivers/platform/x86/uniwill/uniwill-acpi.c
index 73b3d909e2b0..6341dca20b76 100644
--- a/drivers/platform/x86/uniwill/uniwill-acpi.c
+++ b/drivers/platform/x86/uniwill/uniwill-acpi.c
@@ -406,9 +406,6 @@ static const struct key_entry uniwill_keymap[] = {
 	/* Reported when the user wants to toggle the mute status */
 	{ KE_IGNORE,    UNIWILL_OSD_MUTE,                       { KEY_MUTE }},
 
-	/* Reported when the user locks/unlocks the Fn key */
-	{ KE_IGNORE,    UNIWILL_OSD_FN_LOCK,                    { KEY_FN_ESC }},
-
 	/* Reported when the user wants to toggle the brightness of the keyboard */
 	{ KE_KEY,       UNIWILL_OSD_KBDILLUMTOGGLE,             { KEY_KBDILLUMTOGGLE }},
 	{ KE_KEY,       UNIWILL_OSD_KB_LED_LEVEL0,              { KEY_KBDILLUMTOGGLE }},
@@ -1376,6 +1373,13 @@ static int uniwill_notifier_call(struct notifier_block *nb, unsigned long action
 		 * gets implemented.
 		 */
 
+		return NOTIFY_OK;
+	case UNIWILL_OSD_FN_LOCK:
+		if (!uniwill_device_supports(data, UNIWILL_FEATURE_FN_LOCK))
+			return NOTIFY_DONE;
+
+		sysfs_notify(&data->dev->kobj, NULL, "fn_lock");
+
 		return NOTIFY_OK;
 	default:
 		mutex_lock(&data->input_lock);
-- 
cgit v1.2.3


From b7df21c59739cceb7b866c6c5e8a6ba03875ab71 Mon Sep 17 00:00:00 2001
From: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Date: Fri, 20 Feb 2026 14:32:20 +0530
Subject: arm64: dts: qcom: qcm6490-idp: Fix WCD9370 reset GPIO polarity

The WCD9370 audio codec reset line on QCM6490 IDP should be active-low, but
the device tree described it as active-high. As a result, the codec is
kept in reset and fails to reset the SoundWire, leading to timeouts
and ASoC card probe failure (-ETIMEDOUT).

Fix the reset GPIO polarity to GPIO_ACTIVE_LOW so the codec can properly
initialize.

Fixes: aa04c298619f ("arm64: dts: qcom: qcm6490-idp: Add WSA8830 speakers and WCD9370 headset codec")
Signed-off-by: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260220090220.2992193-1-ravi.hothi@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/qcm6490-idp.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
index 089a027c57d5..b2f00e107643 100644
--- a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
+++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
@@ -177,7 +177,7 @@
 		pinctrl-0 = <&wcd_default>;
 		pinctrl-names = "default";
 
-		reset-gpios = <&tlmm 83 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&tlmm 83 GPIO_ACTIVE_LOW>;
 
 		vdd-buck-supply = <&vreg_l17b_1p7>;
 		vdd-rxtx-supply = <&vreg_l18b_1p8>;
-- 
cgit v1.2.3


From ec197dca8735f7627e5cff7e3fa8839b53a28514 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Sun, 22 Feb 2026 08:33:52 +0000
Subject: KVM: arm64: Revert accidental drop of kvm_uninit_stage2_mmu() for
 non-NV VMs

Commit 0c4762e26879 ("KVM: arm64: nv: Avoid NV stage-2 code when NV is
not supported") added an early return to several functions in
arch/arm64/kvm/nested.c to prevent a UBSAN shift-out-of-bounds error
when accessing the pgt union for non-nested VMs.

However, this early return was inadvertently applied to
kvm_arch_flush_shadow_all() as well, causing it to skip the call to
kvm_uninit_stage2_mmu(kvm) for all non-nested VMs.

For pKVM, skipping this teardown means the host never unshares the
guest's memory with the EL2 hypervisor. When the host kernel later
recycles these leaked pages for a new VM, it attempts to re-share them.
The hypervisor correctly rejects this with -EPERM, triggering a host
WARN_ON and hanging the guest.

Fix this by dropping the early return from kvm_arch_flush_shadow_all().
The for-loop guarding the nested MMU cleanup already bounds itself when
nested_mmus_size == 0, allowing execution to proceed to
kvm_uninit_stage2_mmu() as intended.

Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/60916cb6-f460-4751-b910-f63c58700ad0@sirena.org.uk/
Fixes: 0c4762e26879 ("KVM: arm64: nv: Avoid NV stage-2 code when NV is not supported")
Signed-off-by: Fuad Tabba <tabba@google.com>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260222083352.89503-1-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index eeea5e692370..7f1ea85dc67a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1154,9 +1154,6 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	int i;
 
-	if (!kvm->arch.nested_mmus_size)
-		return;
-
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
-- 
cgit v1.2.3


From 822655e6751dde2df7ddaa828c5aba217726c5a2 Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Mon, 23 Feb 2026 09:29:00 -0700
Subject: cxl/port: Introduce port_to_host() helper

In CXL subsystem, a port has its own host device for the port creation
and removal. The host of CXL root and all the first level ports is the
platform firmware device, the host of other ports is their parent port's
device. Create this new helper to much easier to get the host of a cxl
port.

Introduce port_to_host() and use it to replace all places where using
open coded to get the host of a port.

Remove endpoint_host() as its functionality can be replaced by
port_to_host().

[dj: Squashed commit 1 and 3 in the series to commit 1. ]

Signed-off-by: Li Ming <ming.li@zohomail.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260210-fix-port-enumeration-failure-v3-1-06acce0b9ead@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/core.h | 18 ++++++++++++++++++
 drivers/cxl/core/port.c | 29 +++--------------------------
 2 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 007b8aff0238..5b0570df0fd9 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -152,6 +152,24 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c);
 int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
 					struct access_coordinate *c);
 
+static inline struct device *port_to_host(struct cxl_port *port)
+{
+	struct cxl_port *parent = is_cxl_root(port) ? NULL :
+				  to_cxl_port(port->dev.parent);
+
+	/*
+	 * The host of CXL root port and the first level of ports is
+	 * the platform firmware device, the host of all other ports
+	 * is their parent port.
+	 */
+	if (!parent)
+		return port->uport_dev;
+	else if (is_cxl_root(parent))
+		return parent->uport_dev;
+	else
+		return &parent->dev;
+}
+
 static inline struct device *dport_to_host(struct cxl_dport *dport)
 {
 	struct cxl_port *port = dport->port;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index b69c2529744c..6be150e645b6 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -615,22 +615,8 @@ struct cxl_port *parent_port_of(struct cxl_port *port)
 static void unregister_port(void *_port)
 {
 	struct cxl_port *port = _port;
-	struct cxl_port *parent = parent_port_of(port);
-	struct device *lock_dev;
 
-	/*
-	 * CXL root port's and the first level of ports are unregistered
-	 * under the platform firmware device lock, all other ports are
-	 * unregistered while holding their parent port lock.
-	 */
-	if (!parent)
-		lock_dev = port->uport_dev;
-	else if (is_cxl_root(parent))
-		lock_dev = parent->uport_dev;
-	else
-		lock_dev = &parent->dev;
-
-	device_lock_assert(lock_dev);
+	device_lock_assert(port_to_host(port));
 	port->dead = true;
 	device_unregister(&port->dev);
 }
@@ -1427,20 +1413,11 @@ static struct device *grandparent(struct device *dev)
 	return NULL;
 }
 
-static struct device *endpoint_host(struct cxl_port *endpoint)
-{
-	struct cxl_port *port = to_cxl_port(endpoint->dev.parent);
-
-	if (is_cxl_root(port))
-		return port->uport_dev;
-	return &port->dev;
-}
-
 static void delete_endpoint(void *data)
 {
 	struct cxl_memdev *cxlmd = data;
 	struct cxl_port *endpoint = cxlmd->endpoint;
-	struct device *host = endpoint_host(endpoint);
+	struct device *host = port_to_host(endpoint);
 
 	scoped_guard(device, host) {
 		if (host->driver && !endpoint->dead) {
@@ -1456,7 +1433,7 @@ static void delete_endpoint(void *data)
 
 int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
 {
-	struct device *host = endpoint_host(endpoint);
+	struct device *host = port_to_host(endpoint);
 	struct device *dev = &cxlmd->dev;
 
 	get_device(host);
-- 
cgit v1.2.3


From 0066688dbcdcf51680f499936faffe6d0e94194e Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Tue, 10 Feb 2026 19:46:57 +0800
Subject: cxl/port: Hold port host lock during dport adding.

CXL testing environment can trigger following trace
 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000092: 0000 [#1] SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000490-0x0000000000000497]
 RIP: 0010:cxl_dpa_to_region+0x105/0x1f0 [cxl_core]
 Call Trace:
  <TASK>
  cxl_event_trace_record+0xd1/0xa70 [cxl_core]
  __cxl_event_trace_record+0x12f/0x1e0 [cxl_core]
  cxl_mem_get_records_log+0x261/0x500 [cxl_core]
  cxl_mem_get_event_records+0x7c/0xc0 [cxl_core]
  cxl_mock_mem_probe+0xd38/0x1c60 [cxl_mock_mem]
  platform_probe+0x9d/0x130
  really_probe+0x1c8/0x960
  __driver_probe_device+0x187/0x3e0
  driver_probe_device+0x45/0x120
  __device_attach_driver+0x15d/0x280

When CXL subsystem adds a cxl port to a hierarchy, there is a small
window where the new port becomes visible before it is bound to a
driver. This happens because device_add() adds a device to bus device
list before bus_probe_device() binds it to a driver.
So if two cxl memdevs are trying to add a dport to a same port via
devm_cxl_enumerate_ports(), the second cxl memdev may observe the port
and attempt to add a dport, but fails because the port has not yet been
attached to cxl port driver. That causes the memdev->endpoint can not be
updated.

The sequence is like:

CPU 0					CPU 1
devm_cxl_enumerate_ports()
  # port not found, add it
  add_port_attach_ep()
    # hold the parent port lock
    # to add the new port
    devm_cxl_create_port()
      device_add()
	# Add dev to bus devs list
	bus_add_device()
					devm_cxl_enumerate_ports()
					  # found the port
					  find_cxl_port_by_uport()
					  # hold port lock to add a dport
					  device_lock(the port)
					  find_or_add_dport()
					    cxl_port_add_dport()
					      return -ENXIO because port->dev.driver is NULL
					  device_unlock(the port)
	bus_probe_device()
	  # hold the port lock
	  # for attaching
	  device_lock(the port)
	    attaching the new port
	  device_unlock(the port)

To fix this race, require that dport addition holds the host lock
of the target port(the host of CXL root and all cxl host bridge ports is
the platform firmware device, the host of all other ports is their
parent port). The CXL subsystem already requires holding the host lock
while attaching a new port. Therefore, successfully acquiring the host
lock guarantees that port attaching has completed.

Fixes: 4f06d81e7c6a ("cxl: Defer dport allocation for switch ports")
Signed-off-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Link: https://patch.msgid.link/20260210-fix-port-enumeration-failure-v3-2-06acce0b9ead@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/port.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 6be150e645b6..0c5957d1d329 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -1767,7 +1767,16 @@ static struct cxl_dport *find_or_add_dport(struct cxl_port *port,
 {
 	struct cxl_dport *dport;
 
-	device_lock_assert(&port->dev);
+	/*
+	 * The port is already visible in CXL hierarchy, but it may still
+	 * be in the process of binding to the CXL port driver at this point.
+	 *
+	 * port creation and driver binding are protected by the port's host
+	 * lock, so acquire the host lock here to ensure the port has completed
+	 * driver binding before proceeding with dport addition.
+	 */
+	guard(device)(port_to_host(port));
+	guard(device)(&port->dev);
 	dport = cxl_find_dport_by_dev(port, dport_dev);
 	if (!dport) {
 		dport = probe_dport(port, dport_dev);
@@ -1834,13 +1843,11 @@ retry:
 			 * RP port enumerated by cxl_acpi without dport will
 			 * have the dport added here.
 			 */
-			scoped_guard(device, &port->dev) {
-				dport = find_or_add_dport(port, dport_dev);
-				if (IS_ERR(dport)) {
-					if (PTR_ERR(dport) == -EAGAIN)
-						goto retry;
-					return PTR_ERR(dport);
-				}
+			dport = find_or_add_dport(port, dport_dev);
+			if (IS_ERR(dport)) {
+				if (PTR_ERR(dport) == -EAGAIN)
+					goto retry;
+				return PTR_ERR(dport);
 			}
 
 			rc = cxl_add_ep(dport, &cxlmd->dev);
-- 
cgit v1.2.3


From 410666a298c34ebd57256fde6b24c96bd23059a2 Mon Sep 17 00:00:00 2001
From: Roberto Bergantinos Corpas <rbergant@redhat.com>
Date: Thu, 19 Feb 2026 13:04:40 +0100
Subject: nfs: return EISDIR on nfs3_proc_create if d_alias is a dir

If we found an alias through nfs3_do_create/nfs_add_or_obtain
/d_splice_alias which happens to be a dir dentry, we don't return
any error, and simply forget about this alias, but the original
dentry we were adding and passed as parameter remains negative.

This later causes an oops on nfs_atomic_open_v23/finish_open since we
supply a negative dentry to do_dentry_open.

This has been observed running lustre-racer, where dirs and files are
created/removed concurrently with the same name and O_EXCL is not
used to open files (frequent file redirection).

While d_splice_alias typically returns a directory alias or NULL, we
explicitly check d_is_dir() to ensure that we don't attempt to perform
file operations (like finish_open) on a directory inode, which triggers
the observed oops.

Fixes: 7c6c5249f061 ("NFS: add atomic_open for NFSv3 to handle O_TRUNC correctly.")
Reviewed-by: Olga Kornievskaia <okorniev@redhat.com>
Reviewed-by: Scott Mayhew <smayhew@redhat.com>
Signed-off-by: Roberto Bergantinos Corpas <rbergant@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/nfs3proc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 3e2de45c95fe..be2aebf62056 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -392,8 +392,13 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	if (status != 0)
 		goto out_release_acls;
 
-	if (d_alias)
+	if (d_alias) {
+		if (d_is_dir(d_alias)) {
+			status = -EISDIR;
+			goto out_dput;
+		}
 		dentry = d_alias;
+	}
 
 	/* When we created the file with exclusive semantics, make
 	 * sure we set the attributes afterwards. */
-- 
cgit v1.2.3


From 9d851afa482680bdd7c158cc8720284dc9ecb5fe Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sat, 21 Feb 2026 23:40:42 +0800
Subject: selftests/sched_ext: Abort test loop on signal

The runner sets exit_req on SIGINT/SIGTERM but ignores it during the
main loop. This prevents users from cleanly interrupting a test run.

Check exit_req each iteration to safely break out on exit signals.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/runner.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c
index 5748d2c69903..761c21f96404 100644
--- a/tools/testing/selftests/sched_ext/runner.c
+++ b/tools/testing/selftests/sched_ext/runner.c
@@ -166,6 +166,9 @@ int main(int argc, char **argv)
 		enum scx_test_status status;
 		struct scx_test *test = &__scx_tests[i];
 
+		if (exit_req)
+			break;
+
 		if (list) {
 			printf("%s\n", test->name);
 			if (i == (__scx_num_tests - 1))
-- 
cgit v1.2.3


From 551d44200152cb26f75d2ef990aeb6185b7e37fd Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 23 Feb 2026 09:33:08 -0800
Subject: default_gfp(): avoid using the "newfangled" __VA_OPT__ trick

The default_gfp() helper that I added is not wrong, but it turns out
that it causes unnecessary headaches for 'sparse' which doesn't support
the use of __VA_OPT__ (introduced in C++20 and C23, and supported by gcc
and clang for a long time).

We do already use __VA_OPT__ in some other cases in the kernel (drm/xe
and btrfs), but it has been fairly limited.  Now it triggers for pretty
much everything, and sparse ends up not working at all.

We can use the traditional gcc ',##__VA_ARGS__' syntax instead: it may
not be the "C standard" way and is slightly less natural in this
context, but it is the traditional model for this and avoids the sparse
problem.

Reported-and-tested-by: Ricardo Ribalda <ribalda@chromium.org>
Reported-and-tested-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reported-by: Ben Dooks <ben.dooks@codethink.co.uk>
Fixes: e19e1b480ac7 ("add default_gfp() helper macro and use it in the new *alloc_obj() helpers")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2b30a0529d48..90536b2bc42e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -14,8 +14,8 @@ struct vm_area_struct;
 struct mempolicy;
 
 /* Helper macro to avoid gfp flags if they are the default one */
-#define __default_gfp(a,...) a
-#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL)
+#define __default_gfp(a,b,...) b
+#define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
-- 
cgit v1.2.3


From a7b4bc094fbaa7dc7b7b91ae33549bbd7eefaac1 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Wed, 7 Jan 2026 13:22:57 +0100
Subject: module: Remove duplicate freeing of lockdep classes

In the error path of load_module(), under the free_module label, the
code calls lockdep_free_key_range() to release lock classes associated
with the MOD_DATA, MOD_RODATA and MOD_RO_AFTER_INIT module regions, and
subsequently invokes module_deallocate().

Since commit ac3b43283923 ("module: replace module_layout with
module_memory"), the module_deallocate() function calls free_mod_mem(),
which releases the lock classes as well and considers all module
regions.

Attempting to free these classes twice is unnecessary. Remove the
redundant code in load_module().

Fixes: ac3b43283923 ("module: replace module_layout with module_memory")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Aaron Tomlin <atomlin@atomlin.com>
Acked-by: Song Liu <song@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/main.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 2bac4c7cd019..eec6c9cf8dbb 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3544,12 +3544,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_unlock(&module_mutex);
  free_module:
 	mod_stat_bump_invalid(info, flags);
-	/* Free lock-classes; relies on the preceding sync_rcu() */
-	for_class_mod_mem_type(type, core_data) {
-		lockdep_free_key_range(mod->mem[type].base,
-				       mod->mem[type].size);
-	}
-
 	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:
-- 
cgit v1.2.3


From 8d597ba6ec18dae2eec143d4e1c9d81441ca0dda Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Thu, 5 Feb 2026 15:37:08 +0100
Subject: module: Fix the modversions and signing submenus

The module Kconfig file contains a set of options related to "Module
versioning support" (depends on MODVERSIONS) and "Module signature
verification" (depends on MODULE_SIG). The Kconfig tool automatically
creates submenus when an entry for a symbol is followed by consecutive
items that all depend on the symbol. However, this functionality doesn't
work for the mentioned module options. The MODVERSIONS options are
interleaved with ASM_MODVERSIONS, which has no 'depends on MODVERSIONS' but
instead uses 'default HAVE_ASM_MODVERSIONS && MODVERSIONS'. Similarly, the
MODULE_SIG options are interleaved by a comment warning not to forget
signing modules with scripts/sign-file, which uses the condition 'depends
on MODULE_SIG_FORCE && !MODULE_SIG_ALL'.

The result is that the options are confusingly shown when using
a menuconfig tool, as follows:

 [*]   Module versioning support
         Module versioning implementation (genksyms (from source code))  --->
 [ ]   Extended Module Versioning Support
 [*]   Basic Module Versioning Support
 [*]   Source checksum for all modules
 [*]   Module signature verification
 [ ]     Require modules to be validly signed
 [ ]     Automatically sign all modules
       Hash algorithm to sign modules (SHA-256)  --->

Fix the issue by using if/endif to group related options together in
kernel/module/Kconfig, similarly to how the MODULE_DEBUG options are
already grouped. Note that the signing-related options depend on
'MODULE_SIG || IMA_APPRAISE_MODSIG', with the exception of
MODULE_SIG_FORCE, which is valid only for MODULE_SIG and is therefore kept
separately. For consistency, do the same for the MODULE_COMPRESS entries.
The options are then properly placed into submenus, as follows:

 [*]   Module versioning support
         Module versioning implementation (genksyms (from source code))  --->
 [ ]     Extended Module Versioning Support
 [*]     Basic Module Versioning Support
 [*]   Source checksum for all modules
 [*]   Module signature verification
 [ ]     Require modules to be validly signed
 [ ]     Automatically sign all modules
         Hash algorithm to sign modules (SHA-256)  --->

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/Kconfig | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index be74917802ad..43b1bb01fd27 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -169,9 +169,10 @@ config MODVERSIONS
 	  make them incompatible with the kernel you are running.  If
 	  unsure, say N.
 
+if MODVERSIONS
+
 choice
 	prompt "Module versioning implementation"
-	depends on MODVERSIONS
 	help
 	  Select the tool used to calculate symbol versions for modules.
 
@@ -206,7 +207,7 @@ endchoice
 
 config ASM_MODVERSIONS
 	bool
-	default HAVE_ASM_MODVERSIONS && MODVERSIONS
+	default HAVE_ASM_MODVERSIONS
 	help
 	  This enables module versioning for exported symbols also from
 	  assembly. This can be enabled only when the target architecture
@@ -214,7 +215,6 @@ config ASM_MODVERSIONS
 
 config EXTENDED_MODVERSIONS
 	bool "Extended Module Versioning Support"
-	depends on MODVERSIONS
 	help
 	  This enables extended MODVERSIONs support, allowing long symbol
 	  names to be versioned.
@@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS
 
 config BASIC_MODVERSIONS
 	bool "Basic Module Versioning Support"
-	depends on MODVERSIONS
 	default y
 	help
 	  This enables basic MODVERSIONS support, allowing older tools or
@@ -237,6 +236,8 @@ config BASIC_MODVERSIONS
 	  This is enabled by default when MODVERSIONS are enabled.
 	  If unsure, say Y.
 
+endif # MODVERSIONS
+
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
@@ -277,10 +278,11 @@ config MODULE_SIG_FORCE
 	  Reject unsigned modules or signed modules for which we don't have a
 	  key.  Without this, such modules will simply taint the kernel.
 
+if MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_SIG_ALL
 	bool "Automatically sign all modules"
 	default y
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	help
 	  Sign all modules during make modules_install. Without this option,
 	  modules must be signed manually, using the scripts/sign-file tool.
@@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file"
 
 choice
 	prompt "Hash algorithm to sign modules"
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default MODULE_SIG_SHA512
 	help
 	  This determines which sort of hashing algorithm will be used during
@@ -327,7 +328,6 @@ endchoice
 
 config MODULE_SIG_HASH
 	string
-	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
 	default "sha256" if MODULE_SIG_SHA256
 	default "sha384" if MODULE_SIG_SHA384
 	default "sha512" if MODULE_SIG_SHA512
@@ -335,6 +335,8 @@ config MODULE_SIG_HASH
 	default "sha3-384" if MODULE_SIG_SHA3_384
 	default "sha3-512" if MODULE_SIG_SHA3_512
 
+endif # MODULE_SIG || IMA_APPRAISE_MODSIG
+
 config MODULE_COMPRESS
 	bool "Module compression"
 	help
@@ -350,9 +352,10 @@ config MODULE_COMPRESS
 
 	  If unsure, say N.
 
+if MODULE_COMPRESS
+
 choice
 	prompt "Module compression type"
-	depends on MODULE_COMPRESS
 	help
 	  Choose the supported algorithm for module compression.
 
@@ -379,7 +382,6 @@ endchoice
 config MODULE_COMPRESS_ALL
 	bool "Automatically compress all modules"
 	default y
-	depends on MODULE_COMPRESS
 	help
 	  Compress all modules during 'make modules_install'.
 
@@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL
 
 config MODULE_DECOMPRESS
 	bool "Support in-kernel module decompression"
-	depends on MODULE_COMPRESS
 	select ZLIB_INFLATE if MODULE_COMPRESS_GZIP
 	select XZ_DEC if MODULE_COMPRESS_XZ
 	select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD
@@ -400,6 +401,8 @@ config MODULE_DECOMPRESS
 
 	  If unsure, say N.
 
+endif # MODULE_COMPRESS
+
 config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS
 	bool "Allow loading of modules with missing namespace imports"
 	help
-- 
cgit v1.2.3


From 1f0638604f65dae9fc8b6ce937907daf5f0132d0 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 16:25:22 +0800
Subject: selftests/sched_ext: Fix unused-result warning for read()

The read() call in run_test() triggers a warn_unused_result compiler
warning, which breaks the build under -Werror.

Check the return value of read() and exit the child process on failure to
satisfy the compiler and handle pipe read errors.

Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/init_enable_count.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c
index 82c71653977b..44577e30e764 100644
--- a/tools/testing/selftests/sched_ext/init_enable_count.c
+++ b/tools/testing/selftests/sched_ext/init_enable_count.c
@@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global)
 			char buf;
 
 			close(pipe_fds[1]);
-			read(pipe_fds[0], &buf, 1);
+			if (read(pipe_fds[0], &buf, 1) < 0)
+				exit(1);
 			close(pipe_fds[0]);
 			exit(0);
 		}
-- 
cgit v1.2.3


From 0c36a6f6f0eb071379b7995ef571c18c1235adf2 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 21:08:25 +0800
Subject: tools/sched_ext: scx_central: Remove unused '-p' option

The '-p' option is defined in getopt() but not handled in the switch
statement or documented in the help text. Providing '-p' currently
triggers the default error path.

Remove it to sync the optstring with the actual implementation.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/scx_central.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
index 2a805f1d6c8f..710fa03376e2 100644
--- a/tools/sched_ext/scx_central.c
+++ b/tools/sched_ext/scx_central.c
@@ -66,7 +66,7 @@ restart:
 	assert(skel->rodata->nr_cpu_ids > 0);
 	assert(skel->rodata->nr_cpu_ids <= INT32_MAX);
 
-	while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) {
+	while ((opt = getopt(argc, argv, "s:c:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
-- 
cgit v1.2.3


From cbb297323dbed4f6087b5f189585413801d1d45b Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sun, 22 Feb 2026 21:08:26 +0800
Subject: tools/sched_ext: scx_sdt: Remove unused '-f' option

The '-f' option is defined in getopt() but not handled in the switch
statement or documented in the help text. Providing '-f' currently
triggers the default error path.

Remove it to sync the optstring with the actual implementation.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/scx_sdt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sched_ext/scx_sdt.c b/tools/sched_ext/scx_sdt.c
index d8ca9aa316a5..a36405d8df30 100644
--- a/tools/sched_ext/scx_sdt.c
+++ b/tools/sched_ext/scx_sdt.c
@@ -54,7 +54,7 @@ restart:
 	optind = 1;
 	skel = SCX_OPS_OPEN(sdt_ops, scx_sdt);
 
-	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+	while ((opt = getopt(argc, argv, "vh")) != -1) {
 		switch (opt) {
 		case 'v':
 			verbose = true;
-- 
cgit v1.2.3


From 075e70d13edfcb309c8fdc1f444fbd1f834ca1d4 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Mon, 23 Feb 2026 02:47:09 +0800
Subject: selftests/sched_ext: Remove duplicated unistd.h include in rt_stall.c

The header <unistd.h> is included twice in rt_stall.c. Remove the
redundant inclusion to clean up the code.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/rt_stall.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
index ab772e336f86..81ea9b4883e5 100644
--- a/tools/testing/selftests/sched_ext/rt_stall.c
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -15,7 +15,6 @@
 #include <signal.h>
 #include <bpf/bpf.h>
 #include <scx/common.h>
-#include <unistd.h>
 #include "rt_stall.bpf.skel.h"
 #include "scx_test.h"
 #include "../kselftest.h"
-- 
cgit v1.2.3


From e7e222ad73d93fe54d6e6e3a15253a0ecf081a1b Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 11 Feb 2026 17:31:23 -0700
Subject: cxl: Move devm_cxl_add_nvdimm_bridge() to cxl_pmem.ko

Moving the symbol devm_cxl_add_nvdimm_bridge() to
drivers/cxl/cxl_pmem.c, so that cxl_pmem can export a symbol that gives
cxl_acpi a depedency on cxl_pmem kernel module. This is a prepatory patch
to resolve the issue of a race for nvdimm_bus object that is created
during cxl_acpi_probe().

No functional changes besides moving code.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Ira Weiny <ira.weiny@intel.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com?>
Link: https://patch.msgid.link/20260205001633.1813643-2-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/pmem.c | 13 +++----------
 drivers/cxl/cxl.h       |  2 ++
 drivers/cxl/pmem.c      | 14 ++++++++++++++
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index 3c6e76721522..b652e3486038 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -115,15 +115,8 @@ static void unregister_nvb(void *_cxl_nvb)
 	device_unregister(&cxl_nvb->dev);
 }
 
-/**
- * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
- * @host: platform firmware root device
- * @port: CXL port at the root of a CXL topology
- *
- * Return: bridge device that can host cxl_nvdimm objects
- */
-struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
-						     struct cxl_port *port)
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port)
 {
 	struct cxl_nvdimm_bridge *cxl_nvb;
 	struct device *dev;
@@ -155,7 +148,7 @@ err:
 	put_device(dev);
 	return ERR_PTR(rc);
 }
-EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL");
+EXPORT_SYMBOL_FOR_MODULES(__devm_cxl_add_nvdimm_bridge, "cxl_pmem");
 
 static void cxl_nvdimm_release(struct device *dev)
 {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 04c673e7cdb0..f5850800f400 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -920,6 +920,8 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv);
 struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev);
 struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
 						     struct cxl_port *port);
+struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
+						       struct cxl_port *port);
 struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev);
 bool is_cxl_nvdimm(struct device *dev);
 int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index 6a97e4e490b6..c67b30b516bf 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -13,6 +13,20 @@
 
 static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
 
+/**
+ * __devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
+ * @host: platform firmware root device
+ * @port: CXL port at the root of a CXL topology
+ *
+ * Return: bridge device that can host cxl_nvdimm objects
+ */
+struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
+						     struct cxl_port *port)
+{
+	return __devm_cxl_add_nvdimm_bridge(host, port);
+}
+EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL");
+
 static void clear_exclusive(void *mds)
 {
 	clear_exclusive_cxl_commands(mds, exclusive_cmds);
-- 
cgit v1.2.3


From 43d37df67f7770d8d261fdcb64ecc8c314e91303 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 6 Feb 2026 14:30:59 -0800
Subject: drm/xe/wa: Steer RMW of MCR registers while building default LRC

When generating the default LRC, if a register is not masked, we apply
any save-restore programming necessary via a read-modify-write sequence
that will ensure we only update the relevant bits/fields without
clobbering the rest of the register.  However some of the registers that
need to be updated might be MCR registers which require steering to a
non-terminated instance to ensure we can read back a valid, non-zero
value. The steering of reads originating from a command streamer is
controlled by register CS_MMIO_GROUP_INSTANCE_SELECT.  Emit additional
MI_LRI commands to update the steering before any RMW of an MCR register
to ensure the reads are performed properly.

Note that needing to perform a RMW of an MCR register while building the
default LRC is pretty rare.  Most of the MCR registers that are part of
an engine's LRCs are also masked registers, so no MCR is necessary.

Fixes: f2f90989ccff ("drm/xe: Avoid reading RMW registers in emit_wa_job")
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://patch.msgid.link/20260206223058.387014-2-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 6c2e331c915ba9e774aa847921262805feb00863)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h |  6 +++
 drivers/gpu/drm/xe/xe_gt.c               | 66 ++++++++++++++++++++++++++------
 2 files changed, 60 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 68172b0248a6..dc5a4fafa70c 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -96,6 +96,12 @@
 #define   ENABLE_SEMAPHORE_POLL_BIT		REG_BIT(13)
 
 #define RING_CMD_CCTL(base)			XE_REG((base) + 0xc4, XE_REG_OPTION_MASKED)
+
+#define CS_MMIO_GROUP_INSTANCE_SELECT(base)	XE_REG((base) + 0xcc)
+#define   SELECTIVE_READ_ADDRESSING		REG_BIT(30)
+#define   SELECTIVE_READ_GROUP			REG_GENMASK(29, 23)
+#define   SELECTIVE_READ_INSTANCE		REG_GENMASK(22, 16)
+
 /*
  * CMD_CCTL read/write fields take a MOCS value and _not_ a table index.
  * The lsb of each can be considered a separate enabling bit for encryption.
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 9d090d0f2438..df6d04704823 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -210,11 +210,15 @@ static int emit_nop_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	return ret;
 }
 
+/* Dwords required to emit a RMW of a register */
+#define EMIT_RMW_DW 20
+
 static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 {
-	struct xe_reg_sr *sr = &q->hwe->reg_lrc;
+	struct xe_hw_engine *hwe = q->hwe;
+	struct xe_reg_sr *sr = &hwe->reg_lrc;
 	struct xe_reg_sr_entry *entry;
-	int count_rmw = 0, count = 0, ret;
+	int count_rmw = 0, count_rmw_mcr = 0, count = 0, ret;
 	unsigned long idx;
 	struct xe_bb *bb;
 	size_t bb_len = 0;
@@ -224,6 +228,8 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	xa_for_each(&sr->xa, idx, entry) {
 		if (entry->reg.masked || entry->clr_bits == ~0)
 			++count;
+		else if (entry->reg.mcr)
+			++count_rmw_mcr;
 		else
 			++count_rmw;
 	}
@@ -231,17 +237,35 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	if (count)
 		bb_len += count * 2 + 1;
 
-	if (count_rmw)
-		bb_len += count_rmw * 20 + 7;
+	/*
+	 * RMW of MCR registers is the same as a normal RMW, except an
+	 * additional LRI (3 dwords) is required per register to steer the read
+	 * to a nom-terminated instance.
+	 *
+	 * We could probably shorten the batch slightly by eliding the
+	 * steering for consecutive MCR registers that have the same
+	 * group/instance target, but it's not worth the extra complexity to do
+	 * so.
+	 */
+	bb_len += count_rmw * EMIT_RMW_DW;
+	bb_len += count_rmw_mcr * (EMIT_RMW_DW + 3);
+
+	/*
+	 * After doing all RMW, we need 7 trailing dwords to clean up,
+	 * plus an additional 3 dwords to reset steering if any of the
+	 * registers were MCR.
+	 */
+	if (count_rmw || count_rmw_mcr)
+		bb_len += 7 + (count_rmw_mcr ? 3 : 0);
 
-	if (q->hwe->class == XE_ENGINE_CLASS_RENDER)
+	if (hwe->class == XE_ENGINE_CLASS_RENDER)
 		/*
 		 * Big enough to emit all of the context's 3DSTATE via
 		 * xe_lrc_emit_hwe_state_instructions()
 		 */
-		bb_len += xe_gt_lrc_size(gt, q->hwe->class) / sizeof(u32);
+		bb_len += xe_gt_lrc_size(gt, hwe->class) / sizeof(u32);
 
-	xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", q->hwe->name, bb_len);
+	xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", hwe->name, bb_len);
 
 	bb = xe_bb_new(gt, bb_len, false);
 	if (IS_ERR(bb))
@@ -276,13 +300,23 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 		}
 	}
 
-	if (count_rmw) {
-		/* Emit MI_MATH for each RMW reg: 20dw per reg + 7 trailing dw */
-
+	if (count_rmw || count_rmw_mcr) {
 		xa_for_each(&sr->xa, idx, entry) {
 			if (entry->reg.masked || entry->clr_bits == ~0)
 				continue;
 
+			if (entry->reg.mcr) {
+				struct xe_reg_mcr reg = { .__reg.raw = entry->reg.raw };
+				u8 group, instance;
+
+				xe_gt_mcr_get_nonterminated_steering(gt, reg, &group, &instance);
+				*cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
+				*cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(hwe->mmio_base).addr;
+				*cs++ = SELECTIVE_READ_ADDRESSING |
+					REG_FIELD_PREP(SELECTIVE_READ_GROUP, group) |
+					REG_FIELD_PREP(SELECTIVE_READ_INSTANCE, instance);
+			}
+
 			*cs++ = MI_LOAD_REGISTER_REG | MI_LRR_DST_CS_MMIO;
 			*cs++ = entry->reg.addr;
 			*cs++ = CS_GPR_REG(0, 0).addr;
@@ -308,8 +342,9 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 			*cs++ = CS_GPR_REG(0, 0).addr;
 			*cs++ = entry->reg.addr;
 
-			xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x\n",
-				  entry->reg.addr, entry->clr_bits, entry->set_bits);
+			xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x%s\n",
+				  entry->reg.addr, entry->clr_bits, entry->set_bits,
+				  entry->reg.mcr ? " (MCR)" : "");
 		}
 
 		/* reset used GPR */
@@ -321,6 +356,13 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 		*cs++ = 0;
 		*cs++ = CS_GPR_REG(0, 2).addr;
 		*cs++ = 0;
+
+		/* reset steering */
+		if (count_rmw_mcr) {
+			*cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
+			*cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(q->hwe->mmio_base).addr;
+			*cs++ = 0;
+		}
 	}
 
 	cs = xe_lrc_emit_hwe_state_instructions(q, cs);
-- 
cgit v1.2.3


From 93cd0d664661f58f7e7bed7373714ab2ace41734 Mon Sep 17 00:00:00 2001
From: A1RM4X <dev@a1rm4x.com>
Date: Wed, 4 Feb 2026 14:26:48 -0500
Subject: USB: add QUIRK_NO_BOS for video capture several devices

Several USB capture devices also need the USB_QUIRK_NO_BOS set for them
to work properly, odds are they are all the same chip inside, just
different vendor/product ids.

This fixes up:
  - ASUS TUF 4K PRO
  - Avermedia Live Gamer Ultra 2.1 (GC553G2)
  - UGREEN 35871
to now run at full speed (10 Gbps/4K 60 fps mode.)

Link: https://lore.kernel.org/r/CACy+XB-f-51xGpNQFCSm5pE_momTQLu=BaZggHYU1DiDmFX=ug@mail.gmail.com
Cc: stable <stable@kernel.org>
Signed-off-by: A1RM4X <dev@a1rm4x.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 9e7e49712739..e347236d83e8 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -376,6 +376,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* SanDisk Extreme 55AE */
 	{ USB_DEVICE(0x0781, 0x55ae), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Avermedia Live Gamer Ultra 2.1 (GC553G2) - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x07ca, 0x2553), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* Realforce 87U Keyboard */
 	{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
 
@@ -436,6 +439,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* ASUS TUF 4K PRO - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x0b05, 0x1ab9), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/
 	{ USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS },
 
@@ -564,6 +570,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* UGREEN 35871 - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x2b89, 0x5871), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* APTIV AUTOMOTIVE HUB */
 	{ USB_DEVICE(0x2c48, 0x0132), .driver_info =
 			USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT },
-- 
cgit v1.2.3


From 7dff99b354601dd01829e1511711846e04340a69 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 23 Feb 2026 11:18:48 -0800
Subject: Remove WARN_ALL_UNSEEDED_RANDOM kernel config option

This config option goes way back - it used to be an internal debug
option to random.c (at that point called DEBUG_RANDOM_BOOT), then was
renamed and exposed as a config option as CONFIG_WARN_UNSEEDED_RANDOM,
and then further renamed to the current CONFIG_WARN_ALL_UNSEEDED_RANDOM.

It was all done with the best of intentions: the more limited
rate-limited reports were reporting some cases, but if you wanted to see
all the gory details, you'd enable this "ALL" option.

However, it turns out - perhaps not surprisingly - that when people
don't care about and fix the first rate-limited cases, they most
certainly don't care about any others either, and so warning about all
of them isn't actually helping anything.

And the non-ratelimited reporting causes problems, where well-meaning
people enable debug options, but the excessive flood of messages that
nobody cares about will hide actual real information when things go
wrong.

I just got a kernel bug report (which had nothing to do with randomness)
where two thirds of the the truncated dmesg was just variations of

   random: get_random_u32 called from __get_random_u32_below+0x10/0x70 with crng_init=0

and in the process early boot messages had been lost (in addition to
making the messages that _hadn't_ been lost harder to read).

The proper way to find these things for the hypothetical developer that
cares - if such a person exists - is almost certainly with boot time
tracing.  That gives you the option to get call graphs etc too, which is
likely a requirement for fixing any problems anyway.

See Documentation/trace/boottime-trace.rst for that option.

And if we for some reason do want to re-introduce actual printing of
these things, it will need to have some uniqueness filtering rather than
this "just print it all" model.

Fixes: cc1e127bfa95 ("random: remove ratelimiting for in-kernel unseeded randomness")
Acked-by: Jason Donenfeld <Jason@zx2c4.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/random.c       | 12 +-----------
 kernel/configs/debug.config |  1 -
 lib/Kconfig.debug           | 27 ---------------------------
 3 files changed, 1 insertion(+), 39 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index dcd002e1b890..7ff4d29911fd 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -96,8 +96,7 @@ static ATOMIC_NOTIFIER_HEAD(random_ready_notifier);
 /* Control how we warn userspace. */
 static struct ratelimit_state urandom_warning =
 	RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE);
-static int ratelimit_disable __read_mostly =
-	IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM);
+static int ratelimit_disable __read_mostly = 0;
 module_param_named(ratelimit_disable, ratelimit_disable, int, 0644);
 MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression");
 
@@ -168,12 +167,6 @@ int __cold execute_with_initialized_rng(struct notifier_block *nb)
 	return ret;
 }
 
-#define warn_unseeded_randomness() \
-	if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \
-		printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \
-				__func__, (void *)_RET_IP_, crng_init)
-
-
 /*********************************************************************
  *
  * Fast key erasure RNG, the "crng".
@@ -434,7 +427,6 @@ static void _get_random_bytes(void *buf, size_t len)
  */
 void get_random_bytes(void *buf, size_t len)
 {
-	warn_unseeded_randomness();
 	_get_random_bytes(buf, len);
 }
 EXPORT_SYMBOL(get_random_bytes);
@@ -523,8 +515,6 @@ type get_random_ ##type(void)							\
 	struct batch_ ##type *batch;						\
 	unsigned long next_gen;							\
 										\
-	warn_unseeded_randomness();						\
-										\
 	if  (!crng_ready()) {							\
 		_get_random_bytes(&ret, sizeof(ret));				\
 		return ret;							\
diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index 774702591d26..307c97ac5fa9 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -29,7 +29,6 @@ CONFIG_SECTION_MISMATCH_WARN_ONLY=y
 # CONFIG_UBSAN_ALIGNMENT is not set
 # CONFIG_UBSAN_DIV_ZERO is not set
 # CONFIG_UBSAN_TRAP is not set
-# CONFIG_WARN_ALL_UNSEEDED_RANDOM is not set
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_FS_ALLOW_ALL=y
 CONFIG_DEBUG_IRQFLAGS=y
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e2dfbbd3d78..318df4c75454 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1766,33 +1766,6 @@ config STACKTRACE
 	  It is also used by various kernel debugging features that require
 	  stack trace generation.
 
-config WARN_ALL_UNSEEDED_RANDOM
-	bool "Warn for all uses of unseeded randomness"
-	default n
-	help
-	  Some parts of the kernel contain bugs relating to their use of
-	  cryptographically secure random numbers before it's actually possible
-	  to generate those numbers securely. This setting ensures that these
-	  flaws don't go unnoticed, by enabling a message, should this ever
-	  occur. This will allow people with obscure setups to know when things
-	  are going wrong, so that they might contact developers about fixing
-	  it.
-
-	  Unfortunately, on some models of some architectures getting
-	  a fully seeded CRNG is extremely difficult, and so this can
-	  result in dmesg getting spammed for a surprisingly long
-	  time.  This is really bad from a security perspective, and
-	  so architecture maintainers really need to do what they can
-	  to get the CRNG seeded sooner after the system is booted.
-	  However, since users cannot do anything actionable to
-	  address this, by default this option is disabled.
-
-	  Say Y here if you want to receive warnings for all uses of
-	  unseeded randomness.  This will be of use primarily for
-	  those developers interested in improving the security of
-	  Linux kernels running on their architecture (or
-	  subarchitecture).
-
 config DEBUG_KOBJECT
 	bool "kobject debugging"
 	depends on DEBUG_KERNEL
-- 
cgit v1.2.3


From b9fde507355342a2d64225d582dc8b98ff5ecb19 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Date: Thu, 19 Feb 2026 02:38:34 +0000
Subject: usb: gadget: f_tcm: Fix NULL pointer dereferences in nexus handling

The `tpg->tpg_nexus` pointer in the USB Target driver is dynamically
managed and tied to userspace configuration via ConfigFS. It can be
NULL if the USB host sends requests before the nexus is fully
established or immediately after it is dropped.

Currently, functions like `bot_submit_command()` and the data
transfer paths retrieve `tv_nexus = tpg->tpg_nexus` and immediately
dereference `tv_nexus->tvn_se_sess` without any validation. If a
malicious or misconfigured USB host sends a BOT (Bulk-Only Transport)
command during this race window, it triggers a NULL pointer
dereference, leading to a kernel panic (local DoS).

This exposes an inconsistent API usage within the module, as peer
functions like `usbg_submit_command()` and `bot_send_bad_response()`
correctly implement a NULL check for `tv_nexus` before proceeding.

Fix this by bringing consistency to the nexus handling. Add the
missing `if (!tv_nexus)` checks to the vulnerable BOT command and
request processing paths, aborting the command gracefully with an
error instead of crashing the system.

Fixes: c52661d60f63 ("usb-gadget: Initial merge of target module for UASP + BOT")
Cc: stable <stable@kernel.org>
Signed-off-by: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Reviewed-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260219023834.17976-1-jiashengjiangcool@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_tcm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index ec050d8f99f1..a7853dcbb14c 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1222,6 +1222,13 @@ static void usbg_submit_cmd(struct usbg_cmd *cmd)
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		struct usb_gadget *gadget = fuas_to_gadget(cmd->fu);
+
+		dev_err(&gadget->dev, "Missing nexus, ignoring command\n");
+		return;
+	}
+
 	dir = get_cmd_dir(cmd->cmd_buf);
 	if (dir < 0)
 		goto out;
@@ -1483,6 +1490,13 @@ static void bot_cmd_work(struct work_struct *work)
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
+	if (!tv_nexus) {
+		struct usb_gadget *gadget = fuas_to_gadget(cmd->fu);
+
+		dev_err(&gadget->dev, "Missing nexus, ignoring command\n");
+		return;
+	}
+
 	dir = get_cmd_dir(cmd->cmd_buf);
 	if (dir < 0)
 		goto out;
-- 
cgit v1.2.3


From fde0634ad9856b3943a2d1a8cc8de174a63ac840 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Sat, 21 Feb 2026 22:48:15 +0800
Subject: usb: legacy: ncm: Fix NPE in gncm_bind

Commit 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle
with bind/unbind") deferred the allocation of the net_device. This
change leads to a NULL pointer dereference in the legacy NCM driver as
it attempts to access the net_device before it's fully instantiated.

Store the provided qmult, host_addr, and dev_addr into the struct
ncm_opts->net_opts during gncm_bind(). These values will be properly
applied to the net_device when it is allocated and configured later in
the binding process by the NCM function driver.

Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable@kernel.org
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202602181727.fd76c561-lkp@intel.com
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260221-legacy-ncm-v2-1-dfb891d76507@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/legacy/ncm.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index 0f1b45e3abd1..e8d565534053 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -15,8 +15,10 @@
 /* #define DEBUG */
 /* #define VERBOSE_DEBUG */
 
+#include <linux/hex.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string.h>
 #include <linux/usb/composite.h>
 
 #include "u_ether.h"
@@ -129,6 +131,7 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 	struct usb_gadget	*gadget = cdev->gadget;
 	struct f_ncm_opts	*ncm_opts;
 	int			status;
+	u8			mac[ETH_ALEN];
 
 	f_ncm_inst = usb_get_function_instance("ncm");
 	if (IS_ERR(f_ncm_inst))
@@ -136,11 +139,15 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 
 	ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst);
 
-	gether_set_qmult(ncm_opts->net, qmult);
-	if (!gether_set_host_addr(ncm_opts->net, host_addr))
+	ncm_opts->net_opts.qmult = qmult;
+	if (host_addr && mac_pton(host_addr, mac)) {
+		memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN);
 		pr_info("using host ethernet address: %s", host_addr);
-	if (!gether_set_dev_addr(ncm_opts->net, dev_addr))
+	}
+	if (dev_addr && mac_pton(dev_addr, mac)) {
+		memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN);
 		pr_info("using self ethernet address: %s", dev_addr);
+	}
 
 	/* Allocate string descriptor numbers ... note that string
 	 * contents can be overridden by the composite_dev glue.
-- 
cgit v1.2.3


From 0d6c8144ca4d93253de952a5ea0028c19ed7ab68 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Sat, 21 Feb 2026 22:48:16 +0800
Subject: usb: gadget: f_ncm: Fix atomic context locking issue

The ncm_set_alt function was holding a mutex to protect against races
with configfs, which invokes the might-sleep function inside an atomic
context.

Remove the struct net_device pointer from the f_ncm_opts structure to
eliminate the contention. The connection state is now managed by a new
boolean flag to preserve the use-after-free fix from
commit 6334b8e4553c ("usb: gadget: f_ncm: Fix UAF ncm object at re-bind
after usb ep transport error").

BUG: sleeping function called from invalid context
Call Trace:
 dump_stack_lvl+0x83/0xc0
 dump_stack+0x14/0x16
 __might_resched+0x389/0x4c0
 __might_sleep+0x8e/0x100
 ...
 __mutex_lock+0x6f/0x1740
 ...
 ncm_set_alt+0x209/0xa40
 set_config+0x6b6/0xb40
 composite_setup+0x734/0x2b40
 ...

Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable@kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260221-legacy-ncm-v2-2-dfb891d76507@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c            | 29 +++++++++++---------------
 drivers/usb/gadget/function/u_ether_configfs.h | 11 +---------
 drivers/usb/gadget/function/u_ncm.h            |  1 -
 3 files changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 14fc7dce6f39..4da19864d70b 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -58,6 +58,7 @@ struct f_ncm {
 	u8				notify_state;
 	atomic_t			notify_count;
 	bool				is_open;
+	bool				is_connected;
 
 	const struct ndp_parser_opts	*parser_opts;
 	bool				is_crc;
@@ -864,7 +865,6 @@ invalid:
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,13 +887,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		scoped_guard(mutex, &opts->lock)
-			if (opts->net) {
-				DBG(cdev, "reset ncm\n");
-				opts->net = NULL;
-				gether_disconnect(&ncm->port);
-				ncm_reset_values(ncm);
-			}
+		if (ncm->is_connected) {
+			DBG(cdev, "reset ncm\n");
+			ncm->is_connected = false;
+			gether_disconnect(&ncm->port);
+			ncm_reset_values(ncm);
+		}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -926,8 +925,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			scoped_guard(mutex, &opts->lock)
-				opts->net = net;
+			ncm->is_connected = true;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1374,16 +1372,14 @@ err:
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	scoped_guard(mutex, &opts->lock)
-		if (opts->net) {
-			opts->net = NULL;
-			gether_disconnect(&ncm->port);
-		}
+	if (ncm->is_connected) {
+		ncm->is_connected = false;
+		gether_disconnect(&ncm->port);
+	}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1687,7 +1683,6 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
 
-	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
 	gether_setup_opts_default(&opts->net_opts, "usb");
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 217990a266b2..25d8fb05b598 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -327,18 +327,9 @@ out:									\
 					      char *page)			\
 	{									\
 		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		const char *name;						\
 										\
 		guard(mutex)(&opts->lock);					\
-		rtnl_lock();							\
-		if (opts->net_opts.ifname_set)					\
-			name = opts->net_opts.name;				\
-		else if (opts->net)						\
-			name = netdev_name(opts->net);				\
-		else								\
-			name = "(inactive net_device)";				\
-		rtnl_unlock();							\
-		return sysfs_emit(page, "%s\n", name);				\
+		return sysfs_emit(page, "%s\n", opts->net_opts.name);		\
 	}									\
 										\
 	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index d99330fe31e8..6d7538855744 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -19,7 +19,6 @@
 
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
-	struct net_device		*net;
 
 	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;
-- 
cgit v1.2.3


From 7a875c09899ba0404844abfd8f0d54cdc481c151 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 9 Feb 2026 15:37:20 +0100
Subject: usb: yurex: fix race in probe

The bbu member of the descriptor must be set to the value
standing for uninitialized values before the URB whose
completion handler sets bbu is submitted. Otherwise there is
a window during which probing can overwrite already retrieved
data.

Cc: stable <stable@kernel.org>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/20260209143720.1507500-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 9189e4bb213a..7a482cdee1e9 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -272,6 +272,7 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_
 			 dev->int_buffer, YUREX_BUF_SIZE, yurex_interrupt,
 			 dev, 1);
 	dev->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+	dev->bbu = -1;
 	if (usb_submit_urb(dev->urb, GFP_KERNEL)) {
 		retval = -EIO;
 		dev_err(&interface->dev, "Could not submitting URB\n");
@@ -280,7 +281,6 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_
 
 	/* save our data pointer in this interface device */
 	usb_set_intfdata(interface, dev);
-	dev->bbu = -1;
 
 	/* we can register the device now, as it is ready */
 	retval = usb_register_dev(interface, &yurex_class);
-- 
cgit v1.2.3


From f9d69d5e7bde2295eb7488a56f094ac8f5383b92 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Tue, 30 Dec 2025 10:32:08 -0800
Subject: module: Fix kernel panic when a symbol st_shndx is out of bounds

The module loader doesn't check for bounds of the ELF section index in
simplify_symbols():

       for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) {
		const char *name = info->strtab + sym[i].st_name;

		switch (sym[i].st_shndx) {
		case SHN_COMMON:

		[...]

		default:
			/* Divert to percpu allocation if a percpu var. */
			if (sym[i].st_shndx == info->index.pcpu)
				secbase = (unsigned long)mod_percpu(mod);
			else
  /** HERE --> **/		secbase = info->sechdrs[sym[i].st_shndx].sh_addr;
			sym[i].st_value += secbase;
			break;
		}
	}

A symbol with an out-of-bounds st_shndx value, for example 0xffff
(known as SHN_XINDEX or SHN_HIRESERVE), may cause a kernel panic:

  BUG: unable to handle page fault for address: ...
  RIP: 0010:simplify_symbols+0x2b2/0x480
  ...
  Kernel panic - not syncing: Fatal exception

This can happen when module ELF is legitimately using SHN_XINDEX or
when it is corrupted.

Add a bounds check in simplify_symbols() to validate that st_shndx is
within the valid range before using it.

This issue was discovered due to a bug in llvm-objcopy, see relevant
discussion for details [1].

[1] https://lore.kernel.org/linux-modules/20251224005752.201911-1-ihor.solodrai@linux.dev/

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 kernel/module/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index eec6c9cf8dbb..c3ce106c70af 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 			break;
 
 		default:
+			if (sym[i].st_shndx >= info->hdr->e_shnum) {
+				pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n",
+				       mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1);
+				ret = -ENOEXEC;
+				break;
+			}
+
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == info->index.pcpu)
 				secbase = (unsigned long)mod_percpu(mod);
-- 
cgit v1.2.3


From 16cb1a64dce56708a1684bf755ad52fb52c41f87 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Feb 2026 13:12:00 +0100
Subject: RDMA/uverbs: select CONFIG_DMA_SHARED_BUFFER

The addition of dmabuf support in uverbs means that it is no
longer possible to build infiniband support if that is disabled:

arm-linux-gnueabi-ld: drivers/infiniband/core/ib_core_uverbs.o: in function `rdma_user_mmap_entry_remove.part.0':
ib_core_uverbs.c:(.text+0x508): undefined reference to `dma_buf_move_notify'
(dma_buf_move_notify): Unknown destination type (ARM/Thumb) in drivers/infiniband/core/ib_core_uverbs.o
ib_core_uverbs.c:(.text+0x518): undefined reference to `dma_resv_wait_timeout'
(dma_resv_wait_timeout): Unknown destination type (ARM/Thumb) in drivers/infiniband/core/ib_core_uverbs.o

Select this from Kconfig, as we do for the other users.

Fixes: 0ac6f4056c4a ("RDMA/uverbs: Add DMABUF object type and operations")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20260216121213.2088910-1-arnd@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 794b9778816b..78ac2ff5befd 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -6,6 +6,7 @@ menuconfig INFINIBAND
 	depends on INET
 	depends on m || IPV6 != m
 	depends on !ALPHA
+	select DMA_SHARED_BUFFER
 	select IRQ_POLL
 	select DIMLIB
 	help
-- 
cgit v1.2.3


From f9b888599418951b8229bbb28851ed4da50c58e9 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 28 Jan 2026 16:02:42 -0600
Subject: remoteproc: qcom_wcnss: Fix reserved region mapping failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_*
functions for "memory-region"") switched from devm_ioremap_wc() to
devm_ioremap_resource_wc(). The difference is devm_ioremap_resource_wc()
also requests the resource which fails. Testing of both fixed and
dynamic reserved regions indicates that requesting the resource should
work, so I'm not sure why it doesn't work in this case. Fix the issue by
reverting back to devm_ioremap_wc().

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reported-by: André Apitzsch <git@apitzsch.eu>
Fixes: c70b9d5fdcd7 ("remoteproc: qcom: Use of_reserved_mem_region_* functions for "memory-region"")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: André Apitzsch <git@apitzsch.eu> # on BQ Aquaris M5
Link: https://lore.kernel.org/r/20260128220243.3018526-1-robh@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_wcnss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c
index ee18bf2e8054..4add9037dbd5 100644
--- a/drivers/remoteproc/qcom_wcnss.c
+++ b/drivers/remoteproc/qcom_wcnss.c
@@ -537,7 +537,7 @@ static int wcnss_alloc_memory_region(struct qcom_wcnss *wcnss)
 
 	wcnss->mem_phys = wcnss->mem_reloc = res.start;
 	wcnss->mem_size = resource_size(&res);
-	wcnss->mem_region = devm_ioremap_resource_wc(wcnss->dev, &res);
+	wcnss->mem_region = devm_ioremap_wc(wcnss->dev, wcnss->mem_phys, wcnss->mem_size);
 	if (IS_ERR(wcnss->mem_region)) {
 		dev_err(wcnss->dev, "unable to map memory region: %pR\n", &res);
 		return PTR_ERR(wcnss->mem_region);
-- 
cgit v1.2.3


From 7accb1c4321acb617faf934af59d928b0b047e2b Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 3 Feb 2026 15:16:16 -0500
Subject: Bluetooth: L2CAP: Fix invalid response to L2CAP_ECRED_RECONF_REQ

This fixes responding with an invalid result caused by checking the
wrong size of CID which should have been (cmd_len - sizeof(*req)) and
on top of it the wrong result was use L2CAP_CR_LE_INVALID_PARAMS which
is invalid/reserved for reconf when running test like L2CAP/ECFC/BI-03-C:

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 64
        MPS: 64
        Source CID: 64
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reserved (0x000c)
         Result: Reconfiguration failed - one or more Destination CIDs invalid (0x0003)

Fiix L2CAP/ECFC/BI-04-C which expects L2CAP_RECONF_INVALID_MPS (0x0002)
when more than one channel gets its MPS reduced:

> ACL Data RX: Handle 64 flags 0x02 dlen 16
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 8
        MTU: 264
        MPS: 99
        Source CID: 64
!       Source CID: 65
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reconfiguration successful (0x0000)
         Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)

Fix L2CAP/ECFC/BI-05-C when SCID is invalid (85 unconnected):

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 65
        MPS: 64
!        Source CID: 85
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!        Result: Reconfiguration successful (0x0000)
         Result: Reconfiguration failed - one or more Destination CIDs invalid (0x0003)

Fix L2CAP/ECFC/BI-06-C when MPS < L2CAP_ECRED_MIN_MPS (64):

> ACL Data RX: Handle 64 flags 0x02 dlen 14
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 2 len 6
        MTU: 672
!       MPS: 63
        Source CID: 64
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!       Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)
        Result: Reconfiguration failed - other unacceptable parameters (0x0004)

Fix L2CAP/ECFC/BI-07-C when MPS reduced for more than one channel:

> ACL Data RX: Handle 64 flags 0x02 dlen 16
      LE L2CAP: Enhanced Credit Reconfigure Request (0x19) ident 3 len 8
        MTU: 84
!       MPS: 71
        Source CID: 64
!        Source CID: 65
< ACL Data TX: Handle 64 flags 0x00 dlen 10
      LE L2CAP: Enhanced Credit Reconfigure Respond (0x1a) ident 2 len 2
!       Result: Reconfiguration successful (0x0000)
        Result: Reconfiguration failed - reduction in size of MPS not allowed for more than one channel at a time (0x0002)

Link: https://github.com/bluez/bluez/issues/1865
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h |  2 ++
 net/bluetooth/l2cap_core.c    | 63 ++++++++++++++++++++++++++++++-------------
 2 files changed, 47 insertions(+), 18 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index ec3af01e4db9..6f9cf7a05986 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -493,6 +493,8 @@ struct l2cap_ecred_reconf_req {
 #define L2CAP_RECONF_SUCCESS		0x0000
 #define L2CAP_RECONF_INVALID_MTU	0x0001
 #define L2CAP_RECONF_INVALID_MPS	0x0002
+#define L2CAP_RECONF_INVALID_CID	0x0003
+#define L2CAP_RECONF_INVALID_PARAMS	0x0004
 
 struct l2cap_ecred_reconf_rsp {
 	__le16 result;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b628b0fa39b2..81038458be0c 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5310,14 +5310,14 @@ static inline int l2cap_ecred_reconf_req(struct l2cap_conn *conn,
 	struct l2cap_ecred_reconf_req *req = (void *) data;
 	struct l2cap_ecred_reconf_rsp rsp;
 	u16 mtu, mps, result;
-	struct l2cap_chan *chan;
+	struct l2cap_chan *chan[L2CAP_ECRED_MAX_CID] = {};
 	int i, num_scid;
 
 	if (!enable_ecred)
 		return -EINVAL;
 
-	if (cmd_len < sizeof(*req) || cmd_len - sizeof(*req) % sizeof(u16)) {
-		result = L2CAP_CR_LE_INVALID_PARAMS;
+	if (cmd_len < sizeof(*req) || (cmd_len - sizeof(*req)) % sizeof(u16)) {
+		result = L2CAP_RECONF_INVALID_CID;
 		goto respond;
 	}
 
@@ -5327,42 +5327,69 @@ static inline int l2cap_ecred_reconf_req(struct l2cap_conn *conn,
 	BT_DBG("mtu %u mps %u", mtu, mps);
 
 	if (mtu < L2CAP_ECRED_MIN_MTU) {
-		result = L2CAP_RECONF_INVALID_MTU;
+		result = L2CAP_RECONF_INVALID_PARAMS;
 		goto respond;
 	}
 
 	if (mps < L2CAP_ECRED_MIN_MPS) {
-		result = L2CAP_RECONF_INVALID_MPS;
+		result = L2CAP_RECONF_INVALID_PARAMS;
 		goto respond;
 	}
 
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
+
+	if (num_scid > L2CAP_ECRED_MAX_CID) {
+		result = L2CAP_RECONF_INVALID_PARAMS;
+		goto respond;
+	}
+
 	result = L2CAP_RECONF_SUCCESS;
 
+	/* Check if each SCID, MTU and MPS are valid */
 	for (i = 0; i < num_scid; i++) {
 		u16 scid;
 
 		scid = __le16_to_cpu(req->scid[i]);
-		if (!scid)
-			return -EPROTO;
+		if (!scid) {
+			result = L2CAP_RECONF_INVALID_CID;
+			goto respond;
+		}
 
-		chan = __l2cap_get_chan_by_dcid(conn, scid);
-		if (!chan)
-			continue;
+		chan[i] = __l2cap_get_chan_by_dcid(conn, scid);
+		if (!chan[i]) {
+			result = L2CAP_RECONF_INVALID_CID;
+			goto respond;
+		}
 
-		/* If the MTU value is decreased for any of the included
-		 * channels, then the receiver shall disconnect all
-		 * included channels.
+		/* The MTU field shall be greater than or equal to the greatest
+		 * current MTU size of these channels.
 		 */
-		if (chan->omtu > mtu) {
-			BT_ERR("chan %p decreased MTU %u -> %u", chan,
-			       chan->omtu, mtu);
+		if (chan[i]->omtu > mtu) {
+			BT_ERR("chan %p decreased MTU %u -> %u", chan[i],
+			       chan[i]->omtu, mtu);
 			result = L2CAP_RECONF_INVALID_MTU;
+			goto respond;
 		}
 
-		chan->omtu = mtu;
-		chan->remote_mps = mps;
+		/* If more than one channel is being configured, the MPS field
+		 * shall be greater than or equal to the current MPS size of
+		 * each of these channels. If only one channel is being
+		 * configured, the MPS field may be less than the current MPS
+		 * of that channel.
+		 */
+		if (chan[i]->remote_mps >= mps && i) {
+			BT_ERR("chan %p decreased MPS %u -> %u", chan[i],
+			       chan[i]->remote_mps, mps);
+			result = L2CAP_RECONF_INVALID_MPS;
+			goto respond;
+		}
+	}
+
+	/* Commit the new MTU and MPS values after checking they are valid */
+	for (i = 0; i < num_scid; i++) {
+		chan[i]->omtu = mtu;
+		chan[i]->remote_mps = mps;
 	}
 
 respond:
-- 
cgit v1.2.3


From c28d2bff70444a85b3b86aaf241ece9408c7858c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 5 Feb 2026 15:11:34 -0500
Subject: Bluetooth: L2CAP: Fix result of L2CAP_ECRED_CONN_RSP when MTU is too
 short

Test L2CAP/ECFC/BV-26-C expect the response to L2CAP_ECRED_CONN_REQ with
and MTU value < L2CAP_ECRED_MIN_MTU (64) to be L2CAP_CR_LE_INVALID_PARAMS
rather than L2CAP_CR_LE_UNACCEPT_PARAMS.

Also fix not including the correct number of CIDs in the response since
the spec requires all CIDs being rejected to be included in the
response.

Link: https://github.com/bluez/bluez/issues/1868
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h |  6 +++---
 net/bluetooth/l2cap_core.c    | 14 ++++++++------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 6f9cf7a05986..010f1a8fd15f 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -284,9 +284,9 @@ struct l2cap_conn_rsp {
 #define L2CAP_CR_LE_BAD_KEY_SIZE	0x0007
 #define L2CAP_CR_LE_ENCRYPTION		0x0008
 #define L2CAP_CR_LE_INVALID_SCID	0x0009
-#define L2CAP_CR_LE_SCID_IN_USE		0X000A
-#define L2CAP_CR_LE_UNACCEPT_PARAMS	0X000B
-#define L2CAP_CR_LE_INVALID_PARAMS	0X000C
+#define L2CAP_CR_LE_SCID_IN_USE		0x000A
+#define L2CAP_CR_LE_UNACCEPT_PARAMS	0x000B
+#define L2CAP_CR_LE_INVALID_PARAMS	0x000C
 
 /* connect/create channel status */
 #define L2CAP_CS_NO_INFO	0x0000
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 81038458be0c..390d25909104 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5051,13 +5051,15 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	struct l2cap_chan *chan, *pchan;
 	u16 mtu, mps;
 	__le16 psm;
-	u8 result, len = 0;
+	u8 result, rsp_len = 0;
 	int i, num_scid;
 	bool defer = false;
 
 	if (!enable_ecred)
 		return -EINVAL;
 
+	memset(pdu, 0, sizeof(*pdu));
+
 	if (cmd_len < sizeof(*req) || (cmd_len - sizeof(*req)) % sizeof(u16)) {
 		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
@@ -5066,6 +5068,9 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
 
+	/* Always respond with the same number of scids as in the request */
+	rsp_len = cmd_len;
+
 	if (num_scid > L2CAP_ECRED_MAX_CID) {
 		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
@@ -5075,7 +5080,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	mps  = __le16_to_cpu(req->mps);
 
 	if (mtu < L2CAP_ECRED_MIN_MTU || mps < L2CAP_ECRED_MIN_MPS) {
-		result = L2CAP_CR_LE_UNACCEPT_PARAMS;
+		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
 	}
 
@@ -5095,8 +5100,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 
 	BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps);
 
-	memset(pdu, 0, sizeof(*pdu));
-
 	/* Check if we have socket listening on psm */
 	pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src,
 					 &conn->hcon->dst, LE_LINK);
@@ -5121,7 +5124,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		BT_DBG("scid[%d] 0x%4.4x", i, scid);
 
 		pdu->dcid[i] = 0x0000;
-		len += sizeof(*pdu->dcid);
 
 		/* Check for valid dynamic CID range */
 		if (scid < L2CAP_CID_DYN_START || scid > L2CAP_CID_LE_DYN_END) {
@@ -5188,7 +5190,7 @@ response:
 		return 0;
 
 	l2cap_send_cmd(conn, cmd->ident, L2CAP_ECRED_CONN_RSP,
-		       sizeof(*pdu) + len, pdu);
+		       sizeof(*pdu) + rsp_len, pdu);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 21e4271e65094172aadd5beb8caea95dd0fbf6d7 Mon Sep 17 00:00:00 2001
From: Heitor Alves de Siqueira <halves@igalia.com>
Date: Wed, 11 Feb 2026 15:03:35 -0300
Subject: Bluetooth: purge error queues in socket destructors

When TX timestamping is enabled via SO_TIMESTAMPING, SKBs may be queued
into sk_error_queue and will stay there until consumed. If userspace never
gets to read the timestamps, or if the controller is removed unexpectedly,
these SKBs will leak.

Fix by adding skb_queue_purge() calls for sk_error_queue in affected
bluetooth destructors. RFCOMM does not currently use sk_error_queue.

Fixes: 134f4b39df7b ("Bluetooth: add support for skb TX SND/COMPLETION timestamping")
Reported-by: syzbot+7ff4013eabad1407b70a@syzkaller.appspotmail.com
Closes: https://syzbot.org/bug?extid=7ff4013eabad1407b70a
Cc: stable@vger.kernel.org
Signed-off-by: Heitor Alves de Siqueira <halves@igalia.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sock.c   | 1 +
 net/bluetooth/iso.c        | 1 +
 net/bluetooth/l2cap_sock.c | 1 +
 net/bluetooth/sco.c        | 1 +
 4 files changed, 4 insertions(+)

diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 4e7bf63af9c5..0290dea081f6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -2166,6 +2166,7 @@ static void hci_sock_destruct(struct sock *sk)
 	mgmt_cleanup(sk);
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static const struct proto_ops hci_sock_ops = {
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 1459ab161fd2..a38d3774176d 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -746,6 +746,7 @@ static void iso_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void iso_sock_cleanup_listen(struct sock *parent)
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 3ba3ce7eaa98..62ceda979f39 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1817,6 +1817,7 @@ static void l2cap_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 87ba90336e80..cccfaf560317 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -470,6 +470,7 @@ static void sco_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void sco_sock_cleanup_listen(struct sock *parent)
-- 
cgit v1.2.3


From 5c4e9a8b18457ad28b57069ef0f14661e3192b2e Mon Sep 17 00:00:00 2001
From: Jinwang Li <jinwang.li@oss.qualcomm.com>
Date: Thu, 5 Feb 2026 14:26:00 +0800
Subject: Bluetooth: hci_qca: Cleanup on all setup failures

The setup process previously combined error handling and retry gating
under one condition. As a result, the final failed attempt exited
without performing cleanup.

Update the failure path to always perform power and port cleanup on
setup failure, and reopen the port only when retrying.

Fixes: 9e80587aba4c ("Bluetooth: hci_qca: Enhance retry logic in qca_setup")
Signed-off-by: Jinwang Li <jinwang.li@oss.qualcomm.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index c511546f793e..c6de2602b49d 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2046,19 +2046,23 @@ retry:
 	}
 
 out:
-	if (ret && retries < MAX_INIT_RETRIES) {
-		bt_dev_warn(hdev, "Retry BT power ON:%d", retries);
+	if (ret) {
 		qca_power_shutdown(hu);
-		if (hu->serdev) {
-			serdev_device_close(hu->serdev);
-			ret = serdev_device_open(hu->serdev);
-			if (ret) {
-				bt_dev_err(hdev, "failed to open port");
-				return ret;
+
+		if (retries < MAX_INIT_RETRIES) {
+			bt_dev_warn(hdev, "Retry BT power ON:%d", retries);
+			if (hu->serdev) {
+				serdev_device_close(hu->serdev);
+				ret = serdev_device_open(hu->serdev);
+				if (ret) {
+					bt_dev_err(hdev, "failed to open port");
+					return ret;
+				}
 			}
+			retries++;
+			goto retry;
 		}
-		retries++;
-		goto retry;
+		return ret;
 	}
 
 	/* Setup bdaddr */
-- 
cgit v1.2.3


From 05761c2c2b5bfec85c47f60c903c461e9b56cf87 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 11 Feb 2026 15:18:03 -0500
Subject: Bluetooth: L2CAP: Fix response to L2CAP_ECRED_CONN_REQ

Similar to 03dba9cea72f ("Bluetooth: L2CAP: Fix not responding with
L2CAP_CR_LE_ENCRYPTION") the result code L2CAP_CR_LE_ENCRYPTION shall
be used when BT_SECURITY_MEDIUM is set since that means security mode 2
which mean it doesn't require authentication which results in
qualification test L2CAP/ECFC/BV-32-C failing.

Link: https://github.com/bluez/bluez/issues/1871
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 390d25909104..9452c6179acb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5112,7 +5112,8 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 
 	if (!smp_sufficient_security(conn->hcon, pchan->sec_level,
 				     SMP_ALLOW_STK)) {
-		result = L2CAP_CR_LE_AUTHENTICATION;
+		result = pchan->sec_level == BT_SECURITY_MEDIUM ?
+			L2CAP_CR_LE_ENCRYPTION : L2CAP_CR_LE_AUTHENTICATION;
 		goto unlock;
 	}
 
-- 
cgit v1.2.3


From f9a1767ce3a34bc33c3d33473f65dc13a380e379 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:11 -0500
Subject: cgroup/cpuset: Fix incorrect change to effective_xcpus in
 partition_xcpus_del()

The effective_xcpus of a cpuset can contain offline CPUs. In
partition_xcpus_del(), the xcpus parameter is incorrectly used as
a temporary cpumask to mask out offline CPUs. As xcpus can be the
effective_xcpus of a cpuset, this can result in unexpected changes
in that cpumask. Fix this problem by not making any changes to the
xcpus parameter.

Fixes: 11e5f407b64a ("cgroup/cpuset: Keep track of CPUs in isolated partitions")
Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c43efef7df71..a366ef84f982 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1221,8 +1221,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent,
 		isolated_cpus_update(old_prs, parent->partition_root_state,
 				     xcpus);
 
-	cpumask_and(xcpus, xcpus, cpu_active_mask);
 	cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus);
+	cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask);
 }
 
 /*
-- 
cgit v1.2.3


From 68230aac8b9aad243626fbaf3ca170012c17fec5 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:12 -0500
Subject: cgroup/cpuset: Fix incorrect use of cpuset_update_tasks_cpumask() in
 update_cpumasks_hier()

Commit e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2")
incorrectly changed the 2nd parameter of cpuset_update_tasks_cpumask()
from tmp->new_cpus to cp->effective_cpus. This second parameter is just
a temporary cpumask for internal use. The cpuset_update_tasks_cpumask()
function was originally called update_tasks_cpumask() before commit
381b53c3b549 ("cgroup/cpuset: rename functions shared between v1
and v2").

This mistake can incorrectly change the effective_cpus of the
cpuset when it is the top_cpuset or in arm64 architecture where
task_cpu_possible_mask() may differ from cpu_possible_mask.  So far
top_cpuset hasn't been passed to update_cpumasks_hier() yet, but arm64
arch can still be impacted. Fix it by reverting the incorrect change.

Fixes: e2ffe502ba45 ("cgroup/cpuset: Add cpuset.cpus.exclusive for v2")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a366ef84f982..8dfffe2dc9ed 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2157,7 +2157,7 @@ get_css:
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-		cpuset_update_tasks_cpumask(cp, cp->effective_cpus);
+		cpuset_update_tasks_cpumask(cp, tmp->new_cpus);
 
 		/*
 		 * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE
-- 
cgit v1.2.3


From 17b1860034c769c9f7669ae2612e91ef8fdde769 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:13 -0500
Subject: cgroup/cpuset: Clarify exclusion rules for cpuset internal variables

Clarify the locking rules associated with file level internal variables
inside the cpuset code. There is no functional change.

Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 105 ++++++++++++++++++++++++++++---------------------
 1 file changed, 61 insertions(+), 44 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 8dfffe2dc9ed..165e2967025b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -61,6 +61,58 @@ static const char * const perr_strings[] = {
 	[PERR_REMOTE]    = "Have remote partition underneath",
 };
 
+/*
+ * CPUSET Locking Convention
+ * -------------------------
+ *
+ * Below are the three global locks guarding cpuset structures in lock
+ * acquisition order:
+ *  - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock)
+ *  - cpuset_mutex
+ *  - callback_lock (raw spinlock)
+ *
+ * A task must hold all the three locks to modify externally visible or
+ * used fields of cpusets, though some of the internally used cpuset fields
+ * and internal variables can be modified without holding callback_lock. If only
+ * reliable read access of the externally used fields are needed, a task can
+ * hold either cpuset_mutex or callback_lock which are exposed to other
+ * external subsystems.
+ *
+ * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others,
+ * ensuring that it is the only task able to also acquire callback_lock and
+ * be able to modify cpusets.  It can perform various checks on the cpuset
+ * structure first, knowing nothing will change. It can also allocate memory
+ * without holding callback_lock. While it is performing these checks, various
+ * callback routines can briefly acquire callback_lock to query cpusets.  Once
+ * it is ready to make the changes, it takes callback_lock, blocking everyone
+ * else.
+ *
+ * Calls to the kernel memory allocator cannot be made while holding
+ * callback_lock which is a spinlock, as the memory allocator may sleep or
+ * call back into cpuset code and acquire callback_lock.
+ *
+ * Now, the task_struct fields mems_allowed and mempolicy may be changed
+ * by other task, we use alloc_lock in the task_struct fields to protect
+ * them.
+ *
+ * The cpuset_common_seq_show() handlers only hold callback_lock across
+ * small pieces of code, such as when reading out possibly multi-word
+ * cpumasks and nodemasks.
+ */
+
+static DEFINE_MUTEX(cpuset_mutex);
+
+/*
+ * File level internal variables below follow one of the following exclusion
+ * rules.
+ *
+ * RWCS: Read/write-able by holding either cpus_write_lock (and optionally
+ *	 cpuset_mutex) or both cpus_read_lock and cpuset_mutex.
+ *
+ * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable
+ *	 by holding both cpuset_mutex and callback_lock.
+ */
+
 /*
  * For local partitions, update to subpartitions_cpus & isolated_cpus is done
  * in update_parent_effective_cpumask(). For remote partitions, it is done in
@@ -70,19 +122,18 @@ static const char * const perr_strings[] = {
  * Exclusive CPUs distributed out to local or remote sub-partitions of
  * top_cpuset
  */
-static cpumask_var_t	subpartitions_cpus;
+static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 
 /*
- * Exclusive CPUs in isolated partitions
+ * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated)
  */
-static cpumask_var_t	isolated_cpus;
+static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * isolated_cpus updating flag (protected by cpuset_mutex)
- * Set if isolated_cpus is going to be updated in the current
- * cpuset_mutex crtical section.
+ * Set if isolated_cpus is being updated in the current cpuset_mutex
+ * critical section.
  */
-static bool isolated_cpus_updating;
+static bool		isolated_cpus_updating;	/* RWCS */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -98,7 +149,7 @@ static bool isolated_cpus_updating;
  * Note that update_relax_domain_level() in cpuset-v1.c can still call
  * rebuild_sched_domains_locked() directly without using this flag.
  */
-static bool force_sd_rebuild;
+static bool force_sd_rebuild;			/* RWCS */
 
 /*
  * Partition root states:
@@ -218,42 +269,6 @@ struct cpuset top_cpuset = {
 	.partition_root_state = PRS_ROOT,
 };
 
-/*
- * There are two global locks guarding cpuset structures - cpuset_mutex and
- * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel
- * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
- * structures. Note that cpuset_mutex needs to be a mutex as it is used in
- * paths that rely on priority inheritance (e.g. scheduler - on RT) for
- * correctness.
- *
- * A task must hold both locks to modify cpusets.  If a task holds
- * cpuset_mutex, it blocks others, ensuring that it is the only task able to
- * also acquire callback_lock and be able to modify cpusets.  It can perform
- * various checks on the cpuset structure first, knowing nothing will change.
- * It can also allocate memory while just holding cpuset_mutex.  While it is
- * performing these checks, various callback routines can briefly acquire
- * callback_lock to query cpusets.  Once it is ready to make the changes, it
- * takes callback_lock, blocking everyone else.
- *
- * Calls to the kernel memory allocator can not be made while holding
- * callback_lock, as that would risk double tripping on callback_lock
- * from one of the callbacks into the cpuset code from within
- * __alloc_pages().
- *
- * If a task is only holding callback_lock, then it has read-only
- * access to cpusets.
- *
- * Now, the task_struct fields mems_allowed and mempolicy may be changed
- * by other task, we use alloc_lock in the task_struct fields to protect
- * them.
- *
- * The cpuset_common_seq_show() handlers only hold callback_lock across
- * small pieces of code, such as when reading out possibly multi-word
- * cpumasks and nodemasks.
- */
-
-static DEFINE_MUTEX(cpuset_mutex);
-
 /**
  * cpuset_lock - Acquire the global cpuset mutex
  *
@@ -1163,6 +1178,8 @@ static void reset_partition_data(struct cpuset *cs)
 static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus)
 {
 	WARN_ON_ONCE(old_prs == new_prs);
+	lockdep_assert_held(&callback_lock);
+	lockdep_assert_held(&cpuset_mutex);
 	if (new_prs == PRS_ISOLATED)
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
 	else
-- 
cgit v1.2.3


From 14713ed9e9291813849018f32edbf5f6de362088 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:14 -0500
Subject: cgroup/cpuset: Set isolated_cpus_updating only if isolated_cpus is
 changed

As cpuset is updating HK_TYPE_DOMAIN housekeeping mask when there is
a change in the set of isolated CPUs, making this change is now more
costly than before.  Right now, the isolated_cpus_updating flag can be
set even if there is no real change in isolated_cpus. Put in additional
checks to make sure that isolated_cpus_updating is set only if there
is a real change in isolated_cpus.

Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 165e2967025b..edc67c6aa553 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1180,11 +1180,15 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 	WARN_ON_ONCE(old_prs == new_prs);
 	lockdep_assert_held(&callback_lock);
 	lockdep_assert_held(&cpuset_mutex);
-	if (new_prs == PRS_ISOLATED)
+	if (new_prs == PRS_ISOLATED) {
+		if (cpumask_subset(xcpus, isolated_cpus))
+			return;
 		cpumask_or(isolated_cpus, isolated_cpus, xcpus);
-	else
+	} else {
+		if (!cpumask_intersects(xcpus, isolated_cpus))
+			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
-
+	}
 	isolated_cpus_updating = true;
 }
 
-- 
cgit v1.2.3


From 5e6aac573cc4cc8e62aebf880b824e219a5ff557 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:15 -0500
Subject: kselftest/cgroup: Simplify test_cpuset_prs.sh by removing "S+"
 command

The "S+" command is used in the test matrix to enable the cpuset
controller. However this can be done automatically and we never use the
"S-" command to disable cpuset controller. Simplify the test matrix and
reduce clutter by removing the command and doing that automatically.
There is no functional change to the test cases.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/cgroup/test_cpuset_prs.sh | 213 +++++++++++-----------
 1 file changed, 104 insertions(+), 109 deletions(-)

diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 5dff3ad53867..ef16f5610d0b 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -196,7 +196,6 @@ test_add_proc()
 #  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
 #  C<l> = add cpu-list to cpuset.cpus
 #  X<l> = add cpu-list to cpuset.cpus.exclusive
-#  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
 #  CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
 #  O<c>=<v> = Write <v> to CPU online file of <c>
@@ -209,44 +208,43 @@ test_add_proc()
 # sched-debug matching which includes offline CPUs and single-CPU partitions
 # while the second one is for matching cpuset.cpus.isolated.
 #
-SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
+SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1"
 TEST_MATRIX=(
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
-	"   C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .      .     0 A2:0-1"
 	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
-	"   C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
-	"  C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
-	"  C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
-	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
+	"   C0-1     .      .    C2-3    P1   C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3    P1    C1:P1    .      .     0 "
+	"   C0-1     .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3     .     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .     P1     0 "
 	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
-	"  C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
 	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
 	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
-	"C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
-	"C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
-	"C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
+	"  C0-3:P1 C2-3:P1  .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
+	"  C2-3:P1  C2:P1   .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# CPU offlining cases:
-	"   C0-1     .      .    C2-3    S+    C4-5     .     O2=0   0 A1:0-1|B1:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
-	"C0-3:P1:S+ C2-3:P1 .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P2  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
-	"C2-3:P1:S+  C3:P1  .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
-	"C2-3:P1:S+  C3:P1  .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
-	"C2-3:P1:S+  C3:P1  .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"   C0-1     .      .    C2-3     .    C4-5     .     O2=0   0 A1:0-1|B1:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
+	"  C2-3:P1  C3:P1   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -264,88 +262,87 @@ TEST_MATRIX=(
 	#
 	# Remote partition and cpuset.cpus.exclusive tests
 	#
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
-	" C0-3:S+ C1-3:S+ C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
-	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
+	"   C0-3    C1-3  C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+	"  C4:X0-3  X1-3  X2-3     .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+	"  C4:X0-3  X1-3  X2-3     .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
 
 	# Nested remote/local partition tests
-	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+	"   C0-3    C1-3  C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
-	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
 								       A1:P0|A2:P1|A3:P0|B1:P1"
-	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
+	"   C0-3    C1-3   C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
 								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
 								       A1:P0|A2:P2|A3:P1 2-4|2-3"
-	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
 								       A1:P0|A2:P2|A3:P1 2"
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      X5      .      .    0 A1:0-4|A2:1-4|A3:2-4 \
 								       A1:P0|A2:P-2|A3:P-1 ."
-	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
 								       A1:P0|A2:P2|A3:P-1 2-4"
 
 	# Remote partition offline tests
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
-	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
 
 	# An invalidated remote partition cannot self-recover from hotplug
-	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+	"   C0-3    C1-3   C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
 
 	# cpus.exclusive.effective clearing test
-	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
+	"   C0-3    C1-3   C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
 
 	# Invalid to valid remote partition transition test
-	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
-	" C0-3:S+ C1-3:X3:P2
-			    .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+	"   C0-3    C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+	"   C0-3 C1-3:X3:P2 .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
 
 	# Invalid to valid local partition direct transition tests
-	" C1-3:S+:P2 X4:P2  .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
-	" C1-3:S+:P2 X4:P2  .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
-	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
-	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+	" C1-3:P2  X4:P2    .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+	" C1-3:P2  X4:P2    .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+	" C0-3:P2    .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
+	" C0-3:P2    .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
 
 	# Local partition invalidation tests
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .      .      .      .     0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .     X4      .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
-	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
 				   .      .    C4:X     .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
 	# Local partition CPU change tests
-	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
-	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+	" C0-5:P2  C4-5:P1  .      .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+	" C0-5:P2  C4-5:P1  .      .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
 
 	# cpus_allowed/exclusive_cpus update tests
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .    X:C4     .      P2     .     0 A1:4|A2:4|XA2:|XA3:|A3:4 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .     X1      .      P2     .     0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
 								       A1:P0|A3:P-2 ."
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
 				   .      .     X3      P2     .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .      .     X3      .      .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
 								       A1:P0|A3:P2 3"
-	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
 				   .     X4      .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
 								       A1:P0|A3:P-2"
 
@@ -356,37 +353,37 @@ TEST_MATRIX=(
 	#
 	# Adding CPUs to partition root that are not in parent's
 	# cpuset.cpus is allowed, but those extra CPUs are ignored.
-	"C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
+	"  C2-3:P1   C3:P1  .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
 
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
-	"C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
-	" C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+	"   C3:P1     C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
 	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# Changing a partition root to member makes child partitions invalid
-	"C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
+	"  C2-3:P1   C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
 	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
 
 	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
 	# as they overlap.
-	"C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1   .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
 
 	# Deletion of CPUs distributed to child cgroup is allowed.
-	"C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
+	"  C0-1:P1  C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
 
 	# To become a valid partition root, cpuset.cpus must overlap parent's
 	# cpuset.cpus.
-	"  C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
+	"  C0-1:P1   .      .    C2-3     .   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
 
 	# Enabling partition with child cpusets is allowed
-	"  C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
+	"   C0-1    C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
 
 	# A partition root with non-partition root parent is invalid| but it
 	# can be made valid if its parent becomes a partition root too.
-	"  C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
-	"  C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
+	"   C0-1    C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
+	"   C0-1   C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
 
 	# A non-exclusive cpuset.cpus change will not invalidate its siblings partition.
 	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2|B1:3 A1:P1|B1:P0"
@@ -398,23 +395,23 @@ TEST_MATRIX=(
 
 	# Child partition root that try to take all CPUs from parent partition
 	# with tasks will remain invalid.
-	" C1-4:P1:S+ P1     .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
-	" C1-4:P1:S+ P1     .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
-	" C1-4:P1:S+ P1     .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
+	"  C1-4:P1  P1      .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
 
 	# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
 	# affect cpuset.cpus.exclusive.effective.
-	" C1-4:X3:S+ C1:X3  .      .       .     C      .      .     0 A2:1-4|XA2:3"
+	"  C1-4:X3 C1:X3    .      .       .     C      .      .     0 A2:1-4|XA2:3"
 
 	# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
 	# but creating a local partition out of it is not allowed. Similarly and change
 	# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
 	# invalidate it.
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
 								       A1:P0|A2:P2:B1:P1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
-	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
 								       A1:P0|A2:P2:B1:P-1 2-4"
 
 	# When multiple partitions with conflicting cpuset.cpus are created, the
@@ -426,14 +423,14 @@ TEST_MATRIX=(
 	" C1-3:X1-3  .      .    C4-5      .     .      .     C1-2   0 A1:1-3|B1:1-2"
 
 	# cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
-	" C1-3:S+   C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
+	"   C1-3    C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
 
 	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	# Failure cases:
 
 	# A task cannot be added to a partition with no cpu
-	"C2-3:P1:S+  C3:P1  .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1 C3:P1    .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
 
 	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
 	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3|B1:4-5"
@@ -465,31 +462,31 @@ REMOTE_TEST_MATRIX=(
 	#  old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
 	#  new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
 	#  ------ ------ ------- ------- ------- ------- ----- ------ --------
-	" X1-3:S+ X4-6:S+ X1-2     X3     X4-5     X6 \
+	"   X1-3   X4-6  X1-2      X3     X4-5     X6 \
 	      .      .     P2      P2      P2      P2    c11:1-2|c12:3|c21:4-5|c22:6 \
 							 c11:P2|c12:P2|c21:P2|c22:P2 1-6"
-	" CX1-4:S+   .   X1-2:P2   C3      .       .  \
+	"  CX1-4     .  X1-2:P2    C3      .       .  \
 	      .      .     .      C3-4     .       .     p1:3-4|c11:1-2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P0 1-2"
-	" CX1-4:S+   .   X1-2:P2   .       .       .  \
+	"  CX1-4     .  X1-2:P2    .       .       .  \
 	    X2-4     .     .       .       .       .     p1:1,3-4|c11:2 \
 							 p1:P0|c11:P2 2"
-	" CX1-5:S+   .   X1-2:P2 X3-5:P1   .       .  \
+	"  CX1-5     .  X1-2:P2  X3-5:P1   .       .  \
 	    X2-4     .     .       .       .       .     p1:1,5|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X2      .       .       .     p1:1|c11:2|c12:3-4 \
 							 p1:P0|c11:P2|c12:P1 2"
 	# p1 as member, will get its effective CPUs from its parent rtest
-	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
 	      .      .     X1     CX2-4    .       .     p1:5-7|c11:1|c12:2-4 \
 							 p1:P0|c11:P2|c12:P1 1"
-	" CX1-4:S+ X5-6:P1:S+ .    .       .       .  \
-	      .      .   X1-2:P2  X4-5:P1  .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+	"  CX1-4  X5-6:P1  .       .       .       .  \
+	      .      .  X1-2:P2  X4-5:P1   .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
 							 p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
 							 1-2,4-6|1-2,5-6"
 	# c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition
-	" C1-5:P1:S+ .  C1-4:P1   C2-3     .       .  \
+	"  C1-5:P1   .  C1-4:P1   C2-3     .       .  \
 	      .      .     .       P1      .       .     p1:5|c11:1-4|c12:5 \
 							 p1:P1|c11:P1|c12:P-1"
 )
@@ -530,7 +527,6 @@ set_ctrl_state()
 	CGRP=$1
 	STATE=$2
 	SHOWERR=${3}
-	CTRL=${CTRL:=$CONTROLLER}
 	HASERR=0
 	REDIRECT="2> $TMPMSG"
 	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
@@ -540,15 +536,16 @@ set_ctrl_state()
 	for CMD in $(echo $STATE | sed -e "s/:/ /g")
 	do
 		TFILE=$CGRP/cgroup.procs
-		SFILE=$CGRP/cgroup.subtree_control
 		PFILE=$CGRP/cpuset.cpus.partition
 		CFILE=$CGRP/cpuset.cpus
 		XFILE=$CGRP/cpuset.cpus.exclusive
-		case $CMD in
-		    S*) PREFIX=${CMD#?}
-			COMM="echo ${PREFIX}${CTRL} > $SFILE"
+
+		# Enable cpuset controller if not enabled yet
+		[[ -f $CFILE ]] || {
+			COMM="echo +cpuset > $CGRP/../cgroup.subtree_control"
 			eval $COMM $REDIRECT
-			;;
+		}
+		case $CMD in
 		    X*)
 			CPUS=${CMD#?}
 			COMM="echo $CPUS > $XFILE"
@@ -947,7 +944,6 @@ check_test_results()
 run_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
 	RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
 	I=0
@@ -1003,7 +999,6 @@ run_state_test()
 run_remote_state_test()
 {
 	TEST=$1
-	CONTROLLER=cpuset
 	[[ -d rtest ]] || mkdir rtest
 	cd rtest
 	echo +cpuset > cgroup.subtree_control
-- 
cgit v1.2.3


From 3bfe47967191f42d17510713b31a47d9284b8c5a Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:16 -0500
Subject: cgroup/cpuset: Move housekeeping_update()/rebuild_sched_domains()
 together

With the latest changes in sched/isolation.c, rebuild_sched_domains*()
requires the HK_TYPE_DOMAIN housekeeping cpumask to be properly
updated first, if needed, before the sched domains can be
rebuilt. So the two naturally fit together. Do that by creating a new
update_hk_sched_domains() helper to house both actions.

The name of the isolated_cpus_updating flag to control the
call to housekeeping_update() is now outdated. So change it to
update_housekeeping to better reflect its purpose. Also move the call
to update_hk_sched_domains() to the end of cpuset and hotplug operations
before releasing the cpuset_mutex.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 51 ++++++++++++++++++++++++--------------------------
 1 file changed, 24 insertions(+), 27 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index edc67c6aa553..14b07a283a2c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -130,10 +130,9 @@ static cpumask_var_t	subpartitions_cpus;	/* RWCS */
 static cpumask_var_t	isolated_cpus;		/* CSCB */
 
 /*
- * Set if isolated_cpus is being updated in the current cpuset_mutex
- * critical section.
+ * Set if housekeeping cpumasks are to be updated.
  */
-static bool		isolated_cpus_updating;	/* RWCS */
+static bool		update_housekeeping;	/* RWCS */
 
 /*
  * A flag to force sched domain rebuild at the end of an operation.
@@ -1189,7 +1188,7 @@ static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus
 			return;
 		cpumask_andnot(isolated_cpus, isolated_cpus, xcpus);
 	}
-	isolated_cpus_updating = true;
+	update_housekeeping = true;
 }
 
 /*
@@ -1307,22 +1306,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_isolation_cpumasks - Update external isolation related CPU masks
+ * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
  *
- * The following external CPU masks will be updated if necessary:
- * - workqueue unbound cpumask
+ * Update housekeeping cpumasks and rebuild sched domains if necessary.
+ * This should be called at the end of cpuset or hotplug actions.
  */
-static void update_isolation_cpumasks(void)
+static void update_hk_sched_domains(void)
 {
-	int ret;
-
-	if (!isolated_cpus_updating)
-		return;
-
-	ret = housekeeping_update(isolated_cpus);
-	WARN_ON_ONCE(ret < 0);
-
-	isolated_cpus_updating = false;
+	if (update_housekeeping) {
+		/* Updating HK cpumasks implies rebuild sched domains */
+		WARN_ON_ONCE(housekeeping_update(isolated_cpus));
+		update_housekeeping = false;
+		force_sd_rebuild = true;
+	}
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
 }
 
 /**
@@ -1473,7 +1472,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	cs->remote_partition = true;
 	cpumask_copy(cs->effective_xcpus, tmp->new_cpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 	cs->prs_err = 0;
 
@@ -1518,7 +1516,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp)
 	compute_excpus(cs, cs->effective_xcpus);
 	reset_partition_data(cs);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	cpuset_force_rebuild();
 
 	/*
@@ -1589,7 +1586,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus,
 	if (xcpus)
 		cpumask_copy(cs->exclusive_cpus, xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 	if (adding || deleting)
 		cpuset_force_rebuild();
 
@@ -1933,7 +1929,6 @@ write_error:
 		partition_xcpus_add(new_prs, parent, tmp->delmask);
 
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	if ((old_prs != new_prs) && (cmd == partcmd_update))
 		update_partition_exclusive_flag(cs, new_prs);
@@ -2901,7 +2896,6 @@ out:
 	else if (isolcpus_updated)
 		isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus);
 	spin_unlock_irq(&callback_lock);
-	update_isolation_cpumasks();
 
 	/* Force update if switching back to member & update effective_xcpus */
 	update_cpumasks_hier(cs, &tmpmask, !new_prs);
@@ -3191,9 +3185,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	}
 
 	free_cpuset(trialcs);
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 out_unlock:
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
@@ -3301,6 +3294,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 	return retval ?: nbytes;
 }
@@ -3475,6 +3469,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
+	update_hk_sched_domains();
 	cpuset_full_unlock();
 }
 
@@ -3882,10 +3877,12 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-	/* rebuild sched domains if necessary */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_cpuslocked();
 
+	if (update_housekeeping || force_sd_rebuild) {
+		mutex_lock(&cpuset_mutex);
+		update_hk_sched_domains();
+		mutex_unlock(&cpuset_mutex);
+	}
 	free_tmpmasks(ptmp);
 }
 
-- 
cgit v1.2.3


From 6df415aa46ec10d607da5063d88492a7c7762074 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:17 -0500
Subject: cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to
 workqueue

The cpuset_handle_hotplug() may need to invoke housekeeping_update(),
for instance, when an isolated partition is invalidated because its
last active CPU has been put offline.

As we are going to enable dynamic update to the nozh_full housekeeping
cpumask (HK_TYPE_KERNEL_NOISE) soon with the help of CPU hotplug,
allowing the CPU hotplug path to call into housekeeping_update() directly
from update_isolation_cpumasks() will likely cause deadlock. So we
have to defer any call to housekeeping_update() after the CPU hotplug
operation has finished. This is now done via the workqueue where
the update_hk_sched_domains() function will be invoked via the
hk_sd_workfn().

An concurrent cpuset control file write may have executed the required
update_hk_sched_domains() function before the work function is called. So
the work function call may become a no-op when it is invoked.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c                            | 31 +++++++++++++++++++----
 tools/testing/selftests/cgroup/test_cpuset_prs.sh | 11 +++++++-
 2 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 14b07a283a2c..aa915e9b588f 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1324,6 +1324,16 @@ static void update_hk_sched_domains(void)
 		rebuild_sched_domains_locked();
 }
 
+/*
+ * Work function to invoke update_hk_sched_domains()
+ */
+static void hk_sd_workfn(struct work_struct *work)
+{
+	cpuset_full_lock();
+	update_hk_sched_domains();
+	cpuset_full_unlock();
+}
+
 /**
  * rm_siblings_excl_cpus - Remove exclusive CPUs that are used by sibling cpusets
  * @parent: Parent cpuset containing all siblings
@@ -3796,6 +3806,7 @@ unlock:
  */
 static void cpuset_handle_hotplug(void)
 {
+	static DECLARE_WORK(hk_sd_work, hk_sd_workfn);
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
@@ -3878,11 +3889,21 @@ static void cpuset_handle_hotplug(void)
 	}
 
 
-	if (update_housekeeping || force_sd_rebuild) {
-		mutex_lock(&cpuset_mutex);
-		update_hk_sched_domains();
-		mutex_unlock(&cpuset_mutex);
-	}
+	/*
+	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
+	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
+	 * cpumask can correctly reflect what is in isolated_cpus.
+	 *
+	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
+	 * is still pending. Before the pending bit is cleared, the work data
+	 * is copied out and work item dequeued. So it is possible to queue
+	 * the work again before the hk_sd_workfn() is invoked to process the
+	 * previously queued work. Since hk_sd_workfn() doesn't use the work
+	 * item at all, this is not a problem.
+	 */
+	if (update_housekeeping || force_sd_rebuild)
+		queue_work(system_unbound_wq, &hk_sd_work);
+
 	free_tmpmasks(ptmp);
 }
 
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index ef16f5610d0b..a56f4153c64d 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -245,6 +245,9 @@ TEST_MATRIX=(
 	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
 	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
 	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P2   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-2"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0   .      .     0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0  O3=1    .     0 A1:1-2|A2:3 A1:P1|A2:P2  3"
 	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
 	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
@@ -761,7 +764,7 @@ check_cgroup_states()
 # only CPUs in isolated partitions as well as those that are isolated at
 # boot time.
 #
-# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
 # <isolcpus1> - expected sched/domains value
 # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
 #
@@ -770,6 +773,7 @@ check_isolcpus()
 	EXPECTED_ISOLCPUS=$1
 	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
 	ISOLCPUS=$(cat $ISCPUS)
+	HKICPUS=$(cat /sys/devices/system/cpu/isolated)
 	LASTISOLCPU=
 	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
 	if [[ $EXPECTED_ISOLCPUS = . ]]
@@ -807,6 +811,11 @@ check_isolcpus()
 	ISOLCPUS=
 	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
 
+	#
+	# The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS
+	#
+	[[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1
+
 	#
 	# Use the sched domain in debugfs to check isolated CPUs, if available
 	#
-- 
cgit v1.2.3


From a84097e625f2b9e7f273161c004f34b7be63b348 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sat, 21 Feb 2026 13:54:18 -0500
Subject: cgroup/cpuset: Call housekeeping_update() without holding
 cpus_read_lock

The current cpuset partition code is able to dynamically update
the sched domains of a running system and the corresponding
HK_TYPE_DOMAIN housekeeping cpumask to perform what is essentially the
"isolcpus=domain,..." boot command line feature at run time.

The housekeeping cpumask update requires flushing a number of different
workqueues which may not be safe with cpus_read_lock() held as the
workqueue flushing code may acquire cpus_read_lock() or acquiring locks
which have locking dependency with cpus_read_lock() down the chain. Below
is an example of such circular locking problem.

  ======================================================
  WARNING: possible circular locking dependency detected
  6.18.0-test+ #2 Tainted: G S
  ------------------------------------------------------
  test_cpuset_prs/10971 is trying to acquire lock:
  ffff888112ba4958 ((wq_completion)sync_wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x7a/0x180

  but task is already holding lock:
  ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:
  -> #4 (cpuset_mutex){+.+.}-{4:4}:
  -> #3 (cpu_hotplug_lock){++++}-{0:0}:
  -> #2 (rtnl_mutex){+.+.}-{4:4}:
  -> #1 ((work_completion)(&arg.work)){+.+.}-{0:0}:
  -> #0 ((wq_completion)sync_wq){+.+.}-{0:0}:

  Chain exists of:
    (wq_completion)sync_wq --> cpu_hotplug_lock --> cpuset_mutex

  5 locks held by test_cpuset_prs/10971:
   #0: ffff88816810e440 (sb_writers#7){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0
   #1: ffff8891ab620890 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x260/0x5f0
   #2: ffff8890a78b83e8 (kn->active#187){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x2b6/0x5f0
   #3: ffffffffadf32900 (cpu_hotplug_lock){++++}-{0:0}, at: cpuset_partition_write+0x77/0x130
   #4: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130

  Call Trace:
   <TASK>
     :
   touch_wq_lockdep_map+0x93/0x180
   __flush_workqueue+0x111/0x10b0
   housekeeping_update+0x12d/0x2d0
   update_parent_effective_cpumask+0x595/0x2440
   update_prstate+0x89d/0xce0
   cpuset_partition_write+0xc5/0x130
   cgroup_file_write+0x1a5/0x680
   kernfs_fop_write_iter+0x3df/0x5f0
   vfs_write+0x525/0xfd0
   ksys_write+0xf9/0x1d0
   do_syscall_64+0x95/0x520
   entry_SYSCALL_64_after_hwframe+0x76/0x7e

To avoid such a circular locking dependency problem, we have to
call housekeeping_update() without holding the cpus_read_lock() and
cpuset_mutex. The current set of wq's flushed by housekeeping_update()
may not have work functions that call cpus_read_lock() directly,
but we are likely to extend the list of wq's that are flushed in the
future. Moreover, the current set of work functions may hold locks that
may have cpu_hotplug_lock down the dependency chain.

So housekeeping_update() is now called after releasing cpus_read_lock
and cpuset_mutex at the end of a cpuset operation. These two locks are
then re-acquired later before calling rebuild_sched_domains_locked().

To enable mutual exclusion between the housekeeping_update() call and
other cpuset control file write actions, a new top level cpuset_top_mutex
is introduced. This new mutex will be acquired first to allow sharing
variables used by both code paths. However, cpuset update from CPU
hotplug can still happen in parallel with the housekeeping_update()
call, though that should be rare in production environment.

As cpus_read_lock() is now no longer held when
tmigr_isolated_exclude_cpumask() is called, it needs to acquire it
directly.

The lockdep_is_cpuset_held() is also updated to return true if either
cpuset_top_mutex or cpuset_mutex is held.

Fixes: 03ff73510169 ("cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c        | 47 ++++++++++++++++++++++++++++++++++++++-----
 kernel/sched/isolation.c      |  4 +---
 kernel/time/timer_migration.c |  4 +---
 3 files changed, 44 insertions(+), 11 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index aa915e9b588f..aa45351c6f38 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -65,14 +65,28 @@ static const char * const perr_strings[] = {
  * CPUSET Locking Convention
  * -------------------------
  *
- * Below are the three global locks guarding cpuset structures in lock
+ * Below are the four global/local locks guarding cpuset structures in lock
  * acquisition order:
+ *  - cpuset_top_mutex
  *  - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock)
  *  - cpuset_mutex
  *  - callback_lock (raw spinlock)
  *
- * A task must hold all the three locks to modify externally visible or
- * used fields of cpusets, though some of the internally used cpuset fields
+ * As cpuset will now indirectly flush a number of different workqueues in
+ * housekeeping_update() to update housekeeping cpumasks when the set of
+ * isolated CPUs is going to be changed, it may be vulnerable to deadlock
+ * if we hold cpus_read_lock while calling into housekeeping_update().
+ *
+ * The first cpuset_top_mutex will be held except when calling into
+ * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock
+ * and cpuset_mutex will be held instead. The main purpose of this mutex
+ * is to prevent regular cpuset control file write actions from interfering
+ * with the call to housekeeping_update(), though CPU hotplug operation can
+ * still happen in parallel. This mutex also provides protection for some
+ * internal variables.
+ *
+ * A task must hold all the remaining three locks to modify externally visible
+ * or used fields of cpusets, though some of the internally used cpuset fields
  * and internal variables can be modified without holding callback_lock. If only
  * reliable read access of the externally used fields are needed, a task can
  * hold either cpuset_mutex or callback_lock which are exposed to other
@@ -100,6 +114,7 @@ static const char * const perr_strings[] = {
  * cpumasks and nodemasks.
  */
 
+static DEFINE_MUTEX(cpuset_top_mutex);
 static DEFINE_MUTEX(cpuset_mutex);
 
 /*
@@ -111,6 +126,8 @@ static DEFINE_MUTEX(cpuset_mutex);
  *
  * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable
  *	 by holding both cpuset_mutex and callback_lock.
+ *
+ * T:	 Read/write-able by holding the cpuset_top_mutex.
  */
 
 /*
@@ -134,6 +151,11 @@ static cpumask_var_t	isolated_cpus;		/* CSCB */
  */
 static bool		update_housekeeping;	/* RWCS */
 
+/*
+ * Copy of isolated_cpus to be passed to housekeeping_update()
+ */
+static cpumask_var_t	isolated_hk_cpus;	/* T */
+
 /*
  * A flag to force sched domain rebuild at the end of an operation.
  * It can be set in
@@ -297,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void)
  */
 void cpuset_full_lock(void)
 {
+	mutex_lock(&cpuset_top_mutex);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 }
@@ -305,12 +328,14 @@ void cpuset_full_unlock(void)
 {
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
+	mutex_unlock(&cpuset_top_mutex);
 }
 
 #ifdef CONFIG_LOCKDEP
 bool lockdep_is_cpuset_held(void)
 {
-	return lockdep_is_held(&cpuset_mutex);
+	return lockdep_is_held(&cpuset_mutex) ||
+	       lockdep_is_held(&cpuset_top_mutex);
 }
 #endif
 
@@ -1315,9 +1340,20 @@ static void update_hk_sched_domains(void)
 {
 	if (update_housekeeping) {
 		/* Updating HK cpumasks implies rebuild sched domains */
-		WARN_ON_ONCE(housekeeping_update(isolated_cpus));
 		update_housekeeping = false;
 		force_sd_rebuild = true;
+		cpumask_copy(isolated_hk_cpus, isolated_cpus);
+
+		/*
+		 * housekeeping_update() is now called without holding
+		 * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex
+		 * is still being held for mutual exclusion.
+		 */
+		mutex_unlock(&cpuset_mutex);
+		cpus_read_unlock();
+		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
+		cpus_read_lock();
+		mutex_lock(&cpuset_mutex);
 	}
 	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
 	if (force_sd_rebuild)
@@ -3635,6 +3671,7 @@ int __init cpuset_init(void)
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL));
 	BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 3b725d39c06e..ef152d401fe2 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask)
 	struct cpumask *trial, *old = NULL;
 	int err;
 
-	lockdep_assert_cpus_held();
-
 	trial = kmalloc(cpumask_size(), GFP_KERNEL);
 	if (!trial)
 		return -ENOMEM;
@@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask)
 	}
 
 	if (!housekeeping.flags)
-		static_branch_enable_cpuslocked(&housekeeping_overridden);
+		static_branch_enable(&housekeeping_overridden);
 
 	if (housekeeping.flags & HK_FLAG_DOMAIN)
 		old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN);
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 6da9cd562b20..83428aa03aef 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL;
 	int cpu;
 
-	lockdep_assert_cpus_held();
-
 	if (!works)
 		return -ENOMEM;
 	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
@@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask)
 	 * First set previously isolated CPUs as available (unisolate).
 	 * This cpumask contains only CPUs that switched to available now.
 	 */
+	guard(cpus_read_lock)();
 	cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask);
 	cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask);
 
@@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void)
 	cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 	/* Protect against RCU torture hotplug testing */
-	guard(cpus_read_lock)();
 	return tmigr_isolated_exclude_cpumask(cpumask);
 }
 late_initcall(tmigr_init_isolation);
-- 
cgit v1.2.3


From 7cff9a40c6b0f72ccefdaf0ffe03cfac30348f51 Mon Sep 17 00:00:00 2001
From: Mariusz Skamra <mariusz.skamra@codecoup.pl>
Date: Thu, 12 Feb 2026 14:46:46 +0100
Subject: Bluetooth: Fix CIS host feature condition

This fixes the condition for sending the LE Set Host Feature command.
The command is sent to indicate host support for Connected Isochronous
Streams in this case. It has been observed that the system could not
initialize BIS-only capable controllers because the controllers do not
support the command.

As per Core v6.2 | Vol 4, Part E, Table 3.1 the command shall be
supported if CIS Central or CIS Peripheral is supported; otherwise,
the command is optional.

Fixes: 709788b154ca ("Bluetooth: hci_core: Fix using {cis,bis}_capable for current settings")
Cc: stable@vger.kernel.org
Signed-off-by: Mariusz Skamra <mariusz.skamra@codecoup.pl>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index f04a90bce4a9..0b0dc0965f5a 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4592,7 +4592,7 @@ static int hci_le_set_host_features_sync(struct hci_dev *hdev)
 {
 	int err;
 
-	if (iso_capable(hdev)) {
+	if (cis_capable(hdev)) {
 		/* Connected Isochronous Channels (Host Support) */
 		err = hci_le_set_host_feature_sync(hdev, 32,
 						   (iso_enabled(hdev) ? 0x01 :
-- 
cgit v1.2.3


From a8d1d73c81d1e70d2aa49fdaf59d933bb783ffe5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 17 Feb 2026 13:29:43 -0500
Subject: Bluetooth: L2CAP: Fix not checking output MTU is acceptable on
 L2CAP_ECRED_CONN_REQ

Upon receiving L2CAP_ECRED_CONN_REQ the given MTU shall be checked
against the suggested MTU of the listening socket as that is required
by the likes of PTS L2CAP/ECFC/BV-27-C test which expects
L2CAP_CR_LE_UNACCEPT_PARAMS if the MTU is lowers than socket omtu.

In order to be able to set chan->omtu the code now allows setting
setsockopt(BT_SNDMTU), but it is only allowed when connection has not
been stablished since there is no procedure to reconfigure the output
MTU.

Link: https://github.com/bluez/bluez/issues/1895
Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c |  8 ++++++++
 net/bluetooth/l2cap_sock.c | 15 +++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9452c6179acb..90676ca0e92b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5117,6 +5117,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		goto unlock;
 	}
 
+	/* Check if the listening channel has set an output MTU then the
+	 * requested MTU shall be less than or equal to that value.
+	 */
+	if (pchan->omtu && mtu < pchan->omtu) {
+		result = L2CAP_CR_LE_UNACCEPT_PARAMS;
+		goto unlock;
+	}
+
 	result = L2CAP_CR_LE_SUCCESS;
 
 	for (i = 0; i < num_scid; i++) {
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 62ceda979f39..477b4d145459 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1029,10 +1029,17 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 			break;
 		}
 
-		/* Setting is not supported as it's the remote side that
-		 * decides this.
-		 */
-		err = -EPERM;
+		/* Only allow setting output MTU when not connected */
+		if (sk->sk_state == BT_CONNECTED) {
+			err = -EISCONN;
+			break;
+		}
+
+		err = copy_safe_from_sockptr(&mtu, sizeof(mtu), optval, optlen);
+		if (err)
+			break;
+
+		chan->omtu = mtu;
 		break;
 
 	case BT_RCVMTU:
-- 
cgit v1.2.3


From 138d7eca445ef37a0333425d269ee59900ca1104 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 13 Feb 2026 13:33:33 -0500
Subject: Bluetooth: L2CAP: Fix missing key size check for L2CAP_LE_CONN_REQ

This adds a check for encryption key size upon receiving
L2CAP_LE_CONN_REQ which is required by L2CAP/LE/CFC/BV-15-C which
expects L2CAP_CR_LE_BAD_KEY_SIZE.

Link: https://lore.kernel.org/linux-bluetooth/5782243.rdbgypaU67@n9w6sw14/
Fixes: 27e2d4c8d28b ("Bluetooth: Add basic LE L2CAP connect request receiving support")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Tested-by: Christian Eggers <ceggers@arri.de>
---
 net/bluetooth/l2cap_core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 90676ca0e92b..2dcc5bb907b8 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4916,6 +4916,13 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
 		goto response_unlock;
 	}
 
+	/* Check if Key Size is sufficient for the security level */
+	if (!l2cap_check_enc_key_size(conn->hcon, pchan)) {
+		result = L2CAP_CR_LE_BAD_KEY_SIZE;
+		chan = NULL;
+		goto response_unlock;
+	}
+
 	/* Check for valid dynamic CID range */
 	if (scid < L2CAP_CID_DYN_START || scid > L2CAP_CID_LE_DYN_END) {
 		result = L2CAP_CR_LE_INVALID_SCID;
-- 
cgit v1.2.3


From 5839419cffc7788a356428d321e3ec18055c0286 Mon Sep 17 00:00:00 2001
From: Christoffer Sandberg <cs@tuxedo.de>
Date: Mon, 23 Feb 2026 15:20:45 +0100
Subject: Input: i8042 - add TUXEDO InfinityBook Max 16 Gen10 AMD to i8042
 quirk table

The device occasionally wakes up from suspend with missing input on the
internal keyboard and the following suspend attempt results in an instant
wake-up. The quirks fix both issues for this device.

Signed-off-by: Christoffer Sandberg <cs@tuxedo.de>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://patch.msgid.link/20260223142054.50310-1-wse@tuxedocomputers.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index d2cf940b105a..8ebdf4fb9030 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1187,6 +1187,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "X6KK45xU_X6SP45xU"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "WUJIE Series-X5SP4NAG"),
-- 
cgit v1.2.3


From 1bfd7575092420ba5a0b944953c95b74a5646ff8 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 19 Feb 2026 23:35:18 +0000
Subject: drm/xe/sync: Cleanup partially initialized sync on parse failure

xe_sync_entry_parse() can allocate references (syncobj, fence, chain fence,
or user fence) before hitting a later failure path. Several of those paths
returned directly, leaving partially initialized state and leaking refs.

Route these error paths through a common free_sync label and call
xe_sync_entry_cleanup(sync) before returning the error.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260219233516.2938172-5-shuicheng.lin@intel.com
(cherry picked from commit f939bdd9207a5d1fc55cced5459858480686ce22)
Cc: stable@vger.kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sync.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index eb136390dafd..ebf6c96d7a41 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -146,8 +146,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 
 		if (!signal) {
 			sync->fence = drm_syncobj_fence_get(sync->syncobj);
-			if (XE_IOCTL_DBG(xe, !sync->fence))
-				return -EINVAL;
+			if (XE_IOCTL_DBG(xe, !sync->fence)) {
+				err = -EINVAL;
+				goto free_sync;
+			}
 		}
 		break;
 
@@ -167,17 +169,21 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 
 		if (signal) {
 			sync->chain_fence = dma_fence_chain_alloc();
-			if (!sync->chain_fence)
-				return -ENOMEM;
+			if (!sync->chain_fence) {
+				err = -ENOMEM;
+				goto free_sync;
+			}
 		} else {
 			sync->fence = drm_syncobj_fence_get(sync->syncobj);
-			if (XE_IOCTL_DBG(xe, !sync->fence))
-				return -EINVAL;
+			if (XE_IOCTL_DBG(xe, !sync->fence)) {
+				err = -EINVAL;
+				goto free_sync;
+			}
 
 			err = dma_fence_chain_find_seqno(&sync->fence,
 							 sync_in.timeline_value);
 			if (err)
-				return err;
+				goto free_sync;
 		}
 		break;
 
@@ -216,6 +222,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 	sync->timeline_value = sync_in.timeline_value;
 
 	return 0;
+
+free_sync:
+	xe_sync_entry_cleanup(sync);
+	return err;
 }
 ALLOW_ERROR_INJECTION(xe_sync_entry_parse, ERRNO);
 
-- 
cgit v1.2.3


From 0879c3f04f67e2a1677c25dcc24669ce21eb6a6c Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 19 Feb 2026 23:35:19 +0000
Subject: drm/xe/sync: Fix user fence leak on alloc failure

When dma_fence_chain_alloc() fails, properly release the user fence
reference to prevent a memory leak.

Fixes: 0995c2fc39b0 ("drm/xe: Enforce correct user fence signaling order using")
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260219233516.2938172-6-shuicheng.lin@intel.com
(cherry picked from commit a5d5634cde48a9fcd68c8504aa07f89f175074a0)
Cc: stable@vger.kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sync.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index ebf6c96d7a41..24d6d9af20d6 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -206,8 +206,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef,
 			if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence)))
 				return PTR_ERR(sync->ufence);
 			sync->ufence_chain_fence = dma_fence_chain_alloc();
-			if (!sync->ufence_chain_fence)
-				return -ENOMEM;
+			if (!sync->ufence_chain_fence) {
+				err = -ENOMEM;
+				goto free_sync;
+			}
 			sync->ufence_syncobj = ufence_syncobj;
 		}
 
-- 
cgit v1.2.3


From 96a7b71c4438d3b72d6c95e3efdc9e8e8aee6b78 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 23 Feb 2026 13:43:45 -0800
Subject: ubd: Use pointer-to-pointers for io_thread_req arrays

Having an unbounded array for irq_req_buffer and io_req_buffer doesn't
provide any bounds safety, and confuses the needed allocation type,
which is returning a pointer to pointers. Instead of the implicit cast,
switch the variable types.

Reported-by: Nathan Chancellor <nathan@kernel.org>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/all/b04b6c13-7d0e-4a89-9e68-b572b6c686ac@roeck-us.net
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Acked-by: Richard Weinberger <richard@nod.at>
Link: https://patch.msgid.link/20260223214341.work.846-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/um/drivers/ubd_kern.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 012b2bcaa8a0..20fc33300a95 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -69,11 +69,11 @@ struct io_thread_req {
 };
 
 
-static struct io_thread_req * (*irq_req_buffer)[];
+static struct io_thread_req **irq_req_buffer;
 static struct io_thread_req *irq_remainder;
 static int irq_remainder_size;
 
-static struct io_thread_req * (*io_req_buffer)[];
+static struct io_thread_req **io_req_buffer;
 static struct io_thread_req *io_remainder;
 static int io_remainder_size;
 
@@ -398,7 +398,7 @@ static int thread_fd = -1;
 
 static int bulk_req_safe_read(
 	int fd,
-	struct io_thread_req * (*request_buffer)[],
+	struct io_thread_req **request_buffer,
 	struct io_thread_req **remainder,
 	int *remainder_size,
 	int max_recs
@@ -465,7 +465,7 @@ static irqreturn_t ubd_intr(int irq, void *dev)
 			&irq_remainder, &irq_remainder_size,
 			UBD_REQ_BUFFER_SIZE)) >= 0) {
 		for (i = 0; i < len / sizeof(struct io_thread_req *); i++)
-			ubd_end_request((*irq_req_buffer)[i]);
+			ubd_end_request(irq_req_buffer[i]);
 	}
 
 	if (len < 0 && len != -EAGAIN)
@@ -1512,7 +1512,7 @@ void *io_thread(void *arg)
 		}
 
 		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
-			struct io_thread_req *req = (*io_req_buffer)[count];
+			struct io_thread_req *req = io_req_buffer[count];
 			int i;
 
 			io_count++;
-- 
cgit v1.2.3


From f709859f331b8fbd7fede5769d668008fc5ba789 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 23 Feb 2026 11:23:12 -0700
Subject: init/Kconfig: Adjust fixed clang version for __builtin_counted_by_ref

Commit d39a1d7486d9 ("compiler_types: Disable __builtin_counted_by_ref
for Clang") used 22.0.0 as the fixed version for a compiler crash but
the fix was only merged in main (23.0.0) and release/22.x (22.1.0). With
the current fixed version number, prerelease or Android LLVM 22 builds
will still be able to hit the compiler crash when building the kernel.
This can be particularly disruptive when bisecting LLVM.

Use 21.1.0 as the fixed version number to ensure the fix for this crash
is always present.

Fixes: d39a1d7486d9 ("compiler_types: Disable __builtin_counted_by_ref for Clang")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20260223-fix-clang-version-builtin-counted-by-ref-v1-1-3ea478a24f0a@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index c25869cf59c1..b55deae9256c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -153,7 +153,7 @@ config CC_HAS_COUNTED_BY_PTR
 config CC_HAS_BROKEN_COUNTED_BY_REF
 	bool
 	# https://github.com/llvm/llvm-project/issues/182575
-	default y if CC_IS_CLANG && CLANG_VERSION < 220000
+	default y if CC_IS_CLANG && CLANG_VERSION < 220100
 
 config CC_HAS_MULTIDIMENSIONAL_NONSTRING
 	def_bool $(success,echo 'char tag[][4] __attribute__((__nonstring__)) = { };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror)
-- 
cgit v1.2.3


From 7adaaee5edd35a423ae199c41b86bd1ed60ed483 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 15:05:15 -0800
Subject: Input: synaptics-rmi4 - fix a locking bug in an error path

Lock f54->data_mutex when entering the function statement since jumping
to the 'error' label when checking report_size fails causes that mutex
to be unlocked.

This bug has been detected by the Clang thread-safety checker.

Fixes: 3a762dbd5347 ("[media] Input: synaptics-rmi4 - add support for F54 diagnostics")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223215118.2154194-16-bvanassche@acm.org
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/rmi4/rmi_f54.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/rmi4/rmi_f54.c b/drivers/input/rmi4/rmi_f54.c
index ac4041a69fcd..61909e1a39e2 100644
--- a/drivers/input/rmi4/rmi_f54.c
+++ b/drivers/input/rmi4/rmi_f54.c
@@ -538,6 +538,8 @@ static void rmi_f54_work(struct work_struct *work)
 	int error;
 	int i;
 
+	mutex_lock(&f54->data_mutex);
+
 	report_size = rmi_f54_get_report_size(f54);
 	if (report_size == 0) {
 		dev_err(&fn->dev, "Bad report size, report type=%d\n",
@@ -546,8 +548,6 @@ static void rmi_f54_work(struct work_struct *work)
 		goto error;     /* retry won't help */
 	}
 
-	mutex_lock(&f54->data_mutex);
-
 	/*
 	 * Need to check if command has completed.
 	 * If not try again later.
-- 
cgit v1.2.3


From a9dece60cc8246e5fc4c46d391272024bf1d309d Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Sat, 24 Jan 2026 06:32:56 +0530
Subject: drm/msm/adreno: Add GPU to MODULE_DEVICE_TABLE

Since it is possible to independently probe Adreno GPU, add GPU match
table to MODULE_DEVICE_TABLE to allow auto-loading of msm module.

Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/700656/
Link: https://lore.kernel.org/r/20260124-adreno-module-table-v1-1-9c2dbb2638b4@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 554d746f115b..4edfe80c5be7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -302,6 +302,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,kgsl-3d0" },
 	{}
 };
+MODULE_DEVICE_TABLE(of, dt_match);
 
 static int adreno_runtime_resume(struct device *dev)
 {
-- 
cgit v1.2.3


From f7bf1319739291067b2bc4b22bd56336afad8f0a Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Tue, 27 Jan 2026 11:58:49 +0100
Subject: drm/msm/dpu: Fix LM size on a number of platforms

The register space has grown with what seems to be DPU8.
Bump up the .len to match.

Fixes: e3b1f369db5a ("drm/msm/dpu: Add X1E80100 support")
Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP")
Fixes: efcd0107727c ("drm/msm/dpu: add support for SM8550")
Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450")
Fixes: 178575173472 ("drm/msm/dpu: add catalog entry for SAR2130P")
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/701063/
Link: https://lore.kernel.org/r/20260127-topic-lm_size_fix-v1-1-25f88d014dfd@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h   | 12 ++++++------
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h   | 12 ++++++------
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h | 12 ++++++------
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h | 12 ++++++------
 5 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
index 303d33dc7783..9f2bceca1789 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h
@@ -133,7 +133,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = {
 static const struct dpu_lm_cfg sc8280xp_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -141,7 +141,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -149,7 +149,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -157,7 +157,7 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -165,14 +165,14 @@ static const struct dpu_lm_cfg sc8280xp_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
index b09a6af4c474..04b22167f93d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h
@@ -134,7 +134,7 @@ static const struct dpu_sspp_cfg sm8450_sspp[] = {
 static const struct dpu_lm_cfg sm8450_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -142,7 +142,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -150,7 +150,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -158,7 +158,7 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -166,14 +166,14 @@ static const struct dpu_lm_cfg sm8450_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
index 465b6460f875..4c7eb55d474c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h
@@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = {
 static const struct dpu_lm_cfg sm8550_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sm8550_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
index 6caa7d40f368..dec83ea8167d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h
@@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sar2130p_sspp[] = {
 static const struct dpu_lm_cfg sar2130p_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -139,7 +139,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -147,7 +147,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -155,7 +155,7 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -163,14 +163,14 @@ static const struct dpu_lm_cfg sar2130p_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
index 7243eebb85f3..52ff4baa668a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
@@ -130,7 +130,7 @@ static const struct dpu_sspp_cfg x1e80100_sspp[] = {
 static const struct dpu_lm_cfg x1e80100_lm[] = {
 	{
 		.name = "lm_0", .id = LM_0,
-		.base = 0x44000, .len = 0x320,
+		.base = 0x44000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_1,
@@ -138,7 +138,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_0,
 	}, {
 		.name = "lm_1", .id = LM_1,
-		.base = 0x45000, .len = 0x320,
+		.base = 0x45000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_0,
@@ -146,7 +146,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_1,
 	}, {
 		.name = "lm_2", .id = LM_2,
-		.base = 0x46000, .len = 0x320,
+		.base = 0x46000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_3,
@@ -154,7 +154,7 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_2,
 	}, {
 		.name = "lm_3", .id = LM_3,
-		.base = 0x47000, .len = 0x320,
+		.base = 0x47000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_2,
@@ -162,14 +162,14 @@ static const struct dpu_lm_cfg x1e80100_lm[] = {
 		.dspp = DSPP_3,
 	}, {
 		.name = "lm_4", .id = LM_4,
-		.base = 0x48000, .len = 0x320,
+		.base = 0x48000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_5,
 		.pingpong = PINGPONG_4,
 	}, {
 		.name = "lm_5", .id = LM_5,
-		.base = 0x49000, .len = 0x320,
+		.base = 0x49000, .len = 0x400,
 		.features = MIXER_MSM8998_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.lm_pair = LM_4,
-- 
cgit v1.2.3


From 6f6f3535192dd597c5326ea5456ae3bafc7d43b2 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 6 Feb 2026 14:21:52 -0800
Subject: drm/msm: Adjust msm_iommu_pagetable_prealloc_allocate() allocation
 type

In preparation for making the kmalloc family of allocators type aware,
we need to make sure that the returned type from the allocation matches
the type of the variable being assigned. (Before, the allocator would
always return "void *", which can be implicitly cast to any pointer type.)

The assigned type is "void **" but the returned type will be "void ***".
These are the same allocation size (pointer size), but the types do not
match. Adjust the allocation type to match the assignment.

Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/703588/
Link: https://lore.kernel.org/r/20260206222151.work.016-kees@kernel.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index d5dede4ff761..271baf4dc4e8 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -332,7 +332,7 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall
 	struct kmem_cache *pt_cache = get_pt_cache(mmu);
 	int ret;
 
-	p->pages = kvmalloc_array(p->count, sizeof(p->pages), GFP_KERNEL);
+	p->pages = kvmalloc_array(p->count, sizeof(*p->pages), GFP_KERNEL);
 	if (!p->pages)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From b1dcc804f4662256a3e4bd8ac182a7a2c9464723 Mon Sep 17 00:00:00 2001
From: sunliming <sunliming@kylinos.cn>
Date: Fri, 30 Jan 2026 13:36:15 +0800
Subject: drm/msm/dpu: Fix smatch warnings about variable dereferenced before
 check

Fix below smatch warnings:
drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c:161 dpu_hw_sspp_setup_pe_config_v13()
warn: variable dereferenced before check 'ctx' (see line 159)

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601252214.oEaY3UZM-lkp@intel.com/
Signed-off-by: sunliming <sunliming@kylinos.cn>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/701853/
Link: https://lore.kernel.org/r/20260130053615.24886-1-sunliming@linux.dev
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
index e65f1fc026fd..f8f96ad971d7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp_v13.c
@@ -156,11 +156,13 @@ static void dpu_hw_sspp_setup_pe_config_v13(struct dpu_hw_sspp *ctx,
 	u8 color;
 	u32 lr_pe[4], tb_pe[4];
 	const u32 bytemask = 0xff;
-	u32 offset = ctx->cap->sblk->sspp_rec0_blk.base;
+	u32 offset;
 
 	if (!ctx || !pe_ext)
 		return;
 
+	offset = ctx->cap->sblk->sspp_rec0_blk.base;
+
 	c = &ctx->hw;
 	/* program SW pixel extension override for all pipes*/
 	for (color = 0; color < DPU_MAX_PLANES; color++) {
-- 
cgit v1.2.3


From 9f593419eb42c68f31829aed3c199591190bfe5d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Sat, 14 Feb 2026 01:02:59 +0200
Subject: Revert "drm/msm/dpu: try reserving the DSPP-less LM first"

This reverts commit 42f62cd79578 ("drm/msm/dpu: try reserving the
DSPP-less LM first"). It seems on later DPUs using higher LMs require
some additional setup or conflicts with the hardware defaults. Val (and
other developers) reported blue screen on Hamoa (X1E80100) laptops.
Revert the offending commit until we understand, what is the issue.

Fixes: 42f62cd79578 ("drm/msm/dpu: try reserving the DSPP-less LM first")
Reported-by: Val Packett <val@packett.cool>
Closes: https://lore.kernel.org/r/33424a9d-10a6-4479-bba6-12f8ce60da1a@packett.cool
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Tested-by: Manivannan Sadhasivam <mani@kernel.org> # T14s
Patchwork: https://patchwork.freedesktop.org/patch/704814/
Link: https://lore.kernel.org/r/20260214-revert-dspp-less-v1-1-be0d636a2a6e@oss.qualcomm.com
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c | 52 +++++++++-------------------------
 1 file changed, 14 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index 451a4fcf3e65..7e77d88f8959 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -350,26 +350,28 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm,
 	return true;
 }
 
-static bool dpu_rm_find_lms(struct dpu_rm *rm,
-			    struct dpu_global_state *global_state,
-			    uint32_t crtc_id, bool skip_dspp,
-			    struct msm_display_topology *topology,
-			    int *lm_idx, int *pp_idx, int *dspp_idx)
+static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
+			       struct dpu_global_state *global_state,
+			       uint32_t crtc_id,
+			       struct msm_display_topology *topology)
 
 {
+	int lm_idx[MAX_BLOCKS];
+	int pp_idx[MAX_BLOCKS];
+	int dspp_idx[MAX_BLOCKS] = {0};
 	int i, lm_count = 0;
 
+	if (!topology->num_lm) {
+		DPU_ERROR("zero LMs in topology\n");
+		return -EINVAL;
+	}
+
 	/* Find a primary mixer */
 	for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) &&
 			lm_count < topology->num_lm; i++) {
 		if (!rm->mixer_blks[i])
 			continue;
 
-		if (skip_dspp && to_dpu_hw_mixer(rm->mixer_blks[i])->cap->dspp) {
-			DPU_DEBUG("Skipping LM_%d, skipping LMs with DSPPs\n", i);
-			continue;
-		}
-
 		/*
 		 * Reset lm_count to an even index. This will drop the previous
 		 * primary mixer if failed to find its peer.
@@ -408,38 +410,12 @@ static bool dpu_rm_find_lms(struct dpu_rm *rm,
 		}
 	}
 
-	return lm_count == topology->num_lm;
-}
-
-static int _dpu_rm_reserve_lms(struct dpu_rm *rm,
-			       struct dpu_global_state *global_state,
-			       uint32_t crtc_id,
-			       struct msm_display_topology *topology)
-
-{
-	int lm_idx[MAX_BLOCKS];
-	int pp_idx[MAX_BLOCKS];
-	int dspp_idx[MAX_BLOCKS] = {0};
-	int i;
-	bool found;
-
-	if (!topology->num_lm) {
-		DPU_ERROR("zero LMs in topology\n");
-		return -EINVAL;
-	}
-
-	/* Try using non-DSPP LM blocks first */
-	found = dpu_rm_find_lms(rm, global_state, crtc_id, !topology->num_dspp,
-				topology, lm_idx, pp_idx, dspp_idx);
-	if (!found && !topology->num_dspp)
-		found = dpu_rm_find_lms(rm, global_state, crtc_id, false,
-					topology, lm_idx, pp_idx, dspp_idx);
-	if (!found) {
+	if (lm_count != topology->num_lm) {
 		DPU_DEBUG("unable to find appropriate mixers\n");
 		return -ENAVAIL;
 	}
 
-	for (i = 0; i < topology->num_lm; i++) {
+	for (i = 0; i < lm_count; i++) {
 		global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id;
 		global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id;
 		global_state->dspp_to_crtc_id[dspp_idx[i]] =
-- 
cgit v1.2.3


From 5886cc8f895bf578903eb681fca9123065e1012e Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Mon, 23 Feb 2026 08:16:55 +0100
Subject: drm/msm/dpu: Don't use %pK through printk (again)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past %pK was preferable to %p as it would not leak raw pointer
values into the kernel log.
Since commit ad67b74d2469 ("printk: hash addresses printed with %p")
the regular %p has been improved to avoid this issue.
Furthermore, restricted pointers ("%pK") were never meant to be used
through printk(). They can still unintentionally leak raw pointers or
acquire sleeping locks in atomic contexts.

Switch to the regular pointer formatting which is safer and
easier to reason about.

This was previously fixed in this driver in commit 1ba9fbe40337
("drm/msm: Don't use %pK through printk") but an additional usage
was reintroduced in commit 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC
driver to provide GAMMA_LUT DRM property")

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Fixes: 39a750ff5fc9 ("drm/msm/dpu: Add DSPP GC driver to provide GAMMA_LUT DRM property")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/706229/
Link: https://lore.kernel.org/r/20260223-restricted-pointers-msm-v1-1-14c0b451e372@linutronix.de
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
index 188ee0af2c90..23dcbe1ce1b8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
@@ -89,7 +89,7 @@ static void dpu_setup_dspp_gc(struct dpu_hw_dspp *ctx,
 	base = ctx->cap->sblk->gc.base;
 
 	if (!base) {
-		DRM_ERROR("invalid ctx %pK gc base\n", ctx);
+		DRM_ERROR("invalid ctx %p gc base\n", ctx);
 		return;
 	}
 
-- 
cgit v1.2.3


From 4ced4cf5c9d172d91f181df3accdf949d3761aab Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@google.com>
Date: Tue, 17 Feb 2026 18:01:05 +0000
Subject: binfmt_elf_fdpic: fix AUXV size calculation for ELF_HWCAP3 and
 ELF_HWCAP4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 4e6e8c2b757f ("binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4") added
support for AT_HWCAP3 and AT_HWCAP4, but it missed updating the AUX
vector size calculation in create_elf_fdpic_tables() and
AT_VECTOR_SIZE_BASE in include/linux/auxvec.h.

Similar to the fix for AT_HWCAP2 in commit c6a09e342f8e ("binfmt_elf_fdpic:
fix AUXV size calculation when ELF_HWCAP2 is defined"), this omission
leads to a mismatch between the reserved space and the actual number of
AUX entries, eventually triggering a kernel BUG_ON(csp != sp).

Fix this by incrementing nitems when ELF_HWCAP3 or ELF_HWCAP4 are
defined and updating AT_VECTOR_SIZE_BASE.

Cc: Mark Brown <broonie@kernel.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com>
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@futurfusion.io>
Fixes: 4e6e8c2b757f ("binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4")
Signed-off-by: Andrei Vagin <avagin@google.com>
Link: https://patch.msgid.link/20260217180108.1420024-2-avagin@google.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 fs/binfmt_elf_fdpic.c  | 6 ++++++
 include/linux/auxvec.h | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 95b1d0852135..95b65aab7daa 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -595,6 +595,12 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 #ifdef ELF_HWCAP2
 	nitems++;
 #endif
+#ifdef ELF_HWCAP3
+	nitems++;
+#endif
+#ifdef ELF_HWCAP4
+	nitems++;
+#endif
 
 	csp = sp;
 	sp -= nitems * 2 * sizeof(unsigned long);
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 407f7005e6d6..8bcb9b726262 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -4,6 +4,6 @@
 
 #include <uapi/linux/auxvec.h>
 
-#define AT_VECTOR_SIZE_BASE 22 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 24 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif /* _LINUX_AUXVEC_H */
-- 
cgit v1.2.3


From eddb98ad9364b4e778768785d46cfab04ce52100 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 20 Feb 2026 13:43:00 +0900
Subject: ata: libata-eh: correctly handle deferred qc timeouts

A deferred qc may timeout while waiting for the device queue to drain
to be submitted. In such case, since the qc is not active,
ata_scsi_cmd_error_handler() ends up calling scsi_eh_finish_cmd(),
which frees the qc. But as the port deferred_qc field still references
this finished/freed qc, the deferred qc work may eventually attempt to
call ata_qc_issue() against this invalid qc, leading to errors such as
reported by UBSAN (syzbot run):

UBSAN: shift-out-of-bounds in drivers/ata/libata-core.c:5166:24
shift exponent 4210818301 is too large for 64-bit type 'long long unsigned int'
...
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x100/0x190 lib/dump_stack.c:120
 ubsan_epilogue+0xa/0x30 lib/ubsan.c:233
 __ubsan_handle_shift_out_of_bounds+0x279/0x2a0 lib/ubsan.c:494
 ata_qc_issue.cold+0x38/0x9f drivers/ata/libata-core.c:5166
 ata_scsi_deferred_qc_work+0x154/0x1f0 drivers/ata/libata-scsi.c:1679
 process_one_work+0x9d7/0x1920 kernel/workqueue.c:3275
 process_scheduled_works kernel/workqueue.c:3358 [inline]
 worker_thread+0x5da/0xe40 kernel/workqueue.c:3439
 kthread+0x370/0x450 kernel/kthread.c:467
 ret_from_fork+0x754/0xd80 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

Fix this by checking if the qc of a timed out SCSI command is a deferred
one, and in such case, clear the port deferred_qc field and finish the
SCSI command with DID_TIME_OUT.

Reported-by: syzbot+1f77b8ca15336fff21ff@syzkaller.appspotmail.com
Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
---
 drivers/ata/libata-eh.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 72a22b6c9682..b373cceb95d2 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -640,12 +640,28 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		set_host_byte(scmd, DID_OK);
 
 		ata_qc_for_each_raw(ap, qc, i) {
-			if (qc->flags & ATA_QCFLAG_ACTIVE &&
-			    qc->scsicmd == scmd)
+			if (qc->scsicmd != scmd)
+				continue;
+			if ((qc->flags & ATA_QCFLAG_ACTIVE) ||
+			    qc == ap->deferred_qc)
 				break;
 		}
 
-		if (i < ATA_MAX_QUEUE) {
+		if (qc == ap->deferred_qc) {
+			/*
+			 * This is a deferred command that timed out while
+			 * waiting for the command queue to drain. Since the qc
+			 * is not active yet (deferred_qc is still set, so the
+			 * deferred qc work has not issued the command yet),
+			 * simply signal the timeout by finishing the SCSI
+			 * command and clear the deferred qc to prevent the
+			 * deferred qc work from issuing this qc.
+			 */
+			WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE);
+			ap->deferred_qc = NULL;
+			set_host_byte(scmd, DID_TIME_OUT);
+			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
+		} else if (i < ATA_MAX_QUEUE) {
 			/* the scmd has an associated qc */
 			if (!(qc->flags & ATA_QCFLAG_EH)) {
 				/* which hasn't failed yet, timeout */
-- 
cgit v1.2.3


From 55db009926634b20955bd8abbee921adbc8d2cb4 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 20 Feb 2026 12:09:12 +0900
Subject: ata: libata-core: fix cancellation of a port deferred qc work

cancel_work_sync() is a sleeping function so it cannot be called with
the spin lock of a port being held. Move the call to this function in
ata_port_detach() after EH completes, with the port lock released,
together with other work cancellation calls.

Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
---
 drivers/ata/libata-core.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 11909417f017..ccbf320524da 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6269,10 +6269,6 @@ static void ata_port_detach(struct ata_port *ap)
 		}
 	}
 
-	/* Make sure the deferred qc work finished. */
-	cancel_work_sync(&ap->deferred_qc_work);
-	WARN_ON(ap->deferred_qc);
-
 	/* Tell EH to disable all devices */
 	ap->pflags |= ATA_PFLAG_UNLOADING;
 	ata_port_schedule_eh(ap);
@@ -6283,9 +6279,11 @@ static void ata_port_detach(struct ata_port *ap)
 	/* wait till EH commits suicide */
 	ata_port_wait_eh(ap);
 
-	/* it better be dead now */
+	/* It better be dead now and not have any remaining deferred qc. */
 	WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED));
+	WARN_ON(ap->deferred_qc);
 
+	cancel_work_sync(&ap->deferred_qc_work);
 	cancel_delayed_work_sync(&ap->hotplug_task);
 	cancel_delayed_work_sync(&ap->scsi_rescan_task);
 
-- 
cgit v1.2.3


From 41e09ec73d7431dffda01b1e7208a272a5c90fb9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 20 Feb 2026 17:18:58 -0800
Subject: MAINTAINERS: include all of framer under pef2256

The "framer" infrastructure only has one driver - pef2256
and is not covered by any MAINTAINERS entry of its own.
This leads to author not being CCed on patches.
Let's include all of framer/ under the pef2256 entry.
We can split it in the very unlikely event of another
driver appearing.

Link: https://lore.kernel.org/aZefB5f3EAkQQM1m@google.com
Acked-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260221011858.3403605-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c00b5f5d4203..e1a6c6cc2b7c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14410,9 +14410,9 @@ LANTIQ PEF2256 DRIVER
 M:	Herve Codina <herve.codina@bootlin.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/lantiq,pef2256.yaml
-F:	drivers/net/wan/framer/pef2256/
+F:	drivers/net/wan/framer/
 F:	drivers/pinctrl/pinctrl-pef2256.c
-F:	include/linux/framer/pef2256.h
+F:	include/linux/framer/
 
 LASI 53c700 driver for PARISC
 M:	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
-- 
cgit v1.2.3


From 8a8a9fac9efa6423fd74938b940cb7d731780718 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Feb 2026 22:26:05 +0000
Subject: net: do not pass flow_id to set_rps_cpu()

Blamed commit made the assumption that the RPS table for each receive
queue would have the same size, and that it would not change.

Compute flow_id in set_rps_cpu(), do not assume we can use the value
computed by get_rps_cpu(). Otherwise we risk out-of-bound access
and/or crashes.

Fixes: 48aa30443e52 ("net: Cache hash and flow_id to avoid recalculation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Krishna Kumar <krikku@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260220222605.3468081-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 096b3ff13f6b..f3426385f1ba 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4992,8 +4992,7 @@ static bool rps_flow_is_active(struct rps_dev_flow *rflow,
 
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
-	    struct rps_dev_flow *rflow, u16 next_cpu, u32 hash,
-	    u32 flow_id)
+	    struct rps_dev_flow *rflow, u16 next_cpu, u32 hash)
 {
 	if (next_cpu < nr_cpu_ids) {
 		u32 head;
@@ -5004,6 +5003,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		struct rps_dev_flow *tmp_rflow;
 		unsigned int tmp_cpu;
 		u16 rxq_index;
+		u32 flow_id;
 		int rc;
 
 		/* Should we steer this flow to a different hardware queue? */
@@ -5019,6 +5019,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		if (!flow_table)
 			goto out;
 
+		flow_id = rfs_slot(hash, flow_table);
 		tmp_rflow = &flow_table->flows[flow_id];
 		tmp_cpu = READ_ONCE(tmp_rflow->cpu);
 
@@ -5066,7 +5067,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_map *map;
 	int cpu = -1;
-	u32 flow_id;
 	u32 tcpu;
 	u32 hash;
 
@@ -5113,8 +5113,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		/* OK, now we know there is a match,
 		 * we can look at the local (per receive queue) flow table
 		 */
-		flow_id = rfs_slot(hash, flow_table);
-		rflow = &flow_table->flows[flow_id];
+		rflow = &flow_table->flows[rfs_slot(hash, flow_table)];
 		tcpu = rflow->cpu;
 
 		/*
@@ -5133,8 +5132,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		     ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
-			rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash,
-					    flow_id);
+			rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash);
 		}
 
 		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
-- 
cgit v1.2.3


From 7bb09315f93dce6acc54bf59e5a95ba7365c2be4 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 20 Feb 2026 18:40:36 +0900
Subject: tls: Fix race condition in tls_sw_cancel_work_tx()

This issue was discovered during a code audit.

After cancel_delayed_work_sync() is called from tls_sk_proto_close(),
tx_work_handler() can still be scheduled from paths such as the
Delayed ACK handler or ksoftirqd.
As a result, the tx_work_handler() worker may dereference a freed
TLS object.

The following is a simple race scenario:

          cpu0                         cpu1

tls_sk_proto_close()
  tls_sw_cancel_work_tx()
                                 tls_write_space()
                                   tls_sw_write_space()
                                     if (!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
    set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
    cancel_delayed_work_sync(&ctx->tx_work.work);
                                     schedule_delayed_work(&tx_ctx->tx_work.work, 0);

To prevent this race condition, cancel_delayed_work_sync() is
replaced with disable_delayed_work_sync().

Fixes: f87e62d45e51 ("net/tls: remove close callback sock unlock/lock around TX work flush")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/aZgsFO6nfylfvLE7@v4bel
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9937d4c810f2..b1fa62de9dab 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2533,7 +2533,7 @@ void tls_sw_cancel_work_tx(struct tls_context *tls_ctx)
 
 	set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask);
 	set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
-	cancel_delayed_work_sync(&ctx->tx_work.work);
+	disable_delayed_work_sync(&ctx->tx_work.work);
 }
 
 void tls_sw_release_resources_tx(struct sock *sk)
-- 
cgit v1.2.3


From fb868db5f4bccd7a78219313ab2917429f715cea Mon Sep 17 00:00:00 2001
From: Ankit Garg <nktgrg@google.com>
Date: Fri, 20 Feb 2026 13:53:24 -0800
Subject: gve: fix incorrect buffer cleanup in gve_tx_clean_pending_packets for
 QPL

In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA
buffer cleanup path. It iterates num_bufs times and attempts to unmap
entries in the dma array.

This leads to two issues:
1. The dma array shares storage with tx_qpl_buf_ids (union).
 Interpreting buffer IDs as DMA addresses results in attempting to
 unmap incorrect memory locations.
2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed
 the size of the dma array, causing out-of-bounds access warnings
(trace below is how we noticed this issue).

UBSAN: array-index-out-of-bounds in
drivers/net/ethernet/drivers/net/ethernet/google/gve/gve_tx_dqo.c:178:5 index 18 is out of
range for type 'dma_addr_t[18]' (aka 'unsigned long long[18]')
Workqueue: gve gve_service_task [gve]
Call Trace:
<TASK>
dump_stack_lvl+0x33/0xa0
__ubsan_handle_out_of_bounds+0xdc/0x110
gve_tx_stop_ring_dqo+0x182/0x200 [gve]
gve_close+0x1be/0x450 [gve]
gve_reset+0x99/0x120 [gve]
gve_service_task+0x61/0x100 [gve]
process_scheduled_works+0x1e9/0x380

Fix this by properly checking for QPL mode and delegating to
gve_free_tx_qpl_bufs() to reclaim the buffers.

Cc: stable@vger.kernel.org
Fixes: a6fb8d5a8b69 ("gve: Tx path for DQO-QPL")
Signed-off-by: Ankit Garg <nktgrg@google.com>
Reviewed-by: Jordan Rhee <jordanrhee@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220215324.1631350-1-joshwash@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_tx_dqo.c | 56 +++++++++++++---------------
 1 file changed, 25 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 28e85730f785..b57e8f13cb51 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -167,6 +167,25 @@ gve_free_pending_packet(struct gve_tx_ring *tx,
 	}
 }
 
+static void gve_unmap_packet(struct device *dev,
+			     struct gve_tx_pending_packet_dqo *pkt)
+{
+	int i;
+
+	if (!pkt->num_bufs)
+		return;
+
+	/* SKB linear portion is guaranteed to be mapped */
+	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
+			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
+	for (i = 1; i < pkt->num_bufs; i++) {
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
+	}
+	pkt->num_bufs = 0;
+}
+
 /* gve_tx_free_desc - Cleans up all pending tx requests and buffers.
  */
 static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
@@ -176,21 +195,12 @@ static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
 	for (i = 0; i < tx->dqo.num_pending_packets; i++) {
 		struct gve_tx_pending_packet_dqo *cur_state =
 			&tx->dqo.pending_packets[i];
-		int j;
-
-		for (j = 0; j < cur_state->num_bufs; j++) {
-			if (j == 0) {
-				dma_unmap_single(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			} else {
-				dma_unmap_page(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			}
-		}
+
+		if (tx->dqo.qpl)
+			gve_free_tx_qpl_bufs(tx, cur_state);
+		else
+			gve_unmap_packet(tx->dev, cur_state);
+
 		if (cur_state->skb) {
 			dev_consume_skb_any(cur_state->skb);
 			cur_state->skb = NULL;
@@ -1157,22 +1167,6 @@ static void remove_from_list(struct gve_tx_ring *tx,
 	}
 }
 
-static void gve_unmap_packet(struct device *dev,
-			     struct gve_tx_pending_packet_dqo *pkt)
-{
-	int i;
-
-	/* SKB linear portion is guaranteed to be mapped */
-	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
-			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
-	for (i = 1; i < pkt->num_bufs; i++) {
-		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
-					    dma_unmap_len(pkt, len[i]),
-					    DMA_TO_DEVICE, 0);
-	}
-	pkt->num_bufs = 0;
-}
-
 /* Completion types and expected behavior:
  * No Miss compl + Packet compl = Packet completed normally.
  * Miss compl + Re-inject compl = Packet completed normally.
-- 
cgit v1.2.3


From ca220141fa8ebae09765a242076b2b77338106b0 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 19 Feb 2026 09:42:51 +0800
Subject: kcm: fix zero-frag skb in frag_list on partial sendmsg error

Syzkaller reported a warning in kcm_write_msgs() when processing a
message with a zero-fragment skb in the frag_list.

When kcm_sendmsg() fills MAX_SKB_FRAGS fragments in the current skb,
it allocates a new skb (tskb) and links it into the frag_list before
copying data. If the copy subsequently fails (e.g. -EFAULT from
user memory), tskb remains in the frag_list with zero fragments:

  head skb (msg being assembled, NOT yet in sk_write_queue)
  +-----------+
  | frags[17] |  (MAX_SKB_FRAGS, all filled with data)
  | frag_list-+--> tskb
  +-----------+    +----------+
                   | frags[0] |  (empty! copy failed before filling)
                   +----------+

For SOCK_SEQPACKET with partial data already copied, the error path
saves this message via partial_message for later completion. For
SOCK_SEQPACKET, sock_write_iter() automatically sets MSG_EOR, so a
subsequent zero-length write(fd, NULL, 0) completes the message and
queues it to sk_write_queue. kcm_write_msgs() then walks the
frag_list and hits:

  WARN_ON(!skb_shinfo(skb)->nr_frags)

TCP has a similar pattern where skbs are enqueued before data copy
and cleaned up on failure via tcp_remove_empty_skb(). KCM was
missing the equivalent cleanup.

Fix this by tracking the predecessor skb (frag_prev) when allocating
a new frag_list entry. On error, if the tail skb has zero frags,
use frag_prev to unlink and free it in O(1) without walking the
singly-linked frag_list. frag_prev is safe to dereference because
the entire message chain is only held locally (or in kcm->seq_skb)
and is not added to sk_write_queue until MSG_EOR, so the send path
cannot free it underneath us.

Also change the WARN_ON to WARN_ON_ONCE to avoid flooding the log
if the condition is somehow hit repeatedly.

There are currently no KCM selftests in the kernel tree; a simple
reproducer is available at [1].

[1] https://gist.github.com/mrpre/a94d431c757e8d6f168f4dd1a3749daa

Reported-by: syzbot+52624bdfbf2746d37d70@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/000000000000269a1405a12fdc77@google.com/T/
Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260219014256.370092-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/kcm/kcmsock.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 5dd7e0509a48..3912e75079f5 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -628,7 +628,7 @@ retry:
 			skb = txm->frag_skb;
 		}
 
-		if (WARN_ON(!skb_shinfo(skb)->nr_frags) ||
+		if (WARN_ON_ONCE(!skb_shinfo(skb)->nr_frags) ||
 		    WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
 			ret = -EINVAL;
 			goto out;
@@ -749,7 +749,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct kcm_sock *kcm = kcm_sk(sk);
-	struct sk_buff *skb = NULL, *head = NULL;
+	struct sk_buff *skb = NULL, *head = NULL, *frag_prev = NULL;
 	size_t copy, copied = 0;
 	long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 	int eor = (sock->type == SOCK_DGRAM) ?
@@ -824,6 +824,7 @@ start:
 				else
 					skb->next = tskb;
 
+				frag_prev = skb;
 				skb = tskb;
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 				continue;
@@ -933,6 +934,22 @@ partial_message:
 out_error:
 	kcm_push(kcm);
 
+	/* When MAX_SKB_FRAGS was reached, a new skb was allocated and
+	 * linked into the frag_list before data copy. If the copy
+	 * subsequently failed, this skb has zero frags. Remove it from
+	 * the frag_list to prevent kcm_write_msgs from later hitting
+	 * WARN_ON(!skb_shinfo(skb)->nr_frags).
+	 */
+	if (frag_prev && !skb_shinfo(skb)->nr_frags) {
+		if (head == frag_prev)
+			skb_shinfo(head)->frag_list = NULL;
+		else
+			frag_prev->next = NULL;
+		kfree_skb(skb);
+		/* Update skb as it may be saved in partial_message via goto */
+		skb = frag_prev;
+	}
+
 	if (sock->type == SOCK_SEQPACKET) {
 		/* Wrote some bytes before encountering an
 		 * error, return partial success.
-- 
cgit v1.2.3


From 4cfe066a82cdf9e83e48b16000f55280efc98325 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Fri, 20 Feb 2026 16:57:54 +0100
Subject: dpll: zl3073x: fix REF_PHASE_OFFSET_COMP register width for some chip
 IDs

The REF_PHASE_OFFSET_COMP register is 48-bit wide on most zl3073x chip
variants, but only 32-bit wide on chip IDs 0x0E30, 0x0E93..0x0E97 and
0x1F60. The driver unconditionally uses 48-bit read/write operations,
which on 32-bit variants causes reading 2 bytes past the register
boundary (corrupting the value) and writing 2 bytes into the adjacent
register.

Fix this by storing the chip ID in the device structure during probe
and adding a helper to detect the affected variants. Use the correct
register width for read/write operations and the matching sign extension
bit (31 vs 47) when interpreting the phase compensation value.

Fixes: 6287262f761e ("dpll: zl3073x: Add support to adjust phase")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220155755.448185-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/zl3073x/core.c |  1 +
 drivers/dpll/zl3073x/core.h | 28 ++++++++++++++++++++++++++++
 drivers/dpll/zl3073x/dpll.c |  7 +++++--
 drivers/dpll/zl3073x/ref.c  | 25 ++++++++++++++++++++-----
 drivers/dpll/zl3073x/regs.h |  1 +
 5 files changed, 55 insertions(+), 7 deletions(-)

diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c
index 63bd97181b9e..8c5ee28e02f4 100644
--- a/drivers/dpll/zl3073x/core.c
+++ b/drivers/dpll/zl3073x/core.c
@@ -1026,6 +1026,7 @@ int zl3073x_dev_probe(struct zl3073x_dev *zldev,
 				     "Unknown or non-match chip ID: 0x%0x\n",
 				     id);
 	}
+	zldev->chip_id = id;
 
 	/* Read revision, firmware version and custom config version */
 	rc = zl3073x_read_u16(zldev, ZL_REG_REVISION, &revision);
diff --git a/drivers/dpll/zl3073x/core.h b/drivers/dpll/zl3073x/core.h
index dddfcacea5c0..fd2af3c62a7d 100644
--- a/drivers/dpll/zl3073x/core.h
+++ b/drivers/dpll/zl3073x/core.h
@@ -35,6 +35,7 @@ struct zl3073x_dpll;
  * @dev: pointer to device
  * @regmap: regmap to access device registers
  * @multiop_lock: to serialize multiple register operations
+ * @chip_id: chip ID read from hardware
  * @ref: array of input references' invariants
  * @out: array of outs' invariants
  * @synth: array of synths' invariants
@@ -48,6 +49,7 @@ struct zl3073x_dev {
 	struct device		*dev;
 	struct regmap		*regmap;
 	struct mutex		multiop_lock;
+	u16			chip_id;
 
 	/* Invariants */
 	struct zl3073x_ref	ref[ZL3073X_NUM_REFS];
@@ -144,6 +146,32 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev,
 
 int zl3073x_ref_phase_offsets_update(struct zl3073x_dev *zldev, int channel);
 
+/**
+ * zl3073x_dev_is_ref_phase_comp_32bit - check ref phase comp register size
+ * @zldev: pointer to zl3073x device
+ *
+ * Some chip IDs have a 32-bit wide ref_phase_offset_comp register instead
+ * of the default 48-bit.
+ *
+ * Return: true if the register is 32-bit, false if 48-bit
+ */
+static inline bool
+zl3073x_dev_is_ref_phase_comp_32bit(struct zl3073x_dev *zldev)
+{
+	switch (zldev->chip_id) {
+	case 0x0E30:
+	case 0x0E93:
+	case 0x0E94:
+	case 0x0E95:
+	case 0x0E96:
+	case 0x0E97:
+	case 0x1F60:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline bool
 zl3073x_is_n_pin(u8 id)
 {
diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c
index 78edc36b17fb..8ffbede117c6 100644
--- a/drivers/dpll/zl3073x/dpll.c
+++ b/drivers/dpll/zl3073x/dpll.c
@@ -475,8 +475,11 @@ zl3073x_dpll_input_pin_phase_adjust_get(const struct dpll_pin *dpll_pin,
 	ref_id = zl3073x_input_pin_ref_get(pin->id);
 	ref = zl3073x_ref_state_get(zldev, ref_id);
 
-	/* Perform sign extension for 48bit signed value */
-	phase_comp = sign_extend64(ref->phase_comp, 47);
+	/* Perform sign extension based on register width */
+	if (zl3073x_dev_is_ref_phase_comp_32bit(zldev))
+		phase_comp = sign_extend64(ref->phase_comp, 31);
+	else
+		phase_comp = sign_extend64(ref->phase_comp, 47);
 
 	/* Reverse two's complement negation applied during set and convert
 	 * to 32bit signed int
diff --git a/drivers/dpll/zl3073x/ref.c b/drivers/dpll/zl3073x/ref.c
index aa2de13effa8..6b65e6103999 100644
--- a/drivers/dpll/zl3073x/ref.c
+++ b/drivers/dpll/zl3073x/ref.c
@@ -121,8 +121,16 @@ int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index)
 		return rc;
 
 	/* Read phase compensation register */
-	rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
-			      &ref->phase_comp);
+	if (zl3073x_dev_is_ref_phase_comp_32bit(zldev)) {
+		u32 val;
+
+		rc = zl3073x_read_u32(zldev, ZL_REG_REF_PHASE_OFFSET_COMP_32,
+				      &val);
+		ref->phase_comp = val;
+	} else {
+		rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
+				      &ref->phase_comp);
+	}
 	if (rc)
 		return rc;
 
@@ -179,9 +187,16 @@ int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index,
 	if (!rc && dref->sync_ctrl != ref->sync_ctrl)
 		rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL,
 				      ref->sync_ctrl);
-	if (!rc && dref->phase_comp != ref->phase_comp)
-		rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP,
-				       ref->phase_comp);
+	if (!rc && dref->phase_comp != ref->phase_comp) {
+		if (zl3073x_dev_is_ref_phase_comp_32bit(zldev))
+			rc = zl3073x_write_u32(zldev,
+					       ZL_REG_REF_PHASE_OFFSET_COMP_32,
+					       ref->phase_comp);
+		else
+			rc = zl3073x_write_u48(zldev,
+					       ZL_REG_REF_PHASE_OFFSET_COMP,
+					       ref->phase_comp);
+	}
 	if (rc)
 		return rc;
 
diff --git a/drivers/dpll/zl3073x/regs.h b/drivers/dpll/zl3073x/regs.h
index d837bee72b17..5573d7188406 100644
--- a/drivers/dpll/zl3073x/regs.h
+++ b/drivers/dpll/zl3073x/regs.h
@@ -194,6 +194,7 @@
 #define ZL_REF_CONFIG_DIFF_EN			BIT(2)
 
 #define ZL_REG_REF_PHASE_OFFSET_COMP		ZL_REG(10, 0x28, 6)
+#define ZL_REG_REF_PHASE_OFFSET_COMP_32	ZL_REG(10, 0x28, 4)
 
 #define ZL_REG_REF_SYNC_CTRL			ZL_REG(10, 0x2e, 1)
 #define ZL_REF_SYNC_CTRL_MODE			GENMASK(2, 0)
-- 
cgit v1.2.3


From 3aa677625c8fad39989496c51bcff3872c1f16f1 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.quang.nguyen@est.tech>
Date: Fri, 20 Feb 2026 05:05:41 +0000
Subject: tipc: fix duplicate publication key in tipc_service_insert_publ()

TIPC uses named table to store TIPC services represented by type and
instance. Each time an application calls TIPC API bind() to bind a
type/instance to a socket, an entry is created and inserted into the
named table. It looks like this:

named table:
key1, entry1 (type, instance ...)
key2, entry2 (type, instance ...)

In the above table, each entry represents a route for sending data
from one socket to the other. For all publications originated from
the same node, the key is UNIQUE to identify each entry.
It is calculated by this formula:
key = socket portid + number of bindings + 1 (1)

where:
 - socket portid: unique and calculated by using linux kernel function
                  get_random_u32_below(). So, the value is randomized.
 - number of bindings: the number of times a type/instance pair is bound
                       to a socket. This number is linearly increased,
                       starting from 0.

While the socket portid is unique and randomized by linux kernel, the
linear increment of "number of bindings" in formula (1) makes "key" not
unique anymore. For example:
- Socket 1 is created with its associated port number 20062001. Type 1000,
instance 1 is bound to socket 1:
key1: 20062001 + 0 + 1 = 20062002

Then, bind() is called a second time on Socket 1 to by the same type 1000,
instance 1:
key2: 20062001 + 1 + 1 = 20062003

Named table:
key1 (20062002), entry1 (1000, 1 ...)
key2 (20062003), entry2 (1000, 1 ...)

- Socket 2 is created with its associated port number 20062002. Type 1000,
instance 1 is bound to socket 2:
key3: 20062002 + 0 + 1 = 20062003

TIPC looks up the named table and finds out that key2 with the same value
already exists and rejects the insertion into the named table.
This leads to failure of bind() call from application on Socket 2 with error
message EINVAL "Invalid argument".

This commit fixes this issue by adding more port id checking to make sure
that the key is unique to publications originated from the same port id
and node.

Fixes: 218527fe27ad ("tipc: replace name table service range array with rb tree")
Signed-off-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260220050541.237962-1-tung.quang.nguyen@est.tech
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/name_table.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index e74940eab3a4..7f42fb6a8481 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -348,7 +348,8 @@ static bool tipc_service_insert_publ(struct net *net,
 
 	/* Return if the publication already exists */
 	list_for_each_entry(_p, &sr->all_publ, all_publ) {
-		if (_p->key == key && (!_p->sk.node || _p->sk.node == node)) {
+		if (_p->key == key && _p->sk.ref == p->sk.ref &&
+		    (!_p->sk.node || _p->sk.node == node)) {
 			pr_debug("Failed to bind duplicate %u,%u,%u/%u:%u/%u\n",
 				 p->sr.type, p->sr.lower, p->sr.upper,
 				 node, p->sk.ref, key);
@@ -388,7 +389,8 @@ static struct publication *tipc_service_remove_publ(struct service_range *r,
 	u32 node = sk->node;
 
 	list_for_each_entry(p, &r->all_publ, all_publ) {
-		if (p->key != key || (node && node != p->sk.node))
+		if (p->key != key || p->sk.ref != sk->ref ||
+		    (node && node != p->sk.node))
 			continue;
 		list_del(&p->all_publ);
 		list_del(&p->local_publ);
-- 
cgit v1.2.3


From 63c49efc987afefc6b9bb7de083eb8748e0b1789 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:17 -0800
Subject: selftests/bpf: Add simple strscpy() implementation

Replace bpf_strlcpy() in bpf_util.h with a sized_strscpy(), which is a
simplified sized_strscpy() from the kernel (lib/string.c [1]). It:
  * takes a count (destination size) parameter
  * guarantees NULL-termination
  * returns the number of characters copied or -E2BIG

Re-define strscpy macro similar to in-kernel implementation [2]: allow
the count parameter to be optional.

Add #ifdef-s to tools/include/linux/args.h, as they may be defined in
other system headers (for example, __CONCAT in sys/cdefs.h).

Fixup the single existing bpf_strlcpy() call in cgroup_helpers.c

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/lib/string.c?h=v6.19#n113
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/linux/string.h?h=v6.19#n91

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-2-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/linux/args.h                   |  4 +++
 tools/testing/selftests/bpf/bpf_util.h       | 45 ++++++++++++++++++++--------
 tools/testing/selftests/bpf/cgroup_helpers.c |  2 +-
 3 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h
index 2e8e65d975c7..14b268f2389a 100644
--- a/tools/include/linux/args.h
+++ b/tools/include/linux/args.h
@@ -22,7 +22,11 @@
 #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
 
 /* Concatenate two parameters, but allow them to be expanded beforehand. */
+#ifndef __CONCAT
 #define __CONCAT(a, b) a ## b
+#endif
+#ifndef CONCATENATE
 #define CONCATENATE(a, b) __CONCAT(a, b)
+#endif
 
 #endif	/* _LINUX_ARGS_H */
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 4bc2d25f33e1..6cb56501a505 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <syscall.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
+#include <linux/args.h>
 
 static inline unsigned int bpf_num_possible_cpus(void)
 {
@@ -21,25 +22,43 @@ static inline unsigned int bpf_num_possible_cpus(void)
 	return possible_cpus;
 }
 
-/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst
- * is zero-terminated string no matter what (unless sz == 0, in which case
- * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs
- * in what is returned. Given this is internal helper, it's trivial to extend
- * this, when necessary. Use this instead of strncpy inside libbpf source code.
+/*
+ * Simplified strscpy() implementation. The kernel one is in lib/string.c
  */
-static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
+static inline ssize_t sized_strscpy(char *dest, const char *src, size_t count)
 {
-	size_t i;
+	long res = 0;
 
-	if (sz == 0)
-		return;
+	if (count == 0)
+		return -E2BIG;
 
-	sz--;
-	for (i = 0; i < sz && src[i]; i++)
-		dst[i] = src[i];
-	dst[i] = '\0';
+	while (count > 1) {
+		char c;
+
+		c = src[res];
+		dest[res] = c;
+		if (!c)
+			return res;
+		res++;
+		count--;
+	}
+
+	/* Force NUL-termination. */
+	dest[res] = '\0';
+
+	/* Return E2BIG if the source didn't stop */
+	return src[res] ? -E2BIG : res;
 }
 
+#define __strscpy0(dst, src, ...)	\
+	sized_strscpy(dst, src, sizeof(dst))
+#define __strscpy1(dst, src, size)	\
+	sized_strscpy(dst, src, size)
+
+#undef strscpy /* Redefine the placeholder from tools/include/linux/string.h */
+#define strscpy(dst, src, ...)	\
+	CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__)
+
 #define __bpf_percpu_val_align	__attribute__((__aligned__(8)))
 
 #define BPF_DECLARE_PERCPU(type, name)				\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 20cede4db3ce..45cd0b479fe3 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -86,7 +86,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers
 		enable[len] = 0;
 		close(fd);
 	} else {
-		bpf_strlcpy(enable, controllers, sizeof(enable));
+		strscpy(enable, controllers);
 	}
 
 	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
-- 
cgit v1.2.3


From 6a087ac23f5b6619033ad08e60c355b00bb8ce51 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:18 -0800
Subject: selftests/bpf: Replace strcpy() calls with strscpy()

strcpy() does not perform bounds checking and is considered deprecated
[1]. Replace strcpy() calls with strscpy() defined in bpf_util.h.

[1] https://docs.kernel.org/process/deprecated.html#strcpy

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-3-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c           | 2 +-
 tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c     | 2 +-
 tools/testing/selftests/bpf/prog_tests/setget_sockopt.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/sockopt_sk.c     | 2 +-
 tools/testing/selftests/bpf/prog_tests/test_veristat.c  | 4 ++--
 tools/testing/selftests/bpf/xdp_features.c              | 3 ++-
 6 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 0a6a5561bed3..5374b7e16d53 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -432,7 +432,7 @@ int make_sockaddr(int family, const char *addr_str, __u16 port,
 		memset(addr, 0, sizeof(*sun));
 		sun->sun_family = family;
 		sun->sun_path[0] = 0;
-		strcpy(sun->sun_path + 1, addr_str);
+		strscpy(sun->sun_path + 1, addr_str, sizeof(sun->sun_path) - 1);
 		if (len)
 			*len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str);
 		return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index b7d1b52309d0..f829b6f09bc9 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -281,7 +281,7 @@ static void test_dctcp_fallback(void)
 	dctcp_skel = bpf_dctcp__open();
 	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
 		return;
-	strcpy(dctcp_skel->rodata->fallback_cc, "cubic");
+	strscpy(dctcp_skel->rodata->fallback_cc, "cubic");
 	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
 		goto done;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index e4dac529d424..77fe1bfb7504 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -212,7 +212,7 @@ void test_setget_sockopt(void)
 	if (!ASSERT_OK_PTR(skel, "open skel"))
 		goto done;
 
-	strcpy(skel->rodata->veth, "binddevtest1");
+	strscpy(skel->rodata->veth, "binddevtest1");
 	skel->rodata->veth_ifindex = if_nametoindex("binddevtest1");
 	if (!ASSERT_GT(skel->rodata->veth_ifindex, 0, "if_nametoindex"))
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index ba6b3ec1156a..53637431ec5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -142,7 +142,7 @@ static int getsetsockopt(void)
 
 	/* TCP_CONGESTION can extend the string */
 
-	strcpy(buf.cc, "nv");
+	strscpy(buf.cc, "nv");
 	err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv"));
 	if (err) {
 		log_err("Failed to call setsockopt(TCP_CONGESTION)");
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
index b38c16b4247f..9aff08ac55c0 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -24,9 +24,9 @@ static struct fixture *init_fixture(void)
 
 	/* for no_alu32 and cpuv4 veristat is in parent folder */
 	if (access("./veristat", F_OK) == 0)
-		strcpy(fix->veristat, "./veristat");
+		strscpy(fix->veristat, "./veristat");
 	else if (access("../veristat", F_OK) == 0)
-		strcpy(fix->veristat, "../veristat");
+		strscpy(fix->veristat, "../veristat");
 	else
 		PRINT_FAIL("Can't find veristat binary");
 
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
index 595c79141cf3..a27ed663967c 100644
--- a/tools/testing/selftests/bpf/xdp_features.c
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -16,6 +16,7 @@
 
 #include <network_helpers.h>
 
+#include "bpf_util.h"
 #include "xdp_features.skel.h"
 #include "xdp_features.h"
 
@@ -212,7 +213,7 @@ static void set_env_default(void)
 	env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
 	env.feature.action = -EINVAL;
 	env.ifindex = -ENODEV;
-	strcpy(env.ifname, "unknown");
+	strscpy(env.ifname, "unknown");
 	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT,
 		      &env.dut_ctrl_addr, NULL);
 	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT,
-- 
cgit v1.2.3


From ac47870fd795549f03d57e0879fc730c79119f4b Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Sat, 14 Feb 2026 18:51:28 +0800
Subject: drm/msm/dsi: fix hdisplay calculation when programming dsi registers

Recently, the hdisplay calculation is working for 3:1 compressed ratio
only. If we have a video panel with DSC BPP = 8, and BPC = 10, we still
use the default bits_per_pclk = 24, then we get the wrong hdisplay. We
can draw the conclusion by cross-comparing the calculation with the
calculation in dsi_adjust_pclk_for_compression().

Since CMD mode does not use this, we can remove
!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) safely.

Fixes: efcbd6f9cdeb ("drm/msm/dsi: Enable widebus for DSI")
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/704822/
Link: https://lore.kernel.org/r/20260214105145.105308-1-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index e0de545d4077..e8e83ee61eb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -993,7 +993,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 	if (msm_host->dsc) {
 		struct drm_dsc_config *dsc = msm_host->dsc;
-		u32 bytes_per_pclk;
+		u32 bits_per_pclk;
 
 		/* update dsc params with timing params */
 		if (!dsc || !mode->hdisplay || !mode->vdisplay) {
@@ -1015,7 +1015,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 
 		/*
 		 * DPU sends 3 bytes per pclk cycle to DSI. If widebus is
-		 * enabled, bus width is extended to 6 bytes.
+		 * enabled, MDP always sends out 48-bit compressed data per
+		 * pclk and on average, DSI consumes an amount of compressed
+		 * data equivalent to the uncompressed pixel depth per pclk.
 		 *
 		 * Calculate the number of pclks needed to transmit one line of
 		 * the compressed data.
@@ -1027,12 +1029,12 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi)
 		 * unused anyway.
 		 */
 		h_total -= hdisplay;
-		if (wide_bus_enabled && !(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO))
-			bytes_per_pclk = 6;
+		if (wide_bus_enabled)
+			bits_per_pclk = mipi_dsi_pixel_format_to_bpp(msm_host->format);
 		else
-			bytes_per_pclk = 3;
+			bits_per_pclk = 24;
 
-		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc), bytes_per_pclk);
+		hdisplay = DIV_ROUND_UP(msm_dsc_get_bytes_per_line(msm_host->dsc) * 8, bits_per_pclk);
 
 		h_total += hdisplay;
 		ha_end = ha_start + hdisplay;
-- 
cgit v1.2.3


From 5f3518d77419255f8b12bb23c8ec22acbeb6bc5b Mon Sep 17 00:00:00 2001
From: Julius Lehmann <lehmanju@devpi.de>
Date: Sat, 14 Feb 2026 20:34:21 +0100
Subject: HID: magicmouse: fix battery reporting for Apple Magic Trackpad 2

Battery reporting does not work for the Apple Magic Trackpad 2 if it is
connected via USB. The current hid descriptor fixup code checks for a
hid descriptor length of exactly 83 bytes. If the hid descriptor is
larger, which is the case for newer apple mice, the fixup is not
applied.

This fix checks for hid descriptor sizes greater/equal 83 bytes which
applies the fixup for newer devices as well.

Signed-off-by: Julius Lehmann <lehmanju@devpi.de>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-magicmouse.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 17908d52c027..9eadf3252d0d 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -990,7 +990,7 @@ static const __u8 *magicmouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	 */
 	if ((is_usb_magicmouse2(hdev->vendor, hdev->product) ||
 	     is_usb_magictrackpad2(hdev->vendor, hdev->product)) &&
-	    *rsize == 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
+	    *rsize >= 83 && rdesc[46] == 0x84 && rdesc[58] == 0x85) {
 		hid_info(hdev,
 			 "fixing up magicmouse battery report descriptor\n");
 		*rsize = *rsize - 1;
-- 
cgit v1.2.3


From a2e70a89fa58133521b2deae4427d35776bda935 Mon Sep 17 00:00:00 2001
From: Ian Ray <ian.ray@gehealthcare.com>
Date: Tue, 17 Feb 2026 13:51:51 +0200
Subject: HID: multitouch: new class MT_CLS_EGALAX_P80H84

Fixes: f9e82295eec1 ("HID: multitouch: add eGalaxTouch P80H84 support")
Signed-off-by: Ian Ray <ian.ray@gehealthcare.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-multitouch.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 7daa8f6d8187..8052b35bfd7d 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -233,6 +233,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_SMART_TECH			0x0113
 #define MT_CLS_APPLE_TOUCHBAR			0x0114
 #define MT_CLS_YOGABOOK9I			0x0115
+#define MT_CLS_EGALAX_P80H84			0x0116
 #define MT_CLS_SIS				0x0457
 
 #define MT_DEFAULT_MAXCONTACT	10
@@ -438,6 +439,11 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_YOGABOOK9I,
 		.export_all_inputs = true
 	},
+	{ .name = MT_CLS_EGALAX_P80H84,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_CONTACT_CNT_ACCURATE,
+	},
 	{ }
 };
 
@@ -2215,8 +2221,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_EGALAX_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C000) },
-	{ .driver_data = MT_CLS_EGALAX,
-		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+	{ .driver_data = MT_CLS_EGALAX_P80H84,
+		HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },
 
 	/* Elan devices */
-- 
cgit v1.2.3


From b4f4fd947a2a6df7cf1f530dd1028d9f3849eff5 Mon Sep 17 00:00:00 2001
From: Alex Tran <alex.t.tran@gmail.com>
Date: Sat, 31 Jan 2026 15:57:43 -0800
Subject: selftests: hid: tests: test_wacom_generic: add tests for display
 devices and opaque devices

Verify Wacom devices set INPUT_PROP_DIRECT on display devices and
INPUT_PROP_POINTER on opaque devices. Verify INPUT_PROP_POINTER
is not set on display devices and INPUT_PROP_DIRECT is not set
on opaque devices.

Moved test_prop_pointer into TestOpaqueTablet. Created a
DirectTabletTest mixin class for test_prop_direct that can be
inherited by display tablet test classes.Used DirectTabletTest
for TestDTH2452Tablet case.

Signed-off-by: Alex Tran <alex.t.tran@gmail.com>
Tested-by: Erin Skomra <erin.skomra@wacom.com>
Reviewed-by: Erin Skomra <erin.skomra@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 .../selftests/hid/tests/test_wacom_generic.py      | 34 +++++++++++++---------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/hid/tests/test_wacom_generic.py b/tools/testing/selftests/hid/tests/test_wacom_generic.py
index 2d6d04f0ff80..3903f479b15b 100644
--- a/tools/testing/selftests/hid/tests/test_wacom_generic.py
+++ b/tools/testing/selftests/hid/tests/test_wacom_generic.py
@@ -598,18 +598,6 @@ class BaseTest:
                 if unit_set:
                     assert required[usage].contains(field)
 
-        def test_prop_direct(self):
-            """
-            Todo: Verify that INPUT_PROP_DIRECT is set on display devices.
-            """
-            pass
-
-        def test_prop_pointer(self):
-            """
-            Todo: Verify that INPUT_PROP_POINTER is set on opaque devices.
-            """
-            pass
-
 
 class PenTabletTest(BaseTest.TestTablet):
     def assertName(self, uhdev):
@@ -677,6 +665,15 @@ class TestOpaqueTablet(PenTabletTest):
             uhdev.event(130, 240, pressure=0), [], auto_syn=False, strict=True
         )
 
+    def test_prop_pointer(self):
+        """
+        Verify that INPUT_PROP_POINTER is set and INPUT_PROP_DIRECT
+        is not set on opaque devices.
+        """
+        evdev = self.uhdev.get_evdev()
+        assert libevdev.INPUT_PROP_POINTER in evdev.properties
+        assert libevdev.INPUT_PROP_DIRECT not in evdev.properties
+
 
 class TestOpaqueCTLTablet(TestOpaqueTablet):
     def create_device(self):
@@ -862,7 +859,18 @@ class TestPTHX60_Pen(TestOpaqueCTLTablet):
         )
 
 
-class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest):
+class DirectTabletTest():
+    def test_prop_direct(self):
+        """
+        Verify that INPUT_PROP_DIRECT is set and INPUT_PROP_POINTER
+        is not set on display devices.
+        """
+        evdev = self.uhdev.get_evdev()
+        assert libevdev.INPUT_PROP_DIRECT in evdev.properties
+        assert libevdev.INPUT_PROP_POINTER not in evdev.properties
+
+
+class TestDTH2452Tablet(test_multitouch.BaseTest.TestMultitouch, TouchTabletTest, DirectTabletTest):
     ContactIds = namedtuple("ContactIds", "contact_id, tracking_id, slot_num")
 
     def create_device(self):
-- 
cgit v1.2.3


From 9af0feae8016ba58ad7ff784a903404986b395b1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 27 Jan 2026 10:38:39 +0100
Subject: RDMA/core: Fix stale RoCE GIDs during netdev events at registration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RoCE GID entries become stale when netdev properties change during the
IB device registration window. This is reproducible with a udev rule
that sets a MAC address when a VF netdev appears:

  ACTION=="add", SUBSYSTEM=="net", KERNEL=="eth4", \
    RUN+="/sbin/ip link set eth4 address 88:22:33:44:55:66"

After VF creation, show_gids displays GIDs derived from the original
random MAC rather than the configured one.

The root cause is a race between netdev event processing and device
registration:

  CPU 0 (driver)                    CPU 1 (udev/workqueue)
  ──────────────                    ──────────────────────
  ib_register_device()
    ib_cache_setup_one()
      gid_table_setup_one()
        _gid_table_setup_one()
          ← GID table allocated
        rdma_roce_rescan_device()
          ← GIDs populated with
            OLD MAC
                                    ip link set eth4 addr NEW_MAC
                                    NETDEV_CHANGEADDR queued
                                    netdevice_event_work_handler()
                                      ib_enum_all_roce_netdevs()
                                        ← Iterates DEVICE_REGISTERED
                                        ← Device NOT marked yet, SKIP!
    enable_device_and_get()
      xa_set_mark(DEVICE_REGISTERED)
          ← Too late, event was lost

The netdev event handler uses ib_enum_all_roce_netdevs() which only
iterates devices marked DEVICE_REGISTERED. However, this mark is set
late in the registration process, after the GID cache is already
populated. Events arriving in this window are silently dropped.

Fix this by introducing a new xarray mark DEVICE_GID_UPDATES that is
set immediately after the GID table is allocated and initialized. Use
the new mark in ib_enum_all_roce_netdevs() function to iterate devices
instead of DEVICE_REGISTERED.

This is safe because:
- After _gid_table_setup_one(), all required structures exist (port_data,
  immutable, cache.gid)
- The GID table mutex serializes concurrent access between the initial
  rescan and event handlers
- Event handlers correctly update stale GIDs even when racing with rescan
- The mark is cleared in ib_cache_cleanup_one() before teardown

This also fixes similar races for IP address events (inetaddr_event,
inet6addr_event) which use the same enumeration path.

Fixes: 0df91bb67334 ("RDMA/devices: Use xarray to store the client_data")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20260127093839.126291-1-jiri@resnulli.us
Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/cache.c     | 13 +++++++++++++
 drivers/infiniband/core/core_priv.h |  3 +++
 drivers/infiniband/core/device.c    | 34 +++++++++++++++++++++++++++++++++-
 3 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index b415d4aad04f..ee4a2bc68fb2 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -926,6 +926,13 @@ static int gid_table_setup_one(struct ib_device *ib_dev)
 	if (err)
 		return err;
 
+	/*
+	 * Mark the device as ready for GID cache updates. This allows netdev
+	 * event handlers to update the GID cache even before the device is
+	 * fully registered.
+	 */
+	ib_device_enable_gid_updates(ib_dev);
+
 	rdma_roce_rescan_device(ib_dev);
 
 	return err;
@@ -1637,6 +1644,12 @@ void ib_cache_release_one(struct ib_device *device)
 
 void ib_cache_cleanup_one(struct ib_device *device)
 {
+	/*
+	 * Clear the GID updates mark first to prevent event handlers from
+	 * accessing the device while it's being torn down.
+	 */
+	ib_device_disable_gid_updates(device);
+
 	/* The cleanup function waits for all in-progress workqueue
 	 * elements and cleans up the GID cache. This function should be
 	 * called after the device was removed from the devices list and
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 05102769a918..a2c36666e6fc 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -100,6 +100,9 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+void ib_device_enable_gid_updates(struct ib_device *device);
+void ib_device_disable_gid_updates(struct ib_device *device);
+
 typedef int (*nldev_callback)(struct ib_device *device,
 			      struct sk_buff *skb,
 			      struct netlink_callback *cb,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 1b5f1ee0a557..558b73940d66 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -93,6 +93,7 @@ static struct workqueue_struct *ib_unreg_wq;
 static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC);
 static DECLARE_RWSEM(devices_rwsem);
 #define DEVICE_REGISTERED XA_MARK_1
+#define DEVICE_GID_UPDATES XA_MARK_2
 
 static u32 highest_client_id;
 #define CLIENT_REGISTERED XA_MARK_1
@@ -2412,11 +2413,42 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 	unsigned long index;
 
 	down_read(&devices_rwsem);
-	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED)
+	xa_for_each_marked(&devices, index, dev, DEVICE_GID_UPDATES)
 		ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie);
 	up_read(&devices_rwsem);
 }
 
+/**
+ * ib_device_enable_gid_updates - Mark device as ready for GID cache updates
+ * @device: Device to mark
+ *
+ * Called after GID table is allocated and initialized. After this mark is set,
+ * netdevice event handlers can update the device's GID cache. This allows
+ * events that arrive during device registration to be processed, avoiding
+ * stale GID entries when netdev properties change during the device
+ * registration process.
+ */
+void ib_device_enable_gid_updates(struct ib_device *device)
+{
+	down_write(&devices_rwsem);
+	xa_set_mark(&devices, device->index, DEVICE_GID_UPDATES);
+	up_write(&devices_rwsem);
+}
+
+/**
+ * ib_device_disable_gid_updates - Clear the GID updates mark
+ * @device: Device to unmark
+ *
+ * Called before GID table cleanup to prevent event handlers from accessing
+ * the device while it's being torn down.
+ */
+void ib_device_disable_gid_updates(struct ib_device *device)
+{
+	down_write(&devices_rwsem);
+	xa_clear_mark(&devices, device->index, DEVICE_GID_UPDATES);
+	up_write(&devices_rwsem);
+}
+
 /*
  * ib_enum_all_devs - enumerate all ib_devices
  * @cb: Callback to call for each found ib_device
-- 
cgit v1.2.3


From 7a23af417d9dd57b4382356b2e7442e5d2bf5bea Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 18 Feb 2026 09:12:45 +0000
Subject: RDMA/bng_re: Remove unnessary validity checks

Fix below smatch warning:
drivers/infiniband/hw/bng_re/bng_dev.c:113
bng_re_net_ring_free() warn: variable dereferenced before check 'rdev'
(see line 107)

current driver has unnessary validity checks. So, removing these
unnessary validity checks.

Fixes: 4f830cd8d7fe ("RDMA/bng_re: Add infrastructure for enabling Firmware channel")
Fixes: 745065770c2d ("RDMA/bng_re: Register and get the resources from bnge driver")
Fixes: 04e031ff6e60 ("RDMA/bng_re: Initialize the Firmware and Hardware")
Fixes: d0da769c19d0 ("RDMA/bng_re: Add Auxiliary interface")
Reported-by: Simon Horman <horms@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601010413.sWadrQel-lkp@intel.com/
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20260218091246.1764808-2-siva.kallam@broadcom.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/bng_re/bng_dev.c | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c
index cf3bf08e5f26..b8df807c3a64 100644
--- a/drivers/infiniband/hw/bng_re/bng_dev.c
+++ b/drivers/infiniband/hw/bng_re/bng_dev.c
@@ -54,9 +54,6 @@ static void bng_re_destroy_chip_ctx(struct bng_re_dev *rdev)
 {
 	struct bng_re_chip_ctx *chip_ctx;
 
-	if (!rdev->chip_ctx)
-		return;
-
 	kfree(rdev->dev_attr);
 	rdev->dev_attr = NULL;
 
@@ -124,12 +121,6 @@ static int bng_re_net_ring_free(struct bng_re_dev *rdev,
 	struct bnge_fw_msg fw_msg = {};
 	int rc = -EINVAL;
 
-	if (!rdev)
-		return rc;
-
-	if (!aux_dev)
-		return rc;
-
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_FREE);
 	req.ring_type = type;
 	req.ring_id = cpu_to_le16(fw_ring_id);
@@ -150,10 +141,7 @@ static int bng_re_net_ring_alloc(struct bng_re_dev *rdev,
 	struct hwrm_ring_alloc_input req = {};
 	struct hwrm_ring_alloc_output resp;
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
-
-	if (!aux_dev)
-		return rc;
+	int rc;
 
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_ALLOC);
 	req.enables = 0;
@@ -184,10 +172,7 @@ static int bng_re_stats_ctx_free(struct bng_re_dev *rdev)
 	struct hwrm_stat_ctx_free_input req = {};
 	struct hwrm_stat_ctx_free_output resp = {};
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
-
-	if (!aux_dev)
-		return rc;
+	int rc;
 
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_FREE);
 	req.stat_ctx_id = cpu_to_le32(rdev->stats_ctx.fw_id);
@@ -208,13 +193,10 @@ static int bng_re_stats_ctx_alloc(struct bng_re_dev *rdev)
 	struct hwrm_stat_ctx_alloc_output resp = {};
 	struct hwrm_stat_ctx_alloc_input req = {};
 	struct bnge_fw_msg fw_msg = {};
-	int rc = -EINVAL;
+	int rc;
 
 	stats->fw_id = BNGE_INVALID_STATS_CTX_ID;
 
-	if (!aux_dev)
-		return rc;
-
 	bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_ALLOC);
 	req.update_period_ms = cpu_to_le32(1000);
 	req.stats_dma_addr = cpu_to_le64(stats->dma_map);
@@ -486,8 +468,7 @@ static void bng_re_remove(struct auxiliary_device *adev)
 
 	rdev = dev_info->rdev;
 
-	if (rdev)
-		bng_re_remove_device(rdev, adev);
+	bng_re_remove_device(rdev, adev);
 	kfree(dev_info);
 }
 
-- 
cgit v1.2.3


From 3d2e5d12a2eef0ca8a629a422aa593673235c77c Mon Sep 17 00:00:00 2001
From: Siva Reddy Kallam <siva.kallam@broadcom.com>
Date: Wed, 18 Feb 2026 09:12:46 +0000
Subject: RDMA/bng_re: Unwind bng_re_dev_init properly

Fix below smatch warning:
drivers/infiniband/hw/bng_re/bng_dev.c:270
bng_re_dev_init() warn: missing unwind goto?

Current bng_re_dev_init function is not having clear unwinding code.
So, added proper unwinding with ladder.

Fixes: 4f830cd8d7fe ("RDMA/bng_re: Add infrastructure for enabling Firmware channel")
Reported-by: Simon Horman <horms@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202601010413.sWadrQel-lkp@intel.com/
Signed-off-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Link: https://patch.msgid.link/20260218091246.1764808-3-siva.kallam@broadcom.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/bng_re/bng_dev.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c
index b8df807c3a64..d34b5f88cd40 100644
--- a/drivers/infiniband/hw/bng_re/bng_dev.c
+++ b/drivers/infiniband/hw/bng_re/bng_dev.c
@@ -285,7 +285,7 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 				"Failed to register with netedev: %#x\n", rc);
-		return -EINVAL;
+		goto reg_netdev_fail;
 	}
 
 	set_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
@@ -294,19 +294,16 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 		ibdev_err(&rdev->ibdev,
 			  "RoCE requires minimum 2 MSI-X vectors, but only %d reserved\n",
 			  rdev->aux_dev->auxr_info->msix_requested);
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto msix_ctx_fail;
 	}
 	ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n",
 		  rdev->aux_dev->auxr_info->msix_requested);
 
 	rc = bng_re_setup_chip_ctx(rdev);
 	if (rc) {
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
 		ibdev_err(&rdev->ibdev, "Failed to get chip context\n");
-		return -EINVAL;
+		goto msix_ctx_fail;
 	}
 
 	bng_re_query_hwrm_version(rdev);
@@ -315,16 +312,14 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 			  "Failed to allocate RCFW Channel: %#x\n", rc);
-		goto fail;
+		goto alloc_fw_chl_fail;
 	}
 
 	/* Allocate nq record memory */
 	rdev->nqr = kzalloc_obj(*rdev->nqr);
 	if (!rdev->nqr) {
-		bng_re_destroy_chip_ctx(rdev);
-		bnge_unregister_dev(rdev->aux_dev);
-		clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto nq_alloc_fail;
 	}
 
 	rdev->nqr->num_msix = rdev->aux_dev->auxr_info->msix_requested;
@@ -393,9 +388,15 @@ disable_rcfw:
 free_ring:
 	bng_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type);
 free_rcfw:
+	kfree(rdev->nqr);
+nq_alloc_fail:
 	bng_re_free_rcfw_channel(&rdev->rcfw);
-fail:
-	bng_re_dev_uninit(rdev);
+alloc_fw_chl_fail:
+	bng_re_destroy_chip_ctx(rdev);
+msix_ctx_fail:
+	bnge_unregister_dev(rdev->aux_dev);
+	clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags);
+reg_netdev_fail:
 	return rc;
 }
 
-- 
cgit v1.2.3


From 017c1792525064a723971f0216e6ef86a8c7af11 Mon Sep 17 00:00:00 2001
From: Vahagn Vardanian <vahagn@redrays.io>
Date: Mon, 23 Feb 2026 00:00:00 +0000
Subject: wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame()

In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced
at lines 1638 and 1642 without a prior NULL check:

    ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
    ...
    pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value);

The mesh_matches_local() check above only validates the Mesh ID,
Mesh Configuration, and Supported Rates IEs.  It does not verify the
presence of the Mesh Channel Switch Parameters IE (element ID 118).
When a received CSA action frame omits that IE, ieee802_11_parse_elems()
leaves elems->mesh_chansw_params_ie as NULL, and the unconditional
dereference causes a kernel NULL pointer dereference.

A remote mesh peer with an established peer link (PLINK_ESTAB) can
trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame
that includes a matching Mesh ID and Mesh Configuration IE but omits the
Mesh Channel Switch Parameters IE.  No authentication beyond the default
open mesh peering is required.

Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  Oops: Oops: 0000 [#1] SMP NOPTI
  RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211]
  CR2: 0000000000000000

Fix by adding a NULL check for mesh_chansw_params_ie after
mesh_matches_local() returns, consistent with how other optional IEs
are guarded throughout the mesh code.

The bug has been present since v3.13 (released 2014-01-19).

Fixes: 8f2535b92d68 ("mac80211: process the CSA frame for mesh accordingly")
Cc: stable@vger.kernel.org
Signed-off-by: Vahagn Vardanian <vahagn@redrays.io>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 68901f1def0d..129e814abe76 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -1636,6 +1636,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 	if (!mesh_matches_local(sdata, elems))
 		goto free;
 
+	if (!elems->mesh_chansw_params_ie)
+		goto free;
+
 	ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
 	if (!--ifmsh->chsw_ttl)
 		fwd_csa = false;
-- 
cgit v1.2.3


From 021fd0f87004e949cba6f27199b9925bc24ec3a0 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Thu, 19 Feb 2026 08:57:38 +0100
Subject: net/rds: fix recursive lock in rds_tcp_conn_slots_available

syzbot reported a recursive lock warning in rds_tcp_get_peer_sport() as
it calls inet6_getname() which acquires the socket lock that was already
held by __release_sock().

 kworker/u8:6/2985 is trying to acquire lock:
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1709 [inline]
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: inet6_getname+0x15d/0x650 net/ipv6/af_inet6.c:533

 but task is already holding lock:
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1709 [inline]
 ffff88807a07aa20 (k-sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_sock_set_cork+0x2c/0x2e0 net/ipv4/tcp.c:3694
   lock_sock_nested+0x48/0x100 net/core/sock.c:3780
   lock_sock include/net/sock.h:1709 [inline]
   inet6_getname+0x15d/0x650 net/ipv6/af_inet6.c:533
   rds_tcp_get_peer_sport net/rds/tcp_listen.c:70 [inline]
   rds_tcp_conn_slots_available+0x288/0x470 net/rds/tcp_listen.c:149
   rds_recv_hs_exthdrs+0x60f/0x7c0 net/rds/recv.c:265
   rds_recv_incoming+0x9f6/0x12d0 net/rds/recv.c:389
   rds_tcp_data_recv+0x7f1/0xa40 net/rds/tcp_recv.c:243
   __tcp_read_sock+0x196/0x970 net/ipv4/tcp.c:1702
   rds_tcp_read_sock net/rds/tcp_recv.c:277 [inline]
   rds_tcp_data_ready+0x369/0x950 net/rds/tcp_recv.c:331
   tcp_rcv_established+0x19e9/0x2670 net/ipv4/tcp_input.c:6675
   tcp_v6_do_rcv+0x8eb/0x1ba0 net/ipv6/tcp_ipv6.c:1609
   sk_backlog_rcv include/net/sock.h:1185 [inline]
   __release_sock+0x1b8/0x3a0 net/core/sock.c:3213

Reading from the socket struct directly is safe from possible paths. For
rds_tcp_accept_one(), the socket has just been accepted and is not yet
exposed to concurrent access. For rds_tcp_conn_slots_available(), direct
access avoids the recursive deadlock seen during backlog processing
where the socket lock is already held from the __release_sock().

However, rds_tcp_conn_slots_available() is also called from the normal
softirq path via tcp_data_ready() where the lock is not held. This is
also safe because inet_dport is a stable 16 bits field. A READ_ONCE()
annotation as the value might be accessed lockless in a concurrent
access context.

Note that it is also safe to call rds_tcp_conn_slots_available() from
rds_conn_shutdown() because the fan-out is disabled.

Fixes: 9d27a0fb122f ("net/rds: Trigger rds_send_ping() more than once")
Reported-by: syzbot+5efae91f60932839f0a5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5efae91f60932839f0a5
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260219075738.4403-1-fmancera@suse.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rds/connection.c |  3 +++
 net/rds/tcp_listen.c | 28 +++++-----------------------
 2 files changed, 8 insertions(+), 23 deletions(-)

diff --git a/net/rds/connection.c b/net/rds/connection.c
index 185f73b01694..a542f94c0214 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -455,6 +455,9 @@ void rds_conn_shutdown(struct rds_conn_path *cp)
 		rcu_read_unlock();
 	}
 
+	/* we do not hold the socket lock here but it is safe because
+	 * fan-out is disabled when calling conn_slots_available()
+	 */
 	if (conn->c_trans->conn_slots_available)
 		conn->c_trans->conn_slots_available(conn, false);
 }
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index b4ab68a1da6d..08a506aa7ce7 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -59,30 +59,12 @@ void rds_tcp_keepalive(struct socket *sock)
 static int
 rds_tcp_get_peer_sport(struct socket *sock)
 {
-	union {
-		struct sockaddr_storage storage;
-		struct sockaddr addr;
-		struct sockaddr_in sin;
-		struct sockaddr_in6 sin6;
-	} saddr;
-	int sport;
-
-	if (kernel_getpeername(sock, &saddr.addr) >= 0) {
-		switch (saddr.addr.sa_family) {
-		case AF_INET:
-			sport = ntohs(saddr.sin.sin_port);
-			break;
-		case AF_INET6:
-			sport = ntohs(saddr.sin6.sin6_port);
-			break;
-		default:
-			sport = -1;
-		}
-	} else {
-		sport = -1;
-	}
+	struct sock *sk = sock->sk;
+
+	if (!sk)
+		return -1;
 
-	return sport;
+	return ntohs(READ_ONCE(inet_sk(sk)->inet_dport));
 }
 
 /* rds_tcp_accept_one_path(): if accepting on cp_index > 0, make sure the
-- 
cgit v1.2.3


From fdcfce93073d990ed4b71752e31ad1c1d6e9d58b Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Mon, 23 Feb 2026 20:59:33 +0100
Subject: eventpoll: Fix integer overflow in ep_loop_check_proc()

If a recursive call to ep_loop_check_proc() hits the `result = INT_MAX`,
an integer overflow will occur in the calling ep_loop_check_proc() at
`result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1)`,
breaking the recursion depth check.

Fix it by using a different placeholder value that can't lead to an
overflow.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: f2e467a48287 ("eventpoll: Fix semi-unbounded recursion")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Link: https://patch.msgid.link/20260223-epoll-int-overflow-v1-1-452f35132224@google.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventpoll.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 6c36d9dc6926..d20917b03161 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -2061,7 +2061,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
  * @ep: the &struct eventpoll to be currently checked.
  * @depth: Current depth of the path being checked.
  *
- * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep.
+ * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found
+ * a loop or went too deep.
  */
 static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 {
@@ -2080,7 +2081,7 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			struct eventpoll *ep_tovisit;
 			ep_tovisit = epi->ffd.file->private_data;
 			if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
-				result = INT_MAX;
+				result = EP_MAX_NESTS+1;
 			else
 				result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1);
 			if (result > EP_MAX_NESTS)
-- 
cgit v1.2.3


From bae8a5d2e759da2e0cba33ab2080deee96a09373 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Thu, 19 Feb 2026 20:46:37 +0800
Subject: net: wan: farsync: Fix use-after-free bugs caused by unfinished
 tasklets

When the FarSync T-series card is being detached, the fst_card_info is
deallocated in fst_remove_one(). However, the fst_tx_task or fst_int_task
may still be running or pending, leading to use-after-free bugs when the
already freed fst_card_info is accessed in fst_process_tx_work_q() or
fst_process_int_work_q().

A typical race condition is depicted below:

CPU 0 (cleanup)           | CPU 1 (tasklet)
                          | fst_start_xmit()
fst_remove_one()          |   tasklet_schedule()
  unregister_hdlc_device()|
                          | fst_process_tx_work_q() //handler
  kfree(card) //free      |   do_bottom_half_tx()
                          |     card-> //use

The following KASAN trace was captured:

==================================================================
 BUG: KASAN: slab-use-after-free in do_bottom_half_tx+0xb88/0xd00
 Read of size 4 at addr ffff88800aad101c by task ksoftirqd/3/32
 ...
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x55/0x70
  print_report+0xcb/0x5d0
  ? do_bottom_half_tx+0xb88/0xd00
  kasan_report+0xb8/0xf0
  ? do_bottom_half_tx+0xb88/0xd00
  do_bottom_half_tx+0xb88/0xd00
  ? _raw_spin_lock_irqsave+0x85/0xe0
  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  ? __pfx___hrtimer_run_queues+0x10/0x10
  fst_process_tx_work_q+0x67/0x90
  tasklet_action_common+0x1fa/0x720
  ? hrtimer_interrupt+0x31f/0x780
  handle_softirqs+0x176/0x530
  __irq_exit_rcu+0xab/0xe0
  sysvec_apic_timer_interrupt+0x70/0x80
 ...

 Allocated by task 41 on cpu 3 at 72.330843s:
  kasan_save_stack+0x24/0x50
  kasan_save_track+0x17/0x60
  __kasan_kmalloc+0x7f/0x90
  fst_add_one+0x1a5/0x1cd0
  local_pci_probe+0xdd/0x190
  pci_device_probe+0x341/0x480
  really_probe+0x1c6/0x6a0
  __driver_probe_device+0x248/0x310
  driver_probe_device+0x48/0x210
  __device_attach_driver+0x160/0x320
  bus_for_each_drv+0x101/0x190
  __device_attach+0x198/0x3a0
  device_initial_probe+0x78/0xa0
  pci_bus_add_device+0x81/0xc0
  pci_bus_add_devices+0x7e/0x190
  enable_slot+0x9b9/0x1130
  acpiphp_check_bridge.part.0+0x2e1/0x460
  acpiphp_hotplug_notify+0x36c/0x3c0
  acpi_device_hotplug+0x203/0xb10
  acpi_hotplug_work_fn+0x59/0x80
 ...

 Freed by task 41 on cpu 1 at 75.138639s:
  kasan_save_stack+0x24/0x50
  kasan_save_track+0x17/0x60
  kasan_save_free_info+0x3b/0x60
  __kasan_slab_free+0x43/0x70
  kfree+0x135/0x410
  fst_remove_one+0x2ca/0x540
  pci_device_remove+0xa6/0x1d0
  device_release_driver_internal+0x364/0x530
  pci_stop_bus_device+0x105/0x150
  pci_stop_and_remove_bus_device+0xd/0x20
  disable_slot+0x116/0x260
  acpiphp_disable_and_eject_slot+0x4b/0x190
  acpiphp_hotplug_notify+0x230/0x3c0
  acpi_device_hotplug+0x203/0xb10
  acpi_hotplug_work_fn+0x59/0x80
 ...

 The buggy address belongs to the object at ffff88800aad1000
  which belongs to the cache kmalloc-1k of size 1024
 The buggy address is located 28 bytes inside of
  freed 1024-byte region
 The buggy address belongs to the physical page:
 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xaad0
 head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
 flags: 0x100000000000040(head|node=0|zone=1)
 page_type: f5(slab)
 raw: 0100000000000040 ffff888007042dc0 dead000000000122 0000000000000000
 raw: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
 head: 0100000000000040 ffff888007042dc0 dead000000000122 0000000000000000
 head: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
 head: 0100000000000003 ffffea00002ab401 00000000ffffffff 00000000ffffffff
 head: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffff88800aad0f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff88800aad0f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 >ffff88800aad1000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                             ^
  ffff88800aad1080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  ffff88800aad1100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ==================================================================

Fix this by ensuring that both fst_tx_task and fst_int_task are properly
canceled before the fst_card_info is released. Add tasklet_kill() in
fst_remove_one() to synchronize with any pending or running tasklets.
Since unregister_hdlc_device() stops data transmission and reception,
and fst_disable_intr() prevents further interrupts, it is appropriate
to place tasklet_kill() after these calls.

The bugs were identified through static analysis. To reproduce the issue
and validate the fix, a FarSync T-series card was simulated in QEMU and
delays(e.g., mdelay()) were introduced within the tasklet handler to
increase the likelihood of triggering the race condition.

Fixes: 2f623aaf9f31 ("net: farsync: Fix kmemleak when rmmods farsync")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Reviewed-by: Jijie Shao <shaojijie@huawei.com>
Link: https://patch.msgid.link/20260219124637.72578-1-duoming@zju.edu.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/wan/farsync.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 5b01642ca44e..6b2d1e63855e 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2550,6 +2550,8 @@ fst_remove_one(struct pci_dev *pdev)
 
 	fst_disable_intr(card);
 	free_irq(card->irq, card);
+	tasklet_kill(&fst_tx_task);
+	tasklet_kill(&fst_int_task);
 
 	iounmap(card->ctlmem);
 	iounmap(card->mem);
-- 
cgit v1.2.3


From 82aec772fca2223bc5774bd9af486fd95766e578 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 19 Feb 2026 11:50:21 -0800
Subject: netconsole: avoid OOB reads, msg is not nul-terminated

msg passed to netconsole from the console subsystem is not guaranteed
to be nul-terminated. Before recent
commit 7eab73b18630 ("netconsole: convert to NBCON console infrastructure")
the message would be placed in printk_shared_pbufs, a static global
buffer, so KASAN had harder time catching OOB accesses. Now we see:

    printk: console [netcon_ext0] enabled
    BUG: KASAN: slab-out-of-bounds in string+0x1f7/0x240
    Read of size 1 at addr ffff88813b6d4c00 by task pr/netcon_ext0/594

    CPU: 65 UID: 0 PID: 594 Comm: pr/netcon_ext0 Not tainted 6.19.0-11754-g4246fd6547c9
    Call Trace:
     kasan_report+0xe4/0x120
     string+0x1f7/0x240
     vsnprintf+0x655/0xba0
     scnprintf+0xba/0x120
     netconsole_write+0x3fe/0xa10
     nbcon_emit_next_record+0x46e/0x860
     nbcon_kthread_func+0x623/0x750

    Allocated by task 1:
     nbcon_alloc+0x1ea/0x450
     register_console+0x26b/0xe10
     init_netconsole+0xbb0/0xda0

    The buggy address belongs to the object at ffff88813b6d4000
                which belongs to the cache kmalloc-4k of size 4096
    The buggy address is located 0 bytes to the right of
                allocated 3072-byte region [ffff88813b6d4000, ffff88813b6d4c00)

Fixes: c62c0a17f9b7 ("netconsole: Append kernel version to message")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260219195021.2099699-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index d144787b2947..1b6a4135ec08 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1679,7 +1679,8 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 	if (release_len) {
 		release = init_utsname()->release;
 
-		scnprintf(nt->buf, MAX_PRINT_CHUNK, "%s,%s", release, msg);
+		scnprintf(nt->buf, MAX_PRINT_CHUNK, "%s,%.*s", release,
+			  msg_len, msg);
 		msg_len += release_len;
 	} else {
 		memcpy(nt->buf, msg, msg_len);
-- 
cgit v1.2.3


From 7a648d598cb8e8c62af3f0e020a25820a3f3a9a7 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sat, 14 Feb 2026 23:14:51 +0800
Subject: pinctrl: pinconf-generic: Fix memory leak in
 pinconf_generic_parse_dt_config()

In pinconf_generic_parse_dt_config(), if parse_dt_cfg() fails, it returns
directly. This bypasses the cleanup logic and results in a memory leak of
the cfg buffer.

Fix this by jumping to the out label on failure, ensuring kfree(cfg) is
called before returning.

Fixes: 90a18c512884 ("pinctrl: pinconf-generic: Handle string values for generic properties")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Antonio Borneo <antonio.borneo@foss.st.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinconf-generic.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 94b1d057197c..2b030bd0e6ad 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -351,13 +351,13 @@ int pinconf_generic_parse_dt_config(struct device_node *np,
 
 	ret = parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg);
 	if (ret)
-		return ret;
+		goto out;
 	if (pctldev && pctldev->desc->num_custom_params &&
 		pctldev->desc->custom_params) {
 		ret = parse_dt_cfg(np, pctldev->desc->custom_params,
 				   pctldev->desc->num_custom_params, cfg, &ncfg);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* no configs found at all */
-- 
cgit v1.2.3


From a48150d05190b41b5eec19f74b751a75a15a456a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:58:39 +0100
Subject: pinctrl: amdisp: Make amdisp_pinctrl_ops variable static

File-scope 'amdisp_pinctrl_ops' is not used outside of this unit, so
make it static to silence sparse warning:

  pinctrl-amdisp.c:83:26: warning: symbol 'amdisp_pinctrl_ops' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-amdisp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c
index efbf40c776ea..e0874cc086a7 100644
--- a/drivers/pinctrl/pinctrl-amdisp.c
+++ b/drivers/pinctrl/pinctrl-amdisp.c
@@ -80,7 +80,7 @@ static int amdisp_get_group_pins(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-const struct pinctrl_ops amdisp_pinctrl_ops = {
+static const struct pinctrl_ops amdisp_pinctrl_ops = {
 	.get_groups_count	= amdisp_get_groups_count,
 	.get_group_name		= amdisp_get_group_name,
 	.get_group_pins		= amdisp_get_group_pins,
-- 
cgit v1.2.3


From c2e174994c9e98956a85dee9af6fbb293f5ad673 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:58:40 +0100
Subject: pinctrl: cix: sky1: Unexport sky1_pinctrl_pm_ops

File-scope 'sky1_pinctrl_pm_ops' is not used outside of this unit (and
it should not be!), so unexport it and make it static to silence sparse
warning:

  pinctrl-sky1.c:525:25: warning: symbol 'sky1_pinctrl_pm_ops' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/cix/pinctrl-sky1.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pinctrl/cix/pinctrl-sky1.c b/drivers/pinctrl/cix/pinctrl-sky1.c
index 5d0d8be815b2..938894058d86 100644
--- a/drivers/pinctrl/cix/pinctrl-sky1.c
+++ b/drivers/pinctrl/cix/pinctrl-sky1.c
@@ -522,11 +522,10 @@ static int __maybe_unused sky1_pinctrl_resume(struct device *dev)
 	return pinctrl_force_default(spctl->pctl);
 }
 
-const struct dev_pm_ops sky1_pinctrl_pm_ops = {
+static const struct dev_pm_ops sky1_pinctrl_pm_ops = {
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(sky1_pinctrl_suspend,
 					sky1_pinctrl_resume)
 };
-EXPORT_SYMBOL_GPL(sky1_pinctrl_pm_ops);
 
 static int sky1_pinctrl_probe(struct platform_device *pdev)
 {
-- 
cgit v1.2.3


From e9e268ea9df102abef34d7afba59ef4d5868d5d7 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 16 Feb 2026 09:25:50 +0100
Subject: pinctrl: qcom: sdm660-lpass-lpi: Make groups and functions variables
 static

File-scope 'sdm660_lpi_pinctrl_groups' and
'sdm660_lpi_pinctrl_functions' are not used outside of this unit, so
make them static to silence sparse warnings:

  pinctrl-sdm660-lpass-lpi.c:79:27: warning: symbol 'sdm660_lpi_pinctrl_groups' was not declared. Should it be static?
  pinctrl-sdm660-lpass-lpi.c:116:27: warning: symbol 'sdm660_lpi_pinctrl_functions' was not declared. Should it be static?

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
index d93af5f0e8d3..65411abfbfac 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c
@@ -76,7 +76,7 @@ static const char * const pdm_clk_groups[] = { "gpio18" };
 static const char * const pdm_rx_groups[] = { "gpio21", "gpio23", "gpio25" };
 static const char * const pdm_sync_groups[] = { "gpio19" };
 
-const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
+static const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(0, LPI_NO_SLEW, _, _, _, _, 0x0000),
 	LPI_PINGROUP_OFFSET(1, LPI_NO_SLEW, _, _, _, _, 0x1000),
 	LPI_PINGROUP_OFFSET(2, LPI_NO_SLEW, _, _, _, _, 0x2000),
@@ -113,7 +113,7 @@ const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = {
 	LPI_PINGROUP_OFFSET(31, LPI_NO_SLEW, _, _, _, _, 0xb010),
 };
 
-const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
+static const struct lpi_function sdm660_lpi_pinctrl_functions[] = {
 	LPI_FUNCTION(comp_rx),
 	LPI_FUNCTION(dmic1_clk),
 	LPI_FUNCTION(dmic1_data),
-- 
cgit v1.2.3


From a2539b92e4b791c1ba482930b5e51b1591975461 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 19 Feb 2026 00:51:22 +0800
Subject: pinctrl: meson: amlogic-a4: Fix device node reference leak in
 aml_dt_node_to_map_pinmux()

The of_get_parent() function returns a device_node with an incremented
reference count.

Use the __free(device_node) cleanup attribute to ensure of_node_put()
is automatically called when pnode goes out of scope, fixing a
reference leak.

Fixes: 6e9be3abb78c ("pinctrl: Add driver support for Amlogic SoCs")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
index dfa32b11555c..e2293a872dcb 100644
--- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
+++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
@@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 				     unsigned int *num_maps)
 {
 	struct device *dev = pctldev->dev;
-	struct device_node *pnode;
 	unsigned long *configs = NULL;
 	unsigned int num_configs = 0;
 	struct property *prop;
@@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 		return -ENOENT;
 	}
 
-	pnode = of_get_parent(np);
+	struct device_node *pnode __free(device_node) = of_get_parent(np);
 	if (!pnode) {
 		dev_info(dev, "Missing function node\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From fd5bed798f45eb3a178ad527b43ab92705faaf8a Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Feb 2026 17:39:07 +0800
Subject: pinctrl: cirrus: cs42l43: Fix double-put in cs42l43_pin_probe()

devm_add_action_or_reset() already invokes the action on failure,
so the explicit put causes a double-put.

Fixes: 9b07cdf86a0b ("pinctrl: cirrus: Fix fwnode leak in cs42l43_pin_probe()")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
index a8f82104a384..227c37c360e1 100644
--- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
+++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
@@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 		if (child) {
 			ret = devm_add_action_or_reset(&pdev->dev,
 				cs42l43_fwnode_put, child);
-			if (ret) {
-				fwnode_handle_put(child);
+			if (ret)
 				return ret;
-			}
+
 			if (!child->dev)
 				child->dev = priv->dev;
 			fwnode = child;
-- 
cgit v1.2.3


From 45fe4592454368df24d18352be700ff40e7df0c0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Mon, 23 Feb 2026 11:57:18 +0100
Subject: pinctrl: rockchip: Fix configuring a deferred pin

Commit e2c58cbe3aff ("pinctrl: rockchip: Simplify locking with
scoped_guard()") added a scoped_guard() over existing code containing a
"break" instruction.  That "break" was for the outer (existing)
for-loop, which now exits inner, scoped_guard() loop.  If GPIO driver
did not probe, then driver will not bail out, but instead continue to
configure the pin.

Fix the issue by simplifying the code - the break in original code was
leading directly to end of the function returning 0, thus we can simply
return here rockchip_pinconf_defer_pin status.

Reported-by: David Lechner <dlechner@baylibre.com>
Closes: https://lore.kernel.org/r/f5b38942-a584-4e78-a893-de4a219070b2@baylibre.com/
Fixes: e2c58cbe3aff ("pinctrl: rockchip: Simplify locking with scoped_guard()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-rockchip.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index d87c0b1de616..f15b18f334ee 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3640,14 +3640,10 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 			 * or the gpio driver hasn't probed yet.
 			 */
 			scoped_guard(mutex, &bank->deferred_lock) {
-				if (!gpio || !gpio->direction_output) {
-					rc = rockchip_pinconf_defer_pin(bank,
-									pin - bank->pin_base,
-									param, arg);
-					if (rc)
-						return rc;
-					break;
-				}
+				if (!gpio || !gpio->direction_output)
+					return rockchip_pinconf_defer_pin(bank,
+									  pin - bank->pin_base,
+									  param, arg);
 			}
 		}
 
-- 
cgit v1.2.3


From 01e10d0272b932f908b4f9b6609a10cb1f35fafe Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@kernel.org>
Date: Tue, 24 Feb 2026 17:24:18 +0800
Subject: pinctrl: sunxi: Implement gpiochip::get_direction()

After commit 471e998c0e31 ("gpiolib: remove redundant callback check"),
a warning will be printed if the gpio driver does not implement this
callback. The warning was added in commit e623c4303ed1 ("gpiolib:
sanitize the return value of gpio_chip::get_direction()"), but was
masked by the "redundant" check.

The warning can be triggered by any action that calls the callback,
such as dumping the GPIO state from /sys/kernel/debug/gpio.

Implement it for the sunxi driver. This is simply a matter of reading
out the mux value from the registers, then checking if it is one of
the GPIO functions and which direction it is.

Signed-off-by: Chen-Yu Tsai <wens@kernel.org>
Reviewed-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/sunxi/pinctrl-sunxi.c | 51 +++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 48434292a39b..c990b6118172 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -204,6 +204,32 @@ sunxi_pinctrl_desc_find_function_by_pin(struct sunxi_pinctrl *pctl,
 	return NULL;
 }
 
+static struct sunxi_desc_function *
+sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl,
+						const u16 pin_num,
+						const u8 muxval)
+{
+	for (unsigned int i = 0; i < pctl->desc->npins; i++) {
+		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
+		struct sunxi_desc_function *func = pin->functions;
+
+		if (pin->pin.number != pin_num)
+			continue;
+
+		if (pin->variant && !(pctl->variant & pin->variant))
+			continue;
+
+		while (func->name) {
+			if (func->muxval == muxval)
+				return func;
+
+			func++;
+		}
+	}
+
+	return NULL;
+}
+
 static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev)
 {
 	struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
@@ -930,6 +956,30 @@ static const struct pinmux_ops sunxi_pmx_ops = {
 	.strict			= true,
 };
 
+static int sunxi_pinctrl_gpio_get_direction(struct gpio_chip *chip,
+					    unsigned int offset)
+{
+	struct sunxi_pinctrl *pctl = gpiochip_get_data(chip);
+	const struct sunxi_desc_function *func;
+	u32 pin = offset + chip->base;
+	u32 reg, shift, mask;
+	u8 muxval;
+
+	sunxi_mux_reg(pctl, offset, &reg, &shift, &mask);
+
+	muxval = (readl(pctl->membase + reg) & mask) >> shift;
+
+	func = sunxi_pinctrl_desc_find_function_by_pin_and_mux(pctl, pin, muxval);
+	if (!func)
+		return -ENODEV;
+
+	if (!strcmp(func->name, "gpio_out"))
+		return GPIO_LINE_DIRECTION_OUT;
+	if (!strcmp(func->name, "gpio_in") || !strcmp(func->name, "irq"))
+		return GPIO_LINE_DIRECTION_IN;
+	return -EINVAL;
+}
+
 static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip,
 					unsigned offset)
 {
@@ -1599,6 +1649,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 	pctl->chip->request = gpiochip_generic_request;
 	pctl->chip->free = gpiochip_generic_free;
 	pctl->chip->set_config = gpiochip_generic_config;
+	pctl->chip->get_direction = sunxi_pinctrl_gpio_get_direction;
 	pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input;
 	pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output;
 	pctl->chip->get = sunxi_pinctrl_gpio_get;
-- 
cgit v1.2.3


From fd80bd7105f88189f47d465ca8cb7d115570de30 Mon Sep 17 00:00:00 2001
From: Kamal Heib <kheib@redhat.com>
Date: Fri, 20 Feb 2026 17:21:26 -0500
Subject: RDMA/ionic: Fix potential NULL pointer dereference in
 ionic_query_port

The function ionic_query_port() calls ib_device_get_netdev() without
checking the return value which could lead to NULL pointer dereference,
Fix it by checking the return value and return -ENODEV if the 'ndev' is
NULL.

Fixes: 2075bbe8ef03 ("RDMA/ionic: Register device ops for miscellaneous functionality")
Signed-off-by: Kamal Heib <kheib@redhat.com>
Link: https://patch.msgid.link/20260220222125.16973-2-kheib@redhat.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/ionic/ionic_ibdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/ionic/ionic_ibdev.c b/drivers/infiniband/hw/ionic/ionic_ibdev.c
index 164046d00e5d..bd4c73e530d0 100644
--- a/drivers/infiniband/hw/ionic/ionic_ibdev.c
+++ b/drivers/infiniband/hw/ionic/ionic_ibdev.c
@@ -81,6 +81,8 @@ static int ionic_query_port(struct ib_device *ibdev, u32 port,
 		return -EINVAL;
 
 	ndev = ib_device_get_netdev(ibdev, port);
+	if (!ndev)
+		return -ENODEV;
 
 	if (netif_running(ndev) && netif_carrier_ok(ndev)) {
 		attr->state = IB_PORT_ACTIVE;
-- 
cgit v1.2.3


From f22c77ce49db0589103d96487dca56f5b2136362 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:47 -0400
Subject: RDMA/efa: Fix typo in efa_alloc_mr()

The pattern is to check the entire driver request space, not just
sizeof something unrelated.

Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/1-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Acked-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/efa/efa_verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index b5b93b42e6c4..b0aa7c0238ed 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1661,7 +1661,7 @@ static struct efa_mr *efa_alloc_mr(struct ib_pd *ibpd, int access_flags,
 	struct efa_mr *mr;
 
 	if (udata && udata->inlen &&
-	    !ib_is_udata_cleared(udata, 0, sizeof(udata->inlen))) {
+	    !ib_is_udata_cleared(udata, 0, udata->inlen)) {
 		ibdev_dbg(&dev->ibdev,
 			  "Incompatible ABI params, udata not cleared\n");
 		return ERR_PTR(-EINVAL);
-- 
cgit v1.2.3


From 117942ca43e2e3c3d121faae530989931b7f67e1 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:48 -0400
Subject: IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq()

Fix a user triggerable leak on the system call failure path.

Cc: stable@vger.kernel.org
Fixes: ec34a922d243 ("[PATCH] IB/mthca: Add SRQ implementation")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/2-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mthca/mthca_provider.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index ef0635064fba..5c182ae4fc2f 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -428,6 +428,8 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 	if (context && ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) {
 		mthca_free_srq(to_mdev(ibsrq->device), srq);
+		mthca_unmap_user_db(to_mdev(ibsrq->device), &context->uar,
+				    context->db_tab, ucmd.db_index);
 		return -EFAULT;
 	}
 
@@ -436,6 +438,7 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
+	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	if (udata) {
 		struct mthca_ucontext *context =
 			rdma_udata_to_drv_context(
@@ -446,8 +449,6 @@ static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 		mthca_unmap_user_db(to_mdev(srq->device), &context->uar,
 				    context->db_tab, to_msrq(srq)->db_index);
 	}
-
-	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	return 0;
 }
 
-- 
cgit v1.2.3


From 74586c6da9ea222a61c98394f2fc0a604748438c Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:49 -0400
Subject: RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah()

struct irdma_create_ah_resp {  // 8 bytes, no padding
    __u32 ah_id;               // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx)
    __u8  rsvd[4];             // offset 4 - NEVER SET <- LEAK
};

rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata().

The reserved members of the structure were not zeroed.

Cc: stable@vger.kernel.org
Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/3-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 15af53237217..7251cd7a2147 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -5212,7 +5212,7 @@ static int irdma_create_user_ah(struct ib_ah *ibah,
 #define IRDMA_CREATE_AH_MIN_RESP_LEN offsetofend(struct irdma_create_ah_resp, rsvd)
 	struct irdma_ah *ah = container_of(ibah, struct irdma_ah, ibah);
 	struct irdma_device *iwdev = to_iwdev(ibah->pd->device);
-	struct irdma_create_ah_resp uresp;
+	struct irdma_create_ah_resp uresp = {};
 	struct irdma_ah *parent_ah;
 	int err;
 
-- 
cgit v1.2.3


From faa72102b178c7ae6c6afea23879e7c84fc59b4e Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 16 Feb 2026 11:02:50 -0400
Subject: RDMA/ionic: Fix kernel stack leak in ionic_create_cq()

struct ionic_cq_resp resp {
    __u32 cqid[2];         // offset 0 - PARTIALLY SET (see below)
    __u8  udma_mask;       // offset 8 - SET (resp.udma_mask = vcq->udma_mask)
    __u8  rsvd[7];         // offset 9 - NEVER SET <- LEAK
};

rsvd[7]: 7 bytes of stack memory leaked unconditionally.

cqid[2]: The loop at line 1256 iterates over udma_idx but skips indices
where !(vcq->udma_mask & BIT(udma_idx)). The array has 2 entries but
udma_count could be 1, meaning cqid[1] might never be written via
ionic_create_cq_common(). If udma_mask only has bit 0 set, cqid[1] (4
bytes) is also leaked. So potentially 11 bytes leaked.

Cc: stable@vger.kernel.org
Fixes: e8521822c733 ("RDMA/ionic: Register device ops for control path")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://patch.msgid.link/4-v1-83e918d69e73+a9-rdma_udata_rc_jgg@nvidia.com
Acked-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/ionic/ionic_controlpath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/ionic/ionic_controlpath.c b/drivers/infiniband/hw/ionic/ionic_controlpath.c
index 5b3f40bd98d8..4842931f5316 100644
--- a/drivers/infiniband/hw/ionic/ionic_controlpath.c
+++ b/drivers/infiniband/hw/ionic/ionic_controlpath.c
@@ -1218,7 +1218,7 @@ int ionic_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		rdma_udata_to_drv_context(udata, struct ionic_ctx, ibctx);
 	struct ionic_vcq *vcq = to_ionic_vcq(ibcq);
 	struct ionic_tbl_buf buf = {};
-	struct ionic_cq_resp resp;
+	struct ionic_cq_resp resp = {};
 	struct ionic_cq_req req;
 	int udma_idx = 0, rc;
 
-- 
cgit v1.2.3


From 983512f3a87fd8dc4c94dfa6b596b6e57df5aad7 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 20 Feb 2026 19:38:58 +0100
Subject: net: Drop the lock in skb_may_tx_timestamp()

skb_may_tx_timestamp() may acquire sock::sk_callback_lock. The lock must
not be taken in IRQ context, only softirq is okay. A few drivers receive
the timestamp via a dedicated interrupt and complete the TX timestamp
from that handler. This will lead to a deadlock if the lock is already
write-locked on the same CPU.

Taking the lock can be avoided. The socket (pointed by the skb) will
remain valid until the skb is released. The ->sk_socket and ->file
member will be set to NULL once the user closes the socket which may
happen before the timestamp arrives.
If we happen to observe the pointer while the socket is closing but
before the pointer is set to NULL then we may use it because both
pointer (and the file's cred member) are RCU freed.

Drop the lock. Use READ_ONCE() to obtain the individual pointer. Add a
matching WRITE_ONCE() where the pointer are cleared.

Link: https://lore.kernel.org/all/20260205145104.iWinkXHv@linutronix.de
Fixes: b245be1f4db1a ("net-timestamp: no-payload only sysctl")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260220183858.N4ERjFW6@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sock.h |  2 +-
 net/core/skbuff.c  | 23 ++++++++++++++++++-----
 net/socket.c       |  2 +-
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 66b56288c1d3..6c9a83016e95 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2098,7 +2098,7 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk->sk_socket = sock;
+	WRITE_ONCE(sk->sk_socket, sock);
 	if (sock) {
 		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
 		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dc47d3efc72e..0e217041958a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5590,15 +5590,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 
 static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
-	bool ret;
+	struct socket *sock;
+	struct file *file;
+	bool ret = false;
 
 	if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data)))
 		return true;
 
-	read_lock_bh(&sk->sk_callback_lock);
-	ret = sk->sk_socket && sk->sk_socket->file &&
-	      file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
-	read_unlock_bh(&sk->sk_callback_lock);
+	/* The sk pointer remains valid as long as the skb is. The sk_socket and
+	 * file pointer may become NULL if the socket is closed. Both structures
+	 * (including file->cred) are RCU freed which means they can be accessed
+	 * within a RCU read section.
+	 */
+	rcu_read_lock();
+	sock = READ_ONCE(sk->sk_socket);
+	if (!sock)
+		goto out;
+	file = READ_ONCE(sock->file);
+	if (!file)
+		goto out;
+	ret = file_ns_capable(file, &init_user_ns, CAP_NET_RAW);
+out:
+	rcu_read_unlock();
 	return ret;
 }
 
diff --git a/net/socket.c b/net/socket.c
index 136b98c54fb3..05952188127f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -674,7 +674,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		iput(SOCK_INODE(sock));
 		return;
 	}
-	sock->file = NULL;
+	WRITE_ONCE(sock->file, NULL);
 }
 
 /**
-- 
cgit v1.2.3


From bf4fde7db4a8e2613cba36d81ac271f3d66c28f7 Mon Sep 17 00:00:00 2001
From: Ferry Meng <mengferry@linux.alibaba.com>
Date: Tue, 24 Feb 2026 14:02:07 +0800
Subject: erofs: remove more unnecessary #ifdefs

Many #ifdefs can be replaced with IS_ENABLED() to improve code
readability.  No functional changes.

Signed-off-by: Ferry Meng <mengferry@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/super.c | 85 ++++++++++++++++++++++++--------------------------------
 1 file changed, 36 insertions(+), 49 deletions(-)

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index d4995686ac6c..972a0c82198d 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -424,26 +424,23 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = {
 
 static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
 {
-#ifdef CONFIG_FS_DAX
-	struct erofs_sb_info *sbi = fc->s_fs_info;
-
-	switch (mode) {
-	case EROFS_MOUNT_DAX_ALWAYS:
-		set_opt(&sbi->opt, DAX_ALWAYS);
-		clear_opt(&sbi->opt, DAX_NEVER);
-		return true;
-	case EROFS_MOUNT_DAX_NEVER:
-		set_opt(&sbi->opt, DAX_NEVER);
-		clear_opt(&sbi->opt, DAX_ALWAYS);
-		return true;
-	default:
+	if (IS_ENABLED(CONFIG_FS_DAX)) {
+		struct erofs_sb_info *sbi = fc->s_fs_info;
+
+		if (mode == EROFS_MOUNT_DAX_ALWAYS) {
+			set_opt(&sbi->opt, DAX_ALWAYS);
+			clear_opt(&sbi->opt, DAX_NEVER);
+			return true;
+		} else if (mode == EROFS_MOUNT_DAX_NEVER) {
+			set_opt(&sbi->opt, DAX_NEVER);
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+			return true;
+		}
 		DBG_BUGON(1);
 		return false;
 	}
-#else
 	errorfc(fc, "dax options not supported");
 	return false;
-#endif
 }
 
 static int erofs_fc_parse_param(struct fs_context *fc,
@@ -460,31 +457,26 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 
 	switch (opt) {
 	case Opt_user_xattr:
-#ifdef CONFIG_EROFS_FS_XATTR
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_XATTR))
+			errorfc(fc, "{,no}user_xattr options not supported");
+		else if (result.boolean)
 			set_opt(&sbi->opt, XATTR_USER);
 		else
 			clear_opt(&sbi->opt, XATTR_USER);
-#else
-		errorfc(fc, "{,no}user_xattr options not supported");
-#endif
 		break;
 	case Opt_acl:
-#ifdef CONFIG_EROFS_FS_POSIX_ACL
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_POSIX_ACL))
+			errorfc(fc, "{,no}acl options not supported");
+		else if (result.boolean)
 			set_opt(&sbi->opt, POSIX_ACL);
 		else
 			clear_opt(&sbi->opt, POSIX_ACL);
-#else
-		errorfc(fc, "{,no}acl options not supported");
-#endif
 		break;
 	case Opt_cache_strategy:
-#ifdef CONFIG_EROFS_FS_ZIP
-		sbi->opt.cache_strategy = result.uint_32;
-#else
-		errorfc(fc, "compression not supported, cache_strategy ignored");
-#endif
+		if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP))
+			errorfc(fc, "compression not supported, cache_strategy ignored");
+		else
+			sbi->opt.cache_strategy = result.uint_32;
 		break;
 	case Opt_dax:
 		if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS))
@@ -533,24 +525,21 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		break;
 #endif
 	case Opt_directio:
-#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
-		if (result.boolean)
+		if (!IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE))
+			errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		else if (result.boolean)
 			set_opt(&sbi->opt, DIRECT_IO);
 		else
 			clear_opt(&sbi->opt, DIRECT_IO);
-#else
-		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
-#endif
 		break;
 	case Opt_fsoffset:
 		sbi->dif0.fsoff = result.uint_64;
 		break;
 	case Opt_inode_share:
-#ifdef CONFIG_EROFS_FS_PAGE_CACHE_SHARE
-		set_opt(&sbi->opt, INODE_SHARE);
-#else
-		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
-#endif
+		if (!IS_ENABLED(CONFIG_EROFS_FS_PAGE_CACHE_SHARE))
+			errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
+		else
+			set_opt(&sbi->opt, INODE_SHARE);
 		break;
 	}
 	return 0;
@@ -809,8 +798,7 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 	ret = get_tree_bdev_flags(fc, erofs_fc_fill_super,
 		IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ?
 			GET_TREE_BDEV_QUIET_LOOKUP : 0);
-#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
-	if (ret == -ENOTBLK) {
+	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && ret == -ENOTBLK) {
 		struct file *file;
 
 		if (!fc->source)
@@ -824,7 +812,6 @@ static int erofs_fc_get_tree(struct fs_context *fc)
 		    sbi->dif0.file->f_mapping->a_ops->read_folio)
 			return get_tree_nodev(fc, erofs_fc_fill_super);
 	}
-#endif
 	return ret;
 }
 
@@ -1108,12 +1095,12 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",dax=never");
 	if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO))
 		seq_puts(seq, ",directio");
-#ifdef CONFIG_EROFS_FS_ONDEMAND
-	if (sbi->fsid)
-		seq_printf(seq, ",fsid=%s", sbi->fsid);
-	if (sbi->domain_id)
-		seq_printf(seq, ",domain_id=%s", sbi->domain_id);
-#endif
+	if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND)) {
+		if (sbi->fsid)
+			seq_printf(seq, ",fsid=%s", sbi->fsid);
+		if (sbi->domain_id)
+			seq_printf(seq, ",domain_id=%s", sbi->domain_id);
+	}
 	if (sbi->dif0.fsoff)
 		seq_printf(seq, ",fsoffset=%llu", sbi->dif0.fsoff);
 	if (test_opt(opt, INODE_SHARE))
-- 
cgit v1.2.3


From 3d7e6ce34f4fcc7083510c28b17a7c36462a25d4 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Sun, 22 Feb 2026 05:06:33 +0000
Subject: net: usb: pegasus: enable basic endpoint checking

pegasus_probe() fills URBs with hardcoded endpoint pipes without
verifying the endpoint descriptors:

  - usb_rcvbulkpipe(dev, 1) for RX data
  - usb_sndbulkpipe(dev, 2) for TX data
  - usb_rcvintpipe(dev, 3)  for status interrupts

A malformed USB device can present these endpoints with transfer types
that differ from what the driver assumes.

Add a pegasus_usb_ep enum for endpoint numbers, replacing magic
constants throughout. Add usb_check_bulk_endpoints() and
usb_check_int_endpoints() calls before any resource allocation to
verify endpoint types before use, rejecting devices with mismatched
descriptors at probe time, and avoid triggering assertion.

Similar fix to
- commit 90b7f2961798 ("net: usb: rtl8150: enable basic endpoint checking")
- commit 9e7021d2aeae ("net: usb: catc: enable basic endpoint checking")

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260222050633.410165-1-n7l8m4@u.northwestern.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/pegasus.c | 35 ++++++++++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 7b6d6eb60709..b84968c5f074 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -28,6 +28,17 @@ static const char driver_name[] = "pegasus";
 			BMSR_100FULL | BMSR_ANEGCAPABLE)
 #define CARRIER_CHECK_DELAY (2 * HZ)
 
+/*
+ * USB endpoints.
+ */
+
+enum pegasus_usb_ep {
+	PEGASUS_USB_EP_CONTROL	= 0,
+	PEGASUS_USB_EP_BULK_IN	= 1,
+	PEGASUS_USB_EP_BULK_OUT	= 2,
+	PEGASUS_USB_EP_INT_IN	= 3,
+};
+
 static bool loopback;
 static bool mii_mode;
 static char *devid;
@@ -542,7 +553,7 @@ static void read_bulk_callback(struct urb *urb)
 		goto tl_sched;
 goon:
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 	rx_status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC);
@@ -582,7 +593,7 @@ static void rx_fixup(struct tasklet_struct *t)
 		return;
 	}
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 try_again:
@@ -710,7 +721,7 @@ static netdev_tx_t pegasus_start_xmit(struct sk_buff *skb,
 	((__le16 *) pegasus->tx_buff)[0] = cpu_to_le16(l16);
 	skb_copy_from_linear_data(skb, pegasus->tx_buff + 2, skb->len);
 	usb_fill_bulk_urb(pegasus->tx_urb, pegasus->usb,
-			  usb_sndbulkpipe(pegasus->usb, 2),
+			  usb_sndbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_OUT),
 			  pegasus->tx_buff, count,
 			  write_bulk_callback, pegasus);
 	if ((res = usb_submit_urb(pegasus->tx_urb, GFP_ATOMIC))) {
@@ -837,7 +848,7 @@ static int pegasus_open(struct net_device *net)
 	set_registers(pegasus, EthID, 6, net->dev_addr);
 
 	usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb,
-			  usb_rcvbulkpipe(pegasus->usb, 1),
+			  usb_rcvbulkpipe(pegasus->usb, PEGASUS_USB_EP_BULK_IN),
 			  pegasus->rx_skb->data, PEGASUS_MTU,
 			  read_bulk_callback, pegasus);
 	if ((res = usb_submit_urb(pegasus->rx_urb, GFP_KERNEL))) {
@@ -848,7 +859,7 @@ static int pegasus_open(struct net_device *net)
 	}
 
 	usb_fill_int_urb(pegasus->intr_urb, pegasus->usb,
-			 usb_rcvintpipe(pegasus->usb, 3),
+			 usb_rcvintpipe(pegasus->usb, PEGASUS_USB_EP_INT_IN),
 			 pegasus->intr_buff, sizeof(pegasus->intr_buff),
 			 intr_callback, pegasus, pegasus->intr_interval);
 	if ((res = usb_submit_urb(pegasus->intr_urb, GFP_KERNEL))) {
@@ -1133,10 +1144,24 @@ static int pegasus_probe(struct usb_interface *intf,
 	pegasus_t *pegasus;
 	int dev_index = id - pegasus_ids;
 	int res = -ENOMEM;
+	static const u8 bulk_ep_addr[] = {
+		PEGASUS_USB_EP_BULK_IN | USB_DIR_IN,
+		PEGASUS_USB_EP_BULK_OUT | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		PEGASUS_USB_EP_INT_IN | USB_DIR_IN,
+		0};
 
 	if (pegasus_blacklisted(dev))
 		return -ENODEV;
 
+	/* Verify that all required endpoints are present */
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(&intf->dev, "Missing or invalid endpoints\n");
+		return -ENODEV;
+	}
+
 	net = alloc_etherdev(sizeof(struct pegasus));
 	if (!net)
 		goto out;
-- 
cgit v1.2.3


From 4a1ddb0f1c48c2b56f21d8b5200e2e29adf4c1df Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Feb 2026 12:09:00 +0100
Subject: pidfs: avoid misleading break

The break would only break out of the scoped_guard() loop, not the
switch statement. It still works correct as is ofc but let's avoid the
confusion.

Reported-by: David Lechner <dlechner@baylibre.com>
Link:: https://lore.kernel.org/cd2153f1-098b-463c-bbc1-5c6ca9ef1f12@baylibre.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 1e20e36e0ed5..21f9f011a957 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -577,9 +577,8 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			struct user_namespace *user_ns;
 
 			user_ns = task_cred_xxx(task, user_ns);
-			if (!ns_ref_get(user_ns))
-				break;
-			ns_common = to_ns_common(user_ns);
+			if (ns_ref_get(user_ns))
+				ns_common = to_ns_common(user_ns);
 		}
 #endif
 		break;
@@ -589,9 +588,8 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			struct pid_namespace *pid_ns;
 
 			pid_ns = task_active_pid_ns(task);
-			if (!ns_ref_get(pid_ns))
-				break;
-			ns_common = to_ns_common(pid_ns);
+			if (ns_ref_get(pid_ns))
+				ns_common = to_ns_common(pid_ns);
 		}
 #endif
 		break;
-- 
cgit v1.2.3


From c8dbdc6e380e7e96a51706db3e4b7870d8a9402d Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 22 Feb 2026 16:26:01 +0100
Subject: net: phy: register phy led_triggers during probe to avoid AB-BA
 deadlock

There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and
LED_TRIGGER_PHY are enabled:

[ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc             <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock);
[ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234
[ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c
[ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c
[ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0
[ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0
[ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c
[ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78
[ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654                       <-- Hold lock "rtnl_mutex" by calling rtnl_lock();
[ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0
[ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c
[ 1362.104022] [<80014504>] syscall_common+0x34/0x58

Here LED_TRIGGER_PHY is registering LED triggers during phy_attach
while holding RTNL and then taking triggers_list_lock.

[ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168      <-- Trying to get lock "rtnl_mutex" via rtnl_lock();
[ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4
[ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360                 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock);
[ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c
[ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc
[ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c
[ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4
[ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c
[ 1362.232164] [<80014504>] syscall_common+0x34/0x58

Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes
triggers_list_lock and then RTNL. A classical AB-BA deadlock.

phy_led_triggers_registers() does not require the RTNL, it does not
make any calls into the network stack which require protection. There
is also no requirement the PHY has been attached to a MAC, the
triggers only make use of phydev state. This allows the call to
phy_led_triggers_registers() to be placed elsewhere. PHY probe() and
release() don't hold RTNL, so solving the AB-BA deadlock.

Reported-by: Shiji Yang <yangshiji66@outlook.com>
Closes: https://lore.kernel.org/all/OS7PR01MB13602B128BA1AD3FA38B6D1FFBC69A@OS7PR01MB13602.jpnprd01.prod.outlook.com/
Fixes: 06f502f57d0d ("leds: trigger: Introduce a NETDEV trigger")
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Shiji Yang <yangshiji66@outlook.com>
Link: https://patch.msgid.link/20260222152601.1978655-1-andrew@lunn.ch
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy_device.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9b8eaac63b90..cbb4af604aa5 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1866,8 +1866,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error;
 
 	phy_resume(phydev);
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_register(phydev);
 
 	/**
 	 * If the external phy used by current mac interface is managed by
@@ -1982,9 +1980,6 @@ void phy_detach(struct phy_device *phydev)
 	phydev->phy_link_change = NULL;
 	phydev->phylink = NULL;
 
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_unregister(phydev);
-
 	if (phydev->mdio.dev.driver)
 		module_put(phydev->mdio.dev.driver->owner);
 
@@ -3778,16 +3773,27 @@ static int phy_probe(struct device *dev)
 	/* Set the state to READY by default */
 	phydev->state = PHY_READY;
 
+	/* Register the PHY LED triggers */
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_register(phydev);
+
 	/* Get the LEDs from the device tree, and instantiate standard
 	 * LEDs for them.
 	 */
-	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
+	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev)) {
 		err = of_phy_leds(phydev);
+		if (err)
+			goto out;
+	}
+
+	return 0;
 
 out:
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	/* Re-assert the reset signal on error */
-	if (err)
-		phy_device_reset(phydev, 1);
+	phy_device_reset(phydev, 1);
 
 	return err;
 }
@@ -3801,6 +3807,9 @@ static int phy_remove(struct device *dev)
 	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
 		phy_leds_unregister(phydev);
 
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	phydev->state = PHY_DOWN;
 
 	phy_cleanup_ports(phydev);
-- 
cgit v1.2.3


From 78437ab3b769f80526416570f60173c89858dd84 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 13 Feb 2026 00:58:11 +0100
Subject: clk: scu/imx8qxp: do not register driver in probe()

imx_clk_scu_init() registers the imx_clk_scu_driver while commonly being
called from IMX driver's probe() callbacks.

However, it neither makes sense to register drivers from probe()
callbacks of other drivers, nor does the driver core allow registering
drivers with a device lock already being held.

The latter was revealed by commit dc23806a7c47 ("driver core: enforce
device_lock for driver_match_device()") leading to a deadlock condition
described in [1].

Besides that, nothing seems to unregister the imx_clk_scu_driver once
the corresponding driver module is unloaded, which leaves the
driver-core with a dangling pointer.

Also, if there are multiple matching devices for the imx8qxp_clk_driver,
imx8qxp_clk_probe() calls imx_clk_scu_init() multiple times.  However,
any subsequent call after the first one will fail, since the driver-core
does not allow to register the same struct platform_driver multiple
times.

Hence, register the imx_clk_scu_driver from module_init() and unregister
it in module_exit().

Note that we first register the imx8qxp_clk_driver and then call
imx_clk_scu_module_init() to avoid having to call
imx_clk_scu_module_exit() in the unwind path of imx8qxp_clk_init().

Fixes: dc23806a7c47 ("driver core: enforce device_lock for driver_match_device()")
Fixes: 220175cd3979 ("clk: imx: scu: fix build break when compiled as modules")
Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Closes: https://lore.kernel.org/lkml/13955113.uLZWGnKmhe@steina-w/
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com> # TQMa8x/MBa8x
Link: https://lore.kernel.org/lkml/DFU7CEPUSG9A.1KKGVW4HIPMSH@kernel.org/ [1]
Acked-by: Abel Vesa <abelvesa@kernel.org>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://patch.msgid.link/20260212235842.85934-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/clk/imx/clk-imx8qxp.c | 24 +++++++++++++++++++++++-
 drivers/clk/imx/clk-scu.c     | 12 +++++++++++-
 drivers/clk/imx/clk-scu.h     |  2 ++
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
index 3ae162625bb1..c781425a005e 100644
--- a/drivers/clk/imx/clk-imx8qxp.c
+++ b/drivers/clk/imx/clk-imx8qxp.c
@@ -346,7 +346,29 @@ static struct platform_driver imx8qxp_clk_driver = {
 	},
 	.probe = imx8qxp_clk_probe,
 };
-module_platform_driver(imx8qxp_clk_driver);
+
+static int __init imx8qxp_clk_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&imx8qxp_clk_driver);
+	if (ret)
+		return ret;
+
+	ret = imx_clk_scu_module_init();
+	if (ret)
+		platform_driver_unregister(&imx8qxp_clk_driver);
+
+	return ret;
+}
+module_init(imx8qxp_clk_init);
+
+static void __exit imx8qxp_clk_exit(void)
+{
+	imx_clk_scu_module_exit();
+	platform_driver_unregister(&imx8qxp_clk_driver);
+}
+module_exit(imx8qxp_clk_exit);
 
 MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
 MODULE_DESCRIPTION("NXP i.MX8QXP clock driver");
diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c
index 33e637ad3579..a85ec48a798b 100644
--- a/drivers/clk/imx/clk-scu.c
+++ b/drivers/clk/imx/clk-scu.c
@@ -191,6 +191,16 @@ static bool imx_scu_clk_is_valid(u32 rsrc_id)
 	return p != NULL;
 }
 
+int __init imx_clk_scu_module_init(void)
+{
+	return platform_driver_register(&imx_clk_scu_driver);
+}
+
+void __exit imx_clk_scu_module_exit(void)
+{
+	return platform_driver_unregister(&imx_clk_scu_driver);
+}
+
 int imx_clk_scu_init(struct device_node *np,
 		     const struct imx_clk_scu_rsrc_table *data)
 {
@@ -215,7 +225,7 @@ int imx_clk_scu_init(struct device_node *np,
 		rsrc_table = data;
 	}
 
-	return platform_driver_register(&imx_clk_scu_driver);
+	return 0;
 }
 
 /*
diff --git a/drivers/clk/imx/clk-scu.h b/drivers/clk/imx/clk-scu.h
index af7b697f51ca..ca82f2cce897 100644
--- a/drivers/clk/imx/clk-scu.h
+++ b/drivers/clk/imx/clk-scu.h
@@ -25,6 +25,8 @@ extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8dxl;
 extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qxp;
 extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qm;
 
+int __init imx_clk_scu_module_init(void);
+void __exit imx_clk_scu_module_exit(void);
 int imx_clk_scu_init(struct device_node *np,
 		     const struct imx_clk_scu_rsrc_table *data);
 struct clk_hw *imx_scu_of_clk_src_get(struct of_phandle_args *clkspec,
-- 
cgit v1.2.3


From fb73d0e19f12b793bfe013171d931587f37e3552 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Mon, 23 Feb 2026 13:10:20 +0530
Subject: MAINTAINERS: Update AMD XGBE driver maintainers

Due to additional responsibilities, Shyam Sundar S K will no longer be
supporting the AMD XGBE driver. Maintenance will be handled by
Raju Rangoju going forward.

Cc: Raju Rangoju <Raju.Rangoju@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://patch.msgid.link/20260223074020.1987884-1-Shyam-sundar.S-k@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e1a6c6cc2b7c..cf0313ca6039 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1292,7 +1292,6 @@ F:	include/trace/events/amdxdna.h
 F:	include/uapi/drm/amdxdna_accel.h
 
 AMD XGBE DRIVER
-M:	"Shyam Sundar S K" <Shyam-sundar.S-k@amd.com>
 M:	Raju Rangoju <Raju.Rangoju@amd.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
cgit v1.2.3


From ab39cc4cb8ceecdc2b61747433e7237f1ac2b789 Mon Sep 17 00:00:00 2001
From: David Arcari <darcari@redhat.com>
Date: Tue, 24 Feb 2026 07:21:06 -0500
Subject: cpufreq: intel_pstate: Fix NULL pointer dereference in
 update_cpu_qos_request()

The update_cpu_qos_request() function attempts to initialize the 'freq'
variable by dereferencing 'cpudata' before verifying if the 'policy'
is valid.

This issue occurs on systems booted with the "nosmt" parameter, where
all_cpu_data[cpu] is NULL for the SMT sibling threads. As a result,
any call to update_qos_requests() will result in a NULL pointer
dereference as the code will attempt to access pstate.turbo_freq using
the NULL cpudata pointer.

Also, pstate.turbo_freq may be updated by intel_pstate_get_hwp_cap()
after initializing the 'freq' variable, so it is better to defer the
'freq' until intel_pstate_get_hwp_cap() has been called.

Fix this by deferring the 'freq' assignment until after the policy and
driver_data have been validated.

Fixes: ae1bdd23b99f ("cpufreq: intel_pstate: Adjust frequency percentage computations")
Reported-by: Jirka Hladky <jhladky@redhat.com>
Closes: https://lore.kernel.org/all/CAE4VaGDfiPvz3AzrwrwM4kWB3SCkMci25nPO8W1JmTBd=xHzZg@mail.gmail.com/
Signed-off-by: David Arcari <darcari@redhat.com>
Cc: 6.18+ <stable@vger.kernel.org> # 6.18+
[ rjw: Added one paragraph to the changelog ]
Link: https://patch.msgid.link/20260224122106.228116-1-darcari@redhat.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a48af3540c74..bdc37080d319 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1647,8 +1647,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type)
 {
 	struct cpudata *cpudata = all_cpu_data[cpu];
-	unsigned int freq = cpudata->pstate.turbo_freq;
 	struct freq_qos_request *req;
+	unsigned int freq;
 
 	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	if (!policy)
@@ -1661,6 +1661,8 @@ static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type)
 	if (hwp_active)
 		intel_pstate_get_hwp_cap(cpudata);
 
+	freq = cpudata->pstate.turbo_freq;
+
 	if (type == FREQ_QOS_MIN) {
 		freq = DIV_ROUND_UP(freq * global.min_perf_pct, 100);
 	} else {
-- 
cgit v1.2.3


From 5ede90206273ff156a778254f0f972a55e973c89 Mon Sep 17 00:00:00 2001
From: Sofia Schneider <sofia@schn.dev>
Date: Sun, 22 Feb 2026 23:52:40 -0300
Subject: ACPI: OSI: Add DMI quirk for Acer Aspire One D255

The screen backlight turns off during boot (specifically during udev device
initialization) when returning true for _OSI("Windows 2009").

Analyzing the device's DSDT reveals that the firmware takes a different
code path when Windows 7 is reported, which leads to the backlight shutoff.
Add a DMI quirk to invoke dmi_disable_osi_win7 for this model.

Signed-off-by: Sofia Schneider <sofia@schn.dev>
Link: https://patch.msgid.link/20260223025240.518509-1-sofia@schn.dev
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osi.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index f2c943b934be..9470f1830ff5 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -389,6 +389,19 @@ static const struct dmi_system_id acpi_osi_dmi_table[] __initconst = {
 		},
 	},
 
+	/*
+	 * The screen backlight turns off during udev device creation
+	 * when returning true for _OSI("Windows 2009")
+	 */
+	{
+	.callback = dmi_disable_osi_win7,
+	.ident = "Acer Aspire One D255",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "AOD255"),
+		},
+	},
+
 	/*
 	 * The wireless hotkey does not work on those machines when
 	 * returning true for _OSI("Windows 2012")
-- 
cgit v1.2.3


From e710b2283725f0db9e5b99c2483df3f4a7feadbd Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Mon, 23 Feb 2026 11:04:48 +0100
Subject: Revert "hwmon: add SMARC-sAM67 support"

This reverts commit 443b39c82c322c9f3c38bea0389fe927ba00b3b4.

I was just informed that this product is discontinued (without being
ever released to the market). Pull the plug and let's not waste any more
maintainers time.

Signed-off-by: Michael Walle <mwalle@kernel.org>
Link: https://lore.kernel.org/r/20260223100459.844967-4-mwalle@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/index.rst |   1 -
 Documentation/hwmon/sa67.rst  |  41 -----------
 MAINTAINERS                   |   1 -
 drivers/hwmon/Kconfig         |  10 ---
 drivers/hwmon/Makefile        |   1 -
 drivers/hwmon/sa67mcu-hwmon.c | 161 ------------------------------------------
 6 files changed, 215 deletions(-)
 delete mode 100644 Documentation/hwmon/sa67.rst
 delete mode 100644 drivers/hwmon/sa67mcu-hwmon.c

diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index d91dbb20c7dc..b2ca8513cfcd 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -220,7 +220,6 @@ Hardware Monitoring Kernel Drivers
    q54sj108a2
    qnap-mcu-hwmon
    raspberrypi-hwmon
-   sa67
    sbrmi
    sbtsi_temp
    sch5627
diff --git a/Documentation/hwmon/sa67.rst b/Documentation/hwmon/sa67.rst
deleted file mode 100644
index 029c7c169b7f..000000000000
--- a/Documentation/hwmon/sa67.rst
+++ /dev/null
@@ -1,41 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0-only
-
-Kernel driver sa67mcu
-=====================
-
-Supported chips:
-
-   * Kontron sa67mcu
-
-     Prefix: 'sa67mcu'
-
-     Datasheet: not available
-
-Authors: Michael Walle <mwalle@kernel.org>
-
-Description
------------
-
-The sa67mcu is a board management controller which also exposes a hardware
-monitoring controller.
-
-The controller has two voltage and one temperature sensor. The values are
-hold in two 8 bit registers to form one 16 bit value. Reading the lower byte
-will also capture the high byte to make the access atomic. The unit of the
-volatge sensors are 1mV and the unit of the temperature sensor is 0.1degC.
-
-Sysfs entries
--------------
-
-The following attributes are supported.
-
-======================= ========================================================
-in0_label		"VDDIN"
-in0_input		Measured VDDIN voltage.
-
-in1_label		"VDD_RTC"
-in1_input		Measured VDD_RTC voltage.
-
-temp1_input		MCU temperature. Roughly the board temperature.
-======================= ========================================================
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..d5a2078a6717 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24337,7 +24337,6 @@ F:	Documentation/devicetree/bindings/interrupt-controller/kontron,sl28cpld-intc.
 F:	Documentation/devicetree/bindings/pwm/kontron,sl28cpld-pwm.yaml
 F:	Documentation/devicetree/bindings/watchdog/kontron,sl28cpld-wdt.yaml
 F:	drivers/gpio/gpio-sl28cpld.c
-F:	drivers/hwmon/sa67mcu-hwmon.c
 F:	drivers/hwmon/sl28cpld-hwmon.c
 F:	drivers/irqchip/irq-sl28cpld.c
 F:	drivers/pwm/pwm-sl28cpld.c
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 41c381764c2b..486152a8ea77 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1927,16 +1927,6 @@ config SENSORS_RASPBERRYPI_HWMON
 	  This driver can also be built as a module. If so, the module
 	  will be called raspberrypi-hwmon.
 
-config SENSORS_SA67MCU
-	tristate "Kontron sa67mcu hardware monitoring driver"
-	depends on MFD_SL28CPLD || COMPILE_TEST
-	help
-	  If you say yes here you get support for the voltage and temperature
-	  monitor of the sa67 board management controller.
-
-	  This driver can also be built as a module.  If so, the module
-	  will be called sa67mcu-hwmon.
-
 config SENSORS_SL28CPLD
 	tristate "Kontron sl28cpld hardware monitoring driver"
 	depends on MFD_SL28CPLD || COMPILE_TEST
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index eade8e3b1bde..5833c807c688 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -199,7 +199,6 @@ obj-$(CONFIG_SENSORS_PT5161L)	+= pt5161l.o
 obj-$(CONFIG_SENSORS_PWM_FAN)	+= pwm-fan.o
 obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON)	+= qnap-mcu-hwmon.o
 obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON)	+= raspberrypi-hwmon.o
-obj-$(CONFIG_SENSORS_SA67MCU)	+= sa67mcu-hwmon.o
 obj-$(CONFIG_SENSORS_SBTSI)	+= sbtsi_temp.o
 obj-$(CONFIG_SENSORS_SBRMI)	+= sbrmi.o
 obj-$(CONFIG_SENSORS_SCH56XX_COMMON)+= sch56xx-common.o
diff --git a/drivers/hwmon/sa67mcu-hwmon.c b/drivers/hwmon/sa67mcu-hwmon.c
deleted file mode 100644
index 22f703b7b256..000000000000
--- a/drivers/hwmon/sa67mcu-hwmon.c
+++ /dev/null
@@ -1,161 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sl67mcu hardware monitoring driver
- *
- * Copyright 2025 Kontron Europe GmbH
- */
-
-#include <linux/bitfield.h>
-#include <linux/hwmon.h>
-#include <linux/kernel.h>
-#include <linux/mod_devicetable.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/property.h>
-#include <linux/regmap.h>
-
-#define SA67MCU_VOLTAGE(n)	(0x00 + ((n) * 2))
-#define SA67MCU_TEMP(n)		(0x04 + ((n) * 2))
-
-struct sa67mcu_hwmon {
-	struct regmap *regmap;
-	u32 offset;
-};
-
-static int sa67mcu_hwmon_read(struct device *dev,
-			      enum hwmon_sensor_types type, u32 attr,
-			      int channel, long *input)
-{
-	struct sa67mcu_hwmon *hwmon = dev_get_drvdata(dev);
-	unsigned int offset;
-	u8 reg[2];
-	int ret;
-
-	switch (type) {
-	case hwmon_in:
-		switch (attr) {
-		case hwmon_in_input:
-			offset = hwmon->offset + SA67MCU_VOLTAGE(channel);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		break;
-	case hwmon_temp:
-		switch (attr) {
-		case hwmon_temp_input:
-			offset = hwmon->offset + SA67MCU_TEMP(channel);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	/* Reading the low byte will capture the value */
-	ret = regmap_bulk_read(hwmon->regmap, offset, reg, ARRAY_SIZE(reg));
-	if (ret)
-		return ret;
-
-	*input = reg[1] << 8 | reg[0];
-
-	/* Temperatures are s16 and in 0.1degC steps. */
-	if (type == hwmon_temp)
-		*input = sign_extend32(*input, 15) * 100;
-
-	return 0;
-}
-
-static const struct hwmon_channel_info * const sa67mcu_hwmon_info[] = {
-	HWMON_CHANNEL_INFO(in,
-			   HWMON_I_INPUT | HWMON_I_LABEL,
-			   HWMON_I_INPUT | HWMON_I_LABEL),
-	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
-	NULL
-};
-
-static const char *const sa67mcu_hwmon_in_labels[] = {
-	"VDDIN",
-	"VDD_RTC",
-};
-
-static int sa67mcu_hwmon_read_string(struct device *dev,
-				     enum hwmon_sensor_types type, u32 attr,
-				     int channel, const char **str)
-{
-	switch (type) {
-	case hwmon_in:
-		switch (attr) {
-		case hwmon_in_label:
-			*str = sa67mcu_hwmon_in_labels[channel];
-			return 0;
-		default:
-			return -EOPNOTSUPP;
-		}
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static const struct hwmon_ops sa67mcu_hwmon_ops = {
-	.visible = 0444,
-	.read = sa67mcu_hwmon_read,
-	.read_string = sa67mcu_hwmon_read_string,
-};
-
-static const struct hwmon_chip_info sa67mcu_hwmon_chip_info = {
-	.ops = &sa67mcu_hwmon_ops,
-	.info = sa67mcu_hwmon_info,
-};
-
-static int sa67mcu_hwmon_probe(struct platform_device *pdev)
-{
-	struct sa67mcu_hwmon *hwmon;
-	struct device *hwmon_dev;
-	int ret;
-
-	if (!pdev->dev.parent)
-		return -ENODEV;
-
-	hwmon = devm_kzalloc(&pdev->dev, sizeof(*hwmon), GFP_KERNEL);
-	if (!hwmon)
-		return -ENOMEM;
-
-	hwmon->regmap = dev_get_regmap(pdev->dev.parent, NULL);
-	if (!hwmon->regmap)
-		return -ENODEV;
-
-	ret = device_property_read_u32(&pdev->dev, "reg", &hwmon->offset);
-	if (ret)
-		return -EINVAL;
-
-	hwmon_dev = devm_hwmon_device_register_with_info(&pdev->dev,
-							 "sa67mcu_hwmon", hwmon,
-							 &sa67mcu_hwmon_chip_info,
-							 NULL);
-	if (IS_ERR(hwmon_dev))
-		dev_err(&pdev->dev, "failed to register as hwmon device");
-
-	return PTR_ERR_OR_ZERO(hwmon_dev);
-}
-
-static const struct of_device_id sa67mcu_hwmon_of_match[] = {
-	{ .compatible = "kontron,sa67mcu-hwmon", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, sa67mcu_hwmon_of_match);
-
-static struct platform_driver sa67mcu_hwmon_driver = {
-	.probe = sa67mcu_hwmon_probe,
-	.driver = {
-		.name = "sa67mcu-hwmon",
-		.of_match_table = sa67mcu_hwmon_of_match,
-	},
-};
-module_platform_driver(sa67mcu_hwmon_driver);
-
-MODULE_DESCRIPTION("sa67mcu Hardware Monitoring Driver");
-MODULE_AUTHOR("Michael Walle <mwalle@kernel.org>");
-MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 364410170ab33f6e7ef0eb2afb12bf89b0feb3a6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 5 Feb 2026 07:59:20 -0500
Subject: nfsd: report the requested maximum number of threads instead of
 number running

The current netlink and /proc interfaces deviate from their traditional
values when dynamic threading is enabled, and there is currently no way
to know what the current setting is. This patch brings the reporting
back in line with traditional behavior.

Make these interfaces report the requested maximum number of threads
instead of the number currently running. Also, update documentation and
comments to reflect that this value represents a maximum and not the
number currently running.

Fixes: d8316b837c2c ("nfsd: add controls to set the minimum number of threads per pool")
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 Documentation/netlink/specs/nfsd.yaml |  4 ++--
 fs/nfsd/nfsctl.c                      | 18 +++++++++---------
 fs/nfsd/nfssvc.c                      |  7 ++++---
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml
index badb2fe57c98..f87b5a05e5e9 100644
--- a/Documentation/netlink/specs/nfsd.yaml
+++ b/Documentation/netlink/specs/nfsd.yaml
@@ -152,7 +152,7 @@ operations:
             - compound-ops
     -
       name: threads-set
-      doc: set the number of running threads
+      doc: set the maximum number of running threads
       attribute-set: server
       flags: [admin-perm]
       do:
@@ -165,7 +165,7 @@ operations:
             - min-threads
     -
       name: threads-get
-      doc: get the number of running threads
+      doc: get the maximum number of running threads
       attribute-set: server
       do:
         reply:
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b06adb5d5a2e..369da69d5efe 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -377,15 +377,15 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_threads - Start NFSD, or report the current number of running threads
+ * write_threads - Start NFSD, or report the configured number of threads
  *
  * Input:
  *			buf:		ignored
  *			size:		zero
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero
  *
@@ -399,8 +399,8 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	NFS service is started;
  *			passed-in buffer filled with '\n'-terminated C
- *			string numeric value representing the number of
- *			running NFSD threads;
+ *			string numeric value representing the configured
+ *			number of NFSD threads;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -430,7 +430,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 }
 
 /*
- * write_pool_threads - Set or report the current number of threads per pool
+ * write_pool_threads - Set or report the configured number of threads per pool
  *
  * Input:
  *			buf:		ignored
@@ -447,7 +447,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	passed-in buffer filled with '\n'-terminated C
  *			string containing integer values representing the
- *			number of NFSD threads in each pool;
+ *			configured number of NFSD threads in each pool;
  *			return code is the size in bytes of the string
  *	On error:	return code is zero or a negative errno value
  */
@@ -1657,7 +1657,7 @@ out_unlock:
 }
 
 /**
- * nfsd_nl_threads_get_doit - get the number of running threads
+ * nfsd_nl_threads_get_doit - get the maximum number of running threads
  * @skb: reply buffer
  * @info: netlink metadata and command arguments
  *
@@ -1700,7 +1700,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
 			struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];
 
 			err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
-					  sp->sp_nrthreads);
+					  sp->sp_nrthrmax);
 			if (err)
 				goto err_unlock;
 		}
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 0887ee601d3c..4a04208393b8 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -239,12 +239,13 @@ static void nfsd_net_free(struct percpu_ref *ref)
 
 int nfsd_nrthreads(struct net *net)
 {
-	int rv = 0;
+	int i, rv = 0;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	mutex_lock(&nfsd_mutex);
 	if (nn->nfsd_serv)
-		rv = nn->nfsd_serv->sv_nrthreads;
+		for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i)
+			rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax;
 	mutex_unlock(&nfsd_mutex);
 	return rv;
 }
@@ -659,7 +660,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
 
 	if (serv)
 		for (i = 0; i < serv->sv_nrpools && i < n; i++)
-			nthreads[i] = serv->sv_pools[i].sp_nrthreads;
+			nthreads[i] = serv->sv_pools[i].sp_nrthrmax;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 297318a1c26dabb5a2d8540fdf436c22094eb2d7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 24 Feb 2026 12:52:18 +0100
Subject: spi: dt-bindings: snps,dw-abp-ssi: Remove unused bindings

As stated in the da0a672268b3 ("spi: dw: Remove not-going-to-be-supported
code for Baikal SoC") the Baikal platforms are not supported and
the respective driver code was removed. Remove the currently unused bindings.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20260224115218.3499222-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/spi/snps,dw-apb-ssi.yaml   | 31 +---------------------
 1 file changed, 1 insertion(+), 30 deletions(-)

diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index 81838577cf9c..8ebebcebca16 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -22,21 +22,6 @@ allOf:
       properties:
         reg:
           minItems: 2
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - baikal,bt1-sys-ssi
-    then:
-      properties:
-        mux-controls:
-          maxItems: 1
-      required:
-        - mux-controls
-    else:
-      required:
-        - interrupts
   - if:
       properties:
         compatible:
@@ -75,10 +60,6 @@ properties:
         const: intel,mountevans-imc-ssi
       - description: AMD Pensando Elba SoC SPI Controller
         const: amd,pensando-elba-spi
-      - description: Baikal-T1 SPI Controller
-        const: baikal,bt1-ssi
-      - description: Baikal-T1 System Boot SPI Controller
-        const: baikal,bt1-sys-ssi
       - description: Canaan Kendryte K210 SoS SPI Controller
         const: canaan,k210-spi
       - description: Renesas RZ/N1 SPI Controller
@@ -170,6 +151,7 @@ required:
   - "#address-cells"
   - "#size-cells"
   - clocks
+  - interrupts
 
 examples:
   - |
@@ -190,15 +172,4 @@ examples:
         rx-sample-delay-ns = <7>;
       };
     };
-  - |
-    spi@1f040100 {
-      compatible = "baikal,bt1-sys-ssi";
-      reg = <0x1f040100 0x900>,
-            <0x1c000000 0x1000000>;
-      #address-cells = <1>;
-      #size-cells = <0>;
-      mux-controls = <&boot_mux>;
-      clocks = <&ccu_sys>;
-      clock-names = "ssi_clk";
-    };
 ...
-- 
cgit v1.2.3


From 07ed4f05bbfd2bc014974dcc4297fd3aa1cb88c0 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:14 -0800
Subject: hwmon: (it87) Check the it87_lock() return value

Return early in it87_resume() if it87_lock() fails instead of ignoring the
return value of that function. This patch suppresses a Clang thread-safety
warning.

Cc: Frank Crawford <frank@crawford.emu.id.au>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Jean Delvare <jdelvare@suse.com>
Cc: linux-hwmon@vger.kernel.org
Fixes: 376e1a937b30 ("hwmon: (it87) Add calls to smbus_enable/smbus_disable as required")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20260223220102.2158611-15-bart.vanassche@linux.dev
[groeck: Declare 'ret' at the beginning of it87_resume()]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/it87.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index e233aafa8856..5cfb98a0512f 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -3590,10 +3590,13 @@ static int it87_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct it87_data *data = dev_get_drvdata(dev);
+	int err;
 
 	it87_resume_sio(pdev);
 
-	it87_lock(data);
+	err = it87_lock(data);
+	if (err)
+		return err;
 
 	it87_check_pwm(dev);
 	it87_check_limit_regs(data);
-- 
cgit v1.2.3


From 96a1fd0d84b17360840f344826897fa71049870e Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 12 Feb 2026 14:50:38 -0700
Subject: cxl: Fix race of nvdimm_bus object when creating nvdimm objects

Found issue during running of cxl-translate.sh unit test. Adding a 3s
sleep right before the test seems to make the issue reproduce fairly
consistently. The cxl_translate module has dependency on cxl_acpi and
causes orphaned nvdimm objects to reprobe after cxl_acpi is removed.
The nvdimm_bus object is registered by the cxl_nvb object when
cxl_acpi_probe() is called. With the nvdimm_bus object missing,
__nd_device_register() will trigger NULL pointer dereference when
accessing the dev->parent that points to &nvdimm_bus->dev.

[  192.884510] BUG: kernel NULL pointer dereference, address: 000000000000006c
[  192.895383] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS edk2-20250812-19.fc42 08/12/2025
[  192.897721] Workqueue: cxl_port cxl_bus_rescan_queue [cxl_core]
[  192.899459] RIP: 0010:kobject_get+0xc/0x90
[  192.924871] Call Trace:
[  192.925959]  <TASK>
[  192.926976]  ? pm_runtime_init+0xb9/0xe0
[  192.929712]  __nd_device_register.part.0+0x4d/0xc0 [libnvdimm]
[  192.933314]  __nvdimm_create+0x206/0x290 [libnvdimm]
[  192.936662]  cxl_nvdimm_probe+0x119/0x1d0 [cxl_pmem]
[  192.940245]  cxl_bus_probe+0x1a/0x60 [cxl_core]
[  192.943349]  really_probe+0xde/0x380

This patch also relies on the previous change where
devm_cxl_add_nvdimm_bridge() is called from drivers/cxl/pmem.c instead
of drivers/cxl/core.c to ensure the dependency of cxl_acpi on cxl_pmem.

1. Set probe_type of cxl_nvb to PROBE_FORCE_SYNCHRONOUS to ensure the
   driver is probed synchronously when add_device() is called.
2. Add a check in __devm_cxl_add_nvdimm_bridge() to ensure that the
   cxl_nvb driver is attached during cxl_acpi_probe().
3. Take the cxl_root uport_dev lock and the cxl_nvb->dev lock in
   devm_cxl_add_nvdimm() before checking nvdimm_bus is valid.
4. Set cxl_nvdimm flag to CXL_NVD_F_INVALIDATED so cxl_nvdimm_probe()
   will exit with -EBUSY.

The removal of cxl_nvdimm devices should prevent any orphaned devices
from probing once the nvdimm_bus is gone.

[ dj: Fixed 0-day reported kdoc issue. ]
[ dj: Fix cxl_nvb reference leak on error. Gregory (kreview-0811365) ]

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Fixes: 8fdcb1704f61 ("cxl/pmem: Add initial infrastructure for pmem support")
Tested-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Alison Schofield <alison.schofield@intel.com?>
Link: https://patch.msgid.link/20260205001633.1813643-3-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/pmem.c | 29 +++++++++++++++++++++++++++++
 drivers/cxl/cxl.h       |  5 +++++
 drivers/cxl/pmem.c      | 10 ++++++++--
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index b652e3486038..68462e38a977 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -115,6 +115,15 @@ static void unregister_nvb(void *_cxl_nvb)
 	device_unregister(&cxl_nvb->dev);
 }
 
+static bool cxl_nvdimm_bridge_failed_attach(struct cxl_nvdimm_bridge *cxl_nvb)
+{
+	struct device *dev = &cxl_nvb->dev;
+
+	guard(device)(dev);
+	/* If the device has no driver, then it failed to attach. */
+	return dev->driver == NULL;
+}
+
 struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
 						       struct cxl_port *port)
 {
@@ -138,6 +147,11 @@ struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host,
 	if (rc)
 		goto err;
 
+	if (cxl_nvdimm_bridge_failed_attach(cxl_nvb)) {
+		unregister_nvb(cxl_nvb);
+		return ERR_PTR(-ENODEV);
+	}
+
 	rc = devm_add_action_or_reset(host, unregister_nvb, cxl_nvb);
 	if (rc)
 		return ERR_PTR(rc);
@@ -248,6 +262,21 @@ int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port,
 	if (!cxl_nvb)
 		return -ENODEV;
 
+	/*
+	 * Take the uport_dev lock to guard against race of nvdimm_bus object.
+	 * cxl_acpi_probe() registers the nvdimm_bus and is done under the
+	 * root port uport_dev lock.
+	 *
+	 * Take the cxl_nvb device lock to ensure that cxl_nvb driver is in a
+	 * consistent state. And the driver registers nvdimm_bus.
+	 */
+	guard(device)(cxl_nvb->port->uport_dev);
+	guard(device)(&cxl_nvb->dev);
+	if (!cxl_nvb->nvdimm_bus) {
+		rc = -ENODEV;
+		goto err_alloc;
+	}
+
 	cxl_nvd = cxl_nvdimm_alloc(cxl_nvb, cxlmd);
 	if (IS_ERR(cxl_nvd)) {
 		rc = PTR_ERR(cxl_nvd);
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index f5850800f400..9b947286eb9b 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -574,11 +574,16 @@ struct cxl_nvdimm_bridge {
 
 #define CXL_DEV_ID_LEN 19
 
+enum {
+	CXL_NVD_F_INVALIDATED = 0,
+};
+
 struct cxl_nvdimm {
 	struct device dev;
 	struct cxl_memdev *cxlmd;
 	u8 dev_id[CXL_DEV_ID_LEN]; /* for nvdimm, string of 'serial' */
 	u64 dirty_shutdowns;
+	unsigned long flags;
 };
 
 struct cxl_pmem_region_mapping {
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index c67b30b516bf..082ec0f1c3a0 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -14,7 +14,7 @@
 static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
 
 /**
- * __devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
+ * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology
  * @host: platform firmware root device
  * @port: CXL port at the root of a CXL topology
  *
@@ -143,6 +143,9 @@ static int cxl_nvdimm_probe(struct device *dev)
 	struct nvdimm *nvdimm;
 	int rc;
 
+	if (test_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags))
+		return -EBUSY;
+
 	set_exclusive_cxl_commands(mds, exclusive_cmds);
 	rc = devm_add_action_or_reset(dev, clear_exclusive, mds);
 	if (rc)
@@ -323,8 +326,10 @@ static int detach_nvdimm(struct device *dev, void *data)
 	scoped_guard(device, dev) {
 		if (dev->driver) {
 			cxl_nvd = to_cxl_nvdimm(dev);
-			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
+			if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) {
 				release = true;
+				set_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags);
+			}
 		}
 	}
 	if (release)
@@ -367,6 +372,7 @@ static struct cxl_driver cxl_nvdimm_bridge_driver = {
 	.probe = cxl_nvdimm_bridge_probe,
 	.id = CXL_DEVICE_NVDIMM_BRIDGE,
 	.drv = {
+		.probe_type = PROBE_FORCE_SYNCHRONOUS,
 		.suppress_bind_attrs = true,
 	},
 };
-- 
cgit v1.2.3


From 60b5d1f68338aff2c5af0113f04aefa7169c50c2 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Thu, 19 Feb 2026 16:16:17 -0800
Subject: cxl/mbox: validate payload size before accessing contents in
 cxl_payload_from_user_allowed()

cxl_payload_from_user_allowed() casts and dereferences the input
payload without first verifying its size. When a raw mailbox command
is sent with an undersized payload (ie: 1 byte for CXL_MBOX_OP_CLEAR_LOG,
which expects a 16-byte UUID), uuid_equal() reads past the allocated buffer,
triggering a KASAN splat:

BUG: KASAN: slab-out-of-bounds in memcmp+0x176/0x1d0 lib/string.c:683
Read of size 8 at addr ffff88810130f5c0 by task syz.1.62/2258

CPU: 2 UID: 0 PID: 2258 Comm: syz.1.62 Not tainted 6.19.0-dirty #3 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0xab/0xe0 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xce/0x650 mm/kasan/report.c:482
 kasan_report+0xce/0x100 mm/kasan/report.c:595
 memcmp+0x176/0x1d0 lib/string.c:683
 uuid_equal include/linux/uuid.h:73 [inline]
 cxl_payload_from_user_allowed drivers/cxl/core/mbox.c:345 [inline]
 cxl_mbox_cmd_ctor drivers/cxl/core/mbox.c:368 [inline]
 cxl_validate_cmd_from_user drivers/cxl/core/mbox.c:522 [inline]
 cxl_send_cmd+0x9c0/0xb50 drivers/cxl/core/mbox.c:643
 __cxl_memdev_ioctl drivers/cxl/core/memdev.c:698 [inline]
 cxl_memdev_ioctl+0x14f/0x190 drivers/cxl/core/memdev.c:713
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xa8/0x330 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fdaf331ba79
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fdaf1d77038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fdaf3585fa0 RCX: 00007fdaf331ba79
RDX: 00002000000001c0 RSI: 00000000c030ce02 RDI: 0000000000000003
RBP: 00007fdaf33749df R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fdaf3586038 R14: 00007fdaf3585fa0 R15: 00007ffced2af768
 </TASK>

Add 'in_size' parameter to cxl_payload_from_user_allowed() and validate
the payload is large enough.

Fixes: 6179045ccc0c ("cxl/mbox: Block immediate mode in SET_PARTITION_INFO command")
Fixes: 206f9fa9d555 ("cxl/mbox: Add Clear Log mailbox command")
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260220001618.963490-2-dave@stgolabs.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/mbox.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index fa6dd0c94656..e7a6452bf544 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -311,6 +311,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode)
  * cxl_payload_from_user_allowed() - Check contents of in_payload.
  * @opcode: The mailbox command opcode.
  * @payload_in: Pointer to the input payload passed in from user space.
+ * @in_size: Size of @payload_in in bytes.
  *
  * Return:
  *  * true	- payload_in passes check for @opcode.
@@ -325,12 +326,15 @@ static bool cxl_mem_raw_command_allowed(u16 opcode)
  *
  * The specific checks are determined by the opcode.
  */
-static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in)
+static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in,
+					  size_t in_size)
 {
 	switch (opcode) {
 	case CXL_MBOX_OP_SET_PARTITION_INFO: {
 		struct cxl_mbox_set_partition_info *pi = payload_in;
 
+		if (in_size < sizeof(*pi))
+			return false;
 		if (pi->flags & CXL_SET_PARTITION_IMMEDIATE_FLAG)
 			return false;
 		break;
@@ -338,6 +342,8 @@ static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in)
 	case CXL_MBOX_OP_CLEAR_LOG: {
 		const uuid_t *uuid = (uuid_t *)payload_in;
 
+		if (in_size < sizeof(uuid_t))
+			return false;
 		/*
 		 * Restrict the ‘Clear log’ action to only apply to
 		 * Vendor debug logs.
@@ -365,7 +371,8 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox_cmd,
 		if (IS_ERR(mbox_cmd->payload_in))
 			return PTR_ERR(mbox_cmd->payload_in);
 
-		if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in)) {
+		if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in,
+						  in_size)) {
 			dev_dbg(cxl_mbox->host, "%s: input payload not allowed\n",
 				cxl_mem_opcode_to_name(opcode));
 			kvfree(mbox_cmd->payload_in);
-- 
cgit v1.2.3


From 0a70b7cd397e545e926c93715ff6366b67c716f6 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Mon, 23 Feb 2026 11:13:39 -0800
Subject: cxl: Test CXL_DECODER_F_LOCK as a bitmask

The CXL decoder flags are defined as bitmasks, not bit indices.
Using test_bit() to check them interprets the mask value as a bit
index, which is the wrong test.

For CXL_DECODER_F_LOCK the test reads beyond the defined bits, causing
the test to always return false and allowing resets that should have
been blocked.

Replace test_bit() with a bitmask check.

Fixes: 2230c4bdc412 ("cxl: Add handling of locked CXL decoder")
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Tested-by: Gregory Price <gourry@gourry.net>
Link: https://patch.msgid.link/98851c4770e4631753cf9f75b58a3a6daeca2ea2.1771873256.git.alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/hdm.c    | 2 +-
 drivers/cxl/core/region.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index e3f0c39e6812..c222e98ae736 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -904,7 +904,7 @@ static void cxl_decoder_reset(struct cxl_decoder *cxld)
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
 		return;
 
-	if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags))
+	if (cxld->flags & CXL_DECODER_F_LOCK)
 		return;
 
 	if (port->commit_end == id)
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index fec37af1dfbf..780ec947ecf2 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1100,7 +1100,7 @@ static int cxl_rr_assign_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 static void cxl_region_setup_flags(struct cxl_region *cxlr,
 				   struct cxl_decoder *cxld)
 {
-	if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags)) {
+	if (cxld->flags & CXL_DECODER_F_LOCK) {
 		set_bit(CXL_REGION_F_LOCK, &cxlr->flags);
 		clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}
-- 
cgit v1.2.3


From e46f25f5a81f6f1a9ab93bcda80d5dfaea9f4897 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Mon, 23 Feb 2026 11:13:40 -0800
Subject: cxl/region: Test CXL_DECODER_F_NORMALIZED_ADDRESSING as a bitmask

The CXL decoder flags are defined as bitmasks, not bit indices.
Using test_bit() to check them interprets the mask value as a bit
index, which is the wrong test.

For CXL_DECODER_F_NORMALIZED_ADDRESSING the test reads beyond the
flags word, making the flag sometimes appear set and blocking creation
of CXL region debugfs attributes that support poison operations.

Replace test_bit() with a bitmask check.

Found with cxl-test.

Fixes: 208f432406b7 ("cxl: Disable HPA/SPA translation handlers for Normalized Addressing")
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Tested-by: Gregory Price <gourry@gourry.net>
Link: https://patch.msgid.link/63fe4a6203e40e404347f1cdc7a1c55cb4959b86.1771873256.git.alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/region.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 780ec947ecf2..42874948b589 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1105,7 +1105,7 @@ static void cxl_region_setup_flags(struct cxl_region *cxlr,
 		clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}
 
-	if (test_bit(CXL_DECODER_F_NORMALIZED_ADDRESSING, &cxld->flags))
+	if (cxld->flags & CXL_DECODER_F_NORMALIZED_ADDRESSING)
 		set_bit(CXL_REGION_F_NORMALIZED_ADDRESSING, &cxlr->flags);
 }
 
-- 
cgit v1.2.3


From 43277d8f57b490550d33f6f4cb73c28ec6024696 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:19 -0800
Subject: selftests/bpf: Replace strncpy() with strscpy()

strncpy() does not guarantee NULL-termination and is considered
deprecated [1]. Replace strncpy() calls with strscpy().

[1] https://docs.kernel.org/process/deprecated.html#strncpy-on-nul-terminated-strings

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-4-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/network_helpers.c             | 3 +--
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c         | 3 +--
 tools/testing/selftests/bpf/prog_tests/flow_dissector.c   | 4 ++--
 tools/testing/selftests/bpf/prog_tests/queue_stack_map.c  | 4 ++--
 tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/task_local_data.h  | 2 +-
 tools/testing/selftests/bpf/prog_tests/tc_redirect.c      | 2 +-
 tools/testing/selftests/bpf/test_progs.c                  | 2 +-
 tools/testing/selftests/bpf/xdp_hw_metadata.c             | 4 ++--
 9 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 5374b7e16d53..b82f572641b7 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -581,8 +581,7 @@ int open_tuntap(const char *dev_name, bool need_mac)
 		return -1;
 
 	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
-	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+	strscpy(ifr.ifr_name, dev_name);
 
 	err = ioctl(fd, TUNSETIFF, &ifr);
 	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 5225d69bf79b..c69080ca14f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -346,8 +346,7 @@ static void test_task_sleepable(void)
 		close(finish_pipe[1]);
 
 		test_data = malloc(sizeof(char) * 10);
-		strncpy(test_data, "test_data", 10);
-		test_data[9] = '\0';
+		strscpy(test_data, "test_data", 10);
 
 		test_data_long = malloc(sizeof(char) * 5000);
 		for (int i = 0; i < 5000; ++i) {
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 08bae13248c4..fb4892681464 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -570,7 +570,7 @@ static int create_tap(const char *ifname)
 	};
 	int fd, ret;
 
-	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	strscpy(ifr.ifr_name, ifname);
 
 	fd = open("/dev/net/tun", O_RDWR);
 	if (fd < 0)
@@ -599,7 +599,7 @@ static int ifup(const char *ifname)
 	struct ifreq ifr = {};
 	int sk, ret;
 
-	strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+	strscpy(ifr.ifr_name, ifname);
 
 	sk = socket(PF_INET, SOCK_DGRAM, 0);
 	if (sk < 0)
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index a043af9cd6d9..41441325e179 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -28,9 +28,9 @@ static void test_queue_stack_map_by_type(int type)
 		vals[i] = rand();
 
 	if (type == QUEUE)
-		strncpy(file, "./test_queue_map.bpf.o", sizeof(file));
+		strscpy(file, "./test_queue_map.bpf.o");
 	else if (type == STACK)
-		strncpy(file, "./test_stack_map.bpf.o", sizeof(file));
+		strscpy(file, "./test_stack_map.bpf.o");
 	else
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
index 3eefdfed1db9..657d897958b6 100644
--- a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
@@ -34,7 +34,7 @@ void test_skc_to_unix_sock(void)
 
 	memset(&sockaddr, 0, sizeof(sockaddr));
 	sockaddr.sun_family = AF_UNIX;
-	strncpy(sockaddr.sun_path, sock_path, strlen(sock_path));
+	strscpy(sockaddr.sun_path, sock_path);
 	sockaddr.sun_path[0] = '\0';
 
 	err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr));
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
index 0f86b9275cf9..8342e2fe5260 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_data.h
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -262,7 +262,7 @@ retry:
 		if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1))
 			goto retry;
 
-		strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN);
+		strscpy(tld_meta_p->metadata[i].name, name);
 		atomic_store(&tld_meta_p->metadata[i].size, size);
 		return (tld_key_t){(__s16)off};
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 76d72a59365e..64fbda082309 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -1095,7 +1095,7 @@ static int tun_open(char *name)
 
 	ifr.ifr_flags = IFF_TUN | IFF_NO_PI;
 	if (*name)
-		strncpy(ifr.ifr_name, name, IFNAMSIZ);
+		strscpy(ifr.ifr_name, name);
 
 	err = ioctl(fd, TUNSETIFF, &ifr);
 	if (!ASSERT_OK(err, "ioctl TUNSETIFF"))
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 02a85dda30e6..d1418ec1f351 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1799,7 +1799,7 @@ static int worker_main_send_subtests(int sock, struct test_state *state)
 
 		msg.subtest_done.num = i;
 
-		strncpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME);
+		strscpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME);
 
 		msg.subtest_done.error_cnt = subtest_state->error_cnt;
 		msg.subtest_done.skipped = subtest_state->skipped;
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 3d8de0d4c96a..6db3b5555a22 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -550,7 +550,7 @@ static int rxq_num(const char *ifname)
 	struct ifreq ifr = {
 		.ifr_data = (void *)&ch,
 	};
-	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	strscpy(ifr.ifr_name, ifname);
 	int fd, ret;
 
 	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
@@ -571,7 +571,7 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c
 	struct ifreq ifr = {
 		.ifr_data = (void *)cfg,
 	};
-	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	strscpy(ifr.ifr_name, ifname);
 	int fd, ret;
 
 	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
-- 
cgit v1.2.3


From 3ed0bc2d4994c718fb5476b45d4aafec42a1d040 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:20 -0800
Subject: selftests/bpf: Use strscpy in bpftool_helpers.c

Replace strncpy() calls in bpftool_helpers.c with strscpy().

Pass the destination buffer size to detect_bpftool_path() instead of
hardcoding BPFTOOL_PATH_MAX_LEN.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-5-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpftool_helpers.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c
index a5824945a4a5..595a636fa13b 100644
--- a/tools/testing/selftests/bpf/bpftool_helpers.c
+++ b/tools/testing/selftests/bpf/bpftool_helpers.c
@@ -1,15 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include "bpftool_helpers.h"
 #include <unistd.h>
 #include <string.h>
 #include <stdbool.h>
 
+#include "bpf_util.h"
+#include "bpftool_helpers.h"
+
 #define BPFTOOL_PATH_MAX_LEN		64
 #define BPFTOOL_FULL_CMD_MAX_LEN	512
 
 #define BPFTOOL_DEFAULT_PATH		"tools/sbin/bpftool"
 
-static int detect_bpftool_path(char *buffer)
+static int detect_bpftool_path(char *buffer, size_t size)
 {
 	char tmp[BPFTOOL_PATH_MAX_LEN];
 
@@ -18,7 +20,7 @@ static int detect_bpftool_path(char *buffer)
 	 */
 	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "./%s", BPFTOOL_DEFAULT_PATH);
 	if (access(tmp, X_OK) == 0) {
-		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		strscpy(buffer, tmp, size);
 		return 0;
 	}
 
@@ -27,7 +29,7 @@ static int detect_bpftool_path(char *buffer)
 	 */
 	snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "../%s", BPFTOOL_DEFAULT_PATH);
 	if (access(tmp, X_OK) == 0) {
-		strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN);
+		strscpy(buffer, tmp, size);
 		return 0;
 	}
 
@@ -44,7 +46,7 @@ static int run_command(char *args, char *output_buf, size_t output_max_len)
 	int ret;
 
 	/* Detect and cache bpftool binary location */
-	if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path))
+	if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path, sizeof(bpftool_path)))
 		return 1;
 
 	ret = snprintf(command, BPFTOOL_FULL_CMD_MAX_LEN, "%s %s%s",
-- 
cgit v1.2.3


From 9d8685239e85ba5a4899b5b3534c732e3ae5f2aa Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:21 -0800
Subject: selftests/bpf: Use memcpy() for bounded non-NULL-terminated copies

Replace strncpy() with memcpy() in cases where the source is
non-NULL-terminated and the copy length is known.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-6-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c | 6 ++++--
 tools/testing/selftests/bpf/test_verifier.c          | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
index dd75ccb03770..469e92869523 100644
--- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -308,8 +308,10 @@ static int find_field_offset(struct btf *btf, char *pattern, regmatch_t *matches
 		return -1;
 	}
 
-	strncpy(type_str, type, type_sz);
-	strncpy(field_str, field, field_sz);
+	memcpy(type_str, type, type_sz);
+	type_str[type_sz] = '\0';
+	memcpy(field_str, field, field_sz);
+	field_str[field_sz] = '\0';
 	btf_id = btf__find_by_name(btf, type_str);
 	if (btf_id < 0) {
 		PRINT_FAIL("No BTF info for type %s\n", type_str);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 27db34ecf3f5..a8ae03c57bba 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1320,7 +1320,7 @@ static bool cmp_str_seq(const char *log, const char *exp)
 			printf("FAIL\nTestcase bug\n");
 			return false;
 		}
-		strncpy(needle, exp, len);
+		memcpy(needle, exp, len);
 		needle[len] = 0;
 		q = strstr(log, needle);
 		if (!q) {
-- 
cgit v1.2.3


From 4021848a903e65f74cf88997c12b96d6bc2453e6 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:22 -0800
Subject: selftests/bpf: Pass through build flags to bpftool and resolve_btfids

EXTRA_* and SAN_* build flags were not correctly propagated to bpftool
and resolve_btids when building selftests/bpf. This led to various
build errors on attempt to build with SAN_CFLAGS="-fsanitize=address",
for example.

Fix the makefiles to address this:
  - Pass SAN_CFLAGS/SAN_LDFLAGS to bpftool and resolve_btfids build
  - Propagate EXTRA_LDFLAGS to resolve_btfids link command
  - Use pkg-config to detect zlib and zstd for resolve_btfids, similar
    libelf handling

Also check for ASAN flag in selftests/bpf/Makefile for convenience.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-7-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/Makefile    |  7 +++++--
 tools/testing/selftests/bpf/Makefile | 13 +++++++++----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 1733a6e93a07..ef083602b73a 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -65,6 +65,9 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU
 LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
 LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
 
+ZLIB_LIBS  := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz)
+ZSTD_LIBS  := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd)
+
 HOSTCFLAGS_resolve_btfids += -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
@@ -73,7 +76,7 @@ HOSTCFLAGS_resolve_btfids += -g \
           $(LIBELF_FLAGS) \
           -Wall -Werror
 
-LIBS = $(LIBELF_LIBS) -lz
+LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS)
 
 export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR
 include $(srctree)/tools/build/Makefile.include
@@ -83,7 +86,7 @@ $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT)
 
 $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
 	$(call msg,LINK,$@)
-	$(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
+	$(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) $(EXTRA_LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS)
 
 clean_objects := $(wildcard $(OUTPUT)/*.o                \
                             $(OUTPUT)/.*.o.cmd           \
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6776158f1f3e..72a9ba41f95e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -27,7 +27,11 @@ ifneq ($(wildcard $(GENHDR)),)
 endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
+ifdef ASAN
+SAN_CFLAGS 	?= -fsanitize=address -fno-omit-frame-pointer
+else
 SAN_CFLAGS	?=
+endif
 SAN_LDFLAGS	?= $(SAN_CFLAGS)
 RELEASE		?=
 OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
@@ -326,8 +330,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
 		    ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" 	       \
-		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'	       \
-		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'			       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)'			       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
 		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
@@ -338,8 +342,8 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
 		    $(BPFOBJ) | $(BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
 		    ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE)			\
-		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'		\
-		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'				\
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)'			       \
 		    OUTPUT=$(BUILD_DIR)/bpftool/				\
 		    LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/				\
 		    LIBBPF_DESTDIR=$(SCRATCH_DIR)/				\
@@ -404,6 +408,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids	\
 		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
+		EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-- 
cgit v1.2.3


From c5c1e313493cd836863bb673bb2b8beaa915cad9 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:23 -0800
Subject: resolve_btfids: Fix memory leaks reported by ASAN

Running resolve_btfids with ASAN reveals memory leaks in btf_id
handling.

- Change get_id() to use a local buffer
- Make btf_id__add() strdup the name internally
- Add btf_id__free_all() that frees all nodese of a tree
- Call the cleanup function on exit for every tree

Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-8-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/main.c | 81 +++++++++++++++++++++++++++--------------
 1 file changed, 54 insertions(+), 27 deletions(-)

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index ca7fcd03efb6..5208f650080f 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -226,7 +226,7 @@ static struct btf_id *btf_id__find(struct rb_root *root, const char *name)
 }
 
 static struct btf_id *__btf_id__add(struct rb_root *root,
-				    char *name,
+				    const char *name,
 				    enum btf_id_kind kind,
 				    bool unique)
 {
@@ -250,7 +250,11 @@ static struct btf_id *__btf_id__add(struct rb_root *root,
 	id = zalloc(sizeof(*id));
 	if (id) {
 		pr_debug("adding symbol %s\n", name);
-		id->name = name;
+		id->name = strdup(name);
+		if (!id->name) {
+			free(id);
+			return NULL;
+		}
 		id->kind = kind;
 		rb_link_node(&id->rb_node, parent, p);
 		rb_insert_color(&id->rb_node, root);
@@ -258,17 +262,21 @@ static struct btf_id *__btf_id__add(struct rb_root *root,
 	return id;
 }
 
-static inline struct btf_id *btf_id__add(struct rb_root *root, char *name, enum btf_id_kind kind)
+static inline struct btf_id *btf_id__add(struct rb_root *root,
+					 const char *name,
+					 enum btf_id_kind kind)
 {
 	return __btf_id__add(root, name, kind, false);
 }
 
-static inline struct btf_id *btf_id__add_unique(struct rb_root *root, char *name, enum btf_id_kind kind)
+static inline struct btf_id *btf_id__add_unique(struct rb_root *root,
+						const char *name,
+						enum btf_id_kind kind)
 {
 	return __btf_id__add(root, name, kind, true);
 }
 
-static char *get_id(const char *prefix_end)
+static int get_id(const char *prefix_end, char *buf, size_t buf_sz)
 {
 	/*
 	 * __BTF_ID__func__vfs_truncate__0
@@ -277,28 +285,28 @@ static char *get_id(const char *prefix_end)
 	 */
 	int len = strlen(prefix_end);
 	int pos = sizeof("__") - 1;
-	char *p, *id;
+	char *p;
 
 	if (pos >= len)
-		return NULL;
+		return -1;
 
-	id = strdup(prefix_end + pos);
-	if (id) {
-		/*
-		 * __BTF_ID__func__vfs_truncate__0
-		 * id =            ^
-		 *
-		 * cut the unique id part
-		 */
-		p = strrchr(id, '_');
-		p--;
-		if (*p != '_') {
-			free(id);
-			return NULL;
-		}
-		*p = '\0';
-	}
-	return id;
+	if (len - pos >= buf_sz)
+		return -1;
+
+	strcpy(buf, prefix_end + pos);
+	/*
+	 * __BTF_ID__func__vfs_truncate__0
+	 * buf =           ^
+	 *
+	 * cut the unique id part
+	 */
+	p = strrchr(buf, '_');
+	p--;
+	if (*p != '_')
+		return -1;
+	*p = '\0';
+
+	return 0;
 }
 
 static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind kind)
@@ -335,10 +343,9 @@ static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind k
 
 static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 {
-	char *id;
+	char id[KSYM_NAME_LEN];
 
-	id = get_id(name + size);
-	if (!id) {
+	if (get_id(name + size, id, sizeof(id))) {
 		pr_err("FAILED to parse symbol name: %s\n", name);
 		return NULL;
 	}
@@ -346,6 +353,21 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, BTF_ID_KIND_SYM);
 }
 
+static void btf_id__free_all(struct rb_root *root)
+{
+	struct rb_node *next;
+	struct btf_id *id;
+
+	next = rb_first(root);
+	while (next) {
+		id = rb_entry(next, struct btf_id, rb_node);
+		next = rb_next(&id->rb_node);
+		rb_erase(&id->rb_node, root);
+		free(id->name);
+		free(id);
+	}
+}
+
 static void bswap_32_data(void *data, u32 nr_bytes)
 {
 	u32 cnt, i;
@@ -1547,6 +1569,11 @@ dump_btf:
 out:
 	btf__free(obj.base_btf);
 	btf__free(obj.btf);
+	btf_id__free_all(&obj.structs);
+	btf_id__free_all(&obj.unions);
+	btf_id__free_all(&obj.typedefs);
+	btf_id__free_all(&obj.funcs);
+	btf_id__free_all(&obj.sets);
 	if (obj.efile.elf) {
 		elf_end(obj.efile.elf);
 		close(obj.efile.fd);
-- 
cgit v1.2.3


From 45897ced3c1d3940fb5b68fe48c9e144143ae0ae Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:24 -0800
Subject: selftests/bpf: Add DENYLIST.asan

Add a denylist file for tests that should be skipped when built with
userspace ASAN:

    $ make ... SAN_CFLAGS="-fsanitize=address -fno-omit-frame-pointer"

Skip the following tests:

- *arena*: userspace ASAN does not understand BPF arena maps and gets
  confused particularly when map_extra is non-zero
  - non-zero map_extra leads to mmap with MAP_FIXED, and ASAN treats
    this as an unknown memory region
- task_local_data: ASAN complains about "incorrect" aligned_alloc()
  usage, but it's intentional in the test
- uprobe_multi_test: very slow with ASAN enabled

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-9-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/DENYLIST.asan | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/DENYLIST.asan

diff --git a/tools/testing/selftests/bpf/DENYLIST.asan b/tools/testing/selftests/bpf/DENYLIST.asan
new file mode 100644
index 000000000000..d7fe372a2293
--- /dev/null
+++ b/tools/testing/selftests/bpf/DENYLIST.asan
@@ -0,0 +1,3 @@
+*arena*
+task_local_data
+uprobe_multi_test
-- 
cgit v1.2.3


From a1a771bd649212ef32cf9b0bcc63213a762d354a Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:25 -0800
Subject: selftests/bpf: Refactor bpf_get_ksyms() trace helper

ASAN reported a memory leak in bpf_get_ksyms(): it allocates a struct
ksyms internally and never frees it.

Move struct ksyms to trace_helpers.h and return it from the
bpf_get_ksyms(), giving ownership to the caller. Add filtered_syms and
filtered_cnt fields to the ksyms to hold the filtered array of
symbols, previously returned by bpf_get_ksyms().

Fixup the call sites: kprobe_multi_test and bench_trigger.

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260223190736.649171-10-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/benchs/bench_trigger.c | 14 +++++++------
 .../selftests/bpf/prog_tests/kprobe_multi_test.c   | 12 +++++------
 tools/testing/selftests/bpf/trace_helpers.c        | 23 +++++++++++-----------
 tools/testing/selftests/bpf/trace_helpers.h        | 11 +++++++++--
 4 files changed, 34 insertions(+), 26 deletions(-)

diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index aeec9edd3851..f74b313d6ae4 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -230,8 +230,8 @@ static void trigger_fentry_setup(void)
 static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
-	char **syms = NULL;
-	size_t cnt = 0;
+	struct bpf_link *link = NULL;
+	struct ksyms *ksyms = NULL;
 
 	/* Some recursive functions will be skipped in
 	 * bpf_get_ksyms -> skip_entry, as they can introduce sufficient
@@ -241,16 +241,18 @@ static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
 	 * So, don't run the kprobe-multi-all and kretprobe-multi-all on
 	 * a debug kernel.
 	 */
-	if (bpf_get_ksyms(&syms, &cnt, true)) {
+	if (bpf_get_ksyms(&ksyms, true)) {
 		fprintf(stderr, "failed to get ksyms\n");
 		exit(1);
 	}
 
-	opts.syms = (const char **) syms;
-	opts.cnt = cnt;
+	opts.syms = (const char **)ksyms->filtered_syms;
+	opts.cnt = ksyms->filtered_cnt;
 	opts.retprobe = kretprobe;
 	/* attach empty to all the kernel functions except bpf_get_numa_node_id. */
-	if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) {
+	link = bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts);
+	free_kallsyms_local(ksyms);
+	if (!link) {
 		fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n");
 		exit(1);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index 9caef222e528..f81dcd609ee9 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -456,25 +456,23 @@ static void test_kprobe_multi_bench_attach(bool kernel)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	struct kprobe_multi_empty *skel = NULL;
-	char **syms = NULL;
-	size_t cnt = 0;
+	struct ksyms *ksyms = NULL;
 
-	if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms"))
+	if (!ASSERT_OK(bpf_get_ksyms(&ksyms, kernel), "bpf_get_ksyms"))
 		return;
 
 	skel = kprobe_multi_empty__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
 		goto cleanup;
 
-	opts.syms = (const char **) syms;
-	opts.cnt = cnt;
+	opts.syms = (const char **)ksyms->filtered_syms;
+	opts.cnt = ksyms->filtered_cnt;
 
 	do_bench_test(skel, &opts);
 
 cleanup:
 	kprobe_multi_empty__destroy(skel);
-	if (syms)
-		free(syms);
+	free_kallsyms_local(ksyms);
 }
 
 static void test_kprobe_multi_bench_attach_addr(bool kernel)
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index eeaab7013ca2..0e63daf83ed5 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -24,12 +24,6 @@
 #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
 #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
 
-struct ksyms {
-	struct ksym *syms;
-	size_t sym_cap;
-	size_t sym_cnt;
-};
-
 static struct ksyms *ksyms;
 static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
 
@@ -54,6 +48,8 @@ void free_kallsyms_local(struct ksyms *ksyms)
 	if (!ksyms)
 		return;
 
+	free(ksyms->filtered_syms);
+
 	if (!ksyms->syms) {
 		free(ksyms);
 		return;
@@ -610,7 +606,7 @@ static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
 	return compare_name(p1, p2->name);
 }
 
-int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
+int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel)
 {
 	size_t cap = 0, cnt = 0;
 	char *name = NULL, *ksym_name, **syms = NULL;
@@ -637,8 +633,10 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
 	else
 		f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
 
-	if (!f)
+	if (!f) {
+		free_kallsyms_local(ksyms);
 		return -EINVAL;
+	}
 
 	map = hashmap__new(symbol_hash, symbol_equal, NULL);
 	if (IS_ERR(map)) {
@@ -679,15 +677,18 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
 		syms[cnt++] = ksym_name;
 	}
 
-	*symsp = syms;
-	*cntp = cnt;
+	ksyms->filtered_syms = syms;
+	ksyms->filtered_cnt = cnt;
+	*ksymsp = ksyms;
 
 error:
 	free(name);
 	fclose(f);
 	hashmap__free(map);
-	if (err)
+	if (err) {
 		free(syms);
+		free_kallsyms_local(ksyms);
+	}
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index a5576b2dfc26..d5bf1433675d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -23,7 +23,14 @@ struct ksym {
 	long addr;
 	char *name;
 };
-struct ksyms;
+
+struct ksyms {
+	struct ksym *syms;
+	size_t sym_cap;
+	size_t sym_cnt;
+	char **filtered_syms;
+	size_t filtered_cnt;
+};
 
 typedef int (*ksym_cmp_t)(const void *p1, const void *p2);
 typedef int (*ksym_search_cmp_t)(const void *p1, const struct ksym *p2);
@@ -53,7 +60,7 @@ ssize_t get_rel_offset(uintptr_t addr);
 
 int read_build_id(const char *path, char *build_id, size_t size);
 
-int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel);
+int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel);
 int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel);
 
 #endif
-- 
cgit v1.2.3


From 9d0272c91fbc3ae86f2c3b6ba0a0b0ee77d862e3 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:26 -0800
Subject: selftests/bpf: Fix memory leaks in tests

Fix trivial memory leaks detected by userspace ASAN:
  - htab_update: free value buffer in test_reenter_update cleanup
  - test_xsk: inline pkt_stream_replace() in testapp_stats_rx_full()
    and testapp_stats_fill_empty()
  - testing_helpers: free buffer allocated by getline() in
    parse_test_list_file

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-11-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/prog_tests/htab_update.c |  1 +
 tools/testing/selftests/bpf/prog_tests/test_xsk.c  | 24 ++++++++++++++++++----
 tools/testing/selftests/bpf/testing_helpers.c      |  1 +
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c
index d0b405eb2966..ea1a6766fbe9 100644
--- a/tools/testing/selftests/bpf/prog_tests/htab_update.c
+++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c
@@ -61,6 +61,7 @@ static void test_reenter_update(void)
 
 	ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy");
 out:
+	free(value);
 	htab_update__destroy(skel);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index bab4a31621c7..7e38ec6e656b 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -2003,9 +2003,17 @@ int testapp_stats_tx_invalid_descs(struct test_spec *test)
 
 int testapp_stats_rx_full(struct test_spec *test)
 {
-	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+	struct pkt_stream *tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
+	if (!tmp)
+		return TEST_FAILURE;
+	test->ifobj_tx->xsk->pkt_stream = tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	if (!tmp)
 		return TEST_FAILURE;
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = tmp;
 
 	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
 	test->ifobj_rx->release_rx = false;
@@ -2015,9 +2023,17 @@ int testapp_stats_rx_full(struct test_spec *test)
 
 int testapp_stats_fill_empty(struct test_spec *test)
 {
-	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+	struct pkt_stream *tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE);
+	if (!tmp)
+		return TEST_FAILURE;
+	test->ifobj_tx->xsk->pkt_stream = tmp;
+
+	tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	if (!tmp)
 		return TEST_FAILURE;
-	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+	test->ifobj_rx->xsk->pkt_stream = tmp;
 
 	test->ifobj_rx->use_fill_ring = false;
 	test->ifobj_rx->validation_func = validate_fill_empty;
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 16eb37e5bad6..66af0d13751a 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -212,6 +212,7 @@ int parse_test_list_file(const char *path,
 			break;
 	}
 
+	free(buf);
 	fclose(f);
 	return err;
 }
-- 
cgit v1.2.3


From 3eb4a2e399c6766ea0c8291e2adb5e6dc42b6e68 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:27 -0800
Subject: selftests/bpf: Fix cleanup in check_fd_array_cnt__fd_array_too_big()

The Close() macro uses the passed in expression three times, which
leads to repeated execution in case it has side effects. That is,
Close(i--) would decrement i three times.

ASAN caught a stack-buffer-undeflow error at a point where this was
overlooked. Fix it.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-12-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/fd_array.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index c534b4d5f9da..3078d8264deb 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -412,8 +412,8 @@ static void check_fd_array_cnt__fd_array_too_big(void)
 	ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG");
 
 cleanup_fds:
-	while (i > 0)
-		Close(extra_fds[--i]);
+	while (i-- > 0)
+		Close(extra_fds[i]);
 }
 
 void test_fd_array_cnt(void)
-- 
cgit v1.2.3


From ff9511410d5fbdec21a3bbfaa477aa1f56735b33 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:28 -0800
Subject: veristat: Fix a memory leak for preset ENUMERATOR

ASAN detected a memory leak in veristat. The cleanup code handling
ENUMERATOR value missed freeing strdup-ed svalue. Fix it.

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-13-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/veristat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 1be1e353d40a..75f85e0362f5 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -3378,6 +3378,8 @@ int main(int argc, char **argv)
 			}
 		}
 		free(env.presets[i].atoms);
+		if (env.presets[i].value.type == ENUMERATOR)
+			free(env.presets[i].value.svalue);
 	}
 	free(env.presets);
 	return -err;
-- 
cgit v1.2.3


From f7ac552be7f13e834a942f64b1ac87e7755b32f4 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:29 -0800
Subject: selftests/bpf: Fix use-after-free in xdp_metadata test

ASAN reported a use-after-free in close_xsk().

The xsk->socket internally references xsk->umem via socket->ctx->umem,
so the socket must be deleted before the umem. Fix the order of
operations in close_xsk().

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-14-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index 19f92affc2da..5c31054ad4a4 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -126,10 +126,10 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 
 static void close_xsk(struct xsk *xsk)
 {
-	if (xsk->umem)
-		xsk_umem__delete(xsk->umem);
 	if (xsk->socket)
 		xsk_socket__delete(xsk->socket);
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
 	munmap(xsk->umem_area, UMEM_SIZE);
 }
 
-- 
cgit v1.2.3


From 68b8bea1eec392aa50736a859b8f1418067a3bc4 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:30 -0800
Subject: selftests/bpf: Fix double thread join in uprobe_multi_test

ASAN reported a "joining already joined thread" error. The
release_child() may be called multiple times for the same struct
child.

Fix by resetting child->thread to 0 after pthread_join.

Also memset(0) static child variable in test_attach_api().

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-15-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 2ee17ef1dae2..56cbea280fbd 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -62,8 +62,10 @@ static void release_child(struct child *child)
 		return;
 	close(child->go[1]);
 	close(child->go[0]);
-	if (child->thread)
+	if (child->thread) {
 		pthread_join(child->thread, NULL);
+		child->thread = 0;
+	}
 	close(child->c2p[0]);
 	close(child->c2p[1]);
 	if (child->pid > 0)
@@ -331,6 +333,8 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi
 {
 	static struct child child;
 
+	memset(&child, 0, sizeof(child));
+
 	/* no pid filter */
 	__test_attach_api(binary, pattern, opts, NULL);
 
-- 
cgit v1.2.3


From 71dca2950fe9abf8e6fd3d9f5e6342da6634b898 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:31 -0800
Subject: selftests/bpf: Fix resource leaks caused by missing cleanups

ASAN reported a number of resource leaks:
  - Add missing  *__destroy(skel) calls
  - Replace bpf_link__detach() with bpf_link__destroy() where appropriate
  - cgrp_local_storage: Add bpf_link__destroy() when bpf_iter_create fails
  - dynptr: Add missing bpf_object__close()

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-16-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/cgrp_local_storage.c  |  4 +++-
 tools/testing/selftests/bpf/prog_tests/dynptr.c    |  5 +++-
 .../selftests/bpf/prog_tests/sockmap_basic.c       | 28 +++++++++++-----------
 .../selftests/bpf/prog_tests/sockmap_listen.c      |  2 +-
 .../bpf/prog_tests/struct_ops_private_stack.c      |  4 +---
 tools/testing/selftests/bpf/prog_tests/tc_opts.c   |  6 ++---
 .../selftests/bpf/prog_tests/test_tc_tunnel.c      |  5 +++-
 7 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
index 9015e2c2ab12..478a77cb67e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -202,7 +202,7 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 
 	iter_fd = bpf_iter_create(bpf_link__fd(link));
 	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
-		goto out;
+		goto out_link;
 
 	/* trigger the program run */
 	(void)read(iter_fd, buf, sizeof(buf));
@@ -210,6 +210,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 	ASSERT_EQ(skel->bss->cgroup_id, cgroup_id, "cgroup_id");
 
 	close(iter_fd);
+out_link:
+	bpf_link__destroy(link);
 out:
 	cgrp_ls_sleepable__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index b9f86cb91e81..5fda11590708 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -137,11 +137,14 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 		);
 
 		link = bpf_program__attach(prog);
-		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach")) {
+			bpf_object__close(obj);
 			goto cleanup;
+		}
 
 		err = bpf_prog_test_run_opts(aux_prog_fd, &topts);
 		bpf_link__destroy(link);
+		bpf_object__close(obj);
 
 		if (!ASSERT_OK(err, "test_run"))
 			goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 256707e7d20d..dd3c757859f6 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -204,7 +204,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type)
 	/* Fail since bpf_link for the same prog type has been created. */
 	link2 = bpf_program__attach_sockmap(prog_clone, map);
 	if (!ASSERT_ERR_PTR(link2, "bpf_program__attach_sockmap")) {
-		bpf_link__detach(link2);
+		bpf_link__destroy(link2);
 		goto out;
 	}
 
@@ -230,7 +230,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type)
 	if (!ASSERT_OK(err, "bpf_link_update"))
 		goto out;
 out:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 	test_skmsg_load_helpers__destroy(skel);
 }
 
@@ -417,7 +417,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void)
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
 		goto out;
 
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 
 	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
@@ -426,7 +426,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void)
 	/* Fail since attaching with the same prog/map has been done. */
 	link = bpf_program__attach_sockmap(prog, map);
 	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_sockmap"))
-		bpf_link__detach(link);
+		bpf_link__destroy(link);
 
 	err = bpf_prog_detach2(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT);
 	if (!ASSERT_OK(err, "bpf_prog_detach2"))
@@ -747,13 +747,13 @@ static void test_sockmap_skb_verdict_peek_with_link(void)
 	test_sockmap_skb_verdict_peek_helper(map);
 	ASSERT_EQ(pass->bss->clone_called, 1, "clone_called");
 out:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 	test_sockmap_pass_prog__destroy(pass);
 }
 
 static void test_sockmap_unconnected_unix(void)
 {
-	int err, map, stream = 0, dgram = 0, zero = 0;
+	int err, map, stream = -1, dgram = -1, zero = 0;
 	struct test_sockmap_pass_prog *skel;
 
 	skel = test_sockmap_pass_prog__open_and_load();
@@ -764,22 +764,22 @@ static void test_sockmap_unconnected_unix(void)
 
 	stream = xsocket(AF_UNIX, SOCK_STREAM, 0);
 	if (stream < 0)
-		return;
+		goto out;
 
 	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
-	if (dgram < 0) {
-		close(stream);
-		return;
-	}
+	if (dgram < 0)
+		goto out;
 
 	err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY);
-	ASSERT_ERR(err, "bpf_map_update_elem(stream)");
+	if (!ASSERT_ERR(err, "bpf_map_update_elem(stream)"))
+		goto out;
 
 	err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
 	ASSERT_OK(err, "bpf_map_update_elem(dgram)");
-
+out:
 	close(stream);
 	close(dgram);
+	test_sockmap_pass_prog__destroy(skel);
 }
 
 static void test_sockmap_many_socket(void)
@@ -1027,7 +1027,7 @@ static void test_sockmap_skb_verdict_vsock_poll(void)
 	if (xrecv_nonblock(conn, &buf, 1, 0) != 1)
 		FAIL("xrecv_nonblock");
 detach:
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 close:
 	xclose(conn);
 	xclose(peer);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index f1bdccc7e4e7..cc0c68bab907 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -899,7 +899,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk
 
 	redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
 
-	bpf_link__detach(link);
+	bpf_link__destroy(link);
 }
 
 static void redir_partial(int family, int sotype, int sock_map, int parser_map)
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
index 4006879ca3fe..d42123a0fb16 100644
--- a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
@@ -54,9 +54,7 @@ static void test_private_stack_fail(void)
 	}
 
 	err = struct_ops_private_stack_fail__load(skel);
-	if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load"))
-		goto cleanup;
-	return;
+	ASSERT_ERR(err, "struct_ops_private_stack_fail__load");
 
 cleanup:
 	struct_ops_private_stack_fail__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index dd7a138d8c3d..2955750ddada 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -1360,10 +1360,8 @@ static void test_tc_opts_dev_cleanup_target(int target)
 
 	assert_mprog_count_ifindex(ifindex, target, 4);
 
-	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
-	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
-	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
-	return;
+	goto cleanup;
+
 cleanup3:
 	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
 	ASSERT_OK(err, "prog_detach");
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
index 0fe0a8f62486..7fc4d7dd70ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
@@ -699,7 +699,7 @@ void test_tc_tunnel(void)
 		return;
 
 	if (!ASSERT_OK(setup(), "global setup"))
-		return;
+		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) {
 		cfg = &subtests_cfg[i];
@@ -711,4 +711,7 @@ void test_tc_tunnel(void)
 		subtest_cleanup(cfg);
 	}
 	cleanup();
+
+out:
+	test_tc_tunnel__destroy(skel);
 }
-- 
cgit v1.2.3


From 2bb270a0ac68990648c5e84abf73bb7493230ea6 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:32 -0800
Subject: selftests/bpf: Free bpf_object in test_sysctl

ASAN reported a resource leak due to the bpf_object not being tracked
in test_sysctl. Add obj field to struct sysctl_test to properly clean
it up.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-17-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/test_sysctl.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
index 273dd41ca09e..2a1ff821bc97 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -27,6 +27,7 @@ struct sysctl_test {
 		OP_EPERM,
 		SUCCESS,
 	} result;
+	struct bpf_object *obj;
 };
 
 static struct sysctl_test tests[] = {
@@ -1471,6 +1472,7 @@ static int load_sysctl_prog_file(struct sysctl_test *test)
 		return -1;
 	}
 
+	test->obj = obj;
 	return prog_fd;
 }
 
@@ -1573,6 +1575,7 @@ out:
 	/* Detaching w/o checking return code: best effort attempt. */
 	if (progfd != -1)
 		bpf_prog_detach(cgfd, atype);
+	bpf_object__close(test->obj);
 	close(progfd);
 	printf("[%s]\n", err ? "FAIL" : "PASS");
 	return err;
-- 
cgit v1.2.3


From 3e711c8e4707c46cc45d9775b50204d0f2790d77 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:07:33 -0800
Subject: selftests/bpf: Fix array bounds warning in jit_disasm_helpers

Compiler cannot infer upper bound for labels.cnt and warns about
potential buffer overflow in snprintf. Add an explicit bounds
check (... && i < MAX_LOCAL_LABELS) in the loop condition to fix the
warning.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223190736.649171-18-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/jit_disasm_helpers.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
index febd6b12e372..364c557c5115 100644
--- a/tools/testing/selftests/bpf/jit_disasm_helpers.c
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -122,15 +122,15 @@ static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len)
 		pc += cnt;
 	}
 	qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
-	for (i = 0; i < labels.cnt; ++i)
-		/* gcc is unable to infer upper bound for labels.cnt and assumes
-		 * it to be U32_MAX. U32_MAX takes 10 decimal digits.
-		 * snprintf below prints into labels.names[*],
-		 * which has space only for two digits and a letter.
-		 * To avoid truncation warning use (i % MAX_LOCAL_LABELS),
-		 * which informs gcc about printed value upper bound.
-		 */
-		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS);
+	/* gcc is unable to infer upper bound for labels.cnt and
+	 * assumes it to be U32_MAX. U32_MAX takes 10 decimal digits.
+	 * snprintf below prints into labels.names[*], which has space
+	 * only for two digits and a letter.  To avoid truncation
+	 * warning use (i < MAX_LOCAL_LABELS), which informs gcc about
+	 * printed value upper bound.
+	 */
+	for (i = 0; i < labels.cnt && i < MAX_LOCAL_LABELS; ++i)
+		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i);
 
 	/* now print with labels */
 	labels.print_phase = true;
-- 
cgit v1.2.3


From ad90ecedad755e2f3e31364ec3130e5bb2f4b64a Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:16 -0800
Subject: selftests/bpf: Fix out-of-bounds array access bugs reported by ASAN

- kmem_cache_iter: remove unnecessary debug output
- lwt_seg6local: change the type of foobar to char[]
  - the sizeof(foobar) returned the pointer size and not a string
    length as intended
- verifier_log: increase prog_name buffer size in verif_log_subtest()
  - compiler has a conservative estimate of fixed_log_sz value, making
    ASAN complain on snprint() call

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c | 7 ++-----
 tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c   | 2 +-
 tools/testing/selftests/bpf/prog_tests/verifier_log.c    | 2 +-
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
index 6e35e13c2022..399fe9103f83 100644
--- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
@@ -104,11 +104,8 @@ void test_kmem_cache_iter(void)
 	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
 		goto destroy;
 
-	memset(buf, 0, sizeof(buf));
-	while (read(iter_fd, buf, sizeof(buf)) > 0) {
-		/* Read out all contents */
-		printf("%s", buf);
-	}
+	while (read(iter_fd, buf, sizeof(buf)) > 0)
+		; /* Read out all contents */
 
 	/* Next reads should return 0 */
 	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
index 3bc730b7c7fa..1b25d5c5f8fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
@@ -117,7 +117,7 @@ void test_lwt_seg6local(void)
 	const char *ns1 = NETNS_BASE "1";
 	const char *ns6 = NETNS_BASE "6";
 	struct nstoken *nstoken = NULL;
-	const char *foobar = "foobar";
+	const char foobar[] = "foobar";
 	ssize_t bytes;
 	int sfd, cfd;
 	char buf[7];
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
index 8337c6bc5b95..aaa2854974c0 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier_log.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
@@ -47,7 +47,7 @@ static int load_prog(struct bpf_prog_load_opts *opts, bool expect_load_error)
 static void verif_log_subtest(const char *name, bool expect_load_error, int log_level)
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	char *exp_log, prog_name[16], op_name[32];
+	char *exp_log, prog_name[24], op_name[32];
 	struct test_log_buf *skel;
 	struct bpf_program *prog;
 	size_t fixed_log_sz;
-- 
cgit v1.2.3


From a2714e730304c79bf85d2178387255ef8348b897 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:17 -0800
Subject: selftests/bpf: Check BPFTOOL env var in detect_bpftool_path()

The bpftool_maps_access and bpftool_metadata tests may fail on BPF CI
with "command not found", depending on a workflow.
This happens because detect_bpftool_path() only checks two hardcoded
relative paths:
  - ./tools/sbin/bpftool
  - ../tools/sbin/bpftool

Add support for a BPFTOOL environment variable that allows specifying
the exact path to the bpftool binary.

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-2-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpftool_helpers.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c
index 595a636fa13b..929fc257f431 100644
--- a/tools/testing/selftests/bpf/bpftool_helpers.c
+++ b/tools/testing/selftests/bpf/bpftool_helpers.c
@@ -14,6 +14,17 @@
 static int detect_bpftool_path(char *buffer, size_t size)
 {
 	char tmp[BPFTOOL_PATH_MAX_LEN];
+	const char *env_path;
+
+	/* First, check if BPFTOOL environment variable is set */
+	env_path = getenv("BPFTOOL");
+	if (env_path && access(env_path, X_OK) == 0) {
+		strscpy(buffer, env_path, size);
+		return 0;
+	} else if (env_path) {
+		fprintf(stderr, "bpftool '%s' doesn't exist or is not executable\n", env_path);
+		return 1;
+	}
 
 	/* Check default bpftool location (will work if we are running the
 	 * default flavor of test_progs)
@@ -33,7 +44,7 @@ static int detect_bpftool_path(char *buffer, size_t size)
 		return 0;
 	}
 
-	/* Failed to find bpftool binary */
+	fprintf(stderr, "Failed to detect bpftool path, use BPFTOOL env var to override\n");
 	return 1;
 }
 
-- 
cgit v1.2.3


From 4c9d07865c06bb9b9faff1ecf6c4b7cc8f7d67a9 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Mon, 23 Feb 2026 11:11:18 -0800
Subject: selftests/bpf: Don't override SIGSEGV handler with ASAN

test_progs has custom SIGSEGV handler, which interferes with the
address sanitizer [1]. Add an #ifndef to avoid this.

Additionally, declare an __asan_on_error() to dump the test logs in
the same way it happens in the custom SIGSEGV handler.

[1] https://lore.kernel.org/bpf/73d832948b01dbc0ebc60d85574bdf8537f3a810.camel@gmail.com/

Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/20260223191118.655185-3-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 36 +++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index d1418ec1f351..0929f4a7bda4 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1261,14 +1261,8 @@ int get_bpf_max_tramp_links(void)
 	return ret;
 }
 
-#define MAX_BACKTRACE_SZ 128
-void crash_handler(int signum)
+static void dump_crash_log(void)
 {
-	void *bt[MAX_BACKTRACE_SZ];
-	size_t sz;
-
-	sz = backtrace(bt, ARRAY_SIZE(bt));
-
 	fflush(stdout);
 	stdout = env.stdout_saved;
 	stderr = env.stderr_saved;
@@ -1277,12 +1271,32 @@ void crash_handler(int signum)
 		env.test_state->error_cnt++;
 		dump_test_log(env.test, env.test_state, true, false, NULL);
 	}
+}
+
+#define MAX_BACKTRACE_SZ 128
+
+void crash_handler(int signum)
+{
+	void *bt[MAX_BACKTRACE_SZ];
+	size_t sz;
+
+	sz = backtrace(bt, ARRAY_SIZE(bt));
+
+	dump_crash_log();
+
 	if (env.worker_id != -1)
 		fprintf(stderr, "[%d]: ", env.worker_id);
 	fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
 	backtrace_symbols_fd(bt, sz, STDERR_FILENO);
 }
 
+#ifdef __SANITIZE_ADDRESS__
+void __asan_on_error(void)
+{
+	dump_crash_log();
+}
+#endif
+
 void hexdump(const char *prefix, const void *buf, size_t len)
 {
 	for (int i = 0; i < len; i++) {
@@ -1944,13 +1958,15 @@ int main(int argc, char **argv)
 		.parser = parse_arg,
 		.doc = argp_program_doc,
 	};
+	int err, i;
+
+#ifndef __SANITIZE_ADDRESS__
 	struct sigaction sigact = {
 		.sa_handler = crash_handler,
 		.sa_flags = SA_RESETHAND,
-		};
-	int err, i;
-
+	};
 	sigaction(SIGSEGV, &sigact, NULL);
+#endif
 
 	env.stdout_saved = stdout;
 	env.stderr_saved = stderr;
-- 
cgit v1.2.3


From 56e0a838277b12d48477b9c7478ceb5ae528ae2c Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawnguo@kernel.org>
Date: Tue, 24 Feb 2026 15:57:53 +0800
Subject: MAINTAINERS: Update Shawn Guo's address for HiSilicon PCIe controller
 driver

Shawn is no longer with Linaro.  Use his korg email address instead.

Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260224075753.122091-1-shawnguo@kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..f02f50c9d695 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20509,7 +20509,7 @@ F:	Documentation/devicetree/bindings/pci/hisilicon,kirin-pcie.yaml
 F:	drivers/pci/controller/dwc/pcie-kirin.c
 
 PCIE DRIVER FOR HISILICON STB
-M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Shawn Guo <shawnguo@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/hisilicon-histb-pcie.txt
-- 
cgit v1.2.3


From f69cfd8e8fd13b5d57e638fa1542fcd56f594ef0 Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu@kernel.org>
Date: Tue, 24 Feb 2026 17:08:28 +0000
Subject: x86/hyperv: print out reserved vectors in hexadecimal

Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/kernel/cpu/mshyperv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 89a2eb8a0722..9befdc557d9e 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -496,8 +496,9 @@ static void hv_reserve_irq_vectors(void)
 	    test_and_set_bit(HYPERV_DBG_FASTFAIL_VECTOR, system_vectors))
 		BUG();
 
-	pr_info("Hyper-V: reserve vectors: %d %d %d\n", HYPERV_DBG_ASSERT_VECTOR,
-		HYPERV_DBG_SERVICE_VECTOR, HYPERV_DBG_FASTFAIL_VECTOR);
+	pr_info("Hyper-V: reserve vectors: 0x%x 0x%x 0x%x\n",
+		HYPERV_DBG_ASSERT_VECTOR, HYPERV_DBG_SERVICE_VECTOR,
+		HYPERV_DBG_FASTFAIL_VECTOR);
 }
 
 static void __init ms_hyperv_init_platform(void)
-- 
cgit v1.2.3


From 30df81f2228d65bddf492db3929d9fcaffd38fc5 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Mon, 23 Feb 2026 14:56:09 +0800
Subject: scsi: ufs: core: Fix possible NULL pointer dereference in
 ufshcd_add_command_trace()

The kernel log indicates a crash in ufshcd_add_command_trace, due to a NULL
pointer dereference when accessing hwq->id.  This can happen if
ufshcd_mcq_req_to_hwq() returns NULL.

This patch adds a NULL check for hwq before accessing its id field to
prevent a kernel crash.

Kernel log excerpt:
[<ffffffd5d192dc4c>] notify_die+0x4c/0x8c
[<ffffffd5d1814e58>] __die+0x60/0xb0
[<ffffffd5d1814d64>] die+0x4c/0xe0
[<ffffffd5d181575c>] die_kernel_fault+0x74/0x88
[<ffffffd5d1864db4>] __do_kernel_fault+0x314/0x318
[<ffffffd5d2a3cdf8>] do_page_fault+0xa4/0x5f8
[<ffffffd5d2a3cd34>] do_translation_fault+0x34/0x54
[<ffffffd5d1864524>] do_mem_abort+0x50/0xa8
[<ffffffd5d2a297dc>] el1_abort+0x3c/0x64
[<ffffffd5d2a29718>] el1h_64_sync_handler+0x44/0xcc
[<ffffffd5d181133c>] el1h_64_sync+0x80/0x88
[<ffffffd5d255c1dc>] ufshcd_add_command_trace+0x23c/0x320
[<ffffffd5d255bad8>] ufshcd_compl_one_cqe+0xa4/0x404
[<ffffffd5d2572968>] ufshcd_mcq_poll_cqe_lock+0xac/0x104
[<ffffffd5d11c7460>] ufs_mtk_mcq_intr+0x54/0x74 [ufs_mediatek_mod]
[<ffffffd5d19ab92c>] __handle_irq_event_percpu+0xc8/0x348
[<ffffffd5d19abca8>] handle_irq_event+0x3c/0xa8
[<ffffffd5d19b1f0c>] handle_fasteoi_irq+0xf8/0x294
[<ffffffd5d19aa778>] generic_handle_domain_irq+0x54/0x80
[<ffffffd5d18102bc>] gic_handle_irq+0x1d4/0x330
[<ffffffd5d1838210>] call_on_irq_stack+0x44/0x68
[<ffffffd5d183af30>] do_interrupt_handler+0x78/0xd8
[<ffffffd5d2a29c00>] el1_interrupt+0x48/0xa8
[<ffffffd5d2a29ba8>] el1h_64_irq_handler+0x14/0x24
[<ffffffd5d18113c4>] el1h_64_irq+0x80/0x88
[<ffffffd5d2527fb4>] arch_local_irq_enable+0x4/0x1c
[<ffffffd5d25282e4>] cpuidle_enter+0x34/0x54
[<ffffffd5d195a678>] do_idle+0x1dc/0x2f8
[<ffffffd5d195a7c4>] cpu_startup_entry+0x30/0x3c
[<ffffffd5d18155c4>] secondary_start_kernel+0x134/0x1ac
[<ffffffd5d18640bc>] __secondary_switched+0xc4/0xcc

Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223065657.2432447-1-peter.wang@mediatek.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 571a73860561..4dc7fbc2a6db 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -518,8 +518,8 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, struct scsi_cmnd *cmd,
 
 	if (hba->mcq_enabled) {
 		struct ufs_hw_queue *hwq = ufshcd_mcq_req_to_hwq(hba, rq);
-
-		hwq_id = hwq->id;
+		if (hwq)
+			hwq_id = hwq->id;
 	} else {
 		doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	}
-- 
cgit v1.2.3


From 62c015373e1cdb1cdca824bd2dbce2dac0819467 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Mon, 23 Feb 2026 18:37:57 +0800
Subject: scsi: ufs: core: Move link recovery for hibern8 exit failure to
 wl_resume

Move the link recovery trigger from ufshcd_uic_pwr_ctrl() to
__ufshcd_wl_resume(). Ensure link recovery is only attempted when hibern8
exit fails during resume, not during hibern8 enter in suspend. Improve
error handling and prevent unnecessary link recovery attempts.

Fixes: 35dabf4503b9 ("scsi: ufs: core: Use link recovery when h8 exit fails during runtime resume")
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223103906.2533654-1-peter.wang@mediatek.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4dc7fbc2a6db..85987373b961 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4390,14 +4390,6 @@ out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
-	/*
-	 * If the h8 exit fails during the runtime resume process, it becomes
-	 * stuck and cannot be recovered through the error handler.  To fix
-	 * this, use link recovery instead of the error handler.
-	 */
-	if (ret && hba->pm_op_in_progress)
-		ret = ufshcd_link_recovery(hba);
-
 	return ret;
 }
 
@@ -10200,7 +10192,15 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		} else {
 			dev_err(hba->dev, "%s: hibern8 exit failed %d\n",
 					__func__, ret);
-			goto vendor_suspend;
+			/*
+			 * If the h8 exit fails during the runtime resume
+			 * process, it becomes stuck and cannot be recovered
+			 * through the error handler. To fix this, use link
+			 * recovery instead of the error handler.
+			 */
+			ret = ufshcd_link_recovery(hba);
+			if (ret)
+				goto vendor_suspend;
 		}
 	} else if (ufshcd_is_link_off(hba)) {
 		/*
-- 
cgit v1.2.3


From 0902010c8d163f7b62e655efda1a843529152c7c Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 18:07:59 +0800
Subject: regulator: fp9931: Fix PM runtime reference leak in
 fp9931_hwmon_read()

In fp9931_hwmon_read(), if regmap_read() failed, the function returned
the error code without calling pm_runtime_put_autosuspend(), causing
a PM reference leak.

Fixes: 12d821bd13d4 ("regulator: Add FP9931/JD9930 driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Andreas Kemnade <andreas@kemnade.info>
Link: https://patch.msgid.link/20260224-fp9931-v1-1-1cf05cabef4a@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/fp9931.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/regulator/fp9931.c b/drivers/regulator/fp9931.c
index 7fbcc6327cc6..abea3b69d8a0 100644
--- a/drivers/regulator/fp9931.c
+++ b/drivers/regulator/fp9931.c
@@ -144,13 +144,12 @@ static int fp9931_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 		return ret;
 
 	ret = regmap_read(data->regmap, FP9931_REG_TMST_VALUE, &val);
-	if (ret)
-		return ret;
+	if (!ret)
+		*temp = (s8)val * 1000;
 
 	pm_runtime_put_autosuspend(data->dev);
-	*temp = (s8)val * 1000;
 
-	return 0;
+	return ret;
 }
 
 static umode_t fp9931_hwmon_is_visible(const void *data,
-- 
cgit v1.2.3


From 4baaddaa44af01cd4ce239493060738fd0881835 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 19:19:03 +0800
Subject: regulator: bq257xx: Fix device node reference leak in
 bq257xx_reg_dt_parse_gpio()

In bq257xx_reg_dt_parse_gpio(), if fails to get subchild, it returns
without calling of_node_put(child), causing the device node reference
leak.

Fixes: 981dd162b635 ("regulator: bq257xx: Add bq257xx boost regulator driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-bq257-v1-1-8ebbc731c1c3@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bq257xx-regulator.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/regulator/bq257xx-regulator.c b/drivers/regulator/bq257xx-regulator.c
index fc1ccede4468..dab8f1ab4450 100644
--- a/drivers/regulator/bq257xx-regulator.c
+++ b/drivers/regulator/bq257xx-regulator.c
@@ -115,11 +115,10 @@ static void bq257xx_reg_dt_parse_gpio(struct platform_device *pdev)
 		return;
 
 	subchild = of_get_child_by_name(child, pdata->desc.of_match);
+	of_node_put(child);
 	if (!subchild)
 		return;
 
-	of_node_put(child);
-
 	pdata->otg_en_gpio = devm_fwnode_gpiod_get_index(&pdev->dev,
 							 of_fwnode_handle(subchild),
 							 "enable", 0,
-- 
cgit v1.2.3


From bfd7db781e2e7a99b086d645a104d16e368f58ff Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 20:23:30 +0800
Subject: regulator: Kconfig: fix a typo

Fixes a typo in Kconfig, HWWON -> HWMON

Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-kconfig-v1-1-b0c5459ed7a0@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index a708fc63f581..d10b6f9243d5 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -508,7 +508,7 @@ config REGULATOR_FP9931
 	  This driver supports the FP9931/JD9930 voltage regulator chip
 	  which is used to provide power to Electronic Paper Displays
 	  so it is found in E-Book readers.
-	  If HWWON is enabled, it also provides temperature measurement.
+	  If HWMON is enabled, it also provides temperature measurement.
 
 config REGULATOR_LM363X
 	tristate "TI LM363X voltage regulators"
-- 
cgit v1.2.3


From e08f2adcf990b8cf272e90898401a9e481c1c667 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 24 Feb 2026 13:36:09 +0200
Subject: Revert "irqchip/ls-extirq: Use for_each_of_imap_item iterator"

This reverts commit 3ac6dfe3d7a2396602b67667249b146504dfbd2a.

The ls-extirq uses interrupt-map but it's a non-standard use documented
in fsl,ls-extirq.yaml:

        # The driver(drivers/irqchip/irq-ls-extirq.c) have not use standard DT
        # function to parser interrupt-map. So it doesn't consider '#address-size'
        # in parent interrupt controller, such as GIC.
        #
        # When dt-binding verify interrupt-map, item data matrix is spitted at
        # incorrect position. Remove interrupt-map restriction because it always
        # wrong.

This means that by using for_each_of_imap_item and the underlying
of_irq_parse_imap_parent() on its interrupt-map property will effectively
break its functionality

Revert the patch making use of for_each_of_imap_item() in ls-extirq.

Fixes: 3ac6dfe3d7a2 ("irqchip/ls-extirq: Use for_each_of_imap_item iterator")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Acked-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260224113610.1129022-2-ioana.ciornei@nxp.com
---
 drivers/irqchip/irq-ls-extirq.c | 47 ++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c
index a7e9c3885b09..96f9c20621cf 100644
--- a/drivers/irqchip/irq-ls-extirq.c
+++ b/drivers/irqchip/irq-ls-extirq.c
@@ -125,32 +125,45 @@ static const struct irq_domain_ops extirq_domain_ops = {
 static int
 ls_extirq_parse_map(struct ls_extirq_data *priv, struct device_node *node)
 {
-	struct of_imap_parser imap_parser;
-	struct of_imap_item imap_item;
+	const __be32 *map;
+	u32 mapsize;
 	int ret;
 
-	ret = of_imap_parser_init(&imap_parser, node, &imap_item);
-	if (ret)
-		return ret;
+	map = of_get_property(node, "interrupt-map", &mapsize);
+	if (!map)
+		return -ENOENT;
+	if (mapsize % sizeof(*map))
+		return -EINVAL;
+	mapsize /= sizeof(*map);
 
-	for_each_of_imap_item(&imap_parser, &imap_item) {
+	while (mapsize) {
 		struct device_node *ipar;
-		u32 hwirq;
-		int i;
+		u32 hwirq, intsize, j;
 
-		hwirq = imap_item.child_imap[0];
-		if (hwirq >= MAXIRQ) {
-			of_node_put(imap_item.parent_args.np);
+		if (mapsize < 3)
+			return -EINVAL;
+		hwirq = be32_to_cpup(map);
+		if (hwirq >= MAXIRQ)
 			return -EINVAL;
-		}
 		priv->nirq = max(priv->nirq, hwirq + 1);
 
-		ipar = of_node_get(imap_item.parent_args.np);
-		priv->map[hwirq].fwnode = of_fwnode_handle(ipar);
+		ipar = of_find_node_by_phandle(be32_to_cpup(map + 2));
+		map += 3;
+		mapsize -= 3;
+		if (!ipar)
+			return -EINVAL;
+		priv->map[hwirq].fwnode = &ipar->fwnode;
+		ret = of_property_read_u32(ipar, "#interrupt-cells", &intsize);
+		if (ret)
+			return ret;
+
+		if (intsize > mapsize)
+			return -EINVAL;
 
-		priv->map[hwirq].param_count = imap_item.parent_args.args_count;
-		for (i = 0; i < priv->map[hwirq].param_count; i++)
-			priv->map[hwirq].param[i] = imap_item.parent_args.args[i];
+		priv->map[hwirq].param_count = intsize;
+		for (j = 0; j < intsize; ++j)
+			priv->map[hwirq].param[j] = be32_to_cpup(map++);
+		mapsize -= intsize;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From fe5669e363b129cde285bfb4d45abb72d1d77cfc Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 24 Feb 2026 13:36:10 +0200
Subject: irqchip/ls-extirq: Fix devm_of_iomap() error check

The devm_of_iomap() function returns an ERR_PTR() encoded error code on
failure. Replace the incorrect check against NULL with IS_ERR().

Fixes: 05cd654829dd ("irqchip/ls-extirq: Convert to a platform driver to make it work again")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Herve Codina <herve.codina@bootlin.com>
Link: https://patch.msgid.link/20260224113610.1129022-3-ioana.ciornei@nxp.com
Closes: https://lore.kernel.org/all/aYXvfbfT6w0TMsXS@stanley.mountain/
---
 drivers/irqchip/irq-ls-extirq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c
index 96f9c20621cf..d724fe843980 100644
--- a/drivers/irqchip/irq-ls-extirq.c
+++ b/drivers/irqchip/irq-ls-extirq.c
@@ -190,8 +190,10 @@ static int ls_extirq_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, -ENOMEM, "Failed to allocate memory\n");
 
 	priv->intpcr = devm_of_iomap(dev, node, 0, NULL);
-	if (!priv->intpcr)
-		return dev_err_probe(dev, -ENOMEM, "Cannot ioremap OF node %pOF\n", node);
+	if (IS_ERR(priv->intpcr)) {
+		return dev_err_probe(dev, PTR_ERR(priv->intpcr),
+				     "Cannot ioremap OF node %pOF\n", node);
+	}
 
 	ret = ls_extirq_parse_map(priv, node);
 	if (ret)
-- 
cgit v1.2.3


From 095f5693329221ffd9dfe5fcd0079263d462e441 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 17 Feb 2026 15:25:59 +0800
Subject: tools/sched_ext: Sync README.md Kconfig with upstream scx

Sync the documentation with the upstream scx repository to
reflect the current recommended configuration.

Ref: https://github.com/sched-ext/scx/blob/main/README.md#build--install

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/README.md | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md
index 56a9d1557ac4..6e282bce453c 100644
--- a/tools/sched_ext/README.md
+++ b/tools/sched_ext/README.md
@@ -58,14 +58,8 @@ CONFIG_SCHED_CLASS_EXT=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_DEBUG_INFO_BTF=y
-```
-
-It's also recommended that you also include the following Kconfig options:
-
-```
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
-CONFIG_PAHOLE_HAS_BTF_TAG=y
 ```
 
 There is a `Kconfig` file in this directory whose contents you can append to
-- 
cgit v1.2.3


From ee0ff6690f2641b8f6ba8026ec17f6bc48f86649 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 17 Feb 2026 15:26:00 +0800
Subject: tools/sched_ext: Add Kconfig to sync with upstream

Add the missing Kconfig file to tools/sched_ext/ as referenced in
the README.

Ref: https://github.com/sched-ext/scx/blob/main/kernel.config

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/Kconfig | 61 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100644 tools/sched_ext/Kconfig

diff --git a/tools/sched_ext/Kconfig b/tools/sched_ext/Kconfig
new file mode 100644
index 000000000000..275bd97ae62b
--- /dev/null
+++ b/tools/sched_ext/Kconfig
@@ -0,0 +1,61 @@
+# sched-ext mandatory options
+#
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_SCHED_CLASS_EXT=y
+
+# Required by some rust schedulers (e.g. scx_p2dq)
+#
+CONFIG_KALLSYMS_ALL=y
+
+# Required on arm64
+#
+# CONFIG_DEBUG_INFO_REDUCED is not set
+
+# LAVD tracks futex to give an additional time slice for futex holder
+# (i.e., avoiding lock holder preemption) for better system-wide progress.
+# LAVD first tries to use ftrace to trace futex function calls.
+# If that is not available, it tries to use a tracepoint.
+CONFIG_FUNCTION_TRACER=y
+
+# Enable scheduling debugging
+#
+CONFIG_SCHED_DEBUG=y
+
+# Enable extra scheduling features (for a better code coverage while testing
+# the schedulers)
+#
+CONFIG_SCHED_AUTOGROUP=y
+CONFIG_SCHED_CORE=y
+CONFIG_SCHED_MC=y
+
+# Enable fully preemptible kernel for a better test coverage of the schedulers
+#
+# CONFIG_PREEMPT_NONE is not set
+# CONFIG_PREEMPT_VOLUNTARY is not set
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_DYNAMIC=y
+
+# Additional debugging information (useful to catch potential locking issues)
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_PROVE_LOCKING=y
+
+# Bpftrace headers (for additional debug info)
+CONFIG_BPF_EVENTS=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_KPROBES=y
+CONFIG_KPROBE_EVENTS=y
+CONFIG_UPROBES=y
+CONFIG_UPROBE_EVENTS=y
+CONFIG_DEBUG_FS=y
+
+# Enable access to kernel configuration and headers at runtime
+CONFIG_IKHEADERS=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_IKCONFIG=y
-- 
cgit v1.2.3


From a75281626fc8fa6dc6c9cc314ee423e8bc45203b Mon Sep 17 00:00:00 2001
From: Luka Gejak <luka.gejak@linux.dev>
Date: Tue, 24 Feb 2026 14:26:47 +0100
Subject: staging: rtl8723bs: fix potential out-of-bounds read in
 rtw_restruct_wmm_ie

The current code checks 'i + 5 < in_len' at the end of the if statement.
However, it accesses 'in_ie[i + 5]' before that check, which can lead
to an out-of-bounds read. Move the length check to the beginning of the
conditional to ensure the index is within bounds before accessing the
array.

Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Luka Gejak <luka.gejak@linux.dev>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/20260224132647.11642-2-luka.gejak@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8723bs/core/rtw_mlme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c
index 7df651708381..1ef48bf6581c 100644
--- a/drivers/staging/rtl8723bs/core/rtw_mlme.c
+++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c
@@ -1988,7 +1988,10 @@ int rtw_restruct_wmm_ie(struct adapter *adapter, u8 *in_ie, u8 *out_ie, uint in_
 	while (i < in_len) {
 		ielength = initial_out_len;
 
-		if (in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 && in_ie[i + 3] == 0x50  && in_ie[i + 4] == 0xF2 && in_ie[i + 5] == 0x02 && i + 5 < in_len) { /* WMM element ID and OUI */
+		if (i + 5 < in_len &&
+		    in_ie[i] == 0xDD && in_ie[i + 2] == 0x00 &&
+		    in_ie[i + 3] == 0x50 && in_ie[i + 4] == 0xF2 &&
+		    in_ie[i + 5] == 0x02) {
 			for (j = i; j < i + 9; j++) {
 				out_ie[ielength] = in_ie[j];
 				ielength++;
-- 
cgit v1.2.3


From a46435537a844d0f7b4b620baf962cad136422de Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 24 Feb 2026 11:36:09 -0700
Subject: io_uring/cmd_net: use READ_ONCE() for ->addr3 read

Any SQE read should use READ_ONCE(), to ensure the result is read once
and only once. Doesn't really matter for this case, but it's better to
keep these 100% consistent and always use READ_ONCE() for the prep side
of SQE handling.

Fixes: 5d24321e4c15 ("io_uring: Introduce getsockname io_uring cmd")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/cmd_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c
index 57ddaf874611..125a81c520a6 100644
--- a/io_uring/cmd_net.c
+++ b/io_uring/cmd_net.c
@@ -146,7 +146,7 @@ static int io_uring_cmd_getsockname(struct socket *sock,
 		return -EINVAL;
 
 	uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
-	ulen = u64_to_user_ptr(sqe->addr3);
+	ulen = u64_to_user_ptr(READ_ONCE(sqe->addr3));
 	peer = READ_ONCE(sqe->optlen);
 	if (peer > 1)
 		return -EINVAL;
-- 
cgit v1.2.3


From 09833d99db36d74456a4d13eb29c32d56ff8f2b6 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 13 Feb 2026 10:54:10 +0100
Subject: mm/kfence: disable KFENCE upon KASAN HW tags enablement

KFENCE does not currently support KASAN hardware tags.  As a result, the
two features are incompatible when enabled simultaneously.

Given that MTE provides deterministic protection and KFENCE is a
sampling-based debugging tool, prioritize the stronger hardware
protections.  Disable KFENCE initialization and free the pre-allocated
pool if KASAN hardware tags are detected to ensure the system maintains
the security guarantees provided by MTE.

Link: https://lkml.kernel.org/r/20260213095410.1862978-1-glider@google.com
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Alexander Potapenko <glider@google.com>
Suggested-by: Marco Elver <elver@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ernesto Martinez Garcia <ernesto.martinezgarcia@tugraz.at>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Kees Cook <kees@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kfence/core.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index b4ea3262c925..b5aedf505cec 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -13,6 +13,7 @@
 #include <linux/hash.h>
 #include <linux/irq_work.h>
 #include <linux/jhash.h>
+#include <linux/kasan-enabled.h>
 #include <linux/kcsan-checks.h>
 #include <linux/kfence.h>
 #include <linux/kmemleak.h>
@@ -916,6 +917,20 @@ void __init kfence_alloc_pool_and_metadata(void)
 	if (!kfence_sample_interval)
 		return;
 
+	/*
+	 * If KASAN hardware tags are enabled, disable KFENCE, because it
+	 * does not support MTE yet.
+	 */
+	if (kasan_hw_tags_enabled()) {
+		pr_info("disabled as KASAN HW tags are enabled\n");
+		if (__kfence_pool) {
+			memblock_free(__kfence_pool, KFENCE_POOL_SIZE);
+			__kfence_pool = NULL;
+		}
+		kfence_sample_interval = 0;
+		return;
+	}
+
 	/*
 	 * If the pool has already been initialized by arch, there is no need to
 	 * re-allocate the memory pool.
-- 
cgit v1.2.3


From eb9549346f7578eda3755683ac2cfb4d94c0675f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 16 Feb 2026 13:17:44 +0100
Subject: mm: change vma_alloc_folio_noprof() macro to inline function

In a few rare configurations with extra warnings eanbled, the new
drm_pagemap_migrate_populate_ram_pfn() calls vma_alloc_folio_noprof() but
that does not use all the arguments, leading to a harmless warning:

drivers/gpu/drm/drm_pagemap.c: In function 'drm_pagemap_migrate_populate_ram_pfn':
drivers/gpu/drm/drm_pagemap.c:701:63: error: parameter 'addr' set but not used [-Werror=unused-but-set-parameter=]
  701 |                                                 unsigned long addr)
      |                                                 ~~~~~~~~~~~~~~^~~~

Replace the macro with an inline function so the compiler can see how the
argument would be used, but is still able to optimize out the assignments.

Link: https://lkml.kernel.org/r/20260216121751.2378374-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2b30a0529d48..f82d74a77cad 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde
 {
 	return folio_alloc_noprof(gfp, order);
 }
-#define vma_alloc_folio_noprof(gfp, order, vma, addr)		\
-	folio_alloc_noprof(gfp, order)
+static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order,
+		struct vm_area_struct *vma, unsigned long addr)
+{
+	return folio_alloc_noprof(gfp, order);
+}
 #endif
 
 #define alloc_pages(...)			alloc_hooks(alloc_pages_noprof(__VA_ARGS__))
-- 
cgit v1.2.3


From dd085fe9a8ebfc5d10314c60452db38d2b75e609 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Sat, 14 Feb 2026 05:45:35 +0530
Subject: mm: thp: deny THP for files on anonymous inodes

file_thp_enabled() incorrectly allows THP for files on anonymous inodes
(e.g. guest_memfd and secretmem). These files are created via
alloc_file_pseudo(), which does not call get_write_access() and leaves
inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being
true, they appear as read-only regular files when
CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP
collapse.

Anonymous inodes can never pass the inode_is_open_for_write() check
since their i_writecount is never incremented through the normal VFS
open path. The right thing to do is to exclude them from THP eligibility
altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real
filesystem files (e.g. shared libraries), not for pseudo-filesystem
inodes.

For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create
large folios in the page cache via the collapse path, but the
guest_memfd fault handler does not support large folios. This triggers
WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping().

For secretmem, collapse_file() tries to copy page contents through the
direct map, but secretmem pages are removed from the direct map. This
can result in a kernel crash:

    BUG: unable to handle page fault for address: ffff88810284d000
    RIP: 0010:memcpy_orig+0x16/0x130
    Call Trace:
     collapse_file
     hpage_collapse_scan_file
     madvise_collapse

Secretmem is not affected by the crash on upstream as the memory failure
recovery handles the failed copy gracefully, but it still triggers
confusing false memory failure reports:

    Memory failure: 0x106d96f: recovery action for clean unevictable
    LRU page: Recovered

Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all
anonymous inode files.

Link: https://syzkaller.appspot.com/bug?extid=33a04338019ac7e43a44
Link: https://lore.kernel.org/linux-mm/CAEvNRgHegcz3ro35ixkDw39ES8=U6rs6S7iP0gkR9enr7HoGtA@mail.gmail.com
Link: https://lkml.kernel.org/r/20260214001535.435626-1-kartikey406@gmail.com
Fixes: 7fbb5e188248 ("mm: remove VM_EXEC requirement for THP eligibility")
Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
Reported-by: syzbot+33a04338019ac7e43a44@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33a04338019ac7e43a44
Tested-by: syzbot+33a04338019ac7e43a44@syzkaller.appspotmail.com
Tested-by: Lance Yang <lance.yang@linux.dev>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Ackerley Tng <ackerleytng@google.com>
Tested-by: Ackerley Tng <ackerleytng@google.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Fangrui Song <i@maskray.me>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d4ca8cfd7f9d..8e2746ea74ad 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -94,6 +94,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
+	if (IS_ANON_FILE(inode))
+		return false;
+
 	return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
-- 
cgit v1.2.3


From f85b1c6af5bc3872f994df0a5688c1162de07a62 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 16 Feb 2026 14:22:19 +0100
Subject: liveupdate: luo_file: remember retrieve() status

LUO keeps track of successful retrieve attempts on a LUO file.  It does so
to avoid multiple retrievals of the same file.  Multiple retrievals cause
problems because once the file is retrieved, the serialized data
structures are likely freed and the file is likely in a very different
state from what the code expects.

The retrieve boolean in struct luo_file keeps track of this, and is passed
to the finish callback so it knows what work was already done and what it
has left to do.

All this works well when retrieve succeeds.  When it fails,
luo_retrieve_file() returns the error immediately, without ever storing
anywhere that a retrieve was attempted or what its error code was.  This
results in an errored LIVEUPDATE_SESSION_RETRIEVE_FD ioctl to userspace,
but nothing prevents it from trying this again.

The retry is problematic for much of the same reasons listed above.  The
file is likely in a very different state than what the retrieve logic
normally expects, and it might even have freed some serialization data
structures.  Attempting to access them or free them again is going to
break things.

For example, if memfd managed to restore 8 of its 10 folios, but fails on
the 9th, a subsequent retrieve attempt will try to call
kho_restore_folio() on the first folio again, and that will fail with a
warning since it is an invalid operation.

Apart from the retry, finish() also breaks.  Since on failure the
retrieved bool in luo_file is never touched, the finish() call on session
close will tell the file handler that retrieve was never attempted, and it
will try to access or free the data structures that might not exist, much
in the same way as the retry attempt.

There is no sane way of attempting the retrieve again.  Remember the error
retrieve returned and directly return it on a retry.  Also pass this
status code to finish() so it can make the right decision on the work it
needs to do.

This is done by changing the bool to an integer.  A value of 0 means
retrieve was never attempted, a positive value means it succeeded, and a
negative value means it failed and the error code is the value.

Link: https://lkml.kernel.org/r/20260216132221.987987-1-pratyush@kernel.org
Fixes: 7c722a7f44e0 ("liveupdate: luo_file: implement file systems callbacks")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/liveupdate.h   |  9 ++++++---
 kernel/liveupdate/luo_file.c | 41 +++++++++++++++++++++++++----------------
 mm/memfd_luo.c               |  7 ++++++-
 3 files changed, 37 insertions(+), 20 deletions(-)

diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
index fe82a6c3005f..dd11fdc76a5f 100644
--- a/include/linux/liveupdate.h
+++ b/include/linux/liveupdate.h
@@ -23,8 +23,11 @@ struct file;
 /**
  * struct liveupdate_file_op_args - Arguments for file operation callbacks.
  * @handler:          The file handler being called.
- * @retrieved:        The retrieve status for the 'can_finish / finish'
- *                    operation.
+ * @retrieve_status:  The retrieve status for the 'can_finish / finish'
+ *                    operation. A value of 0 means the retrieve has not been
+ *                    attempted, a positive value means the retrieve was
+ *                    successful, and a negative value means the retrieve failed,
+ *                    and the value is the error code of the call.
  * @file:             The file object. For retrieve: [OUT] The callback sets
  *                    this to the new file. For other ops: [IN] The caller sets
  *                    this to the file being operated on.
@@ -40,7 +43,7 @@ struct file;
  */
 struct liveupdate_file_op_args {
 	struct liveupdate_file_handler *handler;
-	bool retrieved;
+	int retrieve_status;
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c
index 8c79058253e1..5acee4174bf0 100644
--- a/kernel/liveupdate/luo_file.c
+++ b/kernel/liveupdate/luo_file.c
@@ -134,9 +134,12 @@ static LIST_HEAD(luo_file_handler_list);
  *                 state that is not preserved. Set by the handler's .preserve()
  *                 callback, and must be freed in the handler's .unpreserve()
  *                 callback.
- * @retrieved:     A flag indicating whether a user/kernel in the new kernel has
+ * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has
  *                 successfully called retrieve() on this file. This prevents
- *                 multiple retrieval attempts.
+ *                 multiple retrieval attempts. A value of 0 means a retrieve()
+ *                 has not been attempted, a positive value means the retrieve()
+ *                 was successful, and a negative value means the retrieve()
+ *                 failed, and the value is the error code of the call.
  * @mutex:         A mutex that protects the fields of this specific instance
  *                 (e.g., @retrieved, @file), ensuring that operations like
  *                 retrieving or finishing a file are atomic.
@@ -161,7 +164,7 @@ struct luo_file {
 	struct file *file;
 	u64 serialized_data;
 	void *private_data;
-	bool retrieved;
+	int retrieve_status;
 	struct mutex mutex;
 	struct list_head list;
 	u64 token;
@@ -298,7 +301,6 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd)
 	luo_file->file = file;
 	luo_file->fh = fh;
 	luo_file->token = token;
-	luo_file->retrieved = false;
 	mutex_init(&luo_file->mutex);
 
 	args.handler = fh;
@@ -577,7 +579,12 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 		return -ENOENT;
 
 	guard(mutex)(&luo_file->mutex);
-	if (luo_file->retrieved) {
+	if (luo_file->retrieve_status < 0) {
+		/* Retrieve was attempted and it failed. Return the error code. */
+		return luo_file->retrieve_status;
+	}
+
+	if (luo_file->retrieve_status > 0) {
 		/*
 		 * Someone is asking for this file again, so get a reference
 		 * for them.
@@ -590,16 +597,19 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token,
 	args.handler = luo_file->fh;
 	args.serialized_data = luo_file->serialized_data;
 	err = luo_file->fh->ops->retrieve(&args);
-	if (!err) {
-		luo_file->file = args.file;
-
-		/* Get reference so we can keep this file in LUO until finish */
-		get_file(luo_file->file);
-		*filep = luo_file->file;
-		luo_file->retrieved = true;
+	if (err) {
+		/* Keep the error code for later use. */
+		luo_file->retrieve_status = err;
+		return err;
 	}
 
-	return err;
+	luo_file->file = args.file;
+	/* Get reference so we can keep this file in LUO until finish */
+	get_file(luo_file->file);
+	*filep = luo_file->file;
+	luo_file->retrieve_status = 1;
+
+	return 0;
 }
 
 static int luo_file_can_finish_one(struct luo_file_set *file_set,
@@ -615,7 +625,7 @@ static int luo_file_can_finish_one(struct luo_file_set *file_set,
 		args.handler = luo_file->fh;
 		args.file = luo_file->file;
 		args.serialized_data = luo_file->serialized_data;
-		args.retrieved = luo_file->retrieved;
+		args.retrieve_status = luo_file->retrieve_status;
 		can_finish = luo_file->fh->ops->can_finish(&args);
 	}
 
@@ -632,7 +642,7 @@ static void luo_file_finish_one(struct luo_file_set *file_set,
 	args.handler = luo_file->fh;
 	args.file = luo_file->file;
 	args.serialized_data = luo_file->serialized_data;
-	args.retrieved = luo_file->retrieved;
+	args.retrieve_status = luo_file->retrieve_status;
 
 	luo_file->fh->ops->finish(&args);
 	luo_flb_file_finish(luo_file->fh);
@@ -788,7 +798,6 @@ int luo_file_deserialize(struct luo_file_set *file_set,
 		luo_file->file = NULL;
 		luo_file->serialized_data = file_ser[i].data;
 		luo_file->token = file_ser[i].token;
-		luo_file->retrieved = false;
 		mutex_init(&luo_file->mutex);
 		list_add_tail(&luo_file->list, &file_set->files_list);
 	}
diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index 5c17da3880c5..e485b828d173 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -326,7 +326,12 @@ static void memfd_luo_finish(struct liveupdate_file_op_args *args)
 	struct memfd_luo_folio_ser *folios_ser;
 	struct memfd_luo_ser *ser;
 
-	if (args->retrieved)
+	/*
+	 * If retrieve was successful, nothing to do. If it failed, retrieve()
+	 * already cleaned up everything it could. So nothing to do there
+	 * either. Only need to clean up when retrieve was not called.
+	 */
+	if (args->retrieve_status)
 		return;
 
 	ser = phys_to_virt(args->serialized_data);
-- 
cgit v1.2.3


From 319d0bff22f3dd7a982c289e8336da69f0581299 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Tue, 17 Feb 2026 11:21:52 +0100
Subject: MAINTAINERS, mailmap: update e-mail address for Vlastimil Babka

Hopefully improve e-mail performance.

Link: https://lkml.kernel.org/r/20260217102151.10425-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    |  1 +
 MAINTAINERS | 18 +++++++++---------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..b3785362f73f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -876,6 +876,7 @@ Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
 Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
 Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+Vlastimil Babka <vbabka@kernel.org> <vbabka@suse.cz>
 WangYuli <wangyuli@aosc.io> <wangyl5933@chinaunicom.cn>
 WangYuli <wangyuli@aosc.io> <wangyuli@deepin.org>
 Weiwen Hu <huweiwen@linux.alibaba.com> <sehuww@mail.scut.edu.cn>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..02fe14782533 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16656,7 +16656,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
@@ -16786,7 +16786,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
@@ -16841,7 +16841,7 @@ F:	mm/oom_kill.c
 
 MEMORY MANAGEMENT - PAGE ALLOCATOR
 M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Vlastimil Babka <vbabka@suse.cz>
+M:	Vlastimil Babka <vbabka@kernel.org>
 R:	Suren Baghdasaryan <surenb@google.com>
 R:	Michal Hocko <mhocko@suse.com>
 R:	Brendan Jackman <jackmanb@google.com>
@@ -16887,7 +16887,7 @@ M:	David Hildenbrand <david@kernel.org>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Harry Yoo <harry.yoo@oracle.com>
 R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
@@ -16986,7 +16986,7 @@ MEMORY MAPPING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 R:	Pedro Falcato <pfalcato@suse.de>
 L:	linux-mm@kvack.org
@@ -17016,7 +17016,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Suren Baghdasaryan <surenb@google.com>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -17032,7 +17032,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
 M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 M:	David Hildenbrand <david@kernel.org>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -23174,7 +23174,7 @@ K:	\b(?i:rust)\b
 RUST [ALLOC]
 M:	Danilo Krummrich <dakr@kernel.org>
 R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
+R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Uladzislau Rezki <urezki@gmail.com>
 L:	rust-for-linux@vger.kernel.org
@@ -24350,7 +24350,7 @@ F:	Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml
 F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
-M:	Vlastimil Babka <vbabka@suse.cz>
+M:	Vlastimil Babka <vbabka@kernel.org>
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Christoph Lameter <cl@gentwo.org>
 R:	David Rientjes <rientjes@google.com>
-- 
cgit v1.2.3


From fdb24a820a5832ec4532273282cbd4f22c291a0d Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@squashfs.org.uk>
Date: Tue, 17 Feb 2026 05:09:55 +0000
Subject: Squashfs: check metadata block offset is within range

Syzkaller reports a "general protection fault in squashfs_copy_data"

This is ultimately caused by a corrupted index look-up table, which
produces a negative metadata block offset.

This is subsequently passed to squashfs_copy_data (via
squashfs_read_metadata) where the negative offset causes an out of bounds
access.

The fix is to check that the offset is within range in
squashfs_read_metadata.  This will trap this and other cases.

Link: https://lkml.kernel.org/r/20260217050955.138351-1-phillip@squashfs.org.uk
Fixes: f400e12656ab ("Squashfs: cache operations")
Reported-by: syzbot+a9747fe1c35a5b115d3f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/699234e2.a70a0220.2c38d7.00e2.GAE@google.com/
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/squashfs/cache.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 8e958db5f786..67abd4dff222 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -344,6 +344,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 	if (unlikely(length < 0))
 		return -EIO;
 
+	if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {
-- 
cgit v1.2.3


From c80f46ac228b48403866d65391ad09bdf0e8562a Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 14 Feb 2026 13:41:21 -0800
Subject: mm/damon/core: disallow non-power of two min_region_sz

DAMON core uses min_region_sz parameter value as the DAMON region
alignment.  The alignment is made using ALIGN() and ALIGN_DOWN(), which
support only the power of two alignments.  But DAMON core API callers can
set min_region_sz to an arbitrary number.  Users can also set it
indirectly, using addr_unit.

When the alignment is not properly set, DAMON behavior becomes difficult
to expect and understand, makes it effectively broken.  It doesn't cause a
kernel crash-like significant issue, though.

Fix the issue by disallowing min_region_sz input that is not a power of
two.  Add the check to damon_commit_ctx(), as all DAMON API callers who
set min_region_sz uses the function.

This can be a sort of behavioral change, but it does not break users, for
the following reasons.  As the symptom is making DAMON effectively broken,
it is not reasonable to believe there are real use cases of non-power of
two min_region_sz.  There is no known use case or issue reports from the
setup, either.

In future, if we find real use cases of non-power of two alignments and we
can support it with low enough overhead, we can consider moving the
restriction.  But, for now, simply disallowing the corner case should be
good enough as a hot fix.

Link: https://lkml.kernel.org/r/20260214214124.87689-1-sj@kernel.org
Fixes: d8f867fa0825 ("mm/damon: add damon_ctx->min_sz_region")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Quanmin Yan <yanquanmin1@huawei.com>
Cc: <stable@vger.kernel.org>	[6.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 01eba1a547d4..adfc52fee9dc 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1252,6 +1252,9 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 {
 	int err;
 
+	if (!is_power_of_2(src->min_region_sz))
+		return -EINVAL;
+
 	err = damon_commit_schemes(dst, src);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From d155aab90fffa00f93cea1f107aef0a3d548b2ff Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Fri, 20 Feb 2026 15:49:40 +0100
Subject: mm/kfence: fix KASAN hardware tag faults during late enablement

When KASAN hardware tags are enabled, re-enabling KFENCE late (via
/sys/module/kfence/parameters/sample_interval) causes KASAN faults.

This happens because the KFENCE pool and metadata are allocated via the
page allocator, which tags the memory, while KFENCE continues to access it
using untagged pointers during initialization.

Use __GFP_SKIP_KASAN for late KFENCE pool and metadata allocations to
ensure the memory remains untagged, consistent with early allocations from
memblock.  To support this, add __GFP_SKIP_KASAN to the allowlist in
__alloc_contig_verify_gfp_mask().

Link: https://lkml.kernel.org/r/20260220144940.2779209-1-glider@google.com
Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure")
Signed-off-by: Alexander Potapenko <glider@google.com>
Suggested-by: Ernesto Martinez Garcia <ernesto.martinezgarcia@tugraz.at>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kfence/core.c | 14 ++++++++------
 mm/page_alloc.c  |  3 ++-
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index b5aedf505cec..7393957f9a20 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -1004,14 +1004,14 @@ static int kfence_init_late(void)
 #ifdef CONFIG_CONTIG_ALLOC
 	struct page *pages;
 
-	pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL, first_online_node,
-				   NULL);
+	pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL | __GFP_SKIP_KASAN,
+				   first_online_node, NULL);
 	if (!pages)
 		return -ENOMEM;
 
 	__kfence_pool = page_to_virt(pages);
-	pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL, first_online_node,
-				   NULL);
+	pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL | __GFP_SKIP_KASAN,
+				   first_online_node, NULL);
 	if (pages)
 		kfence_metadata_init = page_to_virt(pages);
 #else
@@ -1021,11 +1021,13 @@ static int kfence_init_late(void)
 		return -EINVAL;
 	}
 
-	__kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, GFP_KERNEL);
+	__kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE,
+					  GFP_KERNEL | __GFP_SKIP_KASAN);
 	if (!__kfence_pool)
 		return -ENOMEM;
 
-	kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE, GFP_KERNEL);
+	kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE,
+						 GFP_KERNEL | __GFP_SKIP_KASAN);
 #endif
 
 	if (!kfence_metadata_init)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fcc32737f451..2d4b6f1a554e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6928,7 +6928,8 @@ static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask)
 {
 	const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM;
 	const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN |
-				  __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO;
+				  __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO |
+				  __GFP_SKIP_KASAN;
 	const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
 
 	/*
-- 
cgit v1.2.3


From 079c24d5690262e83ee476e2a548e416f3237511 Mon Sep 17 00:00:00 2001
From: Kalesh Singh <kaleshsingh@google.com>
Date: Thu, 19 Feb 2026 15:36:56 -0800
Subject: mm/tracing: rss_stat: ensure curr is false from kthread context

The rss_stat trace event allows userspace tools, like Perfetto [1], to
inspect per-process RSS metric changes over time.

The curr field was introduced to rss_stat in commit e4dcad204d3a
("rss_stat: add support to detect RSS updates of external mm").  Its
intent is to indicate whether the RSS update is for the mm_struct of the
current execution context; and is set to false when operating on a remote
mm_struct (e.g., via kswapd or a direct reclaimer).

However, an issue arises when a kernel thread temporarily adopts a user
process's mm_struct.  Kernel threads do not have their own mm_struct and
normally have current->mm set to NULL.  To operate on user memory, they
can "borrow" a memory context using kthread_use_mm(), which sets
current->mm to the user process's mm.

This can be observed, for example, in the USB Function Filesystem (FFS)
driver.  The ffs_user_copy_worker() handles AIO completions and uses
kthread_use_mm() to copy data to a user-space buffer.  If a page fault
occurs during this copy, the fault handler executes in the kthread's
context.

At this point, current is the kthread, but current->mm points to the user
process's mm.  Since the rss_stat event (from the page fault) is for that
same mm, the condition current->mm == mm becomes true, causing curr to be
incorrectly set to true when the trace event is emitted.

This is misleading because it suggests the mm belongs to the kthread,
confusing userspace tools that track per-process RSS changes and
corrupting their mm_id-to-process association.

Fix this by ensuring curr is always false when the trace event is emitted
from a kthread context by checking for the PF_KTHREAD flag.

Link: https://lkml.kernel.org/r/20260219233708.1971199-1-kaleshsingh@google.com
Link: https://perfetto.dev/ [1]
Fixes: e4dcad204d3a ("rss_stat: add support to detect RSS updates of external mm")
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Cc: "David Hildenbrand (Arm)" <david@kernel.org>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>	[5.10+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/trace/events/kmem.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 7f93e754da5c..cd7920c81f85 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat,
 
 	TP_fast_assign(
 		__entry->mm_id = mm_ptr_to_hash(mm);
-		__entry->curr = !!(current->mm == mm);
+		/*
+		 * curr is true if the mm matches the current task's mm_struct.
+		 * Since kthreads (PF_KTHREAD) have no mm_struct of their own
+		 * but can borrow one via kthread_use_mm(), we must filter them
+		 * out to avoid incorrectly attributing the RSS update to them.
+		 */
+		__entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD);
 		__entry->member = member;
 		__entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member])
 							    << PAGE_SHIFT);
-- 
cgit v1.2.3


From a4ab97e34bb687a2ca63fc70b47e8762e689797f Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 22 Feb 2026 19:57:02 +0800
Subject: mm: fix NULL NODE_DATA dereference for memoryless nodes on boot

Commit d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones
and memory map") moved free_area_init() from setup_arch() to
mm_core_init_early(), which runs after setup_arch() returns.

This changed the ordering relative to init_cpu_to_node() on x86.  Before
the commit, free_area_init() ran during paging_init() (called from
setup_arch()) *before* init_cpu_to_node().  After the commit, it runs
*after* init_cpu_to_node().

On machines with memoryless NUMA nodes (e.g., node 0 has CPUs but no
memory), this causes a NULL pointer dereference:

 1. numa_register_nodes() skips memoryless nodes: no alloc_node_data()
    and no node_set_online() for them.
 2. init_cpu_to_node() sets memoryless nodes online (they have CPUs)
    but does not allocate NODE_DATA.
 3. free_area_init() checks "if (!node_online(nid))" to decide whether
    to call alloc_offline_node_data(). Since the memoryless node is now
    online, the allocation is skipped, leaving NODE_DATA(nid) == NULL.
 4. The immediate "pgdat = NODE_DATA(nid)" dereferences NULL.

The crash happens before console_init(), so no output is visible without
earlyprintk.  With earlyprintk enabled, the following panic is observed:

 BUG: unable to handle page fault for address: 000000000002a1e0
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:free_area_init_node+0x3a/0x540
 Call Trace:
  <TASK>
  free_area_init+0x331/0x4e0
  start_kernel+0x69/0x4a0
  x86_64_start_reservations+0x24/0x30
  x86_64_start_kernel+0x125/0x130
  common_startup_64+0x13e/0x148
  </TASK>
 Kernel panic - not syncing: Attempted to kill the idle task!

Fix this by checking "if (!NODE_DATA(nid))" instead of "if
(!node_online(nid))".  This directly tests whether the per-node data
structure needs to be allocated, regardless of the node's online status.
This change is also safe for non-x86 architectures as they all allocate
NODE_DATA for every node including memoryless ones, so the check simply
evaluates to false with no change in behavior.

Link: https://lkml.kernel.org/r/20260222115702.3659-1-ming.lei@redhat.com
Fixes: d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones and memory map")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mm_init.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index 61d983d23f55..df34797691bd 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1896,7 +1896,11 @@ static void __init free_area_init(void)
 	for_each_node(nid) {
 		pg_data_t *pgdat;
 
-		if (!node_online(nid))
+		/*
+		 * If an architecture has not allocated node data for
+		 * this node, presume the node is memoryless or offline.
+		 */
+		if (!NODE_DATA(nid))
 			alloc_offline_node_data(nid);
 
 		pgdat = NODE_DATA(nid);
-- 
cgit v1.2.3


From 37a012c5c10c3364c5cba5def30dd7a17a6b587a Mon Sep 17 00:00:00 2001
From: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Date: Mon, 23 Feb 2026 17:09:05 +0000
Subject: mailmap: add entry for Daniele Alessandrelli

My Intel email is going to bounce soon.  Map it to my personal Gmail
address.

Link: https://lkml.kernel.org/r/20260223170905.278956-1-daniele.alessandrelli@intel.com
Signed-off-by: Daniele Alessandrelli <daniele.alessandrelli@intel.com>
Cc: Daniele Alessandrelli <daniele.alessandrelli@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index b3785362f73f..cd09bc545586 100644
--- a/.mailmap
+++ b/.mailmap
@@ -211,6 +211,7 @@ Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
+Daniele Alessandrelli <daniele.alessandrelli@gmail.com> <daniele.alessandrelli@intel.com>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
 David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
-- 
cgit v1.2.3


From 410aed670cddac1de4f0c2865f30ec623fd20f78 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosry@kernel.org>
Date: Mon, 23 Feb 2026 16:00:26 +0000
Subject: MAINTAINERS: update Yosry Ahmed's email address

Use my kernel.org email address.

Link: https://lkml.kernel.org/r/20260223160027.122307-1-yosry@kernel.org
Signed-off-by: Yosry Ahmed <yosry@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 3 ++-
 MAINTAINERS | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/.mailmap b/.mailmap
index cd09bc545586..c124a1306d26 100644
--- a/.mailmap
+++ b/.mailmap
@@ -892,7 +892,8 @@ Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn>
 Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com>
 Yixun Lan <dlan@kernel.org> <dlan@gentoo.org>
 Yixun Lan <dlan@kernel.org> <yixun.lan@amlogic.com>
-Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com>
+Yosry Ahmed <yosry@kernel.org> <yosryahmed@google.com>
+Yosry Ahmed <yosry@kernel.org> <yosry.ahmed@linux.dev>
 Yu-Chun Lin <eleanor.lin@realtek.com> <eleanor15x@gmail.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 02fe14782533..e4572a36afd2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -29186,7 +29186,7 @@ K:	zstd
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Yosry Ahmed <yosry.ahmed@linux.dev>
+M:	Yosry Ahmed <yosry@kernel.org>
 M:	Nhat Pham <nphamcs@gmail.com>
 R:	Chengming Zhou <chengming.zhou@linux.dev>
 L:	linux-mm@kvack.org
-- 
cgit v1.2.3


From 2f38fd99c0004676d835ae96ac4f3b54edc02c82 Mon Sep 17 00:00:00 2001
From: wangshuaiwei <wangshuaiwei1@xiaomi.com>
Date: Tue, 24 Feb 2026 14:32:28 +0800
Subject: scsi: ufs: core: Fix shift out of bounds when MAXQ=32

According to JESD223F, the maximum number of queues (MAXQ) is 32. When MCQ
is enabled and ESI is disabled, nr_hw_queues=32 causes a shift overflow
problem.

Fix this by using 64-bit intermediate values to handle the nr_hw_queues=32
case safely.

Signed-off-by: wangshuaiwei <wangshuaiwei1@xiaomi.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260224063228.50112-1-wangshuaiwei1@xiaomi.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 85987373b961..899e663fea6e 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7110,7 +7110,7 @@ static irqreturn_t ufshcd_handle_mcq_cq_events(struct ufs_hba *hba)
 
 	ret = ufshcd_vops_get_outstanding_cqs(hba, &outstanding_cqs);
 	if (ret)
-		outstanding_cqs = (1U << hba->nr_hw_queues) - 1;
+		outstanding_cqs = (1ULL << hba->nr_hw_queues) - 1;
 
 	/* Exclude the poll queues */
 	nr_queues = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL];
-- 
cgit v1.2.3


From 1f99b5d93d99ca17d50b386a674d0ce1f20932d8 Mon Sep 17 00:00:00 2001
From: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Date: Wed, 28 Jan 2026 00:28:28 +0100
Subject: arm64: dts: imx8mq: Set the correct gpu_ahb clock frequency

According to i.MX 8M Quad Reference Manual, GPU_AHB_CLK_ROOT's maximum
frequency is 400MHz.

Fixes: 45d2c84eb3a2 ("arm64: dts: imx8mq: add GPU node")
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 607962f807be..6a25e219832c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -1632,7 +1632,7 @@
 			                         <&clk IMX8MQ_GPU_PLL_OUT>,
 			                         <&clk IMX8MQ_GPU_PLL>;
 			assigned-clock-rates = <800000000>, <800000000>,
-			                       <800000000>, <800000000>, <0>;
+			                       <800000000>, <400000000>, <0>;
 			power-domains = <&pgc_gpu>;
 		};
 
-- 
cgit v1.2.3


From 08903184553def7ba1ad6ba4fa8afe1ba2ee0a21 Mon Sep 17 00:00:00 2001
From: Luke Wang <ziniu.wang_1@nxp.com>
Date: Tue, 3 Feb 2026 19:23:08 +0800
Subject: arm64: dts: imx93-9x9-qsb: change usdhc tuning step for eMMC and SD

During system resume, the following errors occurred:

  [  430.638625] mmc1: error -84 writing Cache Enable bit
  [  430.643618] mmc1: error -84 doing runtime resume

For eMMC and SD, there are two tuning pass windows and the gap between
those two windows may only have one cell. If tuning step > 1, the gap may
just be skipped and host assumes those two windows as a continuous
windows. This will cause a wrong delay cell near the gap to be selected.

Set the tuning step to 1 to avoid selecting the wrong delay cell.

For SDIO, the gap is sufficiently large, so the default tuning step does
not cause this issue.

Fixes: 0565d20cd8c2 ("arm64: dts: freescale: Support i.MX93 9x9 Quick Start Board")
Signed-off-by: Luke Wang <ziniu.wang_1@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts b/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts
index 0852067eab2c..197c8f8b7f66 100644
--- a/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-9x9-qsb.dts
@@ -507,6 +507,7 @@
 	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
 	bus-width = <8>;
 	non-removable;
+	fsl,tuning-step = <1>;
 	status = "okay";
 };
 
@@ -519,6 +520,7 @@
 	vmmc-supply = <&reg_usdhc2_vmmc>;
 	bus-width = <4>;
 	no-mmc;
+	fsl,tuning-step = <1>;
 	status = "okay";
 };
 
-- 
cgit v1.2.3


From bfbc0b5b32a8f28ce284add619bf226716a59bc0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 24 Feb 2026 11:51:16 -0700
Subject: media: dvb-core: fix wrong reinitialization of ringbuffer on reopen

dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the
DVR device.  dvb_ringbuffer_init() calls init_waitqueue_head(), which
reinitializes the waitqueue list head to empty.

Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the
same DVR device share it), this orphans any existing waitqueue entries
from io_uring poll or epoll, leaving them with stale prev/next pointers
while the list head is reset to {self, self}.

The waitqueue and spinlock in dvr_buffer are already properly
initialized once in dvb_dmxdev_init().  The open path only needs to
reset the buffer data pointer, size, and read/write positions.

Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct
assignment of data/size and a call to dvb_ringbuffer_reset(), which
properly resets pread, pwrite, and error with correct memory ordering
without touching the waitqueue or spinlock.

Cc: stable@vger.kernel.org
Fixes: 34731df288a5f ("V4L/DVB (3501): Dmxdev: use dvb_ringbuffer")
Reported-by: syzbot+ab12f0c08dd7ab8d057c@syzkaller.appspotmail.com
Tested-by: syzbot+ab12f0c08dd7ab8d057c@syzkaller.appspotmail.com
Link: https://lore.kernel.org/all/698a26d3.050a0220.3b3015.007d.GAE@google.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/media/dvb-core/dmxdev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index 7cfed24054d0..3c8bc75e4d6c 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -168,7 +168,9 @@ static int dvb_dvr_open(struct inode *inode, struct file *file)
 			mutex_unlock(&dmxdev->mutex);
 			return -ENOMEM;
 		}
-		dvb_ringbuffer_init(&dmxdev->dvr_buffer, mem, DVR_BUFFER_SIZE);
+		dmxdev->dvr_buffer.data = mem;
+		dmxdev->dvr_buffer.size = DVR_BUFFER_SIZE;
+		dvb_ringbuffer_reset(&dmxdev->dvr_buffer);
 		if (dmxdev->may_do_mmap)
 			dvb_vb2_init(&dmxdev->dvr_vb2_ctx, "dvr",
 				     &dmxdev->mutex,
-- 
cgit v1.2.3


From 6acf7860dcc79ed045cc9e6a79c8a8bb6959dba7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Feb 2026 06:21:44 -0800
Subject: zloop: advertise a volatile write cache

Zloop is file system backed and thus needs to sync the underlying file
system to persist data.  Set BLK_FEAT_WRITE_CACHE so that the block
layer actually send flush commands, and fix the flush implementation
as sync_filesystem requires s_umount to be held and the code currently
misses that.

Fixes: eb0570c7df23 ("block: new zoned loop block device driver")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/zloop.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index 8e334f5025fc..ae9bf2a85c21 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -542,6 +542,21 @@ out:
 	zloop_put_cmd(cmd);
 }
 
+/*
+ * Sync the entire FS containing the zone files instead of walking all files.
+ */
+static int zloop_flush(struct zloop_device *zlo)
+{
+	struct super_block *sb = file_inode(zlo->data_dir)->i_sb;
+	int ret;
+
+	down_read(&sb->s_umount);
+	ret = sync_filesystem(sb);
+	up_read(&sb->s_umount);
+
+	return ret;
+}
+
 static void zloop_handle_cmd(struct zloop_cmd *cmd)
 {
 	struct request *rq = blk_mq_rq_from_pdu(cmd);
@@ -562,11 +577,7 @@ static void zloop_handle_cmd(struct zloop_cmd *cmd)
 		zloop_rw(cmd);
 		return;
 	case REQ_OP_FLUSH:
-		/*
-		 * Sync the entire FS containing the zone files instead of
-		 * walking all files
-		 */
-		cmd->ret = sync_filesystem(file_inode(zlo->data_dir)->i_sb);
+		cmd->ret = zloop_flush(zlo);
 		break;
 	case REQ_OP_ZONE_RESET:
 		cmd->ret = zloop_reset_zone(zlo, rq_zone_no(rq));
@@ -981,7 +992,8 @@ static int zloop_ctl_add(struct zloop_options *opts)
 	struct queue_limits lim = {
 		.max_hw_sectors		= SZ_1M >> SECTOR_SHIFT,
 		.chunk_sectors		= opts->zone_size,
-		.features		= BLK_FEAT_ZONED,
+		.features		= BLK_FEAT_ZONED | BLK_FEAT_WRITE_CACHE,
+
 	};
 	unsigned int nr_zones, i, j;
 	struct zloop_device *zlo;
-- 
cgit v1.2.3


From 3c4617117a2b7682cf037be5e5533e379707f050 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Feb 2026 06:21:45 -0800
Subject: zloop: check for spurious options passed to remove

Zloop uses a command option parser for all control commands,
but most options are only valid for adding a new device.  Check
for incorrectly specified options in the remove handler.

Fixes: eb0570c7df23 ("block: new zoned loop block device driver")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/zloop.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c
index ae9bf2a85c21..9e3bb538d5fc 100644
--- a/drivers/block/zloop.c
+++ b/drivers/block/zloop.c
@@ -1174,7 +1174,12 @@ static int zloop_ctl_remove(struct zloop_options *opts)
 	int ret;
 
 	if (!(opts->mask & ZLOOP_OPT_ID)) {
-		pr_err("No ID specified\n");
+		pr_err("No ID specified for remove\n");
+		return -EINVAL;
+	}
+
+	if (opts->mask & ~ZLOOP_OPT_ID) {
+		pr_err("Invalid option specified for remove\n");
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 201ceb94aa1def0024a7c18ce643e5f65026be06 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 23 Feb 2026 19:37:51 -0800
Subject: kunit: irq: Ensure timer doesn't fire too frequently

Fix a bug where kunit_run_irq_test() could hang if the system is too
slow.  This was noticed with the crypto library tests in certain VMs.

Specifically, if kunit_irq_test_timer_func() and the associated hrtimer
code took over 5us to run, then the CPU would spend all its time
executing that code in hardirq context.  As a result, the task executing
kunit_run_irq_test() never had a chance to run, exit the loop, and
cancel the timer.

To fix it, make kunit_irq_test_timer_func() increase the timer interval
when the other contexts aren't having a chance to run.

Fixes: 950a81224e8b ("lib/crypto: tests: Add hash-test-template.h and gen-hash-testvecs.py")
Cc: stable@vger.kernel.org
Reviewed-by: David Gow <david@davidgow.net>
Link: https://lore.kernel.org/r/20260224033751.97615-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 include/kunit/run-in-irq-context.h | 44 ++++++++++++++++++++++++--------------
 1 file changed, 28 insertions(+), 16 deletions(-)

diff --git a/include/kunit/run-in-irq-context.h b/include/kunit/run-in-irq-context.h
index c89b1b1b12dd..bfe60d6cf28d 100644
--- a/include/kunit/run-in-irq-context.h
+++ b/include/kunit/run-in-irq-context.h
@@ -12,16 +12,16 @@
 #include <linux/hrtimer.h>
 #include <linux/workqueue.h>
 
-#define KUNIT_IRQ_TEST_HRTIMER_INTERVAL us_to_ktime(5)
-
 struct kunit_irq_test_state {
 	bool (*func)(void *test_specific_state);
 	void *test_specific_state;
 	bool task_func_reported_failure;
 	bool hardirq_func_reported_failure;
 	bool softirq_func_reported_failure;
+	atomic_t task_func_calls;
 	atomic_t hardirq_func_calls;
 	atomic_t softirq_func_calls;
+	ktime_t interval;
 	struct hrtimer timer;
 	struct work_struct bh_work;
 };
@@ -30,14 +30,25 @@ static enum hrtimer_restart kunit_irq_test_timer_func(struct hrtimer *timer)
 {
 	struct kunit_irq_test_state *state =
 		container_of(timer, typeof(*state), timer);
+	int task_calls, hardirq_calls, softirq_calls;
 
 	WARN_ON_ONCE(!in_hardirq());
-	atomic_inc(&state->hardirq_func_calls);
+	task_calls = atomic_read(&state->task_func_calls);
+	hardirq_calls = atomic_inc_return(&state->hardirq_func_calls);
+	softirq_calls = atomic_read(&state->softirq_func_calls);
+
+	/*
+	 * If the timer is firing too often for the softirq or task to ever have
+	 * a chance to run, increase the timer interval.  This is needed on very
+	 * slow systems.
+	 */
+	if (hardirq_calls >= 20 && (softirq_calls == 0 || task_calls == 0))
+		state->interval = ktime_add_ns(state->interval, 250);
 
 	if (!state->func(state->test_specific_state))
 		state->hardirq_func_reported_failure = true;
 
-	hrtimer_forward_now(&state->timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL);
+	hrtimer_forward_now(&state->timer, state->interval);
 	queue_work(system_bh_wq, &state->bh_work);
 	return HRTIMER_RESTART;
 }
@@ -86,10 +97,14 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	struct kunit_irq_test_state state = {
 		.func = func,
 		.test_specific_state = test_specific_state,
+		/*
+		 * Start with a 5us timer interval.  If the system can't keep
+		 * up, kunit_irq_test_timer_func() will increase it.
+		 */
+		.interval = us_to_ktime(5),
 	};
 	unsigned long end_jiffies;
-	int hardirq_calls, softirq_calls;
-	bool allctx = false;
+	int task_calls, hardirq_calls, softirq_calls;
 
 	/*
 	 * Set up a hrtimer (the way we access hardirq context) and a work
@@ -104,21 +119,18 @@ static inline void kunit_run_irq_test(struct kunit *test, bool (*func)(void *),
 	 * and hardirq), or 1 second, whichever comes first.
 	 */
 	end_jiffies = jiffies + HZ;
-	hrtimer_start(&state.timer, KUNIT_IRQ_TEST_HRTIMER_INTERVAL,
-		      HRTIMER_MODE_REL_HARD);
-	for (int task_calls = 0, calls = 0;
-	     ((calls < max_iterations) || !allctx) &&
-	     !time_after(jiffies, end_jiffies);
-	     task_calls++) {
+	hrtimer_start(&state.timer, state.interval, HRTIMER_MODE_REL_HARD);
+	do {
 		if (!func(test_specific_state))
 			state.task_func_reported_failure = true;
 
+		task_calls = atomic_inc_return(&state.task_func_calls);
 		hardirq_calls = atomic_read(&state.hardirq_func_calls);
 		softirq_calls = atomic_read(&state.softirq_func_calls);
-		calls = task_calls + hardirq_calls + softirq_calls;
-		allctx = (task_calls > 0) && (hardirq_calls > 0) &&
-			 (softirq_calls > 0);
-	}
+	} while ((task_calls + hardirq_calls + softirq_calls < max_iterations ||
+		  (task_calls == 0 || hardirq_calls == 0 ||
+		   softirq_calls == 0)) &&
+		 !time_after(jiffies, end_jiffies));
 
 	/* Cancel the timer and work. */
 	hrtimer_cancel(&state.timer);
-- 
cgit v1.2.3


From 4b44cbb264d0ed3f2f2bc2659db6ce45882f4670 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 24 Feb 2026 15:24:52 -0800
Subject: overflow: Make sure size helpers are always inlined

With kmalloc_obj() performing implicit size calculations, the embedded
size_mul() calls, while marked inline, were not always being inlined.
I noticed a couple places where allocations were making a call out for
things that would otherwise be compile-time calculated. Force the
compilers to always inline these calculations.

Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/20260224232451.work.614-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/overflow.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index eddd987a8513..a8cb6319b4fb 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -42,7 +42,7 @@
  * both the type-agnostic benefits of the macros while also being able to
  * enforce that the return value is, in fact, checked.
  */
-static inline bool __must_check __must_check_overflow(bool overflow)
+static __always_inline bool __must_check __must_check_overflow(bool overflow)
 {
 	return unlikely(overflow);
 }
@@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
+static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2)
 {
 	size_t bytes;
 
@@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
  * with any overflow causing the return value to be SIZE_MAX. The
  * lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_add(size_t addend1, size_t addend2)
+static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2)
 {
 	size_t bytes;
 
@@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2)
  * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX).
  * The lvalue must be size_t to avoid implicit type conversion.
  */
-static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
+static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
 {
 	size_t bytes;
 
-- 
cgit v1.2.3


From 44db7bc66eb38e85bb32777c5fd3a4e7baa84147 Mon Sep 17 00:00:00 2001
From: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Date: Mon, 9 Feb 2026 16:50:13 +0100
Subject: arm64: dts: imx91-tqma9131: improve eMMC pad configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use DSE x4 an PullUp for CMD an DAT, DSE x4 and PullDown for CLK to improve
stability and detection at low temperatures under -25°C.

Fixes: e71db39f0c7c ("arm64: dts: freescale: add initial device tree for TQMa91xx/MBa91xxCA")
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm64/boot/dts/freescale/imx91-tqma9131.dtsi | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx91-tqma9131.dtsi b/arch/arm64/boot/dts/freescale/imx91-tqma9131.dtsi
index 5792952b7a8e..c99d7bc16848 100644
--- a/arch/arm64/boot/dts/freescale/imx91-tqma9131.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx91-tqma9131.dtsi
@@ -272,20 +272,20 @@
 	/* enable SION for data and cmd pad due to ERR052021 */
 	pinctrl_usdhc1: usdhc1grp {
 		fsl,pins = /* PD | FSEL 3 | DSE X5 */
-			   <MX91_PAD_SD1_CLK__USDHC1_CLK		0x5be>,
+			   <MX91_PAD_SD1_CLK__USDHC1_CLK		0x59e>,
 			   /* HYS | FSEL 0 | no drive */
 			   <MX91_PAD_SD1_STROBE__USDHC1_STROBE		0x1000>,
 			   /* HYS | FSEL 3 | X5 */
-			   <MX91_PAD_SD1_CMD__USDHC1_CMD		0x400011be>,
+			   <MX91_PAD_SD1_CMD__USDHC1_CMD		0x4000139e>,
 			   /* HYS | FSEL 3 | X4 */
-			   <MX91_PAD_SD1_DATA0__USDHC1_DATA0		0x4000119e>,
-			   <MX91_PAD_SD1_DATA1__USDHC1_DATA1		0x4000119e>,
-			   <MX91_PAD_SD1_DATA2__USDHC1_DATA2		0x4000119e>,
-			   <MX91_PAD_SD1_DATA3__USDHC1_DATA3		0x4000119e>,
-			   <MX91_PAD_SD1_DATA4__USDHC1_DATA4		0x4000119e>,
-			   <MX91_PAD_SD1_DATA5__USDHC1_DATA5		0x4000119e>,
-			   <MX91_PAD_SD1_DATA6__USDHC1_DATA6		0x4000119e>,
-			   <MX91_PAD_SD1_DATA7__USDHC1_DATA7		0x4000119e>;
+			   <MX91_PAD_SD1_DATA0__USDHC1_DATA0		0x4000139e>,
+			   <MX91_PAD_SD1_DATA1__USDHC1_DATA1		0x4000139e>,
+			   <MX91_PAD_SD1_DATA2__USDHC1_DATA2		0x4000139e>,
+			   <MX91_PAD_SD1_DATA3__USDHC1_DATA3		0x4000139e>,
+			   <MX91_PAD_SD1_DATA4__USDHC1_DATA4		0x4000139e>,
+			   <MX91_PAD_SD1_DATA5__USDHC1_DATA5		0x4000139e>,
+			   <MX91_PAD_SD1_DATA6__USDHC1_DATA6		0x4000139e>,
+			   <MX91_PAD_SD1_DATA7__USDHC1_DATA7		0x4000139e>;
 	};
 
 	pinctrl_wdog: wdoggrp {
-- 
cgit v1.2.3


From b6c94c71f349479b76fcc0ef0dc7147f3f326dff Mon Sep 17 00:00:00 2001
From: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Date: Mon, 9 Feb 2026 16:50:14 +0100
Subject: arm64: dts: imx93-tqma9352: improve eMMC pad configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use DSE x4 an PullUp for CMD an DAT, DSE x4 and PullDown for CLK to improve
stability and detection at low temperatures under -25°C.

Fixes: 0b5fdfaa8e45 ("arm64: dts: freescale: imx93-tqma9352: set SION for cmd and data pad of USDHC")
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi | 26 +++++++++++------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
index 3a23e2eb9feb..ce34a296495c 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
@@ -271,21 +271,21 @@
 	/* enable SION for data and cmd pad due to ERR052021 */
 	pinctrl_usdhc1: usdhc1grp {
 		fsl,pins = <
-			/* PD | FSEL 3 | DSE X5 */
-			MX93_PAD_SD1_CLK__USDHC1_CLK		0x5be
+			/* PD | FSEL 3 | DSE X4 */
+			MX93_PAD_SD1_CLK__USDHC1_CLK		0x59e
 			/* HYS | FSEL 0 | no drive */
 			MX93_PAD_SD1_STROBE__USDHC1_STROBE	0x1000
-			/* HYS | FSEL 3 | X5 */
-			MX93_PAD_SD1_CMD__USDHC1_CMD		0x400011be
-			/* HYS | FSEL 3 | X4 */
-			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x4000119e
-			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x4000119e
-			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x4000119e
-			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x4000119e
-			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x4000119e
-			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x4000119e
-			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x4000119e
-			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x4000119e
+			/* HYS | PU | FSEL 3 | DSE X4 */
+			MX93_PAD_SD1_CMD__USDHC1_CMD		0x4000139e
+			/* HYS | PU | FSEL 3 | DSE X4 */
+			MX93_PAD_SD1_DATA0__USDHC1_DATA0	0x4000139e
+			MX93_PAD_SD1_DATA1__USDHC1_DATA1	0x4000139e
+			MX93_PAD_SD1_DATA2__USDHC1_DATA2	0x4000139e
+			MX93_PAD_SD1_DATA3__USDHC1_DATA3	0x4000139e
+			MX93_PAD_SD1_DATA4__USDHC1_DATA4	0x4000139e
+			MX93_PAD_SD1_DATA5__USDHC1_DATA5	0x4000139e
+			MX93_PAD_SD1_DATA6__USDHC1_DATA6	0x4000139e
+			MX93_PAD_SD1_DATA7__USDHC1_DATA7	0x4000139e
 		>;
 	};
 
-- 
cgit v1.2.3


From 2f61f38a217462411fed950e843b82bc119884cf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 23 Feb 2026 12:19:08 +0000
Subject: net: stmmac: fix timestamping configuration after suspend/resume

When stmmac_init_timestamping() is called, it clears the receive and
transmit path booleans that allow timestamps to be read. These are
never re-initialised until after userspace requests timestamping
features to be enabled.

However, our copy of the timestamp configuration is not cleared, which
means we return the old configuration to userspace when requested.
This is inconsistent. Fix this by clearing the timestamp configuration.

Fixes: d6228b7cdd6e ("net: stmmac: implement the SIOCGHWTSTAMP ioctl")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/E1vuUu4-0000000Afea-0j9B@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 82375d34ad57..91f638ce132e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -853,6 +853,7 @@ static int stmmac_init_timestamping(struct stmmac_priv *priv)
 		netdev_info(priv->dev,
 			    "IEEE 1588-2008 Advanced Timestamp supported\n");
 
+	memset(&priv->tstamp_config, 0, sizeof(priv->tstamp_config));
 	priv->hwts_tx_en = 0;
 	priv->hwts_rx_en = 0;
 
-- 
cgit v1.2.3


From c45f7263100cece247dd3fa5fe277bd97fdb5687 Mon Sep 17 00:00:00 2001
From: Liwei Song <liwei.song@windriver.com>
Date: Thu, 12 Feb 2026 12:00:35 +0800
Subject: firmware: stratix10-rsu: Fix NULL pointer dereference when RSU is
 disabled

When the Remote System Update (RSU) isn't enabled in the First Stage
Boot Loader (FSBL), the driver encounters a NULL pointer dereference when
excute svc_normal_to_secure_thread() thread, resulting in a kernel panic:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
Mem abort info:
...
Data abort info:
...
[0000000000000008] user address but active_mm is swapper
Internal error: Oops: 0000000096000004 [#1]  SMP
Modules linked in:
CPU: 0 UID: 0 PID: 79 Comm: svc_smc_hvc_thr Not tainted 6.19.0-rc8-yocto-standard+ #59 PREEMPT
Hardware name: SoCFPGA Stratix 10 SoCDK (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : svc_normal_to_secure_thread+0x38c/0x990
lr : svc_normal_to_secure_thread+0x144/0x990
...
Call trace:
 svc_normal_to_secure_thread+0x38c/0x990 (P)
 kthread+0x150/0x210
 ret_from_fork+0x10/0x20
Code: 97cfc113 f9400260 aa1403e1 f9400400 (f9400402)
---[ end trace 0000000000000000 ]---

The issue occurs because rsu_send_async_msg() fails when RSU is not enabled
in firmware, causing the channel to be freed via stratix10_svc_free_channel().
However, the probe function continues execution and registers
svc_normal_to_secure_thread(), which subsequently attempts to access the
already-freed channel, triggering the NULL pointer dereference.

Fix this by properly cleaning up the async client and returning early on
failure, preventing the thread from being used with an invalid channel.

Fixes: 15847537b623 ("firmware: stratix10-rsu: Migrate RSU driver to use stratix10 asynchronous framework.")
Cc: stable@kernel.org
Signed-off-by: Liwei Song <liwei.song@windriver.com>
Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
---
 drivers/firmware/stratix10-rsu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c
index 41da07c445a6..e1912108a0fe 100644
--- a/drivers/firmware/stratix10-rsu.c
+++ b/drivers/firmware/stratix10-rsu.c
@@ -768,7 +768,9 @@ static int stratix10_rsu_probe(struct platform_device *pdev)
 				 rsu_async_status_callback);
 	if (ret) {
 		dev_err(dev, "Error, getting RSU status %i\n", ret);
+		stratix10_svc_remove_async_client(priv->chan);
 		stratix10_svc_free_channel(priv->chan);
+		return ret;
 	}
 
 	/* get DCMF version from firmware */
-- 
cgit v1.2.3


From 83236b2e43dba00bee5b82eb5758816b1a674f6a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 24 Feb 2026 21:39:58 -1000
Subject: sched_ext: Disable preemption between scx_claim_exit() and kicking
 helper work

scx_claim_exit() atomically sets exit_kind, which prevents scx_error() from
triggering further error handling. After claiming exit, the caller must kick
the helper kthread work which initiates bypass mode and teardown.

If the calling task gets preempted between claiming exit and kicking the
helper work, and the BPF scheduler fails to schedule it back (since error
handling is now disabled), the helper work is never queued, bypass mode
never activates, tasks stop being dispatched, and the system wedges.

Disable preemption across scx_claim_exit() and the subsequent work kicking
in all callers - scx_disable() and scx_vexit(). Add
lockdep_assert_preemption_disabled() to scx_claim_exit() to enforce the
requirement.

Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index c18e81e8ef51..9280381f8923 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4423,10 +4423,19 @@ done:
 	scx_bypass(false);
 }
 
+/*
+ * Claim the exit on @sch. The caller must ensure that the helper kthread work
+ * is kicked before the current task can be preempted. Once exit_kind is
+ * claimed, scx_error() can no longer trigger, so if the current task gets
+ * preempted and the BPF scheduler fails to schedule it back, the helper work
+ * will never be kicked and the whole system can wedge.
+ */
 static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind)
 {
 	int none = SCX_EXIT_NONE;
 
+	lockdep_assert_preemption_disabled();
+
 	if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind))
 		return false;
 
@@ -4449,6 +4458,7 @@ static void scx_disable(enum scx_exit_kind kind)
 	rcu_read_lock();
 	sch = rcu_dereference(scx_root);
 	if (sch) {
+		guard(preempt)();
 		scx_claim_exit(sch, kind);
 		kthread_queue_work(sch->helper, &sch->disable_work);
 	}
@@ -4771,6 +4781,8 @@ static bool scx_vexit(struct scx_sched *sch,
 {
 	struct scx_exit_info *ei = sch->exit_info;
 
+	guard(preempt)();
+
 	if (!scx_claim_exit(sch, kind))
 		return false;
 
-- 
cgit v1.2.3


From aa8a3f3c67235422a0c3608a8772f69ca3b7b63f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 24 Feb 2026 00:05:11 +0100
Subject: xfrm: add missing extack for XFRMA_SA_PCPU in add_acquire and
 allocspi

We're returning an error caused by invalid user input without setting
an extack. Add one.

Fixes: 1ddf9916ac09 ("xfrm: Add support for per cpu xfrm state handling.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 403b5ecac2c5..3e6477c6082e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1850,6 +1850,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
 		if (pcpu_num >= num_possible_cpus()) {
 			err = -EINVAL;
+			NL_SET_ERR_MSG(extack, "pCPU number too big");
 			goto out_noput;
 		}
 	}
@@ -3001,8 +3002,10 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (attrs[XFRMA_SA_PCPU]) {
 		x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
 		err = -EINVAL;
-		if (x->pcpu_num >= num_possible_cpus())
+		if (x->pcpu_num >= num_possible_cpus()) {
+			NL_SET_ERR_MSG(extack, "pCPU number too big");
 			goto free_state;
+		}
 	}
 
 	err = verify_newpolicy_info(&ua->policy, extack);
-- 
cgit v1.2.3


From b57defcf8f109da5ba9cf59b2a736606faf3d846 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 24 Feb 2026 00:05:12 +0100
Subject: xfrm: fix the condition on x->pcpu_num in xfrm_sa_len

pcpu_num = 0 is a valid value. The marker for "unset pcpu_num" which
makes copy_to_user_state_extra not add the XFRMA_SA_PCPU attribute is
UINT_MAX.

Fixes: 1ddf9916ac09 ("xfrm: Add support for per cpu xfrm state handling.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 3e6477c6082e..4dd8341225bc 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3676,7 +3676,7 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
 	}
 	if (x->if_id)
 		l += nla_total_size(sizeof(x->if_id));
-	if (x->pcpu_num)
+	if (x->pcpu_num != UINT_MAX)
 		l += nla_total_size(sizeof(x->pcpu_num));
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
-- 
cgit v1.2.3


From 7d2fc41f91bc69acb6e01b0fa23cd7d0109a6a23 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 24 Feb 2026 00:05:13 +0100
Subject: xfrm: call xdo_dev_state_delete during state update

When we update an SA, we construct a new state and call
xdo_dev_state_add, but never insert it. The existing state is updated,
then we immediately destroy the new state. Since we haven't added it,
we don't go through the standard state delete code, and we're skipping
removing it from the device (but xdo_dev_state_free will get called
when we destroy the temporary state).

This is similar to commit c5d4d7d83165 ("xfrm: Fix deletion of
offloaded SAs on failure.").

Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 98b362d51836..a00c4fe1ab0c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2264,6 +2264,7 @@ out:
 
 		err = 0;
 		x->km.state = XFRM_STATE_DEAD;
+		xfrm_dev_state_delete(x);
 		__xfrm_state_put(x);
 	}
 
-- 
cgit v1.2.3


From 0c0eef8ccd2413b0a10eb6bbd3442333b1e64dd2 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 24 Feb 2026 00:05:14 +0100
Subject: esp: fix skb leak with espintcp and async crypto

When the TX queue for espintcp is full, esp_output_tail_tcp will
return an error and not free the skb, because with synchronous crypto,
the common xfrm output code will drop the packet for us.

With async crypto (esp_output_done), we need to drop the skb when
esp_output_tail_tcp returns an error.

Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/esp4.c | 9 ++++++---
 net/ipv6/esp6.c | 9 ++++++---
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2c922afadb8f..6dfc0bcdef65 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -235,10 +235,13 @@ static void esp_output_done(void *data, int err)
 		xfrm_dev_resume(skb);
 	} else {
 		if (!err &&
-		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
-			esp_output_tail_tcp(x, skb);
-		else
+		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) {
+			err = esp_output_tail_tcp(x, skb);
+			if (err != -EINPROGRESS)
+				kfree_skb(skb);
+		} else {
 			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
+		}
 	}
 }
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index e75da98f5283..9f75313734f8 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -271,10 +271,13 @@ static void esp_output_done(void *data, int err)
 		xfrm_dev_resume(skb);
 	} else {
 		if (!err &&
-		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
-			esp_output_tail_tcp(x, skb);
-		else
+		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) {
+			err = esp_output_tail_tcp(x, skb);
+			if (err != -EINPROGRESS)
+				kfree_skb(skb);
+		} else {
 			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
+		}
 	}
 }
 
-- 
cgit v1.2.3


From 29c8b85adb47daefc213381bc1831787f512d89b Mon Sep 17 00:00:00 2001
From: Sascha Bischoff <Sascha.Bischoff@arm.com>
Date: Wed, 25 Feb 2026 08:31:40 +0000
Subject: irqchip/gic-v5: Fix inversion of IRS_IDR0.virt flag

It appears that a !! became ! during a cleanup, resulting in inverted
logic when detecting if a host GICv5 implementation is capable of
virtualization.

Re-add the missing !, fixing the behaviour.

Fixes: 3227c3a89d65f ("irqchip/gic-v5: Check if impl is virt capable")
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Link: https://patch.msgid.link/20260225083130.3378490-1-sascha.bischoff@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/irqchip/irq-gic-v5-irs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index eeeb40fb0eaa..4ed2bfa17c01 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -744,7 +744,7 @@ static int __init gicv5_irs_init(struct device_node *node)
 	 */
 	if (list_empty(&irs_nodes)) {
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR0);
-		gicv5_global_data.virt_capable = !FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
+		gicv5_global_data.virt_capable = !!FIELD_GET(GICV5_IRS_IDR0_VIRT, idr);
 
 		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1);
 		irs_setup_pri_bits(idr);
-- 
cgit v1.2.3


From 7fe8dec3f628e9779f1631576f8e693370050348 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:28 +0100
Subject: ALSA: usb-audio: Cap the packet size pre-calculations

We calculate the possible packet sizes beforehand for adaptive and
synchronous endpoints, but we didn't take care of the max frame size
for those pre-calculated values.  When a device or a bus limits the
packet size, a high sample rate or a high number of channels may lead
to the packet sizes that are larger than the given limit, which
results in an error from the USB core at submitting URBs.

As a simple workaround, just add the sanity checks of pre-calculated
packet sizes to have the upper boundary of ep->maxframesize.

Fixes: f0bd62b64016 ("ALSA: usb-audio: Improve frames size computation")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 73bce9712dbd..c887c2f5b25d 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -1378,6 +1378,9 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip,
 		return -EINVAL;
 	}
 
+	ep->packsize[0] = min(ep->packsize[0], ep->maxframesize);
+	ep->packsize[1] = min(ep->packsize[1], ep->maxframesize);
+
 	/* calculate the frequency in 16.16 format */
 	ep->freqm = ep->freqn;
 	ep->freqshift = INT_MIN;
-- 
cgit v1.2.3


From 7cb2a5422f5bbdf1cf32eae0eda41000485b9346 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:29 +0100
Subject: ALSA: usb-audio: Check max frame size for implicit feedback mode, too

When the packet sizes are taken from the capture stream in the
implicit feedback mode, the sizes might be larger than the upper
boundary defined by the descriptor.  As already done for other
transfer modes, we have to cap the sizes accordingly at sending,
otherwise this would lead to an error in USB core at submission of
URBs.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index c887c2f5b25d..2e70dbc479b4 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -221,6 +221,7 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
 
 	packet = ctx->packet_size[idx];
 	if (packet) {
+		packet = min(packet, ep->maxframesize);
 		if (avail && packet >= avail)
 			return -EAGAIN;
 		return packet;
-- 
cgit v1.2.3


From c5bf24c8aba1ff711226ee0f039ff01a5754692b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:30 +0100
Subject: ALSA: usb-audio: Avoid implicit feedback mode on DIYINHK USB Audio
 2.0

Although DIYINHK USB Audio 2.0 (ID 20b1:2009) shows the implicit
feedback source for the capture stream, this would cause several
problems for the playback.  Namely, the device can get wMaxPackSize
1024 for 24/32 bit format with 6 channels, and when a high sample rate
like 352.8kHz or 384kHz is played, the packet size overflows the max
limit.  Also, the device has another two playback altsets, and those
aren't properly handled with the implicit feedback.

Since the device has been working well even before introducing the
implicit feedback, we can assume that it works fine in the async mode.
This patch adds the explicit skip of the implicit fb detection to make
the playback running in the async mode.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221076
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index fbceed8e8d36..c6a78efbcaa3 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2365,6 +2365,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x2040, 0x7281, /* Hauppauge HVR-950Q-MXL */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x20b1, 0x2009, /* XMOS Ltd DIYINHK USB Audio 2.0 */
+		   QUIRK_FLAG_SKIP_IMPLICIT_FB | QUIRK_FLAG_DSD_RAW),
 	DEVICE_FLG(0x2040, 0x8200, /* Hauppauge Woodbury */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */
-- 
cgit v1.2.3


From 4e9113c533acee2ba1f72fd68ee6ecd36b64484e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Feb 2026 09:52:31 +0100
Subject: ALSA: usb-audio: Use inclusive terms

Replace the remaining with inclusive terms; it's only this function
name we overlooked at the previous conversion.

Fixes: 53837b4ac2bd ("ALSA: usb-audio: Replace slave/master terms")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260225085233.316306-5-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 2e70dbc479b4..bf4401aba76c 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -160,8 +160,8 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep)
  * This won't be used for implicit feedback which takes the packet size
  * returned from the sync source
  */
-static int slave_next_packet_size(struct snd_usb_endpoint *ep,
-				  unsigned int avail)
+static int synced_next_packet_size(struct snd_usb_endpoint *ep,
+				   unsigned int avail)
 {
 	unsigned int phase;
 	int ret;
@@ -228,7 +228,7 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
 	}
 
 	if (ep->sync_source)
-		return slave_next_packet_size(ep, avail);
+		return synced_next_packet_size(ep, avail);
 	else
 		return next_packet_size(ep, avail);
 }
-- 
cgit v1.2.3


From 2e7b5cf72e51c9cf9c8b75190189c757df31ddd9 Mon Sep 17 00:00:00 2001
From: Joy Zou <joy.zou@nxp.com>
Date: Wed, 17 Sep 2025 17:53:42 +0800
Subject: dmaengine: fsl-edma: fix channel parameter config for fixed channel
 requests

Configure only the requested channel when a fixed channel is specified
to avoid modifying other channels unintentionally.

Fix parameter configuration when a fixed DMA channel is requested on
i.MX9 AON domain and i.MX8QM/QXP/DXL platforms. When a client requests
a fixed channel (e.g., channel 6), the driver traverses channels 0-5
and may unintentionally modify their configuration if they are unused.

This leads to issues such as setting the `is_multi_fifo` flag unexpectedly,
causing memcpy tests to fail when using the dmatest tool.

Only affect edma memcpy test when the channel is fixed.

Fixes: 72f5801a4e2b ("dmaengine: fsl-edma: integrate v3 support")
Signed-off-by: Joy Zou <joy.zou@nxp.com>
Cc: stable@vger.kernel.org
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250917-b4-edma-chanconf-v1-1-886486e02e91@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/fsl-edma-main.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index dbcdd1e68319..b596baa0a182 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -317,10 +317,8 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 			return NULL;
 		i = fsl_chan - fsl_edma->chans;
 
-		fsl_chan->priority = dma_spec->args[1];
-		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
-		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
-		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+		if (!b_chmux && i != dma_spec->args[0])
+			continue;
 
 		if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
 			continue;
@@ -328,17 +326,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
 			continue;
 
-		if (!b_chmux && i == dma_spec->args[0]) {
-			chan = dma_get_slave_channel(chan);
-			chan->device->privatecnt++;
-			return chan;
-		} else if (b_chmux && !fsl_chan->srcid) {
-			/* if controller support channel mux, choose a free channel */
-			chan = dma_get_slave_channel(chan);
-			chan->device->privatecnt++;
-			fsl_chan->srcid = dma_spec->args[0];
-			return chan;
-		}
+		fsl_chan->srcid = dma_spec->args[0];
+		fsl_chan->priority = dma_spec->args[1];
+		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+
+		chan = dma_get_slave_channel(chan);
+		chan->device->privatecnt++;
+		return chan;
 	}
 	return NULL;
 }
-- 
cgit v1.2.3


From 4a2d046e4b13202a6301a993961f5b30ae4d7119 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 24 Feb 2026 18:31:25 +0800
Subject: erofs: fix interlaced plain identification for encoded extents

Only plain data whose start position and on-disk physical length are
both aligned to the block size should be classified as interlaced
plain extents. Otherwise, it must be treated as shifted plain extents.

This issue was found by syzbot using a crafted compressed image
containing plain extents with unaligned physical lengths, which can
cause OOB read in z_erofs_transform_plain().

Reported-and-tested-by: syzbot+d988dc155e740d76a331@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/699d5714.050a0220.cdd3c.03e7.GAE@google.com
Fixes: 1d191b4ca51d ("erofs: implement encoded extent metadata")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/zmap.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index c8d8e129eb4b..30775502b56d 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -513,6 +513,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 	unsigned int recsz = z_erofs_extent_recsize(vi->z_advise);
 	erofs_off_t pos = round_up(Z_EROFS_MAP_HEADER_END(erofs_iloc(inode) +
 				   vi->inode_isize + vi->xattr_isize), recsz);
+	unsigned int bmask = sb->s_blocksize - 1;
 	bool in_mbox = erofs_inode_in_metabox(inode);
 	erofs_off_t lend = inode->i_size;
 	erofs_off_t l, r, mid, pa, la, lstart;
@@ -596,17 +597,17 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 			map->m_flags |= EROFS_MAP_MAPPED |
 				EROFS_MAP_FULL_MAPPED | EROFS_MAP_ENCODED;
 			fmt = map->m_plen >> Z_EROFS_EXTENT_PLEN_FMT_BIT;
+			if (map->m_plen & Z_EROFS_EXTENT_PLEN_PARTIAL)
+				map->m_flags |= EROFS_MAP_PARTIAL_REF;
+			map->m_plen &= Z_EROFS_EXTENT_PLEN_MASK;
 			if (fmt)
 				map->m_algorithmformat = fmt - 1;
-			else if (interlaced && !erofs_blkoff(sb, map->m_pa))
+			else if (interlaced && !((map->m_pa | map->m_plen) & bmask))
 				map->m_algorithmformat =
 					Z_EROFS_COMPRESSION_INTERLACED;
 			else
 				map->m_algorithmformat =
 					Z_EROFS_COMPRESSION_SHIFTED;
-			if (map->m_plen & Z_EROFS_EXTENT_PLEN_PARTIAL)
-				map->m_flags |= EROFS_MAP_PARTIAL_REF;
-			map->m_plen &= Z_EROFS_EXTENT_PLEN_MASK;
 		}
 	}
 	map->m_llen = lend - map->m_la;
-- 
cgit v1.2.3


From 77b19d053ac2cce9e873007ad4b09f2323c93576 Mon Sep 17 00:00:00 2001
From: Shenghui Shi <brody.shi@m2semi.com>
Date: Mon, 9 Feb 2026 18:37:25 +0800
Subject: dmaengine: dw-edma: fix MSI data programming for multi-IRQ case

When using MSI (not MSI-X) with multiple IRQs, the MSI data value
must be unique per vector to ensure correct interrupt delivery.
Currently, the driver fails to increment the MSI data per vector,
causing interrupts to be misrouted.

Fix this by caching the base MSI data and adjusting each vector's
data accordingly during IRQ setup.

Fixes: e63d79d1ff04 ("dmaengine: dw-edma: Add Synopsys DesignWare eDMA IP core driver")
Signed-off-by: Shenghui Shi <brody.shi@m2semi.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260209103726.414-1-brody.shi@m2semi.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw-edma/dw-edma-core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index e7d698b352d3..5397dbda4f72 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -844,6 +844,7 @@ static int dw_edma_irq_request(struct dw_edma *dw,
 {
 	struct dw_edma_chip *chip = dw->chip;
 	struct device *dev = dw->chip->dev;
+	struct msi_desc *msi_desc;
 	u32 wr_mask = 1;
 	u32 rd_mask = 1;
 	int i, err = 0;
@@ -895,9 +896,12 @@ static int dw_edma_irq_request(struct dw_edma *dw,
 					  &dw->irq[i]);
 			if (err)
 				goto err_irq_free;
-
-			if (irq_get_msi_desc(irq))
+			msi_desc = irq_get_msi_desc(irq);
+			if (msi_desc) {
 				get_cached_msi_msg(irq, &dw->irq[i].msi);
+				if (!msi_desc->pci.msi_attrib.is_msix)
+					dw->irq[i].msi.data = dw->irq[0].msi.data + i;
+			}
 		}
 
 		dw->nr_irqs = i;
-- 
cgit v1.2.3


From a4b0bf6a40f3c107c67a24fbc614510ef5719980 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Wed, 25 Feb 2026 08:55:55 +0200
Subject: x86/efi: defer freeing of boot services memory

efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE
and EFI_BOOT_SERVICES_DATA using memblock_free_late().

There are two issue with that: memblock_free_late() should be used for
memory allocated with memblock_alloc() while the memory reserved with
memblock_reserve() should be freed with free_reserved_area().

More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
efi_free_boot_services() is called before deferred initialization of the
memory map is complete.

Benjamin Herrenschmidt reports that this causes a leak of ~140MB of
RAM on EC2 t3a.nano instances which only have 512MB or RAM.

If the freed memory resides in the areas that memory map for them is
still uninitialized, they won't be actually freed because
memblock_free_late() calls memblock_free_pages() and the latter skips
uninitialized pages.

Using free_reserved_area() at this point is also problematic because
__free_page() accesses the buddy of the freed page and that again might
end up in uninitialized part of the memory map.

Delaying the entire efi_free_boot_services() could be problematic
because in addition to freeing boot services memory it updates
efi.memmap without any synchronization and that's undesirable late in
boot when there is concurrency.

More robust approach is to only defer freeing of the EFI boot services
memory.

Split efi_free_boot_services() in two. First efi_unmap_boot_services()
collects ranges that should be freed into an array then
efi_free_boot_services() later frees them after deferred init is complete.

Link: https://lore.kernel.org/all/ec2aaef14783869b3be6e3c253b2dcbf67dbc12a.camel@kernel.crashing.org
Fixes: 916f676f8dc0 ("x86, efi: Retain boot service code until after switching to virtual mode")
Cc: <stable@vger.kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/include/asm/efi.h          |  2 +-
 arch/x86/platform/efi/efi.c         |  2 +-
 arch/x86/platform/efi/quirks.c      | 55 +++++++++++++++++++++++++++++++++++--
 drivers/firmware/efi/mokvar-table.c |  2 +-
 4 files changed, 55 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index f227a70ac91f..51b4cdbea061 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -138,7 +138,7 @@ extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);
 extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
-extern void efi_free_boot_services(void);
+extern void efi_unmap_boot_services(void);
 
 void arch_efi_call_virt_setup(void);
 void arch_efi_call_virt_teardown(void);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d00c6de7f3b7..d84c6020dda1 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -836,7 +836,7 @@ static void __init __efi_enter_virtual_mode(void)
 	}
 
 	efi_check_for_embedded_firmwares();
-	efi_free_boot_services();
+	efi_unmap_boot_services();
 
 	if (!efi_is_mixed())
 		efi_native_runtime_setup();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 553f330198f2..35caa5746115 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -341,7 +341,7 @@ void __init efi_reserve_boot_services(void)
 
 		/*
 		 * Because the following memblock_reserve() is paired
-		 * with memblock_free_late() for this region in
+		 * with free_reserved_area() for this region in
 		 * efi_free_boot_services(), we must be extremely
 		 * careful not to reserve, and subsequently free,
 		 * critical regions of memory (like the kernel image) or
@@ -404,17 +404,33 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 		pr_err("Failed to unmap VA mapping for 0x%llx\n", va);
 }
 
-void __init efi_free_boot_services(void)
+struct efi_freeable_range {
+	u64 start;
+	u64 end;
+};
+
+static struct efi_freeable_range *ranges_to_free;
+
+void __init efi_unmap_boot_services(void)
 {
 	struct efi_memory_map_data data = { 0 };
 	efi_memory_desc_t *md;
 	int num_entries = 0;
+	int idx = 0;
+	size_t sz;
 	void *new, *new_md;
 
 	/* Keep all regions for /sys/kernel/debug/efi */
 	if (efi_enabled(EFI_DBG))
 		return;
 
+	sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1;
+	ranges_to_free = kzalloc(sz, GFP_KERNEL);
+	if (!ranges_to_free) {
+		pr_err("Failed to allocate storage for freeable EFI regions\n");
+		return;
+	}
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -471,7 +487,15 @@ void __init efi_free_boot_services(void)
 			start = SZ_1M;
 		}
 
-		memblock_free_late(start, size);
+		/*
+		 * With CONFIG_DEFERRED_STRUCT_PAGE_INIT parts of the memory
+		 * map are still not initialized and we can't reliably free
+		 * memory here.
+		 * Queue the ranges to free at a later point.
+		 */
+		ranges_to_free[idx].start = start;
+		ranges_to_free[idx].end = start + size;
+		idx++;
 	}
 
 	if (!num_entries)
@@ -512,6 +536,31 @@ void __init efi_free_boot_services(void)
 	}
 }
 
+static int __init efi_free_boot_services(void)
+{
+	struct efi_freeable_range *range = ranges_to_free;
+	unsigned long freed = 0;
+
+	if (!ranges_to_free)
+		return 0;
+
+	while (range->start) {
+		void *start = phys_to_virt(range->start);
+		void *end = phys_to_virt(range->end);
+
+		free_reserved_area(start, end, -1, NULL);
+		freed += (end - start);
+		range++;
+	}
+	kfree(ranges_to_free);
+
+	if (freed)
+		pr_info("Freeing EFI boot services memory: %ldK\n", freed / SZ_1K);
+
+	return 0;
+}
+arch_initcall(efi_free_boot_services);
+
 /*
  * A number of config table entries get remapped to virtual addresses
  * after entering EFI virtual mode. However, the kexec kernel requires
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 4ff0c2926097..6842aa96d704 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -85,7 +85,7 @@ static struct kobject *mokvar_kobj;
  * as an alternative to ordinary EFI variables, due to platform-dependent
  * limitations. The memory occupied by this table is marked as reserved.
  *
- * This routine must be called before efi_free_boot_services() in order
+ * This routine must be called before efi_unmap_boot_services() in order
  * to guarantee that it can mark the table as reserved.
  *
  * Implicit inputs:
-- 
cgit v1.2.3


From caf91cdf2de8b7134749d32cd4ae5520b108abb7 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:27 -0800
Subject: dmaengine: idxd: Fix lockdep warnings when calling
 idxd_device_config()

Move the check for IDXD_FLAG_CONFIGURABLE and the locking to "inside"
idxd_device_config(), as this is common to all callers, and the one
that wasn't holding the lock was an error (that was causing the
lockdep warning).

Suggested-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-1-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 17 +++++++----------
 drivers/dma/idxd/init.c   | 10 ++++------
 2 files changed, 11 insertions(+), 16 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index c26128529ff4..a704475d87b3 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1125,7 +1125,11 @@ int idxd_device_config(struct idxd_device *idxd)
 {
 	int rc;
 
-	lockdep_assert_held(&idxd->dev_lock);
+	guard(spinlock)(&idxd->dev_lock);
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return 0;
+
 	rc = idxd_wqs_setup(idxd);
 	if (rc < 0)
 		return rc;
@@ -1454,11 +1458,7 @@ int idxd_drv_enable_wq(struct idxd_wq *wq)
 		}
 	}
 
-	rc = 0;
-	spin_lock(&idxd->dev_lock);
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
-		rc = idxd_device_config(idxd);
-	spin_unlock(&idxd->dev_lock);
+	rc = idxd_device_config(idxd);
 	if (rc < 0) {
 		dev_dbg(dev, "Writing wq %d config failed: %d\n", wq->id, rc);
 		goto err;
@@ -1554,10 +1554,7 @@ int idxd_device_drv_probe(struct idxd_dev *idxd_dev)
 	}
 
 	/* Device configuration */
-	spin_lock(&idxd->dev_lock);
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
-		rc = idxd_device_config(idxd);
-	spin_unlock(&idxd->dev_lock);
+	rc = idxd_device_config(idxd);
 	if (rc < 0)
 		return -ENXIO;
 
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index fb80803d5b57..dd32b81a3108 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -1104,12 +1104,10 @@ static void idxd_reset_done(struct pci_dev *pdev)
 	idxd_device_config_restore(idxd, idxd->idxd_saved);
 
 	/* Re-configure IDXD device if allowed. */
-	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
-		rc = idxd_device_config(idxd);
-		if (rc < 0) {
-			dev_err(dev, "HALT: %s config fails\n", idxd_name);
-			goto out;
-		}
+	rc = idxd_device_config(idxd);
+	if (rc < 0) {
+		dev_err(dev, "HALT: %s config fails\n", idxd_name);
+		goto out;
 	}
 
 	/* Bind IDXD device to driver. */
-- 
cgit v1.2.3


From 52d2edea0d63c935e82631e4b9e4a94eccf97b5b Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:28 -0800
Subject: dmaengine: idxd: Fix crash when the event log is disabled

If reporting errors to the event log is not supported by the hardware,
and an error that causes Function Level Reset (FLR) is received, the
driver will try to restore the event log even if it was not allocated.

Also, only try to free the event log if it was properly allocated.

Fixes: 6078a315aec1 ("dmaengine: idxd: Add idxd_device_config_save() and idxd_device_config_restore() helpers")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-2-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 3 +++
 drivers/dma/idxd/init.c   | 3 ++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index a704475d87b3..5265925f3076 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -831,6 +831,9 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	struct device *dev = &idxd->pdev->dev;
 	struct idxd_evl *evl = idxd->evl;
 
+	if (!evl)
+		return;
+
 	gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
 	if (!gencfg.evl_en)
 		return;
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index dd32b81a3108..1c3f9bc7364b 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -973,7 +973,8 @@ static void idxd_device_config_restore(struct idxd_device *idxd,
 
 	idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit;
 
-	idxd->evl->size = saved_evl->size;
+	if (idxd->evl)
+		idxd->evl->size = saved_evl->size;
 
 	for (i = 0; i < idxd->max_groups; i++) {
 		struct idxd_group *saved_group, *group;
-- 
cgit v1.2.3


From d6077df7b75d26e4edf98983836c05d00ebabd8d Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:29 -0800
Subject: dmaengine: idxd: Fix possible invalid memory access after FLR

In the case that the first Function Level Reset (FLR) concludes
correctly, but in the second FLR the scratch area for the saved
configuration cannot be allocated, it's possible for a invalid memory
access to happen.

Always set the deallocated scratch area to NULL after FLR completes.

Fixes: 98d187a98903 ("dmaengine: idxd: Enable Function Level Reset (FLR) for halt")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-3-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/init.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 1c3f9bc7364b..f1cfc7790d95 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -1146,6 +1146,7 @@ static void idxd_reset_done(struct pci_dev *pdev)
 	}
 out:
 	kfree(idxd->idxd_saved);
+	idxd->idxd_saved = NULL;
 }
 
 static const struct pci_error_handlers idxd_error_handler = {
-- 
cgit v1.2.3


From f019d7814bceb6d8a017b3e55cb53deb1e6fd36b Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:30 -0800
Subject: dmaengine: idxd: Flush kernel workqueues on Function Level Reset

When a Function Level Reset (FLR) happens, terminate the pending
descriptors that were issued by in-kernel users and disable the
interrupts associated with those. They will be re-enabled after FLR
finishes.

idxd_wq_flush_desc() is declared on idxd.h because it's going to be
used in by the DMA backend in a future patch.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-4-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 22 ++++++++++++++++++++++
 drivers/dma/idxd/idxd.h   |  1 +
 drivers/dma/idxd/irq.c    | 16 ++++++++++++++++
 3 files changed, 39 insertions(+)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5265925f3076..5e890b6771cb 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1339,6 +1339,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
 
 	free_irq(ie->vector, ie);
 	idxd_flush_pending_descs(ie);
+
+	/* The interrupt might have been already released by FLR */
+	if (ie->int_handle == INVALID_INT_HANDLE)
+		return;
+
 	if (idxd->request_int_handles)
 		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
 	idxd_device_clear_perm_entry(idxd, ie);
@@ -1347,6 +1352,23 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
 	ie->pasid = IOMMU_PASID_INVALID;
 }
 
+void idxd_wq_flush_descs(struct idxd_wq *wq)
+{
+	struct idxd_irq_entry *ie = &wq->ie;
+	struct idxd_device *idxd = wq->idxd;
+
+	guard(mutex)(&wq->wq_lock);
+
+	if (wq->state != IDXD_WQ_ENABLED || wq->type != IDXD_WQT_KERNEL)
+		return;
+
+	idxd_flush_pending_descs(ie);
+	if (idxd->request_int_handles)
+		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->int_handle = INVALID_INT_HANDLE;
+}
+
 int idxd_wq_request_irq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index ea8c4daed38d..ce78b9a7c641 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -803,6 +803,7 @@ void idxd_wq_quiesce(struct idxd_wq *wq);
 int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
 void idxd_wq_free_irq(struct idxd_wq *wq);
 int idxd_wq_request_irq(struct idxd_wq *wq);
+void idxd_wq_flush_descs(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 7782f8c51c32..6a25e1fd0e62 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -397,6 +397,17 @@ static void idxd_device_flr(struct work_struct *work)
 		dev_err(&idxd->pdev->dev, "FLR failed\n");
 }
 
+static void idxd_wqs_flush_descs(struct idxd_device *idxd)
+{
+	int i;
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *wq = idxd->wqs[i];
+
+		idxd_wq_flush_descs(wq);
+	}
+}
+
 static irqreturn_t idxd_halt(struct idxd_device *idxd)
 {
 	union gensts_reg gensts;
@@ -415,6 +426,11 @@ static irqreturn_t idxd_halt(struct idxd_device *idxd)
 		} else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
 			idxd->state = IDXD_DEV_HALTED;
 			idxd_mask_error_interrupts(idxd);
+			/* Flush all pending descriptors, and disable
+			 * interrupts, they will be re-enabled when FLR
+			 * concludes.
+			 */
+			idxd_wqs_flush_descs(idxd);
 			dev_dbg(&idxd->pdev->dev,
 				"idxd halted, doing FLR. After FLR, configs are restored\n");
 			INIT_WORK(&idxd->work, idxd_device_flr);
-- 
cgit v1.2.3


From 2a93f5747d0eef89a3158c91d185d37d0bca2491 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:31 -0800
Subject: dmaengine: idxd: Flush all pending descriptors

When used as a dmaengine, the DMA "core" might ask the driver to
terminate all pending requests, when that happens, flush all pending
descriptors.

In this context, flush means removing the requests from the pending
lists, so even if they are completed after, the user is not notified.

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-5-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/dma.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index dbecd699237e..e4f9788aa635 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -194,6 +194,15 @@ static void idxd_dma_release(struct dma_device *device)
 	kfree(idxd_dma);
 }
 
+static int idxd_dma_terminate_all(struct dma_chan *c)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+
+	idxd_wq_flush_descs(wq);
+
+	return 0;
+}
+
 int idxd_register_dma_device(struct idxd_device *idxd)
 {
 	struct idxd_dma_dev *idxd_dma;
@@ -224,6 +233,7 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	dma->device_issue_pending = idxd_dma_issue_pending;
 	dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = idxd_dma_free_chan_resources;
+	dma->device_terminate_all = idxd_dma_terminate_all;
 
 	rc = dma_async_device_register(dma);
 	if (rc < 0) {
-- 
cgit v1.2.3


From 4fd3c4679f4f33873d7cb90b3eb553bea4db1038 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:32 -0800
Subject: dmaengine: idxd: Wait for submitted operations on
 .device_synchronize()

When the dmaengine "core" asks the driver to synchronize, send a Drain
operation to the device workqueue, which will wait for the already
submitted operations to finish.

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-6-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/dma.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index e4f9788aa635..9937b671f637 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -203,6 +203,13 @@ static int idxd_dma_terminate_all(struct dma_chan *c)
 	return 0;
 }
 
+static void idxd_dma_synchronize(struct dma_chan *c)
+{
+	struct idxd_wq *wq = to_idxd_wq(c);
+
+	idxd_wq_drain(wq);
+}
+
 int idxd_register_dma_device(struct idxd_device *idxd)
 {
 	struct idxd_dma_dev *idxd_dma;
@@ -234,6 +241,7 @@ int idxd_register_dma_device(struct idxd_device *idxd)
 	dma->device_alloc_chan_resources = idxd_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = idxd_dma_free_chan_resources;
 	dma->device_terminate_all = idxd_dma_terminate_all;
+	dma->device_synchronize = idxd_dma_synchronize;
 
 	rc = dma_async_device_register(dma);
 	if (rc < 0) {
-- 
cgit v1.2.3


From 3d33de353b1ff9023d5ec73b9becf80ea87af695 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:33 -0800
Subject: dmaengine: idxd: Fix not releasing workqueue on .release()

The workqueue associated with an DSA/IAA device is not released when
the object is freed.

Fixes: 47c16ac27d4c ("dmaengine: idxd: fix idxd conf_dev 'struct device' lifetime")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-7-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/sysfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index cc2c83d7f710..6d251095c350 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1836,6 +1836,7 @@ static void idxd_conf_device_release(struct device *dev)
 {
 	struct idxd_device *idxd = confdev_to_idxd(dev);
 
+	destroy_workqueue(idxd->wq);
 	kfree(idxd->groups);
 	bitmap_free(idxd->wq_enable_map);
 	kfree(idxd->wqs);
-- 
cgit v1.2.3


From d9cfb5193a047a92a4d3c0e91ea4cc87c8f7c478 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:34 -0800
Subject: dmaengine: idxd: Fix memory leak when a wq is reset

idxd_wq_disable_cleanup() which is called from the reset path for a
workqueue, sets the wq type to NONE, which for other parts of the
driver mean that the wq is empty (all its resources were released).

Only set the wq type to NONE after its resources are released.

Fixes: da32b28c95a7 ("dmaengine: idxd: cleanup workqueue config after disabling")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-8-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5e890b6771cb..efd7bfccc51f 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -175,6 +175,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 	free_descs(wq);
 	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
+	wq->type = IDXD_WQT_NONE;
 }
 EXPORT_SYMBOL_NS_GPL(idxd_wq_free_resources, "IDXD");
 
@@ -382,7 +383,6 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	lockdep_assert_held(&wq->wq_lock);
 	wq->state = IDXD_WQ_DISABLED;
 	memset(wq->wqcfg, 0, idxd->wqcfg_size);
-	wq->type = IDXD_WQT_NONE;
 	wq->threshold = 0;
 	wq->priority = 0;
 	wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
@@ -1558,7 +1558,6 @@ void idxd_drv_disable_wq(struct idxd_wq *wq)
 	idxd_wq_reset(wq);
 	idxd_wq_free_resources(wq);
 	percpu_ref_exit(&wq->wq_active);
-	wq->type = IDXD_WQT_NONE;
 	wq->client_count = 0;
 }
 EXPORT_SYMBOL_NS_GPL(idxd_drv_disable_wq, "IDXD");
-- 
cgit v1.2.3


From c311f5e9248471a950f0a524c2fd736414d98900 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:35 -0800
Subject: dmaengine: idxd: Fix freeing the allocated ida too late

It can happen that when the cdev .release() is called, the driver
already called ida_destroy(). Move ida_free() to the _del() path.

We see with DEBUG_KOBJECT_RELEASE enabled and forcing an early PCI
unbind.

Fixes: 04922b7445a1 ("dmaengine: idxd: fix cdev setup and free device lifetime issues")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-9-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/cdev.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index c37d233535f9..0366c7cf3502 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -158,11 +158,7 @@ static const struct device_type idxd_cdev_file_type = {
 static void idxd_cdev_dev_release(struct device *dev)
 {
 	struct idxd_cdev *idxd_cdev = dev_to_cdev(dev);
-	struct idxd_cdev_context *cdev_ctx;
-	struct idxd_wq *wq = idxd_cdev->wq;
 
-	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
@@ -582,11 +578,15 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
 
 void idxd_wq_del_cdev(struct idxd_wq *wq)
 {
+	struct idxd_cdev_context *cdev_ctx;
 	struct idxd_cdev *idxd_cdev;
 
 	idxd_cdev = wq->idxd_cdev;
 	wq->idxd_cdev = NULL;
 	cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev));
+
+	cdev_ctx = &ictx[wq->idxd->data->type];
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	put_device(cdev_dev(idxd_cdev));
 }
 
-- 
cgit v1.2.3


From ee66bc29578391c9b48523dc9119af67bd5c7c0f Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Wed, 21 Jan 2026 10:34:36 -0800
Subject: dmaengine: idxd: Fix leaking event log memory

During the device remove process, the device is reset, causing the
configuration registers to go back to their default state, which is
zero. As the driver is checking if the event log support was enabled
before deallocating, it will fail if a reset happened before.

Do not check if the support was enabled, the check for 'idxd->evl'
being valid (only allocated if the HW capability is available) is
enough.

Fixes: 244da66cda35 ("dmaengine: idxd: setup event log configuration")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://patch.msgid.link/20260121-idxd-fix-flr-on-kernel-queues-v3-v3-10-7ed70658a9d1@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/device.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index efd7bfccc51f..131138483b87 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -834,10 +834,6 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	if (!evl)
 		return;
 
-	gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
-	if (!gencfg.evl_en)
-		return;
-
 	mutex_lock(&evl->lock);
 	gencfg.evl_en = 0;
 	iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
-- 
cgit v1.2.3


From 54e367cb94d6bef941bbc1132d9959dc73bd4b6f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 25 Feb 2026 10:47:18 +0000
Subject: KVM: arm64: Deduplicate ASID retrieval code

We currently have three versions of the ASID retrieval code, one
in the S1 walker, and two in the VNCR handling (although the last
two are limited to the EL2&0 translation regime).

Make this code common, and take this opportunity to also simplify
the code a bit while switching over to the TTBRx_EL1_ASID macro.

Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260225104718.14209-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  2 ++
 arch/arm64/kvm/at.c                 | 27 ++---------------
 arch/arm64/kvm/nested.c             | 60 +++++++++++++++++++------------------
 3 files changed, 35 insertions(+), 54 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 905c658057a4..091544e6af44 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -397,6 +397,8 @@ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu);
 int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu);
 void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val);
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime);
+
 #define vncr_fixmap(c)						\
 	({							\
 		u32 __c = (c);					\
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 885bd5bb2f41..6588ea251ed7 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -540,31 +540,8 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
 	wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0);
 
 	wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG);
-	if (wr->nG) {
-		u64 asid_ttbr, tcr;
-
-		switch (wi->regime) {
-		case TR_EL10:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL1) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL1));
-			break;
-		case TR_EL20:
-			tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-			asid_ttbr = ((tcr & TCR_A1) ?
-				     vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-				     vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-			break;
-		default:
-			BUG();
-		}
-
-		wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			wr->asid &= GENMASK(7, 0);
-	}
+	if (wr->nG)
+		wr->asid = get_asid_by_regime(vcpu, wi->regime);
 
 	return 0;
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 7f1ea85dc67a..787776aaf4ad 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -854,6 +854,33 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
 	return kvm_inject_nested_sync(vcpu, esr_el2);
 }
 
+u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime)
+{
+	enum vcpu_sysreg ttbr_elx;
+	u64 tcr;
+	u16 asid;
+
+	switch (regime) {
+	case TR_EL10:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1;
+		break;
+	case TR_EL20:
+		tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+		ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2;
+		break;
+	default:
+		BUG();
+	}
+
+	asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx));
+	if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+	    !(tcr & TCR_ASID16))
+		asid &= GENMASK(7, 0);
+
+	return asid;
+}
+
 static void invalidate_vncr(struct vncr_tlb *vt)
 {
 	vt->valid = false;
@@ -1333,20 +1360,8 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return false;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		return asid == vt->wr.asid;
-	}
+	if (vt->wr.nG)
+		return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid;
 
 	return true;
 }
@@ -1449,21 +1464,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	if (read_vncr_el2(vcpu) != vt->gva)
 		return;
 
-	if (vt->wr.nG) {
-		u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
-		u64 ttbr = ((tcr & TCR_A1) ?
-			    vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
-			    vcpu_read_sys_reg(vcpu, TTBR0_EL2));
-		u16 asid;
-
-		asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
-		if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
-		    !(tcr & TCR_ASID16))
-			asid &= GENMASK(7, 0);
-
-		if (asid != vt->wr.asid)
-			return;
-	}
+	if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid)
+		return;
 
 	vt->cpu = smp_processor_id();
 
-- 
cgit v1.2.3


From 93a4a9b732fbb479f95d327aa867d094aed3f712 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Tue, 24 Feb 2026 17:59:52 +0100
Subject: RDMA/core: Check id_priv->restricted_node_type in cma_listen_on_dev()

When listening on wildcard addresses we have a global list for the application
layer rdma_cm_id and for any existing device or any device added in future we
try to listen on any wildcard listener.

When the listener has a restricted_node_type we should prevent listening on
devices with a different node type.

While there fix the documentation comment of rdma_restrict_node_type()
to include rdma_resolve_addr() instead of having rdma_bind_addr() twice.

Fixes: a760e80e90f5 ("RDMA/core: introduce rdma_restrict_node_type()")
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Steve French <smfrench@gmail.com>
Cc: Namjae Jeon <linkinjeon@kernel.org>
Cc: Tom Talpey <tom@talpey.com>
Cc: Long Li <longli@microsoft.com>
Cc: linux-rdma@vger.kernel.org
Cc: linux-cifs@vger.kernel.org
Cc: samba-technical@lists.samba.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Link: https://patch.msgid.link/20260224165951.3582093-2-metze@samba.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/cma.c | 6 +++++-
 include/rdma/rdma_cm.h        | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e54c07c74575..9480d1a51c11 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2729,6 +2729,9 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
 	*to_destroy = NULL;
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return 0;
+	if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED &&
+	    id_priv->restricted_node_type != cma_dev->device->node_type)
+		return 0;
 
 	dev_id_priv =
 		__rdma_create_id(net, cma_listen_handler, id_priv,
@@ -2736,6 +2739,7 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv,
 	if (IS_ERR(dev_id_priv))
 		return PTR_ERR(dev_id_priv);
 
+	dev_id_priv->restricted_node_type = id_priv->restricted_node_type;
 	dev_id_priv->state = RDMA_CM_ADDR_BOUND;
 	memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv),
 	       rdma_addr_size(cma_src_addr(id_priv)));
@@ -4194,7 +4198,7 @@ int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type)
 	}
 
 	mutex_lock(&lock);
-	if (id_priv->cma_dev)
+	if (READ_ONCE(id_priv->state) != RDMA_CM_IDLE)
 		ret = -EALREADY;
 	else
 		id_priv->restricted_node_type = node_type;
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 6de6fd8bd15e..d639ff889e64 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -181,7 +181,7 @@ void rdma_destroy_id(struct rdma_cm_id *id);
  *
  * It needs to be called before the RDMA identifier is bound
  * to an device, which mean it should be called before
- * rdma_bind_addr(), rdma_bind_addr() and rdma_listen().
+ * rdma_bind_addr(), rdma_resolve_addr() and rdma_listen().
  */
 int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type);
 
-- 
cgit v1.2.3


From 104016eb671e19709721c1b0048dd912dc2e96be Mon Sep 17 00:00:00 2001
From: Jacob Moroni <jmoroni@google.com>
Date: Tue, 24 Feb 2026 23:41:53 +0000
Subject: RDMA/umem: Fix double dma_buf_unpin in failure path

In ib_umem_dmabuf_get_pinned_with_dma_device(), the call to
ib_umem_dmabuf_map_pages() can fail. If this occurs, the dmabuf
is immediately unpinned but the umem_dmabuf->pinned flag is still
set. Then, when ib_umem_release() is called, it calls
ib_umem_dmabuf_revoke() which will call dma_buf_unpin() again.

Fix this by removing the immediate unpin upon failure and just let
the ib_umem_release/revoke path handle it. This also ensures the
proper unmap-unpin unwind ordering if the dmabuf_map_pages call
happened to fail due to dma_resv_wait_timeout (and therefore has
a non-NULL umem_dmabuf->sgt).

Fixes: 1e4df4a21c5a ("RDMA/umem: Allow pinned dmabuf umem usage")
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Link: https://patch.msgid.link/20260224234153.1207849-1-jmoroni@google.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/umem_dmabuf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c
index f5298c33e581..d30f24b90bca 100644
--- a/drivers/infiniband/core/umem_dmabuf.c
+++ b/drivers/infiniband/core/umem_dmabuf.c
@@ -218,13 +218,11 @@ ib_umem_dmabuf_get_pinned_with_dma_device(struct ib_device *device,
 
 	err = ib_umem_dmabuf_map_pages(umem_dmabuf);
 	if (err)
-		goto err_unpin;
+		goto err_release;
 	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
 
 	return umem_dmabuf;
 
-err_unpin:
-	dma_buf_unpin(umem_dmabuf->attach);
 err_release:
 	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
 	ib_umem_release(&umem_dmabuf->umem);
-- 
cgit v1.2.3


From 18c16f602a67782f5eb4b5ab9ba73350b9f711ec Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 4 Feb 2026 20:36:26 +0530
Subject: xfs: Replace ASSERT with XFS_IS_CORRUPT in xfs_rtcopy_summary()

Replace ASSERT(sum > 0) with an XFS_IS_CORRUPT() and place it just
after the call to xfs_rtget_summary() so that we don't end up using
an illegal value of sum.

Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 90a94a5b6f7e..aab59f66384e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -112,6 +112,10 @@ xfs_rtcopy_summary(
 			error = xfs_rtget_summary(oargs, log, bbno, &sum);
 			if (error)
 				goto out;
+			if (XFS_IS_CORRUPT(oargs->mp, sum < 0)) {
+				error = -EFSCORRUPTED;
+				goto out;
+			}
 			if (sum == 0)
 				continue;
 			error = xfs_rtmodify_summary(oargs, log, bbno, -sum);
@@ -120,7 +124,6 @@ xfs_rtcopy_summary(
 			error = xfs_rtmodify_summary(nargs, log, bbno, sum);
 			if (error)
 				goto out;
-			ASSERT(sum > 0);
 		}
 	}
 	error = 0;
-- 
cgit v1.2.3


From a49b7ff63f98ba1c4503869c568c99ecffa478f2 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 11 Feb 2026 19:25:13 +0530
Subject: xfs: Refactoring the nagcount and delta calculation

Introduce xfs_growfs_compute_delta() to calculate the nagcount
and delta blocks and refactor the code from xfs_growfs_data_private().
No functional changes.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ag.c | 28 ++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_ag.h |  3 +++
 fs/xfs/xfs_fsops.c     | 17 ++---------------
 3 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9c6765cc2d44..bd8fbb40b49e 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -872,6 +872,34 @@ resv_err:
 	return err2;
 }
 
+void
+xfs_growfs_compute_deltas(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		nb,
+	int64_t			*deltap,
+	xfs_agnumber_t		*nagcountp)
+{
+	xfs_rfsblock_t	nb_div, nb_mod;
+	int64_t		delta;
+	xfs_agnumber_t	nagcount;
+
+	nb_div = nb;
+	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
+	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
+		nb_div++;
+	else if (nb_mod)
+		nb = nb_div * mp->m_sb.sb_agblocks;
+
+	if (nb_div > XFS_MAX_AGNUMBER + 1) {
+		nb_div = XFS_MAX_AGNUMBER + 1;
+		nb = nb_div * mp->m_sb.sb_agblocks;
+	}
+	nagcount = nb_div;
+	delta = nb - mp->m_sb.sb_dblocks;
+	*deltap = delta;
+	*nagcountp = nagcount;
+}
+
 /*
  * Extent the AG indicated by the @id by the length passed in
  */
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 1f24cfa27321..3cd4790768ff 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -331,6 +331,9 @@ struct aghdr_init_data {
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
 int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp,
 			xfs_extlen_t delta);
+void
+xfs_growfs_compute_deltas(struct xfs_mount *mp, xfs_rfsblock_t nb,
+			int64_t *deltap, xfs_agnumber_t *nagcountp);
 int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp,
 			xfs_extlen_t len);
 int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 17255c41786b..8d64d904d73c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -95,18 +95,17 @@ xfs_growfs_data_private(
 	struct xfs_growfs_data	*in)		/* growfs data input struct */
 {
 	xfs_agnumber_t		oagcount = mp->m_sb.sb_agcount;
+	xfs_rfsblock_t		nb = in->newblocks;
 	struct xfs_buf		*bp;
 	int			error;
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
-	xfs_rfsblock_t		nb, nb_div, nb_mod;
 	int64_t			delta;
 	bool			lastag_extended = false;
 	struct xfs_trans	*tp;
 	struct aghdr_init_data	id = {};
 	struct xfs_perag	*last_pag;
 
-	nb = in->newblocks;
 	error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
 	if (error)
 		return error;
@@ -125,20 +124,8 @@ xfs_growfs_data_private(
 			mp->m_sb.sb_rextsize);
 	if (error)
 		return error;
+	xfs_growfs_compute_deltas(mp, nb, &delta, &nagcount);
 
-	nb_div = nb;
-	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
-	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
-		nb_div++;
-	else if (nb_mod)
-		nb = nb_div * mp->m_sb.sb_agblocks;
-
-	if (nb_div > XFS_MAX_AGNUMBER + 1) {
-		nb_div = XFS_MAX_AGNUMBER + 1;
-		nb = nb_div * mp->m_sb.sb_agblocks;
-	}
-	nagcount = nb_div;
-	delta = nb - mp->m_sb.sb_dblocks;
 	/*
 	 * Reject filesystems with a single AG because they are not
 	 * supported, and reject a shrink operation that would cause a
-- 
cgit v1.2.3


From 4ad85e633bc576a5cc8c8310aab141af7ed20efa Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Wed, 11 Feb 2026 19:25:14 +0530
Subject: xfs: Replace &rtg->rtg_group with rtg_group()

Use the already existing rtg_group() wrapper instead of directly
accessing the struct xfs_group member in struct xfs_rtgroup.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
[cem: Conflict resolution against 06873dbd940d]
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_alloc.c |  6 +++---
 fs/xfs/xfs_zone_gc.c    | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 67e0c8f5800f..e3d19b6dc64a 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -78,7 +78,7 @@ xfs_zone_account_reclaimable(
 	struct xfs_rtgroup	*rtg,
 	uint32_t		freed)
 {
-	struct xfs_group	*xg = &rtg->rtg_group;
+	struct xfs_group	*xg = rtg_group(rtg);
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_zone_info	*zi = mp->m_zone_info;
 	uint32_t		used = rtg_rmap(rtg)->i_used_blocks;
@@ -759,7 +759,7 @@ xfs_zone_alloc_blocks(
 
 	trace_xfs_zone_alloc_blocks(oz, allocated, count_fsb);
 
-	*sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	*sector = xfs_gbno_to_daddr(rtg_group(rtg), 0);
 	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector);
 	if (!*is_seq)
 		*sector += XFS_FSB_TO_BB(mp, allocated);
@@ -1080,7 +1080,7 @@ xfs_init_zone(
 	if (write_pointer == 0) {
 		/* zone is empty */
 		atomic_inc(&zi->zi_nr_free_zones);
-		xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+		xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE);
 		iz->available += rtg_blocks(rtg);
 	} else if (write_pointer < rtg_blocks(rtg)) {
 		/* zone is open */
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 48c6cf584447..7efeecd2d85f 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -627,7 +627,7 @@ xfs_zone_gc_alloc_blocks(
 	if (!*count_fsb)
 		return NULL;
 
-	*daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0);
+	*daddr = xfs_gbno_to_daddr(rtg_group(oz->oz_rtg), 0);
 	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr);
 	if (!*is_seq)
 		*daddr += XFS_FSB_TO_BB(mp, oz->oz_allocated);
@@ -702,7 +702,7 @@ xfs_zone_gc_start_chunk(
 	chunk->data = data;
 	chunk->oz = oz;
 	chunk->victim_rtg = iter->victim_rtg;
-	atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+	atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref);
 	atomic_inc(&chunk->victim_rtg->rtg_gccount);
 
 	bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock);
@@ -788,7 +788,7 @@ xfs_zone_gc_split_write(
 	atomic_inc(&chunk->oz->oz_ref);
 
 	split_chunk->victim_rtg = chunk->victim_rtg;
-	atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+	atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref);
 	atomic_inc(&chunk->victim_rtg->rtg_gccount);
 
 	chunk->offset += split_len;
@@ -888,7 +888,7 @@ xfs_zone_gc_finish_reset(
 		goto out;
 	}
 
-	xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+	xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE);
 	atomic_inc(&zi->zi_nr_free_zones);
 
 	xfs_zoned_add_available(mp, rtg_blocks(rtg));
@@ -917,7 +917,7 @@ xfs_submit_zone_reset_bio(
 
 	XFS_STATS_INC(mp, xs_gc_zone_reset_calls);
 
-	bio->bi_iter.bi_sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	bio->bi_iter.bi_sector = xfs_gbno_to_daddr(rtg_group(rtg), 0);
 	if (!bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) {
 		/*
 		 * Also use the bio to drive the state machine when neither
-- 
cgit v1.2.3


From fd81d3fd01a5ee4bd26a7dc440e7a2209277d14b Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Fri, 13 Feb 2026 08:50:06 +1000
Subject: xfs: fix code alignment issues in xfs_ondisk.c

Fixup some code alignment issues in xfs_ondisk.c

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 2e9715cc1641..70605019383c 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -73,7 +73,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf,		64);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr,		64);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry,	8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr,		32);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map,		4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local,	4);
@@ -116,7 +116,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry,		8);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,	4);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
 	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag,	0);
 	XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length,	2);
-- 
cgit v1.2.3


From 03a6d6c4c85d2758534638fb2bb5f72e0f8877d0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2026 15:14:31 +0100
Subject: xfs: cleanup inode counter stats

Most of them are unused, so mark them as such.  Give the remaining ones
names that match their use instead of the historic IRIX ones based on
vnodes.  Note that the names are purely internal to the XFS code, the
user interface is based on section names and arrays of counters.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_icache.c |  6 +++---
 fs/xfs/xfs_stats.c  | 10 +++++-----
 fs/xfs/xfs_stats.h  | 16 ++++++++--------
 fs/xfs/xfs_super.c  |  4 ++--
 4 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index dbaab4ae709f..f76c6decdaa3 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -106,7 +106,7 @@ xfs_inode_alloc(
 	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
 				    M_IGEO(mp)->min_folio_order);
 
-	XFS_STATS_INC(mp, vn_active);
+	XFS_STATS_INC(mp, xs_inodes_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(ip->i_ino == 0);
 
@@ -172,7 +172,7 @@ __xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
-	XFS_STATS_DEC(ip->i_mount, vn_active);
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
@@ -2234,7 +2234,7 @@ xfs_inode_mark_reclaimable(
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			need_inactive;
 
-	XFS_STATS_INC(mp, vn_reclaim);
+	XFS_STATS_INC(mp, xs_inode_mark_reclaimable);
 
 	/*
 	 * We should never get here with any of the reclaim flags already set.
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index 017db0361cd8..bc4a5d6dc795 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -42,7 +42,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		{ "xstrat",		xfsstats_offset(xs_write_calls)	},
 		{ "rw",			xfsstats_offset(xs_attr_get)	},
 		{ "attr",		xfsstats_offset(xs_iflush_count)},
-		{ "icluster",		xfsstats_offset(vn_active)	},
+		{ "icluster",		xfsstats_offset(xs_inodes_active) },
 		{ "vnodes",		xfsstats_offset(xb_get)		},
 		{ "buf",		xfsstats_offset(xs_abtb_2)	},
 		{ "abtb2",		xfsstats_offset(xs_abtc_2)	},
@@ -100,15 +100,15 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
 	int		c;
-	uint32_t	vn_active;
+	uint32_t	xs_inodes_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
 		preempt_disable();
-		/* save vn_active, it's a universal truth! */
-		vn_active = per_cpu_ptr(stats, c)->s.vn_active;
+		/* save xs_inodes_active, it's a universal truth! */
+		xs_inodes_active = per_cpu_ptr(stats, c)->s.xs_inodes_active;
 		memset(per_cpu_ptr(stats, c), 0, sizeof(*stats));
-		per_cpu_ptr(stats, c)->s.vn_active = vn_active;
+		per_cpu_ptr(stats, c)->s.xs_inodes_active = xs_inodes_active;
 		preempt_enable();
 	}
 }
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 153d2381d0a8..64bc0cc18126 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -100,14 +100,14 @@ struct __xfsstats {
 	uint32_t		xs_iflush_count;
 	uint32_t		xs_icluster_flushcnt;
 	uint32_t		xs_icluster_flushinode;
-	uint32_t		vn_active;	/* # vnodes not on free lists */
-	uint32_t		vn_alloc;	/* # times vn_alloc called */
-	uint32_t		vn_get;		/* # times vn_get called */
-	uint32_t		vn_hold;	/* # times vn_hold called */
-	uint32_t		vn_rele;	/* # times vn_rele called */
-	uint32_t		vn_reclaim;	/* # times vn_reclaim called */
-	uint32_t		vn_remove;	/* # times vn_remove called */
-	uint32_t		vn_free;	/* # times vn_free called */
+	uint32_t		xs_inodes_active;
+	uint32_t		__unused_vn_alloc;
+	uint32_t		__unused_vn_get;
+	uint32_t		__unused_vn_hold;
+	uint32_t		xs_inode_destroy;
+	uint32_t		xs_inode_destroy2; /* same as xs_inode_destroy */
+	uint32_t		xs_inode_mark_reclaimable;
+	uint32_t		__unused_vn_free;
 	uint32_t		xb_get;
 	uint32_t		xb_create;
 	uint32_t		xb_get_locked;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index abc45f860a73..f8de44443e81 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -712,8 +712,8 @@ xfs_fs_destroy_inode(
 	trace_xfs_destroy_inode(ip);
 
 	ASSERT(!rwsem_is_locked(&inode->i_rwsem));
-	XFS_STATS_INC(ip->i_mount, vn_rele);
-	XFS_STATS_INC(ip->i_mount, vn_remove);
+	XFS_STATS_INC(ip->i_mount, xs_inode_destroy);
+	XFS_STATS_INC(ip->i_mount, xs_inode_destroy2);
 	xfs_inode_mark_reclaimable(ip);
 }
 
-- 
cgit v1.2.3


From 47553dd60b1da88df2354f841a4f71dd4de6478a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 2 Feb 2026 15:14:32 +0100
Subject: xfs: remove metafile inodes from the active inode stat

The active inode (or active vnode until recently) stat can get much larger
than expected on file systems with a lot of metafile inodes like zoned
file systems on SMR hard disks with 10.000s of rtg rmap inodes.

Remove all metafile inodes from the active counter to make it more useful
to track actual workloads and add a separate counter for active metafile
inodes.

This fixes xfs/177 on SMR hard drives.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_inode_buf.c |  4 ++++
 fs/xfs/libxfs/xfs_metafile.c  |  5 +++++
 fs/xfs/xfs_icache.c           |  5 ++++-
 fs/xfs/xfs_stats.c            | 11 ++++++++---
 fs/xfs/xfs_stats.h            |  3 ++-
 5 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index a017016e9075..3794e5412eba 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -268,6 +268,10 @@ xfs_inode_from_disk(
 	}
 	if (xfs_is_reflink_inode(ip))
 		xfs_ifork_init_cow(ip);
+	if (xfs_is_metadir_inode(ip)) {
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+		XFS_STATS_INC(ip->i_mount, xs_inodes_meta);
+	}
 	return 0;
 
 out_destroy_data_fork:
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
index cf239f862212..71f004e9dc64 100644
--- a/fs/xfs/libxfs/xfs_metafile.c
+++ b/fs/xfs/libxfs/xfs_metafile.c
@@ -61,6 +61,9 @@ xfs_metafile_set_iflag(
 	ip->i_diflags2 |= XFS_DIFLAG2_METADATA;
 	ip->i_metatype = metafile_type;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+	XFS_STATS_INC(ip->i_mount, xs_inodes_meta);
 }
 
 /* Clear the metadata directory inode flag. */
@@ -74,6 +77,8 @@ xfs_metafile_clear_iflag(
 
 	ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	XFS_STATS_INC(ip->i_mount, xs_inodes_active);
+	XFS_STATS_DEC(ip->i_mount, xs_inodes_meta);
 }
 
 /*
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f76c6decdaa3..f2d4294efd37 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -172,7 +172,10 @@ __xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list));
-	XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
+	if (xfs_is_metadir_inode(ip))
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_meta);
+	else
+		XFS_STATS_DEC(ip->i_mount, xs_inodes_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index bc4a5d6dc795..c13d600732c9 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -59,7 +59,8 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		{ "rtrefcntbt",		xfsstats_offset(xs_qm_dqreclaims)},
 		/* we print both series of quota information together */
 		{ "qm",			xfsstats_offset(xs_gc_read_calls)},
-		{ "zoned",		xfsstats_offset(__pad1)},
+		{ "zoned",		xfsstats_offset(xs_inodes_meta)},
+		{ "metafile",		xfsstats_offset(xs_xstrat_bytes)},
 	};
 
 	/* Loop over all stats groups */
@@ -99,16 +100,20 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
+	uint32_t	xs_inodes_active, xs_inodes_meta;
 	int		c;
-	uint32_t	xs_inodes_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
 		preempt_disable();
-		/* save xs_inodes_active, it's a universal truth! */
+		/*
+		 * Save the active / meta inode counters, as they are stateful.
+		 */
 		xs_inodes_active = per_cpu_ptr(stats, c)->s.xs_inodes_active;
+		xs_inodes_meta = per_cpu_ptr(stats, c)->s.xs_inodes_meta;
 		memset(per_cpu_ptr(stats, c), 0, sizeof(*stats));
 		per_cpu_ptr(stats, c)->s.xs_inodes_active = xs_inodes_active;
+		per_cpu_ptr(stats, c)->s.xs_inodes_meta = xs_inodes_meta;
 		preempt_enable();
 	}
 }
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 64bc0cc18126..57c32b86c358 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -142,7 +142,8 @@ struct __xfsstats {
 	uint32_t		xs_gc_read_calls;
 	uint32_t		xs_gc_write_calls;
 	uint32_t		xs_gc_zone_reset_calls;
-	uint32_t		__pad1;
+/* Metafile counters */
+	uint32_t		xs_inodes_meta;
 /* Extra precision counters */
 	uint64_t		xs_xstrat_bytes;
 	uint64_t		xs_write_bytes;
-- 
cgit v1.2.3


From cddfa648f1ab99e30e91455be19cd5ade26338c2 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Thu, 19 Feb 2026 21:38:25 -0600
Subject: xfs: Fix error pointer dereference

The function try_lookup_noperm() can return an error pointer and is not
checked for one.

Add checks for error pointer in xrep_adoption_check_dcache() and
xrep_adoption_zap_dcache().

Detected by Smatch:
fs/xfs/scrub/orphanage.c:449 xrep_adoption_check_dcache() error:
'd_child' dereferencing possible ERR_PTR()

fs/xfs/scrub/orphanage.c:485 xrep_adoption_zap_dcache() error:
'd_child' dereferencing possible ERR_PTR()

Fixes: 73597e3e42b4 ("xfs: ensure dentry consistency when the orphanage adopts a file")
Cc: stable@vger.kernel.org # v6.16
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/orphanage.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c
index 52a108f6d5f4..33c6db6b4498 100644
--- a/fs/xfs/scrub/orphanage.c
+++ b/fs/xfs/scrub/orphanage.c
@@ -442,6 +442,11 @@ xrep_adoption_check_dcache(
 		return 0;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
+	if (IS_ERR(d_child)) {
+		dput(d_orphanage);
+		return PTR_ERR(d_child);
+	}
+
 	if (d_child) {
 		trace_xrep_adoption_check_child(sc->mp, d_child);
 
@@ -479,7 +484,7 @@ xrep_adoption_zap_dcache(
 		return;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
-	while (d_child != NULL) {
+	while (!IS_ERR_OR_NULL(d_child)) {
 		trace_xrep_adoption_invalidate_child(sc->mp, d_child);
 
 		ASSERT(d_is_negative(d_child));
-- 
cgit v1.2.3


From e764dd439d68cfc16724e469db390d779ab49521 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:35 -0800
Subject: xfs: fix copy-paste error in previous fix

Chris Mason noticed that there is a copy-paste error in a recent change
to xrep_dir_teardown that nulls out pointers after freeing the
resources.

Fixes: ba408d299a3bb3c ("xfs: only call xf{array,blob}_destroy if we have a valid pointer")
Link: https://lore.kernel.org/linux-xfs/20260205194211.2307232-1-clm@meta.com/
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/dir_repair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 9dc55c918c78..23b80c54aa60 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -177,7 +177,7 @@ xrep_dir_teardown(
 	rd->dir_names = NULL;
 	if (rd->dir_entries)
 		xfarray_destroy(rd->dir_entries);
-	rd->dir_names = NULL;
+	rd->dir_entries = NULL;
 }
 
 /* Set up for a directory repair. */
-- 
cgit v1.2.3


From 161456987a1fe4ad73c3f36dec1f684316ac9bdd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:35 -0800
Subject: xfs: fix xfs_group release bug in xfs_verify_report_losses

Chris Mason reports that his AI tools noticed that we were using
xfs_perag_put and xfs_group_put to release the group reference returned
by xfs_group_next_range.  However, the iterator function returns an
object with an active refcount, which means that we must use the correct
function to release the active refcount, which is _rele.

Fixes: b8accfd65d31f2 ("xfs: add media verification ioctl")
Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-xfs/20260206030527.2506821-1-clm@meta.com/
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_verify_media.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c
index 069cd371619d..8bbd4ec567f8 100644
--- a/fs/xfs/xfs_verify_media.c
+++ b/fs/xfs/xfs_verify_media.c
@@ -122,7 +122,7 @@ xfs_verify_report_losses(
 
 			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
 			if (error) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 
@@ -158,7 +158,7 @@ xfs_verify_report_losses(
 		if (rtg)
 			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 		if (error) {
-			xfs_group_put(xg);
+			xfs_group_rele(xg);
 			break;
 		}
 	}
-- 
cgit v1.2.3


From eb8550fb75a875657dc29e3925a40244ec6b6bd6 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:36 -0800
Subject: xfs: fix xfs_group release bug in xfs_dax_notify_dev_failure

Chris Mason reports that his AI tools noticed that we were using
xfs_perag_put and xfs_group_put to release the group reference returned
by xfs_group_next_range.  However, the iterator function returns an
object with an active refcount, which means that we must use the correct
function to release the active refcount, which is _rele.

Cc: <stable@vger.kernel.org> # v6.0
Fixes: 6f643c57d57c56 ("xfs: implement ->notify_failure() for XFS")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_notify_failure.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 6be19fa1ebe2..64c8afb935c2 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -304,7 +304,7 @@ xfs_dax_notify_dev_failure(
 
 			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
 			if (error) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 
@@ -340,7 +340,7 @@ xfs_dax_notify_dev_failure(
 		if (rtg)
 			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 		if (error) {
-			xfs_group_put(xg);
+			xfs_group_rele(xg);
 			break;
 		}
 	}
-- 
cgit v1.2.3


From 94014a23e91a3944947048169ccf38b4561cfd0c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:37 -0800
Subject: xfs: fix potential pointer access race in xfs_healthmon_get

Pankaj Raghav asks about this code in xfs_healthmon_get:

  hm = mp->m_healthmon;
  if (hm && !refcount_inc_not_zero(&hm->ref))
    hm = NULL;
  rcu_read_unlock();
  return hm;

(slightly edited to compress a mailing list thread)

"Nit: Should we do a READ_ONCE(mp->m_healthmon) here to avoid any
compiler tricks that can result in an undefined behaviour? I am not sure
if I am being paranoid here.

"So this is my understanding: RCU guarantees that we get a valid object
(actual data of m_healthmon) but does not guarantee the compiler will
not reread the pointer between checking if hm is !NULL and accessing the
pointer as we are doing it lockless.

"So just a barrier() call in rcu_read_lock is enough to make sure this
doesn't happen and probably adding a READ_ONCE() is not needed?"

After some initial confusion I concluded that he's correct.  The
compiler could very well eliminate the hm variable in favor of walking
the pointers twice, turning the code into:

  if (mp->m_healthmon && !refcount_inc_not_zero(&mp->m_healthmon->ref))

If this happens, then xfs_healthmon_detach can sneak in between the
two sides of the && expression and set mp->m_healthmon to NULL, and
thereby cause a null pointer dereference crash.  Fix this by using the
rcu pointer assignment and dereference functions, which ensure that the
proper reordering barriers are in place.

Practically speaking, gcc seems to allocate an actual variable for hm
and only reads mp->m_healthmon once (as intended), but we ought to be
more explicit about requiring this.

Reported-by: Pankaj Raghav <pankaj.raghav@linux.dev>
Fixes: a48373e7d35a89f6f ("xfs: start creating infrastructure for health monitoring")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_healthmon.c | 11 +++++++----
 fs/xfs/xfs_mount.h     |  2 +-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c
index e37c18cec372..4a06d6632f65 100644
--- a/fs/xfs/xfs_healthmon.c
+++ b/fs/xfs/xfs_healthmon.c
@@ -69,7 +69,7 @@ xfs_healthmon_get(
 	struct xfs_healthmon		*hm;
 
 	rcu_read_lock();
-	hm = mp->m_healthmon;
+	hm = rcu_dereference(mp->m_healthmon);
 	if (hm && !refcount_inc_not_zero(&hm->ref))
 		hm = NULL;
 	rcu_read_unlock();
@@ -110,13 +110,13 @@ xfs_healthmon_attach(
 	struct xfs_healthmon	*hm)
 {
 	spin_lock(&xfs_healthmon_lock);
-	if (mp->m_healthmon != NULL) {
+	if (rcu_access_pointer(mp->m_healthmon) != NULL) {
 		spin_unlock(&xfs_healthmon_lock);
 		return -EEXIST;
 	}
 
 	refcount_inc(&hm->ref);
-	mp->m_healthmon = hm;
+	rcu_assign_pointer(mp->m_healthmon, hm);
 	hm->mount_cookie = (uintptr_t)mp->m_super;
 	spin_unlock(&xfs_healthmon_lock);
 
@@ -128,13 +128,16 @@ STATIC void
 xfs_healthmon_detach(
 	struct xfs_healthmon	*hm)
 {
+	struct xfs_mount	*mp;
+
 	spin_lock(&xfs_healthmon_lock);
 	if (hm->mount_cookie == DETACHED_MOUNT_COOKIE) {
 		spin_unlock(&xfs_healthmon_lock);
 		return;
 	}
 
-	XFS_M((struct super_block *)hm->mount_cookie)->m_healthmon = NULL;
+	mp = XFS_M((struct super_block *)hm->mount_cookie);
+	rcu_assign_pointer(mp->m_healthmon, NULL);
 	hm->mount_cookie = DETACHED_MOUNT_COOKIE;
 	spin_unlock(&xfs_healthmon_lock);
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 61c71128d171..ddd4028be8d6 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -345,7 +345,7 @@ typedef struct xfs_mount {
 	struct xfs_hooks	m_dir_update_hooks;
 
 	/* Private data referring to a health monitor object. */
-	struct xfs_healthmon	*m_healthmon;
+	struct xfs_healthmon __rcu	*m_healthmon;
 } xfs_mount_t;
 
 #define M_IGEO(mp)		(&(mp)->m_ino_geo)
-- 
cgit v1.2.3


From 75690e5fdd74fc4d2a4aec58be9a82aec7cee721 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:38 -0800
Subject: xfs: don't report metadata inodes to fserror

Internal metadata inodes are not exposed to userspace programs, so it
makes no sense to pass them to the fserror functions (aka fsnotify).
Instead, report metadata file problems as general filesystem corruption.

Fixes: 5eb4cb18e445d0 ("xfs: convey metadata health events to the health monitor")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_health.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 169123772cb3..6475159eb930 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -314,6 +314,18 @@ xfs_rgno_mark_sick(
 	xfs_rtgroup_put(rtg);
 }
 
+static inline void xfs_inode_report_fserror(struct xfs_inode *ip)
+{
+	/* Report metadata inodes as general filesystem corruption */
+	if (xfs_is_internal_inode(ip)) {
+		fserror_report_metadata(ip->i_mount->m_super, -EFSCORRUPTED,
+				GFP_NOFS);
+		return;
+	}
+
+	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+}
+
 /* Mark the unhealthy parts of an inode. */
 void
 xfs_inode_mark_sick(
@@ -339,7 +351,7 @@ xfs_inode_mark_sick(
 	inode_state_clear(VFS_I(ip), I_DONTCACHE);
 	spin_unlock(&VFS_I(ip)->i_lock);
 
-	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+	xfs_inode_report_fserror(ip);
 	if (mask)
 		xfs_healthmon_report_inode(ip, XFS_HEALTHMON_SICK, old_mask,
 				mask);
@@ -371,7 +383,7 @@ xfs_inode_mark_corrupt(
 	inode_state_clear(VFS_I(ip), I_DONTCACHE);
 	spin_unlock(&VFS_I(ip)->i_lock);
 
-	fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS);
+	xfs_inode_report_fserror(ip);
 	if (mask)
 		xfs_healthmon_report_inode(ip, XFS_HEALTHMON_CORRUPT, old_mask,
 				mask);
-- 
cgit v1.2.3


From 115ea07b94d2f13942fbd93c6acde376db36b16a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 18 Feb 2026 15:25:38 -0800
Subject: xfs: don't report half-built inodes to fserror

Sam Sun apparently found a syzbot way to fuzz a filesystem such that
xfs_iget_cache_miss would free the inode before the fserror code could
catch up.  Frustratingly he doesn't use the syzbot dashboard so there's
no C reproducer and not even a full error report, so I'm guessing that:

Inodes that are being constructed or torn down inside XFS are not
visible to the VFS.  They should never be reported to fserror.
Also, any inode that has been freshly allocated in _cache_miss should be
marked INEW immediately because, well, it's an incompletely constructed
inode that isn't yet visible to the VFS.

Reported-by: Sam Sun <samsun1006219@gmail.com>
Fixes: 5eb4cb18e445d0 ("xfs: convey metadata health events to the health monitor")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_health.c | 8 ++++++--
 fs/xfs/xfs_icache.c | 9 ++++++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 6475159eb930..239b843e83d4 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -316,8 +316,12 @@ xfs_rgno_mark_sick(
 
 static inline void xfs_inode_report_fserror(struct xfs_inode *ip)
 {
-	/* Report metadata inodes as general filesystem corruption */
-	if (xfs_is_internal_inode(ip)) {
+	/*
+	 * Do not report inodes being constructed or freed, or metadata inodes,
+	 * to fsnotify.
+	 */
+	if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIM) ||
+	    xfs_is_internal_inode(ip)) {
 		fserror_report_metadata(ip->i_mount->m_super, -EFSCORRUPTED,
 				GFP_NOFS);
 		return;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f2d4294efd37..a7a09e7eec81 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -639,6 +639,14 @@ xfs_iget_cache_miss(
 	if (!ip)
 		return -ENOMEM;
 
+	/*
+	 * Set XFS_INEW as early as possible so that the health code won't pass
+	 * the inode to the fserror code if the ondisk inode cannot be loaded.
+	 * We're going to free the xfs_inode immediately if that happens, which
+	 * would lead to UAF problems.
+	 */
+	xfs_iflags_set(ip, XFS_INEW);
+
 	error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags);
 	if (error)
 		goto out_destroy;
@@ -716,7 +724,6 @@ xfs_iget_cache_miss(
 	ip->i_udquot = NULL;
 	ip->i_gdquot = NULL;
 	ip->i_pdquot = NULL;
-	xfs_iflags_set(ip, XFS_INEW);
 
 	/* insert the new inode */
 	spin_lock(&pag->pag_ici_lock);
-- 
cgit v1.2.3


From 8baa9bccc0156d6952d337bf17f57ce15902dfe4 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:23:58 +0530
Subject: xfs: Fix xfs_last_rt_bmblock()

Bug description:

If the size of the last rtgroup i.e, the rtg passed to
xfs_last_rt_bmblock() is such that the last rtextent falls in 0th word
offset of a bmblock of the bitmap file tracking this (last) rtgroup,
then in that case xfs_last_rt_bmblock() incorrectly returns the next
bmblock number instead of the current/last used bmblock number.
When xfs_last_rt_bmblock() incorrectly returns the next bmblock,
the loop to grow/modify the bmblocks in xfs_growfs_rtg() doesn't
execute and xfs_growfs basically does a nop in certain cases.

xfs_growfs will do a nop when the new size of the fs will have the same
number of rtgroups i.e, we are only growing the last rtgroup.

Reproduce:
$ mkfs.xfs -m metadir=0 -r rtdev=/dev/loop1 /dev/loop0 \
	-r size=32769b -f
$ mount -o rtdev=/dev/loop1 /dev/loop0 /mnt/scratch
$ xfs_growfs -R $(( 32769 + 1 )) /mnt/scratch
$ xfs_info /mnt/scratch | grep rtextents
$ # We can see that rtextents hasn't changed

Fix:
Fix this by returning the current/last used bmblock when the last
rtgroup size is not a multiple xfs_rtbitmap_rtx_per_rbmblock()
and the next bmblock when the rtgroup size is a multiple of
xfs_rtbitmap_rtx_per_rbmblock() i.e, the existing blocks are
completely used up.
Also, I have renamed xfs_last_rt_bmblock() to
xfs_last_rt_bmblock_to_extend() to signify that this function
returns the bmblock number to extend and NOT always the last used
bmblock number.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index aab59f66384e..ae53ba2093b2 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1082,17 +1082,27 @@ xfs_last_rtgroup_extents(
 }
 
 /*
- * Calculate the last rbmblock currently used.
+ * This will return the bitmap block number (indexed at 0) that will be
+ * extended/modified. There are 2 cases here:
+ * 1. The size of the rtg is such that it is a multiple of
+ *    xfs_rtbitmap_rtx_per_rbmblock() i.e, an integral number of bitmap blocks
+ *    are completely filled up. In this case, we should return
+ *    1 + (the last used bitmap block number).
+ * 2. The size of the rtg is not an multiple of xfs_rtbitmap_rtx_per_rbmblock().
+ *    Here we will return the block number of last used block number. In this
+ *    case, we will modify the last used bitmap block to extend the size of the
+ *    rtgroup.
  *
  * This also deals with the case where there were no rtextents before.
  */
 static xfs_fileoff_t
-xfs_last_rt_bmblock(
+xfs_last_rt_bmblock_to_extend(
 	struct xfs_rtgroup	*rtg)
 {
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	xfs_rgnumber_t		rgno = rtg_rgno(rtg);
 	xfs_fileoff_t		bmbno = 0;
+	unsigned int		mod = 0;
 
 	ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1);
 
@@ -1100,9 +1110,16 @@ xfs_last_rt_bmblock(
 		xfs_rtxnum_t	nrext = xfs_last_rtgroup_extents(mp);
 
 		/* Also fill up the previous block if not entirely full. */
-		bmbno = xfs_rtbitmap_blockcount_len(mp, nrext);
-		if (xfs_rtx_to_rbmword(mp, nrext) != 0)
-			bmbno--;
+		/* We are doing a -1 to convert it to a 0 based index */
+		bmbno = xfs_rtbitmap_blockcount_len(mp, nrext) - 1;
+		div_u64_rem(nrext, xfs_rtbitmap_rtx_per_rbmblock(mp), &mod);
+		/*
+		 * mod = 0 means that all the current blocks are full. So
+		 * return the next block number to be used for the rtgroup
+		 * growth.
+		 */
+		if (mod == 0)
+			bmbno++;
 	}
 
 	return bmbno;
@@ -1207,7 +1224,8 @@ xfs_growfs_rtg(
 			goto out_rele;
 	}
 
-	for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) {
+	for (bmbno = xfs_last_rt_bmblock_to_extend(rtg); bmbno < bmblocks;
+			bmbno++) {
 		error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno);
 		if (error)
 			goto out_error;
-- 
cgit v1.2.3


From ac1d977096a17d56c55bd7f90be48e81ac4cec3f Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:23:59 +0530
Subject: xfs: Add a comment in xfs_log_sb()

Add a comment explaining why the sb_frextents are updated outside the
if (xfs_has_lazycount(mp) check even though it is a lazycounter.
RT groups are supported only in v5 filesystems which always have
lazycounter enabled - so putting it inside the if(xfs_has_lazycount(mp)
check is redundant.

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_sb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 38d16fe1f6d8..47322adb7690 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1347,6 +1347,9 @@ xfs_log_sb(
 	 * feature was introduced.  This counter can go negative due to the way
 	 * we handle nearly-lockless reservations, so we must use the _positive
 	 * variant here to avoid writing out nonsense frextents.
+	 *
+	 * RT groups are only supported on v5 file systems, which always
+	 * have lazy SB counters.
 	 */
 	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) {
 		mp->m_sb.sb_frextents =
-- 
cgit v1.2.3


From c2368fc89a684be2900daaa2bbf68cbc147e8d3d Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:24:00 +0530
Subject: xfs: Update lazy counters in xfs_growfs_rt_bmblock()

Update lazy counters in xfs_growfs_rt_bmblock() similar to the way it
is done xfs_growfs_data_private(). This is because the lazy counters are
not always updated and synching the counters will avoid inconsistencies
between frexents and rtextents(total realtime extent count). This will
be more useful once realtime shrink is implemented as this will prevent
some transient state to occur where frexents might be greater than
total rtextents.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index ae53ba2093b2..153f3c378f9f 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1050,6 +1050,15 @@ xfs_growfs_rt_bmblock(
 	 */
 	xfs_trans_resv_calc(mp, &mp->m_resv);
 
+	/*
+	 * Sync sb counters now to reflect the updated values. Lazy counters are
+	 * not always updated and in order to avoid inconsistencies between
+	 * frextents and rtextents, it is better to sync the counters.
+	 */
+
+	if (xfs_has_lazysbcount(mp))
+		xfs_log_sb(args.tp);
+
 	error = xfs_trans_commit(args.tp);
 	if (error)
 		goto out_free;
-- 
cgit v1.2.3


From 9a654a8fa3191e9ea32c4494b943c0872a3f5d27 Mon Sep 17 00:00:00 2001
From: "Nirjhar Roy (IBM)" <nirjhar.roy.lists@gmail.com>
Date: Fri, 20 Feb 2026 12:24:01 +0530
Subject: xfs: Add comments for usages of some macros.

Add comments explaining when to use XFS_IS_CORRUPT() and ASSERT()

Suggested-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nirjhar Roy (IBM) <nirjhar.roy.lists@gmail.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_platform.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h
index 1e59bf94d1f2..59a33c60e0ca 100644
--- a/fs/xfs/xfs_platform.h
+++ b/fs/xfs/xfs_platform.h
@@ -235,6 +235,10 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
 
 #ifdef XFS_WARN
 
+/*
+ * Please note that this ASSERT doesn't kill the kernel. It will if the kernel
+ * has panic_on_warn set.
+ */
 #define ASSERT(expr)	\
 	(likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__))
 
@@ -245,6 +249,11 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
 #endif /* XFS_WARN */
 #endif /* DEBUG */
 
+/*
+ * Use this to catch metadata corruptions that are not caught by block or
+ * structure verifiers. The reason is that the verifiers check corruptions only
+ * within the scope of the object being verified.
+ */
 #define XFS_IS_CORRUPT(mp, expr)	\
 	(unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \
 					       NULL, 0, __FILE__, __LINE__, \
-- 
cgit v1.2.3


From e97cbf863d8918452c9f81bebdade8d04e2e7b60 Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Wed, 11 Feb 2026 13:29:02 +1000
Subject: xfs: remove duplicate static size checks

In libxfs/xfs_ondisk.h, remove some duplicate entries of
XFS_CHECK_STRUCT_SIZE().

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 70605019383c..7bccfa7b695c 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -136,16 +136,7 @@ xfs_check_ondisk_structs(void)
 	/* ondisk dir/attr structures from xfs/122 */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry,		3);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free,	4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr,		16);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused,	6);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry,	8);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr,		16);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail,	4);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry,		3);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr,		10);
 
 	/* log structures */
 	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
-- 
cgit v1.2.3


From 650b774cf94495465d6a38c31bb1a6ce697b6b37 Mon Sep 17 00:00:00 2001
From: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Date: Wed, 11 Feb 2026 13:29:04 +1000
Subject: xfs: add static size checks for ioctl UABI

The ioctl structures in libxfs/xfs_fs.h are missing static size checks.
It is useful to have static size checks for these structures as adding
new fields to them could cause issues (e.g. extra padding that may be
inserted by the compiler). So add these checks to xfs/xfs_ondisk.h.

Due to different padding/alignment requirements across different
architectures, to avoid build failures, some structures are ommited from
the size checks. For example, structures with "compat_" definitions in
xfs/xfs_ioctl32.h are ommited.

Signed-off-by: Wilfred Mallawa <wilfred.mallawa@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_ondisk.h | 39 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index 7bccfa7b695c..23cde1248f01 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -208,11 +208,6 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic,	0);
 	XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0);
 
-	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat,		192);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
-
 	/*
 	 * Make sure the incore inode timestamp range corresponds to hand
 	 * converted values based on the ondisk format specification.
@@ -292,6 +287,40 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_SB_OFFSET(sb_pad,			281);
 	XFS_CHECK_SB_OFFSET(sb_rtstart,			288);
 	XFS_CHECK_SB_OFFSET(sb_rtreserved,		296);
+
+	/*
+	 * ioctl UABI
+	 *
+	 * Due to different padding/alignment requirements across
+	 * different architectures, some structures are ommited from
+	 * the size checks. In addition, structures with architecture
+	 * dependent size fields are also ommited (e.g. __kernel_long_t).
+	 */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat,		192);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers,		24);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req,		64);
+	XFS_CHECK_STRUCT_SIZE(struct dioattr,			12);
+	XFS_CHECK_STRUCT_SIZE(struct getbmap,			32);
+	XFS_CHECK_STRUCT_SIZE(struct getbmapx,			48);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_cursor,	16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_ent,		4);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_ag_geometry,		128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_rtgroup_geometry,	128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_error_injection,	8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom,		256);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom_v4,		112);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_counts,		32);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_resblks,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_growfs_log,		8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_bulk_ireq,		64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fs_eofblocks,		128);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_fsid,			8);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_metadata,	64);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec,		16);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec_head,	40);
 }
 
 #endif /* __XFS_ONDISK_H */
-- 
cgit v1.2.3


From 6b050482ec40569429d963ac52afa878691b04c9 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 24 Feb 2026 16:17:52 -0800
Subject: cpufreq: intel_pstate: Fix crash during turbo disable

When the system is booted with kernel command line argument "nosmt" or
"maxcpus" to limit the number of CPUs, disabling turbo via:

 echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo

results in a crash:

 PF: supervisor read access in kernel mode
 PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] SMP PTI
 ...
 RIP: 0010:store_no_turbo+0x100/0x1f0
 ...

This occurs because for_each_possible_cpu() returns CPUs even if they
are not online. For those CPUs, all_cpu_data[] will be NULL. Since
commit 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency
updates handling code"), all_cpu_data[] is dereferenced even for CPUs
which are not online, causing the NULL pointer dereference.

To fix that, pass CPU number to intel_pstate_update_max_freq() and use
all_cpu_data[] for those CPUs for which there is a valid cpufreq policy.

Fixes: 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency updates handling code")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221068
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 6.16+ <stable@vger.kernel.org> # 6.16+
Link: https://patch.msgid.link/20260225001752.890164-1-srinivas.pandruvada@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index bdc37080d319..11c58af41900 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1476,13 +1476,13 @@ static void __intel_pstate_update_max_freq(struct cpufreq_policy *policy,
 	refresh_frequency_limits(policy);
 }
 
-static bool intel_pstate_update_max_freq(struct cpudata *cpudata)
+static bool intel_pstate_update_max_freq(int cpu)
 {
-	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return false;
 
-	__intel_pstate_update_max_freq(policy, cpudata);
+	__intel_pstate_update_max_freq(policy, all_cpu_data[cpu]);
 
 	return true;
 }
@@ -1501,7 +1501,7 @@ static void intel_pstate_update_limits_for_all(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		intel_pstate_update_max_freq(all_cpu_data[cpu]);
+		intel_pstate_update_max_freq(cpu);
 
 	mutex_lock(&hybrid_capacity_lock);
 
@@ -1910,7 +1910,7 @@ static void intel_pstate_notify_work(struct work_struct *work)
 	struct cpudata *cpudata =
 		container_of(to_delayed_work(work), struct cpudata, hwp_notify_work);
 
-	if (intel_pstate_update_max_freq(cpudata)) {
+	if (intel_pstate_update_max_freq(cpudata->cpu)) {
 		/*
 		 * The driver will not be unregistered while this function is
 		 * running, so update the capacity without acquiring the driver
-- 
cgit v1.2.3


From c9bc1753b3cc41d0e01fbca7f035258b5f4db0ae Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 24 Feb 2026 13:29:09 +0100
Subject: perf: Fix __perf_event_overflow() vs perf_remove_from_context() race

Make sure that __perf_event_overflow() runs with IRQs disabled for all
possible callchains. Specifically the software events can end up running
it with only preemption disabled.

This opens up a race vs perf_event_exit_event() and friends that will go
and free various things the overflow path expects to be present, like
the BPF program.

Fixes: 592903cdcbf6 ("perf_counter: add an event_list")
Reported-by: Simond Hu <cmdhh1767@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Simond Hu <cmdhh1767@gmail.com>
Link: https://patch.msgid.link/20260224122909.GV1395416@noisy.programming.kicks-ass.net
---
 kernel/events/core.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 22a0f405585b..1f5699b339ec 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10777,6 +10777,13 @@ int perf_event_overflow(struct perf_event *event,
 			struct perf_sample_data *data,
 			struct pt_regs *regs)
 {
+	/*
+	 * Entry point from hardware PMI, interrupts should be disabled here.
+	 * This serializes us against perf_event_remove_from_context() in
+	 * things like perf_event_release_kernel().
+	 */
+	lockdep_assert_irqs_disabled();
+
 	return __perf_event_overflow(event, 1, data, regs);
 }
 
@@ -10853,6 +10860,19 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 {
 	struct hw_perf_event *hwc = &event->hw;
 
+	/*
+	 * This is:
+	 *   - software		preempt
+	 *   - tracepoint	preempt
+	 *   -   tp_target_task	irq (ctx->lock)
+	 *   - uprobes		preempt/irq
+	 *   - kprobes		preempt/irq
+	 *   - hw_breakpoint	irq
+	 *
+	 * Any of these are sufficient to hold off RCU and thus ensure @event
+	 * exists.
+	 */
+	lockdep_assert_preemption_disabled();
 	local64_add(nr, &event->count);
 
 	if (!regs)
@@ -10861,6 +10881,16 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
 	if (!is_sampling_event(event))
 		return;
 
+	/*
+	 * Serialize against event_function_call() IPIs like normal overflow
+	 * event handling. Specifically, must not allow
+	 * perf_event_release_kernel() -> perf_remove_from_context() to make
+	 * progress and 'release' the event from under us.
+	 */
+	guard(irqsave)();
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
 		data->period = nr;
 		return perf_swevent_overflow(event, 1, data, regs);
@@ -11359,6 +11389,11 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 	struct perf_sample_data data;
 	struct perf_event *event;
 
+	/*
+	 * Per being a tracepoint, this runs with preemption disabled.
+	 */
+	lockdep_assert_preemption_disabled();
+
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = entry_size,
@@ -11691,6 +11726,11 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	struct perf_sample_data sample;
 	struct pt_regs *regs = data;
 
+	/*
+	 * Exception context, will have interrupts disabled.
+	 */
+	lockdep_assert_irqs_disabled();
+
 	perf_sample_data_init(&sample, bp->attr.bp_addr, 0);
 
 	if (!bp->hw.state && !perf_exclude_event(bp, regs))
@@ -12155,7 +12195,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 
 	if (regs && !perf_exclude_event(event, regs)) {
 		if (!(event->attr.exclude_idle && is_idle_task(current)))
-			if (__perf_event_overflow(event, 1, &data, regs))
+			if (perf_event_overflow(event, &data, regs))
 				ret = HRTIMER_NORESTART;
 	}
 
-- 
cgit v1.2.3


From ab6088e7a95943af3452b20e3b96caaaef3eeebd Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 24 Feb 2026 16:16:30 -0700
Subject: lib/Kconfig.debug: Require a release version of LLVM 22 for context
 analysis

Using a prerelease version as a minimum supported version for
CONFIG_WARN_CONTEXT_ANALYSIS was reasonable to do while LLVM 22 was the
development version so that people could immediately build from main and
start testing and validating this in their own code. However, it can be
problematic when using prerelease versions of LLVM 22, such as Android
clang 22.0.1 (the current android mainline compiler) or when bisecting
LLVM between llvmorg-22-init and llvmorg-23-init, to build the kernel,
as all compiler fixes for the context analysis may not be present,
potentially resulting in warnings that can easily turn into errors.

Now that LLVM 22 is released as 22.1.0, upgrade the check to require at
least this version to ensure that a user's toolchain actually has all
the changes needed for a smooth experience with context analysis.

Fixes: 3269701cb256 ("compiler-context-analysis: Add infrastructure for Context Analysis with Clang")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Marco Elver <elver@google.com>
Link: https://patch.msgid.link/20260224-bump-clang-ver-context-analysis-v1-1-16cc7a90a040@kernel.org
---
 lib/Kconfig.debug | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 4e2dfbbd3d78..8e2b858078e6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -630,7 +630,7 @@ config DEBUG_FORCE_WEAK_PER_CPU
 
 config WARN_CONTEXT_ANALYSIS
 	bool "Compiler context-analysis warnings"
-	depends on CC_IS_CLANG && CLANG_VERSION >= 220000
+	depends on CC_IS_CLANG && CLANG_VERSION >= 220100
 	# Branch profiling re-defines "if", which messes with the compiler's
 	# ability to analyze __cond_acquires(..), resulting in false positives.
 	depends on !TRACE_BRANCH_PROFILING
@@ -641,7 +641,7 @@ config WARN_CONTEXT_ANALYSIS
 	  and releasing user-definable "context locks".
 
 	  Clang's name of the feature is "Thread Safety Analysis". Requires
-	  Clang 22 or later.
+	  Clang 22.1.0 or later.
 
 	  Produces warnings by default. Select CONFIG_WERROR if you wish to
 	  turn these warnings into errors.
-- 
cgit v1.2.3


From e9fb2028f1eb563e653cff3b0d1c87c5e0203d45 Mon Sep 17 00:00:00 2001
From: Panagiotis Foliadis <pfoliadis@posteo.net>
Date: Wed, 25 Feb 2026 14:53:43 +0000
Subject: ALSA: hda/intel: increase default bdl_pos_adj for Nvidia controllers

The default bdl_pos_adj of 32 for Nvidia HDA controllers is
insufficient on GA102 (and likely other recent Nvidia GPUs) after S3
suspend/resume. The controller's DMA timing degrades after resume,
causing premature IRQ detection in azx_position_ok() which results in
silent HDMI/DP audio output despite userspace reporting a valid
playback state and correct ELD data.

Increase bdl_pos_adj to 64 for AZX_DRIVER_NVIDIA, matching the value
already used by Intel Apollo Lake for the same class of timing issue.

Cc: stable@vger.kernel.org
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221069
Suggested-by: Charalampos Mitrodimas <charmitro@posteo.net>
Signed-off-by: Panagiotis Foliadis <pfoliadis@posteo.net>
Link: https://patch.msgid.link/20260225-nvidia-audio-fix-v1-1-b1383c37ec49@posteo.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/controllers/intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c
index 6fddf400c4a3..3f434994c18d 100644
--- a/sound/hda/controllers/intel.c
+++ b/sound/hda/controllers/intel.c
@@ -1751,6 +1751,8 @@ static int default_bdl_pos_adj(struct azx *chip)
 		return 1;
 	case AZX_DRIVER_ZHAOXINHDMI:
 		return 128;
+	case AZX_DRIVER_NVIDIA:
+		return 64;
 	default:
 		return 32;
 	}
-- 
cgit v1.2.3


From 85f6c439a69afe4fa8a688512e586971e97e273a Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 25 Feb 2026 10:35:57 +0000
Subject: io_uring/timeout: READ_ONCE sqe->addr

We should use READ_ONCE when reading from a SQE, make sure timeout gets
a stable timespec address.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/timeout.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 84dda24f3eb2..cb61d4862fc6 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -462,7 +462,7 @@ int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 			tr->ltimeout = true;
 		if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS))
 			return -EINVAL;
-		if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
+		if (get_timespec64(&tr->ts, u64_to_user_ptr(READ_ONCE(sqe->addr2))))
 			return -EFAULT;
 		if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0)
 			return -EINVAL;
@@ -557,7 +557,7 @@ static int __io_timeout_prep(struct io_kiocb *req,
 	data->req = req;
 	data->flags = flags;
 
-	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
+	if (get_timespec64(&data->ts, u64_to_user_ptr(READ_ONCE(sqe->addr))))
 		return -EFAULT;
 
 	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
-- 
cgit v1.2.3


From 0d785e2c324c90662baa4fe07a0d02233ff92824 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:04 +0100
Subject: s390/idle: Fix cpu idle exit cpu time accounting

With the conversion to generic entry [1] cpu idle exit cpu time accounting
was converted from assembly to C. This introduced an reversed order of cpu
time accounting.

On cpu idle exit the current accounting happens with the following call
chain:

-> do_io_irq()/do_ext_irq()
 -> irq_enter_rcu()
  -> account_hardirq_enter()
   -> vtime_account_irq()
    -> vtime_account_kernel()

vtime_account_kernel() accounts the passed cpu time since last_update_timer
as system time, and updates last_update_timer to the current cpu timer
value.

However the subsequent call of

 -> account_idle_time_irq()

will incorrectly subtract passed cpu time from timer_idle_enter to the
updated last_update_timer value from system_timer. Then last_update_timer
is updated to a sys_enter_timer, which means that last_update_timer goes
back in time.

Subsequently account_hardirq_exit() will account too much cpu time as
hardirq time. The sum of all accounted cpu times is still correct, however
some cpu time which was previously accounted as system time is now
accounted as hardirq time, plus there is the oddity that last_update_timer
goes back in time.

Restore previous behavior by extracting cpu time accounting code from
account_idle_time_irq() into a new update_timer_idle() function and call it
before irq_enter_rcu().

Fixes: 56e62a737028 ("s390: convert to generic entry") [1]
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h |  1 +
 arch/s390/kernel/idle.c      | 13 +++++++++----
 arch/s390/kernel/irq.c       | 10 ++++++++--
 3 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 09f763b9eb40..133059d9a949 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -23,5 +23,6 @@ extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
 void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
+void update_timer_idle(void);
 
 #endif /* _S390_IDLE_H */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 39cb8d0ae348..0f9e53f0a068 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -21,11 +21,10 @@
 
 static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
-void account_idle_time_irq(void)
+void update_timer_idle(void)
 {
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	struct lowcore *lc = get_lowcore();
-	unsigned long idle_time;
 	u64 cycles_new[8];
 	int i;
 
@@ -35,13 +34,19 @@ void account_idle_time_irq(void)
 			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
-	idle_time = lc->int_clock - idle->clock_idle_enter;
-
 	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
 	lc->last_update_clock = lc->int_clock;
 
 	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
 	lc->last_update_timer = lc->sys_enter_timer;
+}
+
+void account_idle_time_irq(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	unsigned long idle_time;
+
+	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
 	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index f81723bc8856..d10a17e6531d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -146,6 +146,10 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle)
+		update_timer_idle();
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -154,7 +158,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			current->thread.last_break = regs->last_break;
 	}
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
@@ -182,6 +185,10 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	bool from_idle;
 
+	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
+	if (from_idle)
+		update_timer_idle();
+
 	irq_enter_rcu();
 
 	if (user_mode(regs)) {
@@ -194,7 +201,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	regs->int_parm = get_lowcore()->ext_params;
 	regs->int_parm_long = get_lowcore()->ext_params2;
 
-	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
 	if (from_idle)
 		account_idle_time_irq();
 
-- 
cgit v1.2.3


From dbc0fb35679ed5d0adecf7d02137ac2c77244b3b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:05 +0100
Subject: s390/vtime: Fix virtual timer forwarding

Since delayed accounting of system time [1] the virtual timer is
forwarded by do_account_vtime() but also vtime_account_kernel(),
vtime_account_softirq(), and vtime_account_hardirq(). This leads
to double accounting of system, guest, softirq, and hardirq time.

Remove accounting from the vtime_account*() family to restore old behavior.

There is only one user of the vtimer interface, which might explain
why nobody noticed this so far.

Fixes: b7394a5f4ce9 ("sched/cputime, s390: Implement delayed accounting of system time") [1]
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 234a0ba30510..122d30b10440 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -225,10 +225,6 @@ static u64 vtime_delta(void)
 	return timer - lc->last_update_timer;
 }
 
-/*
- * Update process times based on virtual cpu times stored by entry.S
- * to the lowcore fields user_timer, system_timer & steal_clock.
- */
 void vtime_account_kernel(struct task_struct *tsk)
 {
 	struct lowcore *lc = get_lowcore();
@@ -238,27 +234,17 @@ void vtime_account_kernel(struct task_struct *tsk)
 		lc->guest_timer += delta;
 	else
 		lc->system_timer += delta;
-
-	virt_timer_forward(delta);
 }
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
 void vtime_account_softirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->softirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->softirq_timer += vtime_delta();
 }
 
 void vtime_account_hardirq(struct task_struct *tsk)
 {
-	u64 delta = vtime_delta();
-
-	get_lowcore()->hardirq_timer += delta;
-
-	virt_timer_forward(delta);
+	get_lowcore()->hardirq_timer += vtime_delta();
 }
 
 /*
-- 
cgit v1.2.3


From aefa6ec890f0d39a89fc80e95908ec1996337eee Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:06 +0100
Subject: s390/idle: Add comment for non obvious code

Add a comment to update_timer_idle() which describes why wall time (not
steal time) is added to steal_timer. This is not obvious and was reported
by Frederic Weisbecker.

Reported-by: Frederic Weisbecker <frederic@kernel.org>
Closes: https://lore.kernel.org/all/aXEVM-04lj0lntMr@localhost.localdomain/
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/idle.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 0f9e53f0a068..4e09f126d4fc 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -34,6 +34,15 @@ void update_timer_idle(void)
 			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
 	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
 	lc->last_update_clock = lc->int_clock;
 
-- 
cgit v1.2.3


From 00d8b035eb71262abb547d47717b19f4a55ad4f2 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:07 +0100
Subject: s390/idle: Slightly optimize idle time accounting

Slightly optimize account_idle_time_irq() and update_timer_idle():

- Use fast single instruction __atomic64() primitives to update per
  cpu idle_time and idle_count, instead of READ_ONCE() / WRITE_ONCE()
  pairs

- stcctm() is an inline assembly with a full memory barrier. This
  leads to a not necessary extra dereference of smp_cpu_mtid in
  update_timer_idle(). Avoid this and read smp_cpu_mtid into a
  variable

- Use __this_cpu_add() instead of this_cpu_add() to avoid disabling /
  enabling of preemption several times in a loop in update_timer_idle().

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/idle.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 4e09f126d4fc..627d82dd900e 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -26,12 +26,13 @@ void update_timer_idle(void)
 	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	struct lowcore *lc = get_lowcore();
 	u64 cycles_new[8];
-	int i;
+	int i, mtid;
 
-	if (smp_cpu_mtid) {
-		stcctm(MT_DIAG, smp_cpu_mtid, cycles_new);
-		for (i = 0; i < smp_cpu_mtid; i++)
-			this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
 	}
 
 	/*
@@ -58,8 +59,8 @@ void account_idle_time_irq(void)
 	idle_time = get_lowcore()->int_clock - idle->clock_idle_enter;
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time);
-	WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1);
+	__atomic64_add(idle_time, &idle->idle_time);
+	__atomic64_add_const(1, &idle->idle_count);
 	account_idle_time(cputime_to_nsecs(idle_time));
 }
 
-- 
cgit v1.2.3


From 257c14e5a1d8de40fded80fd8b525af55a6ded26 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:08 +0100
Subject: s390/idle: Inline update_timer_idle()

Inline update_timer_idle() again to avoid an extra function call. This
way the generated code is close to old assembler version again.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h  |  3 ++-
 arch/s390/include/asm/vtime.h | 34 ++++++++++++++++++++++++++++++++++
 arch/s390/kernel/entry.h      |  2 --
 arch/s390/kernel/idle.c       | 34 ++--------------------------------
 4 files changed, 38 insertions(+), 35 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 133059d9a949..8c5aa7329461 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -19,10 +19,11 @@ struct s390_idle_data {
 	unsigned long mt_cycles_enter[8];
 };
 
+DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
+
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
 void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-void update_timer_idle(void);
 
 #endif /* _S390_IDLE_H */
diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index 9d25fb35a042..b1db75d14e9d 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,6 +2,12 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
+#include <asm/lowcore.h>
+#include <asm/cpu_mf.h>
+#include <asm/idle.h>
+
+DECLARE_PER_CPU(u64, mt_cycles[8]);
+
 static inline void update_timer_sys(void)
 {
 	struct lowcore *lc = get_lowcore();
@@ -20,4 +26,32 @@ static inline void update_timer_mcck(void)
 	lc->last_update_timer = lc->mcck_enter_timer;
 }
 
+static inline void update_timer_idle(void)
+{
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	struct lowcore *lc = get_lowcore();
+	u64 cycles_new[8];
+	int i, mtid;
+
+	mtid = smp_cpu_mtid;
+	if (mtid) {
+		stcctm(MT_DIAG, mtid, cycles_new);
+		for (i = 0; i < mtid; i++)
+			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
+	}
+	/*
+	 * This is a bit subtle: Forward last_update_clock so it excludes idle
+	 * time. For correct steal time calculation in do_account_vtime() add
+	 * passed wall time before idle_enter to steal_timer:
+	 * During the passed wall time before idle_enter CPU time may have
+	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
+	 * The accounted CPU times will be subtracted again from steal_timer
+	 * when accumulated steal time is calculated in do_account_vtime().
+	 */
+	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
+	lc->last_update_clock = lc->int_clock;
+	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
+	lc->last_update_timer = lc->sys_enter_timer;
+}
+
 #endif /* _S390_VTIME_H */
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index dd55cc6bbc28..fb67b4abe68c 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t);
 long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t);
 long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags);
 
-DECLARE_PER_CPU(u64, mt_cycles[8]);
-
 unsigned long stack_alloc(void);
 void stack_free(unsigned long stack);
 
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 627d82dd900e..1f1b06b6b4ef 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -15,41 +15,11 @@
 #include <trace/events/power.h>
 #include <asm/cpu_mf.h>
 #include <asm/cputime.h>
+#include <asm/idle.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
-#include "entry.h"
 
-static DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
-
-void update_timer_idle(void)
-{
-	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
-	struct lowcore *lc = get_lowcore();
-	u64 cycles_new[8];
-	int i, mtid;
-
-	mtid = smp_cpu_mtid;
-	if (mtid) {
-		stcctm(MT_DIAG, mtid, cycles_new);
-		for (i = 0; i < mtid; i++)
-			__this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]);
-	}
-
-	/*
-	 * This is a bit subtle: Forward last_update_clock so it excludes idle
-	 * time. For correct steal time calculation in do_account_vtime() add
-	 * passed wall time before idle_enter to steal_timer:
-	 * During the passed wall time before idle_enter CPU time may have
-	 * been accounted to system, hardirq, softirq, etc. lowcore fields.
-	 * The accounted CPU times will be subtracted again from steal_timer
-	 * when accumulated steal time is calculated in do_account_vtime().
-	 */
-	lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock;
-	lc->last_update_clock = lc->int_clock;
-
-	lc->system_timer += lc->last_update_timer - idle->timer_idle_enter;
-	lc->last_update_timer = lc->sys_enter_timer;
-}
+DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
 
 void account_idle_time_irq(void)
 {
-- 
cgit v1.2.3


From d8b5cf9c63143fae54a734c41e3bb55cf3f365c7 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:09 +0100
Subject: s390/irq/idle: Remove psw bits early

Remove wait, io, external interrupt bits early in do_io_irq()/do_ext_irq()
when previous context was idle. This saves one conditional branch and is
closer to the original old assembly code.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/irq.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index d10a17e6531d..7fdf960191d3 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -147,8 +147,10 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle)
+	if (from_idle) {
 		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
 
 	irq_enter_rcu();
 
@@ -174,9 +176,6 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -186,8 +185,10 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle)
+	if (from_idle) {
 		update_timer_idle();
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
+	}
 
 	irq_enter_rcu();
 
@@ -209,9 +210,6 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
-
-	if (from_idle)
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)
-- 
cgit v1.2.3


From e282ccd308de7b2a65eb4596da8030c18b543071 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:10 +0100
Subject: s390/vtime: Use __this_cpu_read() / get rid of READ_ONCE()

do_account_vtime() runs always with interrupts disabled, therefore use
__this_cpu_read() instead of this_cpu_read() to get rid of a pointless
preempt_disable() / preempt_enable() pair.

Also there are no concurrent writers to the cpu time accounting fields
in lowcore. Therefore get rid of READ_ONCE() usages.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 122d30b10440..4111ff4d727c 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -137,23 +137,16 @@ static int do_account_vtime(struct task_struct *tsk)
 		lc->system_timer += timer;
 
 	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
+	if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
 	/* Calculate cputime delta */
-	user = update_tsk_timer(&tsk->thread.user_timer,
-				READ_ONCE(lc->user_timer));
-	guest = update_tsk_timer(&tsk->thread.guest_timer,
-				 READ_ONCE(lc->guest_timer));
-	system = update_tsk_timer(&tsk->thread.system_timer,
-				  READ_ONCE(lc->system_timer));
-	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
-				   READ_ONCE(lc->hardirq_timer));
-	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
-				   READ_ONCE(lc->softirq_timer));
-	lc->steal_timer +=
-		clock - user - guest - system - hardirq - softirq;
+	user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer);
+	guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer);
+	system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer);
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer);
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer);
+	lc->steal_timer += clock - user - guest - system - hardirq - softirq;
 
 	/* Push account value */
 	if (user) {
-- 
cgit v1.2.3


From 80f63fd09efe9d9c016fd6378116eb7394edd2f2 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:11 +0100
Subject: s390/vtime: Use lockdep_assert_irqs_disabled() instead of BUG_ON()

Use lockdep_assert_irqs_disabled() instead of BUG_ON(). This avoids
crashing the kernel, and generates better code if CONFIG_PROVE_LOCKING
is disabled.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/vtime.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 4111ff4d727c..bf48744d0912 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires)
 
 static inline int virt_timer_forward(u64 elapsed)
 {
-	BUG_ON(!irqs_disabled());
-
+	lockdep_assert_irqs_disabled();
 	if (list_empty(&virt_timer_list))
 		return 0;
 	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);
-- 
cgit v1.2.3


From acbc0437ca3cf6c19005476a4f1f5a7c96ff4256 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 18 Feb 2026 15:20:12 +0100
Subject: s390/idle: Remove psw_idle() prototype

psw_idle() does not exist anymore. Remove its prototype.

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/idle.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h
index 8c5aa7329461..32536ee34aa0 100644
--- a/arch/s390/include/asm/idle.h
+++ b/arch/s390/include/asm/idle.h
@@ -24,6 +24,4 @@ DECLARE_PER_CPU(struct s390_idle_data, s390_idle);
 extern struct device_attribute dev_attr_idle_count;
 extern struct device_attribute dev_attr_idle_time_us;
 
-void psw_idle(struct s390_idle_data *data, unsigned long psw_mask);
-
 #endif /* _S390_IDLE_H */
-- 
cgit v1.2.3


From 1623a554c68f352c17d0a358bc62580dc187f06b Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 23 Feb 2026 23:33:52 +0100
Subject: s390/kexec: Disable stack protector in s390_reset_system()

s390_reset_system() calls set_prefix(0), which switches back to the
absolute lowcore. At that point the stack protector canary no longer
matches the canary from the lowcore the function was entered with, so
the stack check fails.

Mark s390_reset_system() __no_stack_protector. This is safe here since
its callers (__do_machine_kdump() and __do_machine_kexec()) are
effectively no-return and fall back to disabled_wait() on failure.

Fixes: f5730d44e05e ("s390: Add stackprotector support")
Reported-by: Nikita Dubrovskii <nikita@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/ipl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index dcdc7e274848..049c557c452f 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2377,7 +2377,7 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void s390_reset_system(void)
+void __no_stack_protector s390_reset_system(void)
 {
 	/* Disable prefixing */
 	set_prefix(0);
-- 
cgit v1.2.3


From d879ac6756b662a085a743e76023c768c3241579 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Tue, 24 Feb 2026 07:41:07 +0100
Subject: s390/pfault: Fix virtual vs physical address confusion

When Linux is running as guest, runs a user space process and the
user space process accesses a page that the host has paged out,
the guest gets a pfault interrupt and schedules a different process.
Without this mechanism the host would have to suspend the whole
virtual CPU until the page has been paged in.

To setup the pfault interrupt the real address of parameter list
should be passed to DIAGNOSE 0x258, but a virtual address is passed
instead.

That has a performance impact, since the pfault setup never succeeds,
the interrupt is never delivered to a guest and the whole virtual CPU
is suspended as result.

Cc: stable@vger.kernel.org
Fixes: c98d2ecae08f ("s390/mm: Uncouple physical vs virtual address spaces")
Reported-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/mm/pfault.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c
index 2f829448c719..6ecd6b0a22a8 100644
--- a/arch/s390/mm/pfault.c
+++ b/arch/s390/mm/pfault.c
@@ -62,7 +62,7 @@ int __pfault_init(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		: [rc] "+d" (rc)
-		: [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk)
 		: "cc");
 	return rc;
 }
@@ -84,7 +84,7 @@ void __pfault_fini(void)
 		"0:	nopr	%%r7\n"
 		EX_TABLE(0b, 0b)
 		:
-		: [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk)
+		: [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk)
 		: "cc");
 }
 
-- 
cgit v1.2.3


From 2b476739f93d286dc7c2b9d14301eaccccd789d3 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Fri, 13 Feb 2026 17:02:33 +0000
Subject: MAINTAINERS: remove Tudor Ambarus as SPI NOR maintainer

I have not been actively involved in SPI NOR development recently and
would like to step down to focus on my current day-to-day work.

The subsystem remains in good hands with Pratyush and Michael.

Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Acked-by: Michael Walle <mwalle@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..e1694b2c3400 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24909,7 +24909,6 @@ F:	drivers/clk/spear/
 F:	drivers/pinctrl/spear/
 
 SPI NOR SUBSYSTEM
-M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 M:	Pratyush Yadav <pratyush@kernel.org>
 M:	Michael Walle <mwalle@kernel.org>
 L:	linux-mtd@lists.infradead.org
-- 
cgit v1.2.3


From 82d938d5266256d2f4d90ed3733a421493eb3623 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Fri, 13 Feb 2026 17:02:34 +0000
Subject: MAINTAINERS: add Takahiro Kuwano as SPI NOR reviewer

Takahiro has been an active contributor to the SPI NOR subsystem,
providing valuable patches and reviews. Add him as a designated
reviewer to help facilitate patch processing and maintenance.

Cc: Takahiro Kuwano <takahiro.kuwano@infineon.com>
Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Acked-by: Takahiro Kuwano <takahiro.kuwano@infineon.com>
Acked-by: Michael Walle <mwalle@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e1694b2c3400..fc1b0d70fd1f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24911,6 +24911,7 @@ F:	drivers/pinctrl/spear/
 SPI NOR SUBSYSTEM
 M:	Pratyush Yadav <pratyush@kernel.org>
 M:	Michael Walle <mwalle@kernel.org>
+R:	Takahiro Kuwano <takahiro.kuwano@infineon.com>
 L:	linux-mtd@lists.infradead.org
 S:	Maintained
 W:	http://www.linux-mtd.infradead.org/
-- 
cgit v1.2.3


From 8e2f8020270af7777d49c2e7132260983e4fc566 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@linux-m68k.org>
Date: Mon, 16 Feb 2026 18:01:30 +1100
Subject: mtd: Avoid boot crash in RedBoot partition table parser

Given CONFIG_FORTIFY_SOURCE=y and a recent compiler,
commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when
available") produces the warning below and an oops.

    Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000
    ------------[ cut here ]------------
    WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1
    memcmp: detected buffer overflow: 15 byte read of buffer size 14
    Modules linked in:
    CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE

As Kees said, "'names' is pointing to the final 'namelen' many bytes
of the allocation ... 'namelen' could be basically any length at all.
This fortify warning looks legit to me -- this code used to be reading
beyond the end of the allocation."

Since the size of the dynamic allocation is calculated with strlen()
we can use strcmp() instead of memcmp() and remain within bounds.

Cc: Kees Cook <kees@kernel.org>
Cc: stable@vger.kernel.org
Cc: linux-hardening@vger.kernel.org
Link: https://lore.kernel.org/all/202602151911.AD092DFFCD@keescook/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Suggested-by: Kees Cook <kees@kernel.org>
Signed-off-by: Finn Thain <fthain@linux-m68k.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/parsers/redboot.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/parsers/redboot.c b/drivers/mtd/parsers/redboot.c
index 558905160ddb..bf162c44eafe 100644
--- a/drivers/mtd/parsers/redboot.c
+++ b/drivers/mtd/parsers/redboot.c
@@ -270,9 +270,9 @@ nogood:
 
 		strcpy(names, fl->img->name);
 #ifdef CONFIG_MTD_REDBOOT_PARTS_READONLY
-		if (!memcmp(names, "RedBoot", 8) ||
-		    !memcmp(names, "RedBoot config", 15) ||
-		    !memcmp(names, "FIS directory", 14)) {
+		if (!strcmp(names, "RedBoot") ||
+		    !strcmp(names, "RedBoot config") ||
+		    !strcmp(names, "FIS directory")) {
 			parts[i].mask_flags = MTD_WRITEABLE;
 		}
 #endif
-- 
cgit v1.2.3


From 0410e1a4c545c769c59c6eda897ad5d574d0c865 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Mon, 9 Feb 2026 15:56:18 +0800
Subject: mtd: rawnand: cadence: Fix error check for dma_alloc_coherent() in
 cadence_nand_init()

Fix wrong variable used for error checking after dma_alloc_coherent()
call. The function checks cdns_ctrl->dma_cdma_desc instead of
cdns_ctrl->cdma_desc, which could lead to incorrect error handling.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 99135ec23010..d53b35a8b3cb 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -3133,7 +3133,7 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 						  sizeof(*cdns_ctrl->cdma_desc),
 						  &cdns_ctrl->dma_cdma_desc,
 						  GFP_KERNEL);
-	if (!cdns_ctrl->dma_cdma_desc)
+	if (!cdns_ctrl->cdma_desc)
 		return -ENOMEM;
 
 	cdns_ctrl->buf_size = SZ_16K;
-- 
cgit v1.2.3


From 3ea20672d23b21327266534e08ca10d8f281f4ab Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 24 Feb 2026 13:41:20 +0100
Subject: MAINTAINERS: Update contact with the kernel.org address

Use the kernel.org address as a unified single entry to send patches
to. At the same time, update mailmap to group all past contributions.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 .mailmap    |  4 ++++
 MAINTAINERS | 12 ++++++------
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..463de4784ecb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -210,6 +210,10 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
 Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linaro.org>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@free.fr>
+Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linexp.org>
+Daniel Lezcano <daniel.lezcano@kernel.org> <dlezcano@fr.ibm.com>
 Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..6c8752099924 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6280,7 +6280,7 @@ S:	Maintained
 F:	include/linux/clk.h
 
 CLOCKSOURCE, CLOCKEVENT DRIVERS
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Thomas Gleixner <tglx@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
@@ -6669,7 +6669,7 @@ F:	rust/kernel/cpu.rs
 
 CPU IDLE TIME MANAGEMENT FRAMEWORK
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 R:	Christian Loehle <christian.loehle@arm.com>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -6699,7 +6699,7 @@ F:	arch/x86/kernel/msr.c
 
 CPUIDLE DRIVER - ARM BIG LITTLE
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 L:	linux-pm@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -6707,7 +6707,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 F:	drivers/cpuidle/cpuidle-big_little.c
 
 CPUIDLE DRIVER - ARM EXYNOS
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Kukjin Kim <kgene@kernel.org>
 R:	Krzysztof Kozlowski <krzk@kernel.org>
 L:	linux-pm@vger.kernel.org
@@ -26217,7 +26217,7 @@ F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
 M:	Rafael J. Wysocki <rafael@kernel.org>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 R:	Zhang Rui <rui.zhang@intel.com>
 R:	Lukasz Luba <lukasz.luba@arm.com>
 L:	linux-pm@vger.kernel.org
@@ -26247,7 +26247,7 @@ F:	drivers/thermal/amlogic_thermal.c
 
 THERMAL/CPU_COOLING
 M:	Amit Daniel Kachhap <amit.kachhap@gmail.com>
-M:	Daniel Lezcano <daniel.lezcano@linaro.org>
+M:	Daniel Lezcano <daniel.lezcano@kernel.org>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 R:	Lukasz Luba <lukasz.luba@arm.com>
 L:	linux-pm@vger.kernel.org
-- 
cgit v1.2.3


From 085f067389d12bd9800c0a9672a174c1de7a8069 Mon Sep 17 00:00:00 2001
From: Chen Ridong <chenridong@huawei.com>
Date: Wed, 25 Feb 2026 01:15:23 +0000
Subject: cgroup/cpuset: fix null-ptr-deref in rebuild_sched_domains_cpuslocked

A null-pointer-dereference bug was reported by syzbot:

Oops: general protection fault, probably for address 0xdffffc0000000000:
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:bitmap_subset include/linux/bitmap.h:433 [inline]
RIP: 0010:cpumask_subset include/linux/cpumask.h:836 [inline]
RIP: 0010:rebuild_sched_domains_locked kernel/cgroup/cpuset.c:967
RSP: 0018:ffffc90003ecfbc0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000020
RDX: ffff888028de0000 RSI: ffffffff8200f003 RDI: ffffffff8df14f28
RBP: 0000000000000000 R08: 0000000000000cc0 R09: 00000000ffffffff
R10: ffffffff8e7d95b3 R11: 0000000000000001 R12: 0000000000000000
R13: 00000000000f4240 R14: dffffc0000000000 R15: 0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2f463fff CR3: 000000003704c000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 rebuild_sched_domains_cpuslocked kernel/cgroup/cpuset.c:983 [inline]
 rebuild_sched_domains+0x21/0x40 kernel/cgroup/cpuset.c:990
 sched_rt_handler+0xb5/0xe0 kernel/sched/rt.c:2911
 proc_sys_call_handler+0x47f/0x5a0 fs/proc/proc_sysctl.c:600
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6ac/0x1070 fs/read_write.c:688
 ksys_write+0x12a/0x250 fs/read_write.c:740
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The issue occurs when generate_sched_domains() returns ndoms = 1 and
doms = NULL due to a kmalloc failure. This leads to a null-pointer
dereference when accessing doms in rebuild_sched_domains_locked().

Fix this by adding a NULL check for doms before accessing it.

Fixes: 6ee43047e8ad ("cpuset: Remove unnecessary checks in rebuild_sched_domains_locked")
Reported-by: syzbot+460792609a79c085f79f@syzkaller.appspotmail.com
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index aa45351c6f38..271bb99b1b9d 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1002,7 +1002,7 @@ void rebuild_sched_domains_locked(void)
 	* offline CPUs, a warning is emitted and we return directly to
 	* prevent the panic.
 	*/
-	for (i = 0; i < ndoms; ++i) {
+	for (i = 0; doms && i < ndoms; i++) {
 		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask)))
 			return;
 	}
-- 
cgit v1.2.3


From 2d6d260e9a3576256fe9ef6d1f7930c9ec348723 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Mon, 9 Feb 2026 15:20:48 +0100
Subject: usb: mdc800: handle signal and read racing

If a signal arrives after a read has partially completed,
we need to return the number of bytes read. -EINTR is correct
only if that number is zero.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260209142048.1503791-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/image/mdc800.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index 8d8e79afa600..e76a502fa9da 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -707,7 +707,7 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l
 		if (signal_pending (current)) 
 		{
 			mutex_unlock(&mdc800->io_lock);
-			return -EINTR;
+			return len == left ? -EINTR : len-left;
 		}
 
 		sts=left > (mdc800->out_count-mdc800->out_ptr)?mdc800->out_count-mdc800->out_ptr:left;
-- 
cgit v1.2.3


From 1be3b77de4eb89af8ae2fd6610546be778e25589 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Mon, 9 Feb 2026 15:19:37 +0000
Subject: usb: image: mdc800: kill download URB on timeout

mdc800_device_read() submits download_urb and waits for completion.
If the timeout fires and the device has not responded, the function
returns without killing the URB, leaving it active.

A subsequent read() resubmits the same URB while it is still
in-flight, triggering the WARN in usb_submit_urb():

  "URB submitted while active"

Check the return value of wait_event_timeout() and kill the URB if
it indicates timeout, ensuring the URB is complete before its status
is inspected or the URB is resubmitted.

Similar to
- commit 372c93131998 ("USB: yurex: fix control-URB timeout handling")
- commit b98d5000c505 ("media: rc: iguanair: handle timeouts")

Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260209151937.2247202-1-n7l8m4@u.northwestern.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/image/mdc800.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/image/mdc800.c b/drivers/usb/image/mdc800.c
index e76a502fa9da..ca287b770e8c 100644
--- a/drivers/usb/image/mdc800.c
+++ b/drivers/usb/image/mdc800.c
@@ -730,9 +730,11 @@ static ssize_t mdc800_device_read (struct file *file, char __user *buf, size_t l
 					mutex_unlock(&mdc800->io_lock);
 					return len-left;
 				}
-				wait_event_timeout(mdc800->download_wait,
+				retval = wait_event_timeout(mdc800->download_wait,
 				     mdc800->downloaded,
 				     msecs_to_jiffies(TO_DOWNLOAD_GET_READY));
+				if (!retval)
+					usb_kill_urb(mdc800->download_urb);
 				mdc800->downloaded = 0;
 				if (mdc800->download_urb->status != 0)
 				{
-- 
cgit v1.2.3


From 5a674ef871fe9d4c7477127340941f2c4d9a2741 Mon Sep 17 00:00:00 2001
From: "Anirudh Rayabharam (Microsoft)" <anirudh@anirudhrb.com>
Date: Wed, 25 Feb 2026 12:44:02 +0000
Subject: mshv: refactor synic init and cleanup

Rename mshv_synic_init() to mshv_synic_cpu_init() and
mshv_synic_cleanup() to mshv_synic_cpu_exit() to better reflect that
these functions handle per-cpu synic setup and teardown.

Use mshv_synic_init/cleanup() to perform init/cleanup that is not per-cpu.
Move all the synic related setup from mshv_parent_partition_init.

Move the reboot notifier to mshv_synic.c because it currently only
operates on the synic cpuhp state.

Move out synic_pages from the global mshv_root since its use is now
completely local to mshv_synic.c.

This is in preparation for adding more stuff to mshv_synic_init().

No functional change.

Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_root.h      |  5 ++--
 drivers/hv/mshv_root_main.c | 64 +++++-----------------------------------
 drivers/hv/mshv_synic.c     | 71 +++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 75 insertions(+), 65 deletions(-)

diff --git a/drivers/hv/mshv_root.h b/drivers/hv/mshv_root.h
index 04c2a1910a8a..826798f1a8ec 100644
--- a/drivers/hv/mshv_root.h
+++ b/drivers/hv/mshv_root.h
@@ -190,7 +190,6 @@ struct hv_synic_pages {
 };
 
 struct mshv_root {
-	struct hv_synic_pages __percpu *synic_pages;
 	spinlock_t pt_ht_lock;
 	DECLARE_HASHTABLE(pt_htable, MSHV_PARTITIONS_HASH_BITS);
 	struct hv_partition_property_vmm_capabilities vmm_caps;
@@ -249,8 +248,8 @@ int mshv_register_doorbell(u64 partition_id, doorbell_cb_t doorbell_cb,
 void mshv_unregister_doorbell(u64 partition_id, int doorbell_portid);
 
 void mshv_isr(void);
-int mshv_synic_init(unsigned int cpu);
-int mshv_synic_cleanup(unsigned int cpu);
+int mshv_synic_init(struct device *dev);
+void mshv_synic_exit(void);
 
 static inline bool mshv_partition_encrypted(struct mshv_partition *partition)
 {
diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 82ff823ef0ca..54c3e44d24ee 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -2064,7 +2064,6 @@ mshv_dev_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int mshv_cpuhp_online;
 static int mshv_root_sched_online;
 
 static const char *scheduler_type_to_string(enum hv_scheduler_type type)
@@ -2249,27 +2248,6 @@ root_scheduler_deinit(void)
 	free_percpu(root_scheduler_output);
 }
 
-static int mshv_reboot_notify(struct notifier_block *nb,
-			      unsigned long code, void *unused)
-{
-	cpuhp_remove_state(mshv_cpuhp_online);
-	return 0;
-}
-
-struct notifier_block mshv_reboot_nb = {
-	.notifier_call = mshv_reboot_notify,
-};
-
-static void mshv_root_partition_exit(void)
-{
-	unregister_reboot_notifier(&mshv_reboot_nb);
-}
-
-static int __init mshv_root_partition_init(struct device *dev)
-{
-	return register_reboot_notifier(&mshv_reboot_nb);
-}
-
 static int __init mshv_init_vmm_caps(struct device *dev)
 {
 	int ret;
@@ -2314,39 +2292,21 @@ static int __init mshv_parent_partition_init(void)
 			MSHV_HV_MAX_VERSION);
 	}
 
-	mshv_root.synic_pages = alloc_percpu(struct hv_synic_pages);
-	if (!mshv_root.synic_pages) {
-		dev_err(dev, "Failed to allocate percpu synic page\n");
-		ret = -ENOMEM;
+	ret = mshv_synic_init(dev);
+	if (ret)
 		goto device_deregister;
-	}
-
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
-				mshv_synic_init,
-				mshv_synic_cleanup);
-	if (ret < 0) {
-		dev_err(dev, "Failed to setup cpu hotplug state: %i\n", ret);
-		goto free_synic_pages;
-	}
-
-	mshv_cpuhp_online = ret;
 
 	ret = mshv_init_vmm_caps(dev);
 	if (ret)
-		goto remove_cpu_state;
+		goto synic_cleanup;
 
 	ret = mshv_retrieve_scheduler_type(dev);
 	if (ret)
-		goto remove_cpu_state;
-
-	if (hv_root_partition())
-		ret = mshv_root_partition_init(dev);
-	if (ret)
-		goto remove_cpu_state;
+		goto synic_cleanup;
 
 	ret = root_scheduler_init(dev);
 	if (ret)
-		goto exit_partition;
+		goto synic_cleanup;
 
 	ret = mshv_debugfs_init();
 	if (ret)
@@ -2367,13 +2327,8 @@ exit_debugfs:
 	mshv_debugfs_exit();
 deinit_root_scheduler:
 	root_scheduler_deinit();
-exit_partition:
-	if (hv_root_partition())
-		mshv_root_partition_exit();
-remove_cpu_state:
-	cpuhp_remove_state(mshv_cpuhp_online);
-free_synic_pages:
-	free_percpu(mshv_root.synic_pages);
+synic_cleanup:
+	mshv_synic_exit();
 device_deregister:
 	misc_deregister(&mshv_dev);
 	return ret;
@@ -2387,10 +2342,7 @@ static void __exit mshv_parent_partition_exit(void)
 	misc_deregister(&mshv_dev);
 	mshv_irqfd_wq_cleanup();
 	root_scheduler_deinit();
-	if (hv_root_partition())
-		mshv_root_partition_exit();
-	cpuhp_remove_state(mshv_cpuhp_online);
-	free_percpu(mshv_root.synic_pages);
+	mshv_synic_exit();
 }
 
 module_init(mshv_parent_partition_init);
diff --git a/drivers/hv/mshv_synic.c b/drivers/hv/mshv_synic.c
index 216065e21d28..617e8c02e365 100644
--- a/drivers/hv/mshv_synic.c
+++ b/drivers/hv/mshv_synic.c
@@ -12,11 +12,16 @@
 #include <linux/mm.h>
 #include <linux/io.h>
 #include <linux/random.h>
+#include <linux/cpuhotplug.h>
+#include <linux/reboot.h>
 #include <asm/mshyperv.h>
 
 #include "mshv_eventfd.h"
 #include "mshv.h"
 
+static int synic_cpuhp_online;
+static struct hv_synic_pages __percpu *synic_pages;
+
 static u32 synic_event_ring_get_queued_port(u32 sint_index)
 {
 	struct hv_synic_event_ring_page **event_ring_page;
@@ -26,7 +31,7 @@ static u32 synic_event_ring_get_queued_port(u32 sint_index)
 	u32 message;
 	u8 tail;
 
-	spages = this_cpu_ptr(mshv_root.synic_pages);
+	spages = this_cpu_ptr(synic_pages);
 	event_ring_page = &spages->synic_event_ring_page;
 	synic_eventring_tail = (u8 **)this_cpu_ptr(hv_synic_eventring_tail);
 
@@ -393,7 +398,7 @@ unlock_out:
 
 void mshv_isr(void)
 {
-	struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+	struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
 	struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
 	struct hv_message *msg;
 	bool handled;
@@ -446,7 +451,7 @@ void mshv_isr(void)
 	}
 }
 
-int mshv_synic_init(unsigned int cpu)
+static int mshv_synic_cpu_init(unsigned int cpu)
 {
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
@@ -455,7 +460,7 @@ int mshv_synic_init(unsigned int cpu)
 	union hv_synic_sint sint;
 #endif
 	union hv_synic_scontrol sctrl;
-	struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+	struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
 	struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
 	struct hv_synic_event_flags_page **event_flags_page =
 			&spages->synic_event_flags_page;
@@ -542,14 +547,14 @@ cleanup:
 	return -EFAULT;
 }
 
-int mshv_synic_cleanup(unsigned int cpu)
+static int mshv_synic_cpu_exit(unsigned int cpu)
 {
 	union hv_synic_sint sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sirbp sirbp;
 	union hv_synic_scontrol sctrl;
-	struct hv_synic_pages *spages = this_cpu_ptr(mshv_root.synic_pages);
+	struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
 	struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
 	struct hv_synic_event_flags_page **event_flags_page =
 		&spages->synic_event_flags_page;
@@ -663,3 +668,57 @@ mshv_unregister_doorbell(u64 partition_id, int doorbell_portid)
 
 	mshv_portid_free(doorbell_portid);
 }
+
+static int mshv_synic_reboot_notify(struct notifier_block *nb,
+			      unsigned long code, void *unused)
+{
+	if (!hv_root_partition())
+		return 0;
+
+	cpuhp_remove_state(synic_cpuhp_online);
+	return 0;
+}
+
+static struct notifier_block mshv_synic_reboot_nb = {
+	.notifier_call = mshv_synic_reboot_notify,
+};
+
+int __init mshv_synic_init(struct device *dev)
+{
+	int ret = 0;
+
+	synic_pages = alloc_percpu(struct hv_synic_pages);
+	if (!synic_pages) {
+		dev_err(dev, "Failed to allocate percpu synic page\n");
+		return -ENOMEM;
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
+				mshv_synic_cpu_init,
+				mshv_synic_cpu_exit);
+	if (ret < 0) {
+		dev_err(dev, "Failed to setup cpu hotplug state: %i\n", ret);
+		goto free_synic_pages;
+	}
+
+	synic_cpuhp_online = ret;
+
+	ret = register_reboot_notifier(&mshv_synic_reboot_nb);
+	if (ret)
+		goto remove_cpuhp_state;
+
+	return 0;
+
+remove_cpuhp_state:
+	cpuhp_remove_state(synic_cpuhp_online);
+free_synic_pages:
+	free_percpu(synic_pages);
+	return ret;
+}
+
+void mshv_synic_exit(void)
+{
+	unregister_reboot_notifier(&mshv_synic_reboot_nb);
+	cpuhp_remove_state(synic_cpuhp_online);
+	free_percpu(synic_pages);
+}
-- 
cgit v1.2.3


From 622d68772ddf07573cf88e833afe8ba6c70ac748 Mon Sep 17 00:00:00 2001
From: "Anirudh Rayabharam (Microsoft)" <anirudh@anirudhrb.com>
Date: Wed, 25 Feb 2026 12:44:03 +0000
Subject: mshv: add arm64 support for doorbell & intercept SINTs

On x86, the HYPERVISOR_CALLBACK_VECTOR is used to receive synthetic
interrupts (SINTs) from the hypervisor for doorbells and intercepts.
There is no such vector reserved for arm64.

On arm64, the hypervisor exposes a synthetic register that can be read
to find the INTID that should be used for SINTs. This INTID is in the
PPI range.

To better unify the code paths, introduce mshv_sint_vector_init() that
either reads the synthetic register and obtains the INTID (arm64) or
just uses HYPERVISOR_CALLBACK_VECTOR as the interrupt vector (x86).

Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Signed-off-by: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_synic.c     | 119 ++++++++++++++++++++++++++++++++++++++++----
 include/hyperv/hvgdk_mini.h |   2 +
 2 files changed, 111 insertions(+), 10 deletions(-)

diff --git a/drivers/hv/mshv_synic.c b/drivers/hv/mshv_synic.c
index 617e8c02e365..43f1bcbbf2d3 100644
--- a/drivers/hv/mshv_synic.c
+++ b/drivers/hv/mshv_synic.c
@@ -10,17 +10,21 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
+#include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/random.h>
 #include <linux/cpuhotplug.h>
 #include <linux/reboot.h>
 #include <asm/mshyperv.h>
+#include <linux/acpi.h>
 
 #include "mshv_eventfd.h"
 #include "mshv.h"
 
 static int synic_cpuhp_online;
 static struct hv_synic_pages __percpu *synic_pages;
+static int mshv_sint_vector = -1; /* hwirq for the SynIC SINTs */
+static int mshv_sint_irq = -1; /* Linux IRQ for mshv_sint_vector */
 
 static u32 synic_event_ring_get_queued_port(u32 sint_index)
 {
@@ -442,9 +446,7 @@ void mshv_isr(void)
 		if (msg->header.message_flags.msg_pending)
 			hv_set_non_nested_msr(HV_MSR_EOM, 0);
 
-#ifdef HYPERVISOR_CALLBACK_VECTOR
-		add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR);
-#endif
+		add_interrupt_randomness(mshv_sint_vector);
 	} else {
 		pr_warn_once("%s: unknown message type 0x%x\n", __func__,
 			     msg->header.message_type);
@@ -456,9 +458,7 @@ static int mshv_synic_cpu_init(unsigned int cpu)
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sirbp sirbp;
-#ifdef HYPERVISOR_CALLBACK_VECTOR
 	union hv_synic_sint sint;
-#endif
 	union hv_synic_scontrol sctrl;
 	struct hv_synic_pages *spages = this_cpu_ptr(synic_pages);
 	struct hv_message_page **msg_page = &spages->hyp_synic_message_page;
@@ -501,10 +501,12 @@ static int mshv_synic_cpu_init(unsigned int cpu)
 
 	hv_set_non_nested_msr(HV_MSR_SIRBP, sirbp.as_uint64);
 
-#ifdef HYPERVISOR_CALLBACK_VECTOR
+	if (mshv_sint_irq != -1)
+		enable_percpu_irq(mshv_sint_irq, 0);
+
 	/* Enable intercepts */
 	sint.as_uint64 = 0;
-	sint.vector = HYPERVISOR_CALLBACK_VECTOR;
+	sint.vector = mshv_sint_vector;
 	sint.masked = false;
 	sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_non_nested_msr(HV_MSR_SINT0 + HV_SYNIC_INTERCEPTION_SINT_INDEX,
@@ -512,13 +514,12 @@ static int mshv_synic_cpu_init(unsigned int cpu)
 
 	/* Doorbell SINT */
 	sint.as_uint64 = 0;
-	sint.vector = HYPERVISOR_CALLBACK_VECTOR;
+	sint.vector = mshv_sint_vector;
 	sint.masked = false;
 	sint.as_intercept = 1;
 	sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_non_nested_msr(HV_MSR_SINT0 + HV_SYNIC_DOORBELL_SINT_INDEX,
 			      sint.as_uint64);
-#endif
 
 	/* Enable global synic bit */
 	sctrl.as_uint64 = hv_get_non_nested_msr(HV_MSR_SCONTROL);
@@ -573,6 +574,9 @@ static int mshv_synic_cpu_exit(unsigned int cpu)
 	hv_set_non_nested_msr(HV_MSR_SINT0 + HV_SYNIC_DOORBELL_SINT_INDEX,
 			      sint.as_uint64);
 
+	if (mshv_sint_irq != -1)
+		disable_percpu_irq(mshv_sint_irq);
+
 	/* Disable Synic's event ring page */
 	sirbp.as_uint64 = hv_get_non_nested_msr(HV_MSR_SIRBP);
 	sirbp.sirbp_enabled = false;
@@ -683,14 +687,106 @@ static struct notifier_block mshv_synic_reboot_nb = {
 	.notifier_call = mshv_synic_reboot_notify,
 };
 
+#ifndef HYPERVISOR_CALLBACK_VECTOR
+static DEFINE_PER_CPU(long, mshv_evt);
+
+static irqreturn_t mshv_percpu_isr(int irq, void *dev_id)
+{
+	mshv_isr();
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_ACPI
+static int __init mshv_acpi_setup_sint_irq(void)
+{
+	return acpi_register_gsi(NULL, mshv_sint_vector, ACPI_EDGE_SENSITIVE,
+					ACPI_ACTIVE_HIGH);
+}
+
+static void mshv_acpi_cleanup_sint_irq(void)
+{
+	acpi_unregister_gsi(mshv_sint_vector);
+}
+#else
+static int __init mshv_acpi_setup_sint_irq(void)
+{
+	return -ENODEV;
+}
+
+static void mshv_acpi_cleanup_sint_irq(void)
+{
+}
+#endif
+
+static int __init mshv_sint_vector_setup(void)
+{
+	int ret;
+	struct hv_register_assoc reg = {
+		.name = HV_ARM64_REGISTER_SINT_RESERVED_INTERRUPT_ID,
+	};
+	union hv_input_vtl input_vtl = { 0 };
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	ret = hv_call_get_vp_registers(HV_VP_INDEX_SELF, HV_PARTITION_ID_SELF,
+				1, input_vtl, &reg);
+	if (ret || !reg.value.reg64)
+		return -ENODEV;
+
+	mshv_sint_vector = reg.value.reg64;
+	ret = mshv_acpi_setup_sint_irq();
+	if (ret < 0) {
+		pr_err("Failed to setup IRQ for MSHV SINT vector %d: %d\n",
+			mshv_sint_vector, ret);
+		goto out_fail;
+	}
+
+	mshv_sint_irq = ret;
+
+	ret = request_percpu_irq(mshv_sint_irq, mshv_percpu_isr, "MSHV",
+		&mshv_evt);
+	if (ret)
+		goto out_unregister;
+
+	return 0;
+
+out_unregister:
+	mshv_acpi_cleanup_sint_irq();
+out_fail:
+	return ret;
+}
+
+static void mshv_sint_vector_cleanup(void)
+{
+	free_percpu_irq(mshv_sint_irq, &mshv_evt);
+	mshv_acpi_cleanup_sint_irq();
+}
+#else /* !HYPERVISOR_CALLBACK_VECTOR */
+static int __init mshv_sint_vector_setup(void)
+{
+	mshv_sint_vector = HYPERVISOR_CALLBACK_VECTOR;
+	return 0;
+}
+
+static void mshv_sint_vector_cleanup(void)
+{
+}
+#endif /* HYPERVISOR_CALLBACK_VECTOR */
+
 int __init mshv_synic_init(struct device *dev)
 {
 	int ret = 0;
 
+	ret = mshv_sint_vector_setup();
+	if (ret)
+		return ret;
+
 	synic_pages = alloc_percpu(struct hv_synic_pages);
 	if (!synic_pages) {
 		dev_err(dev, "Failed to allocate percpu synic page\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto sint_vector_cleanup;
 	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
@@ -713,6 +809,8 @@ remove_cpuhp_state:
 	cpuhp_remove_state(synic_cpuhp_online);
 free_synic_pages:
 	free_percpu(synic_pages);
+sint_vector_cleanup:
+	mshv_sint_vector_cleanup();
 	return ret;
 }
 
@@ -721,4 +819,5 @@ void mshv_synic_exit(void)
 	unregister_reboot_notifier(&mshv_synic_reboot_nb);
 	cpuhp_remove_state(synic_cpuhp_online);
 	free_percpu(synic_pages);
+	mshv_sint_vector_cleanup();
 }
diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 056ef7b6b360..8bb3dd71c5b4 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/include/hyperv/hvgdk_mini.h
@@ -1121,6 +1121,8 @@ enum hv_register_name {
 	HV_X64_REGISTER_MSR_MTRR_FIX4KF8000	= 0x0008007A,
 
 	HV_X64_REGISTER_REG_PAGE	= 0x0009001C,
+#elif defined(CONFIG_ARM64)
+	HV_ARM64_REGISTER_SINT_RESERVED_INTERRUPT_ID	= 0x00070001,
 #endif
 };
 
-- 
cgit v1.2.3


From 712896ac4bce38a965a1c175f6e7804ed0381334 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 5 Jan 2026 06:47:28 +0000
Subject: idpf: increment completion queue next_to_clean in sw marker wait
 routine

Currently, in idpf_wait_for_sw_marker_completion(), when an
IDPF_TXD_COMPLT_SW_MARKER packet is found, the routine breaks out of
the for loop and does not increment the next_to_clean counter. This
causes the subsequent NAPI polls to run into the same
IDPF_TXD_COMPLT_SW_MARKER packet again and print out the following:

    [   23.261341] idpf 0000:05:00.0 eth1: Unknown TX completion type: 5

Instead, we should increment next_to_clean regardless when an
IDPF_TXD_COMPLT_SW_MARKER packet is found.

Tested: with the patch applied, we do not see the errors above from NAPI
polls anymore.

Fixes: 9d39447051a0 ("idpf: remove SW marker handling from NAPI")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 376050308b06..761a77510467 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2348,7 +2348,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 
 	do {
 		struct idpf_splitq_4b_tx_compl_desc *tx_desc;
-		struct idpf_tx_queue *target;
+		struct idpf_tx_queue *target = NULL;
 		u32 ctype_gen, id;
 
 		tx_desc = flow ? &complq->comp[ntc].common :
@@ -2368,14 +2368,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 		target = complq->txq_grp->txqs[id];
 
 		idpf_queue_clear(SW_MARKER, target);
-		if (target == txq)
-			break;
 
 next:
 		if (unlikely(++ntc == complq->desc_count)) {
 			ntc = 0;
 			gen_flag = !gen_flag;
 		}
+		if (target == txq)
+			break;
 	} while (time_before(jiffies, timeout));
 
 	idpf_queue_assign(GEN_CHK, complq, gen_flag);
-- 
cgit v1.2.3


From d11e5da2d6d87d123e339dc9af7bc1682fc533ce Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 12 Jan 2026 23:09:43 +0000
Subject: idpf: skip deallocating bufq_sets from rx_qgrp if it is NULL

In idpf_rxq_group_alloc(), if rx_qgrp->splitq.bufq_sets failed to get
allocated:

	rx_qgrp->splitq.bufq_sets = kcalloc(vport->num_bufqs_per_qgrp,
					    sizeof(struct idpf_bufq_set),
					    GFP_KERNEL);
	if (!rx_qgrp->splitq.bufq_sets) {
		err = -ENOMEM;
		goto err_alloc;
	}

idpf_rxq_group_rel() would attempt to deallocate it in
idpf_rxq_sw_queue_rel(), causing a kernel panic:

```
[    7.967242] early-network-sshd-n-rexd[3148]: knetbase: Info: [    8.127804] BUG: kernel NULL pointer dereference, address: 00000000000000c0
...
[    8.129779] RIP: 0010:idpf_rxq_group_rel+0x101/0x170
...
[    8.133854] Call Trace:
[    8.133980]  <TASK>
[    8.134092]  idpf_vport_queues_alloc+0x286/0x500
[    8.134313]  idpf_vport_open+0x4d/0x3f0
[    8.134498]  idpf_open+0x71/0xb0
[    8.134668]  __dev_open+0x142/0x260
[    8.134840]  netif_open+0x2f/0xe0
[    8.135004]  dev_open+0x3d/0x70
[    8.135166]  bond_enslave+0x5ed/0xf50
[    8.135345]  ? nla_put_ifalias+0x3d/0x90
[    8.135533]  ? kvfree_call_rcu+0xb5/0x3b0
[    8.135725]  ? kvfree_call_rcu+0xb5/0x3b0
[    8.135916]  do_set_master+0x114/0x160
[    8.136098]  do_setlink+0x412/0xfb0
[    8.136269]  ? security_sock_rcv_skb+0x2a/0x50
[    8.136509]  ? sk_filter_trim_cap+0x7c/0x320
[    8.136714]  ? skb_queue_tail+0x20/0x50
[    8.136899]  ? __nla_validate_parse+0x92/0xe50
[    8.137112]  ? security_capable+0x35/0x60
[    8.137304]  rtnl_newlink+0x95c/0xa00
[    8.137483]  ? __rtnl_unlock+0x37/0x70
[    8.137664]  ? netdev_run_todo+0x63/0x530
[    8.137855]  ? allocate_slab+0x280/0x870
[    8.138044]  ? security_capable+0x35/0x60
[    8.138235]  rtnetlink_rcv_msg+0x2e6/0x340
[    8.138431]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[    8.138650]  netlink_rcv_skb+0x16a/0x1a0
[    8.138840]  netlink_unicast+0x20a/0x320
[    8.139028]  netlink_sendmsg+0x304/0x3b0
[    8.139217]  __sock_sendmsg+0x89/0xb0
[    8.139399]  ____sys_sendmsg+0x167/0x1c0
[    8.139588]  ? ____sys_recvmsg+0xed/0x150
[    8.139780]  ___sys_sendmsg+0xdd/0x120
[    8.139960]  ? ___sys_recvmsg+0x124/0x1e0
[    8.140152]  ? rcutree_enqueue+0x1f/0xb0
[    8.140341]  ? rcutree_enqueue+0x1f/0xb0
[    8.140528]  ? call_rcu+0xde/0x2a0
[    8.140695]  ? evict+0x286/0x2d0
[    8.140856]  ? rcutree_enqueue+0x1f/0xb0
[    8.141043]  ? kmem_cache_free+0x2c/0x350
[    8.141236]  __x64_sys_sendmsg+0x72/0xc0
[    8.141424]  do_syscall_64+0x6f/0x890
[    8.141603]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[    8.141841] RIP: 0033:0x7f2799d21bd0
...
[    8.149905] Kernel panic - not syncing: Fatal exception
[    8.175940] Kernel Offset: 0xf800000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
[    8.176425] Rebooting in 10 seconds..
```

Tested: With this patch, the kernel panic no longer appears.

Fixes: 95af467d9a4e ("idpf: configure resources for RX queues")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 761a77510467..59aafadae3d0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1341,6 +1341,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc)
  */
 static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp)
 {
+	if (!rx_qgrp->splitq.bufq_sets)
+		return;
+
 	for (unsigned int i = 0; i < rx_qgrp->splitq.num_bufq_sets; i++) {
 		struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i];
 
-- 
cgit v1.2.3


From e403bf4013a665961bdfdf65193e3076c3d155a5 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Mon, 12 Jan 2026 23:09:44 +0000
Subject: idpf: skip deallocating txq group's txqs if it is NULL

In idpf_txq_group_alloc(), if any txq group's txqs failed to
allocate memory:

	for (j = 0; j < tx_qgrp->num_txq; j++) {
		tx_qgrp->txqs[j] = kzalloc(sizeof(*tx_qgrp->txqs[j]),
					   GFP_KERNEL);
		if (!tx_qgrp->txqs[j])
			goto err_alloc;
	}

It would cause a NULL ptr kernel panic in idpf_txq_group_rel():

	for (j = 0; j < txq_grp->num_txq; j++) {
		if (flow_sch_en) {
			kfree(txq_grp->txqs[j]->refillq);
			txq_grp->txqs[j]->refillq = NULL;
		}

		kfree(txq_grp->txqs[j]);
		txq_grp->txqs[j] = NULL;
	}

[    6.532461] BUG: kernel NULL pointer dereference, address: 0000000000000058
...
[    6.534433] RIP: 0010:idpf_txq_group_rel+0xc9/0x110
...
[    6.538513] Call Trace:
[    6.538639]  <TASK>
[    6.538760]  idpf_vport_queues_alloc+0x75/0x550
[    6.538978]  idpf_vport_open+0x4d/0x3f0
[    6.539164]  idpf_open+0x71/0xb0
[    6.539324]  __dev_open+0x142/0x260
[    6.539506]  netif_open+0x2f/0xe0
[    6.539670]  dev_open+0x3d/0x70
[    6.539827]  bond_enslave+0x5ed/0xf50
[    6.540005]  ? rcutree_enqueue+0x1f/0xb0
[    6.540193]  ? call_rcu+0xde/0x2a0
[    6.540375]  ? barn_get_empty_sheaf+0x5c/0x80
[    6.540594]  ? __kfree_rcu_sheaf+0xb6/0x1a0
[    6.540793]  ? nla_put_ifalias+0x3d/0x90
[    6.540981]  ? kvfree_call_rcu+0xb5/0x3b0
[    6.541173]  ? kvfree_call_rcu+0xb5/0x3b0
[    6.541365]  do_set_master+0x114/0x160
[    6.541547]  do_setlink+0x412/0xfb0
[    6.541717]  ? security_sock_rcv_skb+0x2a/0x50
[    6.541931]  ? sk_filter_trim_cap+0x7c/0x320
[    6.542136]  ? skb_queue_tail+0x20/0x50
[    6.542322]  ? __nla_validate_parse+0x92/0xe50
ro[o t   t o6 .d5e4f2a5u4l0t]-  ? security_capable+0x35/0x60
[    6.542792]  rtnl_newlink+0x95c/0xa00
[    6.542972]  ? __rtnl_unlock+0x37/0x70
[    6.543152]  ? netdev_run_todo+0x63/0x530
[    6.543343]  ? allocate_slab+0x280/0x870
[    6.543531]  ? security_capable+0x35/0x60
[    6.543722]  rtnetlink_rcv_msg+0x2e6/0x340
[    6.543918]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[    6.544138]  netlink_rcv_skb+0x16a/0x1a0
[    6.544328]  netlink_unicast+0x20a/0x320
[    6.544516]  netlink_sendmsg+0x304/0x3b0
[    6.544748]  __sock_sendmsg+0x89/0xb0
[    6.544928]  ____sys_sendmsg+0x167/0x1c0
[    6.545116]  ? ____sys_recvmsg+0xed/0x150
[    6.545308]  ___sys_sendmsg+0xdd/0x120
[    6.545489]  ? ___sys_recvmsg+0x124/0x1e0
[    6.545680]  ? rcutree_enqueue+0x1f/0xb0
[    6.545867]  ? rcutree_enqueue+0x1f/0xb0
[    6.546055]  ? call_rcu+0xde/0x2a0
[    6.546222]  ? evict+0x286/0x2d0
[    6.546389]  ? rcutree_enqueue+0x1f/0xb0
[    6.546577]  ? kmem_cache_free+0x2c/0x350
[    6.546784]  __x64_sys_sendmsg+0x72/0xc0
[    6.546972]  do_syscall_64+0x6f/0x890
[    6.547150]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[    6.547393] RIP: 0033:0x7fc1a3347bd0
...
[    6.551375] RIP: 0010:idpf_txq_group_rel+0xc9/0x110
...
[    6.578856] Rebooting in 10 seconds..

We should skip deallocating txqs[j] if it is NULL in the first place.

Tested: with this patch, the kernel panic no longer appears.

Fixes: 1c325aac10a8 ("idpf: configure resources for TX queues")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 59aafadae3d0..7613f020b622 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1316,6 +1316,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc)
 		struct idpf_txq_group *txq_grp = &rsrc->txq_grps[i];
 
 		for (unsigned int j = 0; j < txq_grp->num_txq; j++) {
+			if (!txq_grp->txqs[j])
+				continue;
+
 			if (idpf_queue_has(FLOW_SCH_EN, txq_grp->txqs[j])) {
 				kfree(txq_grp->txqs[j]->refillq);
 				txq_grp->txqs[j]->refillq = NULL;
-- 
cgit v1.2.3


From bc3b31977314433e4685ae92853d1b6e91ad7bc2 Mon Sep 17 00:00:00 2001
From: Li Li <boolli@google.com>
Date: Fri, 23 Jan 2026 06:58:06 +0000
Subject: idpf: nullify pointers after they are freed

rss_data->rss_key needs to be nullified after it is freed.
Checks like "if (!rss_data->rss_key)" in the code could fail
if it is not nullified.

Tested: built and booted the kernel.

Fixes: 83f38f210b85 ("idpf: Fix RSS LUT NULL pointer crash on early ethtool operations")
Signed-off-by: Li Li <boolli@google.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 94da5fbd56f1..7ce6a0e4acb6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1320,6 +1320,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter,
 
 free_rss_key:
 	kfree(rss_data->rss_key);
+	rss_data->rss_key = NULL;
 free_qreg_chunks:
 	idpf_vport_deinit_queue_reg_chunks(adapter->vport_config[idx]);
 free_vector_idxs:
-- 
cgit v1.2.3


From 1500a8662d2d41d6bb03e034de45ddfe6d7d362d Mon Sep 17 00:00:00 2001
From: Brian Vazquez <brianvv@google.com>
Date: Mon, 26 Jan 2026 21:55:59 +0000
Subject: idpf: change IRQ naming to match netdev and ethtool queue numbering

The code uses the vidx for the IRQ name but that doesn't match ethtool
reporting nor netdev naming, this makes it hard to tune the device and
associate queues with IRQs. Sequentially requesting irqs starting from
'0' makes the output consistent.

This commit changes the interrupt numbering but preserves the name
format, maintaining ABI compatibility. Existing tools relying on the old
numbering are already non-functional, as they lack a useful correlation
to the interrupts.

Before:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list
/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167
/proc/irq/68/idpf-eth1-TxRx-1/../smp_affinity_list:0
/proc/irq/70/idpf-eth1-TxRx-3/../smp_affinity_list:1
/proc/irq/71/idpf-eth1-TxRx-4/../smp_affinity_list:2
/proc/irq/72/idpf-eth1-Tx-5/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:
     tx_q-0_pkts: 1002
     tx_q-1_pkts: 2679
     tx_q-2_pkts: 1113
     tx_q-3_pkts: 1192 <----- tx_q-3 vs idpf-eth1-Tx-5
     rx_q-0_pkts: 1143
     rx_q-1_pkts: 3172
     rx_q-2_pkts: 1074

After:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list

/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167
/proc/irq/68/idpf-eth1-TxRx-0/../smp_affinity_list:0
/proc/irq/70/idpf-eth1-TxRx-1/../smp_affinity_list:1
/proc/irq/71/idpf-eth1-TxRx-2/../smp_affinity_list:2
/proc/irq/72/idpf-eth1-Tx-3/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:
     tx_q-0_pkts: 118
     tx_q-1_pkts: 134
     tx_q-2_pkts: 228
     tx_q-3_pkts: 138 <--- tx_q-3 matches idpf-eth1-Tx-3
     rx_q-0_pkts: 111
     rx_q-1_pkts: 366
     rx_q-2_pkts: 120

Fixes: d4d558718266 ("idpf: initialize interrupts and enable vport")
Signed-off-by: Brian Vazquez <brianvv@google.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 7613f020b622..b7e922fffc96 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -4077,7 +4077,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport,
 			continue;
 
 		name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name,
-				 vec_name, vidx);
+				 vec_name, vector);
 
 		err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0,
 				  name, q_vector);
-- 
cgit v1.2.3


From 2c31557336a8e4d209ed8d4513cef2c0f15e7ef4 Mon Sep 17 00:00:00 2001
From: Sreedevi Joshi <sreedevi.joshi@intel.com>
Date: Tue, 13 Jan 2026 12:01:13 -0600
Subject: idpf: Fix flow rule delete failure due to invalid validation

When deleting a flow rule using "ethtool -N <dev> delete <location>",
idpf_sideband_action_ena() incorrectly validates fsp->ring_cookie even
though ethtool doesn't populate this field for delete operations. The
uninitialized ring_cookie may randomly match RX_CLS_FLOW_DISC or
RX_CLS_FLOW_WAKE, causing validation to fail and preventing legitimate
rule deletions. Remove the unnecessary sideband action enable check and
ring_cookie validation during delete operations since action validation
is not required when removing existing rules.

Fixes: ada3e24b84a0 ("idpf: add flow steering support")
Signed-off-by: Sreedevi Joshi <sreedevi.joshi@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_ethtool.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 1d78a621d65b..3275b0215655 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -307,9 +307,6 @@ static int idpf_del_flow_steer(struct net_device *netdev,
 	vport_config = vport->adapter->vport_config[np->vport_idx];
 	user_config = &vport_config->user_config;
 
-	if (!idpf_sideband_action_ena(vport, fsp))
-		return -EOPNOTSUPP;
-
 	rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL);
 	if (!rule)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 6aa07e23dd3ccd35a0100c06fcb6b6c3b01e7965 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Thu, 29 Jan 2026 12:00:26 +0800
Subject: ice: recap the VSI and QoS info after rebuild

Fix IRDMA hardware initialization timeout (-110) after resume by
separating VSI-dependent configuration from RDMA resource allocation,
ensuring VSI is rebuilt before IRDMA accesses it.

After resume from suspend, IRDMA hardware initialization fails:
  ice: IRDMA hardware initialization FAILED init_state=4 status=-110

Separate RDMA initialization into two phases:
1. ice_init_rdma() - Allocate resources only (no VSI/QoS access, no plug)
2. ice_rdma_finalize_setup() - Assign VSI/QoS info and plug device

This allows:
- ice_init_rdma() to stay in ice_resume() (mirrors ice_deinit_rdma()
  in ice_suspend())
- VSI assignment deferred until after ice_vsi_rebuild() completes
- QoS info updated after ice_dcb_rebuild() completes
- Device plugged only when control queues, VSI, and DCB are all ready

Fixes: bc69ad74867db ("ice: avoid IRQ collision to fix init failure on ACPI S3 resume")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_idc.c  | 44 ++++++++++++++++++++++++-------
 drivers/net/ethernet/intel/ice/ice_main.c |  7 ++++-
 3 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index def7efa15447..2b2b22af42be 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -987,6 +987,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
+void ice_rdma_finalize_setup(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
 void ice_deinit_rdma(struct ice_pf *pf);
 bool ice_is_wol_supported(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 420d45c2558b..ded029aa71d7 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -360,6 +360,39 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 	auxiliary_device_uninit(adev);
 }
 
+/**
+ * ice_rdma_finalize_setup - Complete RDMA setup after VSI is ready
+ * @pf: ptr to ice_pf
+ *
+ * Sets VSI-dependent information and plugs aux device.
+ * Must be called after ice_init_rdma(), ice_vsi_rebuild(), and
+ * ice_dcb_rebuild() complete.
+ */
+void ice_rdma_finalize_setup(struct ice_pf *pf)
+{
+	struct device *dev = ice_pf_to_dev(pf);
+	struct iidc_rdma_priv_dev_info *privd;
+	int ret;
+
+	if (!ice_is_rdma_ena(pf) || !pf->cdev_info)
+		return;
+
+	privd = pf->cdev_info->iidc_priv;
+	if (!privd || !pf->vsi || !pf->vsi[0] || !pf->vsi[0]->netdev)
+		return;
+
+	/* Assign VSI info now that VSI is valid */
+	privd->netdev = pf->vsi[0]->netdev;
+	privd->vport_id = pf->vsi[0]->vsi_num;
+
+	/* Update QoS info after DCB has been rebuilt */
+	ice_setup_dcb_qos_info(pf, &privd->qos_info);
+
+	ret = ice_plug_aux_dev(pf);
+	if (ret)
+		dev_warn(dev, "Failed to plug RDMA aux device: %d\n", ret);
+}
+
 /**
  * ice_init_rdma - initializes PF for RDMA use
  * @pf: ptr to ice_pf
@@ -398,22 +431,14 @@ int ice_init_rdma(struct ice_pf *pf)
 	}
 
 	cdev->iidc_priv = privd;
-	privd->netdev = pf->vsi[0]->netdev;
 
 	privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr;
 	cdev->pdev = pf->pdev;
-	privd->vport_id = pf->vsi[0]->vsi_num;
 
 	pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2;
-	ice_setup_dcb_qos_info(pf, &privd->qos_info);
-	ret = ice_plug_aux_dev(pf);
-	if (ret)
-		goto err_plug_aux_dev;
+
 	return 0;
 
-err_plug_aux_dev:
-	pf->cdev_info->adev = NULL;
-	xa_erase(&ice_aux_id, pf->aux_idx);
 err_alloc_xa:
 	kfree(privd);
 err_privd_alloc:
@@ -432,7 +457,6 @@ void ice_deinit_rdma(struct ice_pf *pf)
 	if (!ice_is_rdma_ena(pf))
 		return;
 
-	ice_unplug_aux_dev(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
 	kfree(pf->cdev_info->iidc_priv);
 	kfree(pf->cdev_info);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 4da37caa3ec9..62914167d121 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5138,6 +5138,9 @@ int ice_load(struct ice_pf *pf)
 	if (err)
 		goto err_init_rdma;
 
+	/* Finalize RDMA: VSI already created, assign info and plug device */
+	ice_rdma_finalize_setup(pf);
+
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5169,6 +5172,7 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
@@ -5595,6 +5599,7 @@ static int ice_suspend(struct device *dev)
 	 */
 	disabled = ice_service_task_stop(pf);
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 
 	/* Already suspended?, then there is nothing to do */
@@ -7859,7 +7864,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ice_health_clear(pf);
 
-	ice_plug_aux_dev(pf);
+	ice_rdma_finalize_setup(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
 
-- 
cgit v1.2.3


From a9c354e656597aededa027d63d2ff0973f6b033f Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Mon, 2 Feb 2026 11:17:54 +0100
Subject: ice: fix crash in ethtool offline loopback test

Since the conversion of ice to page pool, the ethtool loopback test
crashes:

 BUG: kernel NULL pointer dereference, address: 000000000000000c
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 1100f1067 P4D 0
 Oops: Oops: 0002 [#1] SMP NOPTI
 CPU: 23 UID: 0 PID: 5904 Comm: ethtool Kdump: loaded Not tainted 6.19.0-0.rc7.260128g1f97d9dcf5364.49.eln154.x86_64 #1 PREEMPT(lazy)
 Hardware name: [...]
 RIP: 0010:ice_alloc_rx_bufs+0x1cd/0x310 [ice]
 Code: 83 6c 24 30 01 66 41 89 47 08 0f 84 c0 00 00 00 41 0f b7 dc 48 8b 44 24 18 48 c1 e3 04 41 bb 00 10 00 00 48 8d 2c 18 8b 04 24 <89> 45 0c 41 8b 4d 00 49 d3 e3 44 3b 5c 24 24 0f 83 ac fe ff ff 44
 RSP: 0018:ff7894738aa1f768 EFLAGS: 00010246
 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000700 RDI: 0000000000000000
 RBP: 0000000000000000 R08: ff16dcae79880200 R09: 0000000000000019
 R10: 0000000000000001 R11: 0000000000001000 R12: 0000000000000000
 R13: 0000000000000000 R14: 0000000000000000 R15: ff16dcae6c670000
 FS:  00007fcf428850c0(0000) GS:ff16dcb149710000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000000000c CR3: 0000000121227005 CR4: 0000000000773ef0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ice_vsi_cfg_rxq+0xca/0x460 [ice]
  ice_vsi_cfg_rxqs+0x54/0x70 [ice]
  ice_loopback_test+0xa9/0x520 [ice]
  ice_self_test+0x1b9/0x280 [ice]
  ethtool_self_test+0xe5/0x200
  __dev_ethtool+0x1106/0x1a90
  dev_ethtool+0xbe/0x1a0
  dev_ioctl+0x258/0x4c0
  sock_do_ioctl+0xe3/0x130
  __x64_sys_ioctl+0xb9/0x100
  do_syscall_64+0x7c/0x700
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [...]

It crashes because we have not initialized libeth for the rx ring.

Fix it by treating ICE_VSI_LB VSIs slightly more like normal PF VSIs and
letting them have a q_vector. It's just a dummy, because the loopback
test does not use interrupts, but it contains a napi struct that can be
passed to libeth_rx_fq_create() called from ice_vsi_cfg_rxq() ->
ice_rxq_pp_create().

Fixes: 93f53db9f9dc ("ice: switch to Page Pool")
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c    |  5 ++++-
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  4 ++++
 drivers/net/ethernet/intel/ice/ice_lib.c     | 15 ++++++++++-----
 3 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index afbff8aa9ceb..49b4304c4975 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -124,6 +124,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 	if (vsi->type == ICE_VSI_VF) {
 		ice_calc_vf_reg_idx(vsi->vf, q_vector);
 		goto out;
+	} else if (vsi->type == ICE_VSI_LB) {
+		goto skip_alloc;
 	} else if (vsi->type == ICE_VSI_CTRL && vsi->vf) {
 		struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi);
 
@@ -662,7 +664,8 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 	u32 rx_buf_len;
 	int err;
 
-	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) {
+	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
+	    ring->vsi->type == ICE_VSI_LB) {
 		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index c6bc29cfb8e6..ff003529beba 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1289,6 +1289,10 @@ static u64 ice_loopback_test(struct net_device *netdev)
 	test_vsi->netdev = netdev;
 	tx_ring = test_vsi->tx_rings[0];
 	rx_ring = test_vsi->rx_rings[0];
+	/* Dummy q_vector and napi. Fill the minimum required for
+	 * ice_rxq_pp_create().
+	 */
+	rx_ring->q_vector->napi.dev = netdev;
 
 	if (ice_lbtest_prepare_rings(test_vsi)) {
 		ret = 2;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d921269e1fe7..3cd6296a1fbe 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -107,10 +107,6 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->rxq_map)
 		goto err_rxq_map;
 
-	/* There is no need to allocate q_vectors for a loopback VSI. */
-	if (vsi->type == ICE_VSI_LB)
-		return 0;
-
 	/* allocate memory for q_vector pointers */
 	vsi->q_vectors = devm_kcalloc(dev, vsi->num_q_vectors,
 				      sizeof(*vsi->q_vectors), GFP_KERNEL);
@@ -241,6 +237,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 	case ICE_VSI_LB:
 		vsi->alloc_txq = 1;
 		vsi->alloc_rxq = 1;
+		/* A dummy q_vector, no actual IRQ. */
+		vsi->num_q_vectors = 1;
 		break;
 	default:
 		dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type);
@@ -2428,14 +2426,21 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 		}
 		break;
 	case ICE_VSI_LB:
-		ret = ice_vsi_alloc_rings(vsi);
+		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
 			goto unroll_vsi_init;
 
+		ret = ice_vsi_alloc_rings(vsi);
+		if (ret)
+			goto unroll_alloc_q_vector;
+
 		ret = ice_vsi_alloc_ring_stats(vsi);
 		if (ret)
 			goto unroll_vector_base;
 
+		/* Simply map the dummy q_vector to the only rx_ring */
+		vsi->rx_rings[0]->q_vector = vsi->q_vectors[0];
+
 		break;
 	default:
 		/* clean up the resources and exit */
-- 
cgit v1.2.3


From 4b3d54a85bd37ebf2d9836f0d0de775c0ff21af9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Sat, 7 Feb 2026 11:50:23 +0100
Subject: i40e: Fix preempt count leak in napi poll tracepoint

Using get_cpu() in the tracepoint assignment causes an obvious preempt
count leak because nothing invokes put_cpu() to undo it:

  softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101?

This clearly has seen a lot of testing in the last 3+ years...

Use smp_processor_id() instead.

Fixes: 6d4d584a7ea8 ("i40e: Add i40e_napi_poll tracepoint")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: Tony Nguyen <anthony.l.nguyen@intel.com>
Cc: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Cc: netdev@vger.kernel.org
Reviewed-by: Joe Damato <joe@dama.to>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h
index 759f3d1c4c8f..dde0ccd789ed 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_trace.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h
@@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll,
 		__entry->rx_clean_complete = rx_clean_complete;
 		__entry->tx_clean_complete = tx_clean_complete;
 		__entry->irq_num = q->irq_num;
-		__entry->curr_cpu = get_cpu();
+		__entry->curr_cpu = smp_processor_id();
 		__assign_str(qname);
 		__assign_str(dev_name);
 		__assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask),
-- 
cgit v1.2.3


From feae40a6a178bb525a15f19288016e5778102a99 Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Wed, 10 Dec 2025 12:26:51 +0100
Subject: ixgbevf: fix link setup issue

It may happen that VF spawned for E610 adapter has problem with setting
link up. This happens when ixgbevf supporting mailbox API 1.6 cooperates
with PF driver which doesn't support this version of API, and hence
doesn't support new approach for getting PF link data.

In that case VF asks PF to provide link data but as PF doesn't support
it, returns -EOPNOTSUPP what leads to early bail from link configuration
sequence.

Avoid such situation by using legacy VFLINKS approach whenever negotiated
API version is less than 1.6.

To reproduce the issue just create VF and set its link up - adapter must
be any from the E610 family, ixgbevf must support API 1.6 or higher while
ixgbevf must not.

Fixes: 53f0eb62b4d2 ("ixgbevf: fix getting link speed data for E610 devices")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Cc: stable@vger.kernel.org
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbevf/vf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 74d320879513..b67b580f7f1c 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -852,7 +852,8 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw,
 	if (!mac->get_link_status)
 		goto out;
 
-	if (hw->mac.type == ixgbe_mac_e610_vf) {
+	if (hw->mac.type == ixgbe_mac_e610_vf &&
+	    hw->api_version >= ixgbe_mbox_api_16) {
 		ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up);
 		if (ret_val)
 			goto out;
-- 
cgit v1.2.3


From 5b644464eeeac485685c6632bcc95347ae6c8677 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 6 Jan 2026 16:14:19 +0200
Subject: e1000e: introduce new board type for Panther Lake PCH

Add new board type for Panther Lake devices for separating device-specific
features and flows.
Additionally, remove the deprecated device IDs 0x57B5 and 0x57B6, which
are not used by any existing devices.

Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/e1000.h   |  4 +++-
 drivers/net/ethernet/intel/e1000e/hw.h      |  2 --
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 22 +++++++++++++++++++++-
 drivers/net/ethernet/intel/e1000e/netdev.c  | 15 +++++++--------
 4 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index aa08f397988e..63ebe00376f5 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -117,7 +117,8 @@ enum e1000_boards {
 	board_pch_cnp,
 	board_pch_tgp,
 	board_pch_adp,
-	board_pch_mtp
+	board_pch_mtp,
+	board_pch_ptp
 };
 
 struct e1000_ps_page {
@@ -527,6 +528,7 @@ extern const struct e1000_info e1000_pch_cnp_info;
 extern const struct e1000_info e1000_pch_tgp_info;
 extern const struct e1000_info e1000_pch_adp_info;
 extern const struct e1000_info e1000_pch_mtp_info;
+extern const struct e1000_info e1000_pch_ptp_info;
 extern const struct e1000_info e1000_es2_info;
 
 void e1000e_ptp_init(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index fc8ed38aa095..c7ac599e5a7a 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -118,8 +118,6 @@ struct e1000_hw;
 #define E1000_DEV_ID_PCH_ARL_I219_V24		0x57A1
 #define E1000_DEV_ID_PCH_PTP_I219_LM25		0x57B3
 #define E1000_DEV_ID_PCH_PTP_I219_V25		0x57B4
-#define E1000_DEV_ID_PCH_PTP_I219_LM26		0x57B5
-#define E1000_DEV_ID_PCH_PTP_I219_V26		0x57B6
 #define E1000_DEV_ID_PCH_PTP_I219_LM27		0x57B7
 #define E1000_DEV_ID_PCH_PTP_I219_V27		0x57B8
 #define E1000_DEV_ID_PCH_NVL_I219_LM29		0x57B9
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 0ff8688ac3b8..23421a640097 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -528,7 +528,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw)
 
 	phy->id = e1000_phy_unknown;
 
-	if (hw->mac.type == e1000_pch_mtp) {
+	if (hw->mac.type == e1000_pch_mtp || hw->mac.type == e1000_pch_ptp) {
 		phy->retry_count = 2;
 		e1000e_enable_phy_retry(hw);
 	}
@@ -6208,3 +6208,23 @@ const struct e1000_info e1000_pch_mtp_info = {
 	.phy_ops		= &ich8_phy_ops,
 	.nvm_ops		= &spt_nvm_ops,
 };
+
+const struct e1000_info e1000_pch_ptp_info = {
+	.mac			= e1000_pch_ptp,
+	.flags			= FLAG_IS_ICH
+				  | FLAG_HAS_WOL
+				  | FLAG_HAS_HW_TIMESTAMP
+				  | FLAG_HAS_CTRLEXT_ON_LOAD
+				  | FLAG_HAS_AMT
+				  | FLAG_HAS_FLASH
+				  | FLAG_HAS_JUMBO_FRAMES
+				  | FLAG_APME_IN_WUC,
+	.flags2			= FLAG2_HAS_PHY_STATS
+				  | FLAG2_HAS_EEE,
+	.pba			= 26,
+	.max_hw_frame_size	= 9022,
+	.get_variants		= e1000_get_variants_ich8lan,
+	.mac_ops		= &ich8_mac_ops,
+	.phy_ops		= &ich8_phy_ops,
+	.nvm_ops		= &spt_nvm_ops,
+};
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index ddbe2f7d8112..814698807f3d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -55,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = {
 	[board_pch_tgp]		= &e1000_pch_tgp_info,
 	[board_pch_adp]		= &e1000_pch_adp_info,
 	[board_pch_mtp]		= &e1000_pch_mtp_info,
+	[board_pch_ptp]		= &e1000_pch_ptp_info,
 };
 
 struct e1000_reg_info {
@@ -7925,14 +7926,12 @@ static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp },
-	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_ptp },
+	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_ptp },
 
 	{ 0, 0, 0, 0, 0, 0, 0 }	/* terminate list */
 };
-- 
cgit v1.2.3


From 0942fc6d324eb9c6b16187b2aa994c0823557f06 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 6 Jan 2026 16:14:20 +0200
Subject: e1000e: clear DPG_EN after reset to avoid autonomous power-gating

Panther Lake systems introduced an autonomous power gating feature for
the integrated Gigabit Ethernet in shutdown state (S5) state. As part of
it, the reset value of DPG_EN bit was changed to 1. Clear this bit after
performing hardware reset to avoid errors such as Tx/Rx hangs, or packet
loss/corruption.

Fixes: 0c9183ce61bc ("e1000e: Add support for the next LOM generation")
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/defines.h | 1 +
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 9 +++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index ba331899d186..d4a1041e456d 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -33,6 +33,7 @@
 
 /* Extended Device Control */
 #define E1000_CTRL_EXT_LPCD  0x00000004     /* LCD Power Cycle Done */
+#define E1000_CTRL_EXT_DPG_EN	0x00000008 /* Dynamic Power Gating Enable */
 #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */
 #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */
 #define E1000_CTRL_EXT_EE_RST    0x00002000 /* Reinitialize from EEPROM */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 23421a640097..dea208db1be5 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -4932,6 +4932,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
 	reg |= E1000_KABGTXD_BGSQLBIAS;
 	ew32(KABGTXD, reg);
 
+	/* The hardware reset value of the DPG_EN bit is 1.
+	 * Clear DPG_EN to prevent unexpected autonomous power gating.
+	 */
+	if (hw->mac.type >= e1000_pch_ptp) {
+		reg = er32(CTRL_EXT);
+		reg &= ~E1000_CTRL_EXT_DPG_EN;
+		ew32(CTRL_EXT, reg);
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From f6bf47ab32e0863df50f5501d207dcdddb7fc507 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 23 Feb 2026 22:10:10 +0000
Subject: arm64: io: Rename ioremap_prot() to __ioremap_prot()

Rename our ioremap_prot() implementation to __ioremap_prot() and convert
all arch-internal callers over to the new function.

ioremap_prot() remains as a #define to __ioremap_prot() for
generic_access_phys() and will be subsequently extended to handle user
permissions in 'prot'.

Cc: Zeng Heng <zengheng4@huawei.com>
Cc: Jinjiang Tu <tujinjiang@huawei.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/io.h | 11 ++++++-----
 arch/arm64/kernel/acpi.c    |  2 +-
 arch/arm64/mm/ioremap.c     |  6 +++---
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 83e03abbb2ca..cd2fddfe814a 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -264,19 +264,20 @@ __iowrite64_copy(void __iomem *to, const void *from, size_t count)
 typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size,
 				   pgprot_t *prot);
 int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
+void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot);
 
-#define ioremap_prot ioremap_prot
+#define ioremap_prot __ioremap_prot
 
 #define _PAGE_IOREMAP PROT_DEVICE_nGnRE
 
 #define ioremap_wc(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
+	__ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\
-	ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE))
 
 
 #define ioremap_encrypted(addr, size)	\
-	ioremap_prot((addr), (size), PAGE_KERNEL)
+	__ioremap_prot((addr), (size), PAGE_KERNEL)
 
 /*
  * io{read,write}{16,32,64}be() macros
@@ -297,7 +298,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size)
 	if (pfn_is_map_memory(__phys_to_pfn(addr)))
 		return (void __iomem *)__phys_to_virt(addr);
 
-	return ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
+	return __ioremap_prot(addr, size, __pgprot(PROT_NORMAL));
 }
 
 /*
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index af90128cfed5..a9d884fd1d00 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -377,7 +377,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 				prot = __acpi_get_writethrough_mem_attribute();
 		}
 	}
-	return ioremap_prot(phys, size, prot);
+	return __ioremap_prot(phys, size, prot);
 }
 
 /*
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index b12cbed9b5ad..6eef48ef6278 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -14,8 +14,8 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook)
 	return 0;
 }
 
-void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
-			   pgprot_t pgprot)
+void __iomem *__ioremap_prot(phys_addr_t phys_addr, size_t size,
+			     pgprot_t pgprot)
 {
 	unsigned long last_addr = phys_addr + size - 1;
 
@@ -39,7 +39,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
 
 	return generic_ioremap_prot(phys_addr, size, pgprot);
 }
-EXPORT_SYMBOL(ioremap_prot);
+EXPORT_SYMBOL(__ioremap_prot);
 
 /*
  * Must be called after early_fixmap_init
-- 
cgit v1.2.3


From 8f098037139b294050053123ab2bc0f819d08932 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 23 Feb 2026 22:10:11 +0000
Subject: arm64: io: Extract user memory type in ioremap_prot()

The only caller of ioremap_prot() outside of the generic ioremap()
implementation is generic_access_phys(), which passes a 'pgprot_t' value
determined from the user mapping of the target 'pfn' being accessed by
the kernel. On arm64, the 'pgprot_t' contains all of the non-address
bits from the pte, including the permission controls, and so we end up
returning a new user mapping from ioremap_prot() which faults when
accessed from the kernel on systems with PAN:

  | Unable to handle kernel read from unreadable memory at virtual address ffff80008ea89000
  | ...
  | Call trace:
  |   __memcpy_fromio+0x80/0xf8
  |   generic_access_phys+0x20c/0x2b8
  |   __access_remote_vm+0x46c/0x5b8
  |   access_remote_vm+0x18/0x30
  |   environ_read+0x238/0x3e8
  |   vfs_read+0xe4/0x2b0
  |   ksys_read+0xcc/0x178
  |   __arm64_sys_read+0x4c/0x68

Extract only the memory type from the user 'pgprot_t' in ioremap_prot()
and assert that we're being passed a user mapping, to protect us against
any changes in future that may require additional handling. To avoid
falsely flagging users of ioremap(), provide our own ioremap() macro
which simply wraps __ioremap_prot().

Cc: Zeng Heng <zengheng4@huawei.com>
Cc: Jinjiang Tu <tujinjiang@huawei.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 893dea9ccd08 ("arm64: Add HAVE_IOREMAP_PROT support")
Reported-by: Jinjiang Tu <tujinjiang@huawei.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/io.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index cd2fddfe814a..8cbd1e96fd50 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -266,10 +266,23 @@ typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size,
 int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook);
 void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot);
 
-#define ioremap_prot __ioremap_prot
+static inline void __iomem *ioremap_prot(phys_addr_t phys, size_t size,
+					 pgprot_t user_prot)
+{
+	pgprot_t prot;
+	ptdesc_t user_prot_val = pgprot_val(user_prot);
+
+	if (WARN_ON_ONCE(!(user_prot_val & PTE_USER)))
+		return NULL;
 
-#define _PAGE_IOREMAP PROT_DEVICE_nGnRE
+	prot = __pgprot_modify(PAGE_KERNEL, PTE_ATTRINDX_MASK,
+			       user_prot_val & PTE_ATTRINDX_MASK);
+	return __ioremap_prot(phys, size, prot);
+}
+#define ioremap_prot ioremap_prot
 
+#define ioremap(addr, size)	\
+	__ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)	\
 	__ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC))
 #define ioremap_np(addr, size)	\
-- 
cgit v1.2.3


From 8a85b3131225a8c8143ba2ae29c0eef8c1f9117f Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:30 +0000
Subject: arm64: gcs: Do not set PTE_SHARED on GCS mappings if FEAT_LPA2 is
 enabled

When FEAT_LPA2 is enabled, bits 8-9 of the PTE replace the
shareability attribute with bits 50-51 of the output address. The
_PAGE_GCS{,_RO} definitions include the PTE_SHARED bits as 0b11 (this
matches the other _PAGE_* definitions) but using this macro directly
leads to the following panic when enabling GCS on a system/model with
LPA2:

  Unable to handle kernel paging request at virtual address fffff1ffc32d8008
  Mem abort info:
    ESR = 0x0000000096000004
    EC = 0x25: DABT (current EL), IL = 32 bits
    SET = 0, FnV = 0
    EA = 0, S1PTW = 0
    FSC = 0x04: level 0 translation fault
  Data abort info:
    ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
    CM = 0, WnR = 0, TnD = 0, TagAccess = 0
    GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
  swapper pgtable: 4k pages, 52-bit VAs, pgdp=0000000060f4d000
  [fffff1ffc32d8008] pgd=100000006184b003, p4d=0000000000000000
  Internal error: Oops: 0000000096000004 [#1]  SMP
  CPU: 0 UID: 0 PID: 513 Comm: gcs_write_fault Tainted: G   M                7.0.0-rc1 #1 PREEMPT
  Tainted: [M]=MACHINE_CHECK
  Hardware name: QEMU QEMU Virtual Machine, BIOS 2025.02-8+deb13u1 11/08/2025
  pstate: 03402005 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
  pc : zap_huge_pmd+0x168/0x468
  lr : zap_huge_pmd+0x2c/0x468
  sp : ffff800080beb660
  x29: ffff800080beb660 x28: fff00000c2058180 x27: ffff800080beb898
  x26: fff00000c2058180 x25: ffff800080beb820 x24: 00c800010b600f41
  x23: ffffc1ffc30af1a8 x22: fff00000c2058180 x21: 0000ffff8dc00000
  x20: fff00000c2bc6370 x19: ffff800080beb898 x18: ffff800080bebb60
  x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000007
  x14: 000000000000000a x13: 0000aaaacbbbffff x12: 0000000000000000
  x11: 0000ffff8ddfffff x10: 00000000000001fe x9 : 0000ffff8ddfffff
  x8 : 0000ffff8de00000 x7 : 0000ffff8da00000 x6 : fff00000c2bc6370
  x5 : 0000ffff8da00000 x4 : 000000010b600000 x3 : ffffc1ffc0000000
  x2 : fff00000c2058180 x1 : fffff1ffc32d8000 x0 : 000000c00010b600
  Call trace:
   zap_huge_pmd+0x168/0x468 (P)
   unmap_page_range+0xd70/0x1560
   unmap_single_vma+0x48/0x80
   unmap_vmas+0x90/0x180
   unmap_region+0x88/0xe4
   vms_complete_munmap_vmas+0xf8/0x1e0
   do_vmi_align_munmap+0x158/0x180
   do_vmi_munmap+0xac/0x160
   __vm_munmap+0xb0/0x138
   vm_munmap+0x14/0x20
   gcs_free+0x70/0x80
   mm_release+0x1c/0xc8
   exit_mm_release+0x28/0x38
   do_exit+0x190/0x8ec
   do_group_exit+0x34/0x90
   get_signal+0x794/0x858
   arch_do_signal_or_restart+0x11c/0x3e0
   exit_to_user_mode_loop+0x10c/0x17c
   el0_da+0x8c/0x9c
   el0t_64_sync_handler+0xd0/0xf0
   el0t_64_sync+0x198/0x19c
  Code: aa1603e2 d34cfc00 cb813001 8b011861 (f9400420)

Similarly to how the kernel handles protection_map[], use a
gcs_page_prot variable to store the protection bits and clear PTE_SHARED
if LPA2 is enabled.

Also remove the unused PAGE_GCS{,_RO} macros.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 6497b66ba694 ("arm64/mm: Map pages for guarded control stack")
Reported-by: Emanuele Rocca <emanuele.rocca@arm.com>
Cc: stable@vger.kernel.org
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 3 ---
 arch/arm64/mm/mmap.c                  | 8 ++++++--
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index d27e8872fe3c..2b32639160de 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -164,9 +164,6 @@ static inline bool __pure lpa2_is_enabled(void)
 #define _PAGE_GCS	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER)
 #define _PAGE_GCS_RO	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER)
 
-#define PAGE_GCS	__pgprot(_PAGE_GCS)
-#define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
-
 #define PIE_E0	( \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 08ee177432c2..75f343009b4b 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -34,6 +34,8 @@ static pgprot_t protection_map[16] __ro_after_init = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
 };
 
+static ptdesc_t gcs_page_prot __ro_after_init = _PAGE_GCS_RO;
+
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.
@@ -73,9 +75,11 @@ static int __init adjust_protection_map(void)
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}
 
-	if (lpa2_is_enabled())
+	if (lpa2_is_enabled()) {
 		for (int i = 0; i < ARRAY_SIZE(protection_map); i++)
 			pgprot_val(protection_map[i]) &= ~PTE_SHARED;
+		gcs_page_prot &= ~PTE_SHARED;
+	}
 
 	return 0;
 }
@@ -87,7 +91,7 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = _PAGE_GCS_RO;
+		prot = gcs_page_prot;
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
-- 
cgit v1.2.3


From 47a8aad135ac1aed04b7b0c0a8157fd208075827 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:31 +0000
Subject: arm64: gcs: Honour mprotect(PROT_NONE) on shadow stack mappings

vm_get_page_prot() short-circuits the protection_map[] lookup for a
VM_SHADOW_STACK mapping since it uses a different PIE index from the
typical read/write/exec permissions. However, the side effect is that it
also ignores mprotect(PROT_NONE) by creating an accessible PTE.

Special-case the !(vm_flags & VM_ACCESS_FLAGS) flags to use the
protection_map[VM_NONE] permissions instead. No GCS attributes are
required for an inaccessible PTE.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 6497b66ba694 ("arm64/mm: Map pages for guarded control stack")
Cc: stable@vger.kernel.org
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmap.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 75f343009b4b..92b2f5097a96 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -91,7 +91,11 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = gcs_page_prot;
+		/* Honour mprotect(PROT_NONE) on shadow stack mappings */
+		if (vm_flags & VM_ACCESS_FLAGS)
+			prot = gcs_page_prot;
+		else
+			prot = pgprot_val(protection_map[VM_NONE]);
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
-- 
cgit v1.2.3


From 9d1a7c4a457eac8a7e07e1685f95e54fa551db5e Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 23 Feb 2026 17:45:32 +0000
Subject: kselftest: arm64: Check access to GCS after mprotect(PROT_NONE)

A GCS mapping should not be accessible after mprotect(PROT_NONE). Add a
kselftest for this scenario.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 .../arm64/signal/testcases/gcs_prot_none_fault.c   | 76 ++++++++++++++++++++++
 1 file changed, 76 insertions(+)
 create mode 100644 tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c

diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c
new file mode 100644
index 000000000000..2259f454a202
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2026 ARM Limited
+ */
+
+#include <errno.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static uint64_t *gcs_page;
+static bool post_mprotect;
+
+#ifndef __NR_map_shadow_stack
+#define __NR_map_shadow_stack 453
+#endif
+
+static bool alloc_gcs(struct tdescr *td)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+
+	gcs_page = (void *)syscall(__NR_map_shadow_stack, 0,
+				   page_size, 0);
+	if (gcs_page == MAP_FAILED) {
+		fprintf(stderr, "Failed to map %ld byte GCS: %d\n",
+			page_size, errno);
+		return false;
+	}
+
+	return true;
+}
+
+static int gcs_prot_none_fault_trigger(struct tdescr *td)
+{
+	/* Verify that the page is readable (ie, not completely unmapped) */
+	fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]);
+
+	if (mprotect(gcs_page, sysconf(_SC_PAGE_SIZE), PROT_NONE) != 0) {
+		fprintf(stderr, "mprotect(PROT_NONE) failed: %d\n", errno);
+		return 0;
+	}
+	post_mprotect = true;
+
+	/* This should trigger a fault if PROT_NONE is honoured for the GCS page */
+	fprintf(stderr, "Read value after mprotect(PROT_NONE) 0x%lx\n", gcs_page[0]);
+	return 0;
+}
+
+static int gcs_prot_none_fault_signal(struct tdescr *td, siginfo_t *si,
+				      ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	/* A fault before mprotect(PROT_NONE) is unexpected. */
+	if (!post_mprotect)
+		return 0;
+
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "GCS PROT_NONE fault",
+	.descr = "Read from GCS after mprotect(PROT_NONE) segfaults",
+	.feats_required = FEAT_GCS,
+	.timeout = 3,
+	.sig_ok = SIGSEGV,
+	.sanity_disabled = true,
+	.init = alloc_gcs,
+	.trigger = gcs_prot_none_fault_trigger,
+	.run = gcs_prot_none_fault_signal,
+};
-- 
cgit v1.2.3


From bfd9c931d19aa59fb8371d557774fa169b15db9a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 18 Feb 2026 16:43:47 +0000
Subject: arm64: tlb: Allow XZR argument to TLBI ops

The TLBI instruction accepts XZR as a register argument, and for TLBI
operations with a register argument, there is no functional difference
between using XZR or another GPR which contains zeroes. Operations
without a register argument are encoded as if XZR were used.

Allow the __TLBI_1() macro to use XZR when a register argument is all
zeroes.

Today this only results in a trivial code saving in
__do_compat_cache_op()'s workaround for Neoverse-N1 erratum #1542419. In
subsequent patches this pattern will be used more generally.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oupton@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a2d65d7d6aae..bf1cc9949dc8 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -38,12 +38,12 @@
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
-			       "tlbi " #op ", %0\n"			       \
+			       "tlbi " #op ", %x0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %0",     \
+			       "dsb ish\n		tlbi " #op ", %x0",    \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
-			    : : "r" (arg))
+			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 
-- 
cgit v1.2.3


From a8f78680ee6bf795086384e8aea159a52814f827 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 18 Feb 2026 16:43:48 +0000
Subject: arm64: tlb: Optimize ARM64_WORKAROUND_REPEAT_TLBI

The ARM64_WORKAROUND_REPEAT_TLBI workaround is used to mitigate several
errata where broadcast TLBI;DSB sequences don't provide all the
architecturally required synchronization. The workaround performs more
work than necessary, and can have significant overhead. This patch
optimizes the workaround, as explained below.

The workaround was originally added for Qualcomm Falkor erratum 1009 in
commit:

  d9ff80f83ecb ("arm64: Work around Falkor erratum 1009")

As noted in the message for that commit, the workaround is applied even
in cases where it is not strictly necessary.

The workaround was later reused without changes for:

* Arm Cortex-A76 erratum #1286807
  SDEN v33: https://developer.arm.com/documentation/SDEN-885749/33-0/

* Arm Cortex-A55 erratum #2441007
  SDEN v16: https://developer.arm.com/documentation/SDEN-859338/1600/

* Arm Cortex-A510 erratum #2441009
  SDEN v19: https://developer.arm.com/documentation/SDEN-1873351/1900/

The important details to note are as follows:

1. All relevant errata only affect the ordering and/or completion of
   memory accesses which have been translated by an invalidated TLB
   entry. The actual invalidation of TLB entries is unaffected.

2. The existing workaround is applied to both broadcast and local TLB
   invalidation, whereas for all relevant errata it is only necessary to
   apply a workaround for broadcast invalidation.

3. The existing workaround replaces every TLBI with a TLBI;DSB;TLBI
   sequence, whereas for all relevant errata it is only necessary to
   execute a single additional TLBI;DSB sequence after any number of
   TLBIs are completed by a DSB.

   For example, for a sequence of batched TLBIs:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH

   ... the existing workaround will expand this to:

       TLBI <op1>[, <arg1>]
       DSB ISH                  // additional
       TLBI <op1>[, <arg1>]     // additional
       TLBI <op2>[, <arg2>]
       DSB ISH                  // additional
       TLBI <op2>[, <arg2>]     // additional
       TLBI <op3>[, <arg3>]
       DSB ISH                  // additional
       TLBI <op3>[, <arg3>]     // additional
       DSB ISH

   ... whereas it is sufficient to have:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH
       TLBI <opX>[, <argX>]     // additional
       DSB ISH                  // additional

   Using a single additional TBLI and DSB at the end of the sequence can
   have significantly lower overhead as each DSB which completes a TLBI
   must synchronize with other PEs in the system, with potential
   performance effects both locally and system-wide.

4. The existing workaround repeats each specific TLBI operation, whereas
   for all relevant errata it is sufficient for the additional TLBI to
   use *any* operation which will be broadcast, regardless of which
   translation regime or stage of translation the operation applies to.

   For example, for a single TLBI:

       TLBI ALLE2IS
       DSB ISH

   ... the existing workaround will expand this to:

       TLBI ALLE2IS
       DSB ISH
       TLBI ALLE2IS             // additional
       DSB ISH                  // additional

   ... whereas it is sufficient to have:

       TLBI ALLE2IS
       DSB ISH
       TLBI VALE1IS, XZR        // additional
       DSB ISH                  // additional

   As the additional TLBI doesn't have to match a specific earlier TLBI,
   the additional TLBI can be implemented in separate code, with no
   memory of the earlier TLBIs. The additional TLBI can also use a
   cheaper TLBI operation.

5. The existing workaround is applied to both Stage-1 and Stage-2 TLB
   invalidation, whereas for all relevant errata it is only necessary to
   apply a workaround for Stage-1 invalidation.

   Architecturally, TLBI operations which invalidate only Stage-2
   information (e.g. IPAS2E1IS) are not required to invalidate TLB
   entries which combine information from Stage-1 and Stage-2
   translation table entries, and consequently may not complete memory
   accesses translated by those combined entries. In these cases,
   completion of memory accesses is only guaranteed after subsequent
   invalidation of Stage-1 information (e.g. VMALLE1IS).

Taking the above points into account, this patch reworks the workaround
logic to reduce overhead:

* New __tlbi_sync_s1ish() and __tlbi_sync_s1ish_hyp() functions are
  added and used in place of any dsb(ish) which is used to complete
  broadcast Stage-1 TLB maintenance. When the
  ARM64_WORKAROUND_REPEAT_TLBI workaround is enabled, these helpers will
  execute an additional TLBI;DSB sequence.

  For consistency, it might make sense to add __tlbi_sync_*() helpers
  for local and stage 2 maintenance. For now I've left those with
  open-coded dsb() to keep the diff small.

* The duplication of TLBIs in __TLBI_0() and __TLBI_1() is removed. This
  is no longer needed as the necessary synchronization will happen in
  __tlbi_sync_s1ish() or __tlbi_sync_s1ish_hyp().

* The additional TLBI operation is chosen to have minimal impact:

  - __tlbi_sync_s1ish() uses "TLBI VALE1IS, XZR". This is only used at
    EL1 or at EL2 with {E2H,TGE}=={1,1}, where it will target an unused
    entry for the reserved ASID in the kernel's own translation regime,
    and have no adverse affect.

  - __tlbi_sync_s1ish_hyp() uses "TLBI VALE2IS, XZR". This is only used
    in hyp code, where it will target an unused entry in the hyp code's
    TTBR0 mapping, and should have no adverse effect.

* As __TLBI_0() and __TLBI_1() no longer replace each TLBI with a
  TLBI;DSB;TLBI sequence, batching TLBIs is worthwhile, and there's no
  need for arch_tlbbatch_should_defer() to consider
  ARM64_WORKAROUND_REPEAT_TLBI.

When building defconfig with GCC 15.1.0, compared to v6.19-rc1, this
patch saves ~1KiB of text, makes the vmlinux ~42KiB smaller, and makes
the resulting Image 64KiB smaller:

| [mark@lakrids:~/src/linux]% size vmlinux-*
|    text    data     bss     dec     hex filename
| 21179831        19660919         708216 41548966        279fca6 vmlinux-after
| 21181075        19660903         708216 41550194        27a0172 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l vmlinux-*
| -rwxr-xr-x 1 mark mark 157771472 Feb  4 12:05 vmlinux-after
| -rwxr-xr-x 1 mark mark 157815432 Feb  4 12:05 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l Image-*
| -rw-r--r-- 1 mark mark 41007616 Feb  4 12:05 Image-after
| -rw-r--r-- 1 mark mark 41073152 Feb  4 12:05 Image-before

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oupton@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 59 +++++++++++++++++++++++----------------
 arch/arm64/kernel/sys_compat.c    |  2 +-
 arch/arm64/kvm/hyp/nvhe/mm.c      |  2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c     |  8 +++---
 arch/arm64/kvm/hyp/pgtable.c      |  2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c      | 10 +++----
 6 files changed, 47 insertions(+), 36 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bf1cc9949dc8..1416e652612b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -31,18 +31,10 @@
  */
 #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op "\n"				       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op,	       \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op ", %x0\n"			       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %x0",    \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
@@ -181,6 +173,34 @@ static inline unsigned long get_trans_granule(void)
 		(__pages >> (5 * (scale) + 1)) - 1;			\
 	})
 
+#define __repeat_tlbi_sync(op, arg...)						\
+do {										\
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+		break;								\
+	__tlbi(op, ##arg);							\
+	dsb(ish);								\
+} while (0)
+
+/*
+ * Complete broadcast TLB maintenance issued by the host which invalidates
+ * stage 1 information in the host's own translation regime.
+ */
+static inline void __tlbi_sync_s1ish(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+}
+
+/*
+ * Complete broadcast TLB maintenance issued by hyp code which invalidates
+ * stage 1 translation information in any translation regime.
+ */
+static inline void __tlbi_sync_s1ish_hyp(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale2is, 0);
+}
+
 /*
  *	TLB Invalidation
  *	================
@@ -279,7 +299,7 @@ static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -291,7 +311,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	asid = __TLBI_VADDR(0, ASID(mm));
 	__tlbi(aside1is, asid);
 	__tlbi_user(aside1is, asid);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
@@ -345,20 +365,11 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
 	flush_tlb_page_nosync(vma, uaddr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-	/*
-	 * TLB flush deferral is not required on systems which are affected by
-	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
-	 * will have two consecutive TLBI instructions with a dsb(ish) in between
-	 * defeating the purpose (i.e save overall 'dsb ish' cost).
-	 */
-	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
-		return false;
-
 	return true;
 }
 
@@ -374,7 +385,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
  */
 static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 /*
@@ -509,7 +520,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 {
 	__flush_tlb_range_nosync(vma->vm_mm, start, end, stride,
 				 last_level, tlb_level);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline void local_flush_tlb_contpte(struct vm_area_struct *vma,
@@ -557,7 +568,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	dsb(ishst);
 	__flush_tlb_range_op(vaale1is, start, pages, stride, 0,
 			     TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -571,7 +582,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 4a609e9b65de..b9d4998c97ef 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -37,7 +37,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 			 * We pick the reserved-ASID to minimise the impact.
 			 */
 			__tlbi(aside1is, __TLBI_VADDR(0, 0));
-			dsb(ish);
+			__tlbi_sync_s1ish();
 		}
 
 		ret = caches_clean_inval_user_pou(start, start + chunk);
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index ae8391baebc3..218976287d3f 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -271,7 +271,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
 	 */
 	dsb(ishst);
 	__tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 }
 
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 48da9ca9763f..3dc1ce0d27fe 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -226,7 +226,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -240,7 +240,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt, false);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -266,5 +266,5 @@ void __kvm_flush_vm_context(void)
 	/* Same remark as in enter_vmid_context() */
 	dsb(ish);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0e4ddd28ef5d..9b480f947da2 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -501,7 +501,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 		*unmapped += granule;
 	}
 
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 	mm_ops->put_page(ctx->ptep);
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index ec2569818629..35855dadfb1b 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -115,7 +115,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -176,7 +176,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -192,7 +192,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	exit_vmid_context(&cxt);
@@ -217,7 +217,7 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
 
 /*
@@ -358,7 +358,7 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
 	default:
 		ret = -EINVAL;
 	}
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	if (mmu)
-- 
cgit v1.2.3


From 468711a40d5dfc01bf0a24c1981246a2c93ac405 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 10 Feb 2026 19:12:25 +0100
Subject: PCI: dwc: ep: Refresh MSI Message Address cache on change

Endpoint drivers use dw_pcie_ep_raise_msi_irq() to raise MSI interrupts to
the host.  After 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU
mapping"), dw_pcie_ep_raise_msi_irq() caches the Message Address from the
MSI Capability in ep->msi_msg_addr.  But that Message Address is controlled
by the host, and it may change.  For example, if:

  - firmware on the host configures the Message Address and triggers an
    MSI,

  - a driver on the Endpoint raises the MSI via dw_pcie_ep_raise_msi_irq(),
    which caches the Message Address,

  - a kernel on the host reconfigures the Message Address and the host
    kernel driver triggers another MSI,

dw_pcie_ep_raise_msi_irq() notices that the Message Address no longer
matches the cached ep->msi_msg_addr, warns about it, and returns error
instead of raising the MSI.  The host kernel may hang because it never
receives the MSI.

This was seen with the nvmet_pci_epf_driver: the host UEFI performs NVMe
commands, e.g. Identify Controller to get the name of the controller,
nvmet-pci-epf posts the completion queue entry and raises an IRQ using
dw_pcie_ep_raise_msi_irq().  When the host boots Linux, we see a
WARN_ON_ONCE() from dw_pcie_ep_raise_msi_irq(), and the host kernel hangs
because the nvme driver never gets an IRQ.

Remove the warning when dw_pcie_ep_raise_msi_irq() notices that Message
Address has changed, remap using the new address, and update the
ep->msi_msg_addr cache.

Fixes: 8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Koichiro Den <den@valinux.co.jp>
Acked-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20260210181225.3926165-2-cassel@kernel.org
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 295076cf70de..35d8fc5e1d20 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -905,6 +905,19 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	 * supported, so we avoid reprogramming the region on every MSI,
 	 * specifically unmapping immediately after writel().
 	 */
+	if (ep->msi_iatu_mapped && (ep->msi_msg_addr != msg_addr ||
+				    ep->msi_map_size != map_size)) {
+		/*
+		 * The host changed the MSI target address or the required
+		 * mapping size changed. Reprogramming the iATU when there are
+		 * operations in flight is unsafe on this controller. However,
+		 * there is no unified way to check if we have operations in
+		 * flight, thus we don't know if we should WARN() or not.
+		 */
+		dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
+		ep->msi_iatu_mapped = false;
+	}
+
 	if (!ep->msi_iatu_mapped) {
 		ret = dw_pcie_ep_map_addr(epc, func_no, 0,
 					  ep->msi_mem_phys, msg_addr,
@@ -915,15 +928,6 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 		ep->msi_iatu_mapped = true;
 		ep->msi_msg_addr = msg_addr;
 		ep->msi_map_size = map_size;
-	} else if (WARN_ON_ONCE(ep->msi_msg_addr != msg_addr ||
-				ep->msi_map_size != map_size)) {
-		/*
-		 * The host changed the MSI target address or the required
-		 * mapping size changed. Reprogramming the iATU at runtime is
-		 * unsafe on this controller, so bail out instead of trying to
-		 * update the existing region.
-		 */
-		return -EINVAL;
 	}
 
 	writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset);
-- 
cgit v1.2.3


From c22533c66ccae10511ad6a7afc34bb26c47577e3 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Wed, 11 Feb 2026 18:55:41 +0100
Subject: PCI: dwc: ep: Flush MSI-X write before unmapping its ATU entry

Endpoint drivers use dw_pcie_ep_raise_msix_irq() to raise an MSI-X
interrupt to the host using a writel(), which generates a PCI posted write
transaction.  There's no completion for posted writes, so the writel() may
return before the PCI write completes.  dw_pcie_ep_raise_msix_irq() also
unmaps the outbound ATU entry used for the PCI write, so the write races
with the unmap.

If the PCI write loses the race with the ATU unmap, the write may corrupt
host memory or cause IOMMU errors, e.g., these when running fio with a
larger queue depth against nvmet-pci-epf:

  arm-smmu-v3 fc900000.iommu:      0x0000010000000010
  arm-smmu-v3 fc900000.iommu:      0x0000020000000000
  arm-smmu-v3 fc900000.iommu:      0x000000090000f040
  arm-smmu-v3 fc900000.iommu:      0x0000000000000000
  arm-smmu-v3 fc900000.iommu: event: F_TRANSLATION client: 0000:01:00.0 sid: 0x100 ssid: 0x0 iova: 0x90000f040 ipa: 0x0
  arm-smmu-v3 fc900000.iommu: unpriv data write s1 "Input address caused fault" stag: 0x0

Flush the write by performing a readl() of the same address to ensure that
the write has reached the destination before the ATU entry is unmapped.

The same problem was solved for dw_pcie_ep_raise_msi_irq() in commit
8719c64e76bf ("PCI: dwc: ep: Cache MSI outbound iATU mapping"), but there
it was solved by dedicating an outbound iATU only for MSI. We can't do the
same for MSI-X because each vector can have a different msg_addr and the
msg_addr may be changed while the vector is masked.

Fixes: beb4641a787d ("PCI: dwc: Add MSI-X callbacks handler")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260211175540.105677-2-cassel@kernel.org
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 35d8fc5e1d20..c57ae4d6c5c0 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -1014,6 +1014,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	writel(msg_data, ep->msi_mem + offset);
 
+	/* flush posted write before unmap */
+	readl(ep->msi_mem + offset);
+
 	dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys);
 
 	return 0;
-- 
cgit v1.2.3


From 49abfa812617a7f2d0132c70d23ac98b389c6ec1 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:30 +0000
Subject: drm/amdgpu/userq: Fix reference leak in amdgpu_userq_wait_ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop reference to syncobj and timeline fence when aborting the ioctl due
output array being too small.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: a292fdecd728 ("drm/amdgpu: Implement userqueue signal/wait IOCTL")
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 68951e9c3e6bb22396bc42ef2359751c8315dd27)
Cc: <stable@vger.kernel.org> # v6.16+
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 8013260e29dc..9b9947b94b89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -876,6 +876,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 				dma_fence_unwrap_for_each(f, &iter, fence) {
 					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
 						r = -EINVAL;
+						dma_fence_put(fence);
 						goto free_fences;
 					}
 
@@ -900,6 +901,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
 				r = -EINVAL;
+				dma_fence_put(fence);
 				goto free_fences;
 			}
 
-- 
cgit v1.2.3


From 7b7d7693a55d606d700beb9549c9f7f0e5d9c24f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:31 +0000
Subject: drm/amdgpu/userq: Do not allow userspace to trivially triger kernel
 warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userspace can either deliberately pass in the too small num_fences, or the
required number can legitimately grow between the two calls to the userq
wait ioctl. In both cases we do not want the emit the kernel warning
backtrace since nothing is wrong with the kernel and userspace will simply
get an errno reported back. So lets simply drop the WARN_ONs.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Fixes: a292fdecd728 ("drm/amdgpu: Implement userqueue signal/wait IOCTL")
Cc: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2c333ea579de6cc20ea7bc50e9595ef72863e65c)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 9b9947b94b89..d972dc46f5a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -833,7 +833,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_read[i]->resv,
 						DMA_RESV_USAGE_READ, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -850,7 +850,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_write[i]->resv,
 						DMA_RESV_USAGE_WRITE, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -874,7 +874,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 					goto free_fences;
 
 				dma_fence_unwrap_for_each(f, &iter, fence) {
-					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+					if (num_fences >= wait_info->num_fences) {
 						r = -EINVAL;
 						dma_fence_put(fence);
 						goto free_fences;
@@ -899,7 +899,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			if (r)
 				goto free_fences;
 
-			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+			if (num_fences >= wait_info->num_fences) {
 				r = -EINVAL;
 				dma_fence_put(fence);
 				goto free_fences;
-- 
cgit v1.2.3


From ea78f8c68f4f6211c557df49174c54d167821962 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Fri, 20 Feb 2026 13:47:58 +0530
Subject: drm/amdgpu: add upper bound check on user inputs in signal ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Huge input values in amdgpu_userq_signal_ioctl can lead to a OOM and
could be exploited.

So check these input value against AMDGPU_USERQ_MAX_HANDLES
which is big enough value for genuine use cases and could
potentially avoid OOM.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit be267e15f99bc97cbe202cd556717797cdcf79a5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index d972dc46f5a8..c5f5af20af75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -35,6 +35,8 @@
 static const struct dma_fence_ops amdgpu_userq_fence_ops;
 static struct kmem_cache *amdgpu_userq_fence_slab;
 
+#define AMDGPU_USERQ_MAX_HANDLES	(1U << 16)
+
 int amdgpu_userq_fence_slab_init(void)
 {
 	amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence",
@@ -478,6 +480,11 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (args->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_syncobj_handles = args->num_syncobj_handles;
 	syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles),
 				      size_mul(sizeof(u32), num_syncobj_handles));
-- 
cgit v1.2.3


From 64ac7c09fc44985ec9bb6a9db740899fa40ca613 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Tue, 24 Feb 2026 12:13:09 +0530
Subject: drm/amdgpu: add upper bound check on user inputs in wait ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Huge input values in amdgpu_userq_wait_ioctl can lead to a OOM and
could be exploited.

So check these input value against AMDGPU_USERQ_MAX_HANDLES
which is big enough value for genuine use cases and could
potentially avoid OOM.

v2: squash in Srini's fix

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fcec012c664247531aed3e662f4280ff804d1476)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index c5f5af20af75..7e9cf1868cc9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -671,6 +671,11 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (wait_info->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_read_bo_handles = wait_info->num_bo_read_handles;
 	bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles),
 				      size_mul(sizeof(u32), num_read_bo_handles));
-- 
cgit v1.2.3


From 28dfe4317541e57fe52f9a290394cd29c348228b Mon Sep 17 00:00:00 2001
From: Natalie Vock <natalie.vock@gmx.de>
Date: Mon, 23 Feb 2026 12:45:37 +0100
Subject: drm/amd/display: Use GFP_ATOMIC in dc_create_stream_for_sink

This can be called while preemption is disabled, for example by
dcn32_internal_validate_bw which is called with the FPU active.

Fixes "BUG: scheduling while atomic" messages I encounter on my Navi31
machine.

Signed-off-by: Natalie Vock <natalie.vock@gmx.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b42dae2ebc5c84a68de63ec4ffdfec49362d53f1)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 246893d80f1f..baf820e6eae8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -170,11 +170,11 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (sink == NULL)
 		goto fail;
 
-	stream = kzalloc_obj(struct dc_stream_state);
+	stream = kzalloc_obj(struct dc_stream_state, GFP_ATOMIC);
 	if (stream == NULL)
 		goto fail;
 
-	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_KERNEL);
+	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_ATOMIC);
 	if (stream->update_scratch == NULL)
 		goto fail;
 
-- 
cgit v1.2.3


From 5e0bcc7b88bcd081aaae6f481b10d9ab294fcb69 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:07 -0800
Subject: drm/amdgpu: Unlock a mutex before destroying it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Mutexes must be unlocked before these are destroyed. This has been detected
by the Clang thread-safety analyzer.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Yang Wang <kevinyang.wang@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Fixes: f5e4cc8461c4 ("drm/amdgpu: implement RAS ACA driver framework")
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 270258ba320beb99648dceffb67e86ac76786e55)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index afe5ca81beec..db7858fe0c3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -641,6 +641,7 @@ static void aca_error_fini(struct aca_error *aerr)
 		aca_bank_error_remove(aerr, bank_error);
 
 out_unlock:
+	mutex_unlock(&aerr->lock);
 	mutex_destroy(&aerr->lock);
 }
 
-- 
cgit v1.2.3


From 480ad5f6ead4a47b969aab6618573cd6822bb6a4 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 13:50:23 -0800
Subject: drm/amdgpu: Fix locking bugs in error paths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Do not unlock psp->ras_context.mutex if it has not been locked. This has
been detected by the Clang thread-safety analyzer.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: YiPeng Chai <YiPeng.Chai@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Fixes: b3fb79cda568 ("drm/amdgpu: add mutex to protect ras shared memory")
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6fa01b4335978051d2cd80841728fd63cc597970)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 6e8aad91bcd3..0d3c18f04ac3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -332,13 +332,13 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	if (!context || !context->initialized) {
 		dev_err(adev->dev, "TA is not initialized\n");
 		ret = -EINVAL;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	if (!psp->ta_funcs || !psp->ta_funcs->fn_ta_invoke) {
 		dev_err(adev->dev, "Unsupported function to invoke TA\n");
 		ret = -EOPNOTSUPP;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	context->session_id = ta_id;
@@ -346,7 +346,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
-		goto err_free_shared_buf;
+		goto unlock;
 
 	ret = psp_fn_ta_invoke(psp, cmd_id);
 	if (ret || context->resp_status) {
@@ -354,15 +354,17 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 			ret, context->resp_status);
 		if (!ret) {
 			ret = -EINVAL;
-			goto err_free_shared_buf;
+			goto unlock;
 		}
 	}
 
 	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
-err_free_shared_buf:
+unlock:
 	mutex_unlock(&psp->ras_context.mutex);
+
+free_shared_buf:
 	kfree(shared_buf);
 
 	return ret;
-- 
cgit v1.2.3


From a5fe1a54513196e4bc8f9170006057dc31e7155e Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Sat, 21 Feb 2026 10:03:32 +0530
Subject: drm/amdgpu/vcn5: Add SMU dpm interface type

This will set AMDGPU_VCN_SMU_DPM_INTERFACE_* smu_type
based on soc type and fixing ring timeout issue seen
for DPM enabled case.

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f0f23c315b38c55e8ce9484cf59b65811f350630)
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 0202df5db1e1..6109124f852e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -174,6 +174,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
 		fw_shared->sq.is_enabled = 1;
 
+		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG);
+		fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ?
+			AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU;
+
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 
-- 
cgit v1.2.3


From b57c4ec98c17789136a4db948aec6daadceb5024 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Tue, 24 Feb 2026 10:18:51 +0530
Subject: drm/amdgpu: Fix error handling in slot reset

If the device has not recovered after slot reset is called, it goes to
out label for error handling. There it could make decision based on
uninitialized hive pointer and could result in accessing an uninitialized
list.

Initialize the list and hive properly so that it handles the error
situation and also releases the reset domain lock which is acquired
during error_detected callback.

Fixes: 732c6cefc1ec ("drm/amdgpu: Replace tmp_adev with hive in amdgpu_pci_slot_reset")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bb71362182e59caa227e4192da5a612b09349696)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d9789e0b5201..3e19b51a2763 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -7059,6 +7059,15 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
+	INIT_LIST_HEAD(&device_list);
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		mutex_lock(&hive->hive_lock);
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
+			list_add_tail(&tmp_adev->reset_list, &device_list);
+	} else {
+		list_add_tail(&adev->reset_list, &device_list);
+	}
 
 	if (adev->pcie_reset_ctx.swus)
 		link_dev = adev->pcie_reset_ctx.swus;
@@ -7099,19 +7108,13 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);
-	INIT_LIST_HEAD(&device_list);
 
-	hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
-		mutex_lock(&hive->hive_lock);
 		reset_context.hive = hive;
-		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			tmp_adev->pcie_reset_ctx.in_link_reset = true;
-			list_add_tail(&tmp_adev->reset_list, &device_list);
-		}
 	} else {
 		set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
-		list_add_tail(&adev->reset_list, &device_list);
 	}
 
 	r = amdgpu_device_asic_reset(adev, &device_list, &reset_context);
-- 
cgit v1.2.3


From 6b0d812971370c64b837a2db4275410f478272fe Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 25 Feb 2026 10:51:16 -0600
Subject: drm/amd: Disable MES LR compute W/A

A workaround was introduced in commit 1fb710793ce2 ("drm/amdgpu: Enable
MES lr_compute_wa by default") to help with some hangs observed in gfx1151.

This WA didn't fully fix the issue.  It was actually fixed by adjusting
the VGPR size to the correct value that matched the hardware in commit
b42f3bf9536c ("drm/amdkfd: bump minimum vgpr size for gfx1151").

There are reports of instability on other products with newer GC microcode
versions, and I believe they're caused by this workaround. As we don't
need the workaround any more, remove it.

Fixes: b42f3bf9536c ("drm/amdkfd: bump minimum vgpr size for gfx1151")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9973e64bd6ee7642860a6f3b6958cbf14e89cabd)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 5 -----
 2 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 09ebb13ca5e8..a926a330700e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -720,11 +720,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(mes->adev->dev,
-			      "MES FW version must be >= 0x7f to enable LR compute workaround.\n");
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b1c864dc79a8..5bfa5d1d0b36 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -779,11 +779,6 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(adev->dev,
-			      "MES FW version must be >= 0x82 to enable LR compute workaround.\n");
 
 	/*
 	 * Keep oversubscribe timer for sdma . When we have unmapped doorbell
-- 
cgit v1.2.3


From 2a064262eb378263792cf1fb044de631ac41bcc5 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Wed, 25 Feb 2026 21:15:23 +0000
Subject: sched_ext: Fix out-of-bounds access in scx_idle_init_masks()

scx_idle_node_masks is allocated with num_possible_nodes() elements but
indexed by NUMA node IDs via for_each_node(). On systems with
non-contiguous NUMA node numbering (e.g. nodes 0 and 4), node IDs can
exceed the array size, causing out-of-bounds memory corruption.

Use nr_node_ids instead, which represents the maximum node ID range and
is the correct size for arrays indexed by node ID.

Fixes: 7c60329e3521 ("sched_ext: Add NUMA-awareness to the default idle selection policy")
Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_idle.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 3d9d404d5cd2..e2da6c3968a6 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -663,8 +663,8 @@ void scx_idle_init_masks(void)
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL));
 
-	/* Allocate per-node idle cpumasks */
-	scx_idle_node_masks = kcalloc(num_possible_nodes(),
+	/* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */
+	scx_idle_node_masks = kcalloc(nr_node_ids,
 				      sizeof(*scx_idle_node_masks), GFP_KERNEL);
 	BUG_ON(!scx_idle_node_masks);
 
-- 
cgit v1.2.3


From 12133a483dfa832241fbbf09321109a0ea8a520e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 12:28:30 +0100
Subject: nfc: pn533: properly drop the usb interface reference on disconnect

When the device is disconnected from the driver, there is a "dangling"
reference count on the usb interface that was grabbed in the probe
callback.  Fix this up by properly dropping the reference after we are
done with it.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: c46ee38620a2 ("NFC: pn533: add NXP pn533 nfc device driver")
Link: https://patch.msgid.link/2026022329-flashing-ought-7573@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/pn533/usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 018a80674f06..0f12f86ebb02 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -628,6 +628,7 @@ static void pn533_usb_disconnect(struct usb_interface *interface)
 	usb_free_urb(phy->out_urb);
 	usb_free_urb(phy->ack_urb);
 	kfree(phy->ack_buffer);
+	usb_put_dev(phy->udev);
 
 	nfc_info(&interface->dev, "NXP PN533 NFC device disconnected\n");
 }
-- 
cgit v1.2.3


From 11de1d3ae5565ed22ef1f89d73d8f2d00322c699 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:58:48 +0100
Subject: net: usb: pegasus: validate USB endpoints

The pegasus driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: Petko Manolov <petkan@nucleusys.com>
Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022347-legibly-attest-cc5c@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/pegasus.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index b84968c5f074..c497202b78e8 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -812,8 +812,19 @@ static void unlink_all_urbs(pegasus_t *pegasus)
 
 static int alloc_urbs(pegasus_t *pegasus)
 {
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 	int res = -ENOMEM;
 
+	if (!usb_check_bulk_endpoints(pegasus->intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(pegasus->intf, int_ep_addr))
+		return -ENODEV;
+
 	pegasus->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!pegasus->rx_urb) {
 		return res;
@@ -1168,6 +1179,7 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	pegasus = netdev_priv(net);
 	pegasus->dev_index = dev_index;
+	pegasus->intf = intf;
 
 	res = alloc_urbs(pegasus);
 	if (res < 0) {
@@ -1179,7 +1191,6 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	INIT_DELAYED_WORK(&pegasus->carrier_check, check_carrier);
 
-	pegasus->intf = intf;
 	pegasus->usb = dev;
 	pegasus->net = net;
 
-- 
cgit v1.2.3


From c58b6c29a4c9b8125e8ad3bca0637e00b71e2693 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:59:26 +0100
Subject: net: usb: kalmia: validate USB endpoints

The kalmia driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: d40261236e8e ("net/usb: Add Samsung Kalmia driver for Samsung GT-B3730")
Link: https://patch.msgid.link/2026022326-shack-headstone-ef6f@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kalmia.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c
index 613fc6910f14..ee9c48f7f68f 100644
--- a/drivers/net/usb/kalmia.c
+++ b/drivers/net/usb/kalmia.c
@@ -132,11 +132,18 @@ kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	int status;
 	u8 ethernet_addr[ETH_ALEN];
+	static const u8 ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
 
 	/* Don't bind to AT command interface */
 	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
 		return -EINVAL;
 
+	if (!usb_check_bulk_endpoints(intf, ep_addr))
+		return -ENODEV;
+
 	dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK);
 	dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK);
 	dev->status = NULL;
-- 
cgit v1.2.3


From 4b063c002ca759d1b299988ee23f564c9609c875 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 14:00:06 +0100
Subject: net: usb: kaweth: validate USB endpoints

The kaweth driver should validate that the device it is probing has the
proper number and types of USB endpoints it is expecting before it binds
to it.  If a malicious device were to not have the same urbs the driver
will crash later on when it blindly accesses these endpoints.

Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Link: https://patch.msgid.link/2026022305-substance-virtual-c728@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/kaweth.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index e01d14f6c366..cb2472b59e10 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -883,6 +883,13 @@ static int kaweth_probe(
 	const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 	int result = 0;
 	int rv = -EIO;
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 
 	dev_dbg(dev,
 		"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -896,6 +903,12 @@ static int kaweth_probe(
 		(int)udev->descriptor.bLength,
 		(int)udev->descriptor.bDescriptorType);
 
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(dev, "couldn't find required endpoints\n");
+		return -ENODEV;
+	}
+
 	netdev = alloc_etherdev(sizeof(*kaweth));
 	if (!netdev)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 5cc619583c7e735c4fb801bede671fb6f9c79425 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 18:32:18 +0100
Subject: vsock: Use container_of() to get net namespace in sysctl handlers

current->nsproxy is should not be accessed directly as syzbot has found
that it could be NULL at times, causing crashes.  Fix up the af_vsock
sysctl handlers to use container_of() to deal with the current net
namespace instead of attempting to rely on current.

This is the same type of change done in commit 7f5611cbc487 ("rds:
sysctl: rds_tcp_{rcv,snd}buf: avoid using current->nsproxy")

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Fixes: eafb64f40ca4 ("vsock: add netns to vsock core")
Link: https://patch.msgid.link/2026022318-rearview-gallery-ae13@gregkh
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9880756d9eff..f4062c6a1944 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2825,7 +2825,7 @@ static int vsock_net_mode_string(const struct ctl_table *table, int write,
 	if (write)
 		return -EPERM;
 
-	net = current->nsproxy->net_ns;
+	net = container_of(table->data, struct net, vsock.mode);
 
 	return __vsock_net_mode_string(table, write, buffer, lenp, ppos,
 				       vsock_net_mode(net), NULL);
@@ -2838,7 +2838,7 @@ static int vsock_net_child_mode_string(const struct ctl_table *table, int write,
 	struct net *net;
 	int ret;
 
-	net = current->nsproxy->net_ns;
+	net = container_of(table->data, struct net, vsock.child_ns_mode);
 
 	ret = __vsock_net_mode_string(table, write, buffer, lenp, ppos,
 				      vsock_net_child_mode(net), &new_mode);
-- 
cgit v1.2.3


From 1e3bb184e94125bae7c1703472109a646d0f79d9 Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Tue, 24 Feb 2026 09:20:12 +0100
Subject: tcp: re-enable acceptance of FIN packets when RWIN is 0

Commit 2bd99aef1b19 ("tcp: accept bare FIN packets under memory
pressure") allowed accepting FIN packets in tcp_data_queue() even when
the receive window was closed, to prevent ACK/FIN loops with broken
clients.

Such a FIN packet is in sequence, but because the FIN consumes a
sequence number, it extends beyond the window. Before commit
9ca48d616ed7 ("tcp: do not accept packets beyond window"),
tcp_sequence() only required the seq to be within the window. After
that change, the entire packet (including the FIN) must fit within the
window. As a result, such FIN packets are now dropped and the handling
path is no longer reached.

Be more lenient by not counting the sequence number consumed by the
FIN when calling tcp_sequence(), restoring the previous behavior for
cases where only the FIN extends beyond the window.

Fixes: 9ca48d616ed7 ("tcp: do not accept packets beyond window")
Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260224-fix_zero_wnd_fin-v2-1-a16677ea7cea@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e7b41abb82aa..1c6b8ca67918 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4858,15 +4858,24 @@ static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk,
  */
 
 static enum skb_drop_reason tcp_sequence(const struct sock *sk,
-					 u32 seq, u32 end_seq)
+					 u32 seq, u32 end_seq,
+					 const struct tcphdr *th)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
+	u32 seq_limit;
 
 	if (before(end_seq, tp->rcv_wup))
 		return SKB_DROP_REASON_TCP_OLD_SEQUENCE;
 
-	if (after(end_seq, tp->rcv_nxt + tcp_receive_window(tp))) {
-		if (after(seq, tp->rcv_nxt + tcp_receive_window(tp)))
+	seq_limit = tp->rcv_nxt + tcp_receive_window(tp);
+	if (unlikely(after(end_seq, seq_limit))) {
+		/* Some stacks are known to handle FIN incorrectly; allow the
+		 * FIN to extend beyond the window and check it in detail later.
+		 */
+		if (!after(end_seq - th->fin, seq_limit))
+			return SKB_NOT_DROPPED_YET;
+
+		if (after(seq, seq_limit))
 			return SKB_DROP_REASON_TCP_INVALID_SEQUENCE;
 
 		/* Only accept this packet if receive queue is empty. */
@@ -6379,7 +6388,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 
 step1:
 	/* Step 1: check sequence number */
-	reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
+	reason = tcp_sequence(sk, TCP_SKB_CB(skb)->seq,
+			      TCP_SKB_CB(skb)->end_seq, th);
 	if (reason) {
 		/* RFC793, page 37: "In all states except SYN-SENT, all reset
 		 * (RST) segments are validated by checking their SEQ-fields."
-- 
cgit v1.2.3


From 74511332309844c3de64970841b3c250d85f34ce Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Tue, 24 Feb 2026 09:20:13 +0100
Subject: selftests/net: packetdrill: Verify acceptance of FIN packets when
 RWIN is 0

Add a packetdrill test that verifies we accept bare FIN packets when
the advertised receive window is zero.

Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260224-fix_zero_wnd_fin-v2-2-a16677ea7cea@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_zero_wnd_fin.pkt       | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
new file mode 100644
index 000000000000..e245359a1a91
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_zero_wnd_fin.pkt
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Some TCP stacks send FINs even though the window is closed. We break
+// a possible FIN/ACK loop by accepting the FIN.
+
+--mss=1000
+
+`./defaults.sh`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 < P. 1:60001(60000) ack 1 win 257
+    * > .  1:1(0) ack 60001 win 0
+
+   +0 < F. 60001:60001(0) ack 1 win 257
+   +0 > . 1:1(0) ack 60002 win 0
-- 
cgit v1.2.3


From 676c7af91fcd740d34e7cb788cbc58e3bcafde39 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 24 Feb 2026 19:04:04 +0800
Subject: dpll: zl3073x: Remove redundant cleanup in devm_dpll_init()

The devm_add_action_or_reset() function already executes the cleanup
action on failure before returning an error, so the explicit goto error
and subsequent zl3073x_dev_dpll_fini() call causes double cleanup.

Fixes: ebb1031c5137 ("dpll: zl3073x: Refactor DPLL initialization")
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260224-dpll-v2-1-d7786414a830@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/zl3073x/core.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c
index 8c5ee28e02f4..37f3c33570ee 100644
--- a/drivers/dpll/zl3073x/core.c
+++ b/drivers/dpll/zl3073x/core.c
@@ -981,11 +981,7 @@ zl3073x_devm_dpll_init(struct zl3073x_dev *zldev, u8 num_dplls)
 	}
 
 	/* Add devres action to release DPLL related resources */
-	rc = devm_add_action_or_reset(zldev->dev, zl3073x_dev_dpll_fini, zldev);
-	if (rc)
-		goto error;
-
-	return 0;
+	return devm_add_action_or_reset(zldev->dev, zl3073x_dev_dpll_fini, zldev);
 
 error:
 	zl3073x_dev_dpll_fini(zldev);
-- 
cgit v1.2.3


From 916864e5eda0c52572b11b4cacce41b89622cc35 Mon Sep 17 00:00:00 2001
From: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Date: Tue, 24 Feb 2026 17:58:47 +0530
Subject: MAINTAINERS: Update maintainer entry for QUALCOMM ETHQOS ETHERNET
 DRIVER

Replace Vinod Koul with Mohd Ayaan Anwar as the maintainer of the
QUALCOMM ETHQOS ETHERNET DRIVER. Vinod confirmed he is no longer
active in this area and agreed to be removed.

Acked-by: Vinod Koul <vkoul@kernel.org>
Suggested-by: Russell King (Oracle) <linux@armlinux.org.uk>
Signed-off-by: Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20260224-qcom_ethqos_maintainer-v1-1-24e02701ea52@oss.qualcomm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index cf0313ca6039..a461baa96483 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21692,7 +21692,7 @@ S:	Maintained
 F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
-M:	Vinod Koul <vkoul@kernel.org>
+M:	Mohd Ayaan Anwar <mohd.anwar@oss.qualcomm.com>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained
-- 
cgit v1.2.3


From f975a0955276579e2176a134366ed586071c7c6a Mon Sep 17 00:00:00 2001
From: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Date: Tue, 24 Feb 2026 04:38:36 -0800
Subject: net: mana: Fix double destroy_workqueue on service rescan PCI path

While testing corner cases in the driver, a use-after-free crash
was found on the service rescan PCI path.

When mana_serv_reset() calls mana_gd_suspend(), mana_gd_cleanup()
destroys gc->service_wq. If the subsequent mana_gd_resume() fails
with -ETIMEDOUT or -EPROTO, the code falls through to
mana_serv_rescan() which triggers pci_stop_and_remove_bus_device().
This invokes the PCI .remove callback (mana_gd_remove), which calls
mana_gd_cleanup() a second time, attempting to destroy the already-
freed workqueue. Fix this by NULL-checking gc->service_wq in
mana_gd_cleanup() and setting it to NULL after destruction.

Call stack of issue for reference:
[Sat Feb 21 18:53:48 2026] Call Trace:
[Sat Feb 21 18:53:48 2026]  <TASK>
[Sat Feb 21 18:53:48 2026]  mana_gd_cleanup+0x33/0x70 [mana]
[Sat Feb 21 18:53:48 2026]  mana_gd_remove+0x3a/0xc0 [mana]
[Sat Feb 21 18:53:48 2026]  pci_device_remove+0x41/0xb0
[Sat Feb 21 18:53:48 2026]  device_remove+0x46/0x70
[Sat Feb 21 18:53:48 2026]  device_release_driver_internal+0x1e3/0x250
[Sat Feb 21 18:53:48 2026]  device_release_driver+0x12/0x20
[Sat Feb 21 18:53:48 2026]  pci_stop_bus_device+0x6a/0x90
[Sat Feb 21 18:53:48 2026]  pci_stop_and_remove_bus_device+0x13/0x30
[Sat Feb 21 18:53:48 2026]  mana_do_service+0x180/0x290 [mana]
[Sat Feb 21 18:53:48 2026]  mana_serv_func+0x24/0x50 [mana]
[Sat Feb 21 18:53:48 2026]  process_one_work+0x190/0x3d0
[Sat Feb 21 18:53:48 2026]  worker_thread+0x16e/0x2e0
[Sat Feb 21 18:53:48 2026]  kthread+0xf7/0x130
[Sat Feb 21 18:53:48 2026]  ? __pfx_worker_thread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ? __pfx_kthread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ret_from_fork+0x269/0x350
[Sat Feb 21 18:53:48 2026]  ? __pfx_kthread+0x10/0x10
[Sat Feb 21 18:53:48 2026]  ret_from_fork_asm+0x1a/0x30
[Sat Feb 21 18:53:48 2026]  </TASK>

Fixes: 505cc26bcae0 ("net: mana: Add support for auxiliary device servicing events")
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/aZ2bzL64NagfyHpg@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 5 ++++-
 drivers/net/ethernet/microsoft/mana/mana_en.c   | 4 +++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 0055c231acf6..3926d18f1840 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1946,7 +1946,10 @@ static void mana_gd_cleanup(struct pci_dev *pdev)
 
 	mana_gd_remove_irqs(pdev);
 
-	destroy_workqueue(gc->service_wq);
+	if (gc->service_wq) {
+		destroy_workqueue(gc->service_wq);
+		gc->service_wq = NULL;
+	}
 	dev_dbg(&pdev->dev, "mana gdma cleanup successful\n");
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9b5a72ada5c4..f69e42651359 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -3762,7 +3762,9 @@ void mana_rdma_remove(struct gdma_dev *gd)
 	}
 
 	WRITE_ONCE(gd->rdma_teardown, true);
-	flush_workqueue(gc->service_wq);
+
+	if (gc->service_wq)
+		flush_workqueue(gc->service_wq);
 
 	if (gd->adev)
 		remove_adev(gd);
-- 
cgit v1.2.3


From bb4c698633c0e19717586a6524a33196cff01a32 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Tue, 24 Feb 2026 14:57:08 +0200
Subject: team: avoid NETDEV_CHANGEMTU event when unregistering slave

syzbot is reporting

  unregister_netdevice: waiting for netdevsim0 to become free. Usage count = 3
  ref_tracker: netdev@ffff88807dcf8618 has 1/2 users at
       __netdev_tracker_alloc include/linux/netdevice.h:4400 [inline]
       netdev_hold include/linux/netdevice.h:4429 [inline]
       inetdev_init+0x201/0x4e0 net/ipv4/devinet.c:286
       inetdev_event+0x251/0x1610 net/ipv4/devinet.c:1600
       notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
       call_netdevice_notifiers_mtu net/core/dev.c:2318 [inline]
       netif_set_mtu_ext+0x5aa/0x800 net/core/dev.c:9886
       netif_set_mtu+0xd7/0x1b0 net/core/dev.c:9907
       dev_set_mtu+0x126/0x260 net/core/dev_api.c:248
       team_port_del+0xb07/0xcb0 drivers/net/team/team_core.c:1333
       team_del_slave drivers/net/team/team_core.c:1936 [inline]
       team_device_event+0x207/0x5b0 drivers/net/team/team_core.c:2929
       notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
       call_netdevice_notifiers_extack net/core/dev.c:2281 [inline]
       call_netdevice_notifiers net/core/dev.c:2295 [inline]
       __dev_change_net_namespace+0xcb7/0x2050 net/core/dev.c:12592
       do_setlink+0x2ce/0x4590 net/core/rtnetlink.c:3060
       rtnl_changelink net/core/rtnetlink.c:3776 [inline]
       __rtnl_newlink net/core/rtnetlink.c:3935 [inline]
       rtnl_newlink+0x15a9/0x1be0 net/core/rtnetlink.c:4072
       rtnetlink_rcv_msg+0x7d5/0xbe0 net/core/rtnetlink.c:6958
       netlink_rcv_skb+0x232/0x4b0 net/netlink/af_netlink.c:2550
       netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
       netlink_unicast+0x80f/0x9b0 net/netlink/af_netlink.c:1344
       netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1894

problem. Ido Schimmel found steps to reproduce

  ip link add name team1 type team
  ip link add name dummy1 mtu 1499 master team1 type dummy
  ip netns add ns1
  ip link set dev dummy1 netns ns1
  ip -n ns1 link del dev dummy1

and also found that the same issue was fixed in the bond driver in
commit f51048c3e07b ("bonding: avoid NETDEV_CHANGEMTU event when
unregistering slave").

Let's do similar thing for the team driver, with commit ad7c7b2172c3 ("net:
hold netdev instance lock during sysfs operations") and commit 303a8487a657
("net: s/__dev_set_mtu/__netif_set_mtu/") also applied.

Reported-by: syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Suggested-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Fixes: 3d249d4ca7d0 ("net: introduce ethernet teaming device")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260224125709.317574-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team_core.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index c08a5c1bd6e4..a0fe998cc055 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -1292,7 +1292,7 @@ err_set_mtu:
 
 static void __team_port_change_port_removed(struct team_port *port);
 
-static int team_port_del(struct team *team, struct net_device *port_dev)
+static int team_port_del(struct team *team, struct net_device *port_dev, bool unregister)
 {
 	struct net_device *dev = team->dev;
 	struct team_port *port;
@@ -1330,7 +1330,13 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 	__team_port_change_port_removed(port);
 
 	team_port_set_orig_dev_addr(port);
-	dev_set_mtu(port_dev, port->orig.mtu);
+	if (unregister) {
+		netdev_lock_ops(port_dev);
+		__netif_set_mtu(port_dev, port->orig.mtu);
+		netdev_unlock_ops(port_dev);
+	} else {
+		dev_set_mtu(port_dev, port->orig.mtu);
+	}
 	kfree_rcu(port, rcu);
 	netdev_info(dev, "Port device %s removed\n", portname);
 	netdev_compute_master_upper_features(team->dev, true);
@@ -1634,7 +1640,7 @@ static void team_uninit(struct net_device *dev)
 	ASSERT_RTNL();
 
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
-		team_port_del(team, port->dev);
+		team_port_del(team, port->dev, false);
 
 	__team_change_mode(team, NULL); /* cleanup */
 	__team_options_unregister(team, team_options, ARRAY_SIZE(team_options));
@@ -1933,7 +1939,16 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 
 	ASSERT_RTNL();
 
-	return team_port_del(team, port_dev);
+	return team_port_del(team, port_dev, false);
+}
+
+static int team_del_slave_on_unregister(struct net_device *dev, struct net_device *port_dev)
+{
+	struct team *team = netdev_priv(dev);
+
+	ASSERT_RTNL();
+
+	return team_port_del(team, port_dev, true);
 }
 
 static netdev_features_t team_fix_features(struct net_device *dev,
@@ -2926,7 +2941,7 @@ static int team_device_event(struct notifier_block *unused,
 					       !!netif_oper_up(port->dev));
 		break;
 	case NETDEV_UNREGISTER:
-		team_del_slave(port->team->dev, dev);
+		team_del_slave_on_unregister(port->team->dev, dev);
 		break;
 	case NETDEV_FEAT_CHANGE:
 		if (!port->team->notifier_ctx) {
@@ -2999,3 +3014,4 @@ MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
 MODULE_DESCRIPTION("Ethernet team device driver");
 MODULE_ALIAS_RTNL_LINK(DRV_NAME);
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
-- 
cgit v1.2.3


From 58f8ef625e23a607f4a89758d6b328a2701f7354 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 24 Feb 2026 14:57:09 +0200
Subject: selftests: team: Add a reference count leak test

Add a test for the issue that was fixed in "team: avoid NETDEV_CHANGEMTU
event when unregistering slave".

The test hangs due to a reference count leak without the fix:

 # make -C tools/testing/selftests TARGETS="drivers/net/team" TEST_PROGS=refleak.sh TEST_GEN_PROGS="" run_tests
 [...]
 TAP version 13
 1..1
 # timeout set to 45
 # selftests: drivers/net/team: refleak.sh
 [   50.681299][  T496] unregister_netdevice: waiting for dummy1 to become free. Usage count = 3
 [   71.185325][  T496] unregister_netdevice: waiting for dummy1 to become free. Usage count = 3

And passes with the fix:

 # make -C tools/testing/selftests TARGETS="drivers/net/team" TEST_PROGS=refleak.sh TEST_GEN_PROGS="" run_tests
 [...]
 TAP version 13
 1..1
 # timeout set to 45
 # selftests: drivers/net/team: refleak.sh
 ok 1 selftests: drivers/net/team: refleak.sh

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260224125709.317574-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/team/Makefile   |  1 +
 tools/testing/selftests/drivers/net/team/refleak.sh | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/team/refleak.sh

diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 1340b3df9c31..45a3e7ad3dcb 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -5,6 +5,7 @@ TEST_PROGS := \
 	dev_addr_lists.sh \
 	options.sh \
 	propagation.sh \
+	refleak.sh \
 # end of TEST_PROGS
 
 TEST_INCLUDES := \
diff --git a/tools/testing/selftests/drivers/net/team/refleak.sh b/tools/testing/selftests/drivers/net/team/refleak.sh
new file mode 100755
index 000000000000..ef08213ab964
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/refleak.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/lib.sh
+
+trap cleanup_all_ns EXIT
+
+# Test that there is no reference count leak and that dummy1 can be deleted.
+# https://lore.kernel.org/netdev/4d69abe1-ca8d-4f0b-bcf8-13899b211e57@I-love.SAKURA.ne.jp/
+setup_ns ns1 ns2
+ip -n "$ns1" link add name team1 type team
+ip -n "$ns1" link add name dummy1 mtu 1499 type dummy
+ip -n "$ns1" link set dev dummy1 master team1
+ip -n "$ns1" link set dev dummy1 netns "$ns2"
+ip -n "$ns2" link del dev dummy1
-- 
cgit v1.2.3


From 2700b7e603af39ca55fe9fc876ca123efd44680f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:48 +0200
Subject: net/mlx5: DR, Fix circular locking dependency in dump

Fix a circular locking dependency between dbg_mutex and the domain
rx/tx mutexes that could lead to a deadlock.

The dump path in dr_dump_domain_all() was acquiring locks in the order:
  dbg_mutex -> rx.mutex -> tx.mutex

While the table/matcher creation paths acquire locks in the order:
  rx.mutex -> tx.mutex -> dbg_mutex

This inverted lock ordering creates a circular dependency. Fix this by
changing dr_dump_domain_all() to acquire the domain lock before
dbg_mutex, matching the order used in mlx5dr_table_create() and
mlx5dr_matcher_create().

Lockdep splat:
 ======================================================
 WARNING: possible circular locking dependency detected
 6.19.0-rc6net_next_e817c4e #1 Not tainted
 ------------------------------------------------------
 sos/30721 is trying to acquire lock:
 ffff888102df5900 (&dmn->info.rx.mutex){+.+.}-{4:4}, at:
dr_dump_start+0x131/0x450 [mlx5_core]

 but task is already holding lock:
 ffff888102df5bc0 (&dmn->dump_info.dbg_mutex){+.+.}-{4:4}, at:
dr_dump_start+0x10b/0x450 [mlx5_core]

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #2 (&dmn->dump_info.dbg_mutex){+.+.}-{4:4}:
        __mutex_lock+0x91/0x1060
        mlx5dr_matcher_create+0x377/0x5e0 [mlx5_core]
        mlx5_cmd_dr_create_flow_group+0x62/0xd0 [mlx5_core]
        mlx5_create_flow_group+0x113/0x1c0 [mlx5_core]
        mlx5_chains_create_prio+0x453/0x2290 [mlx5_core]
        mlx5_chains_get_table+0x2e2/0x980 [mlx5_core]
        esw_chains_create+0x1e6/0x3b0 [mlx5_core]
        esw_create_offloads_fdb_tables.cold+0x62/0x63f [mlx5_core]
        esw_offloads_enable+0x76f/0xd20 [mlx5_core]
        mlx5_eswitch_enable_locked+0x35a/0x500 [mlx5_core]
        mlx5_devlink_eswitch_mode_set+0x561/0x950 [mlx5_core]
        devlink_nl_eswitch_set_doit+0x67/0xe0
        genl_family_rcv_msg_doit+0xe0/0x130
        genl_rcv_msg+0x188/0x290
        netlink_rcv_skb+0x4b/0xf0
        genl_rcv+0x24/0x40
        netlink_unicast+0x1ed/0x2c0
        netlink_sendmsg+0x210/0x450
        __sock_sendmsg+0x38/0x60
        __sys_sendto+0x119/0x180
        __x64_sys_sendto+0x20/0x30
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #1 (&dmn->info.tx.mutex){+.+.}-{4:4}:
        __mutex_lock+0x91/0x1060
        mlx5dr_table_create+0x11d/0x530 [mlx5_core]
        mlx5_cmd_dr_create_flow_table+0x62/0x140 [mlx5_core]
        __mlx5_create_flow_table+0x46f/0x960 [mlx5_core]
        mlx5_create_flow_table+0x16/0x20 [mlx5_core]
        esw_create_offloads_fdb_tables+0x136/0x240 [mlx5_core]
        esw_offloads_enable+0x76f/0xd20 [mlx5_core]
        mlx5_eswitch_enable_locked+0x35a/0x500 [mlx5_core]
        mlx5_devlink_eswitch_mode_set+0x561/0x950 [mlx5_core]
        devlink_nl_eswitch_set_doit+0x67/0xe0
        genl_family_rcv_msg_doit+0xe0/0x130
        genl_rcv_msg+0x188/0x290
        netlink_rcv_skb+0x4b/0xf0
        genl_rcv+0x24/0x40
        netlink_unicast+0x1ed/0x2c0
        netlink_sendmsg+0x210/0x450
        __sock_sendmsg+0x38/0x60
        __sys_sendto+0x119/0x180
        __x64_sys_sendto+0x20/0x30
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #0 (&dmn->info.rx.mutex){+.+.}-{4:4}:
        __lock_acquire+0x18b6/0x2eb0
        lock_acquire+0xd3/0x2c0
        __mutex_lock+0x91/0x1060
        dr_dump_start+0x131/0x450 [mlx5_core]
        seq_read_iter+0xe3/0x410
        seq_read+0xfb/0x130
        full_proxy_read+0x53/0x80
        vfs_read+0xba/0x330
        ksys_read+0x65/0xe0
        do_syscall_64+0x70/0xd00
        entry_SYSCALL_64_after_hwframe+0x4b/0x53

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&dmn->dump_info.dbg_mutex);
                                lock(&dmn->info.tx.mutex);
                                lock(&dmn->dump_info.dbg_mutex);
   lock(&dmn->info.rx.mutex);

                   *** DEADLOCK ***

Fixes: 9222f0b27da2 ("net/mlx5: DR, Add support for dumping steering info")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
index 8803fa071c50..18362e9c3314 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c
@@ -1051,8 +1051,8 @@ static int dr_dump_domain_all(struct seq_file *file, struct mlx5dr_domain *dmn)
 	struct mlx5dr_table *tbl;
 	int ret;
 
-	mutex_lock(&dmn->dump_info.dbg_mutex);
 	mlx5dr_domain_lock(dmn);
+	mutex_lock(&dmn->dump_info.dbg_mutex);
 
 	ret = dr_dump_domain(file, dmn);
 	if (ret < 0)
@@ -1065,8 +1065,8 @@ static int dr_dump_domain_all(struct seq_file *file, struct mlx5dr_domain *dmn)
 	}
 
 unlock_mutex:
-	mlx5dr_domain_unlock(dmn);
 	mutex_unlock(&dmn->dump_info.dbg_mutex);
+	mlx5dr_domain_unlock(dmn);
 	return ret;
 }
 
-- 
cgit v1.2.3


From bd7b9f83fb9f85228c3ac9748d9cba9fab7fb5a2 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:49 +0200
Subject: net/mlx5: LAG, disable MPESW in lag_disable_change()

mlx5_lag_disable_change() unconditionally called mlx5_disable_lag() when
LAG was active, which is incorrect for MLX5_LAG_MODE_MPESW.
Hnece, call mlx5_disable_mpesw() when running in MPESW mode.

Fixes: a32327a3a02c ("net/mlx5: Lag, Control MultiPort E-Switch single FDB mode")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c   | 8 ++++++--
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h | 5 +++++
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 9fe47c836ebd..859f042caf79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1869,8 +1869,12 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev)
 	mutex_lock(&ldev->lock);
 
 	ldev->mode_changes_in_progress++;
-	if (__mlx5_lag_is_active(ldev))
-		mlx5_disable_lag(ldev);
+	if (__mlx5_lag_is_active(ldev)) {
+		if (ldev->mode == MLX5_LAG_MODE_MPESW)
+			mlx5_lag_disable_mpesw(ldev);
+		else
+			mlx5_disable_lag(ldev);
+	}
 
 	mutex_unlock(&ldev->lock);
 	mlx5_devcom_comp_unlock(dev->priv.hca_devcom_comp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 04762562d7d9..a63d48d18878 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -65,7 +65,7 @@ err_metadata:
 	return err;
 }
 
-static int enable_mpesw(struct mlx5_lag *ldev)
+static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0;
 	int err;
@@ -126,7 +126,7 @@ err_add_devices:
 	return err;
 }
 
-static void disable_mpesw(struct mlx5_lag *ldev)
+void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev)
 {
 	if (ldev->mode == MLX5_LAG_MODE_MPESW) {
 		mlx5_mpesw_metadata_cleanup(ldev);
@@ -152,9 +152,9 @@ static void mlx5_mpesw_work(struct work_struct *work)
 	}
 
 	if (mpesww->op == MLX5_MPESW_OP_ENABLE)
-		mpesww->result = enable_mpesw(ldev);
+		mpesww->result = mlx5_lag_enable_mpesw(ldev);
 	else if (mpesww->op == MLX5_MPESW_OP_DISABLE)
-		disable_mpesw(ldev);
+		mlx5_lag_disable_mpesw(ldev);
 unlock:
 	mutex_unlock(&ldev->lock);
 	mlx5_devcom_comp_unlock(devcom);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
index f5d9b5c97b0d..b767dbb4f457 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h
@@ -31,6 +31,11 @@ int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev,
 bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev);
 void mlx5_lag_mpesw_disable(struct mlx5_core_dev *dev);
 int mlx5_lag_mpesw_enable(struct mlx5_core_dev *dev);
+#ifdef CONFIG_MLX5_ESWITCH
+void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev);
+#else
+static inline void mlx5_lag_disable_mpesw(struct mlx5_lag *ldev) {}
+#endif /* CONFIG_MLX5_ESWITCH */
 
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_mpesw_speed_update_work(struct work_struct *work);
-- 
cgit v1.2.3


From d7073e8b978ae925f1f0f08754f33f84d8547ea7 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:50 +0200
Subject: net/mlx5: E-switch, Clear legacy flag when moving to switchdev

The cited commit introduced MLX5_PRIV_FLAGS_SWITCH_LEGACY to identify
when a transition to legacy mode is requested via devlink.  However, the
logic failed to clear this flag if the mode was subsequently changed
back to MLX5_ESWITCH_OFFLOADS (switchdev).  Consequently, if a user
toggled from legacy to switchdev, the flag remained set, leaving the
driver with wrong state indicating

Fix this by explicitly clearing the MLX5_PRIV_FLAGS_SWITCH_LEGACY bit
when the requested mode is MLX5_ESWITCH_OFFLOADS.

Fixes: 2a4f56fbcc47 ("net/mlx5e: Keep netdev when leave switchdev for devlink set legacy only")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1b439cef3719..9d51d030596c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4068,6 +4068,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 
 	if (mlx5_mode == MLX5_ESWITCH_LEGACY)
 		esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
+	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS)
+		esw->dev->priv.flags &= ~MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_eswitch_disable_locked(esw);
 	if (mlx5_mode == MLX5_ESWITCH_OFFLOADS) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
-- 
cgit v1.2.3


From 60253042c0b87b61596368489c44d12ba720d11c Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:51 +0200
Subject: net/mlx5: Fix missing devlink lock in SRIOV enable error path

The cited commit miss to add locking in the error path of
mlx5_sriov_enable(). When pci_enable_sriov() fails,
mlx5_device_disable_sriov() is called to clean up. This cleanup function
now expects to be called with the devlink instance lock held.

Add the missing devl_lock(devlink) and devl_unlock(devlink)

Fixes: 84a433a40d0e ("net/mlx5: Lock mlx5 devlink reload callbacks")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index a2fc937d5461..172862a70c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -193,7 +193,9 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
 		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
+		devl_lock(devlink);
 		mlx5_device_disable_sriov(dev, num_vfs, true, true);
+		devl_unlock(devlink);
 	}
 	return err;
 }
-- 
cgit v1.2.3


From 859380694f434597407632c29f30fdb5e763e6cc Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Tue, 24 Feb 2026 13:46:52 +0200
Subject: net/mlx5e: Fix "scheduling while atomic" in IPsec MAC address query

Fix a "scheduling while atomic" bug in mlx5e_ipsec_init_macs() by
replacing mlx5_query_mac_address() with ether_addr_copy() to get the
local MAC address directly from netdev->dev_addr.

The issue occurs because mlx5_query_mac_address() queries the hardware
which involves mlx5_cmd_exec() that can sleep, but it is called from
the mlx5e_ipsec_handle_event workqueue which runs in atomic context.

The MAC address is already available in netdev->dev_addr, so no need
to query hardware. This avoids the sleeping call and resolves the bug.

Call trace:
  BUG: scheduling while atomic: kworker/u112:2/69344/0x00000200
  __schedule+0x7ab/0xa20
  schedule+0x1c/0xb0
  schedule_timeout+0x6e/0xf0
  __wait_for_common+0x91/0x1b0
  cmd_exec+0xa85/0xff0 [mlx5_core]
  mlx5_cmd_exec+0x1f/0x50 [mlx5_core]
  mlx5_query_nic_vport_mac_address+0x7b/0xd0 [mlx5_core]
  mlx5_query_mac_address+0x19/0x30 [mlx5_core]
  mlx5e_ipsec_init_macs+0xc1/0x720 [mlx5_core]
  mlx5e_ipsec_build_accel_xfrm_attrs+0x422/0x670 [mlx5_core]
  mlx5e_ipsec_handle_event+0x2b9/0x460 [mlx5_core]
  process_one_work+0x178/0x2e0
  worker_thread+0x2ea/0x430

Fixes: cee137a63431 ("net/mlx5e: Handle ESN update events")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224114652.1787431-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 9c7064187ed0..f03507a522b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -259,7 +259,6 @@ static void mlx5e_ipsec_init_limits(struct mlx5e_ipsec_sa_entry *sa_entry,
 static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
 	struct mlx5e_ipsec_addr *addrs = &attrs->addrs;
 	struct net_device *netdev = sa_entry->dev;
 	struct xfrm_state *x = sa_entry->x;
@@ -276,7 +275,7 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	    attrs->type != XFRM_DEV_OFFLOAD_PACKET)
 		return;
 
-	mlx5_query_mac_address(mdev, addr);
+	ether_addr_copy(addr, netdev->dev_addr);
 	switch (attrs->dir) {
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;
-- 
cgit v1.2.3


From aa4876fe2d9fcbcaa0592b25f34ec6f6ea7876c1 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 9 Feb 2026 21:41:49 +0800
Subject: ALSA: hda/realtek: add quirk for Acer Nitro ANV15-51

fix mute/micmute LEDs and headset microphone for Acer Nitro ANV15-51.

[ The headset microphone issue is solved by Kailang]

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220279
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260209134149.3076957-1-zhangheng@kylinos.cn
---
 sound/hda/codecs/realtek/alc269.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 43ecfc63ef87..86bb22d19629 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -4075,6 +4075,7 @@ enum {
 	ALC236_FIXUP_HP_MUTE_LED_MICMUTE_GPIO,
 	ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY,
 	ALC245_FIXUP_BASS_HP_DAC,
+	ALC245_FIXUP_ACER_MICMUTE_LED,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -6599,6 +6600,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		/* Borrow the DAC routing selected for those Thinkpads */
 		.v.func = alc285_fixup_thinkpad_x1_gen7,
 	},
+	[ALC245_FIXUP_ACER_MICMUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_hp_coef_micmute_led,
+		.chained = true,
+		.chain_id = ALC2XX_FIXUP_HEADSET_MIC,
+	}
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -6651,6 +6658,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED),
+	SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
-- 
cgit v1.2.3


From 54f9d645a5453d0bfece0c465d34aaf072ea99fa Mon Sep 17 00:00:00 2001
From: Jun Seo <jun.seo.93@proton.me>
Date: Thu, 26 Feb 2026 10:08:20 +0900
Subject: ALSA: usb-audio: Use correct version for UAC3 header validation

The entry of the validators table for UAC3 AC header descriptor is
defined with the wrong protocol version UAC_VERSION_2, while it should
have been UAC_VERSION_3.  This results in the validator never matching
for actual UAC3 devices (protocol == UAC_VERSION_3), causing their
header descriptors to bypass validation entirely.  A malicious USB
device presenting a truncated UAC3 header could exploit this to cause
out-of-bounds reads when the driver later accesses unvalidated
descriptor fields.

The bug was introduced in the same commit as the recently fixed UAC3
feature unit sub-type typo, and appears to be from the same copy-paste
error when the UAC3 section was created from the UAC2 section.

Fixes: 57f8770620e9 ("ALSA: usb-audio: More validations of descriptor units")
Cc: <stable@vger.kernel.org>
Signed-off-by: Jun Seo <jun.seo.93@proton.me>
Link: https://patch.msgid.link/20260226010820.36529-1-jun.seo.93@proton.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/validate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index 4bb4893f6e74..f62b7cc041dc 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -281,7 +281,7 @@ static const struct usb_desc_validator audio_validators[] = {
 	/* UAC_VERSION_2, UAC2_SAMPLE_RATE_CONVERTER: not implemented yet */
 
 	/* UAC3 */
-	FIXED(UAC_VERSION_2, UAC_HEADER, struct uac3_ac_header_descriptor),
+	FIXED(UAC_VERSION_3, UAC_HEADER, struct uac3_ac_header_descriptor),
 	FIXED(UAC_VERSION_3, UAC_INPUT_TERMINAL,
 	      struct uac3_input_terminal_descriptor),
 	FIXED(UAC_VERSION_3, UAC_OUTPUT_TERMINAL,
-- 
cgit v1.2.3


From cd3c877d04683b44a4d50dcdfad54b356e65d158 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Tue, 24 Feb 2026 07:46:37 -0800
Subject: iomap: don't report direct-io retries to fserror

iomap's directio implementation has two magic errno codes that it uses
to signal callers -- ENOTBLK tells the filesystem that it should retry
a write with the pagecache; and EAGAIN tells the caller that pagecache
flushing or invalidation failed and that it should try again.

Neither of these indicate data loss, so let's not report them.

Fixes: a9d573ee88af98 ("iomap: report file I/O errors to the VFS")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/20260224154637.GD2390381@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/direct-io.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 95254aa1b654..e911daedff65 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -87,6 +87,19 @@ static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio)
 	return FSERR_DIRECTIO_READ;
 }
 
+static inline bool should_report_dio_fserror(const struct iomap_dio *dio)
+{
+	switch (dio->error) {
+	case 0:
+	case -EAGAIN:
+	case -ENOTBLK:
+		/* don't send fsnotify for success or magic retry codes */
+		return false;
+	default:
+		return true;
+	}
+}
+
 ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
@@ -96,7 +109,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	if (dops && dops->end_io)
 		ret = dops->end_io(iocb, dio->size, ret, dio->flags);
-	if (dio->error)
+	if (should_report_dio_fserror(dio))
 		fserror_report_io(file_inode(iocb->ki_filp),
 				  iomap_dio_err_type(dio), offset, dio->size,
 				  dio->error, GFP_NOFS);
-- 
cgit v1.2.3


From 28aaa9c39945b7925a1cc1d513c8f21ed38f5e4f Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 10:43:55 +0100
Subject: kthread: consolidate kthread exit paths to prevent use-after-free

Guillaume reported crashes via corrupted RCU callback function pointers
during KUnit testing. The crash was traced back to the pidfs rhashtable
conversion which replaced the 24-byte rb_node with an 8-byte rhash_head
in struct pid, shrinking it from 160 to 144 bytes.

struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With
CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to
192 bytes and share the same slab cache. struct pid.rcu.func and
struct kthread.affinity_node both sit at offset 0x78.

When a kthread exits via make_task_dead() it bypasses kthread_exit() and
misses the affinity_node cleanup. free_kthread_struct() frees the memory
while the node is still linked into the global kthread_affinity_list. A
subsequent list_del() by another kthread writes through dangling list
pointers into the freed and reused memory, corrupting the pid's
rcu.func pointer.

Instead of patching free_kthread_struct() to handle the missed cleanup,
consolidate all kthread exit paths. Turn kthread_exit() into a macro
that calls do_exit() and add kthread_do_exit() which is called from
do_exit() for any task with PF_KTHREAD set. This guarantees that
kthread-specific cleanup always happens regardless of the exit path -
make_task_dead(), direct do_exit(), or kthread_exit().

Replace __to_kthread() with a new tsk_is_kthread() accessor in the
public header. Export do_exit() since module code using the
kthread_exit() macro now needs it directly.

Reported-by: Guillaume Tucker <gtucker@gtucker.io>
Tested-by: Guillaume Tucker <gtucker@gtucker.io>
Tested-by: Mark Brown <broonie@kernel.org>
Tested-by: David Gow <davidgow@google.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/all/20260224-mittlerweile-besessen-2738831ae7f6@brauner
Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes: 4d13f4304fa4 ("kthread: Implement preferred affinity")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/kthread.h | 21 ++++++++++++++++++++-
 kernel/exit.c           |  6 ++++++
 kernel/kthread.c        | 41 +++++------------------------------------
 3 files changed, 31 insertions(+), 37 deletions(-)

diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index c92c1149ee6e..a01a474719a7 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -7,6 +7,24 @@
 
 struct mm_struct;
 
+/* opaque kthread data */
+struct kthread;
+
+/*
+ * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
+ * always remain a kthread.  For kthreads p->worker_private always
+ * points to a struct kthread.  For tasks that are not kthreads
+ * p->worker_private is used to point to other things.
+ *
+ * Return NULL for any task that is not a kthread.
+ */
+static inline struct kthread *tsk_is_kthread(struct task_struct *p)
+{
+	if (p->flags & PF_KTHREAD)
+		return p->worker_private;
+	return NULL;
+}
+
 __printf(4, 5)
 struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 					   void *data,
@@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
-void kthread_exit(long result) __noreturn;
+#define kthread_exit(result) do_exit(result)
 void kthread_complete_and_exit(struct completion *, long) __noreturn;
 int kthreads_update_housekeeping(void);
+void kthread_do_exit(struct kthread *, long);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/kernel/exit.c b/kernel/exit.c
index 8a87021211ae..ede3117fa7d4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
+	struct kthread *kthread;
 	int group_dead;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(tsk->plug);
 
+	kthread = tsk_is_kthread(tsk);
+	if (unlikely(kthread))
+		kthread_do_exit(kthread, code);
+
 	kcov_task_exit(tsk);
 	kmsan_task_exit(tsk);
 
@@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code)
 	lockdep_free_task(tsk);
 	do_task_dead();
 }
+EXPORT_SYMBOL(do_exit);
 
 void __noreturn make_task_dead(int signr)
 {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 20451b624b67..791210daf8b4 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return k->worker_private;
 }
 
-/*
- * Variant of to_kthread() that doesn't assume @p is a kthread.
- *
- * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will
- * always remain a kthread.  For kthreads p->worker_private always
- * points to a struct kthread.  For tasks that are not kthreads
- * p->worker_private is used to point to other things.
- *
- * Return NULL for any task that is not a kthread.
- */
-static inline struct kthread *__to_kthread(struct task_struct *p)
-{
-	void *kthread = p->worker_private;
-	if (kthread && !(p->flags & PF_KTHREAD))
-		kthread = NULL;
-	return kthread;
-}
-
 void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk)
 {
 	struct kthread *kthread = to_kthread(tsk);
@@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park);
 
 bool kthread_should_stop_or_park(void)
 {
-	struct kthread *kthread = __to_kthread(current);
+	struct kthread *kthread = tsk_is_kthread(current);
 
 	if (!kthread)
 		return false;
@@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	if (kthread)
 		return kthread->threadfn;
 	return NULL;
@@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = __to_kthread(task);
+	struct kthread *kthread = tsk_is_kthread(task);
 	void *data = NULL;
 
 	if (kthread)
@@ -309,19 +291,8 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-/**
- * kthread_exit - Cause the current kthread return @result to kthread_stop().
- * @result: The integer value to return to kthread_stop().
- *
- * While kthread_exit can be called directly, it exists so that
- * functions which do some additional work in non-modular code such as
- * module_put_and_kthread_exit can be implemented.
- *
- * Does not return.
- */
-void __noreturn kthread_exit(long result)
+void kthread_do_exit(struct kthread *kthread, long result)
 {
-	struct kthread *kthread = to_kthread(current);
 	kthread->result = result;
 	if (!list_empty(&kthread->affinity_node)) {
 		mutex_lock(&kthread_affinity_lock);
@@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result)
 			kthread->preferred_affinity = NULL;
 		}
 	}
-	do_exit(0);
 }
-EXPORT_SYMBOL(kthread_exit);
 
 /**
  * kthread_complete_and_exit - Exit the current kthread.
@@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 
 bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = __to_kthread(p);
+	struct kthread *kthread = tsk_is_kthread(p);
 	if (!kthread)
 		return false;
 
-- 
cgit v1.2.3


From 7c2889af823340d1d410939b9d547bf184d5fa54 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 25 Feb 2026 15:48:59 +0200
Subject: RDMA/uverbs: Import DMA-BUF module in uverbs_std_types_dmabuf file

Fix the following compilation error:

ERROR: modpost: module ib_uverbs uses symbol dma_buf_move_notify
	from namespace DMA_BUF, but does not import it.

Fixes: 0ac6f4056c4a ("RDMA/uverbs: Add DMABUF object type and operations")
Link: https://patch.msgid.link/20260225-fix-uverbs-compilation-v1-1-acf7b3d0f9fa@nvidia.com
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_dmabuf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/core/uverbs_std_types_dmabuf.c b/drivers/infiniband/core/uverbs_std_types_dmabuf.c
index dfdfcd1d1a44..4a7f8b6f9dc8 100644
--- a/drivers/infiniband/core/uverbs_std_types_dmabuf.c
+++ b/drivers/infiniband/core/uverbs_std_types_dmabuf.c
@@ -10,6 +10,8 @@
 #include "rdma_core.h"
 #include "uverbs.h"
 
+MODULE_IMPORT_NS("DMA_BUF");
+
 static int uverbs_dmabuf_attach(struct dma_buf *dmabuf,
 				struct dma_buf_attachment *attachment)
 {
-- 
cgit v1.2.3


From a382a34276cb94d1cdc620b622dd85c55589a166 Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:32 -0800
Subject: selftests/vsock: change tests to respect write-once child ns mode

The child_ns_mode sysctl parameter becomes write-once in a future patch
in this series, which breaks existing tests. This patch updates the
tests to respect this new policy. No additional tests are added.

Add "global-parent" and "local-parent" namespaces as intermediaries to
spawn namespaces in the given modes. This avoids the need to change
"child_ns_mode" in the init_ns. nsenter must be used because ip netns
unshares the mount namespace so nested "ip netns add" breaks exec calls
from the init ns. Adds nsenter to the deps check.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-1-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/vsock/vmtest.sh | 41 +++++++++++++++++----------------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index dc8dbe74a6d0..86e338886b33 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -210,16 +210,21 @@ check_result() {
 }
 
 add_namespaces() {
-	local orig_mode
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
-
-	for mode in "${NS_MODES[@]}"; do
-		echo "${mode}" > /proc/sys/net/vsock/child_ns_mode
-		ip netns add "${mode}0" 2>/dev/null
-		ip netns add "${mode}1" 2>/dev/null
-	done
-
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
+	ip netns add "global-parent" 2>/dev/null
+	echo "global" | ip netns exec "global-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
+	ip netns add "local-parent" 2>/dev/null
+	echo "local" | ip netns exec "local-parent" \
+		tee /proc/sys/net/vsock/child_ns_mode &>/dev/null
+
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global0" 2>/dev/null
+	nsenter --net=/var/run/netns/global-parent \
+		ip netns add "global1" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local0" 2>/dev/null
+	nsenter --net=/var/run/netns/local-parent \
+		ip netns add "local1" 2>/dev/null
 }
 
 init_namespaces() {
@@ -237,6 +242,8 @@ del_namespaces() {
 		log_host "removed ns ${mode}0"
 		log_host "removed ns ${mode}1"
 	done
+	ip netns del "global-parent" &>/dev/null
+	ip netns del "local-parent" &>/dev/null
 }
 
 vm_ssh() {
@@ -287,7 +294,7 @@ check_args() {
 }
 
 check_deps() {
-	for dep in vng ${QEMU} busybox pkill ssh ss socat; do
+	for dep in vng ${QEMU} busybox pkill ssh ss socat nsenter; do
 		if [[ ! -x $(command -v "${dep}") ]]; then
 			echo -e "skip:    dependency ${dep} not found!\n"
 			exit "${KSFT_SKIP}"
@@ -1231,12 +1238,8 @@ test_ns_local_same_cid_ok() {
 }
 
 test_ns_host_vsock_child_ns_mode_ok() {
-	local orig_mode
-	local rc
-
-	orig_mode=$(cat /proc/sys/net/vsock/child_ns_mode)
+	local rc="${KSFT_PASS}"
 
-	rc="${KSFT_PASS}"
 	for mode in "${NS_MODES[@]}"; do
 		local ns="${mode}0"
 
@@ -1246,15 +1249,13 @@ test_ns_host_vsock_child_ns_mode_ok() {
 			continue
 		fi
 
-		if ! echo "${mode}" > /proc/sys/net/vsock/child_ns_mode; then
-			log_host "child_ns_mode should be writable to ${mode}"
+		if ! echo "${mode}" | ip netns exec "${ns}" \
+			tee /proc/sys/net/vsock/child_ns_mode &>/dev/null; then
 			rc="${KSFT_FAIL}"
 			continue
 		fi
 	done
 
-	echo "${orig_mode}" > /proc/sys/net/vsock/child_ns_mode
-
 	return "${rc}"
 }
 
-- 
cgit v1.2.3


From 102eab95f025b4d3f3a6c0a858400aca2af2fe52 Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:33 -0800
Subject: vsock: lock down child_ns_mode as write-once

Two administrator processes may race when setting child_ns_mode as one
process sets child_ns_mode to "local" and then creates a namespace, but
another process changes child_ns_mode to "global" between the write and
the namespace creation. The first process ends up with a namespace in
"global" mode instead of "local". While this can be detected after the
fact by reading ns_mode and retrying, it is fragile and error-prone.

Make child_ns_mode write-once so that a namespace manager can set it
once and be sure it won't change. Writing a different value after the
first write returns -EBUSY. This applies to all namespaces, including
init_net, where an init process can write "local" to lock all future
namespaces into local mode.

Fixes: eafb64f40ca4 ("vsock: add netns to vsock core")
Suggested-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Co-developed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-2-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/af_vsock.h    | 13 +++++++++++--
 include/net/netns/vsock.h |  3 +++
 net/vmw_vsock/af_vsock.c  | 15 ++++++++++-----
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d3ff48a2fbe0..533d8e75f7bb 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -276,10 +276,19 @@ static inline bool vsock_net_mode_global(struct vsock_sock *vsk)
 	return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL;
 }
 
-static inline void vsock_net_set_child_mode(struct net *net,
+static inline bool vsock_net_set_child_mode(struct net *net,
 					    enum vsock_net_mode mode)
 {
-	WRITE_ONCE(net->vsock.child_ns_mode, mode);
+	int new_locked = mode + 1;
+	int old_locked = 0; /* unlocked */
+
+	if (try_cmpxchg(&net->vsock.child_ns_mode_locked,
+			&old_locked, new_locked)) {
+		WRITE_ONCE(net->vsock.child_ns_mode, mode);
+		return true;
+	}
+
+	return old_locked == new_locked;
 }
 
 static inline enum vsock_net_mode vsock_net_child_mode(struct net *net)
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
index b34d69a22fa8..dc8cbe45f406 100644
--- a/include/net/netns/vsock.h
+++ b/include/net/netns/vsock.h
@@ -17,5 +17,8 @@ struct netns_vsock {
 
 	enum vsock_net_mode mode;
 	enum vsock_net_mode child_ns_mode;
+
+	/* 0 = unlocked, 1 = locked to global, 2 = locked to local */
+	int child_ns_mode_locked;
 };
 #endif /* __NET_NET_NAMESPACE_VSOCK_H */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index f4062c6a1944..2f7d94d682cb 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -90,16 +90,20 @@
  *
  *   - /proc/sys/net/vsock/ns_mode (read-only) reports the current namespace's
  *     mode, which is set at namespace creation and immutable thereafter.
- *   - /proc/sys/net/vsock/child_ns_mode (writable) controls what mode future
+ *   - /proc/sys/net/vsock/child_ns_mode (write-once) controls what mode future
  *     child namespaces will inherit when created. The initial value matches
  *     the namespace's own ns_mode.
  *
  *   Changing child_ns_mode only affects newly created namespaces, not the
  *   current namespace or existing children. A "local" namespace cannot set
- *   child_ns_mode to "global". At namespace creation, ns_mode is inherited
- *   from the parent's child_ns_mode.
+ *   child_ns_mode to "global". child_ns_mode is write-once, so that it may be
+ *   configured and locked down by a namespace manager. Writing a different
+ *   value after the first write returns -EBUSY. At namespace creation, ns_mode
+ *   is inherited from the parent's child_ns_mode.
  *
- *   The init_net mode is "global" and cannot be modified.
+ *   The init_net mode is "global" and cannot be modified. The init_net
+ *   child_ns_mode is also write-once, so an init process (e.g. systemd) can
+ *   set it to "local" to ensure all new namespaces inherit local mode.
  *
  *   The modes affect the allocation and accessibility of CIDs as follows:
  *
@@ -2853,7 +2857,8 @@ static int vsock_net_child_mode_string(const struct ctl_table *table, int write,
 		    new_mode == VSOCK_NET_MODE_GLOBAL)
 			return -EPERM;
 
-		vsock_net_set_child_mode(net, new_mode);
+		if (!vsock_net_set_child_mode(net, new_mode))
+			return -EBUSY;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From b6302e057fdc8f199ddae736ecdf45029f892e5c Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 23 Feb 2026 14:38:34 -0800
Subject: vsock: document write-once behavior of the child_ns_mode sysctl

Update the vsock child_ns_mode documentation to include the new
write-once semantics of setting child_ns_mode. The semantics are
implemented in a preceding patch in this series.

Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20260223-vsock-ns-write-once-v3-3-c0cde6959923@meta.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/admin-guide/sysctl/net.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index c10530624f1e..3b2ad61995d4 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -594,6 +594,9 @@ Values:
 	  their sockets will only be able to connect within their own
 	  namespace.
 
+The first write to ``child_ns_mode`` locks its value. Subsequent writes of the
+same value succeed, but writing a different value returns ``-EBUSY``.
+
 Changing ``child_ns_mode`` only affects namespaces created after the change;
 it does not modify the current namespace or any existing children.
 
-- 
cgit v1.2.3


From 7aa767d0d3d04e50ae94e770db7db8197f666970 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 23 Feb 2026 15:51:00 -0800
Subject: net: consume xmit errors of GSO frames

udpgro_frglist.sh and udpgro_bench.sh are the flakiest tests
currently in NIPA. They fail in the same exact way, TCP GRO
test stalls occasionally and the test gets killed after 10min.

These tests use veth to simulate GRO. They attach a trivial
("return XDP_PASS;") XDP program to the veth to force TSO off
and NAPI on.

Digging into the failure mode we can see that the connection
is completely stuck after a burst of drops. The sender's snd_nxt
is at sequence number N [1], but the receiver claims to have
received (rcv_nxt) up to N + 3 * MSS [2]. Last piece of the puzzle
is that senders rtx queue is not empty (let's say the block in
the rtx queue is at sequence number N - 4 * MSS [3]).

In this state, sender sends a retransmission from the rtx queue
with a single segment, and sequence numbers N-4*MSS:N-3*MSS [3].
Receiver sees it and responds with an ACK all the way up to
N + 3 * MSS [2]. But sender will reject this ack as TCP_ACK_UNSENT_DATA
because it has no recollection of ever sending data that far out [1].
And we are stuck.

The root cause is the mess of the xmit return codes. veth returns
an error when it can't xmit a frame. We end up with a loss event
like this:

  -------------------------------------------------
  |   GSO super frame 1   |   GSO super frame 2   |
  |-----------------------------------------------|
  | seg | seg | seg | seg | seg | seg | seg | seg |
  |  1  |  2  |  3  |  4  |  5  |  6  |  7  |  8  |
  -------------------------------------------------
     x    ok    ok    <ok>|  ok    ok    ok   <x>
                          \\
			   snd_nxt

"x" means packet lost by veth, and "ok" means it went thru.
Since veth has TSO disabled in this test it sees individual segments.
Segment 1 is on the retransmit queue and will be resent.

So why did the sender not advance snd_nxt even tho it clearly did
send up to seg 8? tcp_write_xmit() interprets the return code
from the core to mean that data has not been sent at all. Since
TCP deals with GSO super frames, not individual segment the crux
of the problem is that loss of a single segment can be interpreted
as loss of all. TCP only sees the last return code for the last
segment of the GSO frame (in <> brackets in the diagram above).

Of course for the problem to occur we need a setup or a device
without a Qdisc. Otherwise Qdisc layer disconnects the protocol
layer from the device errors completely.

We have multiple ways to fix this.

 1) make veth not return an error when it lost a packet.
    While this is what I think we did in the past, the issue keeps
    reappearing and it's annoying to debug. The game of whack
    a mole is not great.

 2) fix the damn return codes
    We only talk about NETDEV_TX_OK and NETDEV_TX_BUSY in the
    documentation, so maybe we should make the return code from
    ndo_start_xmit() a boolean. I like that the most, but perhaps
    some ancient, not-really-networking protocol would suffer.

 3) make TCP ignore the errors
    It is not entirely clear to me what benefit TCP gets from
    interpreting the result of ip_queue_xmit()? Specifically once
    the connection is established and we're pushing data - packet
    loss is just packet loss?

 4) this fix
    Ignore the rc in the Qdisc-less+GSO case, since it's unreliable.
    We already always return OK in the TCQ_F_CAN_BYPASS case.
    In the Qdisc-less case let's be a bit more conservative and only
    mask the GSO errors. This path is taken by non-IP-"networks"
    like CAN, MCTP etc, so we could regress some ancient thing.
    This is the simplest, but also maybe the hackiest fix?

Similar fix has been proposed by Eric in the past but never committed
because original reporter was working with an OOT driver and wasn't
providing feedback (see Link).

Link: https://lore.kernel.org/CANn89iJcLepEin7EtBETrZ36bjoD9LrR=k4cfwWh046GB+4f9A@mail.gmail.com
Fixes: 1f59533f9ca5 ("qdisc: validate frames going through the direct_xmit path")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260223235100.108939-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f3426385f1ba..3d2d3b18915c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4822,6 +4822,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 		 * to -1 or to their cpu id, but not to our id.
 		 */
 		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
+			bool is_list = false;
+
 			if (dev_xmit_recursion())
 				goto recursion_alert;
 
@@ -4832,17 +4834,28 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
+				is_list = !!skb->next;
+
 				dev_xmit_recursion_inc();
 				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
 				dev_xmit_recursion_dec();
-				if (dev_xmit_complete(rc)) {
-					HARD_TX_UNLOCK(dev, txq);
-					goto out;
-				}
+
+				/* GSO segments a single SKB into
+				 * a list of frames. TCP expects error
+				 * to mean none of the data was sent.
+				 */
+				if (is_list)
+					rc = NETDEV_TX_OK;
 			}
 			HARD_TX_UNLOCK(dev, txq);
+			if (!skb) /* xmit completed */
+				goto out;
+
 			net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
 					     dev->name);
+			/* NETDEV_TX_BUSY or queue was stopped */
+			if (!is_list)
+				rc = -ENETDOWN;
 		} else {
 			/* Recursion is detected! It is possible,
 			 * unfortunately
@@ -4850,10 +4863,10 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 recursion_alert:
 			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
 					     dev->name);
+			rc = -ENETDOWN;
 		}
 	}
 
-	rc = -ENETDOWN;
 	rcu_read_unlock_bh();
 
 	dev_core_stats_tx_dropped_inc(dev);
-- 
cgit v1.2.3


From 8a5752c6dcc085a3bfc78589925182e4e98468c5 Mon Sep 17 00:00:00 2001
From: Junrui Luo <moonafterrain@outlook.com>
Date: Tue, 24 Feb 2026 19:05:56 +0800
Subject: dpaa2-switch: validate num_ifs to prevent out-of-bounds write

The driver obtains sw_attr.num_ifs from firmware via dpsw_get_attributes()
but never validates it against DPSW_MAX_IF (64). This value controls
iteration in dpaa2_switch_fdb_get_flood_cfg(), which writes port indices
into the fixed-size cfg->if_id[DPSW_MAX_IF] array. When firmware reports
num_ifs >= 64, the loop can write past the array bounds.

Add a bound check for num_ifs in dpaa2_switch_init().

dpaa2_switch_fdb_get_flood_cfg() appends the control interface (port
num_ifs) after all matched ports. When num_ifs == DPSW_MAX_IF and all
ports match the flood filter, the loop fills all 64 slots and the control
interface write overflows by one entry.

The check uses >= because num_ifs == DPSW_MAX_IF is also functionally
broken.

build_if_id_bitmap() silently drops any ID >= 64:
      if (id[i] < DPSW_MAX_IF)
          bmap[id[i] / 64] |= ...

Fixes: 539dda3c5d19 ("staging: dpaa2-switch: properly setup switching domains")
Signed-off-by: Junrui Luo <moonafterrain@outlook.com>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/SYBPR01MB78812B47B7F0470B617C408AAF74A@SYBPR01MB7881.ausprd01.prod.outlook.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 66240c340492..78e21b46a5ba 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -3034,6 +3034,13 @@ static int dpaa2_switch_init(struct fsl_mc_device *sw_dev)
 		goto err_close;
 	}
 
+	if (ethsw->sw_attr.num_ifs >= DPSW_MAX_IF) {
+		dev_err(dev, "DPSW num_ifs %u exceeds max %u\n",
+			ethsw->sw_attr.num_ifs, DPSW_MAX_IF);
+		err = -EINVAL;
+		goto err_close;
+	}
+
 	err = dpsw_get_api_version(ethsw->mc_io, 0,
 				   &ethsw->major,
 				   &ethsw->minor);
-- 
cgit v1.2.3


From 003ce8c9b2ca28fbb4860651e76fb1c9a91f2ea1 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:17:28 +0000
Subject: ALSA: hda: cs35l56: Fix signedness error in cs35l56_hda_posture_put()

In cs35l56_hda_posture_put() assign ucontrol->value.integer.value[0] to
a long instead of an unsigned long. ucontrol->value.integer.value[0] is
a long.

This fixes the sparse warning:

sound/hda/codecs/side-codecs/cs35l56_hda.c:256:20: warning: unsigned value
that used to be signed checked against zero?
sound/hda/codecs/side-codecs/cs35l56_hda.c:252:29: signed value source

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 73cfbfa9caea8 ("ALSA: hda/cs35l56: Add driver for Cirrus Logic CS35L56 amplifier")
Link: https://patch.msgid.link/20260226111728.1700431-1-rf@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/cs35l56_hda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c
index cfc8de2ae499..eb66827eabf8 100644
--- a/sound/hda/codecs/side-codecs/cs35l56_hda.c
+++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c
@@ -249,7 +249,7 @@ static int cs35l56_hda_posture_put(struct snd_kcontrol *kcontrol,
 				   struct snd_ctl_elem_value *ucontrol)
 {
 	struct cs35l56_hda *cs35l56 = snd_kcontrol_chip(kcontrol);
-	unsigned long pos = ucontrol->value.integer.value[0];
+	long pos = ucontrol->value.integer.value[0];
 	bool changed;
 	int ret;
 
-- 
cgit v1.2.3


From baed0d9ba91d4f390da12d5039128ee897253d60 Mon Sep 17 00:00:00 2001
From: Vahagn Vardanian <vahagn@redrays.io>
Date: Wed, 25 Feb 2026 14:06:18 +0100
Subject: netfilter: nf_conntrack_h323: fix OOB read in decode_choice()

In decode_choice(), the boundary check before get_len() uses the
variable `len`, which is still 0 from its initialization at the top of
the function:

    unsigned int type, ext, len = 0;
    ...
    if (ext || (son->attr & OPEN)) {
        BYTE_ALIGN(bs);
        if (nf_h323_error_boundary(bs, len, 0))  /* len is 0 here */
            return H323_ERROR_BOUND;
        len = get_len(bs);                        /* OOB read */

When the bitstream is exactly consumed (bs->cur == bs->end), the check
nf_h323_error_boundary(bs, 0, 0) evaluates to (bs->cur + 0 > bs->end),
which is false.  The subsequent get_len() call then dereferences
*bs->cur++, reading 1 byte past the end of the buffer.  If that byte
has bit 7 set, get_len() reads a second byte as well.

This can be triggered remotely by sending a crafted Q.931 SETUP message
with a User-User Information Element containing exactly 2 bytes of
PER-encoded data ({0x08, 0x00}) to port 1720 through a firewall with
the nf_conntrack_h323 helper active.  The decoder fully consumes the
PER buffer before reaching this code path, resulting in a 1-2 byte
heap-buffer-overflow read confirmed by AddressSanitizer.

Fix this by checking for 2 bytes (the maximum that get_len() may read)
instead of the uninitialized `len`.  This matches the pattern used at
every other get_len() call site in the same file, where the caller
checks for 2 bytes of available data before calling get_len().

Fixes: ec8a8f3c31dd ("netfilter: nf_ct_h323: Extend nf_h323_error_boundary to work on bits as well")
Signed-off-by: Vahagn Vardanian <vahagn@redrays.io>
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260225130619.1248-2-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/netfilter/nf_conntrack_h323_asn1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index 540d97715bd2..62aa22a07876 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -796,7 +796,7 @@ static int decode_choice(struct bitstr *bs, const struct field_t *f,
 
 	if (ext || (son->attr & OPEN)) {
 		BYTE_ALIGN(bs);
-		if (nf_h323_error_boundary(bs, len, 0))
+		if (nf_h323_error_boundary(bs, 2, 0))
 			return H323_ERROR_BOUND;
 		len = get_len(bs);
 		if (nf_h323_error_boundary(bs, len, 0))
-- 
cgit v1.2.3


From 786ea2b694f48e1b34f1dcf104e09357fc99ef34 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 12:41:15 +0000
Subject: ALSA: hda: cs35l56: Remove unnecessary struct cs_dsp_client_ops

Since commit af37511305c0 ("firmware: cs_dsp: Don't require client to
provide a struct cs_dsp_client_ops") the client doesn't have to provide
a struct cs_dsp_client_ops. So remove the dummy cs_dsp_client_ops.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226124115.1811187-1-rf@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/cs35l56_hda.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c
index eb66827eabf8..1ace4beef508 100644
--- a/sound/hda/codecs/side-codecs/cs35l56_hda.c
+++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c
@@ -403,10 +403,6 @@ static void cs35l56_hda_remove_controls(struct cs35l56_hda *cs35l56)
 	snd_ctl_remove(cs35l56->codec->card, cs35l56->volume_ctl);
 }
 
-static const struct cs_dsp_client_ops cs35l56_hda_client_ops = {
-	/* cs_dsp requires the client to provide this even if it is empty */
-};
-
 static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56,
 					     const struct firmware **firmware, char **filename,
 					     const char *base_name, const char *system_name,
@@ -1149,7 +1145,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id)
 	cs35l56->base.cal_index = cs35l56->index;
 
 	cs35l56_init_cs_dsp(&cs35l56->base, &cs35l56->cs_dsp);
-	cs35l56->cs_dsp.client_ops = &cs35l56_hda_client_ops;
 
 	if (cs35l56->base.reset_gpio) {
 		dev_dbg(cs35l56->base.dev, "Hard reset\n");
-- 
cgit v1.2.3


From a0b4c7a49137ed21279f354eb59f49ddae8dffc2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 26 Feb 2026 13:32:33 +0000
Subject: netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict
 sequence

Fix netfslib such that when it's making an unbuffered or DIO write, to make
sure that it sends each subrequest strictly sequentially, waiting till the
previous one is 'committed' before sending the next so that we don't have
pieces landing out of order and potentially leaving a hole if an error
occurs (ENOSPC for example).

This is done by copying in just those bits of issuing, collecting and
retrying subrequests that are necessary to do one subrequest at a time.
Retrying, in particular, is simpler because if the current subrequest needs
retrying, the source iterator can just be copied again and the subrequest
prepped and issued again without needing to be concerned about whether it
needs merging with the previous or next in the sequence.

Note that the issuing loop waits for a subrequest to complete right after
issuing it, but this wait could be moved elsewhere allowing preparatory
steps to be performed whilst the subrequest is in progress.  In particular,
once content encryption is available in netfslib, that could be done whilst
waiting, as could cleanup of buffers that have been completed.

Fixes: 153a9961b551 ("netfs: Implement unbuffered/DIO write support")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/58526.1772112753@warthog.procyon.org.uk
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/direct_write.c      | 228 ++++++++++++++++++++++++++++++++++++++++---
 fs/netfs/internal.h          |   4 +-
 fs/netfs/write_collect.c     |  21 ----
 fs/netfs/write_issue.c       |  41 +-------
 include/trace/events/netfs.h |   4 +-
 5 files changed, 221 insertions(+), 77 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index a9d1c3b2c084..dd1451bf7543 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -9,6 +9,202 @@
 #include <linux/uio.h>
 #include "internal.h"
 
+/*
+ * Perform the cleanup rituals after an unbuffered write is complete.
+ */
+static void netfs_unbuffered_write_done(struct netfs_io_request *wreq)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+
+	_enter("R=%x", wreq->debug_id);
+
+	/* Okay, declare that all I/O is complete. */
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	if (!wreq->error)
+		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
+
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		/* mmap may have got underfoot and we may now have folios
+		 * locally covering the region we just wrote.  Attempt to
+		 * discard the folios, but leave in place any modified locally.
+		 * ->write_iter() is prevented from interfering by the DIO
+		 * counter.
+		 */
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
+	_debug("finished");
+	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
+
+	if (wreq->iocb) {
+		size_t written = umin(wreq->transferred, wreq->len);
+
+		wreq->iocb->ki_pos += written;
+		if (wreq->iocb->ki_complete) {
+			trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete);
+			wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written);
+		}
+		wreq->iocb = VFS_PTR_POISON;
+	}
+
+	netfs_clear_subrequests(wreq);
+}
+
+/*
+ * Collect the subrequest results of unbuffered write subrequests.
+ */
+static void netfs_unbuffered_write_collect(struct netfs_io_request *wreq,
+					   struct netfs_io_stream *stream,
+					   struct netfs_io_subrequest *subreq)
+{
+	trace_netfs_collect_sreq(wreq, subreq);
+
+	spin_lock(&wreq->lock);
+	list_del_init(&subreq->rreq_link);
+	spin_unlock(&wreq->lock);
+
+	wreq->transferred += subreq->transferred;
+	iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+	stream->collected_to = subreq->start + subreq->transferred;
+	wreq->collected_to = stream->collected_to;
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_done);
+
+	trace_netfs_collect_stream(wreq, stream);
+	trace_netfs_collect_state(wreq, wreq->collected_to, 0);
+}
+
+/*
+ * Write data to the server without going through the pagecache and without
+ * writing it to the local cache.  We dispatch the subrequests serially and
+ * wait for each to complete before dispatching the next, lest we leave a gap
+ * in the data written due to a failure such as ENOSPC.  We could, however
+ * attempt to do preparation such as content encryption for the next subreq
+ * whilst the current is in progress.
+ */
+static int netfs_unbuffered_write(struct netfs_io_request *wreq)
+{
+	struct netfs_io_subrequest *subreq = NULL;
+	struct netfs_io_stream *stream = &wreq->io_streams[0];
+	int ret;
+
+	_enter("%llx", wreq->len);
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
+	stream->collected_to = wreq->start;
+
+	for (;;) {
+		bool retry = false;
+
+		if (!subreq) {
+			netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred);
+			subreq = stream->construct;
+			stream->construct = NULL;
+			stream->front = NULL;
+		}
+
+		/* Check if (re-)preparation failed. */
+		if (unlikely(test_bit(NETFS_SREQ_FAILED, &subreq->flags))) {
+			netfs_write_subrequest_terminated(subreq, subreq->error);
+			wreq->error = subreq->error;
+			break;
+		}
+
+		iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred);
+		if (!iov_iter_count(&subreq->io_iter))
+			break;
+
+		subreq->len = netfs_limit_iter(&subreq->io_iter, 0,
+					       stream->sreq_max_len,
+					       stream->sreq_max_segs);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+		stream->submit_extendable_to = subreq->len;
+
+		trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+		stream->issue_write(subreq);
+
+		/* Async, need to wait. */
+		netfs_wait_for_in_progress_stream(wreq, stream);
+
+		if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
+			retry = true;
+		} else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) {
+			ret = subreq->error;
+			wreq->error = ret;
+			netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed);
+			subreq = NULL;
+			break;
+		}
+		ret = 0;
+
+		if (!retry) {
+			netfs_unbuffered_write_collect(wreq, stream, subreq);
+			subreq = NULL;
+			if (wreq->transferred >= wreq->len)
+				break;
+			if (!wreq->iocb && signal_pending(current)) {
+				ret = wreq->transferred ? -EINTR : -ERESTARTSYS;
+				trace_netfs_rreq(wreq, netfs_rreq_trace_intr);
+				break;
+			}
+			continue;
+		}
+
+		/* We need to retry the last subrequest, so first reset the
+		 * iterator, taking into account what, if anything, we managed
+		 * to transfer.
+		 */
+		subreq->error = -EAGAIN;
+		trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
+		if (subreq->transferred > 0)
+			iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+		if (stream->source == NETFS_UPLOAD_TO_SERVER &&
+		    wreq->netfs_ops->retry_request)
+			wreq->netfs_ops->retry_request(wreq, stream);
+
+		__clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_FAILED, &subreq->flags);
+		subreq->io_iter		= wreq->buffer.iter;
+		subreq->start		= wreq->start + wreq->transferred;
+		subreq->len		= wreq->len   - wreq->transferred;
+		subreq->transferred	= 0;
+		subreq->retry_count	+= 1;
+		stream->sreq_max_len	= UINT_MAX;
+		stream->sreq_max_segs	= INT_MAX;
+
+		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
+		stream->prepare_write(subreq);
+
+		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+		netfs_stat(&netfs_n_wh_retry_write_subreq);
+	}
+
+	netfs_unbuffered_write_done(wreq);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+static void netfs_unbuffered_write_async(struct work_struct *work)
+{
+	struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work);
+
+	netfs_unbuffered_write(wreq);
+	netfs_put_request(wreq, netfs_rreq_trace_put_complete);
+}
+
 /*
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
@@ -70,35 +266,35 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 			 */
 			wreq->buffer.iter = *iter;
 		}
+
+		wreq->len = iov_iter_count(&wreq->buffer.iter);
 	}
 
 	__set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags);
-	if (async)
-		__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 
 	/* Copy the data into the bounce buffer and encrypt it. */
 	// TODO
 
 	/* Dispatch the write. */
 	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
-	if (async)
-		wreq->iocb = iocb;
-	wreq->len = iov_iter_count(&wreq->buffer.iter);
-	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
-	if (ret < 0) {
-		_debug("begin = %zd", ret);
-		goto out;
-	}
 
-	if (!async) {
-		ret = netfs_wait_for_write(wreq);
-		if (ret > 0)
-			iocb->ki_pos += ret;
-	} else {
+	if (async) {
+		INIT_WORK(&wreq->work, netfs_unbuffered_write_async);
+		wreq->iocb = iocb;
+		queue_work(system_dfl_wq, &wreq->work);
 		ret = -EIOCBQUEUED;
+	} else {
+		ret = netfs_unbuffered_write(wreq);
+		if (ret < 0) {
+			_debug("begin = %zd", ret);
+		} else {
+			iocb->ki_pos += wreq->transferred;
+			ret = wreq->transferred ?: wreq->error;
+		}
+
+		netfs_put_request(wreq, netfs_rreq_trace_put_complete);
 	}
 
-out:
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	return ret;
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 4319611f5354..d436e20d3418 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -198,6 +198,9 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 						struct file *file,
 						loff_t start,
 						enum netfs_io_origin origin);
+void netfs_prepare_write(struct netfs_io_request *wreq,
+			 struct netfs_io_stream *stream,
+			 loff_t start);
 void netfs_reissue_write(struct netfs_io_stream *stream,
 			 struct netfs_io_subrequest *subreq,
 			 struct iov_iter *source);
@@ -212,7 +215,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 			       struct folio **writethrough_cache);
 ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
 			       struct folio *writethrough_cache);
-int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len);
 
 /*
  * write_retry.c
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 61eab34ea67e..83eb3dc1adf8 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -399,27 +399,6 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 		ictx->ops->invalidate_cache(wreq);
 	}
 
-	if ((wreq->origin == NETFS_UNBUFFERED_WRITE ||
-	     wreq->origin == NETFS_DIO_WRITE) &&
-	    !wreq->error)
-		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
-
-	if (wreq->origin == NETFS_DIO_WRITE &&
-	    wreq->mapping->nrpages) {
-		/* mmap may have got underfoot and we may now have folios
-		 * locally covering the region we just wrote.  Attempt to
-		 * discard the folios, but leave in place any modified locally.
-		 * ->write_iter() is prevented from interfering by the DIO
-		 * counter.
-		 */
-		pgoff_t first = wreq->start >> PAGE_SHIFT;
-		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
-		invalidate_inode_pages2_range(wreq->mapping, first, last);
-	}
-
-	if (wreq->origin == NETFS_DIO_WRITE)
-		inode_dio_end(wreq->inode);
-
 	_debug("finished");
 	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
 	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 34894da5a23e..437268f65640 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -154,9 +154,9 @@ EXPORT_SYMBOL(netfs_prepare_write_failed);
  * Prepare a write subrequest.  We need to allocate a new subrequest
  * if we don't have one.
  */
-static void netfs_prepare_write(struct netfs_io_request *wreq,
-				struct netfs_io_stream *stream,
-				loff_t start)
+void netfs_prepare_write(struct netfs_io_request *wreq,
+			 struct netfs_io_stream *stream,
+			 loff_t start)
 {
 	struct netfs_io_subrequest *subreq;
 	struct iov_iter *wreq_iter = &wreq->buffer.iter;
@@ -698,41 +698,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c
 	return ret;
 }
 
-/*
- * Write data to the server without going through the pagecache and without
- * writing it to the local cache.
- */
-int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len)
-{
-	struct netfs_io_stream *upload = &wreq->io_streams[0];
-	ssize_t part;
-	loff_t start = wreq->start;
-	int error = 0;
-
-	_enter("%zx", len);
-
-	if (wreq->origin == NETFS_DIO_WRITE)
-		inode_dio_begin(wreq->inode);
-
-	while (len) {
-		// TODO: Prepare content encryption
-
-		_debug("unbuffered %zx", len);
-		part = netfs_advance_write(wreq, upload, start, len, false);
-		start += part;
-		len -= part;
-		rolling_buffer_advance(&wreq->buffer, part);
-		if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags))
-			netfs_wait_for_paused_write(wreq);
-		if (test_bit(NETFS_RREQ_FAILED, &wreq->flags))
-			break;
-	}
-
-	netfs_end_issue_write(wreq);
-	_leave(" = %d", error);
-	return error;
-}
-
 /*
  * Write some of a pending folio data back to the server and/or the cache.
  */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 64a382fbc31a..2d366be46a1c 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -57,6 +57,7 @@
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_end_copy_to_cache,	"END-C2C")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_intr,		"INTR   ")	\
 	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
@@ -169,7 +170,8 @@
 	EM(netfs_sreq_trace_put_oom,		"PUT OOM    ")	\
 	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
-	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
+	EM(netfs_sreq_trace_put_terminated,	"PUT TERM   ")	\
+	E_(netfs_sreq_trace_see_failed,		"SEE FAILED ")
 
 #define netfs_folio_traces					\
 	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
-- 
cgit v1.2.3


From 2970525f789c080e7e82ecb09cd85a8bb1d284e4 Mon Sep 17 00:00:00 2001
From: Jingkai Tan <contact@jingk.ai>
Date: Thu, 22 Jan 2026 21:14:10 +0000
Subject: btrfs: handle discard errors in in btrfs_finish_extent_commit()

Coverity (ID: 1226842) reported that the return value of
btrfs_discard_extent() is assigned to ret but is immediately
overwritten by unpin_extent_range() without being checked.

Use the same error handling that is done later in the same function.

Signed-off-by: Jingkai Tan <contact@jingk.ai>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 03cf9f242c70..b0d9baf5b412 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2933,9 +2933,15 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 	while (!TRANS_ABORTED(trans) && cached_state) {
 		struct extent_state *next_state;
 
-		if (btrfs_test_opt(fs_info, DISCARD_SYNC))
+		if (btrfs_test_opt(fs_info, DISCARD_SYNC)) {
 			ret = btrfs_discard_extent(fs_info, start,
 						   end + 1 - start, NULL, true);
+			if (ret) {
+				btrfs_warn(fs_info,
+				"discard failed for extent [%llu, %llu]: errno=%d %s",
+					   start, end, ret, btrfs_decode_error(ret));
+			}
+		}
 
 		next_state = btrfs_next_extent_state(unpin, cached_state);
 		btrfs_clear_extent_dirty(unpin, start, end, &cached_state);
-- 
cgit v1.2.3


From a4fe134fc1d8eb7dcd07e0961c5711b443decd89 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 9 Feb 2026 14:01:45 +1030
Subject: btrfs: fix a double release on reserved extents in cow_one_range()

[BUG]
Commit c28214bde6da ("btrfs: refactor the main loop of
cow_file_range()") refactored the handling of COWing one range.

However it changed the error handling of the reserved extent.

The old cleanup looks like this:

out_drop_extent_cache:
	btrfs_drop_extent_map_range(inode, start, start + cur_alloc_size - 1, false);
out_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, true);
	[...]
	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
		     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;
	/*
	 * For the range (2). If we reserved an extent for our delalloc range
	 * (or a subrange) and failed to create the respective ordered extent,
	 * then it means that when we reserved the extent we decremented the
	 * extent's size from the data space_info's bytes_may_use counter and
	 * incremented the space_info's bytes_reserved counter by the same
	 * amount. We must make sure extent_clear_unlock_delalloc() does not try
	 * to decrement again the data space_info's bytes_may_use counter,
	 * therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV.
	 */
	if (cur_alloc_size) {
	        extent_clear_unlock_delalloc(inode, start,
	                                     start + cur_alloc_size - 1,
	                                     locked_folio, &cached, clear_bits,
	                                     page_ops);
	        btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
	}

Which only calls EXTENT_CLEAR_META_RESV.
As the reserved extent is properly handled by
btrfs_free_reserved_extent().

However the new cleanup is:

	extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached,
				     EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW |
				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
				     PAGE_END_WRITEBACK);
	btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL);
	btrfs_dec_block_group_reservations(fs_info, ins->objectid);
	btrfs_free_reserved_extent(fs_info, ins->objectid, ins->offset, true);

The flag EXTENT_DO_ACCOUNTING implies both EXTENT_CLEAR_META_RESV and
EXTENT_CLEAR_DATA_RESV, which will release the bytes_may_use, which
later btrfs_free_reserved_extent() will do again, causing incorrect
double release (and may underflow bytes_may_use).

[FIX]
Use EXTENT_CLEAR_META_RESV to replace EXTENT_DO_ACCOUNTING, and add back
the comments on why we only use EXTENT_CLEAR_META_RESV.

Fixes: c28214bde6da ("btrfs: refactor the main loop of cow_file_range()")
Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208184920.1102719-1-clm@meta.com/
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b6c763a17406..ade590707793 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1392,10 +1392,25 @@ static int cow_one_range(struct btrfs_inode *inode, struct folio *locked_folio,
 	return ret;
 
 free_reserved:
+	/*
+	 * If we have reserved an extent for the current range and failed to
+	 * create the respective extent map or ordered extent, it means that
+	 * when we reserved the extent we decremented the extent's size from
+	 * the data space_info's bytes_may_use counter and
+	 * incremented the space_info's bytes_reserved counter by the same
+	 * amount.
+	 *
+	 * We must make sure extent_clear_unlock_delalloc() does not try
+	 * to decrement again the data space_info's bytes_may_use counter, which
+	 * will be handled by btrfs_free_reserved_extent().
+	 *
+	 * Therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV, but only
+	 * EXTENT_CLEAR_META_RESV.
+	 */
 	extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached,
 				     EXTENT_LOCKED | EXTENT_DELALLOC |
 				     EXTENT_DELALLOC_NEW |
-				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
+				     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV,
 				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
 				     PAGE_END_WRITEBACK);
 	btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL);
-- 
cgit v1.2.3


From 0649355303995d6539df1fa8feaf50497f94db9b Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:27:14 +0000
Subject: btrfs: change warning messages to error level in open_ctree()

Failure to read the fs root results in a mount error, but we log a warning
message. Same goes for checking the UUID tree, an error results in a mount
failure but we log a warning message. Change the level of the logged
messages from warning to error.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 13e400046c87..de8ce9c588fe 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3642,7 +3642,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		ret = PTR_ERR(fs_info->fs_root);
-		btrfs_warn(fs_info, "failed to read fs tree: %d", ret);
+		btrfs_err(fs_info, "failed to read fs tree: %d", ret);
 		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}
@@ -3663,8 +3663,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		btrfs_info(fs_info, "checking UUID tree");
 		ret = btrfs_check_uuid_tree(fs_info);
 		if (ret) {
-			btrfs_warn(fs_info,
-				"failed to check the UUID tree: %d", ret);
+			btrfs_err(fs_info, "failed to check the UUID tree: %d", ret);
 			close_ctree(fs_info);
 			return ret;
 		}
-- 
cgit v1.2.3


From 64def7d7d62b61044fe619e3cc9cbe60454decd9 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:37:41 +0000
Subject: btrfs: remove redundant warning message in btrfs_check_uuid_tree()

If we fail to start the UUID rescan kthread, btrfs_check_uuid_tree() logs
an error message and returns the error to the single caller, open_ctree().

This however is redundant since the caller already logs an error message,
which is also more informative since it logs the error code. Some remove
the warning message from btrfs_check_uuid_tree() as it doesn't add any
value.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index de8ce9c588fe..b855e2cec2ec 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2972,7 +2972,6 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
 	task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
 	if (IS_ERR(task)) {
 		/* fs_info->update_uuid_tree_gen remains 0 in all error case */
-		btrfs_warn(fs_info, "failed to start uuid_rescan task");
 		up(&fs_info->uuid_tree_rescan_sem);
 		return PTR_ERR(task);
 	}
-- 
cgit v1.2.3


From 4db8d56c6f4cbea7293d4236efac4a507dbfa6b1 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 15:47:57 +0000
Subject: btrfs: remove btrfs_handle_fs_error() after failure to recover log
 trees

There is no need to call btrfs_handle_fs_error() (which we are trying to
deprecate) if we fail to recover log trees:

1) Such a failure results in failing the mount immediately;

2) If the recovery started a transaction before failing, it has already
   aborted the transaction down in the call chain.

So remove the btrfs_handle_fs_error() call, replace it with an error
message and assert that the FS is in error state (so that no partial
updates are committed due to a transaction that was not aborted).

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b855e2cec2ec..e6574456a306 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2023,9 +2023,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	/* returns with log_tree_root freed on success */
 	ret = btrfs_recover_log_trees(log_tree_root);
 	btrfs_put_root(log_tree_root);
-	if (ret) {
-		btrfs_handle_fs_error(fs_info, ret,
-				      "Failed to recover log tree");
+	if (unlikely(ret)) {
+		ASSERT(BTRFS_FS_ERROR(fs_info) != 0);
+		btrfs_err(fs_info, "failed to recover log trees with error: %d", ret);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 912db40655684a0a427c8b118dd0c36eb5a61fe4 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 9 Feb 2026 09:49:49 +0000
Subject: btrfs: convert log messages to error level in btrfs_replay_log()

We are logging messages as warnings but they should really have an error
level instead, as if the respective conditions are met the mount will
fail. So convert them to error level and also log the error code returned
by read_tree_block().

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e6574456a306..028ba86bcf73 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1994,7 +1994,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	int level = btrfs_super_log_root_level(disk_super);
 
 	if (unlikely(fs_devices->rw_devices == 0)) {
-		btrfs_warn(fs_info, "log replay required on RO media");
+		btrfs_err(fs_info, "log replay required on RO media");
 		return -EIO;
 	}
 
@@ -2008,9 +2008,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	check.owner_root = BTRFS_TREE_LOG_OBJECTID;
 	log_tree_root->node = read_tree_block(fs_info, bytenr, &check);
 	if (IS_ERR(log_tree_root->node)) {
-		btrfs_warn(fs_info, "failed to read log tree");
 		ret = PTR_ERR(log_tree_root->node);
 		log_tree_root->node = NULL;
+		btrfs_err(fs_info, "failed to read log tree with error: %d", ret);
 		btrfs_put_root(log_tree_root);
 		return ret;
 	}
-- 
cgit v1.2.3


From 8ac7fad32b93044f4350ab35f11fee1a61286723 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Feb 2026 14:23:29 +0000
Subject: btrfs: remove pointless WARN_ON() in cache_save_setup()

This WARN_ON(ret) is never executed since the previous if statement makes
us jump into the 'out_put' label when ret is not zero. The existing
transaction abort inside the if statement also gives us a stack trace,
so we don't need to move the WARN_ON(ret) into the if statement either.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5f76683b3f21..77285ade3a0e 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -3341,7 +3341,6 @@ again:
 		btrfs_abort_transaction(trans, ret);
 		goto out_put;
 	}
-	WARN_ON(ret);
 
 	/* We've already setup this transaction, go ahead and exit */
 	if (block_group->cache_generation == trans->transid &&
-- 
cgit v1.2.3


From 2ab22446425c2c72b44926bc964c263e06e7e137 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 11 Feb 2026 11:01:25 -0800
Subject: btrfs: fix referenced/exclusive check in squota_check_parent_usage()

We compared rfer_cmpr against excl_cmpr_sum instead of rfer_cmpr_sum
which is confusing.

I expect that
rfer_cmpr == excl_cmpr in squota, but it is much better to be consistent
in case of any surprises or bugs.

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/cover.1764796022.git.boris@bur.io/T/#mccb231643ffd290b44a010d4419474d280be5537
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 38adadb936dc..19edd25ff5d1 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -370,7 +370,7 @@ static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrf
 		nr_members++;
 	}
 	mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum ||
-		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum);
+		    parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != rfer_cmpr_sum);
 
 	WARN(mismatch,
 	     "parent squota qgroup %hu/%llu has mismatched usage from its %d members. "
-- 
cgit v1.2.3


From 3f501412f2079ca14bf68a18d80a2b7a823f1f64 Mon Sep 17 00:00:00 2001
From: Miquel Sabaté Solà <mssola@mssola.com>
Date: Mon, 16 Feb 2026 22:12:15 +0100
Subject: btrfs: free pages on error in btrfs_uring_read_extent()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In this function the 'pages' object is never freed in the hopes that it is
picked up by btrfs_uring_read_finished() whenever that executes in the
future. But that's just the happy path. Along the way previous
allocations might have gone wrong, or we might not get -EIOCBQUEUED from
btrfs_encoded_read_regular_fill_pages(). In all these cases, we go to a
cleanup section that frees all memory allocated by this function without
assuming any deferred execution, and this also needs to happen for the
'pages' allocation.

Fixes: 34310c442e17 ("btrfs: add io_uring command for encoded reads (ENCODED_READ ioctl)")
Signed-off-by: Miquel Sabaté Solà <mssola@mssola.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f1b56be6f8f4..dadf9bf30f08 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4651,7 +4651,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
 	struct extent_io_tree *io_tree = &inode->io_tree;
-	struct page **pages;
+	struct page **pages = NULL;
 	struct btrfs_uring_priv *priv = NULL;
 	unsigned long nr_pages;
 	int ret;
@@ -4709,6 +4709,11 @@ out_fail:
 	btrfs_unlock_extent(io_tree, start, lockend, &cached_state);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	kfree(priv);
+	for (int i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			__free_page(pages[i]);
+	}
+	kfree(pages);
 	return ret;
 }
 
-- 
cgit v1.2.3


From a7526533128fd3210e15cee1e14c7a0fe97087c1 Mon Sep 17 00:00:00 2001
From: Miquel Sabaté Solà <mssola@mssola.com>
Date: Mon, 16 Feb 2026 01:22:52 +0100
Subject: btrfs: don't commit the super block when unmounting a shutdown
 filesystem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When unmounting a filesystem we will try, among many other things, to
commit the super block. On a filesystem that was shutdown, though, this
will always fail with -EROFS as writes are forbidden on this context;
and an error will be reported.

Don't commit the super block on this situation, which should be fine as
the filesystem is frozen before shutdown and, therefore, it should be at
a consistent state.

Signed-off-by: Miquel Sabaté Solà <mssola@mssola.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 028ba86bcf73..6a38489a4e18 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4397,9 +4397,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 		 */
 		btrfs_flush_workqueue(fs_info->delayed_workers);
 
-		ret = btrfs_commit_super(fs_info);
-		if (ret)
-			btrfs_err(fs_info, "commit super ret %d", ret);
+		/*
+		 * If the filesystem is shutdown, then an attempt to commit the
+		 * super block (or any write) will just fail. Since we freeze
+		 * the filesystem before shutting it down, the filesystem is in
+		 * a consistent state and we don't need to commit super blocks.
+		 */
+		if (!btrfs_is_shutdown(fs_info)) {
+			ret = btrfs_commit_super(fs_info);
+			if (ret)
+				btrfs_err(fs_info, "commit super block returned %d", ret);
+		}
 	}
 
 	kthread_stop(fs_info->transaction_kthread);
-- 
cgit v1.2.3


From 3cf0f35779d364cf2003c617bb7f3f3e41023372 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 18:25:42 +0000
Subject: btrfs: fix error message order of parameters in
 btrfs_delete_delayed_dir_index()

Fix the error message in btrfs_delete_delayed_dir_index() if
__btrfs_add_delayed_item() fails: the message says root, inode, index,
error, but we're actually passing index, root, inode, error.

Fixes: adc1ef55dc04 ("btrfs: add details to error messages at btrfs_delete_delayed_dir_index()")
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 1739a0b29c49..2746841c167d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1657,7 +1657,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	if (unlikely(ret)) {
 		btrfs_err(trans->fs_info,
 "failed to add delayed dir index item, root: %llu, inode: %llu, index: %llu, error: %d",
-			  index, btrfs_root_id(node->root), node->inode_id, ret);
+			  btrfs_root_id(node->root), node->inode_id, index, ret);
 		btrfs_delayed_item_release_metadata(dir->root, item);
 		btrfs_release_delayed_item(item);
 	}
-- 
cgit v1.2.3


From 511dc8912ae3e929c1a182f5e6b2326516fd42a0 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 10:21:44 +0000
Subject: btrfs: fix incorrect key offset in error message in
 check_dev_extent_item()

Fix the error message in check_dev_extent_item(), when an overlapping
stripe is encountered. For dev extents, objectid is the disk number and
offset the physical address, so prev_key->objectid should actually be
prev_key->offset.

(I can't take any credit for this one - this was discovered by Chris and
his friend Claude.)

Reported-by: Chris Mason <clm@fb.com>
Fixes: 008e2512dc56 ("btrfs: tree-checker: add dev extent item checks")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 452394b34d01..9774779f060b 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1921,7 +1921,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf,
 		if (unlikely(prev_key->offset + prev_len > key->offset)) {
 			generic_err(leaf, slot,
 		"dev extent overlap, prev offset %llu len %llu current offset %llu",
-				    prev_key->objectid, prev_len, key->offset);
+				    prev_key->offset, prev_len, key->offset);
 			return -EUCLEAN;
 		}
 	}
-- 
cgit v1.2.3


From a10172780526c2002e062102ad4f2aabac495889 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 14:39:46 +0000
Subject: btrfs: fix objectid value in error message in check_extent_data_ref()

Fix a copy-paste error in check_extent_data_ref(): we're printing root
as in the message above, we should be printing objectid.

Fixes: f333a3c7e832 ("btrfs: tree-checker: validate dref root and objectid")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 9774779f060b..ac4c4573ee39 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1740,7 +1740,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
 			     objectid > BTRFS_LAST_FREE_OBJECTID)) {
 			extent_err(leaf, slot,
 				   "invalid extent data backref objectid value %llu",
-				   root);
+				   objectid);
 			return -EUCLEAN;
 		}
 		if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
-- 
cgit v1.2.3


From 44e2fda66427a0442d8d2c0e6443256fb458ab6b Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:46:13 +0000
Subject: btrfs: fix warning in scrub_verify_one_metadata()

Commit b471965fdb2d ("btrfs: fix replace/scrub failure with
metadata_uuid") fixed the comparison in scrub_verify_one_metadata() to
use metadata_uuid rather than fsid, but left the warning as it was. Fix
it so it matches what we're doing.

Fixes: b471965fdb2d ("btrfs: fix replace/scrub failure with metadata_uuid")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2a64e2d50ced..052d83feea9a 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -744,7 +744,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		btrfs_warn_rl(fs_info,
 	      "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU",
 			      logical, stripe->mirror_num,
-			      header->fsid, fs_info->fs_devices->fsid);
+			      header->fsid, fs_info->fs_devices->metadata_uuid);
 		return;
 	}
 	if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid,
-- 
cgit v1.2.3


From 1c7e9111f4e6d6d42bc47759c9af1ef91f03ac2c Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:32:39 +0000
Subject: btrfs: print correct subvol num if active swapfile prevents deletion

Fix the error message in btrfs_delete_subvolume() if we can't delete a
subvolume because it has an active swapfile: we were printing the number
of the parent rather than the target.

Fixes: 60021bd754c6 ("btrfs: prevent subvol with swapfile from being deleted")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ade590707793..d28d55beaacd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4779,7 +4779,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
 		spin_unlock(&dest->root_item_lock);
 		btrfs_warn(fs_info,
 			   "attempt to delete subvolume %llu with active swapfile",
-			   btrfs_root_id(root));
+			   btrfs_root_id(dest));
 		ret = -EPERM;
 		goto out_up_write;
 	}
-- 
cgit v1.2.3


From 587bb33b10bda645a1028c1737ad3992b3d7cf61 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:46:41 +0000
Subject: btrfs: fix compat mask in error messages in btrfs_check_features()

Commit d7f67ac9a928 ("btrfs: relax block-group-tree feature dependency
checks") introduced a regression when it comes to handling unsupported
incompat or compat_ro flags. Beforehand we only printed the flags that
we didn't recognize, afterwards we printed them all, which is less
useful. Fix the error handling so it behaves like it used to.

Fixes: d7f67ac9a928 ("btrfs: relax block-group-tree feature dependency checks")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6a38489a4e18..49987334dd15 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3187,7 +3187,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
 		btrfs_err(fs_info,
 		"cannot mount because of unknown incompat features (0x%llx)",
-		    incompat);
+		    incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP);
 		return -EINVAL;
 	}
 
@@ -3219,7 +3219,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	if (compat_ro_unsupp && is_rw_mount) {
 		btrfs_err(fs_info,
 	"cannot mount read-write because of unknown compat_ro features (0x%llx)",
-		       compat_ro);
+		       compat_ro_unsupp);
 		return -EINVAL;
 	}
 
@@ -3232,7 +3232,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
 		btrfs_err(fs_info,
 "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
-			  compat_ro);
+			  compat_ro_unsupp);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From f15fb3d41543244d1179f423da4a4832a55bc050 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Fri, 20 Feb 2026 12:53:17 +0000
Subject: btrfs: fix chunk map leak in btrfs_map_block() after
 btrfs_chunk_map_num_copies()

Fix a chunk map leak in btrfs_map_block(): if we return early with -EINVAL,
we're not freeing the chunk map that we've just looked up.

Fixes: 0ae653fbec2b ("btrfs: reduce chunk_map lookups in btrfs_map_block()")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 50f7aae70418..b8cbd3ecb94d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6921,8 +6921,10 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	}
 
 	num_copies = btrfs_chunk_map_num_copies(map);
-	if (io_geom.mirror_num > num_copies)
-		return -EINVAL;
+	if (io_geom.mirror_num > num_copies) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	map_offset = logical - map->start;
 	io_geom.raid56_full_stripe_start = (u64)-1;
-- 
cgit v1.2.3


From 54b9395b186a60d1655186c561a505c590654395 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Fri, 20 Feb 2026 12:52:56 +0000
Subject: btrfs: fix chunk map leak in btrfs_map_block() after
 btrfs_translate_remap()

If the call to btrfs_translate_remap() in btrfs_map_block() returns an
error code, we were leaking the chunk map. Fix it by jumping to out
rather than returning directly.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125830.2352988-1-clm@meta.com/
Fixes: 18ba64992871 ("btrfs: redirect I/O for remapped block groups")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b8cbd3ecb94d..3c37c5d2267b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6907,7 +6907,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 
 		ret = btrfs_translate_remap(fs_info, &new_logical, length);
 		if (ret)
-			return ret;
+			goto out;
 
 		if (new_logical != logical) {
 			btrfs_free_chunk_map(map);
-- 
cgit v1.2.3


From 7885ca40c305c64ffa444e1fc55edd6acb7a6e5b Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 14:16:02 +0000
Subject: btrfs: fix transaction handle leaks in
 btrfs_last_identity_remap_gone()

btrfs_abort_transaction(), unlike btrfs_commit_transaction(), doesn't
also free the transaction handle. Fix the instances in
btrfs_last_identity_remap_gone() where we're also leaking the
transaction on abort.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125129.2245240-1-clm@meta.com/
Fixes: 979e1dc3d69e ("btrfs: handle deletions from remapped block group")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fcd0a2ba3554..2119dddd6f8e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4723,6 +4723,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = btrfs_remove_dev_extents(trans, chunk_map);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 
@@ -4732,6 +4733,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 		if (unlikely(ret)) {
 			mutex_unlock(&trans->fs_info->chunk_mutex);
 			btrfs_abort_transaction(trans, ret);
+			btrfs_end_transaction(trans);
 			return ret;
 		}
 	}
@@ -4750,6 +4752,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map,
 	ret = remove_chunk_stripes(trans, chunk_map, path);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
+		btrfs_end_transaction(trans);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From f8db8009ea65297dba7786668d4561f6dbd99678 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 14:30:59 +0000
Subject: btrfs: check block group lookup in remove_range_from_remap_tree()

Add a check in remove_range_from_remap_tree() after we call
btrfs_lookup_block_group(), to check if it is NULL. This shouldn't
happen, but if it does we at least get an error rather than a segfault.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125125129.2245240-1-clm@meta.com/
Fixes: 979e1dc3d69e ("btrfs: handle deletions from remapped block group")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2119dddd6f8e..cdb53c0b26ec 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -5985,6 +5985,9 @@ static int remove_range_from_remap_tree(struct btrfs_trans_handle *trans,
 		struct btrfs_block_group *dest_bg;
 
 		dest_bg = btrfs_lookup_block_group(fs_info, new_addr);
+		if (unlikely(!dest_bg))
+			return -EUCLEAN;
+
 		adjust_block_group_remap_bytes(trans, dest_bg, -overlap_length);
 		btrfs_put_block_group(dest_bg);
 		ret = btrfs_add_to_free_space_tree(trans,
-- 
cgit v1.2.3


From 22f8bcec5aeb05104b3eaa950cb5a345e95f0aa8 Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 3 Feb 2026 08:55:07 +0800
Subject: HID: intel-ish-hid: ipc: Add Nova Lake-H/S PCI device IDs

Add device IDs of Nova Lake-H and Nova Lake-S into ishtp support list.

Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ipc/hw-ish.h  |  2 ++
 drivers/hid/intel-ish-hid/ipc/pci-ish.c | 12 ++++++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index fa5d68c36313..27389971b96c 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -39,6 +39,8 @@
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_H		0xE345
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P		0xE445
 #define PCI_DEVICE_ID_INTEL_ISH_WCL		0x4D45
+#define PCI_DEVICE_ID_INTEL_ISH_NVL_H		0xD354
+#define PCI_DEVICE_ID_INTEL_ISH_NVL_S		0x6E78
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 1612e8cb23f0..ed3405c05e73 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -28,11 +28,15 @@ enum ishtp_driver_data_index {
 	ISHTP_DRIVER_DATA_LNL_M,
 	ISHTP_DRIVER_DATA_PTL,
 	ISHTP_DRIVER_DATA_WCL,
+	ISHTP_DRIVER_DATA_NVL_H,
+	ISHTP_DRIVER_DATA_NVL_S,
 };
 
 #define ISH_FW_GEN_LNL_M "lnlm"
 #define ISH_FW_GEN_PTL "ptl"
 #define ISH_FW_GEN_WCL "wcl"
+#define ISH_FW_GEN_NVL_H "nvlh"
+#define ISH_FW_GEN_NVL_S "nvls"
 
 #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin"
 #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin"
@@ -47,6 +51,12 @@ static struct ishtp_driver_data ishtp_driver_data[] = {
 	[ISHTP_DRIVER_DATA_WCL] = {
 		.fw_generation = ISH_FW_GEN_WCL,
 	},
+	[ISHTP_DRIVER_DATA_NVL_H] = {
+		.fw_generation = ISH_FW_GEN_NVL_H,
+	},
+	[ISHTP_DRIVER_DATA_NVL_S] = {
+		.fw_generation = ISH_FW_GEN_NVL_S,
+	},
 };
 
 static const struct pci_device_id ish_pci_tbl[] = {
@@ -76,6 +86,8 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)},
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)},
 	{PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)},
+	{PCI_DEVICE_DATA(INTEL, ISH_NVL_H, ISHTP_DRIVER_DATA_NVL_H)},
+	{PCI_DEVICE_DATA(INTEL, ISH_NVL_S, ISHTP_DRIVER_DATA_NVL_S)},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
-- 
cgit v1.2.3


From 7c698de0dc5daa1e1a5fd1f0c6aa1b6bb2f5d867 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 24 Feb 2026 10:00:02 +0100
Subject: HID: apple: Add EPOMAKER TH87 to the non-apple keyboards list

EPOMAKER TH87 has the very same ID as Apple Aluminum keyboard
(05ac:024f) although it doesn't work as expected in compatible way.

Put three entries to the non-apple keyboards list to exclude this
device: one for BT ("TH87"), one for USB ("HFD Epomaker TH87") and one
for dongle ("2.4G Wireless Receiver").

Link: https://bugzilla.suse.com/show_bug.cgi?id=1258455
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-apple.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 894adc23367b..9dcb252c5d6c 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -365,6 +365,9 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = {
 	{ "A3R" },
 	{ "hfd.cn" },
 	{ "WKB603" },
+	{ "TH87" },			/* EPOMAKER TH87 BT mode */
+	{ "HFD Epomaker TH87" },	/* EPOMAKER TH87 USB mode */
+	{ "2.4G Wireless Receiver" },	/* EPOMAKER TH87 dongle */
 };
 
 static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
-- 
cgit v1.2.3


From 8f153eb745463b0715f1aad41e765cd83e9da8c0 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 29 Jan 2026 10:24:05 +0800
Subject: wifi: ath12k: use correct pdev id when requesting firmware stats

To get firmware statistics, currently ar->pdev->pdev_id is passed as an
argument to ath12k_mac_get_fw_stats() in ath12k_mac_op_sta_statistics().
For single pdev device like WCN7850, its value is 0 which represents the
SoC pdev id. As a result, WCN7850 firmware sends the same reply to host
twice, which further results in memory leak:

  unreferenced object 0xffff88812e286000 (size 192):
  comm "softirq", pid 0, jiffies 4294981997
  hex dump (first 32 bytes):
    10 a5 40 11 81 88 ff ff 10 a5 40 11 81 88 ff ff  ..@.......@.....
    00 00 00 00 00 00 00 00 80 ff ff ff 33 05 00 00  ............3...
  backtrace (crc cecc8c82):
    __kmalloc_cache_noprof
    ath12k_wmi_tlv_fw_stats_parse
    ath12k_wmi_tlv_iter
    ath12k_wmi_op_rx
    ath12k_htc_rx_completion_handler
    ath12k_ce_per_engine_service
    ath12k_pci_ce_workqueue
    process_one_work
    bh_worker
    tasklet_action
    handle_softirqs

Detailed explanation is:

  1. ath12k_mac_get_fw_stats() called in ath12k_mac_op_sta_statistics() to
     get vdev statistics, making the caller thread wait.
  2. firmware sends the first reply, ath12k_wmi_tlv_fw_stats_data_parse()
     allocates buffers to cache necessary information. Following that, in
     ath12k_wmi_fw_stats_process() if events of all started vdev haved been
     received, is_end flag is set hence the waiting thread gets waken up by
     the ar->fw_stats_done/->fw_stats_complete signals.
  3. ath12k_mac_get_fw_stats() wakes up and returns successfully.
     ath12k_mac_op_sta_statistics() saves required parameters and calls
     ath12k_fw_stats_reset() to free buffers allocated earlier.
  4. firmware sends the second reply. As usual, buffers are allocated and
     attached to the ar->fw_stats.vdevs list. Note this time there is no
     thread waiting, therefore no chance to free those buffers.
  5. ath12k module gets unloaded. If there has been no more firmware
     statistics request made since step 4, or if the request fails (see
     the example in the following patch), there is no chance to call
     ath12k_fw_stats_reset(). Consequently those buffers leak.

Actually for single pdev device, using SoC pdev id in
ath12k_mac_op_sta_statistics() is wrong, because the purpose is to get
statistics of a specific station, which is mapped to a specific pdev. That
said, the id of actual individual pdev should be fetched and used instead.
The helper ath12k_mac_get_target_pdev_id() serves for this purpose, hence
use it to fix this issue. Note it also works for other devices as well due
to the single_pdev_only check inside.

The same applies to ath12k_mac_op_get_txpower() and
ath12k_mac_op_link_sta_statistics() as well.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00302-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.115823.3

Fixes: 79e7b04b5388 ("wifi: ath12k: report station mode signal strength")
Fixes: e92c658b056b ("wifi: ath12k: add get_txpower mac ops")
Fixes: ebebe66ec208 ("wifi: ath12k: fill link station statistics for MLO")
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260129-ath12k-fw-stats-fixes-v1-1-55d66064f4d5@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 68431a0e128e..5287fa2f66e5 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5430,7 +5430,7 @@ int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw,
 					 ar->last_tx_power_update))
 		goto send_tx_power;
 
-	params.pdev_id = ar->pdev->pdev_id;
+	params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 	params.vdev_id = arvif->vdev_id;
 	params.stats_id = WMI_REQUEST_PDEV_STAT;
 	ret = ath12k_mac_get_fw_stats(ar, &params);
@@ -13452,7 +13452,7 @@ void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	/* TODO: Use real NF instead of default one. */
 	signal = rate_info.rssi_comb;
 
-	params.pdev_id = ar->pdev->pdev_id;
+	params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 	params.vdev_id = 0;
 	params.stats_id = WMI_REQUEST_VDEV_STAT;
 
@@ -13580,7 +13580,7 @@ void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw,
 	spin_unlock_bh(&ar->ab->dp->dp_lock);
 
 	if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA) {
-		params.pdev_id = ar->pdev->pdev_id;
+		params.pdev_id = ath12k_mac_get_target_pdev_id(ar);
 		params.vdev_id = 0;
 		params.stats_id = WMI_REQUEST_VDEV_STAT;
 
-- 
cgit v1.2.3


From 7259b1a0e54c2d3051ac8f1eb01de121b11118ea Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 29 Jan 2026 10:24:06 +0800
Subject: wifi: ath12k: fix station lookup failure when disconnecting from AP

In ath12k_wmi_tlv_fw_stats_data_parse() and
ath12k_wmi_tlv_rssi_chain_parse(), the driver uses
ieee80211_find_sta_by_ifaddr() to look up the station associated with the
incoming firmware statistics. This works under normal conditions but fails
during AP disconnection, resulting in log messages like:

 wlan0: deauthenticating from xxxxxx by local choice (Reason: 3=DEAUTH_LEAVING)
 wlan0: moving STA xxxxxx to state 3
 wlan0: moving STA xxxxxx to state 2
 wlan0: moving STA xxxxxx to state 1
 ath12k_pci 0000:02:00.0: not found station bssid xxxxxx for vdev stat
 ath12k_pci 0000:02:00.0: not found station of bssid xxxxxx for rssi chain
 ath12k_pci 0000:02:00.0: failed to pull fw stats: -71
 ath12k_pci 0000:02:00.0: time out while waiting for get fw stats
 wlan0: Removed STA xxxxxx
 wlan0: Destroyed STA xxxxxx

The failure happens because the station has already been removed from
ieee80211_local::sta_hash by the time firmware statistics are requested
through drv_sta_statistics().

Switch the lookup to ath12k_link_sta_find_by_addr(), which searches the
driver's link station hash table that still has the station recorded
at that time.  This also implicitly fixes another issue: the current code
always uses deflink regardless of which link the statistics belong to,
which is incorrect in MLO scenarios. The new helper returns the correct
link station.

Additionally, raise the log level on lookup failures. With the updated
helper, such failures should no longer occur under normal conditions.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00302-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.115823.3

Fixes: 79e7b04b5388 ("wifi: ath12k: report station mode signal strength")
Fixes: 6af5bc381b36 ("wifi: ath12k: report station mode per-chain signal strength")
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260129-ath12k-fw-stats-fixes-v1-2-55d66064f4d5@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 36 +++++++++++++----------------------
 1 file changed, 13 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 7617fc3a2479..404f031a3c87 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8241,8 +8241,6 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 	struct ath12k_fw_stats *stats = parse->stats;
 	struct ath12k *ar;
 	struct ath12k_link_vif *arvif;
-	struct ieee80211_sta *sta;
-	struct ath12k_sta *ahsta;
 	struct ath12k_link_sta *arsta;
 	int i, ret = 0;
 	const void *data = ptr;
@@ -8278,21 +8276,19 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 
 		arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id));
 		if (arvif) {
-			sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar),
-							   arvif->bssid,
-							   NULL);
-			if (sta) {
-				ahsta = ath12k_sta_to_ahsta(sta);
-				arsta = &ahsta->deflink;
+			spin_lock_bh(&ab->base_lock);
+			arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid);
+			if (arsta) {
 				arsta->rssi_beacon = le32_to_cpu(src->beacon_snr);
 				ath12k_dbg(ab, ATH12K_DBG_WMI,
 					   "wmi stats vdev id %d snr %d\n",
 					   src->vdev_id, src->beacon_snr);
 			} else {
-				ath12k_dbg(ab, ATH12K_DBG_WMI,
-					   "not found station bssid %pM for vdev stat\n",
-					   arvif->bssid);
+				ath12k_warn(ab,
+					    "not found link sta with bssid %pM for vdev stat\n",
+					    arvif->bssid);
 			}
+			spin_unlock_bh(&ab->base_lock);
 		}
 
 		data += sizeof(*src);
@@ -8363,8 +8359,6 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab,
 	struct ath12k_fw_stats *stats = parse->stats;
 	struct ath12k_link_vif *arvif;
 	struct ath12k_link_sta *arsta;
-	struct ieee80211_sta *sta;
-	struct ath12k_sta *ahsta;
 	struct ath12k *ar;
 	int vdev_id;
 	int j;
@@ -8400,19 +8394,15 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab,
 		   "stats bssid %pM vif %p\n",
 		   arvif->bssid, arvif->ahvif->vif);
 
-	sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar),
-					   arvif->bssid,
-					   NULL);
-	if (!sta) {
-		ath12k_dbg(ab, ATH12K_DBG_WMI,
-			   "not found station of bssid %pM for rssi chain\n",
-			   arvif->bssid);
+	guard(spinlock_bh)(&ab->base_lock);
+	arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid);
+	if (!arsta) {
+		ath12k_warn(ab,
+			    "not found link sta with bssid %pM for rssi chain\n",
+			    arvif->bssid);
 		return -EPROTO;
 	}
 
-	ahsta = ath12k_sta_to_ahsta(sta);
-	arsta = &ahsta->deflink;
-
 	BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) >
 		     ARRAY_SIZE(stats_rssi->rssi_avg_beacon));
 
-- 
cgit v1.2.3


From 3540cc453f5679d8c4d5ccc9834a1f5f8184af3a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:43:48 +0100
Subject: ALSA: usb-audio: Drop superfluous kernel-doc markers

We don't process USB-audio driver code for kernel-doc, and the "/**"
marker leads to warnings with W=1 builds.  Drop the superfluous
markers.

Link: https://patch.msgid.link/20260226154414.1081568-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_s1810c.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/sound/usb/mixer_s1810c.c b/sound/usb/mixer_s1810c.c
index 473cb29efa7f..7eac7d1bce64 100644
--- a/sound/usb/mixer_s1810c.c
+++ b/sound/usb/mixer_s1810c.c
@@ -71,7 +71,7 @@
  *   * e I guess the same as with mixer
  *
  */
-/** struct s1810c_ctl_packet - basic vendor request
+/* struct s1810c_ctl_packet - basic vendor request
  * @selector: device/mixer/output
  * @b: request-dependant field b
  * @tag: fixed value identifying type of request
@@ -94,14 +94,14 @@ struct s1810c_ctl_packet {
 	__le32 e;
 };
 
-/** selectors for CMD request
+/* selectors for CMD request
  */
 #define SC1810C_SEL_DEVICE 0
 #define SC1810C_SEL_MIXER 0x64
 #define SC1810C_SEL_OUTPUT 0x65
 
 
-/** control ids */
+/* control ids */
 #define SC1810C_CTL_LINE_SW	0
 #define SC1810C_CTL_MUTE_SW	1
 #define SC1824C_CTL_MONO_SW	2
@@ -127,7 +127,7 @@ struct s1810c_ctl_packet {
 #define SC1810C_GET_STATE_TAG	SC1810C_SET_STATE_TAG
 #define SC1810C_GET_STATE_LEN	SC1810C_SET_STATE_LEN
 
-/** Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB).
+/* Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB).
  * raw_level = 2^24 * 10^(db_level / 20), thus
  * -3dB = 0xb53bf0 (technically, half-power -3.01...dB would be 0xb504f3)
  * -96dB = 0x109
@@ -145,7 +145,7 @@ struct s1810c_ctl_packet {
 #define MIXER_LEVEL_N3DB 0xb53bf0
 #define MIXER_LEVEL_0DB 0x1000000
 
-/**
+/*
  * This packet includes mixer volumes and
  * various other fields, it's an extended
  * version of ctl_packet, with a and b
@@ -155,7 +155,7 @@ struct s1810c_state_packet {
 	__le32 fields[63];
 };
 
-/** indices into s1810c_state_packet.fields[]
+/* indices into s1810c_state_packet.fields[]
  */
 #define SC1810C_STATE_TAG_IDX	2
 #define SC1810C_STATE_LEN_IDX	3
-- 
cgit v1.2.3


From 1d6452a0ce78cd3f4e48943b5ba21d273a658298 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:43:49 +0100
Subject: ALSA: usb: qcom: Correct parameter comment for
 uaudio_transfer_buffer_setup()

At fixing the memory leak of xfer buffer, we forgot to update the
corresponding comment, too.  This resulted in a kernel-doc warning
with W=1.  Let's correct it.

Fixes: 5c7ef5001292 ("ALSA: qc_audio_offload: avoid leaking xfer_buf allocation")
Link: https://patch.msgid.link/20260226154414.1081568-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/qcom/qc_audio_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 01e6063c2207..510b68cced33 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -1007,7 +1007,7 @@ put_suspend:
 /**
  * uaudio_transfer_buffer_setup() - fetch and populate xfer buffer params
  * @subs: usb substream
- * @xfer_buf: xfer buf to be allocated
+ * @xfer_buf_cpu: xfer buf to be allocated
  * @xfer_buf_len: size of allocation
  * @mem_info: QMI response info
  *
-- 
cgit v1.2.3


From dc9786a06d53291a5af824e854dd0769b1a97dbe Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:54:45 +0100
Subject: ALSA: us144mkii: Drop kernel-doc markers

We don't process this driver code for kernel-doc, and the "/**" marker
leads to warnings with W=1 builds.  Drop the superfluous markers, and
also fix the invalid mark up, too.

Link: https://patch.msgid.link/20260226155456.1092186-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/us144mkii.c          | 14 ++++++------
 sound/usb/usx2y/us144mkii_capture.c  | 12 +++++------
 sound/usb/usx2y/us144mkii_controls.c | 42 ++++++++++++++++++------------------
 sound/usb/usx2y/us144mkii_midi.c     | 22 +++++++++----------
 sound/usb/usx2y/us144mkii_playback.c | 10 ++++-----
 5 files changed, 50 insertions(+), 50 deletions(-)

diff --git a/sound/usb/usx2y/us144mkii.c b/sound/usb/usx2y/us144mkii.c
index bc71968df8e2..0cf4fa74e210 100644
--- a/sound/usb/usx2y/us144mkii.c
+++ b/sound/usb/usx2y/us144mkii.c
@@ -10,8 +10,8 @@ MODULE_AUTHOR("Šerif Rami <ramiserifpersia@gmail.com>");
 MODULE_DESCRIPTION("ALSA Driver for TASCAM US-144MKII");
 MODULE_LICENSE("GPL");
 
-/**
- * @brief Module parameters for ALSA card instantiation.
+/*
+ * Module parameters for ALSA card instantiation.
  *
  * These parameters allow users to configure how the ALSA sound card
  * for the TASCAM US-144MKII is instantiated.
@@ -269,7 +269,7 @@ void tascam_stop_work_handler(struct work_struct *work)
 	atomic_set(&tascam->active_urbs, 0);
 }
 
-/**
+/*
  * tascam_card_private_free() - Frees private data associated with the sound
  * card.
  * @card: Pointer to the ALSA sound card instance.
@@ -291,7 +291,7 @@ static void tascam_card_private_free(struct snd_card *card)
 	}
 }
 
-/**
+/*
  * tascam_suspend() - Handles device suspension.
  * @intf: The USB interface being suspended.
  * @message: Power management message.
@@ -332,7 +332,7 @@ static int tascam_suspend(struct usb_interface *intf, pm_message_t message)
 	return 0;
 }
 
-/**
+/*
  * tascam_resume() - Handles device resumption from suspend.
  * @intf: The USB interface being resumed.
  *
@@ -390,7 +390,7 @@ static void tascam_error_timer(struct timer_list *t)
 		schedule_work(&tascam->midi_out_work);
 }
 
-/**
+/*
  * tascam_probe() - Probes for the TASCAM US-144MKII device.
  * @intf: The USB interface being probed.
  * @usb_id: The USB device ID.
@@ -565,7 +565,7 @@ free_card:
 	return err;
 }
 
-/**
+/*
  * tascam_disconnect() - Disconnects the TASCAM US-144MKII device.
  * @intf: The USB interface being disconnected.
  *
diff --git a/sound/usb/usx2y/us144mkii_capture.c b/sound/usb/usx2y/us144mkii_capture.c
index 00188ff6cd51..af120bf62173 100644
--- a/sound/usb/usx2y/us144mkii_capture.c
+++ b/sound/usb/usx2y/us144mkii_capture.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_capture_open() - Opens the PCM capture substream.
  * @substream: The ALSA PCM substream to open.
  *
@@ -23,7 +23,7 @@ static int tascam_capture_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_close() - Closes the PCM capture substream.
  * @substream: The ALSA PCM substream to close.
  *
@@ -41,7 +41,7 @@ static int tascam_capture_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_prepare() - Prepares the PCM capture substream for use.
  * @substream: The ALSA PCM substream to prepare.
  *
@@ -62,7 +62,7 @@ static int tascam_capture_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_pointer() - Returns the current capture pointer position.
  * @substream: The ALSA PCM substream.
  *
@@ -91,7 +91,7 @@ tascam_capture_pointer(struct snd_pcm_substream *substream)
 	return do_div(pos, runtime->buffer_size);
 }
 
-/**
+/*
  * tascam_capture_ops - ALSA PCM operations for capture.
  *
  * This structure defines the callback functions for capture stream operations,
@@ -109,7 +109,7 @@ const struct snd_pcm_ops tascam_capture_ops = {
 	.pointer = tascam_capture_pointer,
 };
 
-/**
+/*
  * decode_tascam_capture_block() - Decodes a raw 512-byte block from the device.
  * @src_block: Pointer to the 512-byte raw source block.
  * @dst_block: Pointer to the destination buffer for decoded audio frames.
diff --git a/sound/usb/usx2y/us144mkii_controls.c b/sound/usb/usx2y/us144mkii_controls.c
index 62055fb8e7ba..81ded11e3709 100644
--- a/sound/usb/usx2y/us144mkii_controls.c
+++ b/sound/usb/usx2y/us144mkii_controls.c
@@ -3,8 +3,8 @@
 
 #include "us144mkii.h"
 
-/**
- * @brief Text descriptions for playback output source options.
+/*
+ * Text descriptions for playback output source options.
  *
  * Used by ALSA kcontrol elements to provide user-friendly names for
  * the playback routing options (e.g., "Playback 1-2", "Playback 3-4").
@@ -12,15 +12,15 @@
 static const char *const playback_source_texts[] = { "Playback 1-2",
 						     "Playback 3-4" };
 
-/**
- * @brief Text descriptions for capture input source options.
+/*
+ * Text descriptions for capture input source options.
  *
  * Used by ALSA kcontrol elements to provide user-friendly names for
  * the capture routing options (e.g., "Analog In", "Digital In").
  */
 static const char *const capture_source_texts[] = { "Analog In", "Digital In" };
 
-/**
+/*
  * tascam_playback_source_info() - ALSA control info callback for playback
  * source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -38,7 +38,7 @@ static int tascam_playback_source_info(struct snd_kcontrol *kcontrol,
 	return snd_ctl_enum_info(uinfo, 1, 2, playback_source_texts);
 }
 
-/**
+/*
  * tascam_line_out_get() - ALSA control get callback for Line Outputs Source.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure to fill.
@@ -60,7 +60,7 @@ static int tascam_line_out_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_line_out_put() - ALSA control put callback for Line Outputs Source.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure containing the new value.
@@ -89,7 +89,7 @@ static int tascam_line_out_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_line_out_control - ALSA kcontrol definition for Line Outputs Source.
  *
  * This defines a new ALSA mixer control named "Line OUTPUTS Source" that allows
@@ -106,7 +106,7 @@ static const struct snd_kcontrol_new tascam_line_out_control = {
 	.put = tascam_line_out_put,
 };
 
-/**
+/*
  * tascam_digital_out_get() - ALSA control get callback for Digital Outputs
  * Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -129,7 +129,7 @@ static int tascam_digital_out_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_digital_out_put() - ALSA control put callback for Digital Outputs
  * Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -159,7 +159,7 @@ static int tascam_digital_out_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_digital_out_control - ALSA kcontrol definition for Digital Outputs
  * Source.
  *
@@ -177,7 +177,7 @@ static const struct snd_kcontrol_new tascam_digital_out_control = {
 	.put = tascam_digital_out_put,
 };
 
-/**
+/*
  * tascam_capture_source_info() - ALSA control info callback for capture source.
  * @kcontrol: The ALSA kcontrol instance.
  * @uinfo: The ALSA control element info structure to fill.
@@ -194,7 +194,7 @@ static int tascam_capture_source_info(struct snd_kcontrol *kcontrol,
 	return snd_ctl_enum_info(uinfo, 1, 2, capture_source_texts);
 }
 
-/**
+/*
  * tascam_capture_12_get() - ALSA control get callback for Capture channels 1
  * and 2 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -217,7 +217,7 @@ static int tascam_capture_12_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_12_put() - ALSA control put callback for Capture channels 1
  * and 2 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -247,7 +247,7 @@ static int tascam_capture_12_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_capture_12_control - ALSA kcontrol definition for Capture channels 1
  * and 2 Source.
  *
@@ -265,7 +265,7 @@ static const struct snd_kcontrol_new tascam_capture_12_control = {
 	.put = tascam_capture_12_put,
 };
 
-/**
+/*
  * tascam_capture_34_get() - ALSA control get callback for Capture channels 3
  * and 4 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -288,7 +288,7 @@ static int tascam_capture_34_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_capture_34_put() - ALSA control put callback for Capture channels 3
  * and 4 Source.
  * @kcontrol: The ALSA kcontrol instance.
@@ -318,7 +318,7 @@ static int tascam_capture_34_put(struct snd_kcontrol *kcontrol,
 	return changed;
 }
 
-/**
+/*
  * tascam_capture_34_control - ALSA kcontrol definition for Capture channels 3
  * and 4 Source.
  *
@@ -336,7 +336,7 @@ static const struct snd_kcontrol_new tascam_capture_34_control = {
 	.put = tascam_capture_34_put,
 };
 
-/**
+/*
  * tascam_samplerate_info() - ALSA control info callback for Sample Rate.
  * @kcontrol: The ALSA kcontrol instance.
  * @uinfo: The ALSA control element info structure to fill.
@@ -356,7 +356,7 @@ static int tascam_samplerate_info(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_samplerate_get() - ALSA control get callback for Sample Rate.
  * @kcontrol: The ALSA kcontrol instance.
  * @ucontrol: The ALSA control element value structure to fill.
@@ -400,7 +400,7 @@ static int tascam_samplerate_get(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-/**
+/*
  * tascam_samplerate_control - ALSA kcontrol definition for Sample Rate.
  *
  * This defines a new ALSA mixer control named "Sample Rate" that displays
diff --git a/sound/usb/usx2y/us144mkii_midi.c b/sound/usb/usx2y/us144mkii_midi.c
index ed2afec2a89a..4871797b1670 100644
--- a/sound/usb/usx2y/us144mkii_midi.c
+++ b/sound/usb/usx2y/us144mkii_midi.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_midi_in_work_handler() - Deferred work for processing MIDI input.
  * @work: The work_struct instance.
  *
@@ -75,7 +75,7 @@ out:
 	usb_put_urb(urb);
 }
 
-/**
+/*
  * tascam_midi_in_open() - Opens the MIDI input substream.
  * @substream: The ALSA rawmidi substream to open.
  *
@@ -92,7 +92,7 @@ static int tascam_midi_in_open(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_in_close() - Closes the MIDI input substream.
  * @substream: The ALSA rawmidi substream to close.
  *
@@ -103,7 +103,7 @@ static int tascam_midi_in_close(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_in_trigger() - Triggers MIDI input stream activity.
  * @substream: The ALSA rawmidi substream.
  * @up: Boolean indicating whether to start (1) or stop (0) the stream.
@@ -150,7 +150,7 @@ static void tascam_midi_in_trigger(struct snd_rawmidi_substream *substream,
 	}
 }
 
-/**
+/*
  * tascam_midi_in_ops - ALSA rawmidi operations for MIDI input.
  *
  * This structure defines the callback functions for MIDI input stream
@@ -205,7 +205,7 @@ out:
 	usb_put_urb(urb);
 }
 
-/**
+/*
  * tascam_midi_out_work_handler() - Deferred work for sending MIDI data
  * @work: The work_struct instance.
  *
@@ -282,7 +282,7 @@ static void tascam_midi_out_work_handler(struct work_struct *work)
 	}
 }
 
-/**
+/*
  * tascam_midi_out_open() - Opens the MIDI output substream.
  * @substream: The ALSA rawmidi substream to open.
  *
@@ -301,7 +301,7 @@ static int tascam_midi_out_open(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_out_close() - Closes the MIDI output substream.
  * @substream: The ALSA rawmidi substream to close.
  *
@@ -312,7 +312,7 @@ static int tascam_midi_out_close(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_midi_out_drain() - Drains the MIDI output stream.
  * @substream: The ALSA rawmidi substream.
  *
@@ -340,7 +340,7 @@ static void tascam_midi_out_drain(struct snd_rawmidi_substream *substream)
 	usb_kill_anchored_urbs(&tascam->midi_out_anchor);
 }
 
-/**
+/*
  * tascam_midi_out_trigger() - Triggers MIDI output stream activity.
  * @substream: The ALSA rawmidi substream.
  * @up: Boolean indicating whether to start (1) or stop (0) the stream.
@@ -361,7 +361,7 @@ static void tascam_midi_out_trigger(struct snd_rawmidi_substream *substream,
 	}
 }
 
-/**
+/*
  * tascam_midi_out_ops - ALSA rawmidi operations for MIDI output.
  *
  * This structure defines the callback functions for MIDI output stream
diff --git a/sound/usb/usx2y/us144mkii_playback.c b/sound/usb/usx2y/us144mkii_playback.c
index 0cb9699ec211..7efaca0a6489 100644
--- a/sound/usb/usx2y/us144mkii_playback.c
+++ b/sound/usb/usx2y/us144mkii_playback.c
@@ -3,7 +3,7 @@
 
 #include "us144mkii.h"
 
-/**
+/*
  * tascam_playback_open() - Opens the PCM playback substream.
  * @substream: The ALSA PCM substream to open.
  *
@@ -23,7 +23,7 @@ static int tascam_playback_open(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_close() - Closes the PCM playback substream.
  * @substream: The ALSA PCM substream to close.
  *
@@ -41,7 +41,7 @@ static int tascam_playback_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_prepare() - Prepares the PCM playback substream for use.
  * @substream: The ALSA PCM substream to prepare.
  *
@@ -108,7 +108,7 @@ static int tascam_playback_prepare(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-/**
+/*
  * tascam_playback_pointer() - Returns the current playback pointer position.
  * @substream: The ALSA PCM substream.
  *
@@ -137,7 +137,7 @@ tascam_playback_pointer(struct snd_pcm_substream *substream)
 	return do_div(pos, runtime->buffer_size);
 }
 
-/**
+/*
  * tascam_playback_ops - ALSA PCM operations for playback.
  *
  * This structure defines the callback functions for playback stream operations,
-- 
cgit v1.2.3


From ec3070f01fa30f2c5547d645dbb76174304bf0e4 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Thu, 8 Jan 2026 17:09:54 +0100
Subject: HID: multitouch: Keep latency normal on deactivate for reactivation
 gesture

Uniwill devices have a built in gesture in the touchpad to de- and
reactivate it by double taping the upper left corner. This gesture stops
working when latency is set to high, so this patch keeps the latency on
normal.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
[jkosina@suse.com: change bit from 24 to 25]
[jkosina@suse.com: update shortlog]
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-multitouch.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 8052b35bfd7d..b8a748bbf0fd 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -77,6 +77,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_ORIENTATION_INVERT	BIT(22)
 #define MT_QUIRK_APPLE_TOUCHBAR		BIT(23)
 #define MT_QUIRK_YOGABOOK9I		BIT(24)
+#define MT_QUIRK_KEEP_LATENCY_ON_CLOSE	BIT(25)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -214,6 +215,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_WIN_8_DISABLE_WAKEUP		0x0016
 #define MT_CLS_WIN_8_NO_STICKY_FINGERS		0x0017
 #define MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU	0x0018
+#define MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE	0x0019
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -335,6 +337,15 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_WIN8_PTP_BUTTONS,
 		.export_all_inputs = true },
+	{ .name = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_STICKY_FINGERS |
+			MT_QUIRK_WIN8_PTP_BUTTONS |
+			MT_QUIRK_KEEP_LATENCY_ON_CLOSE,
+		.export_all_inputs = true },
 
 	/*
 	 * vendor specific classes
@@ -855,7 +866,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			if ((cls->name == MT_CLS_WIN_8 ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU ||
-			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) &&
+			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP ||
+			     cls->name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE) &&
 				(field->application == HID_DG_TOUCHPAD ||
 				 field->application == HID_DG_TOUCHSCREEN))
 				app->quirks |= MT_QUIRK_CONFIDENCE;
@@ -1768,7 +1780,8 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	int ret;
 
 	if (td->is_haptic_touchpad && (td->mtclass.name == MT_CLS_WIN_8 ||
-	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT)) {
+	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
+	    td->mtclass.name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE)) {
 		if (hid_haptic_input_configured(hdev, td->haptic, hi) == 0)
 			td->is_haptic_touchpad = false;
 	} else {
@@ -2081,7 +2094,12 @@ static void mt_on_hid_hw_open(struct hid_device *hdev)
 
 static void mt_on_hid_hw_close(struct hid_device *hdev)
 {
-	mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
+	struct mt_device *td = hid_get_drvdata(hdev);
+
+	if (td->mtclass.quirks & MT_QUIRK_KEEP_LATENCY_ON_CLOSE)
+		mt_set_modes(hdev, HID_LATENCY_NORMAL, TOUCHPAD_REPORT_NONE);
+	else
+		mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
 }
 
 /*
@@ -2468,6 +2486,14 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_UNITEC,
 			USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) },
 
+	/* Uniwill touchpads */
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0255) },
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0274) },
+
 	/* VTL panels */
 	{ .driver_data = MT_CLS_VTL,
 		MT_USB_DEVICE(USB_VENDOR_ID_VTL,
-- 
cgit v1.2.3


From 021ca6b670bebebc409d43845efcfe8c11c1dd54 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 23 Feb 2026 22:33:22 +0900
Subject: mm/slab: pass __GFP_NOWARN to refill_sheaf() if fallback is available

When refill_sheaf() is called, failing to refill the sheaf doesn't
necessarily mean the allocation will fail because a fallback path
might be available and serve the allocation request.

Suppress spurious warnings by passing __GFP_NOWARN along with
__GFP_NOMEMALLOC whenever a fallback path is available.

When the caller is alloc_full_sheaf() or __pcs_replace_empty_main(),
the kernel always falls back to the slowpath (__slab_alloc_node()).
For __prefill_sheaf_pfmemalloc(), the fallback path is available
only when gfp_pfmemalloc_allowed() returns true.

Reported-and-tested-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Closes: https://lore.kernel.org/linux-mm/aZt2-oS9lkmwT7Ch@debian.local
Fixes: 1ce20c28eafd ("slab: handle pfmemalloc slabs properly with sheaves")
Link: https://lore.kernel.org/linux-mm/aZwSreGj9-HHdD-j@hyeyoo
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260223133322.16705-1-harry.yoo@oracle.com
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 862642c165ed..4ce24d9ee7e4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2822,7 +2822,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 	if (!sheaf)
 		return NULL;
 
-	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC)) {
+	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 		free_empty_sheaf(s, sheaf);
 		return NULL;
 	}
@@ -4575,7 +4575,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 
 	if (empty) {
-		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC)) {
+		if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
 			full = empty;
 		} else {
 			/*
@@ -4890,9 +4890,14 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_noprof);
 static int __prefill_sheaf_pfmemalloc(struct kmem_cache *s,
 				      struct slab_sheaf *sheaf, gfp_t gfp)
 {
-	int ret = 0;
+	gfp_t gfp_nomemalloc;
+	int ret;
+
+	gfp_nomemalloc = gfp | __GFP_NOMEMALLOC;
+	if (gfp_pfmemalloc_allowed(gfp))
+		gfp_nomemalloc |= __GFP_NOWARN;
 
-	ret = refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC);
+	ret = refill_sheaf(s, sheaf, gfp_nomemalloc);
 
 	if (likely(!ret || !gfp_pfmemalloc_allowed(gfp)))
 		return ret;
-- 
cgit v1.2.3


From f3ec502b6755a3bfb12c1c47025ef989ff9efc72 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 25 Feb 2026 08:34:07 -0800
Subject: mm/slab: mark alloc tags empty for sheaves allocated with
 __GFP_NO_OBJ_EXT

alloc_empty_sheaf() allocates sheaves from SLAB_KMALLOC caches using
__GFP_NO_OBJ_EXT to avoid recursion, however it does not mark their
allocation tags empty before freeing, which results in a warning when
CONFIG_MEM_ALLOC_PROFILING_DEBUG is set. Fix this by marking allocation
tags for such sheaves as empty.

The problem was technically introduced in commit 4c0a17e28340 but only
becomes possible to hit with commit 913ffd3a1bf5.

Fixes: 4c0a17e28340 ("slab: prevent recursive kmalloc() in alloc_empty_sheaf()")
Fixes: 913ffd3a1bf5 ("slab: handle kmalloc sheaves bootstrap")
Reported-by: David Wang <00107082@163.com>
Closes: https://lore.kernel.org/all/20260223155128.3849-1-00107082@163.com/
Analyzed-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Tested-by: David Wang <00107082@163.com>
Link: https://patch.msgid.link/20260225163407.2218712-1-surenb@google.com
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 include/linux/gfp_types.h |  2 ++
 mm/slab.h                 |  4 ++--
 mm/slub.c                 | 33 +++++++++++++++++++++++----------
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 814bb2892f99..6c75df30a281 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
diff --git a/mm/slab.h b/mm/slab.h
index 71c7261bf822..f6ef862b60ef 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -290,14 +290,14 @@ static inline void *nearest_obj(struct kmem_cache *cache,
 
 /* Determine object index from a given position */
 static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
-					  void *addr, void *obj)
+					  void *addr, const void *obj)
 {
 	return reciprocal_divide(kasan_reset_tag(obj) - addr,
 				 cache->reciprocal_size);
 }
 
 static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
+					const struct slab *slab, const void *obj)
 {
 	if (is_kfence_address(obj))
 		return 0;
diff --git a/mm/slub.c b/mm/slub.c
index 4ce24d9ee7e4..52f021711744 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2041,18 +2041,18 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node,
 
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
+static inline void mark_obj_codetag_empty(const void *obj)
 {
-	struct slab *obj_exts_slab;
+	struct slab *obj_slab;
 	unsigned long slab_exts;
 
-	obj_exts_slab = virt_to_slab(obj_exts);
-	slab_exts = slab_obj_exts(obj_exts_slab);
+	obj_slab = virt_to_slab(obj);
+	slab_exts = slab_obj_exts(obj_slab);
 	if (slab_exts) {
 		get_slab_obj_exts(slab_exts);
-		unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
-						 obj_exts_slab, obj_exts);
-		struct slabobj_ext *ext = slab_obj_ext(obj_exts_slab,
+		unsigned int offs = obj_to_index(obj_slab->slab_cache,
+						 obj_slab, obj);
+		struct slabobj_ext *ext = slab_obj_ext(obj_slab,
 						       slab_exts, offs);
 
 		if (unlikely(is_codetag_empty(&ext->ref))) {
@@ -2090,7 +2090,7 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 
 #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
-static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {}
+static inline void mark_obj_codetag_empty(const void *obj) {}
 static inline bool mark_failed_objexts_alloc(struct slab *slab) { return false; }
 static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
 			struct slabobj_ext *vec, unsigned int objects) {}
@@ -2211,7 +2211,7 @@ retry:
 		 * assign slabobj_exts in parallel. In this case the existing
 		 * objcg vector should be reused.
 		 */
-		mark_objexts_empty(vec);
+		mark_obj_codetag_empty(vec);
 		if (unlikely(!allow_spin))
 			kfree_nolock(vec);
 		else
@@ -2254,7 +2254,7 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin)
 	 * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that
 	 * the extension for obj_exts is expected to be NULL.
 	 */
-	mark_objexts_empty(obj_exts);
+	mark_obj_codetag_empty(obj_exts);
 	if (allow_spin)
 		kfree(obj_exts);
 	else
@@ -2312,6 +2312,10 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 
 #else /* CONFIG_SLAB_OBJ_EXT */
 
+static inline void mark_obj_codetag_empty(const void *obj)
+{
+}
+
 static inline void init_slab_obj_exts(struct slab *slab)
 {
 }
@@ -2783,6 +2787,15 @@ static inline struct slab_sheaf *alloc_empty_sheaf(struct kmem_cache *s,
 
 static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf)
 {
+	/*
+	 * If the sheaf was created with __GFP_NO_OBJ_EXT flag then its
+	 * corresponding extension is NULL and alloc_tag_sub() will throw a
+	 * warning, therefore replace NULL with CODETAG_EMPTY to indicate
+	 * that the extension for this sheaf is expected to be NULL.
+	 */
+	if (s->flags & SLAB_KMALLOC)
+		mark_obj_codetag_empty(sheaf);
+
 	kfree(sheaf);
 
 	stat(s, SHEAF_FREE);
-- 
cgit v1.2.3


From 2b351ea42820a7ecc2e8305724536512984f4419 Mon Sep 17 00:00:00 2001
From: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Date: Thu, 26 Feb 2026 11:17:12 +0530
Subject: mm/slub: drop duplicate kernel-doc for ksize()

The implementation of ksize() was updated with kernel-doc by commit
fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c")
However, the public header still contains a kernel-doc comment
attached to the ksize() prototype.

Having documentation both in the header and next to the implementation
causes Sphinx to treat the function as being documented twice,
resulting in the warning:

  WARNING: Duplicate C declaration, also defined at core-api/mm-api:521
  Declaration is '.. c:function:: size_t ksize(const void *objp)'

Kernel-doc guidelines recommend keeping the documentation with the
function implementation. Therefore remove the redundant kernel-doc
block from include/linux/slab.h so that the implementation in slub.c
remains the canonical source for documentation.

No functional change.

Fixes: fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c")
Signed-off-by: Sanjay Chitroda <sanjayembeddedse@gmail.com>
Link: https://patch.msgid.link/20260226054712.3610744-1-sanjayembedded@gmail.com
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 include/linux/slab.h | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/include/linux/slab.h b/include/linux/slab.h
index a5a5e4108ae5..15a60b501b95 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp);
 DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T))
 DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T))
 
-/**
- * ksize - Report actual allocation size of associated object
- *
- * @objp: Pointer returned from a prior kmalloc()-family allocation.
- *
- * This should not be used for writing beyond the originally requested
- * allocation size. Either use krealloc() or round up the allocation size
- * with kmalloc_size_roundup() prior to allocation. If this is used to
- * access beyond the originally requested allocation size, UBSAN_BOUNDS
- * and/or FORTIFY_SOURCE may trip, since they only know about the
- * originally allocated size via the __alloc_size attribute.
- */
 size_t ksize(const void *objp);
 
 #ifdef CONFIG_PRINTK
-- 
cgit v1.2.3


From 71c1978ab6d2c6d48c31311855f1a85377c152ae Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Feb 2026 16:47:52 +0100
Subject: ASoC: SDCA: Fix comments for sdca_irq_request()

The kernel-doc comments for sdca_irq_request() contained some typos
that lead to build warnings with W=1.  Let's correct them.

Fixes: b126394d9ec6 ("ASoC: SDCA: Generic interrupt support")
Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260226154753.1083320-1-tiwai@suse.de
---
 sound/soc/sdca/sdca_interrupts.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index d9e22cf40f77..95b1ab4ba1b0 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -265,9 +265,9 @@ static int sdca_irq_request_locked(struct device *dev,
 }
 
 /**
- * sdca_request_irq - request an individual SDCA interrupt
+ * sdca_irq_request - request an individual SDCA interrupt
  * @dev: Pointer to the struct device against which things should be allocated.
- * @interrupt_info: Pointer to the interrupt information structure.
+ * @info: Pointer to the interrupt information structure.
  * @sdca_irq: SDCA interrupt position.
  * @name: Name to be given to the IRQ.
  * @handler: A callback thread function to be called for the IRQ.
-- 
cgit v1.2.3


From 795469820c638b4449f3bb90ee5e98ebccfbc480 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 23 Feb 2026 14:01:56 -0800
Subject: kcsan: test: Adjust "expect" allocation type for kmalloc_obj

The call to kmalloc_obj(observed.lines) returns "char (*)[3][512]",
a pointer to the whole 2D array. But "expect" wants to be "char (*)[512]",
the decayed pointer type, as if it were observed.lines itself (though
without the "3" bounds). This produces the following build error:

../kernel/kcsan/kcsan_test.c: In function '__report_matches':
../kernel/kcsan/kcsan_test.c:171:16: error: assignment to 'char (*)[512]' from incompatible pointer type 'char (*)[3][512]'
[-Wincompatible-pointer-types]
  171 |         expect = kmalloc_obj(observed.lines);
      |                ^

Instead of changing the "expect" type to "char (*)[3][512]" and
requiring a dereference at each use (e.g. "(expect*)[0]"), just
explicitly cast the return to the desired type.

Note that I'm intentionally not switching back to byte-based "kmalloc"
here because I cannot find a way for the Coccinelle script (which will
be used going forward to catch future conversions) to exclude this case.

Tested with:

$ ./tools/testing/kunit/kunit.py run \
	--kconfig_add CONFIG_DEBUG_KERNEL=y \
	--kconfig_add CONFIG_KCSAN=y \
	--kconfig_add CONFIG_KCSAN_KUNIT_TEST=y \
	--arch=x86_64 --qemu_args '-smp 2' kcsan

Reported-by: Nathan Chancellor <nathan@kernel.org>
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Signed-off-by: Kees Cook <kees@kernel.org>
---
 kernel/kcsan/kcsan_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 79e655ea4ca1..ae758150ccb9 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -168,7 +168,7 @@ static bool __report_matches(const struct expect_report *r)
 	if (!report_available())
 		return false;
 
-	expect = kmalloc_obj(observed.lines);
+	expect = (typeof(expect))kmalloc_obj(observed.lines);
 	if (WARN_ON(!expect))
 		return false;
 
-- 
cgit v1.2.3


From e5cb94ba5f96d691d8885175d4696d6ae6bc5ec9 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 26 Feb 2026 08:22:32 +0000
Subject: arm64: Fix sampling the "stable" virtual counter in preemptible
 section
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ben reports that when running with CONFIG_DEBUG_PREEMPT, using
__arch_counter_get_cntvct_stable() results in well deserves warnings,
as we access a per-CPU variable without preemption disabled.

Fix the issue by disabling preemption on reading the counter. We can
probably do a lot better by not disabling preemption on systems that
do not require horrible workarounds to return a valid counter value,
but this plugs the issue for the time being.

Fixes: 29cc0f3aa7c6 ("arm64: Force the use of CNTVCT_EL0 in __delay()")
Reported-by: Ben Horgan <ben.horgan@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/aZw3EGs4rbQvbAzV@e134344.arm.com
Tested-by: Ben Horgan <ben.horgan@arm.com>
Tested-by: André Draszik <andre.draszik@linaro.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/lib/delay.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index d02341303899..e278e060e78a 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -32,7 +32,11 @@ static inline unsigned long xloops_to_cycles(unsigned long xloops)
  * Note that userspace cannot change the offset behind our back either,
  * as the vcpu mutex is held as long as KVM_RUN is in progress.
  */
-#define __delay_cycles()	__arch_counter_get_cntvct_stable()
+static cycles_t notrace __delay_cycles(void)
+{
+	guard(preempt_notrace)();
+	return __arch_counter_get_cntvct_stable();
+}
 
 void __delay(unsigned long cycles)
 {
-- 
cgit v1.2.3


From df6e4ab654dc482c1d45776257a62ac10e14086c Mon Sep 17 00:00:00 2001
From: Sumit Gupta <sumitg@nvidia.com>
Date: Thu, 26 Feb 2026 17:29:11 +0530
Subject: arm64: topology: Fix false warning in counters_read_on_cpu() for
 same-CPU reads

The counters_read_on_cpu() function warns when called with IRQs
disabled to prevent deadlock in smp_call_function_single(). However,
this warning is spurious when reading counters on the current CPU,
since no IPI is needed for same CPU reads.

Commit 12eb8f4fff24 ("cpufreq: CPPC: Update FIE arch_freq_scale in
ticks for non-PCC regs") changed the CPPC Frequency Invariance Engine
to read AMU counters directly from the scheduler tick for non-PCC
register spaces (like FFH), instead of deferring to a kthread. This
means counters_read_on_cpu() is now called with IRQs disabled from the
tick handler, triggering the warning.

Fix this by restructuring the logic: when IRQs are disabled (tick
context), call the function directly for same-CPU reads. Otherwise
use smp_call_function_single().

Fixes: 997c021abc6e ("cpufreq: CPPC: Update FIE arch_freq_scale in ticks for non-PCC regs")
Suggested-by: Will Deacon <will@kernel.org>
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/topology.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 3fe1faab0362..b32f13358fbb 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -400,16 +400,25 @@ static inline
 int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
 {
 	/*
-	 * Abort call on counterless CPU or when interrupts are
-	 * disabled - can lead to deadlock in smp sync call.
+	 * Abort call on counterless CPU.
 	 */
 	if (!cpu_has_amu_feat(cpu))
 		return -EOPNOTSUPP;
 
-	if (WARN_ON_ONCE(irqs_disabled()))
-		return -EPERM;
-
-	smp_call_function_single(cpu, func, val, 1);
+	if (irqs_disabled()) {
+		/*
+		 * When IRQs are disabled (tick path: sched_tick ->
+		 * topology_scale_freq_tick or cppc_scale_freq_tick), only local
+		 * CPU counter reads are allowed. Remote CPU counter read would
+		 * require smp_call_function_single() which is unsafe with IRQs
+		 * disabled.
+		 */
+		if (WARN_ON_ONCE(cpu != smp_processor_id()))
+			return -EPERM;
+		func(val);
+	} else {
+		smp_call_function_single(cpu, func, val, 1);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 8678591b47469fe16357234efef9b260317b8be4 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 25 Feb 2026 15:02:51 -0700
Subject: kbuild: Split .modinfo out from ELF_DETAILS

Commit 3e86e4d74c04 ("kbuild: keep .modinfo section in
vmlinux.unstripped") added .modinfo to ELF_DETAILS while removing it
from COMMON_DISCARDS, as it was needed in vmlinux.unstripped and
ELF_DETAILS was present in all architecture specific vmlinux linker
scripts. While this shuffle is fine for vmlinux, ELF_DETAILS and
COMMON_DISCARDS may be used by other linker scripts, such as the s390
and x86 compressed boot images, which may not expect to have a .modinfo
section. In certain circumstances, this could result in a bootloader
failing to load the compressed kernel [1].

Commit ddc6cbef3ef1 ("s390/boot/vmlinux.lds.S: Ensure bzImage ends with
SecureBoot trailer") recently addressed this for the s390 bzImage but
the same bug remains for arm, parisc, and x86. The presence of .modinfo
in the x86 bzImage was the root cause of the issue worked around with
commit d50f21091358 ("kbuild: align modinfo section for Secureboot
Authenticode EDK2 compat"). misc.c in arch/x86/boot/compressed includes
lib/decompress_unzstd.c, which in turn includes lib/xxhash.c and its
MODULE_LICENSE / MODULE_DESCRIPTION macros due to the STATIC definition.

Split .modinfo out from ELF_DETAILS into its own macro and handle it in
all vmlinux linker scripts. Discard .modinfo in the places where it was
previously being discarded from being in COMMON_DISCARDS, as it has
never been necessary in those uses.

Cc: stable@vger.kernel.org
Fixes: 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped")
Reported-by: Ed W <lists@wildgooses.com>
Closes: https://lore.kernel.org/587f25e0-a80e-46a5-9f01-87cb40cfa377@wildgooses.com/ [1]
Tested-by: Ed W <lists@wildgooses.com> # x86_64
Link: https://patch.msgid.link/20260225-separate-modinfo-from-elf-details-v1-1-387ced6baf4b@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 arch/alpha/kernel/vmlinux.lds.S           | 1 +
 arch/arc/kernel/vmlinux.lds.S             | 1 +
 arch/arm/boot/compressed/vmlinux.lds.S    | 1 +
 arch/arm/kernel/vmlinux-xip.lds.S         | 1 +
 arch/arm/kernel/vmlinux.lds.S             | 1 +
 arch/arm64/kernel/vmlinux.lds.S           | 1 +
 arch/csky/kernel/vmlinux.lds.S            | 1 +
 arch/hexagon/kernel/vmlinux.lds.S         | 1 +
 arch/loongarch/kernel/vmlinux.lds.S       | 1 +
 arch/m68k/kernel/vmlinux-nommu.lds        | 1 +
 arch/m68k/kernel/vmlinux-std.lds          | 1 +
 arch/m68k/kernel/vmlinux-sun3.lds         | 1 +
 arch/mips/kernel/vmlinux.lds.S            | 1 +
 arch/nios2/kernel/vmlinux.lds.S           | 1 +
 arch/openrisc/kernel/vmlinux.lds.S        | 1 +
 arch/parisc/boot/compressed/vmlinux.lds.S | 1 +
 arch/parisc/kernel/vmlinux.lds.S          | 1 +
 arch/powerpc/kernel/vmlinux.lds.S         | 1 +
 arch/riscv/kernel/vmlinux.lds.S           | 1 +
 arch/s390/kernel/vmlinux.lds.S            | 1 +
 arch/sh/kernel/vmlinux.lds.S              | 1 +
 arch/sparc/kernel/vmlinux.lds.S           | 1 +
 arch/um/kernel/dyn.lds.S                  | 1 +
 arch/um/kernel/uml.lds.S                  | 1 +
 arch/x86/boot/compressed/vmlinux.lds.S    | 2 +-
 arch/x86/kernel/vmlinux.lds.S             | 1 +
 include/asm-generic/vmlinux.lds.h         | 4 +++-
 27 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index 2efa7dfc798a..2d136c63db16 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -71,6 +71,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 61a1b2b96e1d..6af63084ff28 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -123,6 +123,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	DISCARDS
 
diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S
index d411abd4310e..2d916647df03 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.S
+++ b/arch/arm/boot/compressed/vmlinux.lds.S
@@ -21,6 +21,7 @@ SECTIONS
     COMMON_DISCARDS
     *(.ARM.exidx*)
     *(.ARM.extab*)
+    *(.modinfo)
     *(.note.*)
     *(.rel.*)
     *(.printk_index)
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index f2e8d4fac068..5afb725998ec 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -154,6 +154,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index d592a203f9c6..c07843c3c53d 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -153,6 +153,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ad6133b89e7a..2964aad0362e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -349,6 +349,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	HEAD_SYMBOLS
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
index d718961786d2..81943981b3af 100644
--- a/arch/csky/kernel/vmlinux.lds.S
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -109,6 +109,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 1150b77fa281..aae22283b5e0 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -62,6 +62,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.hexagon.attributes 0 : { *(.hexagon.attributes) }
 
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index 08ea921cdec1..d0e1377a041d 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -147,6 +147,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 #ifdef CONFIG_EFI_STUB
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index 2624fc18c131..45d7f4b0177b 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -85,6 +85,7 @@ SECTIONS {
 	_end = .;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* Sections to be discarded */
diff --git a/arch/m68k/kernel/vmlinux-std.lds b/arch/m68k/kernel/vmlinux-std.lds
index 1ccdd04ae462..7326586afe15 100644
--- a/arch/m68k/kernel/vmlinux-std.lds
+++ b/arch/m68k/kernel/vmlinux-std.lds
@@ -58,6 +58,7 @@ SECTIONS
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
diff --git a/arch/m68k/kernel/vmlinux-sun3.lds b/arch/m68k/kernel/vmlinux-sun3.lds
index f13ddcc2af5c..1b19fef201fb 100644
--- a/arch/m68k/kernel/vmlinux-sun3.lds
+++ b/arch/m68k/kernel/vmlinux-sun3.lds
@@ -51,6 +51,7 @@ __init_begin = .;
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 2b708fac8d2c..579b2cc1995a 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -217,6 +217,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* These must appear regardless of  .  */
diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S
index 37b958055064..206f92445bfa 100644
--- a/arch/nios2/kernel/vmlinux.lds.S
+++ b/arch/nios2/kernel/vmlinux.lds.S
@@ -57,6 +57,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 049bff45f612..9b29c3211774 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -101,6 +101,7 @@ SECTIONS
 	/* Throw in the debugging sections */
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
         /* Sections to be discarded -- must be last */
diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S
index ab7b43990857..87d24cc824b6 100644
--- a/arch/parisc/boot/compressed/vmlinux.lds.S
+++ b/arch/parisc/boot/compressed/vmlinux.lds.S
@@ -90,6 +90,7 @@ SECTIONS
 	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
+		*(.modinfo)
 #ifdef CONFIG_64BIT
 		/* temporary hack until binutils is fixed to not emit these
 		 * for static binaries
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index b445e47903cf..0ca93d6d7235 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -165,6 +165,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.note 0 : { *(.note) }
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 15850296c0a9..8fc11d6565bf 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -397,6 +397,7 @@ SECTIONS
 	_end = . ;
 
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 61bd5ba6680a..997f9eb3b22b 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -170,6 +170,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.riscv.attributes 0 : { *(.riscv.attributes) }
 
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 53bcbb91bb9b..2b62395e35bf 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -221,6 +221,7 @@ SECTIONS
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/*
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index 008c30289eaa..169c63fb3c1d 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -89,6 +89,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f1b86eb30340..7ea510d9b42f 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -191,6 +191,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index a36b7918a011..ad3cefeff2ac 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -172,6 +172,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index a409d4b66114..30aa24348d60 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -113,6 +113,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 587ce3e7c504..e0b152715d9c 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -88,7 +88,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
 		*(.hash) *(.gnu.hash)
-		*(.note.*)
+		*(.note.*) *(.modinfo)
 	}
 
 	.got.plt (INFO) : {
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3a24a3fc55f5..4711a35e706c 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -427,6 +427,7 @@ SECTIONS
 	.llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
 #endif
 
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index eeb070f330bd..1e1580febe4b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -848,12 +848,14 @@
 
 /* Required sections not related to debugging. */
 #define ELF_DETAILS							\
-		.modinfo : { *(.modinfo) . = ALIGN(8); }		\
 		.comment 0 : { *(.comment) }				\
 		.symtab 0 : { *(.symtab) }				\
 		.strtab 0 : { *(.strtab) }				\
 		.shstrtab 0 : { *(.shstrtab) }
 
+#define MODINFO								\
+		.modinfo : { *(.modinfo) . = ALIGN(8); }
+
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
 	. = ALIGN(8);							\
-- 
cgit v1.2.3


From d2395bb194ef212b36521ec4fa85e38b45675acb Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 25 Feb 2026 15:07:17 -0700
Subject: genksyms: Fix parsing a declarator with a preceding attribute

After commit 07919126ecfc ("netfilter: annotate NAT helper hook pointers
with __rcu"), genksyms fails to parse the __rcu annotation when building
with CONFIG_DEBUG_INFO_BTF=y, CONFIG_PAHOLE_HAS_BTF_TAG=y, and a version
of clang that supports btf_type_tag.

  $ clang --version | head -1
  ClangBuiltLinux clang version 22.1.0 (https://github.com/llvm/llvm-project.git 4434dabb69916856b824f68a64b029c67175e532)

  $ cat kernel/configs/repro.config
  CONFIG_BPF_SYSCALL=y
  CONFIG_MODVERSIONS=y
  # CONFIG_DEBUG_INFO_NONE is not set
  CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
  CONFIG_DEBUG_INFO_BTF=y

  $ make -skj"$(nproc)" ARCH=x86_64 LLVM=1 mrproper defconfig repro.config all
  WARNING: modpost: EXPORT symbol "nf_nat_ftp_hook" [vmlinux] version generation failed, symbol will not be versioned.
  ...
  WARNING: modpost: EXPORT symbol "nf_nat_irc_hook" [vmlinux] version generation failed, symbol will not be versioned.
  ...

genksyms falls over parsing the __rcu attribute in the declarator:

  # Kernel reproducer
  $ make -skj"$(nproc)" ARCH=x86_64 KCFLAGS=-D__GENKSYMS__ LLVM=1 net/netfilter/nf_conntrack_ftp.i

  $ scripts/genksyms/genksyms -w <net/netfilter/nf_conntrack_ftp.i &| rg 'syntax error'
  include/linux/netfilter/nf_conntrack_ftp.h:29: syntax error
  net/netfilter/nf_conntrack_ftp.c:46: syntax error

  # Trivial reproducer
  $ cat test.c
  int (*func)(void *foo, int bar);
  int (__attribute__((btf_type_tag("rcu"))) *func_with_attr)(void *foo, int bar);

  $ scripts/genksyms/genksyms -w <test.c
  <stdin>:2: syntax error

Optionally allow an attribute to precede a declarator to resolve this
error and properly generate symbol versions.

Fixes: 07919126ecfc ("netfilter: annotate NAT helper hook pointers with __rcu")
Link: https://patch.msgid.link/20260225-genksyms-fix-attribute-declarator-v1-1-1b21478663fb@kernel.org
Tested-by: Nicolas Schier <nsc@kernel.org>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/genksyms/parse.y | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index efdcf07c4eb6..cabcd146f3aa 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -325,8 +325,8 @@ direct_declarator:
 		{ $$ = $4; }
 	| direct_declarator BRACKET_PHRASE
 		{ $$ = $2; }
-	| '(' declarator ')'
-		{ $$ = $3; }
+	| '(' attribute_opt declarator ')'
+		{ $$ = $4; }
 	;
 
 /* Nested declarators differ from regular declarators in that they do
-- 
cgit v1.2.3


From ef06fd16d48704eac868441d98d4ef083d8f3d07 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 26 Feb 2026 07:55:25 +0000
Subject: bpf, arm64: Force 8-byte alignment for JIT buffer to prevent atomic
 tearing

struct bpf_plt contains a u64 target field. Currently, the BPF JIT
allocator requests an alignment of 4 bytes (sizeof(u32)) for the JIT
buffer.

Because the base address of the JIT buffer can be 4-byte aligned (e.g.,
ending in 0x4 or 0xc), the relative padding logic in build_plt() fails
to ensure that target lands on an 8-byte boundary.

This leads to two issues:
1. UBSAN reports misaligned-access warnings when dereferencing the
   structure.
2. More critically, target is updated concurrently via WRITE_ONCE() in
   bpf_arch_text_poke() while the JIT'd code executes ldr. On arm64,
   64-bit loads/stores are only guaranteed to be single-copy atomic if
   they are 64-bit aligned. A misaligned target risks a torn read,
   causing the JIT to jump to a corrupted address.

Fix this by increasing the allocation alignment requirement to 8 bytes
(sizeof(u64)) in bpf_jit_binary_pack_alloc(). This anchors the base of
the JIT buffer to an 8-byte boundary, allowing the relative padding math
in build_plt() to correctly align the target field.

Fixes: b2ad54e1533e ("bpf, arm64: Implement bpf_arch_text_poke() for arm64")
Signed-off-by: Fuad Tabba <tabba@google.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20260226075525.233321-1-tabba@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 356d33c7a4ae..adf84962d579 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2119,7 +2119,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align);
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
-					      sizeof(u32), &header, &image_ptr,
+					      sizeof(u64), &header, &image_ptr,
 					      jit_fill_hole);
 	if (!ro_header) {
 		prog = orig_prog;
-- 
cgit v1.2.3


From ad6fface76da42721c15e8fb281570aaa44a2c01 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 25 Feb 2026 12:12:49 +0100
Subject: bpf: Fix kprobe_multi cookies access in show_fdinfo callback

We don't check if cookies are available on the kprobe_multi link
before accessing them in show_fdinfo callback, we should.

Cc: stable@vger.kernel.org
Fixes: da7e9c0a7fbc ("bpf: Add show_fdinfo for kprobe_multi")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20260225111249.186230-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9bc0dfd235af..0b040a417442 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2454,8 +2454,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 					 struct seq_file *seq)
 {
 	struct bpf_kprobe_multi_link *kmulti_link;
+	bool has_cookies;
 
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
+	has_cookies = !!kmulti_link->cookies;
 
 	seq_printf(seq,
 		   "kprobe_cnt:\t%u\n"
@@ -2467,7 +2469,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link,
 	for (int i = 0; i < kmulti_link->cnt; i++) {
 		seq_printf(seq,
 			   "%llu\t %pS\n",
-			   kmulti_link->cookies[i],
+			   has_cookies ? kmulti_link->cookies[i] : 0,
 			   (void *)kmulti_link->addrs[i]);
 	}
 }
-- 
cgit v1.2.3


From b7bf516c3ecd9a2aae2dc2635178ab87b734fef1 Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Wed, 25 Feb 2026 05:34:44 +0000
Subject: bpf: Fix stack-out-of-bounds write in devmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

get_upper_ifindexes() iterates over all upper devices and writes their
indices into an array without checking bounds.

Also the callers assume that the max number of upper devices is
MAX_NEST_DEV and allocate excluded_devices[1+MAX_NEST_DEV] on the stack,
but that assumption is not correct and the number of upper devices could
be larger than MAX_NEST_DEV (e.g., many macvlans), causing a
stack-out-of-bounds write.

Add a max parameter to get_upper_ifindexes() to avoid the issue.
When there are too many upper devices, return -EOVERFLOW and abort the
redirect.

To reproduce, create more than MAX_NEST_DEV(8) macvlans on a device with
an XDP program attached using BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS.
Then send a packet to the device to trigger the XDP redirect path.

Reported-by: syzbot+10cc7f13760b31bd2e61@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698c4ce3.050a0220.340abe.000b.GAE@google.com/T/
Fixes: aeea1b86f936 ("bpf, devmap: Exclude XDP broadcast to master device")
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Link: https://lore.kernel.org/r/20260225053506.4738-1-kohei@enjuk.jp
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/devmap.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2625601de76e..2984e938f94d 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -588,18 +588,22 @@ static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifin
 }
 
 /* Get ifindex of each upper device. 'indexes' must be able to hold at
- * least MAX_NEST_DEV elements.
- * Returns the number of ifindexes added.
+ * least 'max' elements.
+ * Returns the number of ifindexes added, or -EOVERFLOW if there are too
+ * many upper devices.
  */
-static int get_upper_ifindexes(struct net_device *dev, int *indexes)
+static int get_upper_ifindexes(struct net_device *dev, int *indexes, int max)
 {
 	struct net_device *upper;
 	struct list_head *iter;
 	int n = 0;
 
 	netdev_for_each_upper_dev_rcu(dev, upper, iter) {
+		if (n >= max)
+			return -EOVERFLOW;
 		indexes[n++] = upper->ifindex;
 	}
+
 	return n;
 }
 
@@ -615,7 +619,11 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 	int err;
 
 	if (exclude_ingress) {
-		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
+		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices,
+						   ARRAY_SIZE(excluded_devices) - 1);
+		if (num_excluded < 0)
+			return num_excluded;
+
 		excluded_devices[num_excluded++] = dev_rx->ifindex;
 	}
 
@@ -733,7 +741,11 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 	int err;
 
 	if (exclude_ingress) {
-		num_excluded = get_upper_ifindexes(dev, excluded_devices);
+		num_excluded = get_upper_ifindexes(dev, excluded_devices,
+						   ARRAY_SIZE(excluded_devices) - 1);
+		if (num_excluded < 0)
+			return num_excluded;
+
 		excluded_devices[num_excluded++] = dev->ifindex;
 	}
 
-- 
cgit v1.2.3


From 60e3cbef3500ad6101bc91946e645f69b1bb9556 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Tue, 24 Feb 2026 16:33:51 -0800
Subject: selftests/bpf: Fix a memory leak in xdp_flowtable test

test_progs run with ASAN reported [1]:

  ==126==ERROR: LeakSanitizer: detected memory leaks

  Direct leak of 32 byte(s) in 1 object(s) allocated from:
      #0 0x7f1ff3cfa340 in calloc ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:77
      #1 0x5610c15bb520 in bpf_program_attach_fd /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/lib/bpf/libbpf.c:13164
      #2 0x5610c15bb740 in bpf_program__attach_xdp /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/lib/bpf/libbpf.c:13204
      #3 0x5610c14f91d3 in test_xdp_flowtable /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c:138
      #4 0x5610c1533566 in run_one_test /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/test_progs.c:1406
      #5 0x5610c1537fb0 in main /codebuild/output/src685977285/src/actions-runner/_work/vmtest/vmtest/src/tools/testing/selftests/bpf/test_progs.c:2097
      #6 0x7f1ff25df1c9  (/lib/x86_64-linux-gnu/libc.so.6+0x2a1c9) (BuildId: 8e9fd827446c24067541ac5390e6f527fb5947bb)
      #7 0x7f1ff25df28a in __libc_start_main (/lib/x86_64-linux-gnu/libc.so.6+0x2a28a) (BuildId: 8e9fd827446c24067541ac5390e6f527fb5947bb)
      #8 0x5610c0bd3180 in _start (/tmp/work/vmtest/vmtest/selftests/bpf/test_progs+0x593180) (BuildId: cdf9f103f42307dc0a2cd6cfc8afcbc1366cf8bd)

Fix by properly destroying bpf_link on exit in xdp_flowtable test.

[1] https://github.com/kernel-patches/vmtest/actions/runs/22361085418/job/64716490680

Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Link: https://lore.kernel.org/r/20260225003351.465104-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
index 3f9146d83d79..325e0b64dc35 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
@@ -67,7 +67,7 @@ void test_xdp_flowtable(void)
 	struct nstoken *tok = NULL;
 	int iifindex, stats_fd;
 	__u32 value, key = 0;
-	struct bpf_link *link;
+	struct bpf_link *link = NULL;
 
 	if (SYS_NOFAIL("nft -v")) {
 		fprintf(stdout, "Missing required nft tool\n");
@@ -160,6 +160,7 @@ void test_xdp_flowtable(void)
 
 	ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed");
 out:
+	bpf_link__destroy(link);
 	xdp_flowtable__destroy(skel);
 	if (tok)
 		close_netns(tok);
-- 
cgit v1.2.3


From 6881af27f9ea0f5ca8f606f573ef5cc25ca31fe4 Mon Sep 17 00:00:00 2001
From: "T.J. Mercier" <tjmercier@google.com>
Date: Tue, 24 Feb 2026 16:33:48 -0800
Subject: selftests/bpf: Fix OOB read in dmabuf_collector

Dmabuf name allocations can be less than DMA_BUF_NAME_LEN characters,
but bpf_probe_read_kernel always tries to read exactly that many bytes.
If a name is less than DMA_BUF_NAME_LEN characters,
bpf_probe_read_kernel will read past the end. bpf_probe_read_kernel_str
stops at the first NUL terminator so use it instead, like
iter_dmabuf_for_each already does.

Fixes: ae5d2c59ecd7 ("selftests/bpf: Add test for dmabuf_iter")
Reported-by: Jerome Lee <jaewookl@quicinc.com>
Signed-off-by: T.J. Mercier <tjmercier@google.com>
Link: https://lore.kernel.org/r/20260225003349.113746-1-tjmercier@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/dmabuf_iter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
index 13cdb11fdeb2..9cbb7442646e 100644
--- a/tools/testing/selftests/bpf/progs/dmabuf_iter.c
+++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
@@ -48,7 +48,7 @@ int dmabuf_collector(struct bpf_iter__dmabuf *ctx)
 
 	/* Buffers are not required to be named */
 	if (pname) {
-		if (bpf_probe_read_kernel(name, sizeof(name), pname))
+		if (bpf_probe_read_kernel_str(name, sizeof(name), pname) < 0)
 			return 1;
 
 		/* Name strings can be provided by userspace */
-- 
cgit v1.2.3


From 459cb3c054c2352bb321648744b620259a716b60 Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Thu, 26 Feb 2026 08:41:48 +0100
Subject: kbuild: install-extmod-build: Package resolve_btfids if necessary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CONFIG_DEBUG_INFO_BTF_MODULES is enabled and vmlinux is available,
Makefile.modfinal and gen-btf.sh will try to use resolve_btfids on the
module .ko. install-extmod-build currently does not package
resolve_btfids, so that step fails.

Package resolve_btfids if it may be used.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20260226-kbuild-resolve_btfids-v1-1-2bf38b93dfe7@linutronix.de
[nathan: Small commit message tweaks]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/package/install-extmod-build | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 2576cf7902db..f12e1ffe409e 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -32,6 +32,10 @@ mkdir -p "${destdir}"
 		echo tools/objtool/objtool
 	fi
 
+	if is_enabled CONFIG_DEBUG_INFO_BTF_MODULES; then
+		echo tools/bpf/resolve_btfids/resolve_btfids
+	fi
+
 	echo Module.symvers
 	echo "arch/${SRCARCH}/include/generated"
 	echo include/config/auto.conf
-- 
cgit v1.2.3


From 749989b2d90ddc7dd253ad3b11a77cf882721acf Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Thu, 26 Feb 2026 12:45:17 +0000
Subject: sched_ext: Fix SCX_EFLAG_INITIALIZED being a no-op flag

SCX_EFLAG_INITIALIZED is the sole member of enum scx_exit_flags with no
explicit value, so the compiler assigns it 0. This makes the bitwise OR
in scx_ops_init() a no-op:

    sch->exit_info->flags |= SCX_EFLAG_INITIALIZED; /* |= 0 */

As a result, BPF schedulers cannot distinguish whether ops.init()
completed successfully by inspecting exit_info->flags.

Assign the value 1LLU << 0 so the flag is actually set.

Fixes: f3aec2adce8d ("sched_ext: Add SCX_EFLAG_INITIALIZED to indicate successful ops.init()")
Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 386c677e4c9a..11ebb744d893 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -74,7 +74,7 @@ enum scx_exit_flags {
 	 * info communication. The following flag indicates whether ops.init()
 	 * finished successfully.
 	 */
-	SCX_EFLAG_INITIALIZED,
+	SCX_EFLAG_INITIALIZED   = 1LLU << 0,
 };
 
 /*
-- 
cgit v1.2.3


From dd677d0598387ea623820ab2bd0e029c377445a3 Mon Sep 17 00:00:00 2001
From: Justin Tee <justintee8345@gmail.com>
Date: Thu, 4 Dec 2025 12:26:13 -0800
Subject: nvmet-fcloop: Check remoteport port_state before calling done
 callback

In nvme_fc_handle_ls_rqst_work, the lsrsp->done callback is only set when
remoteport->port_state is FC_OBJSTATE_ONLINE.  Otherwise, the
nvme_fc_xmt_ls_rsp's LLDD call to lport->ops->xmt_ls_rsp is expected to
fail and the nvme-fc transport layer itself will directly call
nvme_fc_xmt_ls_rsp_free instead of relying on LLDD's done callback to free
the lsrsp resources.

Update the fcloop_t2h_xmt_ls_rsp routine to check remoteport->port_state.
If online, then lsrsp->done callback will free the lsrsp.  Else, return
-ENODEV to signal the nvme-fc transport to handle freeing lsrsp.

Cc: Ewan D. Milne <emilne@redhat.com>
Tested-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Closes: https://lore.kernel.org/linux-nvme/21255200-a271-4fa0-b099-97755c8acd4c@work/
Fixes: 10c165af35d2 ("nvmet-fcloop: call done callback even when remote port is gone")
Signed-off-by: Justin Tee <justintee8345@gmail.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/fcloop.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index c30e9a3e014f..38bd2db3d6bb 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -491,6 +491,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 	struct fcloop_rport *rport = remoteport->private;
 	struct nvmet_fc_target_port *targetport = rport->targetport;
 	struct fcloop_tport *tport;
+	int ret = 0;
 
 	if (!targetport) {
 		/*
@@ -500,12 +501,18 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 		 * We end up here from delete association exchange:
 		 * nvmet_fc_xmt_disconnect_assoc sends an async request.
 		 *
-		 * Return success because this is what LLDDs do; silently
-		 * drop the response.
+		 * Return success when remoteport is still online because this
+		 * is what LLDDs do and silently drop the response.  Otherwise,
+		 * return with error to signal upper layer to perform the lsrsp
+		 * resource cleanup.
 		 */
-		lsrsp->done(lsrsp);
+		if (remoteport->port_state == FC_OBJSTATE_ONLINE)
+			lsrsp->done(lsrsp);
+		else
+			ret = -ENODEV;
+
 		kmem_cache_free(lsreq_cache, tls_req);
-		return 0;
+		return ret;
 	}
 
 	memcpy(lsreq->rspaddr, lsrsp->rspbuf,
-- 
cgit v1.2.3


From b6c3af46c26f2d07c10a1452adc34b821719327e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 23 Feb 2026 19:06:51 +0100
Subject: pinctrl: cy8c95x0: Don't miss reading the last bank registers

When code had been changed to use for_each_set_clump8(), it mistakenly
switched from chip->nport to chip->tpin since the cy8c9540 and cy8c9560
have a 4-pin gap. This, in particular, led to the missed read of
the last bank interrupt status register and hence missing interrupts
on those pins. Restore the upper limit in for_each_set_clump8() to take
into consideration that gap.

Fixes: 83e29a7a1fdf ("pinctrl: cy8c95x0; Switch to use for_each_set_clump8()")
Cc: stable@vger.kernel.org
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-cy8c95x0.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index a4b04bf6d081..5c055d344ac9 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -627,7 +627,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		write_val = bitmap_get_value8(tval, offset);
@@ -655,7 +655,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg,
 	bitmap_scatter(tmask, mask, chip->map, MAX_LINE);
 	bitmap_scatter(tval, val, chip->map, MAX_LINE);
 
-	for_each_set_clump8(offset, bits, tmask, chip->tpin) {
+	for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) {
 		unsigned int i = offset / 8;
 
 		ret = cy8c95x0_regmap_read_bits(chip, reg, i, bits, &read_val);
-- 
cgit v1.2.3


From e96493229a6399e902062213c6381162464cdd50 Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@foss.st.com>
Date: Tue, 24 Feb 2026 16:09:22 +0100
Subject: spi: stm32: fix missing pointer assignment in case of dma chaining

Commit c4f2c05ab029 ("spi: stm32: fix pointer-to-pointer variables usage")
introduced a regression since dma descriptors generated as part of the
stm32_spi_prepare_rx_dma_mdma_chaining function are not well propagated
to the caller function, leading to mdma-dma chaining being no more
functional.

Fixes: c4f2c05ab029 ("spi: stm32: fix pointer-to-pointer variables usage")
Signed-off-by: Alain Volmat <alain.volmat@foss.st.com>
Acked-by: Antonio Quartulli <antonio@mandelbit.com>
Link: https://patch.msgid.link/20260224-spi-stm32-chaining-fix-v1-1-5da7a4851b66@foss.st.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index b99de8c4cc99..33f211e159ef 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1625,6 +1625,9 @@ static int stm32_spi_prepare_rx_dma_mdma_chaining(struct stm32_spi *spi,
 		return -EINVAL;
 	}
 
+	*rx_mdma_desc = _mdma_desc;
+	*rx_dma_desc = _dma_desc;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4fc3a433c13944ee5766ec5b9bf6f1eb4d29b880 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Mon, 23 Feb 2026 13:34:35 -0300
Subject: smb: client: use atomic_t for mnt_cifs_flags

Use atomic_t for cifs_sb_info::mnt_cifs_flags as it's currently
accessed locklessly and may be changed concurrently in mount/remount
and reconnect paths.

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c   |   2 +-
 fs/smb/client/cifs_fs_sb.h   |   2 +-
 fs/smb/client/cifs_ioctl.h   |   8 ---
 fs/smb/client/cifs_unicode.c |  14 ----
 fs/smb/client/cifs_unicode.h |  14 +++-
 fs/smb/client/cifsacl.c      |  17 ++---
 fs/smb/client/cifsfs.c       |  84 ++++++++++++------------
 fs/smb/client/cifsglob.h     |  61 ++++++++++++++----
 fs/smb/client/connect.c      |  65 +++++++++++--------
 fs/smb/client/dfs_cache.c    |   2 +-
 fs/smb/client/dir.c          |  53 ++++++++-------
 fs/smb/client/file.c         |  90 +++++++++++++-------------
 fs/smb/client/fs_context.c   | 149 +++++++++++++++++++++----------------------
 fs/smb/client/fs_context.h   |   2 +-
 fs/smb/client/inode.c        | 142 +++++++++++++++++++++--------------------
 fs/smb/client/ioctl.c        |   2 +-
 fs/smb/client/link.c         |  14 ++--
 fs/smb/client/misc.c         |  16 +++--
 fs/smb/client/readdir.c      |  39 +++++------
 fs/smb/client/reparse.c      |  27 ++++----
 fs/smb/client/reparse.h      |   4 +-
 fs/smb/client/smb1ops.c      |  22 ++++---
 fs/smb/client/smb2file.c     |   2 +-
 fs/smb/client/smb2misc.c     |  18 ++----
 fs/smb/client/smb2ops.c      |   8 +--
 fs/smb/client/smb2pdu.c      |  13 ++--
 fs/smb/client/xattr.c        |   6 +-
 27 files changed, 462 insertions(+), 414 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index c327c246a9b4..04bb95091f49 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -118,7 +118,7 @@ static const char *path_no_prefix(struct cifs_sb_info *cifs_sb,
 	if (!*path)
 		return path;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 	    cifs_sb->prepath) {
 		len = strlen(cifs_sb->prepath) + 1;
 		if (unlikely(len > strlen(path)))
diff --git a/fs/smb/client/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h
index 5e8d163cb5f8..84e7e366b0ff 100644
--- a/fs/smb/client/cifs_fs_sb.h
+++ b/fs/smb/client/cifs_fs_sb.h
@@ -55,7 +55,7 @@ struct cifs_sb_info {
 	struct nls_table *local_nls;
 	struct smb3_fs_context *ctx;
 	atomic_t active;
-	unsigned int mnt_cifs_flags;
+	atomic_t mnt_cifs_flags;
 	struct delayed_work prune_tlinks;
 	struct rcu_head rcu;
 
diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h
index b51ce64fcccf..147496ac9f9f 100644
--- a/fs/smb/client/cifs_ioctl.h
+++ b/fs/smb/client/cifs_ioctl.h
@@ -122,11 +122,3 @@ struct smb3_notify_info {
 #define CIFS_GOING_FLAGS_DEFAULT                0x0     /* going down */
 #define CIFS_GOING_FLAGS_LOGFLUSH               0x1     /* flush log but not data */
 #define CIFS_GOING_FLAGS_NOLOGFLUSH             0x2     /* don't flush log nor data */
-
-static inline bool cifs_forced_shutdown(struct cifs_sb_info *sbi)
-{
-	if (CIFS_MOUNT_SHUTDOWN & sbi->mnt_cifs_flags)
-		return true;
-	else
-		return false;
-}
diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c
index e7891b4406f2..e2edc207cef2 100644
--- a/fs/smb/client/cifs_unicode.c
+++ b/fs/smb/client/cifs_unicode.c
@@ -11,20 +11,6 @@
 #include "cifsglob.h"
 #include "cifs_debug.h"
 
-int cifs_remap(struct cifs_sb_info *cifs_sb)
-{
-	int map_type;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
-		map_type = SFM_MAP_UNI_RSVD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
-		map_type = SFU_MAP_UNI_RSVD;
-	else
-		map_type = NO_MAP_UNI_RSVD;
-
-	return map_type;
-}
-
 /* Convert character using the SFU - "Services for Unix" remapping range */
 static bool
 convert_sfu_char(const __u16 src_char, char *target)
diff --git a/fs/smb/client/cifs_unicode.h b/fs/smb/client/cifs_unicode.h
index 9249db3b78c3..3e9cd9acf0a9 100644
--- a/fs/smb/client/cifs_unicode.h
+++ b/fs/smb/client/cifs_unicode.h
@@ -22,6 +22,7 @@
 #include <linux/types.h>
 #include <linux/nls.h>
 #include "../../nls/nls_ucs2_utils.h"
+#include "cifsglob.h"
 
 /*
  * Macs use an older "SFM" mapping of the symbols above. Fortunately it does
@@ -65,10 +66,21 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen,
 			      const struct nls_table *codepage);
 int cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		       const struct nls_table *cp, int map_chars);
-int cifs_remap(struct cifs_sb_info *cifs_sb);
 __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
 			      int *utf16_len, const struct nls_table *cp,
 			      int remap);
 wchar_t cifs_toupper(wchar_t in);
 
+static inline int cifs_remap(const struct cifs_sb_info *cifs_sb)
+{
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_MAP_SFM_CHR)
+		return SFM_MAP_UNI_RSVD;
+	if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+		return SFU_MAP_UNI_RSVD;
+
+	return NO_MAP_UNI_RSVD;
+}
+
 #endif /* _CIFS_UNICODE_H */
diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 6fa12c901c14..f4cb3018a358 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -356,7 +356,7 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct smb_sid *psid,
 				psid->num_subauth, SID_MAX_SUB_AUTHORITIES);
 	}
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) ||
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_UID_FROM_ACL) ||
 	    (cifs_sb_master_tcon(cifs_sb)->posix_extensions)) {
 		uint32_t unix_id;
 		bool is_group;
@@ -1612,7 +1612,8 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 	struct smb_acl *dacl_ptr = NULL;
 	struct smb_ntsd *pntsd = NULL; /* acl obtained from server */
 	struct smb_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags;
 	struct tcon_link *tlink;
 	struct smb_version_operations *ops;
 	bool mode_from_sid, id_from_sid;
@@ -1643,15 +1644,9 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 		return rc;
 	}
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)
-		mode_from_sid = true;
-	else
-		mode_from_sid = false;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
-		id_from_sid = true;
-	else
-		id_from_sid = false;
+	sbflags = cifs_sb_flags(cifs_sb);
+	mode_from_sid = sbflags & CIFS_MOUNT_MODE_FROM_SID;
+	id_from_sid = sbflags & CIFS_MOUNT_UID_FROM_ACL;
 
 	/* Potentially, five new ACEs can be added to the ACL for U,G,O mapping */
 	if (pnmode && *pnmode != NO_CHANGE_64) { /* chmod */
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 99b04234a08e..427558404aa5 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -226,16 +226,18 @@ cifs_sb_deactive(struct super_block *sb)
 static int
 cifs_read_super(struct super_block *sb)
 {
-	struct inode *inode;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
+	unsigned int sbflags;
 	struct timespec64 ts;
+	struct inode *inode;
 	int rc = 0;
 
 	cifs_sb = CIFS_SB(sb);
 	tcon = cifs_sb_master_tcon(cifs_sb);
+	sbflags = cifs_sb_flags(cifs_sb);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
+	if (sbflags & CIFS_MOUNT_POSIXACL)
 		sb->s_flags |= SB_POSIXACL;
 
 	if (tcon->snapshot_time)
@@ -311,7 +313,7 @@ cifs_read_super(struct super_block *sb)
 	}
 
 #ifdef CONFIG_CIFS_NFSD_EXPORT
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		cifs_dbg(FYI, "export ops supported\n");
 		sb->s_export_op = &cifs_export_ops;
 	}
@@ -389,8 +391,7 @@ statfs_out:
 
 static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
-	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(CIFS_SB(file));
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct inode *inode = file_inode(file);
 	int rc;
@@ -418,11 +419,9 @@ out_unlock:
 static int cifs_permission(struct mnt_idmap *idmap,
 			   struct inode *inode, int mask)
 {
-	struct cifs_sb_info *cifs_sb;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 
-	cifs_sb = CIFS_SB(inode->i_sb);
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
+	if (sbflags & CIFS_MOUNT_NO_PERM) {
 		if ((mask & MAY_EXEC) && !execute_ok(inode))
 			return -EACCES;
 		else
@@ -568,15 +567,17 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 static void
 cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
 	seq_puts(s, ",cache=");
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+	if (sbflags & CIFS_MOUNT_STRICT_IO)
 		seq_puts(s, "strict");
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
+	else if (sbflags & CIFS_MOUNT_DIRECT_IO)
 		seq_puts(s, "none");
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
+	else if (sbflags & CIFS_MOUNT_RW_CACHE)
 		seq_puts(s, "singleclient"); /* assume only one client access */
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE)
+	else if (sbflags & CIFS_MOUNT_RO_CACHE)
 		seq_puts(s, "ro"); /* read only caching assumed */
 	else
 		seq_puts(s, "loose");
@@ -637,6 +638,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct sockaddr *srcaddr;
+	unsigned int sbflags;
+
 	srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr;
 
 	seq_show_option(s, "vers", tcon->ses->server->vals->version_string);
@@ -670,16 +673,17 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 				   (int)(srcaddr->sa_family));
 	}
 
+	sbflags = cifs_sb_flags(cifs_sb);
 	seq_printf(s, ",uid=%u",
 		   from_kuid_munged(&init_user_ns, cifs_sb->ctx->linux_uid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
+	if (sbflags & CIFS_MOUNT_OVERR_UID)
 		seq_puts(s, ",forceuid");
 	else
 		seq_puts(s, ",noforceuid");
 
 	seq_printf(s, ",gid=%u",
 		   from_kgid_munged(&init_user_ns, cifs_sb->ctx->linux_gid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
+	if (sbflags & CIFS_MOUNT_OVERR_GID)
 		seq_puts(s, ",forcegid");
 	else
 		seq_puts(s, ",noforcegid");
@@ -722,53 +726,53 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
+	if (sbflags & CIFS_MOUNT_NO_DFS)
 		seq_puts(s, ",nodfs");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+	if (sbflags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
+	if (sbflags & CIFS_MOUNT_SET_UID)
 		seq_puts(s, ",setuids");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
+	if (sbflags & CIFS_MOUNT_UID_FROM_ACL)
 		seq_puts(s, ",idsfromsid");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+	if (sbflags & CIFS_MOUNT_SERVER_INUM)
 		seq_puts(s, ",serverino");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+	if (sbflags & CIFS_MOUNT_RWPIDFORWARD)
 		seq_puts(s, ",rwpidforward");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
+	if (sbflags & CIFS_MOUNT_NOPOSIXBRL)
 		seq_puts(s, ",forcemand");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+	if (sbflags & CIFS_MOUNT_NO_XATTR)
 		seq_puts(s, ",nouser_xattr");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
+	if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR)
 		seq_puts(s, ",mapchars");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
+	if (sbflags & CIFS_MOUNT_MAP_SFM_CHR)
 		seq_puts(s, ",mapposix");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
+	if (sbflags & CIFS_MOUNT_UNX_EMUL)
 		seq_puts(s, ",sfu");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	if (sbflags & CIFS_MOUNT_NO_BRL)
 		seq_puts(s, ",nobrl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE)
+	if (sbflags & CIFS_MOUNT_NO_HANDLE_CACHE)
 		seq_puts(s, ",nohandlecache");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)
+	if (sbflags & CIFS_MOUNT_MODE_FROM_SID)
 		seq_puts(s, ",modefromsid");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
+	if (sbflags & CIFS_MOUNT_CIFS_ACL)
 		seq_puts(s, ",cifsacl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+	if (sbflags & CIFS_MOUNT_DYNPERM)
 		seq_puts(s, ",dynperm");
 	if (root->d_sb->s_flags & SB_POSIXACL)
 		seq_puts(s, ",acl");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
+	if (sbflags & CIFS_MOUNT_MF_SYMLINKS)
 		seq_puts(s, ",mfsymlinks");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
+	if (sbflags & CIFS_MOUNT_FSCACHE)
 		seq_puts(s, ",fsc");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
+	if (sbflags & CIFS_MOUNT_NOSSYNC)
 		seq_puts(s, ",nostrictsync");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (sbflags & CIFS_MOUNT_NO_PERM)
 		seq_puts(s, ",noperm");
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID)
 		seq_printf(s, ",backupuid=%u",
 			   from_kuid_munged(&init_user_ns,
 					    cifs_sb->ctx->backupuid));
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID)
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID)
 		seq_printf(s, ",backupgid=%u",
 			   from_kgid_munged(&init_user_ns,
 					    cifs_sb->ctx->backupgid));
@@ -909,10 +913,10 @@ static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 static int cifs_drop_inode(struct inode *inode)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 
 	/* no serverino => unconditional eviction */
-	return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) ||
+	return !(sbflags & CIFS_MOUNT_SERVER_INUM) ||
 		inode_generic_drop(inode);
 }
 
@@ -950,7 +954,7 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb)
 	char *s, *p;
 	char sep;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH)
 		return dget(sb->s_root);
 
 	full_path = cifs_build_path_to_root(ctx, cifs_sb,
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 080ea601c209..6f9b6c72962b 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1580,24 +1580,59 @@ CIFS_I(struct inode *inode)
 	return container_of(inode, struct cifsInodeInfo, netfs.inode);
 }
 
-static inline struct cifs_sb_info *
-CIFS_SB(struct super_block *sb)
+static inline void *cinode_to_fsinfo(struct cifsInodeInfo *cinode)
+{
+	return cinode->netfs.inode.i_sb->s_fs_info;
+}
+
+static inline void *super_to_fsinfo(struct super_block *sb)
 {
 	return sb->s_fs_info;
 }
 
-static inline struct cifs_sb_info *
-CIFS_FILE_SB(struct file *file)
+static inline void *inode_to_fsinfo(struct inode *inode)
+{
+	return inode->i_sb->s_fs_info;
+}
+
+static inline void *file_to_fsinfo(struct file *file)
+{
+	return file_inode(file)->i_sb->s_fs_info;
+}
+
+static inline void *dentry_to_fsinfo(struct dentry *dentry)
+{
+	return dentry->d_sb->s_fs_info;
+}
+
+static inline void *const_dentry_to_fsinfo(const struct dentry *dentry)
 {
-	return CIFS_SB(file_inode(file)->i_sb);
+	return dentry->d_sb->s_fs_info;
+}
+
+#define CIFS_SB(_ptr) \
+	((struct cifs_sb_info *) \
+	 _Generic((_ptr), \
+		  struct cifsInodeInfo * : cinode_to_fsinfo, \
+		  const struct dentry * : const_dentry_to_fsinfo, \
+		  struct super_block * : super_to_fsinfo, \
+		  struct dentry * : dentry_to_fsinfo, \
+		  struct inode * : inode_to_fsinfo, \
+		  struct file * : file_to_fsinfo)(_ptr))
+
+/*
+ * Use atomic_t for @cifs_sb->mnt_cifs_flags as it is currently accessed
+ * locklessly and may be changed concurrently by mount/remount and reconnect
+ * paths.
+ */
+static inline unsigned int cifs_sb_flags(const struct cifs_sb_info *cifs_sb)
+{
+	return atomic_read(&cifs_sb->mnt_cifs_flags);
 }
 
 static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
-		return '/';
-	else
-		return '\\';
+	return (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) ? '/' : '\\';
 }
 
 static inline void
@@ -2314,9 +2349,8 @@ static inline bool __cifs_cache_state_check(struct cifsInodeInfo *cinode,
 					    unsigned int oplock_flags,
 					    unsigned int sb_flags)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode->netfs.inode.i_sb);
+	unsigned int sflags = cifs_sb_flags(CIFS_SB(cinode));
 	unsigned int oplock = READ_ONCE(cinode->oplock);
-	unsigned int sflags = cifs_sb->mnt_cifs_flags;
 
 	return (oplock & oplock_flags) || (sflags & sb_flags);
 }
@@ -2336,4 +2370,9 @@ static inline void cifs_reset_oplock(struct cifsInodeInfo *cinode)
 		WRITE_ONCE(cinode->oplock, 0);
 }
 
+static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi)
+{
+	return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN;
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 33dfe116ca52..87686c804057 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2915,8 +2915,8 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 {
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
-	unsigned int oldflags = old->mnt_cifs_flags & CIFS_MOUNT_MASK;
-	unsigned int newflags = new->mnt_cifs_flags & CIFS_MOUNT_MASK;
+	unsigned int oldflags = cifs_sb_flags(old) & CIFS_MOUNT_MASK;
+	unsigned int newflags = cifs_sb_flags(new) & CIFS_MOUNT_MASK;
 
 	if ((sb->s_flags & CIFS_MS_MASK) != (mnt_data->flags & CIFS_MS_MASK))
 		return 0;
@@ -2971,9 +2971,9 @@ static int match_prepath(struct super_block *sb,
 	struct smb3_fs_context *ctx = mnt_data->ctx;
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
-	bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	bool old_set = (cifs_sb_flags(old) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 		old->prepath;
-	bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) &&
+	bool new_set = (cifs_sb_flags(new) & CIFS_MOUNT_USE_PREFIX_PATH) &&
 		new->prepath;
 
 	if (tcon->origin_fullpath &&
@@ -3004,7 +3004,7 @@ cifs_match_super(struct super_block *sb, void *data)
 	cifs_sb = CIFS_SB(sb);
 
 	/* We do not want to use a superblock that has been shutdown */
-	if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) {
+	if (cifs_forced_shutdown(cifs_sb)) {
 		spin_unlock(&cifs_tcp_ses_lock);
 		return 0;
 	}
@@ -3469,6 +3469,8 @@ ip_connect(struct TCP_Server_Info *server)
 int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 {
 	struct smb3_fs_context *ctx = cifs_sb->ctx;
+	unsigned int sbflags;
+	int rc = 0;
 
 	INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
 	INIT_LIST_HEAD(&cifs_sb->tcon_sb_link);
@@ -3493,17 +3495,16 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 	}
 	ctx->local_nls = cifs_sb->local_nls;
 
-	smb3_update_mnt_flags(cifs_sb);
+	sbflags = smb3_update_mnt_flags(cifs_sb);
 
 	if (ctx->direct_io)
 		cifs_dbg(FYI, "mounting share using direct i/o\n");
 	if (ctx->cache_ro) {
 		cifs_dbg(VFS, "mounting share with read only caching. Ensure that the share will not be modified while in use.\n");
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RO_CACHE;
+		sbflags |= CIFS_MOUNT_RO_CACHE;
 	} else if (ctx->cache_rw) {
 		cifs_dbg(VFS, "mounting share in single client RW caching mode. Ensure that no other systems will be accessing the share.\n");
-		cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_RO_CACHE |
-					    CIFS_MOUNT_RW_CACHE);
+		sbflags |= CIFS_MOUNT_RO_CACHE | CIFS_MOUNT_RW_CACHE;
 	}
 
 	if ((ctx->cifs_acl) && (ctx->dynperm))
@@ -3512,16 +3513,19 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 	if (ctx->prepath) {
 		cifs_sb->prepath = kstrdup(ctx->prepath, GFP_KERNEL);
 		if (cifs_sb->prepath == NULL)
-			return -ENOMEM;
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+			rc = -ENOMEM;
+		else
+			sbflags |= CIFS_MOUNT_USE_PREFIX_PATH;
 	}
 
-	return 0;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+	return rc;
 }
 
 /* Release all succeed connections */
 void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
 {
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
 	int rc = 0;
 
 	if (mnt_ctx->tcon)
@@ -3533,7 +3537,7 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
 	mnt_ctx->ses = NULL;
 	mnt_ctx->tcon = NULL;
 	mnt_ctx->server = NULL;
-	mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
+	atomic_andnot(CIFS_MOUNT_POSIX_PATHS, &cifs_sb->mnt_cifs_flags);
 	free_xid(mnt_ctx->xid);
 }
 
@@ -3587,19 +3591,23 @@ out:
 int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 {
 	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon = NULL;
 	struct cifs_sb_info *cifs_sb;
 	struct smb3_fs_context *ctx;
-	struct cifs_tcon *tcon = NULL;
+	unsigned int sbflags;
 	int rc = 0;
 
-	if (WARN_ON_ONCE(!mnt_ctx || !mnt_ctx->server || !mnt_ctx->ses || !mnt_ctx->fs_ctx ||
-			 !mnt_ctx->cifs_sb)) {
-		rc = -EINVAL;
-		goto out;
+	if (WARN_ON_ONCE(!mnt_ctx))
+		return -EINVAL;
+	if (WARN_ON_ONCE(!mnt_ctx->server || !mnt_ctx->ses ||
+			 !mnt_ctx->fs_ctx || !mnt_ctx->cifs_sb)) {
+		mnt_ctx->tcon = NULL;
+		return -EINVAL;
 	}
 	server = mnt_ctx->server;
 	ctx = mnt_ctx->fs_ctx;
 	cifs_sb = mnt_ctx->cifs_sb;
+	sbflags = cifs_sb_flags(cifs_sb);
 
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(mnt_ctx->ses, ctx);
@@ -3614,9 +3622,9 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * path (i.e., do not remap / and \ and do not map any special characters)
 	 */
 	if (tcon->posix_extensions) {
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-		cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
-					     CIFS_MOUNT_MAP_SPECIAL_CHR);
+		sbflags |= CIFS_MOUNT_POSIX_PATHS;
+		sbflags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
+			     CIFS_MOUNT_MAP_SPECIAL_CHR);
 	}
 
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
@@ -3643,12 +3651,11 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	/* do not care if a following call succeed - informational */
 	if (!tcon->pipe && server->ops->qfs_tcon) {
 		server->ops->qfs_tcon(mnt_ctx->xid, tcon, cifs_sb);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) {
+		if (sbflags & CIFS_MOUNT_RO_CACHE) {
 			if (tcon->fsDevInfo.DeviceCharacteristics &
 			    cpu_to_le32(FILE_READ_ONLY_DEVICE))
 				cifs_dbg(VFS, "mounted to read only share\n");
-			else if ((cifs_sb->mnt_cifs_flags &
-				  CIFS_MOUNT_RW_CACHE) == 0)
+			else if (!(sbflags & CIFS_MOUNT_RW_CACHE))
 				cifs_dbg(VFS, "read only mount of RW share\n");
 			/* no need to log a RW mount of a typical RW share */
 		}
@@ -3660,11 +3667,12 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 	 * Inside cifs_fscache_get_super_cookie it checks
 	 * that we do not get super cookie twice.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
+	if (sbflags & CIFS_MOUNT_FSCACHE)
 		cifs_fscache_get_super_cookie(tcon);
 
 out:
 	mnt_ctx->tcon = tcon;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
 	return rc;
 }
 
@@ -3783,7 +3791,8 @@ int cifs_is_path_remote(struct cifs_mount_ctx *mnt_ctx)
 			cifs_sb, full_path, tcon->Flags & SMB_SHARE_IS_IN_DFS);
 		if (rc != 0) {
 			cifs_server_dbg(VFS, "cannot query dirs between root and final path, enabling CIFS_MOUNT_USE_PREFIX_PATH\n");
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+			atomic_or(CIFS_MOUNT_USE_PREFIX_PATH,
+				  &cifs_sb->mnt_cifs_flags);
 			rc = 0;
 		}
 	}
@@ -3863,7 +3872,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 	 * Force the use of prefix path to support failover on DFS paths that resolve to targets
 	 * that have different prefix paths.
 	 */
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 	kfree(cifs_sb->prepath);
 	cifs_sb->prepath = ctx->prepath;
 	ctx->prepath = NULL;
@@ -4357,7 +4366,7 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
 	kuid_t fsuid = current_fsuid();
 	int err;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		return cifs_get_tlink(cifs_sb_master_tlink(cifs_sb));
 
 	spin_lock(&cifs_sb->tlink_tree_lock);
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 983132735d72..83f8cf2f8d2b 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1333,7 +1333,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
 	 * Force the use of prefix path to support failover on DFS paths that resolve to targets
 	 * that have different prefix paths.
 	 */
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 
 	refresh_tcon_referral(tcon, true);
 	return 0;
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index cb10088197d2..953f1fee8cb8 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -82,10 +82,11 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 					       const char *tree, int tree_len,
 					       bool prefix)
 {
-	int dfsplen;
-	int pplen = 0;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	char dirsep = CIFS_DIR_SEP(cifs_sb);
+	int pplen = 0;
+	int dfsplen;
 	char *s;
 
 	if (unlikely(!page))
@@ -96,7 +97,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 	else
 		dfsplen = 0;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if (sbflags & CIFS_MOUNT_USE_PREFIX_PATH)
 		pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0;
 
 	s = dentry_path_raw(direntry, page, PATH_MAX);
@@ -123,7 +124,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa
 	if (dfsplen) {
 		s -= dfsplen;
 		memcpy(s, tree, dfsplen);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
+		if (sbflags & CIFS_MOUNT_POSIX_PATHS) {
 			int i;
 			for (i = 0; i < dfsplen; i++) {
 				if (s[i] == '\\')
@@ -152,7 +153,7 @@ char *build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page
 static int
 check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry);
 	int i;
 
 	if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength &&
@@ -160,7 +161,7 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon)
 		     le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
 		return -ENAMETOOLONG;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS)) {
 		for (i = 0; i < direntry->d_name.len; i++) {
 			if (direntry->d_name.name[i] == '\\') {
 				cifs_dbg(FYI, "Invalid file name\n");
@@ -181,11 +182,12 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	int rc = -ENOENT;
 	int create_options = CREATE_NOT_DIR;
 	int desired_access;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon = tlink_tcon(tlink);
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct inode *newinode = NULL;
+	unsigned int sbflags;
 	int disposition;
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
@@ -365,6 +367,7 @@ retry_open:
 	 * If Open reported that we actually created a file then we now have to
 	 * set the mode if possible.
 	 */
+	sbflags = cifs_sb_flags(cifs_sb);
 	if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
 		struct cifs_unix_set_info_args args = {
 				.mode	= mode,
@@ -374,7 +377,7 @@ retry_open:
 				.device	= 0,
 		};
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
 				args.gid = inode->i_gid;
@@ -411,9 +414,9 @@ cifs_create_get_file_info:
 			if (server->ops->set_lease_key)
 				server->ops->set_lease_key(newinode, fid);
 			if ((*oplock & CIFS_CREATE_ACTION) && S_ISREG(newinode->i_mode)) {
-				if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+				if (sbflags & CIFS_MOUNT_DYNPERM)
 					newinode->i_mode = mode;
-				if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+				if (sbflags & CIFS_MOUNT_SET_UID) {
 					newinode->i_uid = current_fsuid();
 					if (inode->i_mode & S_ISGID)
 						newinode->i_gid = inode->i_gid;
@@ -458,18 +461,20 @@ int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		 struct file *file, unsigned int oflags, umode_t mode)
 {
-	int rc;
-	unsigned int xid;
-	struct tcon_link *tlink;
-	struct cifs_tcon *tcon;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_open_info_data buf = {};
 	struct TCP_Server_Info *server;
-	struct cifs_fid fid = {};
+	struct cifsFileInfo *file_info;
 	struct cifs_pending_open open;
+	struct cifs_fid fid = {};
+	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	unsigned int sbflags;
+	unsigned int xid;
 	__u32 oplock;
-	struct cifsFileInfo *file_info;
-	struct cifs_open_info_data buf = {};
+	int rc;
 
-	if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb))))
+	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
 
 	/*
@@ -499,7 +504,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
 		 inode, direntry, direntry);
 
-	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink)) {
 		rc = PTR_ERR(tlink);
 		goto out_free_xid;
@@ -536,13 +541,13 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 		goto out;
 	}
 
-	if (file->f_flags & O_DIRECT &&
-	    CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-		if (CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) {
+		if (sbflags & CIFS_MOUNT_NO_BRL)
 			file->f_op = &cifs_file_direct_nobrl_ops;
 		else
 			file->f_op = &cifs_file_direct_ops;
-		}
+	}
 
 	file_info = cifs_new_fileinfo(&fid, file, tlink, oplock, buf.symlink_target);
 	if (file_info == NULL) {
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 18f31d4eb98d..f3ddcdf406c8 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -270,7 +270,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq)
 static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
 	struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode);
 	struct cifsFileInfo *open_file = NULL;
 
 	rreq->rsize = cifs_sb->ctx->rsize;
@@ -281,7 +281,7 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
 		open_file = file->private_data;
 		rreq->netfs_priv = file->private_data;
 		req->cfile = cifsFileInfo_get(open_file);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RWPIDFORWARD)
 			req->pid = req->cfile->pid;
 	} else if (rreq->origin != NETFS_WRITEBACK) {
 		WARN_ON_ONCE(1);
@@ -906,7 +906,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
 		 * close  because it may cause a error when we open this file
 		 * again and get at least level II oplock.
 		 */
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_STRICT_IO)
 			set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
 		cifs_set_oplock_level(cifsi, 0);
 	}
@@ -955,11 +955,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
 int cifs_file_flush(const unsigned int xid, struct inode *inode,
 		    struct cifsFileInfo *cfile)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon;
 	int rc;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC)
 		return 0;
 
 	if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) {
@@ -1015,24 +1015,24 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 int cifs_open(struct inode *inode, struct file *file)
 
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_open_info_data data = {};
+	struct cifsFileInfo *cfile = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_pending_open open;
+	bool posix_open_ok = false;
+	struct cifs_fid fid = {};
+	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	const char *full_path;
+	unsigned int sbflags;
 	int rc = -EACCES;
 	unsigned int xid;
 	__u32 oplock;
-	struct cifs_sb_info *cifs_sb;
-	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon;
-	struct tcon_link *tlink;
-	struct cifsFileInfo *cfile = NULL;
 	void *page;
-	const char *full_path;
-	bool posix_open_ok = false;
-	struct cifs_fid fid = {};
-	struct cifs_pending_open open;
-	struct cifs_open_info_data data = {};
 
 	xid = get_xid();
 
-	cifs_sb = CIFS_SB(inode->i_sb);
 	if (unlikely(cifs_forced_shutdown(cifs_sb))) {
 		free_xid(xid);
 		return smb_EIO(smb_eio_trace_forced_shutdown);
@@ -1056,9 +1056,9 @@ int cifs_open(struct inode *inode, struct file *file)
 	cifs_dbg(FYI, "inode = 0x%p file flags are 0x%x for %s\n",
 		 inode, file->f_flags, full_path);
 
-	if (file->f_flags & O_DIRECT &&
-	    cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) {
+		if (sbflags & CIFS_MOUNT_NO_BRL)
 			file->f_op = &cifs_file_direct_nobrl_ops;
 		else
 			file->f_op = &cifs_file_direct_ops;
@@ -1209,7 +1209,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode);
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 
 	down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
@@ -1222,7 +1222,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		rc = cifs_push_posix_locks(cfile);
 	else
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
@@ -2011,7 +2011,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cinode);
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 
 	/* we are going to update can_cache_brlcks here - need a write access */
@@ -2024,7 +2024,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		rc = cifs_push_posix_locks(cfile);
 	else
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
@@ -2428,11 +2428,11 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 	cifs_read_flock(fl, &type, &lock, &unlock, &wait_flag,
 			tcon->ses->server);
-	cifs_sb = CIFS_FILE_SB(file);
+	cifs_sb = CIFS_SB(file);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		posix_lck = true;
 
 	if (!lock && !unlock) {
@@ -2455,14 +2455,14 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl)
 
 int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 {
-	int rc, xid;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
+	struct cifsFileInfo *cfile;
 	int lock = 0, unlock = 0;
 	bool wait_flag = false;
 	bool posix_lck = false;
-	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	struct cifsFileInfo *cfile;
 	__u32 type;
+	int rc, xid;
 
 	rc = -EACCES;
 	xid = get_xid();
@@ -2477,12 +2477,11 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 
 	cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag,
 			tcon->ses->server);
-	cifs_sb = CIFS_FILE_SB(file);
 	set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
+	    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0))
 		posix_lck = true;
 	/*
 	 * BB add code here to normalize offset and length to account for
@@ -2532,11 +2531,11 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
 struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 					bool fsuid_only)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode);
 	struct cifsFileInfo *open_file = NULL;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
 
 	/* only filter by fsuid on multiuser mounts */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
 	spin_lock(&cifs_inode->open_file_lock);
@@ -2589,10 +2588,10 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
 		return rc;
 	}
 
-	cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb);
+	cifs_sb = CIFS_SB(cifs_inode);
 
 	/* only filter by fsuid on multiuser mounts */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
 	spin_lock(&cifs_inode->open_file_lock);
@@ -2787,7 +2786,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct TCP_Server_Info *server;
 	struct cifsFileInfo *smbfile = file->private_data;
 	struct inode *inode = file_inode(file);
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 
 	rc = file_write_and_wait_range(file, start, end);
 	if (rc) {
@@ -2801,7 +2800,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		 file, datasync);
 
 	tcon = tlink_tcon(smbfile->tlink);
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
 		if (server->ops->flush == NULL) {
 			rc = -ENOSYS;
@@ -2853,7 +2852,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file->f_mapping->host;
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	ssize_t rc;
 
 	rc = netfs_start_io_write(inode);
@@ -2870,7 +2869,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	if (rc <= 0)
 		goto out;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) &&
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) &&
 	    (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
 				     server->vals->exclusive_lock_type, 0,
 				     NULL, CIFS_WRITE_OP))) {
@@ -2893,7 +2892,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)
 						iocb->ki_filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -2906,7 +2905,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 	if (CIFS_CACHE_WRITE(cinode)) {
 		if (cap_unix(tcon->ses) &&
 		    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-		    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+		    ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
 			written = netfs_file_write_iter(iocb, from);
 			goto out;
 		}
@@ -2994,7 +2993,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)
 						iocb->ki_filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -3011,7 +3010,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 	if (!CIFS_CACHE_READ(cinode))
 		return netfs_unbuffered_read_iter(iocb, to);
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) {
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0) {
 		if (iocb->ki_flags & IOCB_DIRECT)
 			return netfs_unbuffered_read_iter(iocb, to);
 		return netfs_buffered_read_iter(iocb, to);
@@ -3130,10 +3129,9 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file,
 	if (is_inode_writable(cifsInode) ||
 		((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) {
 		/* This inode is open for write at least once */
-		struct cifs_sb_info *cifs_sb;
+		struct cifs_sb_info *cifs_sb = CIFS_SB(cifsInode);
 
-		cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DIRECT_IO) {
 			/* since no page cache to corrupt on directio
 			we can change size safely */
 			return true;
@@ -3181,7 +3179,7 @@ void cifs_oplock_break(struct work_struct *work)
 	server = tcon->ses->server;
 
 	scoped_guard(spinlock, &cinode->open_file_lock) {
-		unsigned int sbflags = cifs_sb->mnt_cifs_flags;
+		unsigned int sbflags = cifs_sb_flags(cifs_sb);
 
 		server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
 					      cfile->oplock_epoch, &purge_cache);
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 09fe749e97ee..54090739535f 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -2062,161 +2062,160 @@ smb3_cleanup_fs_context(struct smb3_fs_context *ctx)
 	kfree(ctx);
 }
 
-void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb)
+unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	struct smb3_fs_context *ctx = cifs_sb->ctx;
 
 	if (ctx->nodfs)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_DFS;
+		sbflags |= CIFS_MOUNT_NO_DFS;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_DFS;
+		sbflags &= ~CIFS_MOUNT_NO_DFS;
 
 	if (ctx->noperm)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
+		sbflags |= CIFS_MOUNT_NO_PERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_PERM;
+		sbflags &= ~CIFS_MOUNT_NO_PERM;
 
 	if (ctx->setuids)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID;
+		sbflags |= CIFS_MOUNT_SET_UID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SET_UID;
+		sbflags &= ~CIFS_MOUNT_SET_UID;
 
 	if (ctx->setuidfromacl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UID_FROM_ACL;
+		sbflags |= CIFS_MOUNT_UID_FROM_ACL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UID_FROM_ACL;
+		sbflags &= ~CIFS_MOUNT_UID_FROM_ACL;
 
 	if (ctx->server_ino)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
+		sbflags |= CIFS_MOUNT_SERVER_INUM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
+		sbflags &= ~CIFS_MOUNT_SERVER_INUM;
 
 	if (ctx->remap)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SFM_CHR;
+		sbflags |= CIFS_MOUNT_MAP_SFM_CHR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SFM_CHR;
+		sbflags &= ~CIFS_MOUNT_MAP_SFM_CHR;
 
 	if (ctx->sfu_remap)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
+		sbflags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR;
+		sbflags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR;
 
 	if (ctx->no_xattr)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR;
+		sbflags |= CIFS_MOUNT_NO_XATTR;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_XATTR;
+		sbflags &= ~CIFS_MOUNT_NO_XATTR;
 
 	if (ctx->sfu_emul)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
+		sbflags |= CIFS_MOUNT_UNX_EMUL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UNX_EMUL;
+		sbflags &= ~CIFS_MOUNT_UNX_EMUL;
 
 	if (ctx->nobrl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
+		sbflags |= CIFS_MOUNT_NO_BRL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_BRL;
+		sbflags &= ~CIFS_MOUNT_NO_BRL;
 
 	if (ctx->nohandlecache)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE;
+		sbflags |= CIFS_MOUNT_NO_HANDLE_CACHE;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_HANDLE_CACHE;
+		sbflags &= ~CIFS_MOUNT_NO_HANDLE_CACHE;
 
 	if (ctx->nostrictsync)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC;
+		sbflags |= CIFS_MOUNT_NOSSYNC;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOSSYNC;
+		sbflags &= ~CIFS_MOUNT_NOSSYNC;
 
 	if (ctx->mand_lock)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOPOSIXBRL;
+		sbflags |= CIFS_MOUNT_NOPOSIXBRL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOPOSIXBRL;
+		sbflags &= ~CIFS_MOUNT_NOPOSIXBRL;
 
 	if (ctx->rwpidforward)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD;
+		sbflags |= CIFS_MOUNT_RWPIDFORWARD;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_RWPIDFORWARD;
+		sbflags &= ~CIFS_MOUNT_RWPIDFORWARD;
 
 	if (ctx->mode_ace)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MODE_FROM_SID;
+		sbflags |= CIFS_MOUNT_MODE_FROM_SID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MODE_FROM_SID;
+		sbflags &= ~CIFS_MOUNT_MODE_FROM_SID;
 
 	if (ctx->cifs_acl)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
+		sbflags |= CIFS_MOUNT_CIFS_ACL;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_ACL;
+		sbflags &= ~CIFS_MOUNT_CIFS_ACL;
 
 	if (ctx->backupuid_specified)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID;
+		sbflags |= CIFS_MOUNT_CIFS_BACKUPUID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPUID;
+		sbflags &= ~CIFS_MOUNT_CIFS_BACKUPUID;
 
 	if (ctx->backupgid_specified)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID;
+		sbflags |= CIFS_MOUNT_CIFS_BACKUPGID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPGID;
+		sbflags &= ~CIFS_MOUNT_CIFS_BACKUPGID;
 
 	if (ctx->override_uid)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID;
+		sbflags |= CIFS_MOUNT_OVERR_UID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_UID;
+		sbflags &= ~CIFS_MOUNT_OVERR_UID;
 
 	if (ctx->override_gid)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID;
+		sbflags |= CIFS_MOUNT_OVERR_GID;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_GID;
+		sbflags &= ~CIFS_MOUNT_OVERR_GID;
 
 	if (ctx->dynperm)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM;
+		sbflags |= CIFS_MOUNT_DYNPERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DYNPERM;
+		sbflags &= ~CIFS_MOUNT_DYNPERM;
 
 	if (ctx->fsc)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_FSCACHE;
+		sbflags |= CIFS_MOUNT_FSCACHE;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_FSCACHE;
+		sbflags &= ~CIFS_MOUNT_FSCACHE;
 
 	if (ctx->multiuser)
-		cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER |
-					    CIFS_MOUNT_NO_PERM);
+		sbflags |= CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER;
+		sbflags &= ~CIFS_MOUNT_MULTIUSER;
 
 
 	if (ctx->strict_io)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO;
+		sbflags |= CIFS_MOUNT_STRICT_IO;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_STRICT_IO;
+		sbflags &= ~CIFS_MOUNT_STRICT_IO;
 
 	if (ctx->direct_io)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
+		sbflags |= CIFS_MOUNT_DIRECT_IO;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DIRECT_IO;
+		sbflags &= ~CIFS_MOUNT_DIRECT_IO;
 
 	if (ctx->mfsymlinks)
-		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS;
+		sbflags |= CIFS_MOUNT_MF_SYMLINKS;
 	else
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MF_SYMLINKS;
-	if (ctx->mfsymlinks) {
-		if (ctx->sfu_emul) {
-			/*
-			 * Our SFU ("Services for Unix") emulation allows now
-			 * creating new and reading existing SFU symlinks.
-			 * Older Linux kernel versions were not able to neither
-			 * read existing nor create new SFU symlinks. But
-			 * creating and reading SFU style mknod and FIFOs was
-			 * supported for long time. When "mfsymlinks" and
-			 * "sfu" are both enabled at the same time, it allows
-			 * reading both types of symlinks, but will only create
-			 * them with mfsymlinks format. This allows better
-			 * Apple compatibility, compatibility with older Linux
-			 * kernel clients (probably better for Samba too)
-			 * while still recognizing old Windows style symlinks.
-			 */
-			cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n");
-		}
-	}
-	cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SHUTDOWN;
+		sbflags &= ~CIFS_MOUNT_MF_SYMLINKS;
 
-	return;
+	if (ctx->mfsymlinks && ctx->sfu_emul) {
+		/*
+		 * Our SFU ("Services for Unix") emulation allows now
+		 * creating new and reading existing SFU symlinks.
+		 * Older Linux kernel versions were not able to neither
+		 * read existing nor create new SFU symlinks. But
+		 * creating and reading SFU style mknod and FIFOs was
+		 * supported for long time. When "mfsymlinks" and
+		 * "sfu" are both enabled at the same time, it allows
+		 * reading both types of symlinks, but will only create
+		 * them with mfsymlinks format. This allows better
+		 * Apple compatibility, compatibility with older Linux
+		 * kernel clients (probably better for Samba too)
+		 * while still recognizing old Windows style symlinks.
+		 */
+		cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n");
+	}
+	sbflags &= ~CIFS_MOUNT_SHUTDOWN;
+	atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+	return sbflags;
 }
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 49b2a6f09ca2..0b64fcb5d302 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -374,7 +374,7 @@ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx,
 			struct smb3_fs_context *ctx);
 int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb,
 				    struct cifs_ses *ses);
-void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
+unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
 
 /*
  * max deferred close timeout (jiffies) - 2^30
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index d4d3cfeb6c90..3e844c55ab8a 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -40,32 +40,33 @@ static void cifs_set_netfs_context(struct inode *inode)
 
 static void cifs_set_ops(struct inode *inode)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &cifs_file_inode_ops;
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
+		if (sbflags & CIFS_MOUNT_DIRECT_IO) {
 			set_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags);
-			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+			if (sbflags & CIFS_MOUNT_NO_BRL)
 				inode->i_fop = &cifs_file_direct_nobrl_ops;
 			else
 				inode->i_fop = &cifs_file_direct_ops;
-		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
-			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+		} else if (sbflags & CIFS_MOUNT_STRICT_IO) {
+			if (sbflags & CIFS_MOUNT_NO_BRL)
 				inode->i_fop = &cifs_file_strict_nobrl_ops;
 			else
 				inode->i_fop = &cifs_file_strict_ops;
-		} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
+		} else if (sbflags & CIFS_MOUNT_NO_BRL)
 			inode->i_fop = &cifs_file_nobrl_ops;
 		else { /* not direct, send byte range locks */
 			inode->i_fop = &cifs_file_ops;
 		}
 
 		/* check if server can support readahead */
-		if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read <
-				PAGE_SIZE + MAX_CIFS_HDR_SIZE)
+		if (tcon->ses->server->max_read < PAGE_SIZE + MAX_CIFS_HDR_SIZE)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
 		else
 			inode->i_data.a_ops = &cifs_addr_ops;
@@ -194,8 +195,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
 	inode->i_gid = fattr->cf_gid;
 
 	/* if dynperm is set, don't clobber existing mode */
-	if (inode_state_read(inode) & I_NEW ||
-	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM))
+	if ((inode_state_read(inode) & I_NEW) ||
+	    !(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DYNPERM))
 		inode->i_mode = fattr->cf_mode;
 
 	cifs_i->cifsAttrs = fattr->cf_cifsattrs;
@@ -248,10 +249,8 @@ cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
-		return;
-
-	fattr->cf_uniqueid = iunique(sb, ROOT_I);
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM))
+		fattr->cf_uniqueid = iunique(sb, ROOT_I);
 }
 
 /* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */
@@ -259,6 +258,8 @@ void
 cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 			 struct cifs_sb_info *cifs_sb)
 {
+	unsigned int sbflags;
+
 	memset(fattr, 0, sizeof(*fattr));
 	fattr->cf_uniqueid = le64_to_cpu(info->UniqueId);
 	fattr->cf_bytes = le64_to_cpu(info->NumOfBytes);
@@ -317,8 +318,9 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 		break;
 	}
 
+	sbflags = cifs_sb_flags(cifs_sb);
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) {
+	if (!(sbflags & CIFS_MOUNT_OVERR_UID)) {
 		u64 id = le64_to_cpu(info->Uid);
 		if (id < ((uid_t)-1)) {
 			kuid_t uid = make_kuid(&init_user_ns, id);
@@ -328,7 +330,7 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
 	}
 	
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) {
+	if (!(sbflags & CIFS_MOUNT_OVERR_GID)) {
 		u64 id = le64_to_cpu(info->Gid);
 		if (id < ((gid_t)-1)) {
 			kgid_t gid = make_kgid(&init_user_ns, id);
@@ -382,7 +384,7 @@ static int update_inode_info(struct super_block *sb,
 	 *
 	 * If file type or uniqueid is different, return error.
 	 */
-	if (unlikely((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+	if (unlikely((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) &&
 		     CIFS_I(*inode)->uniqueid != fattr->cf_uniqueid)) {
 		CIFS_I(*inode)->time = 0; /* force reval */
 		return -ESTALE;
@@ -468,7 +470,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path,
 		cifs_fill_uniqueid(sb, fattr);
 
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1081,7 +1083,7 @@ cifs_backup_query_path_info(int xid,
 	else if ((tcon->ses->capabilities &
 		  tcon->ses->server->vals->cap_nt_find) == 0)
 		info.info_level = SMB_FIND_FILE_INFO_STANDARD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+	else if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)
 		info.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	else /* no srvino useful for fallback to some netapp */
 		info.info_level = SMB_FIND_FILE_DIRECTORY_INFO;
@@ -1109,7 +1111,7 @@ static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_blo
 	struct TCP_Server_Info *server = tcon->ses->server;
 	int rc;
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)) {
 		if (*inode)
 			fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid;
 		else
@@ -1263,14 +1265,15 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 			  struct inode **inode,
 			  const char *full_path)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_open_info_data tmp_data = {};
-	struct cifs_tcon *tcon;
+	void *smb1_backup_rsp_buf = NULL;
 	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon;
 	struct tcon_link *tlink;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	void *smb1_backup_rsp_buf = NULL;
-	int rc = 0;
+	unsigned int sbflags;
 	int tmprc = 0;
+	int rc = 0;
 
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
@@ -1370,16 +1373,17 @@ static int cifs_get_fattr(struct cifs_open_info_data *data,
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 handle_mnt_opt:
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
+	sbflags = cifs_sb_flags(cifs_sb);
 	/* query for SFU type info if supported and needed */
 	if ((fattr->cf_cifsattrs & ATTR_SYSTEM) &&
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) {
+	    (sbflags & CIFS_MOUNT_UNX_EMUL)) {
 		tmprc = cifs_sfu_type(fattr, full_path, cifs_sb, xid);
 		if (tmprc)
 			cifs_dbg(FYI, "cifs_sfu_type failed: %d\n", tmprc);
 	}
 
 	/* fill in 0777 bits from ACL */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) {
+	if (sbflags & CIFS_MOUNT_MODE_FROM_SID) {
 		rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode,
 				       true, full_path, fid);
 		if (rc == -EREMOTE)
@@ -1389,7 +1393,7 @@ handle_mnt_opt:
 				 __func__, rc);
 			goto out;
 		}
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
+	} else if (sbflags & CIFS_MOUNT_CIFS_ACL) {
 		rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode,
 				       false, full_path, fid);
 		if (rc == -EREMOTE)
@@ -1399,7 +1403,7 @@ handle_mnt_opt:
 				 __func__, rc);
 			goto out;
 		}
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
+	} else if (sbflags & CIFS_MOUNT_UNX_EMUL)
 		/* fill in remaining high mode bits e.g. SUID, VTX */
 		cifs_sfu_mode(fattr, full_path, cifs_sb, xid);
 	else if (!(tcon->posix_extensions))
@@ -1409,7 +1413,7 @@ handle_mnt_opt:
 
 
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (sbflags & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1509,7 +1513,7 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data,
 	 * 3. Tweak fattr based on mount options
 	 */
 	/* check for Minshall+French symlinks */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) {
 		tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path);
 		cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
 	}
@@ -1660,7 +1664,7 @@ struct inode *cifs_root_iget(struct super_block *sb)
 	int len;
 	int rc;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+	if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH)
 	    && cifs_sb->prepath) {
 		len = strlen(cifs_sb->prepath);
 		path = kzalloc(len + 2 /* leading sep + null */, GFP_KERNEL);
@@ -2098,8 +2102,9 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 		 const char *full_path, struct cifs_sb_info *cifs_sb,
 		 struct cifs_tcon *tcon, const unsigned int xid)
 {
-	int rc = 0;
 	struct inode *inode = NULL;
+	unsigned int sbflags;
+	int rc = 0;
 
 	if (tcon->posix_extensions) {
 		rc = smb311_posix_get_inode_info(&inode, full_path,
@@ -2139,6 +2144,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 	if (parent->i_mode & S_ISGID)
 		mode |= S_ISGID;
 
+	sbflags = cifs_sb_flags(cifs_sb);
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (tcon->unix_ext) {
 		struct cifs_unix_set_info_args args = {
@@ -2148,7 +2154,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 			.mtime	= NO_CHANGE_64,
 			.device	= 0,
 		};
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (parent->i_mode & S_ISGID)
 				args.gid = parent->i_gid;
@@ -2166,14 +2172,14 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 	{
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 		struct TCP_Server_Info *server = tcon->ses->server;
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
+		if (!(sbflags & CIFS_MOUNT_CIFS_ACL) &&
 		    (mode & S_IWUGO) == 0 && server->ops->mkdir_setinfo)
 			server->ops->mkdir_setinfo(inode, full_path, cifs_sb,
 						   tcon, xid);
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
+		if (sbflags & CIFS_MOUNT_DYNPERM)
 			inode->i_mode = (mode | S_IFDIR);
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			inode->i_uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
 				inode->i_gid = parent->i_gid;
@@ -2686,7 +2692,7 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct cached_fid *cfid = NULL;
 
@@ -2727,7 +2733,7 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 	}
 
 	/* hardlinked files w/ noserverino get "special" treatment */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) &&
 	    S_ISREG(inode->i_mode) && inode->i_nlink != 1)
 		return true;
 
@@ -2752,10 +2758,10 @@ cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 int
 cifs_revalidate_mapping(struct inode *inode)
 {
-	int rc;
 	struct cifsInodeInfo *cifs_inode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	unsigned long *flags = &cifs_inode->flags;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	int rc;
 
 	/* swapfiles are not supposed to be shared */
 	if (IS_SWAPFILE(inode))
@@ -2768,7 +2774,7 @@ cifs_revalidate_mapping(struct inode *inode)
 
 	if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) {
 		/* for cache=singleclient, do not invalidate */
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RW_CACHE)
 			goto skip_invalidate;
 
 		cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size;
@@ -2892,10 +2898,11 @@ int cifs_revalidate_dentry(struct dentry *dentry)
 int cifs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		 struct kstat *stat, u32 request_mask, unsigned int flags)
 {
-	struct dentry *dentry = path->dentry;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(path->dentry);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	struct dentry *dentry = path->dentry;
 	struct inode *inode = d_inode(dentry);
+	unsigned int sbflags;
 	int rc;
 
 	if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb))))
@@ -2952,12 +2959,13 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	 * enabled, and the admin hasn't overridden them, set the ownership
 	 * to the fsuid/fsgid of the current process.
 	 */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) &&
-	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
+	sbflags = cifs_sb_flags(cifs_sb);
+	if ((sbflags & CIFS_MOUNT_MULTIUSER) &&
+	    !(sbflags & CIFS_MOUNT_CIFS_ACL) &&
 	    !tcon->unix_ext) {
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID))
+		if (!(sbflags & CIFS_MOUNT_OVERR_UID))
 			stat->uid = current_fsuid();
-		if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID))
+		if (!(sbflags & CIFS_MOUNT_OVERR_GID))
 			stat->gid = current_fsgid();
 	}
 	return 0;
@@ -3102,7 +3110,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	void *page = alloc_dentry_path();
 	struct inode *inode = d_inode(direntry);
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	struct cifs_unix_set_info_args *args = NULL;
@@ -3113,7 +3121,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 
 	xid = get_xid();
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
 
 	rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs);
@@ -3266,26 +3274,26 @@ out:
 static int
 cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 {
-	unsigned int xid;
-	kuid_t uid = INVALID_UID;
-	kgid_t gid = INVALID_GID;
 	struct inode *inode = d_inode(direntry);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	struct cifsFileInfo *cfile = NULL;
-	const char *full_path;
 	void *page = alloc_dentry_path();
-	int rc = -EACCES;
-	__u32 dosattr = 0;
 	__u64 mode = NO_CHANGE_64;
-	bool posix = cifs_sb_master_tcon(cifs_sb)->posix_extensions;
+	kuid_t uid = INVALID_UID;
+	kgid_t gid = INVALID_GID;
+	const char *full_path;
+	__u32 dosattr = 0;
+	int rc = -EACCES;
+	unsigned int xid;
 
 	xid = get_xid();
 
 	cifs_dbg(FYI, "setattr on file %pd attrs->ia_valid 0x%x\n",
 		 direntry, attrs->ia_valid);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+	if (sbflags & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;
 
 	rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs);
@@ -3346,8 +3354,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if (attrs->ia_valid & ATTR_GID)
 		gid = attrs->ia_gid;
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)) {
+	if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) {
 		if (uid_valid(uid) || gid_valid(gid)) {
 			mode = NO_CHANGE_64;
 			rc = id_mode_to_cifs_acl(inode, full_path, &mode,
@@ -3358,9 +3365,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 				goto cifs_setattr_exit;
 			}
 		}
-	} else
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID))
+	} else if (!(sbflags & CIFS_MOUNT_SET_UID)) {
 		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
+	}
 
 	/* skip mode change if it's just for clearing setuid/setgid */
 	if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
@@ -3369,9 +3376,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 	if (attrs->ia_valid & ATTR_MODE) {
 		mode = attrs->ia_mode;
 		rc = 0;
-		if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-		    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) ||
-		    posix) {
+		if ((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) ||
+		    cifs_sb_master_tcon(cifs_sb)->posix_extensions) {
 			rc = id_mode_to_cifs_acl(inode, full_path, &mode,
 						INVALID_UID, INVALID_GID);
 			if (rc) {
@@ -3393,7 +3399,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 			dosattr = cifsInode->cifsAttrs | ATTR_READONLY;
 
 			/* fix up mode if we're not using dynperm */
-			if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
+			if ((sbflags & CIFS_MOUNT_DYNPERM) == 0)
 				attrs->ia_mode = inode->i_mode & ~S_IWUGO;
 		} else if ((mode & S_IWUGO) &&
 			   (cifsInode->cifsAttrs & ATTR_READONLY)) {
@@ -3404,7 +3410,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 				dosattr |= ATTR_NORMAL;
 
 			/* reset local inode permissions to normal */
-			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+			if (!(sbflags & CIFS_MOUNT_DYNPERM)) {
 				attrs->ia_mode &= ~(S_IALLUGO);
 				if (S_ISDIR(inode->i_mode))
 					attrs->ia_mode |=
@@ -3413,7 +3419,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 					attrs->ia_mode |=
 						cifs_sb->ctx->file_mode;
 			}
-		} else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
+		} else if (!(sbflags & CIFS_MOUNT_DYNPERM)) {
 			/* ignore mode change - ATTR_READONLY hasn't changed */
 			attrs->ia_valid &= ~ATTR_MODE;
 		}
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 8dc2651e237f..9afab3237e54 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -216,7 +216,7 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
 	 */
 	case CIFS_GOING_FLAGS_LOGFLUSH:
 	case CIFS_GOING_FLAGS_NOLOGFLUSH:
-		sbi->mnt_cifs_flags |= CIFS_MOUNT_SHUTDOWN;
+		atomic_or(CIFS_MOUNT_SHUTDOWN, &sbi->mnt_cifs_flags);
 		goto shutdown_good;
 	default:
 		rc = -EINVAL;
diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c
index a2f7bfa8ad1e..434e8fe74080 100644
--- a/fs/smb/client/link.c
+++ b/fs/smb/client/link.c
@@ -544,14 +544,15 @@ int
 cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	     struct dentry *direntry, const char *symname)
 {
-	int rc = -EOPNOTSUPP;
-	unsigned int xid;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	struct inode *newinode = NULL;
 	struct tcon_link *tlink;
 	struct cifs_tcon *pTcon;
 	const char *full_path;
+	int rc = -EOPNOTSUPP;
+	unsigned int sbflags;
+	unsigned int xid;
 	void *page;
-	struct inode *newinode = NULL;
 
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
@@ -580,6 +581,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	cifs_dbg(FYI, "symname is %s\n", symname);
 
 	/* BB what if DFS and this volume is on different share? BB */
+	sbflags = cifs_sb_flags(cifs_sb);
 	rc = -EOPNOTSUPP;
 	switch (cifs_symlink_type(cifs_sb)) {
 	case CIFS_SYMLINK_TYPE_UNIX:
@@ -594,14 +596,14 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 		break;
 
 	case CIFS_SYMLINK_TYPE_MFSYMLINKS:
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+		if (sbflags & CIFS_MOUNT_MF_SYMLINKS) {
 			rc = create_mf_symlink(xid, pTcon, cifs_sb,
 					       full_path, symname);
 		}
 		break;
 
 	case CIFS_SYMLINK_TYPE_SFU:
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+		if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 			rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon,
 						  full_path, S_IFLNK,
 						  0, symname);
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 22cde46309fe..bc24c92b8b95 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -275,13 +275,15 @@ dump_smb(void *buf, int smb_buf_length)
 void
 cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		struct cifs_tcon *tcon = NULL;
 
 		if (cifs_sb->master_tlink)
 			tcon = cifs_sb_master_tcon(cifs_sb);
 
-		cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM;
+		atomic_andnot(CIFS_MOUNT_SERVER_INUM, &cifs_sb->mnt_cifs_flags);
 		cifs_sb->mnt_cifs_serverino_autodisabled = true;
 		cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s\n",
 			 tcon ? tcon->tree_name : "new server");
@@ -382,11 +384,13 @@ void cifs_done_oplock_break(struct cifsInodeInfo *cinode)
 bool
 backup_cred(struct cifs_sb_info *cifs_sb)
 {
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) {
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
+
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID) {
 		if (uid_eq(cifs_sb->ctx->backupuid, current_fsuid()))
 			return true;
 	}
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) {
+	if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID) {
 		if (in_group_p(cifs_sb->ctx->backupgid))
 			return true;
 	}
@@ -955,7 +959,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix)
 			convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb));
 	}
 
-	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+	atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags);
 	return 0;
 }
 
@@ -984,7 +988,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
 	 * look up or tcon is not DFS.
 	 */
 	if (strlen(full_path) < 2 || !cifs_sb ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) ||
+	    (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS) ||
 	    !is_tcon_dfs(tcon))
 		return 0;
 
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index 8615a8747b7f..be22bbc4a65a 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -121,7 +121,7 @@ retry:
 			 * want to clobber the existing one with the one that
 			 * the readdir code created.
 			 */
-			if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM))
+			if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM))
 				fattr->cf_uniqueid = CIFS_I(inode)->uniqueid;
 
 			/*
@@ -177,6 +177,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
 	struct cifs_open_info_data data = {
 		.reparse = { .tag = fattr->cf_cifstag, },
 	};
+	unsigned int sbflags;
 
 	fattr->cf_uid = cifs_sb->ctx->linux_uid;
 	fattr->cf_gid = cifs_sb->ctx->linux_gid;
@@ -215,12 +216,12 @@ out_reparse:
 	 * may look wrong since the inodes may not have timed out by the time
 	 * "ls" does a stat() call on them.
 	 */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
-	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID))
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID))
 		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL &&
-	    fattr->cf_cifsattrs & ATTR_SYSTEM) {
+	if ((sbflags & CIFS_MOUNT_UNX_EMUL) &&
+	    (fattr->cf_cifsattrs & ATTR_SYSTEM)) {
 		if (fattr->cf_eof == 0)  {
 			fattr->cf_mode &= ~S_IFMT;
 			fattr->cf_mode |= S_IFIFO;
@@ -345,13 +346,14 @@ static int
 _initiate_cifs_search(const unsigned int xid, struct file *file,
 		     const char *full_path)
 {
-	__u16 search_flags;
-	int rc = 0;
-	struct cifsFileInfo *cifsFile;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 	struct tcon_link *tlink = NULL;
-	struct cifs_tcon *tcon;
 	struct TCP_Server_Info *server;
+	struct cifsFileInfo *cifsFile;
+	struct cifs_tcon *tcon;
+	unsigned int sbflags;
+	__u16 search_flags;
+	int rc = 0;
 
 	if (file->private_data == NULL) {
 		tlink = cifs_sb_tlink(cifs_sb);
@@ -385,6 +387,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file,
 	cifs_dbg(FYI, "Full path: %s start at: %lld\n", full_path, file->f_pos);
 
 ffirst_retry:
+	sbflags = cifs_sb_flags(cifs_sb);
 	/* test for Unix extensions */
 	/* but now check for them on the share/mount not on the SMB session */
 	/* if (cap_unix(tcon->ses) { */
@@ -395,7 +398,7 @@ ffirst_retry:
 	else if ((tcon->ses->capabilities &
 		  tcon->ses->server->vals->cap_nt_find) == 0) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_INFO_STANDARD;
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
+	} else if (sbflags & CIFS_MOUNT_SERVER_INUM) {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
 	} else /* not srvinos - BB fixme add check for backlevel? */ {
 		cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO;
@@ -411,8 +414,7 @@ ffirst_retry:
 
 	if (rc == 0) {
 		cifsFile->invalidHandle = false;
-	} else if ((rc == -EOPNOTSUPP) &&
-		   (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	} else if (rc == -EOPNOTSUPP && (sbflags & CIFS_MOUNT_SERVER_INUM)) {
 		cifs_autodisable_serverino(cifs_sb);
 		goto ffirst_retry;
 	}
@@ -690,7 +692,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
 	loff_t first_entry_in_buffer;
 	loff_t index_to_find = pos;
 	struct cifsFileInfo *cfile = file->private_data;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	/* check if index in the buffer */
 
@@ -955,6 +957,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_dirent de = { NULL, };
 	struct cifs_fattr fattr;
+	unsigned int sbflags;
 	struct qstr name;
 	int rc = 0;
 
@@ -1019,15 +1022,15 @@ static int cifs_filldir(char *find_entry, struct file *file,
 		break;
 	}
 
-	if (de.ino && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) {
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (de.ino && (sbflags & CIFS_MOUNT_SERVER_INUM)) {
 		fattr.cf_uniqueid = de.ino;
 	} else {
 		fattr.cf_uniqueid = iunique(sb, ROOT_I);
 		cifs_autodisable_serverino(cifs_sb);
 	}
 
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) &&
-	    couldbe_mf_symlink(&fattr))
+	if ((sbflags & CIFS_MOUNT_MF_SYMLINKS) && couldbe_mf_symlink(&fattr))
 		/*
 		 * trying to get the type and mode can be slow,
 		 * so just call those regular files for now, and mark
@@ -1058,7 +1061,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct cached_fid *cfid = NULL;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(file);
 
 	xid = get_xid();
 
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index ce9b923498b5..cd1e1eaee67a 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -55,17 +55,18 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 				 const char *full_path, const char *symname)
 {
 	struct reparse_symlink_data_buffer *buf = NULL;
-	struct cifs_open_info_data data = {};
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
 	const char *symroot = cifs_sb->ctx->symlinkroot;
+	struct cifs_open_info_data data = {};
+	char sep = CIFS_DIR_SEP(cifs_sb);
+	char *symlink_target = NULL;
+	u16 len, plen, poff, slen;
+	unsigned int sbflags;
+	__le16 *path = NULL;
 	struct inode *new;
+	char *sym = NULL;
 	struct kvec iov;
-	__le16 *path = NULL;
 	bool directory;
-	char *symlink_target = NULL;
-	char *sym = NULL;
-	char sep = CIFS_DIR_SEP(cifs_sb);
-	u16 len, plen, poff, slen;
 	int rc = 0;
 
 	if (strlen(symname) > REPARSE_SYM_PATH_MAX)
@@ -83,8 +84,8 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		.symlink_target = symlink_target,
 	};
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
-	    symroot && symname[0] == '/') {
+	sbflags = cifs_sb_flags(cifs_sb);
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symroot && symname[0] == '/') {
 		/*
 		 * This is a request to create an absolute symlink on the server
 		 * which does not support POSIX paths, and expects symlink in
@@ -164,7 +165,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 	 * mask these characters in NT object prefix by '_' and then change
 	 * them back.
 	 */
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/')
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/')
 		sym[0] = sym[1] = sym[2] = sym[5] = '_';
 
 	path = cifs_convert_path_to_utf16(sym, cifs_sb);
@@ -173,7 +174,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		goto out;
 	}
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
 		sym[0] = '\\';
 		sym[1] = sym[2] = '?';
 		sym[5] = ':';
@@ -197,7 +198,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 	slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX);
 	poff = 0;
 	plen = slen;
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+	if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
 		/*
 		 * For absolute NT symlinks skip leading "\\??\\" in PrintName as
 		 * PrintName is user visible location in DOS/Win32 format (not in NT format).
@@ -824,7 +825,7 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
 		goto out;
 	}
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
+	if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) &&
 	    symroot && !relative) {
 		/*
 		 * This is an absolute symlink from the server which does not
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index 570b0d25aeba..0164dc47bdfd 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -33,7 +33,7 @@ static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb,
 {
 	u32 uid = le32_to_cpu(*(__le32 *)ptr);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_UID)
 		return cifs_sb->ctx->linux_uid;
 	return make_kuid(current_user_ns(), uid);
 }
@@ -43,7 +43,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb,
 {
 	u32 gid = le32_to_cpu(*(__le32 *)ptr);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_GID)
 		return cifs_sb->ctx->linux_gid;
 	return make_kgid(current_user_ns(), gid);
 }
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index aed49aaef8c4..9643eca0cb70 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -49,6 +49,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 
 	if (!CIFSSMBQFSUnixInfo(xid, tcon)) {
 		__u64 cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
+		unsigned int sbflags;
 
 		cifs_dbg(FYI, "unix caps which server supports %lld\n", cap);
 		/*
@@ -75,14 +76,16 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 		if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)
 			cifs_dbg(VFS, "per-share encryption not supported yet\n");
 
+		if (cifs_sb)
+			sbflags = cifs_sb_flags(cifs_sb);
+
 		cap &= CIFS_UNIX_CAP_MASK;
 		if (ctx && ctx->no_psx_acl)
 			cap &= ~CIFS_UNIX_POSIX_ACL_CAP;
 		else if (CIFS_UNIX_POSIX_ACL_CAP & cap) {
 			cifs_dbg(FYI, "negotiated posix acl support\n");
 			if (cifs_sb)
-				cifs_sb->mnt_cifs_flags |=
-					CIFS_MOUNT_POSIXACL;
+				sbflags |= CIFS_MOUNT_POSIXACL;
 		}
 
 		if (ctx && ctx->posix_paths == 0)
@@ -90,10 +93,12 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 		else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) {
 			cifs_dbg(FYI, "negotiate posix pathnames\n");
 			if (cifs_sb)
-				cifs_sb->mnt_cifs_flags |=
-					CIFS_MOUNT_POSIX_PATHS;
+				sbflags |= CIFS_MOUNT_POSIX_PATHS;
 		}
 
+		if (cifs_sb)
+			atomic_set(&cifs_sb->mnt_cifs_flags, sbflags);
+
 		cifs_dbg(FYI, "Negotiate caps 0x%x\n", (int)cap);
 #ifdef CONFIG_CIFS_DEBUG2
 		if (cap & CIFS_UNIX_FCNTL_CAP)
@@ -1147,7 +1152,7 @@ static int cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 				__u64 volatile_fid, __u16 net_fid,
 				struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__u8 op;
 
 	op = !!((oplock & CIFS_CACHE_READ_FLG) || (sbflags & CIFS_MOUNT_RO_CACHE));
@@ -1282,7 +1287,8 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 	       struct dentry *dentry, struct cifs_tcon *tcon,
 	       const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode);
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	struct inode *newinode = NULL;
 	int rc;
 
@@ -1298,7 +1304,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 			.mtime	= NO_CHANGE_64,
 			.device	= dev,
 		};
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
+		if (sbflags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			args.gid = current_fsgid();
 		} else {
@@ -1317,7 +1323,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
 		if (rc == 0)
 			d_instantiate(dentry, newinode);
 		return rc;
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+	} else if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 		/*
 		 * Check if mounted with mount parm 'sfu' mount parm.
 		 * SFU emulation should work with all servers
diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c
index 1ab41de2b634..ed651c946251 100644
--- a/fs/smb/client/smb2file.c
+++ b/fs/smb/client/smb2file.c
@@ -72,7 +72,7 @@ int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_i
 	 * POSIX server does not distinguish between symlinks to file and
 	 * symlink directory. So nothing is needed to fix on the client side.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS)
 		return 0;
 
 	if (!*target)
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index e19674d9b92b..973fce3c959c 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -455,17 +455,8 @@ calc_size_exit:
 __le16 *
 cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 {
-	int len;
 	const char *start_of_path;
-	__le16 *to;
-	int map_type;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
-		map_type = SFM_MAP_UNI_RSVD;
-	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
-		map_type = SFU_MAP_UNI_RSVD;
-	else
-		map_type = NO_MAP_UNI_RSVD;
+	int len;
 
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
@@ -479,14 +470,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	} else
 		start_of_path = from;
 
-	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
-				   cifs_sb->local_nls, map_type);
-	return to;
+	return cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
+				     cifs_sb->local_nls, cifs_remap(cifs_sb));
 }
 
 __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__le32 lease = 0;
 
 	if ((oplock & CIFS_CACHE_WRITE_FLG) || (sbflags & CIFS_MOUNT_RW_CACHE))
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index fea9a35caa57..7f2d3459cbf9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -986,7 +986,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon,
 				rc = -EREMOTE;
 		}
 		if (rc == -EREMOTE && IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) &&
-		    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS))
+		    (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS))
 			rc = -EOPNOTSUPP;
 		goto out;
 	}
@@ -2691,7 +2691,7 @@ static int smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
 				__u64 volatile_fid, __u16 net_fid,
 				struct cifsInodeInfo *cinode, unsigned int oplock)
 {
-	unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags;
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode));
 	__u8 op;
 
 	if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
@@ -5332,7 +5332,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode,
 			  struct dentry *dentry, struct cifs_tcon *tcon,
 			  const char *full_path, umode_t mode, dev_t dev)
 {
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode));
 	int rc = -EOPNOTSUPP;
 
 	/*
@@ -5341,7 +5341,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode,
 	 * supports block and char device, socket & fifo,
 	 * and was used by default in earlier versions of Windows
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+	if (sbflags & CIFS_MOUNT_UNX_EMUL) {
 		rc = cifs_sfu_make_node(xid, inode, dentry, tcon,
 					full_path, mode, dev);
 	} else if (CIFS_REPARSE_SUPPORT(tcon)) {
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index ef655acf673d..a2a96d817717 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3182,22 +3182,19 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 	}
 
 	if ((oparms->disposition != FILE_OPEN) && (oparms->cifs_sb)) {
+		unsigned int sbflags = cifs_sb_flags(oparms->cifs_sb);
 		bool set_mode;
 		bool set_owner;
 
-		if ((oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) &&
-		    (oparms->mode != ACL_NO_MODE))
+		if ((sbflags & CIFS_MOUNT_MODE_FROM_SID) &&
+		    oparms->mode != ACL_NO_MODE) {
 			set_mode = true;
-		else {
+		} else {
 			set_mode = false;
 			oparms->mode = ACL_NO_MODE;
 		}
 
-		if (oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
-			set_owner = true;
-		else
-			set_owner = false;
-
+		set_owner = sbflags & CIFS_MOUNT_UID_FROM_ACL;
 		if (set_owner | set_mode) {
 			cifs_dbg(FYI, "add sd with mode 0x%x\n", oparms->mode);
 			rc = add_sd_context(iov, &n_iov, oparms->mode, set_owner);
diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c
index e1a7d9a10a53..23227f2f9428 100644
--- a/fs/smb/client/xattr.c
+++ b/fs/smb/client/xattr.c
@@ -149,7 +149,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 			break;
 		}
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 			goto out;
 
 		if (pTcon->ses->server->ops->set_EA) {
@@ -309,7 +309,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 			break;
 		}
 
-		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+		if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 			goto out;
 
 		if (pTcon->ses->server->ops->query_all_EAs)
@@ -398,7 +398,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
+	if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR)
 		return -EOPNOTSUPP;
 
 	tlink = cifs_sb_tlink(cifs_sb);
-- 
cgit v1.2.3


From d9d1e319b39ea685ede59319002d567c159d23c3 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 25 Feb 2026 21:34:55 -0300
Subject: smb: client: fix broken multichannel with krb5+signing

When mounting a share with 'multichannel,max_channels=n,sec=krb5i',
the client was duplicating signing key for all secondary channels,
thus making the server fail all commands sent from secondary channels
due to bad signatures.

Every channel has its own signing key, so when establishing a new
channel with krb5 auth, make sure to use the new session key as the
derived key to generate channel's signing key in SMB2_auth_kerberos().

Repro:

$ mount.cifs //srv/share /mnt -o multichannel,max_channels=4,sec=krb5i
$ sleep 5
$ umount /mnt
$ dmesg
  ...
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x4 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13

Reported-by: Xiaoli Feng <xifeng@redhat.com>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a2a96d817717..04e361ed2356 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1714,19 +1714,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 	is_binding = (ses->ses_status == SES_GOOD);
 	spin_unlock(&ses->ses_lock);
 
-	/* keep session key if binding */
-	if (!is_binding) {
-		kfree_sensitive(ses->auth_key.response);
-		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
-						 GFP_KERNEL);
-		if (!ses->auth_key.response) {
-			cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n",
-				 msg->sesskey_len);
-			rc = -ENOMEM;
-			goto out_put_spnego_key;
-		}
-		ses->auth_key.len = msg->sesskey_len;
+	kfree_sensitive(ses->auth_key.response);
+	ses->auth_key.response = kmemdup(msg->data,
+					 msg->sesskey_len,
+					 GFP_KERNEL);
+	if (!ses->auth_key.response) {
+		cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n",
+			 __func__, msg->sesskey_len);
+		rc = -ENOMEM;
+		goto out_put_spnego_key;
 	}
+	ses->auth_key.len = msg->sesskey_len;
 
 	sess_data->iov[1].iov_base = msg->data + msg->sesskey_len;
 	sess_data->iov[1].iov_len = msg->secblob_len;
-- 
cgit v1.2.3


From 2f37dc436d4e61ff7ae0b0353cf91b8c10396e4d Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 26 Feb 2026 22:28:45 +0100
Subject: smb: client: Don't log plaintext credentials in cifs_set_cifscreds

When debug logging is enabled, cifs_set_cifscreds() logs the key
payload and exposes the plaintext username and password. Remove the
debug log to avoid exposing credentials.

Fixes: 8a8798a5ff90 ("cifs: fetch credentials out of keyring for non-krb5 auth multiuser mounts")
Cc: stable@vger.kernel.org
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 87686c804057..4c34d9603e05 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2236,7 +2236,6 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	/* find first : in payload */
 	payload = upayload->data;
 	delim = strnchr(payload, upayload->datalen, ':');
-	cifs_dbg(FYI, "payload=%s\n", payload);
 	if (!delim) {
 		cifs_dbg(FYI, "Unable to find ':' in payload (datalen=%d)\n",
 			 upayload->datalen);
-- 
cgit v1.2.3


From e35626f610f3d2b7953ccddf6a77453da22b3a9e Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Tue, 24 Feb 2026 21:28:32 +0100
Subject: net/sched: ets: fix divide by zero in the offload path

Offloading ETS requires computing each class' WRR weight: this is done by
averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned
int, the same integer size as the individual DRR quanta, can overflow and
even cause division by zero, like it happened in the following splat:

 Oops: divide error: 0000 [#1] SMP PTI
 CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G            E       6.19.0-virtme #45 PREEMPT(full)
 Tainted: [E]=UNSIGNED_MODULE
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Call Trace:
  <TASK>
  ets_qdisc_change+0x870/0xf40 [sch_ets]
  qdisc_create+0x12b/0x540
  tc_modify_qdisc+0x6d7/0xbd0
  rtnetlink_rcv_msg+0x168/0x6b0
  netlink_rcv_skb+0x5c/0x110
  netlink_unicast+0x1d6/0x2b0
  netlink_sendmsg+0x22e/0x470
  ____sys_sendmsg+0x38a/0x3c0
  ___sys_sendmsg+0x99/0xe0
  __sys_sendmsg+0x8a/0xf0
  do_syscall_64+0x111/0xf80
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
 RIP: 0033:0x7f440b81c77e
 Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa
 RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e
 RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003
 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8
 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980
  </TASK>
 Modules linked in: sch_ets(E) netdevsim(E)
 ---[ end trace 0000000000000000 ]---
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
 ---[ end Kernel panic - not syncing: Fatal exception ]---

Fix this using 64-bit integers for 'q_sum' and 'q_psum'.

Cc: stable@vger.kernel.org
Fixes: d35eb52bd2ac ("net: sch_ets: Make the ETS qdisc offloadable")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/28504887df314588c7255e9911769c36f751edee.1771964872.git.dcaratti@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_ets.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 306e046276d4..a4b07b661b77 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch)
 	struct ets_sched *q = qdisc_priv(sch);
 	struct tc_ets_qopt_offload qopt;
 	unsigned int w_psum_prev = 0;
-	unsigned int q_psum = 0;
-	unsigned int q_sum = 0;
 	unsigned int quantum;
 	unsigned int w_psum;
 	unsigned int weight;
 	unsigned int i;
+	u64 q_psum = 0;
+	u64 q_sum = 0;
 
 	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
 		return;
@@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch)
 
 	for (i = 0; i < q->nbands; i++) {
 		quantum = q->classes[i].quantum;
-		q_psum += quantum;
-		w_psum = quantum ? q_psum * 100 / q_sum : 0;
+		if (quantum) {
+			q_psum += quantum;
+			w_psum = div64_u64(q_psum * 100, q_sum);
+		} else {
+			w_psum = 0;
+		}
 		weight = w_psum - w_psum_prev;
 		w_psum_prev = w_psum;
 
-- 
cgit v1.2.3


From 2ef2b20cf4e04ac8a6ba68493f8780776ff84300 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 25 Feb 2026 13:15:47 +0000
Subject: net: annotate data-races around sk->sk_{data_ready,write_space}

skmsg (and probably other layers) are changing these pointers
while other cpus might read them concurrently.

Add corresponding READ_ONCE()/WRITE_ONCE() annotations
for UDP, TCP and AF_UNIX.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by: syzbot+87f770387a9e5dc6b79b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/699ee9fc.050a0220.1cd54b.0009.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260225131547.1085509-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skmsg.c         | 14 +++++++-------
 net/ipv4/tcp.c           |  4 ++--
 net/ipv4/tcp_bpf.c       |  2 +-
 net/ipv4/tcp_input.c     | 14 ++++++++------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/udp.c           |  2 +-
 net/ipv4/udp_bpf.c       |  2 +-
 net/unix/af_unix.c       |  8 ++++----
 8 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2e26174c9919..3261793abe83 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_strp_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
@@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
-	psock->saved_data_ready = NULL;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
+	WRITE_ONCE(psock->saved_data_ready, NULL);
 	strp_stop(&psock->strp);
 }
 
@@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_verdict_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
@@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
 	psock->saved_data_ready = NULL;
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f84d9a45cc9d..8cdc26e8ad68 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1446,7 +1446,7 @@ out_err:
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
 	if (binding)
@@ -4181,7 +4181,7 @@ ao_parse:
 		break;
 	case TCP_NOTSENT_LOWAT:
 		WRITE_ONCE(tp->notsent_lowat, val);
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		break;
 	case TCP_INQ:
 		if (val > 1 || val < 0)
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index c449a044895e..813d2e498c93 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 			WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
 			tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 		} else {
-			sk->sk_write_space = psock->saved_write_space;
+			WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 			/* Pairs with lockless read in sk_clone_lock() */
 			sock_replace_proto(sk, psock->sk_proto);
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 41c57efd125c..6404e53382ca 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5425,7 +5425,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM);
 		return;
 	}
@@ -5635,7 +5635,7 @@ err:
 void tcp_data_ready(struct sock *sk)
 {
 	if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE))
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5691,7 +5691,7 @@ queue_and_out:
 			inet_csk(sk)->icsk_ack.pending |=
 					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
 			inet_csk_schedule_ack(sk);
-			sk->sk_data_ready(sk);
+			READ_ONCE(sk->sk_data_ready)(sk);
 
 			if (skb_queue_len(&sk->sk_receive_queue) && skb->len) {
 				reason = SKB_DROP_REASON_PROTO_MEM;
@@ -6114,7 +6114,9 @@ static void tcp_new_space(struct sock *sk)
 		tp->snd_cwnd_stamp = tcp_jiffies32;
 	}
 
-	INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk);
+	INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space),
+			sk_stream_write_space,
+			sk);
 }
 
 /* Caller made space either from:
@@ -6325,7 +6327,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 				BUG();
 			WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp);
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk);
+				READ_ONCE(sk->sk_data_ready)(sk);
 		}
 	}
 }
@@ -7792,7 +7794,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			sock_put(fastopen_sk);
 			goto drop_and_free;
 		}
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
 	} else {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index d9c5a43bd281..dafb63b923d0 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 		reason = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent);
+			READ_ONCE(parent->sk_data_ready)(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6c6b68a66dcd..014fdfdd331b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 		 * using prepare_to_wait_exclusive().
 		 */
 		while (nb) {
-			INDIRECT_CALL_1(sk->sk_data_ready,
+			INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready),
 					sock_def_readable, sk);
 			nb--;
 		}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 91233e37cd97..779a3a03762f 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
 
 	if (restore) {
-		sk->sk_write_space = psock->saved_write_space;
+		WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3756a93dc63a..7eaa5b187fef 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1785,7 +1785,7 @@ restart:
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	return 0;
 
@@ -2278,7 +2278,7 @@ restart_locked:
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	scm_destroy(&scm);
 	return len;
@@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 
 	return 0;
 out_unlock:
@@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		spin_unlock(&other->sk_receive_queue.lock);
 
 		unix_state_unlock(other);
-		other->sk_data_ready(other);
+		READ_ONCE(other->sk_data_ready)(other);
 		sent += size;
 	}
 
-- 
cgit v1.2.3


From 93c9475c04acad2457a7e7ea4e3ec40a6e6d94a7 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 25 Feb 2026 16:39:55 +0200
Subject: bridge: Check relevant per-VLAN options in VLAN range grouping

The br_vlan_opts_eq_range() function determines if consecutive VLANs can
be grouped together in a range for compact netlink notifications. It
currently checks state, tunnel info, and multicast router configuration,
but misses two categories of per-VLAN options that affect the output:
1. User-visible priv_flags (neigh_suppress, mcast_enabled)
2. Port multicast context (mcast_max_groups, mcast_n_groups)

When VLANs have different settings for these options, they are incorrectly
grouped into ranges, causing netlink notifications to report only one
VLAN's settings for the entire range.

Fix by checking priv_flags equality, but only for flags that affect netlink
output (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED and BR_VLFLAG_MCAST_ENABLED),
and comparing multicast context (mcast_max_groups and mcast_n_groups).

Example showing the bugs before the fix:

$ bridge vlan set vid 10 dev dummy1 neigh_suppress on
$ bridge vlan set vid 11 dev dummy1 neigh_suppress off
$ bridge -d vlan show dev dummy1
  port             vlan-id
  dummy1           10-11
                      ... neigh_suppress on

$ bridge vlan set vid 10 dev dummy1 mcast_max_groups 100
$ bridge vlan set vid 11 dev dummy1 mcast_max_groups 200
$ bridge -d vlan show dev dummy1
  port             vlan-id
  dummy1           10-11
                      ... mcast_max_groups 100

After the fix, VLANs 10 and 11 are shown as separate entries with their
correct individual settings.

Fixes: a1aee20d5db2 ("net: bridge: Add netlink knobs for number / maximum MDB entries")
Fixes: 83f6d600796c ("bridge: vlan: Allow setting VLAN neighbor suppression state")
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260225143956.3995415-2-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_private.h      | 10 ++++++++++
 net/bridge/br_vlan_options.c | 26 +++++++++++++++++++++++---
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b9b2981c4841..9b55d38ea9ed 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1344,6 +1344,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1,
 	       true;
 }
 
+static inline bool
+br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1,
+				    const struct net_bridge_mcast_port *pmctx2)
+{
+	return br_multicast_ngroups_get(pmctx1) ==
+	       br_multicast_ngroups_get(pmctx2) &&
+	       br_multicast_ngroups_get_max(pmctx1) ==
+	       br_multicast_ngroups_get_max(pmctx2);
+}
+
 static inline bool
 br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx)
 {
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
index 8fa89b04ee94..5514e1fc8d1f 100644
--- a/net/bridge/br_vlan_options.c
+++ b/net/bridge/br_vlan_options.c
@@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr,
 	u8 range_mc_rtr = br_vlan_multicast_router(range_end);
 	u8 curr_mc_rtr = br_vlan_multicast_router(v_curr);
 
-	return v_curr->state == range_end->state &&
-	       __vlan_tun_can_enter_range(v_curr, range_end) &&
-	       curr_mc_rtr == range_mc_rtr;
+	if (v_curr->state != range_end->state)
+		return false;
+
+	if (!__vlan_tun_can_enter_range(v_curr, range_end))
+		return false;
+
+	if (curr_mc_rtr != range_mc_rtr)
+		return false;
+
+	/* Check user-visible priv_flags that affect output */
+	if ((v_curr->priv_flags ^ range_end->priv_flags) &
+	    (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED))
+		return false;
+
+#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+	if (!br_vlan_is_master(v_curr) &&
+	    !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) &&
+	    !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx,
+						 &range_end->port_mcast_ctx))
+		return false;
+#endif
+
+	return true;
 }
 
 bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v,
-- 
cgit v1.2.3


From 13540021be228dcda63d02b2245ce8dad01d8473 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Wed, 25 Feb 2026 16:39:56 +0200
Subject: selftests: net: Add bridge VLAN range grouping tests

Add a new test file bridge_vlan_dump.sh with four test cases that verify
VLANs with different per-VLAN options are not incorrectly grouped into
ranges in the dump output.

The tests verify the kernel's br_vlan_opts_eq_range() function correctly
prevents VLAN range grouping when neigh_suppress, mcast_max_groups,
mcast_n_groups, or mcast_enabled options differ.

Each test verifies that VLANs with different option values appear as
individual entries rather than ranges, and that VLANs with matching
values are properly grouped together.

Example output:

$ ./bridge_vlan_dump.sh
TEST: VLAN range grouping with neigh_suppress                       [ OK ]
TEST: VLAN range grouping with mcast_max_groups                     [ OK ]
TEST: VLAN range grouping with mcast_n_groups                       [ OK ]
TEST: VLAN range grouping with mcast_enabled                        [ OK ]

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20260225143956.3995415-3-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile            |   1 +
 tools/testing/selftests/net/bridge_vlan_dump.sh | 204 ++++++++++++++++++++++++
 2 files changed, 205 insertions(+)
 create mode 100755 tools/testing/selftests/net/bridge_vlan_dump.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index afdea6d95bde..605c54c0e8a3 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -15,6 +15,7 @@ TEST_PROGS := \
 	big_tcp.sh \
 	bind_bhash.sh \
 	bpf_offload.py \
+	bridge_vlan_dump.sh \
 	broadcast_ether_dst.sh \
 	broadcast_pmtu.sh \
 	busy_poll_test.sh \
diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh
new file mode 100755
index 000000000000..ad66731d2a6f
--- /dev/null
+++ b/tools/testing/selftests/net/bridge_vlan_dump.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in
+# the dump if they have the same per-VLAN options. These tests verify that
+# VLANs with different per-VLAN option values are not grouped together.
+
+# shellcheck disable=SC1091,SC2034,SC2154,SC2317
+source lib.sh
+
+ALL_TESTS="
+	vlan_range_neigh_suppress
+	vlan_range_mcast_max_groups
+	vlan_range_mcast_n_groups
+	vlan_range_mcast_enabled
+"
+
+setup_prepare()
+{
+	setup_ns NS
+	defer cleanup_all_ns
+
+	ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \
+		vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1
+	ip -n "$NS" link set dev br0 up
+
+	ip -n "$NS" link add name dummy0 type dummy
+	ip -n "$NS" link set dev dummy0 master br0
+	ip -n "$NS" link set dev dummy0 up
+}
+
+vlan_range_neigh_suppress()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different neigh_suppress values and verify no range grouping
+	bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on
+	check_err $? "Failed to set neigh_suppress for VLAN 10"
+
+	bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off
+	check_err $? "Failed to set neigh_suppress for VLAN 11"
+
+	# Verify VLANs are not shown as a range, but individual entries exist
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different neigh_suppress incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same neigh_suppress value and verify range grouping
+	bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on
+	check_err $? "Failed to set neigh_suppress for VLAN 11"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same neigh_suppress not grouped"
+
+	log_test "VLAN range grouping with neigh_suppress"
+}
+
+vlan_range_mcast_max_groups()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different mcast_max_groups values and verify no range grouping
+	bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100
+	check_err $? "Failed to set mcast_max_groups for VLAN 10"
+
+	bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200
+	check_err $? "Failed to set mcast_max_groups for VLAN 11"
+
+	# Verify VLANs are not shown as a range, but individual entries exist
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_max_groups incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same mcast_max_groups value and verify range grouping
+	bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100
+	check_err $? "Failed to set mcast_max_groups for VLAN 11"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_max_groups not grouped"
+
+	log_test "VLAN range grouping with mcast_max_groups"
+}
+
+vlan_range_mcast_n_groups()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Add different numbers of multicast groups to each VLAN
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10
+	check_err $? "Failed to add mdb entry to VLAN 10"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10
+
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10
+	check_err $? "Failed to add second mdb entry to VLAN 10"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10
+
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11
+	check_err $? "Failed to add mdb entry to VLAN 11"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11
+
+	# Verify VLANs are not shown as a range due to different mcast_n_groups
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_n_groups incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Add another group to VLAN 11 to match VLAN 10's count
+	bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11
+	check_err $? "Failed to add second mdb entry to VLAN 11"
+	defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_n_groups not grouped"
+
+	log_test "VLAN range grouping with mcast_n_groups"
+}
+
+vlan_range_mcast_enabled()
+{
+	RET=0
+
+	# Add two new consecutive VLANs for range grouping test
+	bridge -n "$NS" vlan add vid 10 dev br0 self
+	defer bridge -n "$NS" vlan del vid 10 dev br0 self
+
+	bridge -n "$NS" vlan add vid 11 dev br0 self
+	defer bridge -n "$NS" vlan del vid 11 dev br0 self
+
+	bridge -n "$NS" vlan add vid 10 dev dummy0
+	defer bridge -n "$NS" vlan del vid 10 dev dummy0
+
+	bridge -n "$NS" vlan add vid 11 dev dummy0
+	defer bridge -n "$NS" vlan del vid 11 dev dummy0
+
+	# Configure different mcast_snooping for bridge VLANs
+	# Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs
+	bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1
+	bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0
+
+	# Verify port VLANs are not grouped due to different mcast_enabled
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_fail $? "VLANs with different mcast_enabled incorrectly grouped"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$"
+	check_err $? "VLAN 10 individual entry not found"
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$"
+	check_err $? "VLAN 11 individual entry not found"
+
+	# Configure same mcast_snooping and verify range grouping
+	bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1
+
+	bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11"
+	check_err $? "VLANs with same mcast_enabled not grouped"
+
+	log_test "VLAN range grouping with mcast_enabled"
+}
+
+# Verify the newest tested option is supported
+if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then
+	echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support"
+	exit "$ksft_skip"
+fi
+
+trap defer_scopes_cleanup EXIT
+setup_prepare
+tests_run
+
+exit "$EXIT_STATUS"
-- 
cgit v1.2.3


From be11a537224d72b906db6b98510619770298c8a4 Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Tue, 24 Feb 2026 23:43:59 +0530
Subject: net: ethernet: ti: am65-cpsw-nuss/cpsw-ale: Fix multicast entry
 handling in ALE table

In the current implementation, flushing multicast entries in MAC mode
incorrectly deletes entries for all ports instead of only the target port,
disrupting multicast traffic on other ports. The cause is adding multicast
entries by setting only host port bit, and not setting the MAC port bits.

Fix this by setting the MAC port's bit in the port mask while adding the
multicast entry. Also fix the flush logic to preserve the host port bit
during removal of MAC port and free ALE entries when mask contains only
host port.

Fixes: 5c50a856d550 ("drivers: net: ethernet: cpsw: add multicast address to ALE table")
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260224181359.2055322-1-c-vankar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 drivers/net/ethernet/ti/cpsw_ale.c       | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 5924db6be3fe..967918050433 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(common->ale,
 			      ndev->flags & IFF_ALLMULTI, port->port_id);
 
-	port_mask = ALE_PORT_HOST;
+	port_mask = BIT(port->port_id) | ALE_PORT_HOST;
 	/* Clear all mcast from ALE */
 	cpsw_ale_flush_multicast(common->ale, port_mask, -1);
 
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index bb969dd435b4..be7b69319221 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -450,14 +450,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 				      ale->port_mask_bits);
 	if ((mask & port_mask) == 0)
 		return; /* ports dont intersect, not interested */
-	mask &= ~port_mask;
+	mask &= (~port_mask | ALE_PORT_HOST);
 
-	/* free if only remaining port is host port */
-	if (mask)
+	if (mask == 0x0 || mask == ALE_PORT_HOST)
+		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+	else
 		cpsw_ale_set_port_mask(ale_entry, mask,
 				       ale->port_mask_bits);
-	else
-		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
 int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
-- 
cgit v1.2.3


From 4fc87c240b8f30e22b7ebaae29d57105589e1c0b Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Tue, 10 Feb 2026 23:28:20 +0000
Subject: rust_binder: fix oneway spam detection

The spam detection logic in TreeRange was executed before the current
request was inserted into the tree. So the new request was not being
factored in the spam calculation. Fix this by moving the logic after
the new range has been inserted.

Also, the detection logic for ArrayRange was missing altogether which
meant large spamming transactions could get away without being detected.
Fix this by implementing an equivalent low_oneway_space() in ArrayRange.

Note that I looked into centralizing this logic in RangeAllocator but
iterating through 'state' and 'size' got a bit too complicated (for me)
and I abandoned this effort.

Cc: stable <stable@kernel.org>
Cc: Alice Ryhl <aliceryhl@google.com>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://patch.msgid.link/20260210232949.3770644-1-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/range_alloc/array.rs | 35 +++++++++++++++++++++++++++--
 drivers/android/binder/range_alloc/mod.rs   |  4 ++--
 drivers/android/binder/range_alloc/tree.rs  | 18 +++++++--------
 3 files changed, 44 insertions(+), 13 deletions(-)

diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs
index 07e1dec2ce63..ada1d1b4302e 100644
--- a/drivers/android/binder/range_alloc/array.rs
+++ b/drivers/android/binder/range_alloc/array.rs
@@ -118,7 +118,7 @@ impl<T> ArrayRangeAllocator<T> {
         size: usize,
         is_oneway: bool,
         pid: Pid,
-    ) -> Result<usize> {
+    ) -> Result<(usize, bool)> {
         // Compute new value of free_oneway_space, which is set only on success.
         let new_oneway_space = if is_oneway {
             match self.free_oneway_space.checked_sub(size) {
@@ -146,7 +146,38 @@ impl<T> ArrayRangeAllocator<T> {
             .ok()
             .unwrap();
 
-        Ok(insert_at_offset)
+        // Start detecting spammers once we have less than 20%
+        // of async space left (which is less than 10% of total
+        // buffer size).
+        //
+        // (This will short-circuit, so `low_oneway_space` is
+        // only called when necessary.)
+        let oneway_spam_detected =
+            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
+
+        Ok((insert_at_offset, oneway_spam_detected))
+    }
+
+    /// Find the amount and size of buffers allocated by the current caller.
+    ///
+    /// The idea is that once we cross the threshold, whoever is responsible
+    /// for the low async space is likely to try to send another async transaction,
+    /// and at some point we'll catch them in the act.  This is more efficient
+    /// than keeping a map per pid.
+    fn low_oneway_space(&self, calling_pid: Pid) -> bool {
+        let mut total_alloc_size = 0;
+        let mut num_buffers = 0;
+
+        // Warn if this pid has more than 50 transactions, or more than 50% of
+        // async space (which is 25% of total buffer size). Oneway spam is only
+        // detected when the threshold is exceeded.
+        for range in &self.ranges {
+            if range.state.is_oneway() && range.state.pid() == calling_pid {
+                total_alloc_size += range.size;
+                num_buffers += 1;
+            }
+        }
+        num_buffers > 50 || total_alloc_size > self.size / 4
     }
 
     pub(crate) fn reservation_abort(&mut self, offset: usize) -> Result<FreedRange> {
diff --git a/drivers/android/binder/range_alloc/mod.rs b/drivers/android/binder/range_alloc/mod.rs
index 2301e2bc1a1f..1f4734468ff1 100644
--- a/drivers/android/binder/range_alloc/mod.rs
+++ b/drivers/android/binder/range_alloc/mod.rs
@@ -188,11 +188,11 @@ impl<T> RangeAllocator<T> {
                 self.reserve_new(args)
             }
             Impl::Array(array) => {
-                let offset =
+                let (offset, oneway_spam_detected) =
                     array.reserve_new(args.debug_id, args.size, args.is_oneway, args.pid)?;
                 Ok(ReserveNew::Success(ReserveNewSuccess {
                     offset,
-                    oneway_spam_detected: false,
+                    oneway_spam_detected,
                     _empty_array_alloc: args.empty_array_alloc,
                     _new_tree_alloc: args.new_tree_alloc,
                     _tree_alloc: args.tree_alloc,
diff --git a/drivers/android/binder/range_alloc/tree.rs b/drivers/android/binder/range_alloc/tree.rs
index 838fdd2b47ea..48796fcdb362 100644
--- a/drivers/android/binder/range_alloc/tree.rs
+++ b/drivers/android/binder/range_alloc/tree.rs
@@ -164,15 +164,6 @@ impl<T> TreeRangeAllocator<T> {
             self.free_oneway_space
         };
 
-        // Start detecting spammers once we have less than 20%
-        // of async space left (which is less than 10% of total
-        // buffer size).
-        //
-        // (This will short-circut, so `low_oneway_space` is
-        // only called when necessary.)
-        let oneway_spam_detected =
-            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
-
         let (found_size, found_off, tree_node, free_tree_node) = match self.find_best_match(size) {
             None => {
                 pr_warn!("ENOSPC from range_alloc.reserve_new - size: {}", size);
@@ -203,6 +194,15 @@ impl<T> TreeRangeAllocator<T> {
             self.free_tree.insert(free_tree_node);
         }
 
+        // Start detecting spammers once we have less than 20%
+        // of async space left (which is less than 10% of total
+        // buffer size).
+        //
+        // (This will short-circuit, so `low_oneway_space` is
+        // only called when necessary.)
+        let oneway_spam_detected =
+            is_oneway && new_oneway_space < self.size / 10 && self.low_oneway_space(pid);
+
         Ok((found_off, oneway_spam_detected))
     }
 
-- 
cgit v1.2.3


From 8ef2c15aeae07647f530d30f6daaf79eb801bcd1 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 11:53:26 +0000
Subject: rust_binder: check ownership before using vma

When installing missing pages (or zapping them), Rust Binder will look
up the vma in the mm by address, and then call vm_insert_page (or
zap_page_range_single). However, if the vma is closed and replaced with
a different vma at the same address, this can lead to Rust Binder
installing pages into the wrong vma.

By installing the page into a writable vma, it becomes possible to write
to your own binder pages, which are normally read-only. Although you're
not supposed to be able to write to those pages, the intent behind the
design of Rust Binder is that even if you get that ability, it should not
lead to anything bad. Unfortunately, due to another bug, that is not the
case.

To fix this, store a pointer in vm_private_data and check that the vma
returned by vma_lookup() has the right vm_ops and vm_private_data before
trying to use the vma. This should ensure that Rust Binder will refuse
to interact with any other VMA. The plan is to introduce more vma
abstractions to avoid this unsafe access to vm_ops and vm_private_data,
but for now let's start with the simplest possible fix.

C Binder performs the same check in a slightly different way: it
provides a vm_ops->close that sets a boolean to true, then checks that
boolean after calling vma_lookup(), but this is more fragile
than the solution in this patch. (We probably still want to do both, but
the vm_ops->close callback will be added later as part of the follow-up
vma API changes.)

It's still possible to remap the vma so that pages appear in the right
vma, but at the wrong offset, but this is a separate issue and will be
fixed when Rust Binder gets a vm_ops->close callback.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-check-v2-1-60f9d695a990@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/page_range.rs | 83 +++++++++++++++++++++++++++---------
 1 file changed, 63 insertions(+), 20 deletions(-)

diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
index fdd97112ef5c..67aae783e8b8 100644
--- a/drivers/android/binder/page_range.rs
+++ b/drivers/android/binder/page_range.rs
@@ -142,6 +142,30 @@ pub(crate) struct ShrinkablePageRange {
     _pin: PhantomPinned,
 }
 
+// We do not define any ops. For now, used only to check identity of vmas.
+static BINDER_VM_OPS: bindings::vm_operations_struct = pin_init::zeroed();
+
+// To ensure that we do not accidentally install pages into or zap pages from the wrong vma, we
+// check its vm_ops and private data before using it.
+fn check_vma(vma: &virt::VmaRef, owner: *const ShrinkablePageRange) -> Option<&virt::VmaMixedMap> {
+    // SAFETY: Just reading the vm_ops pointer of any active vma is safe.
+    let vm_ops = unsafe { (*vma.as_ptr()).vm_ops };
+    if !ptr::eq(vm_ops, &BINDER_VM_OPS) {
+        return None;
+    }
+
+    // SAFETY: Reading the vm_private_data pointer of a binder-owned vma is safe.
+    let vm_private_data = unsafe { (*vma.as_ptr()).vm_private_data };
+    // The ShrinkablePageRange is only dropped when the Process is dropped, which only happens once
+    // the file's ->release handler is invoked, which means the ShrinkablePageRange outlives any
+    // VMA associated with it, so there can't be any false positives due to pointer reuse here.
+    if !ptr::eq(vm_private_data, owner.cast()) {
+        return None;
+    }
+
+    vma.as_mixedmap_vma()
+}
+
 struct Inner {
     /// Array of pages.
     ///
@@ -308,6 +332,18 @@ impl ShrinkablePageRange {
         inner.size = num_pages;
         inner.vma_addr = vma.start();
 
+        // This pointer is only used for comparison - it's not dereferenced.
+        //
+        // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on
+        // `vm_private_data`.
+        unsafe {
+            (*vma.as_ptr()).vm_private_data = ptr::from_ref(self).cast_mut().cast::<c_void>()
+        };
+
+        // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on
+        // `vm_ops`.
+        unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS };
+
         Ok(num_pages)
     }
 
@@ -399,22 +435,24 @@ impl ShrinkablePageRange {
         //
         // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a
         // workqueue.
-        MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
-            .mmap_read_lock()
-            .vma_lookup(vma_addr)
-            .ok_or(ESRCH)?
-            .as_mixedmap_vma()
-            .ok_or(ESRCH)?
-            .vm_insert_page(user_page_addr, &new_page)
-            .inspect_err(|err| {
-                pr_warn!(
-                    "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
-                    user_page_addr,
-                    vma_addr,
-                    i,
-                    err
-                )
-            })?;
+        check_vma(
+            MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
+                .mmap_read_lock()
+                .vma_lookup(vma_addr)
+                .ok_or(ESRCH)?,
+            self,
+        )
+        .ok_or(ESRCH)?
+        .vm_insert_page(user_page_addr, &new_page)
+        .inspect_err(|err| {
+            pr_warn!(
+                "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
+                user_page_addr,
+                vma_addr,
+                i,
+                err
+            )
+        })?;
 
         let inner = self.lock.lock();
 
@@ -667,12 +705,15 @@ unsafe extern "C" fn rust_shrink_free_page(
     let mmap_read;
     let mm_mutex;
     let vma_addr;
+    let range_ptr;
 
     {
         // CAST: The `list_head` field is first in `PageInfo`.
         let info = item as *mut PageInfo;
         // SAFETY: The `range` field of `PageInfo` is immutable.
-        let range = unsafe { &*((*info).range) };
+        range_ptr = unsafe { (*info).range };
+        // SAFETY: The `range` outlives its `PageInfo` values.
+        let range = unsafe { &*range_ptr };
 
         mm = match range.mm.mmget_not_zero() {
             Some(mm) => MmWithUser::into_mmput_async(mm),
@@ -717,9 +758,11 @@ unsafe extern "C" fn rust_shrink_free_page(
     // SAFETY: The lru lock is locked when this method is called.
     unsafe { bindings::spin_unlock(&raw mut (*lru).lock) };
 
-    if let Some(vma) = mmap_read.vma_lookup(vma_addr) {
-        let user_page_addr = vma_addr + (page_index << PAGE_SHIFT);
-        vma.zap_page_range_single(user_page_addr, PAGE_SIZE);
+    if let Some(unchecked_vma) = mmap_read.vma_lookup(vma_addr) {
+        if let Some(vma) = check_vma(unchecked_vma, range_ptr) {
+            let user_page_addr = vma_addr + (page_index << PAGE_SHIFT);
+            vma.zap_page_range_single(user_page_addr, PAGE_SIZE);
+        }
     }
 
     drop(mmap_read);
-- 
cgit v1.2.3


From 4cb9e13fec0de7c942f5f927469beb8e48ddd20f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 11:53:27 +0000
Subject: rust_binder: avoid reading the written value in offsets array

When sending a transaction, its offsets array is first copied into the
target proc's vma, and then the values are read back from there. This is
normally fine because the vma is a read-only mapping, so the target
process cannot change the value under us.

However, if the target process somehow gains the ability to write to its
own vma, it could change the offset before it's read back, causing the
kernel to misinterpret what the sender meant. If the sender happens to
send a payload with a specific shape, this could in the worst case lead
to the receiver being able to privilege escalate into the sender.

The intent is that gaining the ability to change the read-only vma of
your own process should not be exploitable, so remove this TOCTOU read
even though it's unexploitable without another Binder bug.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-check-v2-2-60f9d695a990@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/thread.rs | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/android/binder/thread.rs b/drivers/android/binder/thread.rs
index 0b62d24b2118..c004214b1662 100644
--- a/drivers/android/binder/thread.rs
+++ b/drivers/android/binder/thread.rs
@@ -1015,12 +1015,9 @@ impl Thread {
 
         // Copy offsets if there are any.
         if offsets_size > 0 {
-            {
-                let mut reader =
-                    UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size)
-                        .reader();
-                alloc.copy_into(&mut reader, aligned_data_size, offsets_size)?;
-            }
+            let mut offsets_reader =
+                UserSlice::new(UserPtr::from_addr(trd_data_ptr.offsets as _), offsets_size)
+                    .reader();
 
             let offsets_start = aligned_data_size;
             let offsets_end = aligned_data_size + offsets_size;
@@ -1041,11 +1038,9 @@ impl Thread {
                 .step_by(size_of::<u64>())
                 .enumerate()
             {
-                let offset: usize = view
-                    .alloc
-                    .read::<u64>(index_offset)?
-                    .try_into()
-                    .map_err(|_| EINVAL)?;
+                let offset = offsets_reader.read::<u64>()?;
+                view.alloc.write(index_offset, &offset)?;
+                let offset: usize = offset.try_into().map_err(|_| EINVAL)?;
 
                 if offset < end_of_previous_object || !is_aligned(offset, size_of::<u32>()) {
                     pr_warn!("Got transaction with invalid offset.");
-- 
cgit v1.2.3


From 2e303f0febb65a434040774b793ba8356698802b Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Tue, 24 Feb 2026 18:16:39 +0000
Subject: rust_binder: call set_notification_done() without proc lock

Consider the following sequence of events on a death listener:
1. The remote process dies and sends a BR_DEAD_BINDER message.
2. The local process invokes the BC_CLEAR_DEATH_NOTIFICATION command.
3. The local process then invokes the BC_DEAD_BINDER_DONE.
Then, the kernel will reply to the BC_DEAD_BINDER_DONE command with a
BR_CLEAR_DEATH_NOTIFICATION_DONE reply using push_work_if_looper().

However, this can result in a deadlock if the current thread is not a
looper. This is because dead_binder_done() still holds the proc lock
during set_notification_done(), which called push_work_if_looper().
Normally, push_work_if_looper() takes the thread lock, which is fine to
take under the proc lock. But if the current thread is not a looper,
then it falls back to delivering the reply to the process work queue,
which involves taking the proc lock. Since the proc lock is already
held, this is a deadlock.

Fix this by releasing the proc lock during set_notification_done(). It
was not intentional that it was held during that function to begin with.

I don't think this ever happens in Android because BC_DEAD_BINDER_DONE
is only invoked in response to BR_DEAD_BINDER messages, and the kernel
always delivers BR_DEAD_BINDER to a looper. So there's no scenario where
Android userspace will call BC_DEAD_BINDER_DONE on a non-looper thread.

Cc: stable <stable@kernel.org>
Fixes: eafedbc7c050 ("rust_binder: add Rust Binder driver")
Reported-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com
Tested-by: syzbot+c8287e65a57a89e7fb72@syzkaller.appspotmail.com
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://patch.msgid.link/20260224-binder-dead-binder-done-proc-lock-v1-1-bbe1b8a6e74a@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/process.rs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/android/binder/process.rs b/drivers/android/binder/process.rs
index 41de5593197c..f06498129aa9 100644
--- a/drivers/android/binder/process.rs
+++ b/drivers/android/binder/process.rs
@@ -1295,7 +1295,8 @@ impl Process {
     }
 
     pub(crate) fn dead_binder_done(&self, cookie: u64, thread: &Thread) {
-        if let Some(death) = self.inner.lock().pull_delivered_death(cookie) {
+        let death = self.inner.lock().pull_delivered_death(cookie);
+        if let Some(death) = death {
             death.set_notification_done(thread);
         }
     }
-- 
cgit v1.2.3


From a0b9b0f1433c845bda708753db32befef78e0f1f Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 18 Feb 2026 15:13:23 +0000
Subject: rust_binder: use lock_vma_under_rcu() in use_page_slow()

There's no reason to lock the whole mm when we are doing operations on
the vma if we can help it, so to reduce contention, use the
lock_vma_under_rcu() abstraction.

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Link: https://patch.msgid.link/20260218-binder-vma-rcu-v1-1-8bd45b2b1183@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/page_range.rs | 37 ++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
index 67aae783e8b8..9dfc154e5dd4 100644
--- a/drivers/android/binder/page_range.rs
+++ b/drivers/android/binder/page_range.rs
@@ -435,24 +435,25 @@ impl ShrinkablePageRange {
         //
         // Using `mmput_async` avoids this, because then the `mm` cleanup is instead queued to a
         // workqueue.
-        check_vma(
-            MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?)
-                .mmap_read_lock()
-                .vma_lookup(vma_addr)
-                .ok_or(ESRCH)?,
-            self,
-        )
-        .ok_or(ESRCH)?
-        .vm_insert_page(user_page_addr, &new_page)
-        .inspect_err(|err| {
-            pr_warn!(
-                "Failed to vm_insert_page({}): vma_addr:{} i:{} err:{:?}",
-                user_page_addr,
-                vma_addr,
-                i,
-                err
-            )
-        })?;
+        let mm = MmWithUser::into_mmput_async(self.mm.mmget_not_zero().ok_or(ESRCH)?);
+        {
+            let vma_read;
+            let mmap_read;
+            let vma = if let Some(ret) = mm.lock_vma_under_rcu(vma_addr) {
+                vma_read = ret;
+                check_vma(&vma_read, self)
+            } else {
+                mmap_read = mm.mmap_read_lock();
+                mmap_read
+                    .vma_lookup(vma_addr)
+                    .and_then(|vma| check_vma(vma, self))
+            };
+
+            match vma {
+                Some(vma) => vma.vm_insert_page(user_page_addr, &new_page)?,
+                None => return Err(ESRCH),
+            }
+        }
 
         let inner = self.lock.lock();
 
-- 
cgit v1.2.3


From 16fdabe143fce2cbf89139677728e17e21b46c28 Mon Sep 17 00:00:00 2001
From: Tzung-Bi Shih <tzungbi@kernel.org>
Date: Thu, 5 Feb 2026 09:28:40 +0000
Subject: gpio: Fix resource leaks on errors in gpiochip_add_data_with_key()

Since commit aab5c6f20023 ("gpio: set device type for GPIO chips"),
`gdev->dev.release` is unset.  As a result, the reference count to
`gdev->dev` isn't dropped on the error handling paths.

Drop the reference on errors.

Also reorder the instructions to make the error handling simpler.
Now gpiochip_add_data_with_key() roughly looks like:

   >>> Some memory allocation.  Go to ERR ZONE 1 on errors.
   >>> device_initialize().

   gpiodev_release() takes over the responsibility for freeing the
   resources of `gdev->dev`.  The subsequent error handling paths
   shouldn't go through ERR ZONE 1 again which leads to double free.

   >>> Some initialization mainly on `gdev`.
   >>> The rest of initialization.  Go to ERR ZONE 2 on errors.
   >>> Chip registration success and exit.

   >>> ERR ZONE 2.  gpio_device_put() and exit.
   >>> ERR ZONE 1.

Cc: stable@vger.kernel.org
Fixes: aab5c6f20023 ("gpio: set device type for GPIO chips")
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://patch.msgid.link/20260205092840.2574840-1-tzungbi@kernel.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib.c | 101 +++++++++++++++++++++++--------------------------
 1 file changed, 48 insertions(+), 53 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86a171e96b0e..f77d5121a8a8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -892,13 +892,15 @@ static const struct device_type gpio_dev_type = {
 #define gcdev_unregister(gdev)		device_del(&(gdev)->dev)
 #endif
 
+/*
+ * An initial reference count has been held in gpiochip_add_data_with_key().
+ * The caller should drop the reference via gpio_device_put() on errors.
+ */
 static int gpiochip_setup_dev(struct gpio_device *gdev)
 {
 	struct fwnode_handle *fwnode = dev_fwnode(&gdev->dev);
 	int ret;
 
-	device_initialize(&gdev->dev);
-
 	/*
 	 * If fwnode doesn't belong to another device, it's safe to clear its
 	 * initialized flag.
@@ -964,9 +966,11 @@ static void gpiochip_setup_devs(void)
 	list_for_each_entry_srcu(gdev, &gpio_devices, list,
 				 srcu_read_lock_held(&gpio_devices_srcu)) {
 		ret = gpiochip_setup_dev(gdev);
-		if (ret)
+		if (ret) {
+			gpio_device_put(gdev);
 			dev_err(&gdev->dev,
 				"Failed to initialize gpio device (%d)\n", ret);
+		}
 	}
 }
 
@@ -1047,71 +1051,72 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	int base = 0;
 	int ret;
 
-	/*
-	 * First: allocate and populate the internal stat container, and
-	 * set up the struct device.
-	 */
 	gdev = kzalloc(sizeof(*gdev), GFP_KERNEL);
 	if (!gdev)
 		return -ENOMEM;
-
-	gdev->dev.type = &gpio_dev_type;
-	gdev->dev.bus = &gpio_bus_type;
-	gdev->dev.parent = gc->parent;
-	rcu_assign_pointer(gdev->chip, gc);
-
 	gc->gpiodev = gdev;
 	gpiochip_set_data(gc, data);
 
-	device_set_node(&gdev->dev, gpiochip_choose_fwnode(gc));
-
 	ret = ida_alloc(&gpio_ida, GFP_KERNEL);
 	if (ret < 0)
 		goto err_free_gdev;
 	gdev->id = ret;
 
-	ret = dev_set_name(&gdev->dev, GPIOCHIP_NAME "%d", gdev->id);
+	ret = init_srcu_struct(&gdev->srcu);
 	if (ret)
 		goto err_free_ida;
+	rcu_assign_pointer(gdev->chip, gc);
 
-	if (gc->parent && gc->parent->driver)
-		gdev->owner = gc->parent->driver->owner;
-	else if (gc->owner)
-		/* TODO: remove chip->owner */
-		gdev->owner = gc->owner;
-	else
-		gdev->owner = THIS_MODULE;
+	ret = init_srcu_struct(&gdev->desc_srcu);
+	if (ret)
+		goto err_cleanup_gdev_srcu;
+
+	ret = dev_set_name(&gdev->dev, GPIOCHIP_NAME "%d", gdev->id);
+	if (ret)
+		goto err_cleanup_desc_srcu;
+
+	device_initialize(&gdev->dev);
+	/*
+	 * After this point any allocated resources to `gdev` will be
+	 * free():ed by gpiodev_release().  If you add new resources
+	 * then make sure they get free():ed there.
+	 */
+	gdev->dev.type = &gpio_dev_type;
+	gdev->dev.bus = &gpio_bus_type;
+	gdev->dev.parent = gc->parent;
+	device_set_node(&gdev->dev, gpiochip_choose_fwnode(gc));
 
 	ret = gpiochip_get_ngpios(gc, &gdev->dev);
 	if (ret)
-		goto err_free_dev_name;
+		goto err_put_device;
+	gdev->ngpio = gc->ngpio;
 
 	gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL);
 	if (!gdev->descs) {
 		ret = -ENOMEM;
-		goto err_free_dev_name;
+		goto err_put_device;
 	}
 
 	gdev->label = kstrdup_const(gc->label ?: "unknown", GFP_KERNEL);
 	if (!gdev->label) {
 		ret = -ENOMEM;
-		goto err_free_descs;
+		goto err_put_device;
 	}
 
-	gdev->ngpio = gc->ngpio;
 	gdev->can_sleep = gc->can_sleep;
-
 	rwlock_init(&gdev->line_state_lock);
 	RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier);
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier);
-
-	ret = init_srcu_struct(&gdev->srcu);
-	if (ret)
-		goto err_free_label;
-
-	ret = init_srcu_struct(&gdev->desc_srcu);
-	if (ret)
-		goto err_cleanup_gdev_srcu;
+#ifdef CONFIG_PINCTRL
+	INIT_LIST_HEAD(&gdev->pin_ranges);
+#endif
+	if (gc->parent && gc->parent->driver)
+		gdev->owner = gc->parent->driver->owner;
+	else if (gc->owner)
+		/* TODO: remove chip->owner */
+		gdev->owner = gc->owner;
+	else
+		gdev->owner = THIS_MODULE;
 
 	scoped_guard(mutex, &gpio_devices_lock) {
 		/*
@@ -1127,7 +1132,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 			if (base < 0) {
 				ret = base;
 				base = 0;
-				goto err_cleanup_desc_srcu;
+				goto err_put_device;
 			}
 
 			/*
@@ -1147,14 +1152,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		ret = gpiodev_add_to_list_unlocked(gdev);
 		if (ret) {
 			gpiochip_err(gc, "GPIO integer space overlap, cannot add chip\n");
-			goto err_cleanup_desc_srcu;
+			goto err_put_device;
 		}
 	}
 
-#ifdef CONFIG_PINCTRL
-	INIT_LIST_HEAD(&gdev->pin_ranges);
-#endif
-
 	if (gc->names)
 		gpiochip_set_desc_names(gc);
 
@@ -1248,25 +1249,19 @@ err_remove_from_list:
 	scoped_guard(mutex, &gpio_devices_lock)
 		list_del_rcu(&gdev->list);
 	synchronize_srcu(&gpio_devices_srcu);
-	if (gdev->dev.release) {
-		/* release() has been registered by gpiochip_setup_dev() */
-		gpio_device_put(gdev);
-		goto err_print_message;
-	}
+err_put_device:
+	gpio_device_put(gdev);
+	goto err_print_message;
+
 err_cleanup_desc_srcu:
 	cleanup_srcu_struct(&gdev->desc_srcu);
 err_cleanup_gdev_srcu:
 	cleanup_srcu_struct(&gdev->srcu);
-err_free_label:
-	kfree_const(gdev->label);
-err_free_descs:
-	kfree(gdev->descs);
-err_free_dev_name:
-	kfree(dev_name(&gdev->dev));
 err_free_ida:
 	ida_free(&gpio_ida, gdev->id);
 err_free_gdev:
 	kfree(gdev);
+
 err_print_message:
 	/* failures here can mean systems won't boot... */
 	if (ret != -EPROBE_DEFER) {
-- 
cgit v1.2.3


From 24d87712727a5017ad142d63940589a36cd25647 Mon Sep 17 00:00:00 2001
From: Ariel Silver <arielsilver77@gmail.com>
Date: Sat, 21 Feb 2026 15:26:00 +0100
Subject: media: dvb-net: fix OOB access in ULE extension header tables

The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables
in handle_one_ule_extension() are declared with 255 elements (valid
indices 0-254), but the index htype is derived from network-controlled
data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When
htype equals 255, an out-of-bounds read occurs on the function pointer
table, and the OOB value may be called as a function pointer.

Add a bounds check on htype against the array size before either table
is accessed. Out-of-range values now cause the SNDU to be discarded.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Ariel Silver <arielsilver77@gmail.com>
Signed-off-by: Ariel Silver <arielsilver77@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/dvb-core/dvb_net.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index 8bb8dd34c223..a2159b2bc176 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -228,6 +228,9 @@ static int handle_one_ule_extension( struct dvb_net_priv *p )
 	unsigned char hlen = (p->ule_sndu_type & 0x0700) >> 8;
 	unsigned char htype = p->ule_sndu_type & 0x00FF;
 
+	if (htype >= ARRAY_SIZE(ule_mandatory_ext_handlers))
+		return -1;
+
 	/* Discriminate mandatory and optional extension headers. */
 	if (hlen == 0) {
 		/* Mandatory extension header */
-- 
cgit v1.2.3


From 3385ea97c14d271dcb0c6e6fcf16972f819eecd8 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:50 +0100
Subject: platform/x86: oxpec: Add support for OneXPlayer APEX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OneXPlayer Apex is a new Strix Halo handheld. It uses the same registers
as the OneXPlayer Fly devices. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-2-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 144a454103b9..59d6f9d9a905 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -11,7 +11,7 @@
  *
  * Copyright (C) 2022 Joaquín I. Aramendía <samsagax@gmail.com>
  * Copyright (C) 2024 Derek J. Clark <derekjohn.clark@gmail.com>
- * Copyright (C) 2025 Antheas Kapenekakis <lkml@antheas.dev>
+ * Copyright (C) 2025-2026 Antheas Kapenekakis <lkml@antheas.dev>
  */
 
 #include <linux/acpi.h>
@@ -142,6 +142,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_2,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER APEX"),
+		},
+		.driver_data = (void *)oxp_fly,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
-- 
cgit v1.2.3


From 4049c46edb5d44c0de045f6f504371705dd603dd Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:51 +0100
Subject: platform/x86: oxpec: Add support for OneXPlayer X1z
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

X1z is a variant of OneXPlayer X1 A with 8840U. It seems that only one
user has this one. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-3-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 59d6f9d9a905..623d9a452c46 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -219,6 +219,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_mini_amd_pro,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1z"),
+		},
+		.driver_data = (void *)oxp_x1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
-- 
cgit v1.2.3


From 2a3b4a8c10a64a62c4243007139d253dc1324dfd Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:52 +0100
Subject: platform/x86: oxpec: Add support for OneXPlayer X1 Air
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

X1 Air is an X1 variant with a newer Intel chipset. It uses the same
registers as the X1. Add a quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-4-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index 623d9a452c46..d6ef8dbf568e 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -240,6 +240,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)oxp_x1,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1Air"),
+		},
+		.driver_data = (void *)oxp_x1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"),
-- 
cgit v1.2.3


From cd0883055b04586770dab43c64159348bf480a3e Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 23 Feb 2026 19:29:53 +0100
Subject: platform/x86: oxpec: Add support for Aokzoe A2 Pro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Aokzoe A2 Pro is an older device that the oxpec driver is missing the
quirk for. It has the same behavior as the AOKZOE A1 devices. Add a
quirk for it to the oxpec driver.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20260223183004.2696892-5-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/oxpec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c
index d6ef8dbf568e..6d4a53a2ed60 100644
--- a/drivers/platform/x86/oxpec.c
+++ b/drivers/platform/x86/oxpec.c
@@ -114,6 +114,13 @@ static const struct dmi_system_id dmi_table[] = {
 		},
 		.driver_data = (void *)aok_zoe_a1,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "AOKZOE A2 Pro"),
+		},
+		.driver_data = (void *)aok_zoe_a1,
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"),
-- 
cgit v1.2.3


From 916727cfdb72cd01fef3fa6746e648f8cb70e713 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 25 Feb 2026 15:06:46 -0600
Subject: platform/x86: hp-bioscfg: Support allocations of larger data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some systems have much larger amounts of enumeration attributes
than have been previously encountered. This can lead to page allocation
failures when using kcalloc().  Switch over to using kvcalloc() to
allow larger allocations.

Fixes: 6b2770bfd6f92 ("platform/x86: hp-bioscfg: enum-attributes")
Cc: stable@vger.kernel.org
Reported-by: Paul Kerry <p.kerry@sheffield.ac.uk>
Tested-by: Paul Kerry <p.kerry@sheffield.ac.uk>
Closes: https://bugs.debian.org/1127612
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patch.msgid.link/20260225210646.59381-1-mario.limonciello@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
index 470b9f44ed7a..af4d1920d488 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c
@@ -94,8 +94,11 @@ int hp_alloc_enumeration_data(void)
 	bioscfg_drv.enumeration_instances_count =
 		hp_get_instance_count(HP_WMI_BIOS_ENUMERATION_GUID);
 
-	bioscfg_drv.enumeration_data = kzalloc_objs(*bioscfg_drv.enumeration_data,
-						    bioscfg_drv.enumeration_instances_count);
+	if (!bioscfg_drv.enumeration_instances_count)
+		return -EINVAL;
+	bioscfg_drv.enumeration_data = kvcalloc(bioscfg_drv.enumeration_instances_count,
+						sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL);
+
 	if (!bioscfg_drv.enumeration_data) {
 		bioscfg_drv.enumeration_instances_count = 0;
 		return -ENOMEM;
@@ -444,6 +447,6 @@ void hp_exit_enumeration_attributes(void)
 	}
 	bioscfg_drv.enumeration_instances_count = 0;
 
-	kfree(bioscfg_drv.enumeration_data);
+	kvfree(bioscfg_drv.enumeration_data);
 	bioscfg_drv.enumeration_data = NULL;
 }
-- 
cgit v1.2.3


From 622cc8d078e5d7586f0e40dd7aea515a946da48c Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Thu, 26 Feb 2026 15:19:43 +0100
Subject: platform/x86: asus-armoury: add support for GX650RX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model GX650RX.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260226141944.352923-2-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 001c011fdd56..f9d9136aec7b 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1457,6 +1457,38 @@ static const struct dmi_system_id power_limits[] = {
 			},
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GX650RX"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_def = 70,
+				.ppt_pl1_spl_max = 90,
+				.ppt_pl2_sppt_min = 28,
+				.ppt_pl2_sppt_def = 70,
+				.ppt_pl2_sppt_max = 100,
+				.ppt_pl3_fppt_min = 28,
+				.ppt_pl3_fppt_def = 110,
+				.ppt_pl3_fppt_max = 125,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 25,
+				.nv_temp_target_min = 76,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_max = 50,
+				.ppt_pl2_sppt_min = 28,
+				.ppt_pl2_sppt_max = 50,
+				.ppt_pl3_fppt_min = 28,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 76,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G513I"),
-- 
cgit v1.2.3


From c55b84fa567ed33bc651675bcaf8d53bd12d910a Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Thu, 26 Feb 2026 15:19:44 +0100
Subject: platform/x86: asus-armoury: add support for FA401UM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model FA401UM.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260226141944.352923-3-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index f9d9136aec7b..208f6fe16168 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -346,6 +346,35 @@ struct power_data {
  * _def is not required and will be assumed to be default == max if missing.
  */
 static const struct dmi_system_id power_limits[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "FA401UM"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 35,
+				.ppt_pl2_sppt_max = 80,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 80,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 15,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 25,
+				.ppt_pl1_spl_max = 35,
+				.ppt_pl2_sppt_min = 31,
+				.ppt_pl2_sppt_max = 44,
+				.ppt_pl3_fppt_min = 45,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "FA401UV"),
-- 
cgit v1.2.3


From 3350c2b3f2b8a3b985a020a4ef4f2f050a4b6a1d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 25 Feb 2026 21:12:29 -0800
Subject: platform_data/mlxreg: mlxreg.h: fix all kernel-doc warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the correct kernel-doc format & notation to eliminate
kernel-doc warnings:

Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE1' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE2' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:24 Enum value
 'MLX_WDT_TYPE3' not described in enum 'mlxreg_wdt_type'
Warning: include/linux/platform_data/mlxreg.h:37 bad line:
 PHYs ready / unready state;
Warning: include/linux/platform_data/mlxreg.h:153 struct member 'np'
 not described in 'mlxreg_core_data'
Warning: include/linux/platform_data/mlxreg.h:153 struct member 'hpdev'
 not described in 'mlxreg_core_data'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260226051232.549537-1-rdunlap@infradead.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 include/linux/platform_data/mlxreg.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index f6cca7a035c7..50b6be57da66 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -13,10 +13,10 @@
 /**
  * enum mlxreg_wdt_type - type of HW watchdog
  *
- * TYPE1 HW watchdog implementation exist in old systems.
- * All new systems have TYPE2 HW watchdog.
- * TYPE3 HW watchdog can exist on all systems with new CPLD.
- * TYPE3 is selected by WD capability bit.
+ * @MLX_WDT_TYPE1: HW watchdog implementation in old systems.
+ * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog.
+ * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD.
+ *   TYPE3 is selected by WD capability bit.
  */
 enum mlxreg_wdt_type {
 	MLX_WDT_TYPE1,
@@ -35,7 +35,7 @@ enum mlxreg_wdt_type {
  * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming
  *			      after hardware-firmware synchronization handshake;
  * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card
-			     PHYs ready / unready state;
+ *			     PHYs ready / unready state;
  * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware
  *			      availability / unavailability for the ports on line card;
  * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive
@@ -123,8 +123,8 @@ struct mlxreg_hotplug_device {
  * @reg_pwr: attribute power register;
  * @reg_ena: attribute enable register;
  * @mode: access mode;
- * @np - pointer to node platform associated with attribute;
- * @hpdev - hotplug device data;
+ * @np: pointer to node platform associated with attribute;
+ * @hpdev: hotplug device data;
  * @notifier: pointer to event notifier block;
  * @health_cntr: dynamic device health indication counter;
  * @attached: true if device has been attached after good health indication;
-- 
cgit v1.2.3


From 377f8e788945d45b012ed9cfc35ca56c02e86cd8 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Mon, 16 Feb 2026 18:55:38 +0100
Subject: HID: asus: add xg mobile 2023 external hardware support

XG mobile stations have the 0x5a endpoint and has to be initialized:
add them to hid-asus.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-asus.c | 3 +++
 drivers/hid/hid-ids.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 7a08e964b9cc..687b785e2d0c 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1497,6 +1497,9 @@ static const struct hid_device_id asus_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+	    USB_DEVICE_ID_ASUSTEK_XGM_2023),
+	},
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
 	  QUIRK_ROG_CLAYMORE_II_KEYBOARD },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 3e299a30dcde..4ab7640b119a 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -229,6 +229,7 @@
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X		0x1b4c
 #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD	0x196b
 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD	0x1869
+#define USB_DEVICE_ID_ASUSTEK_XGM_2023	0x1a9a
 
 #define USB_VENDOR_ID_ATEN		0x0557
 #define USB_DEVICE_ID_ATEN_UC100KM	0x2004
-- 
cgit v1.2.3


From 48fafffcf29bb968c9dee6bf507c1e57d0ccb6b5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 26 Feb 2026 17:33:15 +0200
Subject: phy: make PHY_COMMON_PROPS Kconfig symbol conditionally
 user-selectable

Geert reports that enabling CONFIG_KUNIT_ALL_TESTS shouldn't enable
features that aren't enabled without it. That isn't what "*all* tests"
means, but as the prompt puts it, "All KUnit tests with satisfied
dependencies".

The impact is that enabling CONFIG_KUNIT_ALL_TESTS brings features which
cannot be disabled as built-in into the kernel.

Keep the pattern where consumer drivers have to "select PHY_COMMON_PROPS",
but if KUNIT_ALL_TESTS is enabled, also make PHY_COMMON_PROPS user
selectable, so it can be turned off.

Modify PHY_COMMON_PROPS_TEST to depend on PHY_COMMON_PROPS rather than
select it.

Fixes: e7556b59ba65 ("phy: add phy_get_rx_polarity() and phy_get_tx_polarity()")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/linux-phy/CAMuHMdUBaoYKNj52gn8DQeZFZ42Cvm6xT6fvo0-_twNv1k3Jhg@mail.gmail.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260226153315.3530378-1-vladimir.oltean@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/Kconfig | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 02467dfd4fb0..1875d5b784f6 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -6,7 +6,7 @@
 menu "PHY Subsystem"
 
 config PHY_COMMON_PROPS
-	bool
+	bool "PHY common properties" if KUNIT_ALL_TESTS
 	help
 	  This parses properties common between generic PHYs and Ethernet PHYs.
 
@@ -16,8 +16,7 @@ config PHY_COMMON_PROPS
 
 config PHY_COMMON_PROPS_TEST
 	tristate "KUnit tests for PHY common props" if !KUNIT_ALL_TESTS
-	select PHY_COMMON_PROPS
-	depends on KUNIT
+	depends on KUNIT && PHY_COMMON_PROPS
 	default KUNIT_ALL_TESTS
 	help
 	  This builds KUnit tests for the PHY common property API.
-- 
cgit v1.2.3


From a258d843a3e4cb687da19437f8f81fee55ad7d35 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 26 Feb 2026 20:28:53 +0200
Subject: phy: lynx-28g: skip CDR lock workaround for lanes disabled in the
 device tree

The blamed commit introduced support for specifying individual lanes as
OF nodes in the device, and these can have status = "disabled".

When that happens, for_each_available_child_of_node() skips them and
lynx_28g_probe_lane() -> devm_phy_create() is not called, so lane->phy
will be NULL. Yet it will be dereferenced in lynx_28g_cdr_lock_check(),
resulting in a crash.

This used to be well handled in v3 of that patch:
https://lore.kernel.org/linux-phy/20250926180505.760089-14-vladimir.oltean@nxp.com/
but until v5 was merged, the logic to support per-lane OF nodes was
split into a separate change, and the per-SoC compatible strings patch
was deferred to a "part 2" set. The splitting was done improperly, and
that handling of NULL lane->phy pointers was not integrated into the
proper commit.

Fixes: 7df7d58abbd6 ("phy: lynx-28g: support individual lanes as OF PHY providers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260226182853.1103616-1-vladimir.oltean@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-lynx-28g.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/phy/freescale/phy-fsl-lynx-28g.c b/drivers/phy/freescale/phy-fsl-lynx-28g.c
index 2b0fd95ba62f..63427fc34e26 100644
--- a/drivers/phy/freescale/phy-fsl-lynx-28g.c
+++ b/drivers/phy/freescale/phy-fsl-lynx-28g.c
@@ -1069,6 +1069,8 @@ static void lynx_28g_cdr_lock_check(struct work_struct *work)
 
 	for (i = 0; i < LYNX_28G_NUM_LANE; i++) {
 		lane = &priv->lane[i];
+		if (!lane->phy)
+			continue;
 
 		mutex_lock(&lane->phy->mutex);
 
-- 
cgit v1.2.3


From f0cf0a882a02dcf28547f32264f6fd37e9a7b147 Mon Sep 17 00:00:00 2001
From: Yixun Lan <dlan@kernel.org>
Date: Mon, 16 Feb 2026 23:26:53 +0800
Subject: phy: k1-usb: add disconnect function support

A disconnect status BIT of USB2 PHY need to be cleared, otherwise
it will fail to work properly during next connection when devices
connect to roothub directly.

Fixes: fe4bc1a08638 ("phy: spacemit: support K1 USB2.0 PHY controller")
Signed-off-by: Yixun Lan <dlan@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20260216152653.25244-1-dlan@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/spacemit/phy-k1-usb2.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/phy/spacemit/phy-k1-usb2.c b/drivers/phy/spacemit/phy-k1-usb2.c
index 342061380012..9215d0b223b2 100644
--- a/drivers/phy/spacemit/phy-k1-usb2.c
+++ b/drivers/phy/spacemit/phy-k1-usb2.c
@@ -48,6 +48,9 @@
 #define  PHY_CLK_HSTXP_EN		BIT(3)		/* clock hstxp enable */
 #define  PHY_HSTXP_MODE			BIT(4)		/* 0: force en_txp to be 1; 1: no force */
 
+#define PHY_K1_HS_HOST_DISC		0x40
+#define  PHY_K1_HS_HOST_DISC_CLR		BIT(0)
+
 #define PHY_PLL_DIV_CFG			0x98
 #define  PHY_FDIV_FRACT_8_15		GENMASK(7, 0)
 #define  PHY_FDIV_FRACT_16_19		GENMASK(11, 8)
@@ -142,9 +145,20 @@ static int spacemit_usb2phy_exit(struct phy *phy)
 	return 0;
 }
 
+static int spacemit_usb2phy_disconnect(struct phy *phy, int port)
+{
+	struct spacemit_usb2phy *sphy = phy_get_drvdata(phy);
+
+	regmap_update_bits(sphy->regmap_base, PHY_K1_HS_HOST_DISC,
+			   PHY_K1_HS_HOST_DISC_CLR, PHY_K1_HS_HOST_DISC_CLR);
+
+	return 0;
+}
+
 static const struct phy_ops spacemit_usb2phy_ops = {
 	.init = spacemit_usb2phy_init,
 	.exit = spacemit_usb2phy_exit,
+	.disconnect = spacemit_usb2phy_disconnect,
 	.owner = THIS_MODULE,
 };
 
-- 
cgit v1.2.3


From 584b457f4166293bdfa50f930228e9fb91a38392 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 12 Feb 2026 18:39:19 +0800
Subject: phy: ti: j721e-wiz: Fix device node reference leak in
 wiz_get_lane_phy_types()

The serdes device_node is obtained using of_get_child_by_name(),
which increments the reference count. However, it is never put,
leading to a reference leak.

Add the missing of_node_put() calls to ensure the reference count is
properly balanced.

Fixes: 7ae14cf581f2 ("phy: ti: j721e-wiz: Implement DisplayPort mode to the wiz driver")
Suggested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20260212-wiz-v2-1-6e8bd4cc7a4a@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-j721e-wiz.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index 6e9ecb88dc8b..6b584706b913 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1425,6 +1425,7 @@ static int wiz_get_lane_phy_types(struct device *dev, struct wiz *wiz)
 			dev_err(dev,
 				"%s: Reading \"reg\" from \"%s\" failed: %d\n",
 				__func__, subnode->name, ret);
+			of_node_put(serdes);
 			return ret;
 		}
 		of_property_read_u32(subnode, "cdns,num-lanes", &num_lanes);
@@ -1439,6 +1440,7 @@ static int wiz_get_lane_phy_types(struct device *dev, struct wiz *wiz)
 		}
 	}
 
+	of_node_put(serdes);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 81af9e40e2e4e1aa95f09fb34811760be6742c58 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@oss.qualcomm.com>
Date: Thu, 19 Feb 2026 13:11:48 +0200
Subject: phy: qcom: qmp-ufs: Fix SM8650 PCS table for Gear 4

According to internal documentation, on SM8650, when the PHY is configured
in Gear 4, the QPHY_V6_PCS_UFS_PLL_CNTL register needs to have the same
value as for Gear 5.

At the moment, there is no board that comes with a UFS 3.x device, so
this issue doesn't show up, but with the new Eliza SoC, which uses the
same init sequence as SM8650, on the MTP board, the link startup fails
with the current Gear 4 PCS table.

So fix that by moving the entry into the PCS generic table instead,
while keeping the value from Gear 5 configuration.

Cc: stable@vger.kernel.org # v6.10
Fixes: b9251e64a96f ("phy: qcom: qmp-ufs: update SM8650 tables for Gear 4 & 5")
Suggested-by: Nitin Rawat <nitin.rawat@oss.qualcomm.com>
Signed-off-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-HDK
Link: https://patch.msgid.link/20260219-phy-qcom-qmp-ufs-fix-sm8650-pcs-g4-table-v1-1-f136505b57f6@oss.qualcomm.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-ufs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
index df138a5442eb..771bc7c2ab50 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c
@@ -990,6 +990,7 @@ static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = {
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_MULTI_LANE_CTRL1, 0x02),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_MID_TERM_CTRL1, 0x43),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PCS_CTRL1, 0xc1),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_SIGDET_CTRL2, 0x68),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_POST_EMP_LVL_S4, 0x0e),
@@ -999,13 +1000,11 @@ static const struct qmp_phy_init_tbl sm8650_ufsphy_pcs[] = {
 };
 
 static const struct qmp_phy_init_tbl sm8650_ufsphy_g4_pcs[] = {
-	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x13),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x04),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x04),
 };
 
 static const struct qmp_phy_init_tbl sm8650_ufsphy_g5_pcs[] = {
-	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_PLL_CNTL, 0x33),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_TX_HSGEAR_CAPABILITY, 0x05),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HSGEAR_CAPABILITY, 0x05),
 	QMP_PHY_INIT_CFG(QPHY_V6_PCS_UFS_RX_HS_G5_SYNC_LENGTH_CAPABILITY, 0x4d),
-- 
cgit v1.2.3


From e9217ca77dc35b4978db0fe901685ddb3f1e223a Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 23 Feb 2026 16:58:09 +0900
Subject: mm/slab: initialize slab->stride early to avoid memory ordering
 issues

When alloc_slab_obj_exts() is called later (instead of during slab
allocation and initialization), slab->stride and slab->obj_exts are
updated after the slab is already accessible by multiple CPUs.

The current implementation does not enforce memory ordering between
slab->stride and slab->obj_exts. For correctness, slab->stride must be
visible before slab->obj_exts. Otherwise, concurrent readers may observe
slab->obj_exts as non-zero while stride is still stale.

With stale slab->stride, slab_obj_ext() could return the wrong obj_ext.
This could cause two problems:

  - obj_cgroup_put() is called on the wrong objcg, leading to
    a use-after-free due to incorrect reference counting [1] by
    decrementing the reference count more than it was incremented.

  - refill_obj_stock() is called on the wrong objcg, leading to
    a page_counter overflow [2] by uncharging more memory than charged.

Fix this by unconditionally initializing slab->stride in
alloc_slab_obj_exts_early(), before the need_slab_obj_exts() check.
In the case of SLAB_OBJ_EXT_IN_OBJ, it is overridden in the function.

This ensures updates to slab->stride become visible before the slab
can be accessed by other CPUs via the per-node partial slab list
(protected by spinlock with acquire/release semantics).

Thanks to Shakeel Butt for pointing out this issue [3].

[vbabka@kernel.org: the bug reports [1] and [2] are not yet fully fixed,
 with investigation ongoing, but it is nevertheless a step in the right
 direction to only set stride once after allocating the slab and not
 change it later ]

Fixes: 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Link: https://lore.kernel.org/lkml/ca241daa-e7e7-4604-a48d-de91ec9184a5@linux.ibm.com [1]
Link: https://lore.kernel.org/all/ddff7c7d-c0c3-4780-808f-9a83268bbf0c@linux.ibm.com [2]
Link: https://lore.kernel.org/linux-mm/aZu9G9mVIVzSm6Ft@hyeyoo [3]
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 52f021711744..0c906fefc31b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2196,7 +2196,6 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
 retry:
 	old_exts = READ_ONCE(slab->obj_exts);
 	handle_failed_objexts_alloc(old_exts, vec, objects);
-	slab_set_stride(slab, sizeof(struct slabobj_ext));
 
 	if (new_slab) {
 		/*
@@ -2272,6 +2271,9 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 	void *addr;
 	unsigned long obj_exts;
 
+	/* Initialize stride early to avoid memory ordering issues */
+	slab_set_stride(slab, sizeof(struct slabobj_ext));
+
 	if (!need_slab_obj_exts(s))
 		return;
 
@@ -2288,7 +2290,6 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab)
 		obj_exts |= MEMCG_DATA_OBJEXTS;
 #endif
 		slab->obj_exts = obj_exts;
-		slab_set_stride(slab, sizeof(struct slabobj_ext));
 	} else if (s->flags & SLAB_OBJ_EXT_IN_OBJ) {
 		unsigned int offset = obj_exts_offset_in_object(s);
 
-- 
cgit v1.2.3


From 663eb8763c251dbcd0536b14ec134e63e4173348 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 4 Feb 2026 17:41:58 +0100
Subject: i3c: simplify combined i3c/i2c dependencies

All combined i2c/i3c drivers appear to suffer from the same link
time problem when CONFIG_I3C is set to 'm':

arm-linux-gnueabi-ld: drivers/iio/magnetometer/mmc5633.o: in function `mmc5633_i3c_driver_init':
mmc5633.c:(.init.text+0x30): undefined reference to `i3c_driver_register_with_owner'

This was previously fixed every time by marking individual
drivers as 'depends on I2C; depends on I3C || !I3C', but this gets
tedious and is somewhat confusing.

Add a Kconfig symbol 'I3C_OR_I2C' to help replace those dependencies,
and use this in all the existing drivers that had already fixed it
as well as the new mmc5633 driver.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260204164216.544409-1-arnd@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/hwmon/Kconfig            |  6 ++----
 drivers/i3c/Kconfig              | 12 ++++++++++++
 drivers/iio/magnetometer/Kconfig |  3 +--
 drivers/misc/amd-sbi/Kconfig     |  3 +--
 4 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 41c381764c2b..ecfba861f66d 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1493,8 +1493,7 @@ config SENSORS_LM73
 
 config SENSORS_LM75
 	tristate "National Semiconductor LM75 and compatibles"
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
 	help
@@ -2392,8 +2391,7 @@ config SENSORS_TMP103
 
 config SENSORS_TMP108
 	tristate "Texas Instruments TMP108"
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
 	help
diff --git a/drivers/i3c/Kconfig b/drivers/i3c/Kconfig
index 30a441506f61..626c54b386d5 100644
--- a/drivers/i3c/Kconfig
+++ b/drivers/i3c/Kconfig
@@ -22,3 +22,15 @@ menuconfig I3C
 if I3C
 source "drivers/i3c/master/Kconfig"
 endif # I3C
+
+config I3C_OR_I2C
+	tristate
+	default m if I3C=m
+	default I2C
+	help
+	  Device drivers using module_i3c_i2c_driver() can use either
+	  i2c or i3c hosts, but cannot be built-in for the kernel when
+	  CONFIG_I3C=m.
+
+	  Add 'depends on I2C_OR_I3C' in Kconfig for those drivers to
+	  get the correct dependencies.
diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig
index 9345fb6d5317..fb313e591e85 100644
--- a/drivers/iio/magnetometer/Kconfig
+++ b/drivers/iio/magnetometer/Kconfig
@@ -143,8 +143,7 @@ config MMC5633
 	tristate "MEMSIC MMC5633 3-axis magnetic sensor"
 	select REGMAP_I2C
 	select REGMAP_I3C if I3C
-	depends on I2C
-	depends on I3C || !I3C
+	depends on I3C_OR_I2C
 	help
 	  Say yes here to build support for the MEMSIC MMC5633 3-axis
 	  magnetic sensor.
diff --git a/drivers/misc/amd-sbi/Kconfig b/drivers/misc/amd-sbi/Kconfig
index be022c71a90c..30e7fad7356c 100644
--- a/drivers/misc/amd-sbi/Kconfig
+++ b/drivers/misc/amd-sbi/Kconfig
@@ -1,10 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config AMD_SBRMI_I2C
 	tristate "AMD side band RMI support"
-	depends on I2C
+	depends on I3C_OR_I2C
 	depends on ARM || ARM64 || COMPILE_TEST
 	select REGMAP_I2C
-	depends on I3C || !I3C
 	select REGMAP_I3C if I3C
 	help
 	  Side band RMI over I2C/I3C support for AMD out of band management.
-- 
cgit v1.2.3


From 0f5197ea9a73a4c406c75e6d8af3a13f7f96ae89 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 25 Feb 2026 11:38:05 -0800
Subject: nvme-multipath: fix leak on try_module_get failure

We need to fall back to the synchronous removal if we can't get a
reference on the module needed for the deferred removal.

Fixes: 62188639ec16 ("nvme-multipath: introduce delayed removal of the multipath head node")
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/multipath.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index bfcc5904e6a2..fc6800a9f7f9 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1310,13 +1310,11 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	if (!list_empty(&head->list))
 		goto out;
 
-	if (head->delayed_removal_secs) {
-		/*
-		 * Ensure that no one could remove this module while the head
-		 * remove work is pending.
-		 */
-		if (!try_module_get(THIS_MODULE))
-			goto out;
+	/*
+	 * Ensure that no one could remove this module while the head
+	 * remove work is pending.
+	 */
+	if (head->delayed_removal_secs && try_module_get(THIS_MODULE)) {
 		mod_delayed_work(nvme_wq, &head->remove_work,
 				head->delayed_removal_secs * HZ);
 	} else {
-- 
cgit v1.2.3


From f505a45776d149632e3bd0b87f0da1609607161a Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 26 Feb 2026 23:15:22 +0100
Subject: smb: client: Use snprintf in cifs_set_cifscreds

Replace unbounded sprintf() calls with the safer snprintf(). Avoid using
magic numbers and use strlen() to calculate the key descriptor buffer
size. Save the size in a local variable and reuse it for the bounded
snprintf() calls. Remove CIFSCREDS_DESC_SIZE.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 4c34d9603e05..3bad2c5c523d 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2167,9 +2167,6 @@ void __cifs_put_smb_ses(struct cifs_ses *ses)
 
 #ifdef CONFIG_KEYS
 
-/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */
-#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1)
-
 /* Populate username and pw fields from keyring if possible */
 static int
 cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
@@ -2177,6 +2174,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	int rc = 0;
 	int is_domain = 0;
 	const char *delim, *payload;
+	size_t desc_sz;
 	char *desc;
 	ssize_t len;
 	struct key *key;
@@ -2185,7 +2183,9 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	struct sockaddr_in6 *sa6;
 	const struct user_key_payload *upayload;
 
-	desc = kmalloc(CIFSCREDS_DESC_SIZE, GFP_KERNEL);
+	/* "cifs:a:" and "cifs:d:" are the same length; +1 for NUL terminator */
+	desc_sz = strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1;
+	desc = kmalloc(desc_sz, GFP_KERNEL);
 	if (!desc)
 		return -ENOMEM;
 
@@ -2193,11 +2193,11 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	switch (server->dstaddr.ss_family) {
 	case AF_INET:
 		sa = (struct sockaddr_in *)&server->dstaddr;
-		sprintf(desc, "cifs:a:%pI4", &sa->sin_addr.s_addr);
+		snprintf(desc, desc_sz, "cifs:a:%pI4", &sa->sin_addr.s_addr);
 		break;
 	case AF_INET6:
 		sa6 = (struct sockaddr_in6 *)&server->dstaddr;
-		sprintf(desc, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr);
+		snprintf(desc, desc_sz, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr);
 		break;
 	default:
 		cifs_dbg(FYI, "Bad ss_family (%hu)\n",
@@ -2216,7 +2216,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 		}
 
 		/* didn't work, try to find a domain key */
-		sprintf(desc, "cifs:d:%s", ses->domainName);
+		snprintf(desc, desc_sz, "cifs:d:%s", ses->domainName);
 		cifs_dbg(FYI, "%s: desc=%s\n", __func__, desc);
 		key = request_key(&key_type_logon, desc, "");
 		if (IS_ERR(key)) {
-- 
cgit v1.2.3


From 39195990e4c093c9eecf88f29811c6de29265214 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 27 Feb 2026 06:10:08 -0600
Subject: PCI: Correct PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fb82437fdd8c ("PCI: Change capability register offsets to hex") incorrectly
converted the PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 value from decimal 52 to hex
0x32:

  -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52      /* v2 endpoints with link end here */
  +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32    /* end of v2 EPs w/ link */

This broke PCI capabilities in a VMM because subsequent ones weren't
DWORD-aligned.

Change PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 to the correct value of 0x34.

fb82437fdd8c was from Baruch Siach <baruch@tkos.co.il>, but this was not
Baruch's fault; it's a mistake I made when applying the patch.

Fixes: fb82437fdd8c ("PCI: Change capability register offsets to hex")
Reported-by: David Woodhouse <dwmw2@infradead.org>
Closes: https://lore.kernel.org/all/3ae392a0158e9d9ab09a1d42150429dd8ca42791.camel@infradead.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
---
 include/uapi/linux/pci_regs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index ec1c54b5a310..14f634ab9350 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -712,7 +712,7 @@
 #define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
 #define PCI_EXP_LNKSTA2		0x32	/* Link Status 2 */
 #define  PCI_EXP_LNKSTA2_FLIT		0x0400 /* Flit Mode Status */
-#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x32	/* end of v2 EPs w/ link */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	0x34	/* end of v2 EPs w/ link */
 #define PCI_EXP_SLTCAP2		0x34	/* Slot Capabilities 2 */
 #define  PCI_EXP_SLTCAP2_IBPD	0x00000001 /* In-band PD Disable Supported */
 #define PCI_EXP_SLTCTL2		0x38	/* Slot Control 2 */
-- 
cgit v1.2.3


From 550bae2c0931dbb664a61b08c21cf156f0a5362a Mon Sep 17 00:00:00 2001
From: Maíra Canal <mcanal@igalia.com>
Date: Thu, 12 Feb 2026 11:49:44 -0300
Subject: pmdomain: bcm: bcm2835-power: Fix broken reset status read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

bcm2835_reset_status() has a misplaced parenthesis on every PM_READ()
call. Since PM_READ(reg) expands to readl(power->base + (reg)), the
expression:

    PM_READ(PM_GRAFX & PM_V3DRSTN)

computes the bitwise AND of the register offset PM_GRAFX with the
bitmask PM_V3DRSTN before using the result as a register offset, reading
from the wrong MMIO address instead of the intended PM_GRAFX register.
The same issue affects the PM_IMAGE cases.

Fix by moving the closing parenthesis so PM_READ() receives only the
register offset, and the bitmask is applied to the value returned by
the read.

Fixes: 670c672608a1 ("soc: bcm: bcm2835-pm: Add support for power domains under a new binding.")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/bcm/bcm2835-power.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c
index 1d29addfe036..0450202bbee2 100644
--- a/drivers/pmdomain/bcm/bcm2835-power.c
+++ b/drivers/pmdomain/bcm/bcm2835-power.c
@@ -580,11 +580,11 @@ static int bcm2835_reset_status(struct reset_controller_dev *rcdev,
 
 	switch (id) {
 	case BCM2835_RESET_V3D:
-		return !PM_READ(PM_GRAFX & PM_V3DRSTN);
+		return !(PM_READ(PM_GRAFX) & PM_V3DRSTN);
 	case BCM2835_RESET_H264:
-		return !PM_READ(PM_IMAGE & PM_H264RSTN);
+		return !(PM_READ(PM_IMAGE) & PM_H264RSTN);
 	case BCM2835_RESET_ISP:
-		return !PM_READ(PM_IMAGE & PM_ISPRSTN);
+		return !(PM_READ(PM_IMAGE) & PM_ISPRSTN);
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From e31b556c0ba21f20c298aa61181b96541140b7b9 Mon Sep 17 00:00:00 2001
From: Romain Sioen <romain.sioen@microchip.com>
Date: Fri, 6 Feb 2026 17:32:58 +0100
Subject: HID: mcp2221: cancel last I2C command on read error

When an I2C SMBus read operation fails, the MCP2221 internal state machine
may not reset correctly, causing subsequent transactions to fail.

By adding a short delay and explicitly cancelling the last command,
we ensure the device is ready for the next operation.

Fix an issue where i2cdetect was not able to detect all devices correctly
on the bus.

Signed-off-by: Romain Sioen <romain.sioen@microchip.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-mcp2221.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index 33603b019f97..ef3b5c77c38e 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -353,6 +353,8 @@ static int mcp_i2c_smbus_read(struct mcp2221 *mcp,
 				usleep_range(90, 100);
 				retries++;
 			} else {
+				usleep_range(980, 1000);
+				mcp_cancel_last_cmd(mcp);
 				return ret;
 			}
 		} else {
-- 
cgit v1.2.3


From 032e084f0d43fda78c33abfc704ac13a0891a6e7 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Fri, 27 Feb 2026 18:43:09 +0000
Subject: tools/sched_ext: fix strtoul() misuse in scx_hotplug_seq()

scx_hotplug_seq() uses strtoul() but validates the result with a
negative check (val < 0), which can never be true for an unsigned
return value.

Use the endptr mechanism to verify the entire string was consumed,
and check errno == ERANGE for overflow detection.

Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/include/scx/compat.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index 8b4897fc8b99..edccc99c7294 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -125,6 +125,7 @@ static inline long scx_hotplug_seq(void)
 {
 	int fd;
 	char buf[32];
+	char *endptr;
 	ssize_t len;
 	long val;
 
@@ -137,8 +138,10 @@ static inline long scx_hotplug_seq(void)
 	buf[len] = 0;
 	close(fd);
 
-	val = strtoul(buf, NULL, 10);
-	SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val);
+	errno = 0;
+	val = strtoul(buf, &endptr, 10);
+	SCX_BUG_ON(errno == ERANGE || endptr == buf ||
+		   (*endptr != '\n' && *endptr != '\0'), "invalid num hotplug events: %ld", val);
 
 	return val;
 }
-- 
cgit v1.2.3


From 3d17d76d1ffb139a7492317b196ee03c8eabc9dc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 27 Feb 2026 09:07:45 -0800
Subject: io_uring/zcrx: don't set rx_page_size when not requested

The rx_buf_len parameter was recently added to the Rx zero-copy
implementation. The expectation is that when not set system will
maintain previous behavior and use the default buffer size (PAGE_SIZE).

This works correctly at the iouring level, but we don't preserve
the same "zero means default" semantics when registering the memory
provider on the netdev. mp_param.rx_page_size is unconditionally
set to PAGE_SIZE. This causes __net_mp_open_rxq() to check for
QCFG_RX_PAGE_SIZE support in the driver, and return -EOPNOTSUPP
for drivers that don't advertise it -- even though the user never
asked for large buffers.

Only set mp_param.rx_page_size when rx_buf_len was explicitly provided,
so that the default page size path works on all zcrx-capable drivers.
mlx5 and fbnic only support 4kB pages in the current release.

Fixes: 795663b4d160 ("io_uring/zcrx: implement large rx buffer support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 97984a73a95d..19b287d21f4b 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -837,7 +837,8 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	if (ret)
 		goto netdev_put_unlock;
 
-	mp_param.rx_page_size = 1U << ifq->niov_shift;
+	if (reg.rx_buf_len)
+		mp_param.rx_page_size = 1U << ifq->niov_shift;
 	mp_param.mp_ops = &io_uring_pp_zc_ops;
 	mp_param.mp_priv = ifq;
 	ret = __net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param, NULL);
-- 
cgit v1.2.3


From 7b6275c80a0c81c5f8943272292dfe67730ce849 Mon Sep 17 00:00:00 2001
From: Eric Badger <ebadger@purestorage.com>
Date: Mon, 23 Feb 2026 10:28:55 -0800
Subject: xprtrdma: Decrement re_receiving on the early exit paths

In the event that rpcrdma_post_recvs() fails to create a work request
(due to memory allocation failure, say) or otherwise exits early, we
should decrement ep->re_receiving before returning. Otherwise we will
hang in rpcrdma_xprt_drain() as re_receiving will never reach zero and
the completion will never be triggered.

On a system with high memory pressure, this can appear as the following
hung task:

    INFO: task kworker/u385:17:8393 blocked for more than 122 seconds.
          Tainted: G S          E       6.19.0 #3
    "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
    task:kworker/u385:17 state:D stack:0     pid:8393  tgid:8393  ppid:2      task_flags:0x4248060 flags:0x00080000
    Workqueue: xprtiod xprt_autoclose [sunrpc]
    Call Trace:
     <TASK>
     __schedule+0x48b/0x18b0
     ? ib_post_send_mad+0x247/0xae0 [ib_core]
     schedule+0x27/0xf0
     schedule_timeout+0x104/0x110
     __wait_for_common+0x98/0x180
     ? __pfx_schedule_timeout+0x10/0x10
     wait_for_completion+0x24/0x40
     rpcrdma_xprt_disconnect+0x444/0x460 [rpcrdma]
     xprt_rdma_close+0x12/0x40 [rpcrdma]
     xprt_autoclose+0x5f/0x120 [sunrpc]
     process_one_work+0x191/0x3e0
     worker_thread+0x2e3/0x420
     ? __pfx_worker_thread+0x10/0x10
     kthread+0x10d/0x230
     ? __pfx_kthread+0x10/0x10
     ret_from_fork+0x273/0x2b0
     ? __pfx_kthread+0x10/0x10
     ret_from_fork_asm+0x1a/0x30

Fixes: 15788d1d1077 ("xprtrdma: Do not refresh Receive Queue while it is draining")
Signed-off-by: Eric Badger <ebadger@purestorage.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/xprtrdma/verbs.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 15bbf953dfad..b51a162885bb 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1362,7 +1362,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 	needed += RPCRDMA_MAX_RECV_BATCH;
 
 	if (atomic_inc_return(&ep->re_receiving) > 1)
-		goto out;
+		goto out_dec;
 
 	/* fast path: all needed reps can be found on the free list */
 	wr = NULL;
@@ -1385,7 +1385,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 		++count;
 	}
 	if (!wr)
-		goto out;
+		goto out_dec;
 
 	rc = ib_post_recv(ep->re_id->qp, wr,
 			  (const struct ib_recv_wr **)&bad_wr);
@@ -1400,9 +1400,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed)
 			--count;
 		}
 	}
+
+out_dec:
 	if (atomic_dec_return(&ep->re_receiving) > 0)
 		complete(&ep->re_done);
-
 out:
 	trace_xprtrdma_post_recvs(r_xprt, count);
 	ep->re_receive_count += count;
-- 
cgit v1.2.3


From 4529e0015432977af3ecc3b9f940fc2a1ef1b265 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <anna.schumaker@oracle.com>
Date: Wed, 18 Feb 2026 11:41:15 -0500
Subject: NFS: Fix NFS KConfig typos

Two issues were noticed after the NFS v4.0 KConfig changes were merged
upstream. First, the text of CONFIG_NFS_V4 should not encourage people
to select it if they are unsure. Second, the new CONFIG_NFS_V4_0 option
should default to "on" instead of "off" to avoid breaking people's
setups if they are using NFS v4.0.

Reported-by: Niklas Cassel <cassel@kernel.org>
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Fixes: 4e0269352534 ("NFS: Add a way to disable NFS v4.0 via KConfig")
Fixes: 7537db24806f ("NFS: Merge CONFIG_NFS_V4_1 with CONFIG_NFS_V4")
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 12cb0ca738af..6bb30543eff0 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -87,7 +87,7 @@ config NFS_V4
 	  space programs which can be found in the Linux nfs-utils package,
 	  available from http://linux-nfs.org/.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 config NFS_SWAP
 	bool "Provide swap over NFS support"
@@ -100,6 +100,7 @@ config NFS_SWAP
 config NFS_V4_0
 	bool "NFS client support for NFSv4.0"
 	depends on NFS_V4
+	default y
 	help
 	  This option enables support for minor version 0 of the NFSv4 protocol
 	  (RFC 3530) in the kernel's NFS client.
-- 
cgit v1.2.3


From e6b899f08066e744f89df16ceb782e06868bd148 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:09 +0100
Subject: nsfs: tighten permission checks for ns iteration ioctls

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-1-d2c2853313bd@kernel.org
Fixes: a1d220d9dafa ("nsfs: iterate through mount namespaces")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.12+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c                 | 13 +++++++++++++
 include/linux/ns_common.h |  2 ++
 kernel/nscommon.c         |  6 ++++++
 3 files changed, 21 insertions(+)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index db91de208645..be36c10c38cf 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -199,6 +199,17 @@ static bool nsfs_ioctl_valid(unsigned int cmd)
 	return false;
 }
 
+static bool may_use_nsfs_ioctl(unsigned int cmd)
+{
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(NS_MNT_GET_NEXT):
+		fallthrough;
+	case _IOC_NR(NS_MNT_GET_PREV):
+		return may_see_all_namespaces();
+	}
+	return true;
+}
+
 static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			unsigned long arg)
 {
@@ -214,6 +225,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 
 	if (!nsfs_ioctl_valid(ioctl))
 		return -ENOIOCTLCMD;
+	if (!may_use_nsfs_ioctl(ioctl))
+		return -EPERM;
 
 	ns = get_proc_ns(file_inode(filp));
 	switch (ioctl) {
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 825f5865bfc5..c8e227a3f9e2 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns)
 
 #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
 
+bool may_see_all_namespaces(void);
+
 static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns)
 {
 	return atomic_read(&ns->__ns_ref_active);
diff --git a/kernel/nscommon.c b/kernel/nscommon.c
index bdc3c86231d3..3166c1fd844a 100644
--- a/kernel/nscommon.c
+++ b/kernel/nscommon.c
@@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns)
 			return;
 	}
 }
+
+bool may_see_all_namespaces(void)
+{
+	return (task_active_pid_ns(current) == &init_pid_ns) &&
+	       ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN);
+}
-- 
cgit v1.2.3


From d2324a9317f00013facb0ba00b00440e19d2af5e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:10 +0100
Subject: nsfs: tighten permission checks for handle opening

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-2-d2c2853313bd@kernel.org
Fixes: 5222470b2fbb ("nsfs: support file handles")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.18+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index be36c10c38cf..c215878d55e8 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -627,7 +627,7 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 
-	if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) {
+	if (owning_ns && !may_see_all_namespaces()) {
 		ns->ops->put(ns);
 		return ERR_PTR(-EPERM);
 	}
-- 
cgit v1.2.3


From 8d76afe84fa2babf604b3c173730d4d2b067e361 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:11 +0100
Subject: nstree: tighten permission checks for listing

Even privileged services should not necessarily be able to see other
privileged service's namespaces so they can't leak information to each
other. Use may_see_all_namespaces() helper that centralizes this policy
until the nstree adapts.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-3-d2c2853313bd@kernel.org
Fixes: 76b6f5dfb3fd ("nstree: add listns()")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.19+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/nstree.c | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/kernel/nstree.c b/kernel/nstree.c
index f36c59e6951d..6d12e5900ac0 100644
--- a/kernel/nstree.c
+++ b/kernel/nstree.c
@@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls,
 static inline bool __must_check may_list_ns(const struct klistns *kls,
 					    struct ns_common *ns)
 {
-	if (kls->user_ns) {
-		if (kls->userns_capable)
-			return true;
-	} else {
-		struct ns_common *owner;
-		struct user_namespace *user_ns;
-
-		owner = ns_owner(ns);
-		if (owner)
-			user_ns = to_user_ns(owner);
-		else
-			user_ns = &init_user_ns;
-		if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN))
-			return true;
-	}
-
-	if (is_current_namespace(ns))
+	if (kls->user_ns && kls->userns_capable)
 		return true;
-
-	if (ns->ns_type != CLONE_NEWUSER)
-		return false;
-
-	if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN))
+	if (is_current_namespace(ns))
 		return true;
-
-	return false;
+	return may_see_all_namespaces();
 }
 
 static inline void ns_put(struct ns_common *ns)
@@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls)
 
 	ret = 0;
 	head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head;
-	kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN);
+	kls->userns_capable = may_see_all_namespaces();
 
 	rcu_read_lock();
 
-- 
cgit v1.2.3


From 4c7b2ec23cc5d880e3ffe35e8c2aad686b67723a Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 26 Feb 2026 14:50:12 +0100
Subject: selftests: fix mntns iteration selftests

Now that we changed permission checking make sure that we reflect that
in the selftests.

Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-4-d2c2853313bd@kernel.org
Fixes: 9d87b1067382 ("selftests: add tests for mntns iteration")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Cc: stable@kernel.org # v6.14+
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 .../selftests/filesystems/nsfs/iterate_mntns.c     | 25 +++++++++++++---------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
index 61e55dfbf121..e19ff8168baf 100644
--- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
+++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
@@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) {
 	__u64 mnt_ns_id[MNT_NS_COUNT];
 };
 
+static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info)
+{
+	for (int i = 0; i < MNT_NS_COUNT; i++) {
+		if (mnt_ns_id[i] == info->mnt_ns_id)
+			return true;
+	}
+	return false;
+}
+
 FIXTURE_SETUP(iterate_mount_namespaces)
 {
 	for (int i = 0; i < MNT_NS_COUNT; i++)
 		self->fd_mnt_ns[i] = -EBADF;
 
-	/*
-	 * Creating a new user namespace let's us guarantee that we only see
-	 * mount namespaces that we did actually create.
-	 */
-	ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
-
 	for (int i = 0; i < MNT_NS_COUNT; i++) {
 		struct mnt_ns_info info = {};
 
@@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward)
 	fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC);
 	ASSERT_GE(fd_mnt_ns_cur, 0);
 
-	for (;; count++) {
+	for (;;) {
 		struct mnt_ns_info info = {};
 		int fd_mnt_ns_next;
 
 		fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info);
 		if (fd_mnt_ns_next < 0 && errno == ENOENT)
 			break;
+		if (mntns_in_list(self->mnt_ns_id, &info))
+			count++;
 		ASSERT_GE(fd_mnt_ns_next, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_next;
@@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards)
 	fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC);
 	ASSERT_GE(fd_mnt_ns_cur, 0);
 
-	for (;; count++) {
+	for (;;) {
 		struct mnt_ns_info info = {};
 		int fd_mnt_ns_prev;
 
 		fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info);
 		if (fd_mnt_ns_prev < 0 && errno == ENOENT)
 			break;
+		if (mntns_in_list(self->mnt_ns_id, &info))
+			count++;
 		ASSERT_GE(fd_mnt_ns_prev, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_prev;
@@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward)
 		ASSERT_GE(fd_mnt_ns_next, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_next;
-		ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
 	}
 }
 
@@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward)
 		ASSERT_GE(fd_mnt_ns_prev, 0);
 		ASSERT_EQ(close(fd_mnt_ns_cur), 0);
 		fd_mnt_ns_cur = fd_mnt_ns_prev;
-		ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
 	}
 }
 
-- 
cgit v1.2.3


From 1df97a7453eec80c1912c2d0360290a3970a7671 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:01 -0800
Subject: bpf: Register dtor for freeing special fields

There is a race window where BPF hash map elements can leak special
fields if the program with access to the map value recreates these
special fields between the check_and_free_fields done on the map value
and its eventual return to the memory allocator.

Several ways were explored prior to this patch, most notably [0] tried
to use a poison value to reject attempts to recreate special fields for
map values that have been logically deleted but still accessible to BPF
programs (either while sitting in the free list or when reused). While
this approach works well for task work, timers, wq, etc., it is harder
to apply the idea to kptrs, which have a similar race and failure mode.

Instead, we change bpf_mem_alloc to allow registering destructor for
allocated elements, such that when they are returned to the allocator,
any special fields created while they were accessible to programs in the
mean time will be freed. If these values get reused, we do not free the
fields again before handing the element back. The special fields thus
may remain initialized while the map value sits in a free list.

When bpf_mem_alloc is retired in the future, a similar concept can be
introduced to kmalloc_nolock-backed kmem_cache, paired with the existing
idea of a constructor.

Note that the destructor registration happens in map_check_btf, after
the BTF record is populated and (at that point) avaiable for inspection
and duplication. Duplication is necessary since the freeing of embedded
bpf_mem_alloc can be decoupled from actual map lifetime due to logic
introduced to reduce the cost of rcu_barrier()s in mem alloc free path in
9f2c6e96c65e ("bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc.").

As such, once all callbacks are done, we must also free the duplicated
record. To remove dependency on the bpf_map itself, also stash the key
size of the map to obtain value from htab_elem long after the map is
gone.

  [0]: https://lore.kernel.org/bpf/20260216131341.1285427-1-mykyta.yatsenko5@gmail.com

Fixes: 14a324f6a67e ("bpf: Wire up freeing of referenced kptr")
Fixes: 1bfbc267ec91 ("bpf: Enable bpf_timer and bpf_wq in any context")
Reported-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: syzbot@syzkaller.appspotmail.com
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_mem_alloc.h |  6 +++
 kernel/bpf/hashtab.c          | 87 +++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/memalloc.c         | 58 +++++++++++++++++++++++------
 3 files changed, 140 insertions(+), 11 deletions(-)

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index e45162ef59bb..4ce0d27f8ea2 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -14,6 +14,8 @@ struct bpf_mem_alloc {
 	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
+	void (*dtor_ctx_free)(void *ctx);
+	void *dtor_ctx;
 };
 
 /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects.
@@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 /* The percpu allocation with a specific unit size. */
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
+void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma,
+			    void (*dtor)(void *obj, void *ctx),
+			    void (*dtor_ctx_free)(void *ctx),
+			    void *ctx);
 
 /* Check the allocation size for kmalloc equivalent allocator */
 int bpf_mem_alloc_check_size(bool percpu, size_t size);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3b9d297a53be..582f0192b7e1 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -125,6 +125,11 @@ struct htab_elem {
 	char key[] __aligned(8);
 };
 
+struct htab_btf_record {
+	struct btf_record *record;
+	u32 key_size;
+};
+
 static inline bool htab_is_prealloc(const struct bpf_htab *htab)
 {
 	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
@@ -457,6 +462,84 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 	return 0;
 }
 
+static void htab_mem_dtor(void *obj, void *ctx)
+{
+	struct htab_btf_record *hrec = ctx;
+	struct htab_elem *elem = obj;
+	void *map_value;
+
+	if (IS_ERR_OR_NULL(hrec->record))
+		return;
+
+	map_value = htab_elem_value(elem, hrec->key_size);
+	bpf_obj_free_fields(hrec->record, map_value);
+}
+
+static void htab_pcpu_mem_dtor(void *obj, void *ctx)
+{
+	void __percpu *pptr = *(void __percpu **)obj;
+	struct htab_btf_record *hrec = ctx;
+	int cpu;
+
+	if (IS_ERR_OR_NULL(hrec->record))
+		return;
+
+	for_each_possible_cpu(cpu)
+		bpf_obj_free_fields(hrec->record, per_cpu_ptr(pptr, cpu));
+}
+
+static void htab_dtor_ctx_free(void *ctx)
+{
+	struct htab_btf_record *hrec = ctx;
+
+	btf_record_free(hrec->record);
+	kfree(ctx);
+}
+
+static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *))
+{
+	u32 key_size = htab->map.key_size;
+	const struct bpf_mem_alloc *ma;
+	struct htab_btf_record *hrec;
+	int err;
+
+	/* No need for dtors. */
+	if (IS_ERR_OR_NULL(htab->map.record))
+		return 0;
+
+	hrec = kzalloc(sizeof(*hrec), GFP_KERNEL);
+	if (!hrec)
+		return -ENOMEM;
+	hrec->key_size = key_size;
+	hrec->record = btf_record_dup(htab->map.record);
+	if (IS_ERR(hrec->record)) {
+		err = PTR_ERR(hrec->record);
+		kfree(hrec);
+		return err;
+	}
+	ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma;
+	/* Kinda sad, but cast away const-ness since we change ma->dtor. */
+	bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec);
+	return 0;
+}
+
+static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			      const struct btf_type *key_type, const struct btf_type *value_type)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+	if (htab_is_prealloc(htab))
+		return 0;
+	/*
+	 * We must set the dtor using this callback, as map's BTF record is not
+	 * populated in htab_map_alloc(), so it will always appear as NULL.
+	 */
+	if (htab_is_percpu(htab))
+		return htab_set_dtor(htab, htab_pcpu_mem_dtor);
+	else
+		return htab_set_dtor(htab, htab_mem_dtor);
+}
+
 static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -2281,6 +2364,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2303,6 +2387,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2482,6 +2567,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
@@ -2502,6 +2588,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_check_btf = htab_map_check_btf,
 	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index bd45dda9dc35..682a9f34214b 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -102,6 +102,8 @@ struct bpf_mem_cache {
 	int percpu_size;
 	bool draining;
 	struct bpf_mem_cache *tgt;
+	void (*dtor)(void *obj, void *ctx);
+	void *dtor_ctx;
 
 	/* list of objects to be freed after RCU GP */
 	struct llist_head free_by_rcu;
@@ -260,12 +262,14 @@ static void free_one(void *obj, bool percpu)
 	kfree(obj);
 }
 
-static int free_all(struct llist_node *llnode, bool percpu)
+static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool percpu)
 {
 	struct llist_node *pos, *t;
 	int cnt = 0;
 
 	llist_for_each_safe(pos, t, llnode) {
+		if (c->dtor)
+			c->dtor((void *)pos + LLIST_NODE_SZ, c->dtor_ctx);
 		free_one(pos, percpu);
 		cnt++;
 	}
@@ -276,7 +280,7 @@ static void __free_rcu(struct rcu_head *head)
 {
 	struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace);
 
-	free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
+	free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size);
 	atomic_set(&c->call_rcu_ttrace_in_progress, 0);
 }
 
@@ -308,7 +312,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c)
 	if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) {
 		if (unlikely(READ_ONCE(c->draining))) {
 			llnode = llist_del_all(&c->free_by_rcu_ttrace);
-			free_all(llnode, !!c->percpu_size);
+			free_all(c, llnode, !!c->percpu_size);
 		}
 		return;
 	}
@@ -417,7 +421,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c)
 	dec_active(c, &flags);
 
 	if (unlikely(READ_ONCE(c->draining))) {
-		free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
+		free_all(c, llist_del_all(&c->waiting_for_gp), !!c->percpu_size);
 		atomic_set(&c->call_rcu_in_progress, 0);
 	} else {
 		call_rcu_hurry(&c->rcu, __free_by_rcu);
@@ -635,13 +639,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
 	 * Except for waiting_for_gp_ttrace list, there are no concurrent operations
 	 * on these lists, so it is safe to use __llist_del_all().
 	 */
-	free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu);
-	free_all(__llist_del_all(&c->free_llist), percpu);
-	free_all(__llist_del_all(&c->free_llist_extra), percpu);
-	free_all(__llist_del_all(&c->free_by_rcu), percpu);
-	free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu);
-	free_all(llist_del_all(&c->waiting_for_gp), percpu);
+	free_all(c, llist_del_all(&c->free_by_rcu_ttrace), percpu);
+	free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), percpu);
+	free_all(c, __llist_del_all(&c->free_llist), percpu);
+	free_all(c, __llist_del_all(&c->free_llist_extra), percpu);
+	free_all(c, __llist_del_all(&c->free_by_rcu), percpu);
+	free_all(c, __llist_del_all(&c->free_llist_extra_rcu), percpu);
+	free_all(c, llist_del_all(&c->waiting_for_gp), percpu);
 }
 
 static void check_mem_cache(struct bpf_mem_cache *c)
@@ -680,6 +684,9 @@ static void check_leaked_objs(struct bpf_mem_alloc *ma)
 
 static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
 {
+	/* We can free dtor ctx only once all callbacks are done using it. */
+	if (ma->dtor_ctx_free)
+		ma->dtor_ctx_free(ma->dtor_ctx);
 	check_leaked_objs(ma);
 	free_percpu(ma->cache);
 	free_percpu(ma->caches);
@@ -1014,3 +1021,32 @@ int bpf_mem_alloc_check_size(bool percpu, size_t size)
 
 	return 0;
 }
+
+void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, void (*dtor)(void *obj, void *ctx),
+			    void (*dtor_ctx_free)(void *ctx), void *ctx)
+{
+	struct bpf_mem_caches *cc;
+	struct bpf_mem_cache *c;
+	int cpu, i;
+
+	ma->dtor_ctx_free = dtor_ctx_free;
+	ma->dtor_ctx = ctx;
+
+	if (ma->cache) {
+		for_each_possible_cpu(cpu) {
+			c = per_cpu_ptr(ma->cache, cpu);
+			c->dtor = dtor;
+			c->dtor_ctx = ctx;
+		}
+	}
+	if (ma->caches) {
+		for_each_possible_cpu(cpu) {
+			cc = per_cpu_ptr(ma->caches, cpu);
+			for (i = 0; i < NUM_CACHES; i++) {
+				c = &cc->cache[i];
+				c->dtor = dtor;
+				c->dtor_ctx = ctx;
+			}
+		}
+	}
+}
-- 
cgit v1.2.3


From ae51772b1e94ba1d76db19085957dbccac189c1c Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:02 -0800
Subject: bpf: Lose const-ness of map in map_check_btf()

BPF hash map may now use the map_check_btf() callback to decide whether
to set a dtor on its bpf_mem_alloc or not. Unlike C++ where members can
opt out of const-ness using mutable, we must lose the const qualifier on
the callback such that we can avoid the ugly cast. Make the change and
adjust all existing users, and lose the comment in hashtab.c.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h               | 4 ++--
 include/linux/bpf_local_storage.h | 2 +-
 kernel/bpf/arena.c                | 2 +-
 kernel/bpf/arraymap.c             | 2 +-
 kernel/bpf/bloom_filter.c         | 2 +-
 kernel/bpf/bpf_insn_array.c       | 2 +-
 kernel/bpf/bpf_local_storage.c    | 2 +-
 kernel/bpf/hashtab.c              | 9 ++++-----
 kernel/bpf/local_storage.c        | 2 +-
 kernel/bpf/lpm_trie.c             | 2 +-
 kernel/bpf/syscall.c              | 2 +-
 11 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b78b53198a2e..05b34a6355b0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -124,7 +124,7 @@ struct bpf_map_ops {
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
-	int (*map_check_btf)(const struct bpf_map *map,
+	int (*map_check_btf)(struct bpf_map *map,
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
@@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 		map->ops->map_seq_show_elem;
 }
 
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
 		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 85efa9772530..8157e8da61d4 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage);
 void bpf_local_storage_map_free(struct bpf_map *map,
 				struct bpf_local_storage_cache *cache);
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+int bpf_local_storage_map_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type);
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 144f30e740e8..f355cf1c1a16 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -303,7 +303,7 @@ static long arena_map_update_elem(struct bpf_map *map, void *key,
 	return -EOPNOTSUPP;
 }
 
-static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int arena_map_check_btf(struct bpf_map *map, const struct btf *btf,
 			       const struct btf_type *key_type, const struct btf_type *value_type)
 {
 	return 0;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 26763df6134a..33de68c95ad8 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -548,7 +548,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int array_map_check_btf(const struct bpf_map *map,
+static int array_map_check_btf(struct bpf_map *map,
 			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index 35e1ddca74d2..b73336c976b7 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -180,7 +180,7 @@ static long bloom_map_update_elem(struct bpf_map *map, void *key,
 	return -EINVAL;
 }
 
-static int bloom_map_check_btf(const struct bpf_map *map,
+static int bloom_map_check_btf(struct bpf_map *map,
 			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
diff --git a/kernel/bpf/bpf_insn_array.c b/kernel/bpf/bpf_insn_array.c
index c0286f25ca3c..a2f84afe6f7c 100644
--- a/kernel/bpf/bpf_insn_array.c
+++ b/kernel/bpf/bpf_insn_array.c
@@ -98,7 +98,7 @@ static long insn_array_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
-static int insn_array_check_btf(const struct bpf_map *map,
+static int insn_array_check_btf(struct bpf_map *map,
 			      const struct btf *btf,
 			      const struct btf_type *key_type,
 			      const struct btf_type *value_type)
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b28f07d3a0db..2bf5ca5ae0df 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -797,7 +797,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
 	return 0;
 }
 
-int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+int bpf_local_storage_map_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 582f0192b7e1..bc6bc8bb871d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -496,10 +496,10 @@ static void htab_dtor_ctx_free(void *ctx)
 	kfree(ctx);
 }
 
-static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void *))
+static int htab_set_dtor(struct bpf_htab *htab, void (*dtor)(void *, void *))
 {
 	u32 key_size = htab->map.key_size;
-	const struct bpf_mem_alloc *ma;
+	struct bpf_mem_alloc *ma;
 	struct htab_btf_record *hrec;
 	int err;
 
@@ -518,12 +518,11 @@ static int htab_set_dtor(const struct bpf_htab *htab, void (*dtor)(void *, void
 		return err;
 	}
 	ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma;
-	/* Kinda sad, but cast away const-ness since we change ma->dtor. */
-	bpf_mem_alloc_set_dtor((struct bpf_mem_alloc *)ma, dtor, htab_dtor_ctx_free, hrec);
+	bpf_mem_alloc_set_dtor(ma, dtor, htab_dtor_ctx_free, hrec);
 	return 0;
 }
 
-static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf,
 			      const struct btf_type *key_type, const struct btf_type *value_type)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 1ccbf28b2ad9..8fca0c64f7b1 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -364,7 +364,7 @@ static long cgroup_storage_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
-static int cgroup_storage_check_btf(const struct bpf_map *map,
+static int cgroup_storage_check_btf(struct bpf_map *map,
 				    const struct btf *btf,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1adeb4d3b8cf..0f57608b385d 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -751,7 +751,7 @@ free_stack:
 	return err;
 }
 
-static int trie_check_btf(const struct bpf_map *map,
+static int trie_check_btf(struct bpf_map *map,
 			  const struct btf *btf,
 			  const struct btf_type *key_type,
 			  const struct btf_type *value_type)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0378e83b4099..274039e36465 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1234,7 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(bpf_obj_name_cpy);
 
-int map_check_no_btf(const struct bpf_map *map,
+int map_check_no_btf(struct bpf_map *map,
 		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type)
-- 
cgit v1.2.3


From f41deee082dc7b1c198de21710cb5cb9c604cae0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:03 -0800
Subject: bpf: Delay freeing fields in local storage

Currently, when use_kmalloc_nolock is false, the freeing of fields for a
local storage selem is done eagerly before waiting for the RCU or RCU
tasks trace grace period to elapse. This opens up a window where the
program which has access to the selem can recreate the fields after the
freeing of fields is done eagerly, causing memory leaks when the element
is finally freed and returned to the kernel.

Make a few changes to address this. First, delay the freeing of fields
until after the grace periods have expired using a __bpf_selem_free_rcu
wrapper which is eventually invoked after transitioning through the
necessary number of grace period waits. Replace usage of the kfree_rcu
with call_rcu to be able to take a custom callback. Finally, care needs
to be taken to extend the rcu barriers for all cases, and not just when
use_kmalloc_nolock is true, as RCU and RCU tasks trace callbacks can be
in flight for either case and access the smap field, which is used to
obtain the BTF record to walk over special fields in the map value.

While we're at it, drop migrate_disable() from bpf_selem_free_rcu, since
migration should be disabled for RCU callbacks already.

Fixes: 9bac675e6368 ("bpf: Postpone bpf_obj_free_fields to the rcu callback")
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-4-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/bpf_local_storage.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 2bf5ca5ae0df..d7db1ada2dad 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -164,16 +164,28 @@ static void bpf_local_storage_free(struct bpf_local_storage *local_storage,
 			     bpf_local_storage_free_trace_rcu);
 }
 
-/* rcu tasks trace callback for use_kmalloc_nolock == false */
-static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
+/* rcu callback for use_kmalloc_nolock == false */
+static void __bpf_selem_free_rcu(struct rcu_head *rcu)
 {
 	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
 
 	selem = container_of(rcu, struct bpf_local_storage_elem, rcu);
+	/* bpf_selem_unlink_nofail may have already cleared smap and freed fields. */
+	smap = rcu_dereference_check(SDATA(selem)->smap, 1);
+
+	if (smap)
+		bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
+	kfree(selem);
+}
+
+/* rcu tasks trace callback for use_kmalloc_nolock == false */
+static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
+{
 	if (rcu_trace_implies_rcu_gp())
-		kfree(selem);
+		__bpf_selem_free_rcu(rcu);
 	else
-		kfree_rcu(selem, rcu);
+		call_rcu(rcu, __bpf_selem_free_rcu);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -181,7 +193,7 @@ static void __bpf_selem_free(struct bpf_local_storage_elem *selem,
 			     bool vanilla_rcu)
 {
 	if (vanilla_rcu)
-		kfree_rcu(selem, rcu);
+		call_rcu(&selem->rcu, __bpf_selem_free_rcu);
 	else
 		call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu);
 }
@@ -195,11 +207,8 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu)
 	/* The bpf_local_storage_map_free will wait for rcu_barrier */
 	smap = rcu_dereference_check(SDATA(selem)->smap, 1);
 
-	if (smap) {
-		migrate_disable();
+	if (smap)
 		bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
-		migrate_enable();
-	}
 	kfree_nolock(selem);
 }
 
@@ -214,18 +223,12 @@ static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 void bpf_selem_free(struct bpf_local_storage_elem *selem,
 		    bool reuse_now)
 {
-	struct bpf_local_storage_map *smap;
-
-	smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held());
-
 	if (!selem->use_kmalloc_nolock) {
 		/*
 		 * No uptr will be unpin even when reuse_now == false since uptr
 		 * is only supported in task local storage, where
 		 * smap->use_kmalloc_nolock == true.
 		 */
-		if (smap)
-			bpf_obj_free_fields(smap->map.record, SDATA(selem)->data);
 		__bpf_selem_free(selem, reuse_now);
 		return;
 	}
@@ -958,10 +961,9 @@ restart:
 	 */
 	synchronize_rcu();
 
-	if (smap->use_kmalloc_nolock) {
-		rcu_barrier_tasks_trace();
-		rcu_barrier();
-	}
+	/* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */
+	rcu_barrier_tasks_trace();
+	rcu_barrier();
 	kvfree(smap->buckets);
 	bpf_map_area_free(smap);
 }
-- 
cgit v1.2.3


From baa35b3cb6b642b903162aacff13181e170c4ecc Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:04 -0800
Subject: bpf: Retire rcu_trace_implies_rcu_gp() from local storage

This assumption will always hold going forward, hence just remove the
various checks and assume it is true with a comment for the uninformed
reader.

Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/bpf_local_storage.c | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index d7db1ada2dad..9c96a4477f81 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -107,14 +107,12 @@ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
 {
 	struct bpf_local_storage *local_storage;
 
-	/* If RCU Tasks Trace grace period implies RCU grace period, do
-	 * kfree(), else do kfree_rcu().
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
 	 */
 	local_storage = container_of(rcu, struct bpf_local_storage, rcu);
-	if (rcu_trace_implies_rcu_gp())
-		kfree(local_storage);
-	else
-		kfree_rcu(local_storage, rcu);
+	kfree(local_storage);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -138,10 +136,11 @@ static void bpf_local_storage_free_rcu(struct rcu_head *rcu)
 
 static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		bpf_local_storage_free_rcu(rcu);
-	else
-		call_rcu(rcu, bpf_local_storage_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	bpf_local_storage_free_rcu(rcu);
 }
 
 static void bpf_local_storage_free(struct bpf_local_storage *local_storage,
@@ -182,10 +181,11 @@ static void __bpf_selem_free_rcu(struct rcu_head *rcu)
 /* rcu tasks trace callback for use_kmalloc_nolock == false */
 static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		__bpf_selem_free_rcu(rcu);
-	else
-		call_rcu(rcu, __bpf_selem_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	__bpf_selem_free_rcu(rcu);
 }
 
 /* Handle use_kmalloc_nolock == false */
@@ -214,10 +214,11 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu)
 
 static void bpf_selem_free_trace_rcu(struct rcu_head *rcu)
 {
-	if (rcu_trace_implies_rcu_gp())
-		bpf_selem_free_rcu(rcu);
-	else
-		call_rcu(rcu, bpf_selem_free_rcu);
+	/*
+	 * RCU Tasks Trace grace period implies RCU grace period, do
+	 * kfree() directly.
+	 */
+	bpf_selem_free_rcu(rcu);
 }
 
 void bpf_selem_free(struct bpf_local_storage_elem *selem,
-- 
cgit v1.2.3


From 2939d7b3b0e5f35359ce8f69dbbad0bfc4e920b6 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Fri, 27 Feb 2026 14:48:05 -0800
Subject: selftests/bpf: Add tests for special fields races

Add a couple of tests to ensure that the refcount drops to zero when we
exercise the race where creation of a special field succeeds the logical
bpf_obj_free_fields done when deleting an element. Prior to previous
changes, the fields would be freed eagerly and repopulate and end up
leaking, causing the reference to not drop down correctly. Running this
test on a kernel without fixes will cause a hang in delete_module, since
the module reference stays active due to the leaked kptr not dropping
it. After the fixes tests succeed as expected.

Reviewed-by: Amery Hung <ameryhung@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260227224806.646888-6-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/prog_tests/map_kptr_race.c       | 218 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/map_kptr_race.c  | 197 +++++++++++++++++++
 2 files changed, 415 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
 create mode 100644 tools/testing/selftests/bpf/progs/map_kptr_race.c

diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
new file mode 100644
index 000000000000..506ed55e8528
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "map_kptr_race.skel.h"
+
+static int get_map_id(int map_fd)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+
+	if (!ASSERT_OK(bpf_map_get_info_by_fd(map_fd, &info, &len), "get_map_info"))
+		return -1;
+	return info.id;
+}
+
+static int read_refs(struct map_kptr_race *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	int ret;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &opts);
+	if (!ASSERT_OK(ret, "count_ref run"))
+		return -1;
+	if (!ASSERT_OK(opts.retval, "count_ref retval"))
+		return -1;
+	return skel->bss->num_of_refs;
+}
+
+static void test_htab_leak(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct map_kptr_race *skel, *watcher;
+	int ret, map_id;
+
+	skel = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_htab_leak), &opts);
+	if (!ASSERT_OK(ret, "test_htab_leak run"))
+		goto out_skel;
+	if (!ASSERT_OK(opts.retval, "test_htab_leak retval"))
+		goto out_skel;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_hash_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "htab refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	map_kptr_race__destroy(skel);
+}
+
+static void test_percpu_htab_leak(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct map_kptr_race *skel, *watcher;
+	int ret, map_id;
+
+	skel = map_kptr_race__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+	if (skel->rodata->nr_cpus > 16)
+		skel->rodata->nr_cpus = 16;
+
+	ret = map_kptr_race__load(skel);
+	if (!ASSERT_OK(ret, "load"))
+		goto out_skel;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_percpu_htab_leak), &opts);
+	if (!ASSERT_OK(ret, "test_percpu_htab_leak run"))
+		goto out_skel;
+	if (!ASSERT_OK(opts.retval, "test_percpu_htab_leak retval"))
+		goto out_skel;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_percpu_hash_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "percpu_htab refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	map_kptr_race__destroy(skel);
+}
+
+static void test_sk_ls_leak(void)
+{
+	struct map_kptr_race *skel, *watcher;
+	int listen_fd = -1, client_fd = -1, map_id;
+
+	skel = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (!ASSERT_OK(map_kptr_race__attach(skel), "attach"))
+		goto out_skel;
+
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(listen_fd, 0, "start_server"))
+		goto out_skel;
+
+	client_fd = connect_to_fd(listen_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto out_skel;
+
+	if (!ASSERT_EQ(skel->bss->sk_ls_leak_done, 1, "sk_ls_leak_done"))
+		goto out_skel;
+
+	close(client_fd);
+	client_fd = -1;
+	close(listen_fd);
+	listen_fd = -1;
+
+	map_id = get_map_id(bpf_map__fd(skel->maps.race_sk_ls_map));
+	if (!ASSERT_GE(map_id, 0, "map_id"))
+		goto out_skel;
+
+	watcher = map_kptr_race__open_and_load();
+	if (!ASSERT_OK_PTR(watcher, "watcher open_and_load"))
+		goto out_skel;
+
+	watcher->bss->target_map_id = map_id;
+	watcher->links.map_put = bpf_program__attach(watcher->progs.map_put);
+	if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry"))
+		goto out_watcher;
+	watcher->links.sk_map_free = bpf_program__attach(watcher->progs.sk_map_free);
+	if (!ASSERT_OK_PTR(watcher->links.sk_map_free, "attach fexit"))
+		goto out_watcher;
+
+	map_kptr_race__destroy(skel);
+	skel = NULL;
+
+	kern_sync_rcu();
+
+	while (!READ_ONCE(watcher->bss->map_freed))
+		sched_yield();
+
+	ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed");
+	ASSERT_EQ(read_refs(watcher), 2, "sk_ls refcount");
+
+out_watcher:
+	map_kptr_race__destroy(watcher);
+out_skel:
+	if (client_fd >= 0)
+		close(client_fd);
+	if (listen_fd >= 0)
+		close(listen_fd);
+	map_kptr_race__destroy(skel);
+}
+
+void serial_test_map_kptr_race(void)
+{
+	if (test__start_subtest("htab_leak"))
+		test_htab_leak();
+	if (test__start_subtest("percpu_htab_leak"))
+		test_percpu_htab_leak();
+	if (test__start_subtest("sk_ls_leak"))
+		test_sk_ls_leak();
+}
diff --git a/tools/testing/selftests/bpf/progs/map_kptr_race.c b/tools/testing/selftests/bpf/progs/map_kptr_race.c
new file mode 100644
index 000000000000..f6f136cd8f60
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_kptr_race.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+struct map_value {
+	struct prog_test_ref_kfunc __kptr *ref_ptr;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} race_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} race_percpu_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} race_sk_ls_map SEC(".maps");
+
+int num_of_refs;
+int sk_ls_leak_done;
+int target_map_id;
+int map_freed;
+const volatile int nr_cpus;
+
+SEC("tc")
+int test_htab_leak(struct __sk_buff *skb)
+{
+	struct prog_test_ref_kfunc *p, *old;
+	struct map_value val = {};
+	struct map_value *v;
+	int key = 0;
+
+	if (bpf_map_update_elem(&race_hash_map, &key, &val, BPF_ANY))
+		return 1;
+
+	v = bpf_map_lookup_elem(&race_hash_map, &key);
+	if (!v)
+		return 2;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 3;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	bpf_map_delete_elem(&race_hash_map, &key);
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 4;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	return 0;
+}
+
+static int fill_percpu_kptr(struct map_value *v)
+{
+	struct prog_test_ref_kfunc *p, *old;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 1;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+	return 0;
+}
+
+SEC("tc")
+int test_percpu_htab_leak(struct __sk_buff *skb)
+{
+	struct map_value *v, *arr[16] = {};
+	struct map_value val = {};
+	int key = 0;
+	int err = 0;
+
+	if (bpf_map_update_elem(&race_percpu_hash_map, &key, &val, BPF_ANY))
+		return 1;
+
+	for (int i = 0; i < nr_cpus; i++) {
+		v = bpf_map_lookup_percpu_elem(&race_percpu_hash_map, &key, i);
+		if (!v)
+			return 2;
+		arr[i] = v;
+	}
+
+	bpf_map_delete_elem(&race_percpu_hash_map, &key);
+
+	for (int i = 0; i < nr_cpus; i++) {
+		v = arr[i];
+		err = fill_percpu_kptr(v);
+		if (err)
+			return 3;
+	}
+
+	return 0;
+}
+
+SEC("tp_btf/inet_sock_set_state")
+int BPF_PROG(test_sk_ls_leak, struct sock *sk, int oldstate, int newstate)
+{
+	struct prog_test_ref_kfunc *p, *old;
+	struct map_value *v;
+
+	if (newstate != BPF_TCP_SYN_SENT)
+		return 0;
+
+	if (sk_ls_leak_done)
+		return 0;
+
+	v = bpf_sk_storage_get(&race_sk_ls_map, sk, NULL,
+				BPF_SK_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 0;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	bpf_sk_storage_delete(&race_sk_ls_map, sk);
+
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+	if (!p)
+		return 0;
+	old = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (old)
+		bpf_kfunc_call_test_release(old);
+
+	sk_ls_leak_done = 1;
+	return 0;
+}
+
+long target_map_ptr;
+
+SEC("fentry/bpf_map_put")
+int BPF_PROG(map_put, struct bpf_map *map)
+{
+	if (target_map_id && map->id == (u32)target_map_id)
+		target_map_ptr = (long)map;
+	return 0;
+}
+
+SEC("fexit/htab_map_free")
+int BPF_PROG(htab_map_free, struct bpf_map *map)
+{
+	if (target_map_ptr && (long)map == target_map_ptr)
+		map_freed = 1;
+	return 0;
+}
+
+SEC("fexit/bpf_sk_storage_map_free")
+int BPF_PROG(sk_map_free, struct bpf_map *map)
+{
+	if (target_map_ptr && (long)map == target_map_ptr)
+		map_freed = 1;
+	return 0;
+}
+
+SEC("syscall")
+int count_ref(void *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long arg = 0;
+
+	p = bpf_kfunc_call_test_acquire(&arg);
+	if (!p)
+		return 1;
+
+	num_of_refs = p->cnt.refs.counter;
+
+	bpf_kfunc_call_test_release(p);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 869c63d5975d55e97f6b168e885452b3da20ea47 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:14:55 +0800
Subject: bpf: Fix race in cpumap on PREEMPT_RT

On PREEMPT_RT kernels, the per-CPU xdp_bulk_queue (bq) can be accessed
concurrently by multiple preemptible tasks on the same CPU.

The original code assumes bq_enqueue() and __cpu_map_flush() run
atomically with respect to each other on the same CPU, relying on
local_bh_disable() to prevent preemption. However, on PREEMPT_RT,
local_bh_disable() only calls migrate_disable() (when
PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable
preemption, which allows CFS scheduling to preempt a task during
bq_flush_to_queue(), enabling another task on the same CPU to enter
bq_enqueue() and operate on the same per-CPU bq concurrently.

This leads to several races:

1. Double __list_del_clearprev(): after bq->count is reset in
   bq_flush_to_queue(), a preempting task can call bq_enqueue() ->
   bq_flush_to_queue() on the same bq when bq->count reaches
   CPU_MAP_BULK_SIZE. Both tasks then call __list_del_clearprev()
   on the same bq->flush_node, the second call dereferences the
   prev pointer that was already set to NULL by the first.

2. bq->count and bq->q[] races: concurrent bq_enqueue() can corrupt
   the packet queue while bq_flush_to_queue() is processing it.

The race between task A (__cpu_map_flush -> bq_flush_to_queue) and
task B (bq_enqueue -> bq_flush_to_queue) on the same CPU:

  Task A (xdp_do_flush)          Task B (cpu_map_enqueue)
  ----------------------         ------------------------
  bq_flush_to_queue(bq)
    spin_lock(&q->producer_lock)
    /* flush bq->q[] to ptr_ring */
    bq->count = 0
    spin_unlock(&q->producer_lock)
                                   bq_enqueue(rcpu, xdpf)
    <-- CFS preempts Task A -->      bq->q[bq->count++] = xdpf
                                     /* ... more enqueues until full ... */
                                     bq_flush_to_queue(bq)
                                       spin_lock(&q->producer_lock)
                                       /* flush to ptr_ring */
                                       spin_unlock(&q->producer_lock)
                                       __list_del_clearprev(flush_node)
                                         /* sets flush_node.prev = NULL */
    <-- Task A resumes -->
    __list_del_clearprev(flush_node)
      flush_node.prev->next = ...
      /* prev is NULL -> kernel oops */

Fix this by adding a local_lock_t to xdp_bulk_queue and acquiring it
in bq_enqueue() and __cpu_map_flush(). These paths already run under
local_bh_disable(), so use local_lock_nested_bh() which on non-RT is
a pure annotation with no overhead, and on PREEMPT_RT provides a
per-CPU sleeping lock that serializes access to the bq.

To reproduce, insert an mdelay(100) between bq->count = 0 and
__list_del_clearprev() in bq_flush_to_queue(), then run reproducer
provided by syzkaller.

Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Reported-by: syzbot+2b3391f44313b3983e91@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69369331.a70a0220.38f243.009d.GAE@google.com/T/
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://lore.kernel.org/r/20260225121459.183121-2-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cpumap.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 04171fbc39cb..32b43cb9061b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -29,6 +29,7 @@
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
+#include <linux/local_lock.h>
 #include <linux/completion.h>
 #include <trace/events/xdp.h>
 #include <linux/btf_ids.h>
@@ -52,6 +53,7 @@ struct xdp_bulk_queue {
 	struct list_head flush_node;
 	struct bpf_cpu_map_entry *obj;
 	unsigned int count;
+	local_lock_t bq_lock;
 };
 
 /* Struct for every remote "destination" CPU in map */
@@ -451,6 +453,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	for_each_possible_cpu(i) {
 		bq = per_cpu_ptr(rcpu->bulkq, i);
 		bq->obj = rcpu;
+		local_lock_init(&bq->bq_lock);
 	}
 
 	/* Alloc queue */
@@ -722,6 +725,8 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 	struct ptr_ring *q;
 	int i;
 
+	lockdep_assert_held(&bq->bq_lock);
+
 	if (unlikely(!bq->count))
 		return;
 
@@ -749,11 +754,15 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 }
 
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+ * Thus, safe percpu variable access. PREEMPT_RT relies on
+ * local_lock_nested_bh() to serialise access to the per-CPU bq.
  */
 static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 {
-	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+	struct xdp_bulk_queue *bq;
+
+	local_lock_nested_bh(&rcpu->bulkq->bq_lock);
+	bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
 		bq_flush_to_queue(bq);
@@ -774,6 +783,8 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 
 		list_add(&bq->flush_node, flush_list);
 	}
+
+	local_unlock_nested_bh(&rcpu->bulkq->bq_lock);
 }
 
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
@@ -810,7 +821,9 @@ void __cpu_map_flush(struct list_head *flush_list)
 	struct xdp_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
+		local_lock_nested_bh(&bq->obj->bulkq->bq_lock);
 		bq_flush_to_queue(bq);
+		local_unlock_nested_bh(&bq->obj->bulkq->bq_lock);
 
 		/* If already running, costs spin_lock_irqsave + smb_mb */
 		wake_up_process(bq->obj->kthread);
-- 
cgit v1.2.3


From 1872e75375c40add4a35990de3be77b5741c252c Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:14:56 +0800
Subject: bpf: Fix race in devmap on PREEMPT_RT

On PREEMPT_RT kernels, the per-CPU xdp_dev_bulk_queue (bq) can be
accessed concurrently by multiple preemptible tasks on the same CPU.

The original code assumes bq_enqueue() and __dev_flush() run atomically
with respect to each other on the same CPU, relying on
local_bh_disable() to prevent preemption. However, on PREEMPT_RT,
local_bh_disable() only calls migrate_disable() (when
PREEMPT_RT_NEEDS_BH_LOCK is not set) and does not disable
preemption, which allows CFS scheduling to preempt a task during
bq_xmit_all(), enabling another task on the same CPU to enter
bq_enqueue() and operate on the same per-CPU bq concurrently.

This leads to several races:

1. Double-free / use-after-free on bq->q[]: bq_xmit_all() snapshots
   cnt = bq->count, then iterates bq->q[0..cnt-1] to transmit frames.
   If preempted after the snapshot, a second task can call bq_enqueue()
   -> bq_xmit_all() on the same bq, transmitting (and freeing) the
   same frames. When the first task resumes, it operates on stale
   pointers in bq->q[], causing use-after-free.

2. bq->count and bq->q[] corruption: concurrent bq_enqueue() modifying
   bq->count and bq->q[] while bq_xmit_all() is reading them.

3. dev_rx/xdp_prog teardown race: __dev_flush() clears bq->dev_rx and
   bq->xdp_prog after bq_xmit_all(). If preempted between
   bq_xmit_all() return and bq->dev_rx = NULL, a preempting
   bq_enqueue() sees dev_rx still set (non-NULL), skips adding bq to
   the flush_list, and enqueues a frame. When __dev_flush() resumes,
   it clears dev_rx and removes bq from the flush_list, orphaning the
   newly enqueued frame.

4. __list_del_clearprev() on flush_node: similar to the cpumap race,
   both tasks can call __list_del_clearprev() on the same flush_node,
   the second dereferences the prev pointer already set to NULL.

The race between task A (__dev_flush -> bq_xmit_all) and task B
(bq_enqueue -> bq_xmit_all) on the same CPU:

  Task A (xdp_do_flush)          Task B (ndo_xdp_xmit redirect)
  ----------------------         --------------------------------
  __dev_flush(flush_list)
    bq_xmit_all(bq)
      cnt = bq->count  /* e.g. 16 */
      /* start iterating bq->q[] */
    <-- CFS preempts Task A -->
                                   bq_enqueue(dev, xdpf)
                                     bq->count == DEV_MAP_BULK_SIZE
                                     bq_xmit_all(bq, 0)
                                       cnt = bq->count  /* same 16! */
                                       ndo_xdp_xmit(bq->q[])
                                       /* frames freed by driver */
                                       bq->count = 0
    <-- Task A resumes -->
      ndo_xdp_xmit(bq->q[])
      /* use-after-free: frames already freed! */

Fix this by adding a local_lock_t to xdp_dev_bulk_queue and acquiring
it in bq_enqueue() and __dev_flush(). These paths already run under
local_bh_disable(), so use local_lock_nested_bh() which on non-RT is
a pure annotation with no overhead, and on PREEMPT_RT provides a
per-CPU sleeping lock that serializes access to the bq.

Fixes: 3253cb49cbad ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://lore.kernel.org/r/20260225121459.183121-3-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/devmap.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2984e938f94d..3d619d01088e 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -45,6 +45,7 @@
  * types of devmap; only the lookup and insertion is different.
  */
 #include <linux/bpf.h>
+#include <linux/local_lock.h>
 #include <net/xdp.h>
 #include <linux/filter.h>
 #include <trace/events/xdp.h>
@@ -60,6 +61,7 @@ struct xdp_dev_bulk_queue {
 	struct net_device *dev_rx;
 	struct bpf_prog *xdp_prog;
 	unsigned int count;
+	local_lock_t bq_lock;
 };
 
 struct bpf_dtab_netdev {
@@ -381,6 +383,8 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 	int to_send = cnt;
 	int i;
 
+	lockdep_assert_held(&bq->bq_lock);
+
 	if (unlikely(!cnt))
 		return;
 
@@ -425,10 +429,12 @@ void __dev_flush(struct list_head *flush_list)
 	struct xdp_dev_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
+		local_lock_nested_bh(&bq->dev->xdp_bulkq->bq_lock);
 		bq_xmit_all(bq, XDP_XMIT_FLUSH);
 		bq->dev_rx = NULL;
 		bq->xdp_prog = NULL;
 		__list_del_clearprev(&bq->flush_node);
+		local_unlock_nested_bh(&bq->dev->xdp_bulkq->bq_lock);
 	}
 }
 
@@ -451,12 +457,16 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 
 /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
  * variable access, and map elements stick around. See comment above
- * xdp_do_flush() in filter.c.
+ * xdp_do_flush() in filter.c. PREEMPT_RT relies on local_lock_nested_bh()
+ * to serialise access to the per-CPU bq.
  */
 static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)
 {
-	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
+	struct xdp_dev_bulk_queue *bq;
+
+	local_lock_nested_bh(&dev->xdp_bulkq->bq_lock);
+	bq = this_cpu_ptr(dev->xdp_bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
 		bq_xmit_all(bq, 0);
@@ -477,6 +487,8 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 	}
 
 	bq->q[bq->count++] = xdpf;
+
+	local_unlock_nested_bh(&dev->xdp_bulkq->bq_lock);
 }
 
 static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
@@ -1127,8 +1139,13 @@ static int dev_map_notification(struct notifier_block *notifier,
 		if (!netdev->xdp_bulkq)
 			return NOTIFY_BAD;
 
-		for_each_possible_cpu(cpu)
-			per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
+		for_each_possible_cpu(cpu) {
+			struct xdp_dev_bulk_queue *bq;
+
+			bq = per_cpu_ptr(netdev->xdp_bulkq, cpu);
+			bq->dev = netdev;
+			local_lock_init(&bq->bq_lock);
+		}
 		break;
 	case NETDEV_UNREGISTER:
 		/* This rcu_read_lock/unlock pair is needed because
-- 
cgit v1.2.3


From 62413a9c3cb183afb9bb6e94dd68caf4e4145f4c Mon Sep 17 00:00:00 2001
From: Paul Moses <p@1g4.org>
Date: Mon, 23 Feb 2026 15:05:44 +0000
Subject: net/sched: act_gate: snapshot parameters with RCU on replace

The gate action can be replaced while the hrtimer callback or dump path is
walking the schedule list.

Convert the parameters to an RCU-protected snapshot and swap updates under
tcf_lock, freeing the previous snapshot via call_rcu(). When REPLACE omits
the entry list, preserve the existing schedule so the effective state is
unchanged.

Fixes: a51c328df310 ("net: qos: introduce a gate control flow action")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moses <p@1g4.org>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260223150512.2251594-2-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tc_act/tc_gate.h |  33 ++++--
 net/sched/act_gate.c         | 265 ++++++++++++++++++++++++++++++-------------
 2 files changed, 212 insertions(+), 86 deletions(-)

diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h
index b147a3bb1a46..e0fded18e18c 100644
--- a/include/net/tc_act/tc_gate.h
+++ b/include/net/tc_act/tc_gate.h
@@ -32,6 +32,7 @@ struct tcf_gate_params {
 	s32			tcfg_clockid;
 	size_t			num_entries;
 	struct list_head	entries;
+	struct rcu_head		rcu;
 };
 
 #define GATE_ACT_GATE_OPEN	BIT(0)
@@ -39,7 +40,7 @@ struct tcf_gate_params {
 
 struct tcf_gate {
 	struct tc_action	common;
-	struct tcf_gate_params	param;
+	struct tcf_gate_params __rcu *param;
 	u8			current_gate_status;
 	ktime_t			current_close_time;
 	u32			current_entry_octets;
@@ -51,47 +52,65 @@ struct tcf_gate {
 
 #define to_gate(a) ((struct tcf_gate *)a)
 
+static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a)
+{
+	struct tcf_gate *gact = to_gate(a);
+
+	return rcu_dereference_protected(gact->param,
+					 lockdep_is_held(&gact->tcf_lock));
+}
+
 static inline s32 tcf_gate_prio(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	s32 tcfg_prio;
 
-	tcfg_prio = to_gate(a)->param.tcfg_priority;
+	p = tcf_gate_params_locked(a);
+	tcfg_prio = p->tcfg_priority;
 
 	return tcfg_prio;
 }
 
 static inline u64 tcf_gate_basetime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_basetime;
 
-	tcfg_basetime = to_gate(a)->param.tcfg_basetime;
+	p = tcf_gate_params_locked(a);
+	tcfg_basetime = p->tcfg_basetime;
 
 	return tcfg_basetime;
 }
 
 static inline u64 tcf_gate_cycletime(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletime;
 
-	tcfg_cycletime = to_gate(a)->param.tcfg_cycletime;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletime = p->tcfg_cycletime;
 
 	return tcfg_cycletime;
 }
 
 static inline u64 tcf_gate_cycletimeext(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u64 tcfg_cycletimeext;
 
-	tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext;
+	p = tcf_gate_params_locked(a);
+	tcfg_cycletimeext = p->tcfg_cycletime_ext;
 
 	return tcfg_cycletimeext;
 }
 
 static inline u32 tcf_gate_num_entries(const struct tc_action *a)
 {
+	struct tcf_gate_params *p;
 	u32 num_entries;
 
-	num_entries = to_gate(a)->param.num_entries;
+	p = tcf_gate_params_locked(a);
+	num_entries = p->num_entries;
 
 	return num_entries;
 }
@@ -105,7 +124,7 @@ static inline struct action_gate_entry
 	u32 num_entries;
 	int i = 0;
 
-	p = &to_gate(a)->param;
+	p = tcf_gate_params_locked(a);
 	num_entries = p->num_entries;
 
 	list_for_each_entry(entry, &p->entries, list)
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 686eaed81b81..fdbfcaa3e2ab 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact)
 	return KTIME_MAX;
 }
 
-static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
+static void tcf_gate_params_free_rcu(struct rcu_head *head);
+
+static void gate_get_start_time(struct tcf_gate *gact,
+				const struct tcf_gate_params *param,
+				ktime_t *start)
 {
-	struct tcf_gate_params *param = &gact->param;
 	ktime_t now, base, cycle;
 	u64 n;
 
@@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer)
 {
 	struct tcf_gate *gact = container_of(timer, struct tcf_gate,
 					     hitimer);
-	struct tcf_gate_params *p = &gact->param;
 	struct tcfg_gate_entry *next;
+	struct tcf_gate_params *p;
 	ktime_t close_time, now;
 
 	spin_lock(&gact->tcf_lock);
 
+	p = rcu_dereference_protected(gact->param,
+				      lockdep_is_held(&gact->tcf_lock));
 	next = gact->next_entry;
 
 	/* cycle start, clear pending bit, clear total octets */
@@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries)
 	}
 }
 
+static int tcf_gate_copy_entries(struct tcf_gate_params *dst,
+				 const struct tcf_gate_params *src,
+				 struct netlink_ext_ack *extack)
+{
+	struct tcfg_gate_entry *entry;
+	int i = 0;
+
+	list_for_each_entry(entry, &src->entries, list) {
+		struct tcfg_gate_entry *new;
+
+		new = kzalloc(sizeof(*new), GFP_ATOMIC);
+		if (!new) {
+			NL_SET_ERR_MSG(extack, "Not enough memory for entry");
+			return -ENOMEM;
+		}
+
+		new->index      = entry->index;
+		new->gate_state = entry->gate_state;
+		new->interval   = entry->interval;
+		new->ipv        = entry->ipv;
+		new->maxoctets  = entry->maxoctets;
+		list_add_tail(&new->list, &dst->entries);
+		i++;
+	}
+
+	dst->num_entries = i;
+	return 0;
+}
+
 static int parse_gate_list(struct nlattr *list_attr,
 			   struct tcf_gate_params *sched,
 			   struct netlink_ext_ack *extack)
@@ -270,24 +304,44 @@ release_list:
 	return err;
 }
 
-static void gate_setup_timer(struct tcf_gate *gact, u64 basetime,
-			     enum tk_offsets tko, s32 clockid,
-			     bool do_init)
+static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime,
+				    enum tk_offsets tko,
+				    enum tk_offsets old_tko,
+				    s32 clockid, s32 old_clockid)
 {
-	if (!do_init) {
-		if (basetime == gact->param.tcfg_basetime &&
-		    tko == gact->tk_offset &&
-		    clockid == gact->param.tcfg_clockid)
-			return;
+	return basetime != old_basetime ||
+	       clockid != old_clockid ||
+	       tko != old_tko;
+}
 
-		spin_unlock_bh(&gact->tcf_lock);
-		hrtimer_cancel(&gact->hitimer);
-		spin_lock_bh(&gact->tcf_lock);
+static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko,
+			      struct netlink_ext_ack *extack)
+{
+	switch (clockid) {
+	case CLOCK_REALTIME:
+		*tko = TK_OFFS_REAL;
+		return 0;
+	case CLOCK_MONOTONIC:
+		*tko = TK_OFFS_MAX;
+		return 0;
+	case CLOCK_BOOTTIME:
+		*tko = TK_OFFS_BOOT;
+		return 0;
+	case CLOCK_TAI:
+		*tko = TK_OFFS_TAI;
+		return 0;
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
+		return -EINVAL;
 	}
-	gact->param.tcfg_basetime = basetime;
-	gact->param.tcfg_clockid = clockid;
-	gact->tk_offset = tko;
-	hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT);
+}
+
+static void gate_setup_timer(struct tcf_gate *gact, s32 clockid,
+			     enum tk_offsets tko)
+{
+	WRITE_ONCE(gact->tk_offset, tko);
+	hrtimer_setup(&gact->hitimer, gate_timer_func, clockid,
+		      HRTIMER_MODE_ABS_SOFT);
 }
 
 static int tcf_gate_init(struct net *net, struct nlattr *nla,
@@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id);
-	enum tk_offsets tk_offset = TK_OFFS_TAI;
+	u64 cycletime = 0, basetime = 0, cycletime_ext = 0;
+	struct tcf_gate_params *p = NULL, *old_p = NULL;
+	enum tk_offsets old_tk_offset = TK_OFFS_TAI;
+	const struct tcf_gate_params *cur_p = NULL;
 	bool bind = flags & TCA_ACT_FLAGS_BIND;
 	struct nlattr *tb[TCA_GATE_MAX + 1];
+	enum tk_offsets tko = TK_OFFS_TAI;
 	struct tcf_chain *goto_ch = NULL;
-	u64 cycletime = 0, basetime = 0;
-	struct tcf_gate_params *p;
+	s32 timer_clockid = CLOCK_TAI;
+	bool use_old_entries = false;
+	s32 old_clockid = CLOCK_TAI;
+	bool need_cancel = false;
 	s32 clockid = CLOCK_TAI;
 	struct tcf_gate *gact;
 	struct tc_gate *parm;
+	u64 old_basetime = 0;
 	int ret = 0, err;
 	u32 gflags = 0;
 	s32 prio = -1;
@@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_GATE_PARMS])
 		return -EINVAL;
 
-	if (tb[TCA_GATE_CLOCKID]) {
+	if (tb[TCA_GATE_CLOCKID])
 		clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]);
-		switch (clockid) {
-		case CLOCK_REALTIME:
-			tk_offset = TK_OFFS_REAL;
-			break;
-		case CLOCK_MONOTONIC:
-			tk_offset = TK_OFFS_MAX;
-			break;
-		case CLOCK_BOOTTIME:
-			tk_offset = TK_OFFS_BOOT;
-			break;
-		case CLOCK_TAI:
-			tk_offset = TK_OFFS_TAI;
-			break;
-		default:
-			NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
-			return -EINVAL;
-		}
-	}
 
 	parm = nla_data(tb[TCA_GATE_PARMS]);
 	index = parm->index;
@@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		return -EEXIST;
 	}
 
+	gact = to_gate(*a);
+
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p) {
+		err = -ENOMEM;
+		goto chain_put;
+	}
+	INIT_LIST_HEAD(&p->entries);
+
+	use_old_entries = !tb[TCA_GATE_ENTRY_LIST];
+	if (!use_old_entries) {
+		err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
+		if (err < 0)
+			goto err_free;
+		use_old_entries = !err;
+	}
+
+	if (ret == ACT_P_CREATED && use_old_entries) {
+		NL_SET_ERR_MSG(extack, "The entry list is empty");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	if (ret != ACT_P_CREATED) {
+		rcu_read_lock();
+		cur_p = rcu_dereference(gact->param);
+
+		old_basetime  = cur_p->tcfg_basetime;
+		old_clockid   = cur_p->tcfg_clockid;
+		old_tk_offset = READ_ONCE(gact->tk_offset);
+
+		basetime      = old_basetime;
+		cycletime_ext = cur_p->tcfg_cycletime_ext;
+		prio          = cur_p->tcfg_priority;
+		gflags        = cur_p->tcfg_flags;
+
+		if (!tb[TCA_GATE_CLOCKID])
+			clockid = old_clockid;
+
+		err = 0;
+		if (use_old_entries) {
+			err = tcf_gate_copy_entries(p, cur_p, extack);
+			if (!err && !tb[TCA_GATE_CYCLE_TIME])
+				cycletime = cur_p->tcfg_cycletime;
+		}
+		rcu_read_unlock();
+		if (err)
+			goto err_free;
+	}
+
 	if (tb[TCA_GATE_PRIORITY])
 		prio = nla_get_s32(tb[TCA_GATE_PRIORITY]);
 
@@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GATE_FLAGS])
 		gflags = nla_get_u32(tb[TCA_GATE_FLAGS]);
 
-	gact = to_gate(*a);
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&gact->param.entries);
+	if (tb[TCA_GATE_CYCLE_TIME])
+		cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
 
-	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
-	if (err < 0)
-		goto release_idr;
+	if (tb[TCA_GATE_CYCLE_TIME_EXT])
+		cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
 
-	spin_lock_bh(&gact->tcf_lock);
-	p = &gact->param;
+	err = gate_clock_resolve(clockid, &tko, extack);
+	if (err)
+		goto err_free;
+	timer_clockid = clockid;
 
-	if (tb[TCA_GATE_CYCLE_TIME])
-		cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
+	need_cancel = ret != ACT_P_CREATED &&
+		      gate_timer_needs_cancel(basetime, old_basetime,
+					      tko, old_tk_offset,
+					      timer_clockid, old_clockid);
 
-	if (tb[TCA_GATE_ENTRY_LIST]) {
-		err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
-		if (err < 0)
-			goto chain_put;
-	}
+	if (need_cancel)
+		hrtimer_cancel(&gact->hitimer);
+
+	spin_lock_bh(&gact->tcf_lock);
 
 	if (!cycletime) {
 		struct tcfg_gate_entry *entry;
@@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		list_for_each_entry(entry, &p->entries, list)
 			cycle = ktime_add_ns(cycle, entry->interval);
 		cycletime = cycle;
-		if (!cycletime) {
-			err = -EINVAL;
-			goto chain_put;
-		}
 	}
 	p->tcfg_cycletime = cycletime;
+	p->tcfg_cycletime_ext = cycletime_ext;
 
-	if (tb[TCA_GATE_CYCLE_TIME_EXT])
-		p->tcfg_cycletime_ext =
-			nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
-
-	gate_setup_timer(gact, basetime, tk_offset, clockid,
-			 ret == ACT_P_CREATED);
+	if (need_cancel || ret == ACT_P_CREATED)
+		gate_setup_timer(gact, timer_clockid, tko);
 	p->tcfg_priority = prio;
 	p->tcfg_flags = gflags;
-	gate_get_start_time(gact, &start);
+	p->tcfg_basetime = basetime;
+	p->tcfg_clockid = timer_clockid;
+	gate_get_start_time(gact, p, &start);
+
+	old_p = rcu_replace_pointer(gact->param, p,
+				    lockdep_is_held(&gact->tcf_lock));
 
 	gact->current_close_time = start;
 	gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING;
@@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 
+	if (old_p)
+		call_rcu(&old_p->rcu, tcf_gate_params_free_rcu);
+
 	return ret;
 
+err_free:
+	release_entry_list(&p->entries);
+	kfree(p);
 chain_put:
-	spin_unlock_bh(&gact->tcf_lock);
-
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 release_idr:
@@ -446,21 +546,29 @@ release_idr:
 	 * without taking tcf_lock.
 	 */
 	if (ret == ACT_P_CREATED)
-		gate_setup_timer(gact, gact->param.tcfg_basetime,
-				 gact->tk_offset, gact->param.tcfg_clockid,
-				 true);
+		gate_setup_timer(gact, timer_clockid, tko);
+
 	tcf_idr_release(*a, bind);
 	return err;
 }
 
+static void tcf_gate_params_free_rcu(struct rcu_head *head)
+{
+	struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu);
+
+	release_entry_list(&p->entries);
+	kfree(p);
+}
+
 static void tcf_gate_cleanup(struct tc_action *a)
 {
 	struct tcf_gate *gact = to_gate(a);
 	struct tcf_gate_params *p;
 
-	p = &gact->param;
 	hrtimer_cancel(&gact->hitimer);
-	release_entry_list(&p->entries);
+	p = rcu_dereference_protected(gact->param, 1);
+	if (p)
+		call_rcu(&p->rcu, tcf_gate_params_free_rcu);
 }
 
 static int dumping_entry(struct sk_buff *skb,
@@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a,
 	struct nlattr *entry_list;
 	struct tcf_t t;
 
-	spin_lock_bh(&gact->tcf_lock);
-	opt.action = gact->tcf_action;
-
-	p = &gact->param;
+	rcu_read_lock();
+	opt.action = READ_ONCE(gact->tcf_action);
+	p = rcu_dereference(gact->param);
 
 	if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
@@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &gact->tcf_tm);
 	if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD))
 		goto nla_put_failure;
-	spin_unlock_bh(&gact->tcf_lock);
+	rcu_read_unlock();
 
 	return skb->len;
 
 nla_put_failure:
-	spin_unlock_bh(&gact->tcf_lock);
+	rcu_read_unlock();
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 76e954155b45294c502e3d3a9e15757c858ca55e Mon Sep 17 00:00:00 2001
From: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Date: Fri, 27 Feb 2026 22:32:21 +0100
Subject: bpf: Introduce tnum_step to step through tnum's members

This commit introduces tnum_step(), a function that, when given t, and a
number z returns the smallest member of t larger than z. The number z
must be greater or equal to the smallest member of t and less than the
largest member of t.

The first step is to compute j, a number that keeps all of t's known
bits, and matches all unknown bits to z's bits. Since j is a member of
the t, it is already a candidate for result. However, we want our result
to be (minimally) greater than z.

There are only two possible cases:

(1) Case j <= z. In this case, we want to increase the value of j and
make it > z.
(2) Case j > z. In this case, we want to decrease the value of j while
keeping it > z.

(Case 1) j <= z

t = xx11x0x0
z = 10111101 (189)
j = 10111000 (184)
         ^
         k

(Case 1.1) Let's first consider the case where j < z. We will address j
== z later.

Since z > j, there had to be a bit position that was 1 in z and a 0 in
j, beyond which all positions of higher significance are equal in j and
z. Further, this position could not have been unknown in a, because the
unknown positions of a match z. This position had to be a 1 in z and
known 0 in t.

Let k be position of the most significant 1-to-0 flip. In our example, k
= 3 (starting the count at 1 at the least significant bit).  Setting (to
1) the unknown bits of t in positions of significance smaller than
k will not produce a result > z. Hence, we must set/unset the unknown
bits at positions of significance higher than k. Specifically, we look
for the next larger combination of 1s and 0s to place in those
positions, relative to the combination that exists in z. We can achieve
this by concatenating bits at unknown positions of t into an integer,
adding 1, and writing the bits of that result back into the
corresponding bit positions previously extracted from z.

>From our example, considering only positions of significance greater
than k:

t =  xx..x
z =  10..1
    +    1
     -----
     11..0

This is the exact combination 1s and 0s we need at the unknown bits of t
in positions of significance greater than k. Further, our result must
only increase the value minimally above z. Hence, unknown bits in
positions of significance smaller than k should remain 0. We finally
have,

result = 11110000 (240)

(Case 1.2) Now consider the case when j = z, for example

t = 1x1x0xxx
z = 10110100 (180)
j = 10110100 (180)

Matching the unknown bits of the t to the bits of z yielded exactly z.
To produce a number greater than z, we must set/unset the unknown bits
in t, and *all* the unknown bits of t candidates for being set/unset. We
can do this similar to Case 1.1, by adding 1 to the bits extracted from
the masked bit positions of z. Essentially, this case is equivalent to
Case 1.1, with k = 0.

t =  1x1x0xxx
z =  .0.1.100
    +       1
    ---------
     .0.1.101

This is the exact combination of bits needed in the unknown positions of
t. After recalling the known positions of t, we get

result = 10110101 (181)

(Case 2) j > z

t = x00010x1
z = 10000010 (130)
j = 10001011 (139)
	^
	k

Since j > z, there had to be a bit position which was 0 in z, and a 1 in
j, beyond which all positions of higher significance are equal in j and
z. This position had to be a 0 in z and known 1 in t. Let k be the
position of the most significant 0-to-1 flip. In our example, k = 4.

Because of the 0-to-1 flip at position k, a member of t can become
greater than z if the bits in positions greater than k are themselves >=
to z. To make that member *minimally* greater than z, the bits in
positions greater than k must be exactly = z. Hence, we simply match all
of t's unknown bits in positions more significant than k to z's bits. In
positions less significant than k, we set all t's unknown bits to 0
to retain minimality.

In our example, in positions of greater significance than k (=4),
t=x000. These positions are matched with z (1000) to produce 1000. In
positions of lower significance than k, t=10x1. All unknown bits are set
to 0 to produce 1001. The final result is:

result = 10001001 (137)

This concludes the computation for a result > z that is a member of t.

The procedure for tnum_step() in this commit implements the idea
described above. As a proof of correctness, we verified the algorithm
against a logical specification of tnum_step. The specification asserts
the following about the inputs t, z and output res that:

1. res is a member of t, and
2. res is strictly greater than z, and
3. there does not exist another value res2 such that
	3a. res2 is also a member of t, and
	3b. res2 is greater than z
	3c. res2 is smaller than res

We checked the implementation against this logical specification using
an SMT solver. The verification formula in SMTLIB format is available
at [1]. The verification returned an "unsat": indicating that no input
assignment exists for which the implementation and the specification
produce different outputs.

In addition, we also automatically generated the logical encoding of the
C implementation using Agni [2] and verified it against the same
specification. This verification also returned an "unsat", confirming
that the implementation is equivalent to the specification. The formula
for this check is also available at [3].

Link: https://pastebin.com/raw/2eRWbiit [1]
Link: https://github.com/bpfverif/agni [2]
Link: https://pastebin.com/raw/EztVbBJ2 [3]
Co-developed-by: Srinivas Narayana <srinivas.narayana@rutgers.edu>
Signed-off-by: Srinivas Narayana <srinivas.narayana@rutgers.edu>
Co-developed-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu>
Signed-off-by: Santosh Nagarakatte <santosh.nagarakatte@rutgers.edu>
Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Link: https://lore.kernel.org/r/93fdf71910411c0f19e282ba6d03b4c65f9c5d73.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/tnum.h |  3 +++
 kernel/bpf/tnum.c    | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index fa4654ffb621..ca2cfec8de08 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a)
 	return !(tnum_subreg(a)).mask;
 }
 
+/* Returns the smallest member of t larger than z */
+u64 tnum_step(struct tnum t, u64 z);
+
 #endif /* _LINUX_TNUM_H */
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 26fbfbb01700..4abc359b3db0 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -269,3 +269,59 @@ struct tnum tnum_bswap64(struct tnum a)
 {
 	return TNUM(swab64(a.value), swab64(a.mask));
 }
+
+/* Given tnum t, and a number z such that tmin <= z < tmax, where tmin
+ * is the smallest member of the t (= t.value) and tmax is the largest
+ * member of t (= t.value | t.mask), returns the smallest member of t
+ * larger than z.
+ *
+ * For example,
+ * t      = x11100x0
+ * z      = 11110001 (241)
+ * result = 11110010 (242)
+ *
+ * Note: if this function is called with z >= tmax, it just returns
+ * early with tmax; if this function is called with z < tmin, the
+ * algorithm already returns tmin.
+ */
+u64 tnum_step(struct tnum t, u64 z)
+{
+	u64 tmax, j, p, q, r, s, v, u, w, res;
+	u8 k;
+
+	tmax = t.value | t.mask;
+
+	/* if z >= largest member of t, return largest member of t */
+	if (z >= tmax)
+		return tmax;
+
+	/* if z < smallest member of t, return smallest member of t */
+	if (z < t.value)
+		return t.value;
+
+	/* keep t's known bits, and match all unknown bits to z */
+	j = t.value | (z & t.mask);
+
+	if (j > z) {
+		p = ~z & t.value & ~t.mask;
+		k = fls64(p); /* k is the most-significant 0-to-1 flip */
+		q = U64_MAX << k;
+		r = q & z; /* positions > k matched to z */
+		s = ~q & t.value; /* positions <= k matched to t.value */
+		v = r | s;
+		res = v;
+	} else {
+		p = z & ~t.value & ~t.mask;
+		k = fls64(p); /* k is the most-significant 1-to-0 flip */
+		q = U64_MAX << k;
+		r = q & t.mask & z; /* unknown positions > k, matched to z */
+		s = q & ~t.mask; /* known positions > k, set to 1 */
+		v = r | s;
+		/* add 1 to unknown positions > k to make value greater than z */
+		u = v + (1ULL << k);
+		/* extract bits in unknown positions > k from u, rest from t.value */
+		w = (u & t.mask) | t.value;
+		res = w;
+	}
+	return res;
+}
-- 
cgit v1.2.3


From efc11a667878a1d655ff034a93a539debbfedb12 Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:35:02 +0100
Subject: bpf: Improve bounds when tnum has a single possible value

We're hitting an invariant violation in Cilium that sometimes leads to
BPF programs being rejected and Cilium failing to start [1]. The
following extract from verifier logs shows what's happening:

  from 201 to 236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0
  236: R1=0 R6=ctx() R7=1 R9=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100)) R10=fp0
  ; if (magic == MARK_MAGIC_HOST || magic == MARK_MAGIC_OVERLAY || magic == MARK_MAGIC_ENCRYPT) @ bpf_host.c:1337
  236: (16) if w9 == 0xe00 goto pc+45   ; R9=scalar(smin=umin=smin32=umin32=3585,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100))
  237: (16) if w9 == 0xf00 goto pc+1
  verifier bug: REG INVARIANTS VIOLATION (false_reg1): range bounds violation u64=[0xe01, 0xe00] s64=[0xe01, 0xe00] u32=[0xe01, 0xe00] s32=[0xe01, 0xe00] var_off=(0xe00, 0x0)

We reach instruction 236 with two possible values for R9, 0xe00 and
0xf00. This is perfectly reflected in the tnum, but of course the ranges
are less accurate and cover [0xe00; 0xf00]. Taking the fallthrough path
at instruction 236 allows the verifier to reduce the range to
[0xe01; 0xf00]. The tnum is however not updated.

With these ranges, at instruction 237, the verifier is not able to
deduce that R9 is always equal to 0xf00. Hence the fallthrough pass is
explored first, the verifier refines the bounds using the assumption
that R9 != 0xf00, and ends up with an invariant violation.

This pattern of impossible branch + bounds refinement is common to all
invariant violations seen so far. The long-term solution is likely to
rely on the refinement + invariant violation check to detect dead
branches, as started by Eduard. To fix the current issue, we need
something with less refactoring that we can backport.

This patch uses the tnum_step helper introduced in the previous patch to
detect the above situation. In particular, three cases are now detected
in the bounds refinement:

1. The u64 range and the tnum only overlap in umin.
   u64:  ---[xxxxxx]-----
   tnum: --xx----------x-

2. The u64 range and the tnum only overlap in the maximum value
   represented by the tnum, called tmax.
   u64:  ---[xxxxxx]-----
   tnum: xx-----x--------

3. The u64 range and the tnum only overlap in between umin (excluded)
   and umax.
   u64:  ---[xxxxxx]-----
   tnum: xx----x-------x-

To detect these three cases, we call tnum_step(tnum, umin), which
returns the smallest member of the tnum greater than umin, called
tnum_next here. We're in case (1) if umin is part of the tnum and
tnum_next is greater than umax. We're in case (2) if umin is not part of
the tnum and tnum_next is equal to tmax. Finally, we're in case (3) if
umin is not part of the tnum, tnum_next is inferior or equal to umax,
and calling tnum_step a second time gives us a value past umax.

This change implements these three cases. With it, the above bytecode
looks as follows:

  0: (85) call bpf_get_prandom_u32#7    ; R0=scalar()
  1: (47) r0 |= 3584                    ; R0=scalar(smin=0x8000000000000e00,umin=umin32=3584,smin32=0x80000e00,var_off=(0xe00; 0xfffffffffffff1ff))
  2: (57) r0 &= 3840                    ; R0=scalar(smin=umin=smin32=umin32=3584,smax=umax=smax32=umax32=3840,var_off=(0xe00; 0x100))
  3: (15) if r0 == 0xe00 goto pc+2      ; R0=3840
  4: (15) if r0 == 0xf00 goto pc+1
  4: R0=3840
  6: (95) exit

In addition to the new selftests, this change was also verified with
Agni [3]. For the record, the raw SMT is available at [4]. The property
it verifies is that: If a concrete value x is contained in all input
abstract values, after __update_reg_bounds, it will continue to be
contained in all output abstract values.

Link: https://github.com/cilium/cilium/issues/44216 [1]
Link: https://pchaigno.github.io/test-verifier-complexity.html [2]
Link: https://github.com/bpfverif/agni [3]
Link: https://pastebin.com/raw/naCfaqNx [4]
Fixes: 0df1a55afa83 ("bpf: Warn on internal verifier errors")
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Tested-by: Marco Schirrmeister <mschirrmeister@gmail.com>
Co-developed-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Signed-off-by: Harishankar Vishwanathan <harishankar.vishwanathan@gmail.com>
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/ef254c4f68be19bd393d450188946821c588565d.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb12ba020649..401d6c4960ec 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2379,6 +2379,9 @@ static void __update_reg32_bounds(struct bpf_reg_state *reg)
 
 static void __update_reg64_bounds(struct bpf_reg_state *reg)
 {
+	u64 tnum_next, tmax;
+	bool umin_in_tnum;
+
 	/* min signed is max(sign bit) | min(other bits) */
 	reg->smin_value = max_t(s64, reg->smin_value,
 				reg->var_off.value | (reg->var_off.mask & S64_MIN));
@@ -2388,6 +2391,33 @@ static void __update_reg64_bounds(struct bpf_reg_state *reg)
 	reg->umin_value = max(reg->umin_value, reg->var_off.value);
 	reg->umax_value = min(reg->umax_value,
 			      reg->var_off.value | reg->var_off.mask);
+
+	/* Check if u64 and tnum overlap in a single value */
+	tnum_next = tnum_step(reg->var_off, reg->umin_value);
+	umin_in_tnum = (reg->umin_value & ~reg->var_off.mask) == reg->var_off.value;
+	tmax = reg->var_off.value | reg->var_off.mask;
+	if (umin_in_tnum && tnum_next > reg->umax_value) {
+		/* The u64 range and the tnum only overlap in umin.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: --xx----------x-
+		 */
+		___mark_reg_known(reg, reg->umin_value);
+	} else if (!umin_in_tnum && tnum_next == tmax) {
+		/* The u64 range and the tnum only overlap in the maximum value
+		 * represented by the tnum, called tmax.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: xx-----x--------
+		 */
+		___mark_reg_known(reg, tmax);
+	} else if (!umin_in_tnum && tnum_next <= reg->umax_value &&
+		   tnum_step(reg->var_off, tnum_next) > reg->umax_value) {
+		/* The u64 range and the tnum only overlap in between umin
+		 * (excluded) and umax.
+		 * u64:  ---[xxxxxx]-----
+		 * tnum: xx----x-------x-
+		 */
+		___mark_reg_known(reg, tnum_next);
+	}
 }
 
 static void __update_reg_bounds(struct bpf_reg_state *reg)
-- 
cgit v1.2.3


From e6ad477d1bf8829973cddd9accbafa9d1a6cd15a Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:36:30 +0100
Subject: selftests/bpf: Test refinement of single-value tnum

This patch introduces selftests to cover the new bounds refinement
logic introduced in the previous patch. Without the previous patch,
the first two tests fail because of the invariant violation they
trigger. The last test fails because the R10 access is not detected as
dead code. In addition, all three tests fail because of R0 having a
non-constant value in the verifier logs.

In addition, the last two cases are covering the negative cases: when we
shouldn't refine the bounds because the u64 and tnum overlap in at least
two values.

Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/90d880c8cf587b9f7dc715d8961cd1b8111d01a8.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/progs/verifier_bounds.c  | 137 +++++++++++++++++++++
 1 file changed, 137 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 560531404bce..97065a26cf70 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1863,4 +1863,141 @@ l1_%=:	r0 = 1;				\
 	: __clobber_all);
 }
 
+/* This test covers the bounds deduction when the u64 range and the tnum
+ * overlap only at umax. After instruction 3, the ranges look as follows:
+ *
+ * 0    umin=0xe01     umax=0xf00                              U64_MAX
+ * |    [xxxxxxxxxxxxxx]                                       |
+ * |----------------------------|------------------------------|
+ * |   x               x                                       | tnum values
+ *
+ * The verifier can therefore deduce that the R0=0xf0=240.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum on umax")
+__msg("3: (15) if r0 == 0xe0 {{.*}} R0=240")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void bounds_refinement_tnum_umax(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 |= 0xe0;			\
+	r0 &= 0xf0;			\
+	if r0 == 0xe0 goto +2;		\
+	if r0 == 0xf0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction when the u64 range and the tnum
+ * overlap only at umin. After instruction 3, the ranges look as follows:
+ *
+ * 0    umin=0xe00     umax=0xeff                              U64_MAX
+ * |    [xxxxxxxxxxxxxx]                                       |
+ * |----------------------------|------------------------------|
+ * |    x               x                                      | tnum values
+ *
+ * The verifier can therefore deduce that the R0=0xe0=224.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum on umin")
+__msg("3: (15) if r0 == 0xf0 {{.*}} R0=224")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void bounds_refinement_tnum_umin(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 |= 0xe0;			\
+	r0 &= 0xf0;			\
+	if r0 == 0xf0 goto +2;		\
+	if r0 == 0xe0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction when the only possible tnum value is
+ * in the middle of the u64 range. After instruction 3, the ranges look as
+ * follows:
+ *
+ * 0    umin=0x7cf   umax=0x7df                                U64_MAX
+ * |    [xxxxxxxxxxxx]                                         |
+ * |----------------------------|------------------------------|
+ * |     x            x            x            x            x | tnum values
+ *       |            +--- 0x7e0
+ *       +--- 0x7d0
+ *
+ * Since the lower four bits are zero, the tnum and the u64 range only overlap
+ * in R0=0x7d0=2000. Instruction 5 is therefore dead code.
+ */
+SEC("socket")
+__description("bounds refinement with single-value tnum in middle of range")
+__msg("3: (a5) if r0 < 0x7cf {{.*}} R0=2000")
+__success __log_level(2)
+__naked void bounds_refinement_tnum_middle(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 & 0x0f goto +4;		\
+	if r0 > 0x7df goto +3;		\
+	if r0 < 0x7cf goto +2;		\
+	if r0 == 0x7d0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test cover the negative case for the tnum/u64 overlap. Since
+ * they contain the same two values (i.e., {0, 1}), we can't deduce
+ * anything more.
+ */
+SEC("socket")
+__description("bounds refinement: several overlaps between tnum and u64")
+__msg("2: (25) if r0 > 0x1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=1,var_off=(0x0; 0x1))")
+__failure __log_level(2)
+__naked void bounds_refinement_several_overlaps(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 < 0 goto +3;		\
+	if r0 > 1 goto +2;		\
+	if r0 == 1 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test cover the negative case for the tnum/u64 overlap. Since
+ * they overlap in the two values contained by the u64 range (i.e.,
+ * {0xf, 0x10}), we can't deduce anything more.
+ */
+SEC("socket")
+__description("bounds refinement: multiple overlaps between tnum and u64")
+__msg("2: (25) if r0 > 0x10 {{.*}} R0=scalar(smin=umin=smin32=umin32=15,smax=umax=smax32=umax32=16,var_off=(0x0; 0x1f))")
+__failure __log_level(2)
+__naked void bounds_refinement_multiple_overlaps(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	if r0 < 0xf goto +3;		\
+	if r0 > 0x10 goto +2;		\
+	if r0 == 0x10 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 024cea2d647ed8ab942f19544b892d324dba42b4 Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Fri, 27 Feb 2026 22:42:45 +0100
Subject: selftests/bpf: Avoid simplification of crafted bounds test

The reg_bounds_crafted tests validate the verifier's range analysis
logic. They focus on the actual ranges and thus ignore the tnum. As a
consequence, they carry the assumption that the tested cases can be
reproduced in userspace without using the tnum information.

Unfortunately, the previous change the refinement logic breaks that
assumption for one test case:

  (u64)2147483648 (u32)<op> [4294967294; 0x100000000]

The tested bytecode is shown below. Without our previous improvement, on
the false branch of the condition, R7 is only known to have u64 range
[0xfffffffe; 0x100000000]. With our improvement, and using the tnum
information, we can deduce that R7 equals 0x100000000.

  19: (bc) w0 = w6                ; R6=0x80000000
  20: (bc) w0 = w7                ; R7=scalar(smin=umin=0xfffffffe,smax=umax=0x100000000,smin32=-2,smax32=0,var_off=(0x0; 0x1ffffffff))
  21: (be) if w6 <= w7 goto pc+3  ; R6=0x80000000 R7=0x100000000

R7's tnum is (0; 0x1ffffffff). On the false branch, regs_refine_cond_op
refines R7's u32 range to [0; 0x7fffffff]. Then, __reg32_deduce_bounds
refines the s32 range to 0 using u32 and finally also sets u32=0.
From this, __reg_bound_offset improves the tnum to (0; 0x100000000).
Finally, our previous patch uses this new tnum to deduce that it only
intersect with u64=[0xfffffffe; 0x100000000] in a single value:
0x100000000.

Because the verifier uses the tnum to reach this constant value, the
selftest is unable to reproduce it by only simulating ranges. The
solution implemented in this patch is to change the test case such that
there is more than one overlap value between u64 and the tnum. The max.
u64 value is thus changed from 0x100000000 to 0x300000000.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/50641c6a7ef39520595dcafa605692427c1006ec.1772225741.git.paul.chaignon@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/reg_bounds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index d93a0c7b1786..0322f817d07b 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -2091,7 +2091,7 @@ static struct subtest_case crafted_cases[] = {
 	{U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}},
 
 	{U64, U32, {0, 0x100000000}, {0, 0}},
-	{U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}},
+	{U64, U32, {0xfffffffe, 0x300000000}, {0x80000000, 0x80000000}},
 
 	{U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}},
 	/* these are tricky cases where lower 32 bits allow to tighten 64
-- 
cgit v1.2.3


From 29252397bcc1e0a1f85e5c3bee59c325f5c26341 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 25 Feb 2026 20:35:45 +0000
Subject: inet: annotate data-races around isk->inet_num

UDP/TCP lookups are using RCU, thus isk->inet_num accesses
should use READ_ONCE() and WRITE_ONCE() where needed.

Fixes: 3ab5aee7fe84 ("net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260225203545.1512417-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet6_hashtables.h | 2 +-
 include/net/inet_hashtables.h  | 2 +-
 include/net/ip.h               | 2 +-
 net/ipv4/inet_hashtables.c     | 8 ++++----
 net/ipv4/tcp_diag.c            | 2 +-
 net/ipv6/inet6_hashtables.c    | 3 ++-
 6 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 282e29237d93..c16de5b7963f 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk,
 {
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_family != AF_INET6 ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
 	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 		return false;
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ac05a52d9e13..5a979dcab538 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk,
 			      int dif, int sdif)
 {
 	if (!net_eq(sock_net(sk), net) ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    sk->sk_addrpair != cookie)
 	        return false;
 
diff --git a/include/net/ip.h b/include/net/ip.h
index 69d5cef46004..7f9abd457e01 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
-	ipcm->protocol = inet->inet_num;
+	ipcm->protocol = READ_ONCE(inet->inet_num);
 }
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index fca980772c81..9bfccc283fa6 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 		    struct inet_bind2_bucket *tb2, unsigned short port)
 {
-	inet_sk(sk)->inet_num = port;
+	WRITE_ONCE(inet_sk(sk)->inet_num, port);
 	inet_csk(sk)->icsk_bind_hash = tb;
 	inet_csk(sk)->icsk_bind2_hash = tb2;
 	sk_add_bind_node(sk, &tb2->owners);
@@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk)
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
 	inet_csk(sk)->icsk_bind_hash = NULL;
-	inet_sk(sk)->inet_num = 0;
+	WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 	sk->sk_userlocks &= ~SOCK_CONNECT_BIND;
 
 	spin_lock(&head2->lock);
@@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
+	if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum &&
 			!ipv6_only_sock(sk)) {
 		if (sk->sk_rcv_saddr != daddr)
 			return -1;
@@ -1206,7 +1206,7 @@ error:
 
 		sk->sk_hash = 0;
 		inet_sk(sk)->inet_sport = 0;
-		inet_sk(sk)->inet_num = 0;
+		WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 
 		if (tw)
 			inet_twsk_bind_unhash(tw, hinfo);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index d83efd91f461..7935702e394b 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -509,7 +509,7 @@ next_chunk:
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
 				goto next_normal;
-			if (r->id.idiag_sport != htons(sk->sk_num) &&
+			if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) &&
 			    r->id.idiag_sport)
 				goto next_normal;
 			if (r->id.idiag_dport != sk->sk_dport &&
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 5e1da088d8e1..182d38e6d6d8 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
+	if (net_eq(sock_net(sk), net) &&
+	    READ_ONCE(inet_sk(sk)->inet_num) == hnum &&
 	    sk->sk_family == PF_INET6) {
 		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 			return -1;
-- 
cgit v1.2.3


From 0b3cd139be565b85f4a3579e376152b9def6256a Mon Sep 17 00:00:00 2001
From: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Date: Thu, 26 Feb 2026 12:40:15 +0100
Subject: net/sched: sch_cake: avoid sync overhead when unlimited
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Skip inter-instance sync when no rate limit is configured, as it serves
no purpose and only adds overhead.

Fixes: 1bddd758bac2 ("net/sched: sch_cake: share shaper state across sub-instances of cake_mq")
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20260226-cake-mq-skip-sync-bandwidth-unlimited-v1-1-01830bb4db87@tu-berlin.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index a01f14b1c216..b23fc7d9fafe 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch)
 	u64 delay;
 	u32 len;
 
-	if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) {
+	if (q->config->is_shared && q->rate_ns &&
+	    now - q->last_checked_active >= q->config->sync_time) {
 		struct net_device *dev = qdisc_dev(sch);
 		struct cake_sched_data *other_priv;
 		u64 new_rate = q->config->rate_bps;
-- 
cgit v1.2.3


From 15c2715a52645fd8e6e18b7abc3449292d118c7c Mon Sep 17 00:00:00 2001
From: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Date: Thu, 26 Feb 2026 12:40:16 +0100
Subject: net/sched: sch_cake: fixup cake_mq rate adjustment for diffserv
 config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cake_mq's rate adjustment during the sync periods did not adjust the
rates for every tin in a diffserv config. This lead to inconsistencies
of rates between the tins. Fix this by setting the rates for all tins
during synchronization.

Fixes: 1bddd758bac2 ("net/sched: sch_cake: share shaper state across sub-instances of cake_mq")
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20260226-cake-mq-skip-sync-bandwidth-unlimited-v1-2-01830bb4db87@tu-berlin.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 50 +++++++++++++++++++++++---------------------------
 1 file changed, 23 insertions(+), 27 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index b23fc7d9fafe..9efe23f8371b 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = {
 	1239850263, 1191209601, 1147878294, 1108955788
 };
 
-static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
-			  u64 target_ns, u64 rtt_est_ns);
+static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust);
+
 /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
  * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
  *
@@ -2040,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch)
 		if (num_active_qs > 1)
 			new_rate = div64_u64(q->config->rate_bps, num_active_qs);
 
-		/* mtu = 0 is used to only update the rate and not mess with cobalt params */
-		cake_set_rate(b, new_rate, 0, 0, 0);
+		cake_configure_rates(sch, new_rate, true);
 		q->last_checked_active = now;
 		q->active_queues = num_active_qs;
-		q->rate_ns = b->tin_rate_ns;
-		q->rate_shft = b->tin_rate_shft;
 	}
 
 begin:
@@ -2362,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
 	b->cparams.p_dec = 1 << 20; /* 1/4096 */
 }
 
-static int cake_config_besteffort(struct Qdisc *sch)
+static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct cake_tin_data *b = &q->tins[0];
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 
 	q->tin_cnt = 1;
 
@@ -2381,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_precedence(struct Qdisc *sch)
+static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 	/* convert high-level (user visible) parameters into internal format */
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 256;
 	u32 i;
 
@@ -2457,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch)
  *	Total 12 traffic classes.
  */
 
-static int cake_config_diffserv8(struct Qdisc *sch)
+static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*	Pruned list of traffic classes for typical applications:
  *
@@ -2474,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch)
  */
 
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 256;
 	u32 i;
 
@@ -2505,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_diffserv4(struct Qdisc *sch)
+static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*  Further pruned list of traffic classes for four-class system:
  *
@@ -2518,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch)
  */
 
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 1024;
 
 	q->tin_cnt = 4;
@@ -2547,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch)
 	return 0;
 }
 
-static int cake_config_diffserv3(struct Qdisc *sch)
+static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu)
 {
 /*  Simplified Diffserv structure with 3 tins.
  *		Latency Sensitive	(CS7, CS6, EF, VA, TOS4)
@@ -2555,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch)
  *		Low Priority		(LE, CS1)
  */
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 mtu = psched_mtu(qdisc_dev(sch));
-	u64 rate = q->config->rate_bps;
 	u32 quantum = 1024;
 
 	q->tin_cnt = 3;
@@ -2581,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch)
 	return 0;
 }
 
-static void cake_reconfigure(struct Qdisc *sch)
+static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust)
 {
+	u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch));
 	struct cake_sched_data *qd = qdisc_priv(sch);
 	struct cake_sched_config *q = qd->config;
 	int c, ft;
 
 	switch (q->tin_mode) {
 	case CAKE_DIFFSERV_BESTEFFORT:
-		ft = cake_config_besteffort(sch);
+		ft = cake_config_besteffort(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_PRECEDENCE:
-		ft = cake_config_precedence(sch);
+		ft = cake_config_precedence(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV8:
-		ft = cake_config_diffserv8(sch);
+		ft = cake_config_diffserv8(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV4:
-		ft = cake_config_diffserv4(sch);
+		ft = cake_config_diffserv4(sch, rate, mtu);
 		break;
 
 	case CAKE_DIFFSERV_DIFFSERV3:
 	default:
-		ft = cake_config_diffserv3(sch);
+		ft = cake_config_diffserv3(sch, rate, mtu);
 		break;
 	}
 
@@ -2617,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch)
 
 	qd->rate_ns   = qd->tins[ft].tin_rate_ns;
 	qd->rate_shft = qd->tins[ft].tin_rate_shft;
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+	struct cake_sched_data *qd = qdisc_priv(sch);
+	struct cake_sched_config *q = qd->config;
+
+	cake_configure_rates(sch, qd->config->rate_bps, false);
 
 	if (q->buffer_config_limit) {
 		qd->buffer_limit = q->buffer_config_limit;
-- 
cgit v1.2.3


From ba14798653bb815b4dcd116c5265a9f748bc0c7f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 26 Feb 2026 17:19:17 +0100
Subject: selftests: netfilter: nft_queue.sh: avoid flakes on debug kernels

Jakub reports test flakes on debug kernels:
 FAIL: test_udp_gro_ct: Expected software segmentation to occur, had 23 and 17

This test assumes that the kernels nfnetlink_queue module sees N GSO
packets, segments them into M skbs and queues them to userspace for
reinjection.

Hence, if M >= N, no segmentation occurred.

However, its possible that this happens:
- nfnetlink_queue gets GSO packet
- segments that into n skbs
- userspace buffer is full, kernel drops the segmented skbs

-> "toqueue" counter incremented by 1, "fromqueue" is unchanged.

If this happens often enough in a single run, M >= N check triggers
incorrectly.

To solve this, allow the nf_queue.c test program to set the FAIL_OPEN
flag so that the segmented skbs bypass the queueing step in the kernel
if the receive buffer is full.

Also, reduce number of sending socat instances, decrease their priority
and increase nice value for the nf_queue program itself to reduce the
probability of overruns happening in the first place.

Fixes: 59ecffa3995e ("selftests: netfilter: nft_queue.sh: add udp fraglist gro test case")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20260218184114.0b405b72@kernel.org/
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260226161920.1205-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netfilter/nf_queue.c   | 10 ++++++++--
 tools/testing/selftests/net/netfilter/nft_queue.sh | 13 +++++++++----
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c
index 9e56b9d47037..116c0ca0eabb 100644
--- a/tools/testing/selftests/net/netfilter/nf_queue.c
+++ b/tools/testing/selftests/net/netfilter/nf_queue.c
@@ -18,6 +18,7 @@
 struct options {
 	bool count_packets;
 	bool gso_enabled;
+	bool failopen;
 	int verbose;
 	unsigned int queue_num;
 	unsigned int timeout;
@@ -30,7 +31,7 @@ static struct options opts;
 
 static void help(const char *p)
 {
-	printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
+	printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
 }
 
 static int parse_attr_cb(const struct nlattr *attr, void *data)
@@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void)
 
 	flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0;
 	flags |= NFQA_CFG_F_UID_GID;
+	if (opts.failopen)
+		flags |= NFQA_CFG_F_FAIL_OPEN;
 	mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags));
 	mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags));
 
@@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) {
+	while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) {
 		switch (c) {
 		case 'c':
 			opts.count_packets = true;
@@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv)
 		case 'G':
 			opts.gso_enabled = false;
 			break;
+		case 'o':
+			opts.failopen = true;
+			break;
 		case 'v':
 			opts.verbose++;
 			break;
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 139bc1211878..ea766bdc5d04 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -591,6 +591,7 @@ EOF
 test_udp_gro_ct()
 {
 	local errprefix="FAIL: test_udp_gro_ct:"
+	local timeout=5
 
 	ip netns exec "$nsrouter" conntrack -F 2>/dev/null
 
@@ -630,10 +631,10 @@ table inet udpq {
 	}
 }
 EOF
-	timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
+	timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc &
 	local rpid=$!
 
-	ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" &
+	ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" &
 	local nfqpid=$!
 
 	ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on
@@ -643,8 +644,12 @@ EOF
 
 	local bs=512
 	local count=$(((32 * 1024 * 1024) / bs))
-	dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do
-		timeout 5 ip netns exec "$ns1" \
+
+	local nprocs=$(nproc)
+	[ $nprocs -gt 1 ] && nprocs=$((nprocs - 1))
+
+	dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do
+		timeout "$timeout" nice -n 19 ip netns exec "$ns1" \
 			socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 &
 	done
 
-- 
cgit v1.2.3


From 11cb63b0d1a0685e0831ae3c77223e002ef18189 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 25 Feb 2026 10:43:48 -0300
Subject: net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and
 shared blocks

As Paolo said earlier [1]:

"Since the blamed commit below, classify can return TC_ACT_CONSUMED while
the current skb being held by the defragmentation engine. As reported by
GangMin Kim, if such packet is that may cause a UaF when the defrag engine
later on tries to tuch again such packet."

act_ct was never meant to be used in the egress path, however some users
are attaching it to egress today [2]. Attempting to reach a middle
ground, we noticed that, while most qdiscs are not handling
TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we
address the issue by only allowing act_ct to bind to clsact/ingress
qdiscs and shared blocks. That way it's still possible to attach act_ct to
egress (albeit only with clsact).

[1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/
[2] https://lore.kernel.org/netdev/cc6bfb4a-4a2b-42d8-b9ce-7ef6644fb22b@ovn.org/

Reported-by: GangMin Kim <km.kim1503@gmail.com>
Fixes: 3f14b377d01d ("net/sched: act_ct: fix skb leak and crash on ooo frags")
CC: stable@vger.kernel.org
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260225134349.1287037-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/act_api.h | 1 +
 net/sched/act_ct.c    | 6 ++++++
 net/sched/cls_api.c   | 7 +++++++
 3 files changed, 14 insertions(+)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index e1e8f0f7dacb..d11b79107930 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -70,6 +70,7 @@ struct tc_action {
 #define TCA_ACT_FLAGS_REPLACE	(1U << (TCA_ACT_FLAGS_USER_BITS + 2))
 #define TCA_ACT_FLAGS_NO_RTNL	(1U << (TCA_ACT_FLAGS_USER_BITS + 3))
 #define TCA_ACT_FLAGS_AT_INGRESS	(1U << (TCA_ACT_FLAGS_USER_BITS + 4))
+#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT	(1U << (TCA_ACT_FLAGS_USER_BITS + 5))
 
 /* Update lastuse only if needed, to avoid dirtying a cache line.
  * We use a temp variable to avoid fetching jiffies twice.
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index bd51522c7953..7d5e50c921a0 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
+	if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Attaching ct to a non ingress/clsact qdisc is unsupported");
+		return -EOPNOTSUPP;
+	}
+
 	err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
 	if (err < 0)
 		return err;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 343309e9009b..4829c27446e3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid)
 	return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS));
 }
 
+static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q)
+{
+	return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS));
+}
+
 static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 			  struct netlink_ext_ack *extack)
 {
@@ -2420,6 +2425,8 @@ replay:
 		flags |= TCA_ACT_FLAGS_NO_RTNL;
 	if (is_qdisc_ingress(parent))
 		flags |= TCA_ACT_FLAGS_AT_INGRESS;
+	if (is_ingress_or_clsact(block, q))
+		flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT;
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      flags, extack);
 	if (err == 0) {
-- 
cgit v1.2.3


From b14e82abf78affa50f4cabe8493e17f9adcfcec7 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 25 Feb 2026 10:43:49 -0300
Subject: selftests/tc-testing: Create tests to exercise act_ct binding
 restrictions

Add 4 test cases to exercise new act_ct binding restrictions:

- Try to attach act_ct to an ets qdisc
- Attach act_ct to an ingress qdisc
- Attach act_ct to a clsact/egress qdisc
- Attach act_ct to a shared block

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260225134349.1287037-2-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/tc-testing/tc-tests/actions/ct.json  | 159 +++++++++++++++++++++
 1 file changed, 159 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
index 7d07c55bb668..33bb8f3ff8ed 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json
@@ -505,5 +505,164 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "8883",
+        "name": "Try to attach act_ct to an ets qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 root handle 1: ets bands 2"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "2",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip",
+        "matchJSON": [],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 root"
+        ]
+    },
+    {
+        "id": "3b10",
+        "name": "Attach act_ct to an ingress qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0337",
+        "name": "Attach act_ct to a clsact/egress qdisc",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
+        "id": "4f60",
+        "name": "Attach act_ct to a shared block",
+        "category": [
+            "actions",
+            "ct"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ct",
+                0,
+                1,
+                255
+            ],
+            "$TC qdisc add dev $DEV1 ingress_block 21 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip",
+        "matchJSON": [
+            {
+                "kind": "matchall"
+            },
+            {
+                "options": {
+                    "actions": [
+                        {
+                            "order": 1,
+                            "kind": "ct",
+                            "index": 42,
+                            "ref": 1,
+                            "bind": 1
+                        }
+                    ]
+                }
+            }
+        ],
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress_block 21 clsact"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 15fba71533bcdfaa8eeba69a5a5a2927afdf664a Mon Sep 17 00:00:00 2001
From: Valentin Spreckels <valentin@spreckels.dev>
Date: Thu, 26 Feb 2026 20:54:09 +0100
Subject: net: usb: r8152: add TRENDnet TUC-ET2G

The TRENDnet TUC-ET2G is a RTL8156 based usb ethernet adapter. Add its
vendor and product IDs.

Signed-off-by: Valentin Spreckels <valentin@spreckels.dev>
Link: https://patch.msgid.link/20260226195409.7891-2-valentin@spreckels.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c   | 1 +
 include/linux/usb/r8152.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4af85728ac4f..0c83bbbea2e7 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
 	{ USB_DEVICE(VENDOR_ID_DELL,    0xb097) },
 	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
+	{ USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) },
 	{}
 };
 
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 2ca60828f28b..1502b2a355f9 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -32,6 +32,7 @@
 #define VENDOR_ID_DLINK			0x2001
 #define VENDOR_ID_DELL			0x413c
 #define VENDOR_ID_ASUS			0x0b05
+#define VENDOR_ID_TRENDNET		0x20f4
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
-- 
cgit v1.2.3


From dabffd08545ffa1d7183bc45e387860984025291 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Thu, 26 Feb 2026 11:28:33 -0800
Subject: net: mana: Ring doorbell at 4 CQ wraparounds

MANA hardware requires at least one doorbell ring every 8 wraparounds
of the CQ. The driver rings the doorbell as a form of flow control to
inform hardware that CQEs have been consumed.

The NAPI poll functions mana_poll_tx_cq() and mana_poll_rx_cq() can
poll up to CQE_POLLING_BUFFER (512) completions per call. If the CQ
has fewer than 512 entries, a single poll call can process more than
4 wraparounds without ringing the doorbell. The doorbell threshold
check also uses ">" instead of ">=", delaying the ring by one extra
CQE beyond 4 wraparounds. Combined, these issues can cause the driver
to exceed the 8-wraparound hardware limit, leading to missed
completions and stalled queues.

Fix this by capping the number of CQEs polled per call to 4 wraparounds
of the CQ in both TX and RX paths. Also change the doorbell threshold
from ">" to ">=" so the doorbell is rung as soon as 4 wraparounds are
reached.

Cc: stable@vger.kernel.org
Fixes: 58a63729c957 ("net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings")
Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20260226192833.1050807-1-longli@microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 933e9d681ded..9017e806ecda 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1770,8 +1770,14 @@ static void mana_poll_tx_cq(struct mana_cq *cq)
 	ndev = txq->ndev;
 	apc = netdev_priv(ndev);
 
+	/* Limit CQEs polled to 4 wraparounds of the CQ to ensure the
+	 * doorbell can be rung in time for the hardware's requirement
+	 * of at least one doorbell ring every 8 wraparounds.
+	 */
 	comp_read = mana_gd_poll_cq(cq->gdma_cq, completions,
-				    CQE_POLLING_BUFFER);
+				    min((cq->gdma_cq->queue_size /
+					  COMP_ENTRY_SIZE) * 4,
+					 CQE_POLLING_BUFFER));
 
 	if (comp_read < 1)
 		return;
@@ -2156,7 +2162,14 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
 	struct mana_rxq *rxq = cq->rxq;
 	int comp_read, i;
 
-	comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER);
+	/* Limit CQEs polled to 4 wraparounds of the CQ to ensure the
+	 * doorbell can be rung in time for the hardware's requirement
+	 * of at least one doorbell ring every 8 wraparounds.
+	 */
+	comp_read = mana_gd_poll_cq(cq->gdma_cq, comp,
+				    min((cq->gdma_cq->queue_size /
+					  COMP_ENTRY_SIZE) * 4,
+					 CQE_POLLING_BUFFER));
 	WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER);
 
 	rxq->xdp_flush = false;
@@ -2201,11 +2214,11 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
 		mana_gd_ring_cq(gdma_queue, SET_ARM_BIT);
 		cq->work_done_since_doorbell = 0;
 		napi_complete_done(&cq->napi, w);
-	} else if (cq->work_done_since_doorbell >
-		   cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) {
+	} else if (cq->work_done_since_doorbell >=
+		   (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) {
 		/* MANA hardware requires at least one doorbell ring every 8
 		 * wraparounds of CQ even if there is no need to arm the CQ.
-		 * This driver rings the doorbell as soon as we have exceeded
+		 * This driver rings the doorbell as soon as it has processed
 		 * 4 wraparounds.
 		 */
 		mana_gd_ring_cq(gdma_queue, 0);
-- 
cgit v1.2.3


From 8168a7b72bdee3790b126f63bd30306759206b15 Mon Sep 17 00:00:00 2001
From: Ashish Kalra <ashish.kalra@amd.com>
Date: Fri, 6 Feb 2026 21:26:45 +0000
Subject: crypto: ccp - allow callers to use HV-Fixed page API when SEV is
 disabled

When SEV is disabled, the HV-Fixed page allocation call fails, which in
turn causes SFS initialization to fail.

Fix the HV-Fixed API so callers (for example, SFS) can use it even when
SEV is disabled by performing normal page allocation and freeing.

Fixes: e09701dcdd9c ("crypto: ccp - Add new HV-Fixed page allocation/free API")
Cc: stable@vger.kernel.org
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 096f993974d1..8b2dfc11289b 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -1105,15 +1105,12 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages)
 {
 	struct psp_device *psp_master = psp_get_master_device();
 	struct snp_hv_fixed_pages_entry *entry;
-	struct sev_device *sev;
 	unsigned int order;
 	struct page *page;
 
-	if (!psp_master || !psp_master->sev_data)
+	if (!psp_master)
 		return NULL;
 
-	sev = psp_master->sev_data;
-
 	order = get_order(PMD_SIZE * num_2mb_pages);
 
 	/*
@@ -1126,7 +1123,8 @@ struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages)
 	 * This API uses SNP_INIT_EX to transition allocated pages to HV_Fixed
 	 * page state, fail if SNP is already initialized.
 	 */
-	if (sev->snp_initialized)
+	if (psp_master->sev_data &&
+	    ((struct sev_device *)psp_master->sev_data)->snp_initialized)
 		return NULL;
 
 	/* Re-use freed pages that match the request */
@@ -1162,7 +1160,7 @@ void snp_free_hv_fixed_pages(struct page *page)
 	struct psp_device *psp_master = psp_get_master_device();
 	struct snp_hv_fixed_pages_entry *entry, *nentry;
 
-	if (!psp_master || !psp_master->sev_data)
+	if (!psp_master)
 		return;
 
 	/*
-- 
cgit v1.2.3


From 889b0e2721e793eb46cf7d17b965aa3252af3ec8 Mon Sep 17 00:00:00 2001
From: Alper Ak <alperyasinak1@gmail.com>
Date: Mon, 9 Feb 2026 13:30:42 +0300
Subject: crypto: ccp - Fix use-after-free on error path

In the error path of sev_tsm_init_locked(), the code dereferences 't'
after it has been freed with kfree(). The pr_err() statement attempts
to access t->tio_en and t->tio_init_done after the memory has been
released.

Move the pr_err() call before kfree(t) to access the fields while the
memory is still valid.

This issue reported by Smatch static analyser

Fixes:4be423572da1 ("crypto/ccp: Implement SEV-TIO PCIe IDE (phase1)")
Signed-off-by: Alper Ak <alperyasinak1@gmail.com>
Acked-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev-tsm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/ccp/sev-dev-tsm.c b/drivers/crypto/ccp/sev-dev-tsm.c
index adc9542ae806..b07ae529b591 100644
--- a/drivers/crypto/ccp/sev-dev-tsm.c
+++ b/drivers/crypto/ccp/sev-dev-tsm.c
@@ -378,9 +378,9 @@ void sev_tsm_init_locked(struct sev_device *sev, void *tio_status_page)
 	return;
 
 error_exit:
-	kfree(t);
 	pr_err("Failed to enable SEV-TIO: ret=%d en=%d initdone=%d SEV=%d\n",
 	       ret, t->tio_en, t->tio_init_done, boot_cpu_has(X86_FEATURE_SEV));
+	kfree(t);
 }
 
 void sev_tsm_uninit(struct sev_device *sev)
-- 
cgit v1.2.3


From d240b079a37e90af03fd7dfec94930eb6c83936e Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 19 Feb 2026 00:54:00 +0100
Subject: crypto: atmel-sha204a - Fix OOM ->tfm_count leak

If memory allocation fails, decrement ->tfm_count to avoid blocking
future reads.

Cc: stable@vger.kernel.org
Fixes: da001fb651b0 ("crypto: atmel-i2c - add support for SHA204A random number generator")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/atmel-sha204a.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
index 8adc7fe71c04..98d1023007e3 100644
--- a/drivers/crypto/atmel-sha204a.c
+++ b/drivers/crypto/atmel-sha204a.c
@@ -52,9 +52,10 @@ static int atmel_sha204a_rng_read_nonblocking(struct hwrng *rng, void *data,
 		rng->priv = 0;
 	} else {
 		work_data = kmalloc_obj(*work_data, GFP_ATOMIC);
-		if (!work_data)
+		if (!work_data) {
+			atomic_dec(&i2c_priv->tfm_count);
 			return -ENOMEM;
-
+		}
 		work_data->ctx = i2c_priv;
 		work_data->client = i2c_priv->client;
 
-- 
cgit v1.2.3


From 778031e1658d206a52bf9491c91ae5d4f4a2509d Mon Sep 17 00:00:00 2001
From: Matt DeVillier <matt.devillier@gmail.com>
Date: Thu, 26 Feb 2026 10:30:55 -0600
Subject: ALSA: hda/ca0132: Set HP/Speaker auto-detect default from headphone
 pin verb

HP/Speaker auto-detect (VNID_HP_ASEL) has been off by default for every
CA0132 device since the driver was added in 2012. vnode_lswitch is
always initialized to 0 in ca0132_init_chip(), and no quirk or other
code path enables it. As a result, headphone jack detection works only
after the user manually turns on "HP/Speaker Auto Detect" in alsamixer,
which is not obvious on laptops with combo jacks (e.g. Google Link,
Alienware).

Change the default to follow the headphone pin config: if the pin verb
has presence detect enabled (no AC_DEFCFG_MISC_NO_PRESENCE) and the
codec supports it (AC_PINCAP_PRES_DETECT), enable HP_ASEL by default.
This lets firmware (coreboot, UEFI, etc.) express whether the headphone
jack supports insertion detection. Devices with combo jacks can default
to auto-detect; devices with fixed/no jack leave it off.

Signed-off-by: Matt DeVillier <matt.devillier@gmail.com>
Link: https://patch.msgid.link/20260226163055.825167-1-matt.devillier@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/ca0132.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/codecs/ca0132.c b/sound/hda/codecs/ca0132.c
index bf342a76807c..a0677d7da8e2 100644
--- a/sound/hda/codecs/ca0132.c
+++ b/sound/hda/codecs/ca0132.c
@@ -9816,6 +9816,15 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->dig_in = 0x09;
 		break;
 	}
+
+	/* Default HP/Speaker auto-detect from headphone pin verb: enable if the
+	 * pin config indicates presence detect (not AC_DEFCFG_MISC_NO_PRESENCE).
+	 */
+	if (spec->unsol_tag_hp &&
+	    (snd_hda_query_pin_caps(codec, spec->unsol_tag_hp) & AC_PINCAP_PRES_DETECT) &&
+	    !(get_defcfg_misc(snd_hda_codec_get_pincfg(codec, spec->unsol_tag_hp)) &
+	      AC_DEFCFG_MISC_NO_PRESENCE))
+		spec->vnode_lswitch[VNID_HP_ASEL - VNODE_START_NID] = 1;
 }
 
 static int ca0132_prepare_verbs(struct hda_codec *codec)
-- 
cgit v1.2.3


From bd72a37b219b9b424bc5ec28f660ebdc129de7cb Mon Sep 17 00:00:00 2001
From: Lianqin Hu <hulianqin@vivo.com>
Date: Fri, 27 Feb 2026 02:11:02 +0000
Subject: ALSA: usb-audio: Add iface reset and delay quirk for AB13X USB Audio

Setting up the interface when suspended/resumeing fail on this card.
Adding a reset and delay quirk will eliminate this problem.

usb 1-1: New USB device found, idVendor=0624, idProduct=3d3f
usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
usb 1-1: Product: AB13X USB Audio
usb 1-1: Manufacturer: Generic
usb 1-1: SerialNumber: 20210726905926

Signed-off-by: Lianqin Hu <hulianqin@vivo.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/TYUPR06MB621795D087BF2D594027C235D273A@TYUPR06MB6217.apcprd06.prod.outlook.com
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index c6a78efbcaa3..d54a1a44a69b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2219,6 +2219,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x05e1, 0x0480, /* Hauppauge Woodbury */
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
+	DEVICE_FLG(0x0624, 0x3d3f, /* AB13X USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x0644, 0x8043, /* TEAC UD-501/UD-501V2/UD-503/NT-503 */
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY |
 		   QUIRK_FLAG_IFACE_DELAY),
-- 
cgit v1.2.3


From 068641bc9dc3d680d1ec4f6ee9199d4812041dff Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 27 Feb 2026 20:13:27 +0800
Subject: ALSA: hda/realtek: Add quirk for HP Pavilion 15-eh1xxx to enable mute
 LED

The HP Pavilion 15-eh1xxx series uses the HP mainboard 88D1 with ALC245
and needs the ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT quirk to make the
mute led working.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=215978
Cc: <stable@vger.kernel.org>
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260227121327.3751341-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 86bb22d19629..4c49f1195e1b 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6904,6 +6904,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88b3, "HP ENVY x360 Convertible 15-es0xxx", ALC245_FIXUP_HP_ENVY_X360_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x88d1, "HP Pavilion 15-eh1xxx (mainboard 88D1)", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88eb, "HP Victus 16-e0xxx", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
-- 
cgit v1.2.3


From 05ac3846ffe53fc63e454eb195ce8a6bab7a6a88 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Fri, 27 Feb 2026 22:46:40 +0800
Subject: ALSA: hda/tas2781: A workaround solution to lower-vol issue among
 lower calibrated-impedance micro-speaker on TAS2781

On TAS2781, if the Speaker calibrated impedance is lower than default
value hard-coded inside the TAS2781, it will cuase vol lower than
normal. In order to fix this issue, the parameter of SineGainI need
updating.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Tested-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Link: https://patch.msgid.link/20260227144641.1243-1-shenghao-ding@ti.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781.h                        |  1 +
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 15 +---
 sound/soc/codecs/tas2781-fmwlib.c              | 94 ++++++++++++++++++++++++++
 3 files changed, 98 insertions(+), 12 deletions(-)

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index 7c03bdc951bb..e847cf51878c 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -151,6 +151,7 @@ struct tasdevice {
 	struct bulk_reg_val *cali_data_backup;
 	struct bulk_reg_val alp_cali_bckp;
 	struct tasdevice_fw *cali_data_fmw;
+	void *cali_specific;
 	unsigned int dev_addr;
 	unsigned int err_code;
 	unsigned char cur_book;
diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 74c3cf1e45e1..67240ce184e1 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -60,7 +60,6 @@ struct tas2781_hda_i2c_priv {
 	int (*save_calibration)(struct tas2781_hda *h);
 
 	int hda_chip_id;
-	bool skip_calibration;
 };
 
 static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data)
@@ -479,8 +478,7 @@ static void tasdevice_dspfw_init(void *context)
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
-	if (!hda_priv->skip_calibration)
-		hda_priv->save_calibration(tas_hda);
+	hda_priv->save_calibration(tas_hda);
 }
 
 static void tasdev_fw_ready(const struct firmware *fmw, void *context)
@@ -535,7 +533,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 	void *master_data)
 {
 	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
-	struct tas2781_hda_i2c_priv *hda_priv = tas_hda->hda_priv;
 	struct hda_component_parent *parent = master_data;
 	struct hda_component *comp;
 	struct hda_codec *codec;
@@ -564,14 +561,6 @@ static int tas2781_hda_bind(struct device *dev, struct device *master,
 		break;
 	}
 
-	/*
-	 * Using ASUS ROG Xbox Ally X (RC73XA) UEFI calibration data
-	 * causes audio dropouts during playback, use fallback data
-	 * from DSP firmware as a workaround.
-	 */
-	if (codec->core.subsystem_id == 0x10431384)
-		hda_priv->skip_calibration = true;
-
 	guard(pm_runtime_active_auto)(dev);
 
 	comp->dev = dev;
@@ -643,6 +632,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 		 */
 		device_name = "TIAS2781";
 		hda_priv->hda_chip_id = HDA_TAS2781;
+		tas_hda->priv->chip_id = TAS2781;
 		hda_priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
 	} else if (strstarts(dev_name(&clt->dev), "i2c-TXNW2770")) {
@@ -656,6 +646,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 			     "i2c-TXNW2781:00-tas2781-hda.0")) {
 		device_name = "TXNW2781";
 		hda_priv->hda_chip_id = HDA_TAS2781;
+		tas_hda->priv->chip_id = TAS2781;
 		hda_priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
 	} else if (strstr(dev_name(&clt->dev), "INT8866")) {
diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index c969eb38704e..5798d518d94c 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -32,6 +32,10 @@
 #define TAS2781_YRAM1_PAGE			42
 #define TAS2781_YRAM1_START_REG			88
 
+#define TAS2781_PG_REG		TASDEVICE_REG(0x00, 0x00, 0x7c)
+#define TAS2781_PG_1_0		0xA0
+#define TAS2781_PG_2_0		0xA8
+
 #define TAS2781_YRAM2_START_PAGE		43
 #define TAS2781_YRAM2_END_PAGE			49
 #define TAS2781_YRAM2_START_REG			8
@@ -98,6 +102,12 @@ struct blktyp_devidx_map {
 	unsigned char dev_idx;
 };
 
+struct tas2781_cali_specific {
+	unsigned char sin_gni[4];
+	int sin_gni_reg;
+	bool is_sin_gn_flush;
+};
+
 static const char deviceNumber[TASDEVICE_DSP_TAS_MAX_DEVICE] = {
 	1, 2, 1, 2, 1, 1, 0, 2, 4, 3, 1, 2, 3, 4, 1, 2
 };
@@ -2454,6 +2464,84 @@ static int tasdevice_load_data(struct tasdevice_priv *tas_priv,
 	return ret;
 }
 
+static int tas2781_cali_preproc(struct tasdevice_priv *priv, int i)
+{
+	struct tas2781_cali_specific *spec = priv->tasdevice[i].cali_specific;
+	struct calidata *cali_data = &priv->cali_data;
+	struct cali_reg *p = &cali_data->cali_reg_array;
+	unsigned char *data = cali_data->data;
+	int rc;
+
+	/*
+	 * On TAS2781, if the Speaker calibrated impedance is lower than
+	 * default value hard-coded inside the TAS2781, it will cuase vol
+	 * lower than normal. In order to fix this issue, the parameter of
+	 * SineGainI need updating.
+	 */
+	if (spec == NULL) {
+		int k = i * (cali_data->cali_dat_sz_per_dev + 1);
+		int re_org, re_cal, corrected_sin_gn, pg_id;
+		unsigned char r0_deflt[4];
+
+		spec = devm_kzalloc(priv->dev, sizeof(*spec), GFP_KERNEL);
+		if (spec == NULL)
+			return -ENOMEM;
+		priv->tasdevice[i].cali_specific = spec;
+		rc = tasdevice_dev_bulk_read(priv, i, p->r0_reg, r0_deflt, 4);
+		if (rc < 0) {
+			dev_err(priv->dev, "invalid RE from %d = %d\n", i, rc);
+			return rc;
+		}
+		/*
+		 * SineGainI need to be re-calculated, calculate the high 16
+		 * bits.
+		 */
+		re_org = r0_deflt[0] << 8 | r0_deflt[1];
+		re_cal = data[k + 1] << 8 | data[k + 2];
+		if (re_org > re_cal) {
+			rc = tasdevice_dev_read(priv, i, TAS2781_PG_REG,
+						 &pg_id);
+			if (rc < 0) {
+				dev_err(priv->dev, "invalid PG id %d = %d\n",
+					i, rc);
+				return rc;
+			}
+
+			spec->sin_gni_reg = (pg_id == TAS2781_PG_1_0) ?
+				TASDEVICE_REG(0, 0x1b, 0x34) :
+				TASDEVICE_REG(0, 0x18, 0x1c);
+
+			rc = tasdevice_dev_bulk_read(priv, i,
+						      spec->sin_gni_reg,
+						      spec->sin_gni, 4);
+			if (rc < 0) {
+				dev_err(priv->dev, "wrong sinegaini %d = %d\n",
+					i, rc);
+				return rc;
+			}
+			corrected_sin_gn = re_org * ((spec->sin_gni[0] << 8) +
+						       spec->sin_gni[1]);
+			corrected_sin_gn /= re_cal;
+			spec->sin_gni[0] = corrected_sin_gn >> 8;
+			spec->sin_gni[1] = corrected_sin_gn & 0xff;
+
+			spec->is_sin_gn_flush = true;
+		}
+	}
+
+	if (spec->is_sin_gn_flush) {
+		rc = tasdevice_dev_bulk_write(priv, i, spec->sin_gni_reg,
+						       spec->sin_gni, 4);
+		if (rc < 0) {
+			dev_err(priv->dev, "update failed %d = %d\n",
+				i, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+
 static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 {
 	struct calidata *cali_data = &priv->cali_data;
@@ -2469,6 +2557,12 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 	}
 	k++;
 
+	if (priv->chip_id == TAS2781) {
+		rc = tas2781_cali_preproc(priv, i);
+		if (rc < 0)
+			return;
+	}
+
 	rc = tasdevice_dev_bulk_write(priv, i, p->r0_reg, &(data[k]), 4);
 	if (rc < 0) {
 		dev_err(priv->dev, "chn %d r0_reg bulk_wr err = %d\n", i, rc);
-- 
cgit v1.2.3


From d4d5633d8b19b0e745a7910aea49956b3b47900d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 27 Feb 2026 16:57:00 +0100
Subject: ALSA: firewire: dice: Fix printf warning with W=1

The use of snprintf() may cause a warning with W=1 due to the possibly
truncated string.  As the truncation doesn't really matter (and won't
happen practically) in the case of dice driver, just shut it up by
replacing with scnprintf().

Link: https://patch.msgid.link/20260227155705.1557224-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/dice/dice.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c
index 85d265c7d544..f7a50bae4b55 100644
--- a/sound/firewire/dice/dice.c
+++ b/sound/firewire/dice/dice.c
@@ -122,7 +122,7 @@ static void dice_card_strings(struct snd_dice *dice)
 	fw_csr_string(dev->config_rom + 5, CSR_VENDOR, vendor, sizeof(vendor));
 	strscpy(model, "?");
 	fw_csr_string(dice->unit->directory, CSR_MODEL, model, sizeof(model));
-	snprintf(card->longname, sizeof(card->longname),
+	scnprintf(card->longname, sizeof(card->longname),
 		 "%s %s (serial %u) at %s, S%d",
 		 vendor, model, dev->config_rom[4] & 0x3fffff,
 		 dev_name(&dice->unit->device), 100 << dev->max_speed);
-- 
cgit v1.2.3


From 0ed2e8bf61d6d5df1d78f4e24b682dff4c394e17 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 28 Feb 2026 04:56:20 -0700
Subject: io_uring: correct comment for IORING_SETUP_TASKRUN_FLAG

Sync with a recent liburing fix, which corrects the comment explaining
when the IORING_SETUP_TASKRUN_FLAG setup flag is valid to use. May be
use with COOP_TASKRUN or DEFER_TASKRUN, not useful without either of
this task_work mechanisms being used.

Link: https://github.com/axboe/liburing/pull/1543
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 6750c383a2ab..1ff16141c8a5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -188,7 +188,8 @@ enum io_uring_sqe_flags_bit {
 /*
  * If COOP_TASKRUN is set, get notified if task work is available for
  * running and a kernel transition would be needed to run it. This sets
- * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
+ * IORING_SQ_TASKRUN in the sq ring flags. Not valid without COOP_TASKRUN
+ * or DEFER_TASKRUN.
  */
 #define IORING_SETUP_TASKRUN_FLAG	(1U << 9)
 #define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */
-- 
cgit v1.2.3


From 407fd8b8d8cce03856aa67329715de48b254b529 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Feb 2026 19:03:03 +0100
Subject: KVM: remove CONFIG_KVM_GENERIC_MMU_NOTIFIER

All architectures now use MMU notifier for KVM page table management.
Remove the Kconfig symbol and the code that is used when it is
disabled.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     |  1 -
 arch/loongarch/kvm/Kconfig |  1 -
 arch/mips/kvm/Kconfig      |  1 -
 arch/powerpc/kvm/Kconfig   |  4 ----
 arch/powerpc/kvm/powerpc.c |  1 -
 arch/riscv/kvm/Kconfig     |  1 -
 arch/s390/kvm/Kconfig      |  2 --
 arch/x86/kvm/Kconfig       |  1 -
 include/linux/kvm_host.h   |  7 +------
 virt/kvm/Kconfig           |  9 +--------
 virt/kvm/kvm_main.c        | 16 ----------------
 11 files changed, 2 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 4f803fd1c99a..7d1f22fd490b 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -21,7 +21,6 @@ menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	select KVM_COMMON
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index ed4f724db774..8e5213609975 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -28,7 +28,6 @@ config KVM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select VIRT_XFER_TO_GUEST_WORK
 	select SCHED_INFO
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index cc13cc35f208..b1b9a1d67758 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -23,7 +23,6 @@ config KVM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select HAVE_KVM_READONLY_MEM
 	help
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index c9a2d50ff1b0..9a0d1c1aca6c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -38,7 +38,6 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -81,7 +80,6 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_BOOK3S_HV_PMU
 	select CMA
 	help
@@ -203,7 +201,6 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -220,7 +217,6 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 9a89a6d98f97..3da40ea8c562 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -625,7 +625,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 77379f77840a..ec2cee0a39e0 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -30,7 +30,6 @@ config KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select VIRT_XFER_TO_GUEST_WORK
-	select KVM_GENERIC_MMU_NOTIFIER
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	help
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 917ac740513e..5b835bc6a194 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -28,9 +28,7 @@ config KVM
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
 	select KVM_VFIO
-	select MMU_NOTIFIER
 	select VIRT_XFER_TO_GUEST_WORK
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMU_LOCKLESS_AGING
 	help
 	  Support hosting paravirtualized guest machines using the SIE
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index d916bd766c94..801bf9e520db 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM_X86
 	def_tristate KVM if (KVM_INTEL != n || KVM_AMD != n)
 	select KVM_COMMON
-	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_ELIDE_TLB_FLUSH_IF_YOUNG
 	select KVM_MMU_LOCKLESS_AGING
 	select HAVE_KVM_IRQCHIP
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index dde605cb894e..34759a262b28 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -253,7 +253,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	unsigned long attributes;
 };
@@ -275,7 +274,6 @@ struct kvm_gfn_range {
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
-#endif
 
 enum {
 	OUTSIDE_GUEST_MODE,
@@ -849,13 +847,12 @@ struct kvm {
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
 	gfn_t mmu_invalidate_range_start;
 	gfn_t mmu_invalidate_range_end;
-#endif
+
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
 	struct dentry *debugfs_dentry;
@@ -2118,7 +2115,6 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -2196,7 +2192,6 @@ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
 
 	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
 }
-#endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 267c7369c765..794976b88c6f 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -5,6 +5,7 @@ config KVM_COMMON
        bool
        select EVENTFD
        select INTERVAL_TREE
+       select MMU_NOTIFIER
        select PREEMPT_NOTIFIERS
 
 config HAVE_KVM_PFNCACHE
@@ -93,24 +94,16 @@ config HAVE_KVM_PM_NOTIFIER
 config KVM_GENERIC_HARDWARE_ENABLING
        bool
 
-config KVM_GENERIC_MMU_NOTIFIER
-       select MMU_NOTIFIER
-       bool
-
 config KVM_ELIDE_TLB_FLUSH_IF_YOUNG
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_MMU_LOCKLESS_AGING
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_GENERIC_MEMORY_ATTRIBUTES
-       depends on KVM_GENERIC_MMU_NOTIFIER
        bool
 
 config KVM_GUEST_MEMFD
-       depends on KVM_GENERIC_MMU_NOTIFIER
        select XARRAY_MULTI
        bool
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 22f8a672e1fd..29ee01747347 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -502,7 +502,6 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_destroy_vcpus);
 
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
@@ -901,15 +900,6 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
-
-static int kvm_init_mmu_notifier(struct kvm *kvm)
-{
-	return 0;
-}
-
-#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
-
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
 				unsigned long state,
@@ -1226,10 +1216,8 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
-#endif
 out_err_no_mmu_notifier:
 	kvm_disable_virtualization();
 out_err_no_disable:
@@ -1292,7 +1280,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
@@ -1311,9 +1298,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->mn_active_invalidate_count = 0;
 	else
 		WARN_ON(kvm->mmu_invalidate_in_progress);
-#else
-	kvm_flush_shadow_all(kvm);
-#endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
-- 
cgit v1.2.3


From 70295a479da684905c18d96656d781823f418ec2 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Feb 2026 19:06:31 +0100
Subject: KVM: always define KVM_CAP_SYNC_MMU

KVM_CAP_SYNC_MMU is provided by KVM's MMU notifiers, which are now always
available.  Move the definition from individual architectures to common
code.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 10 ++++------
 arch/arm64/kvm/arm.c           |  1 -
 arch/loongarch/kvm/vm.c        |  1 -
 arch/mips/kvm/mips.c           |  1 -
 arch/powerpc/kvm/powerpc.c     |  5 -----
 arch/riscv/kvm/vm.c            |  1 -
 arch/s390/kvm/kvm-s390.c       |  1 -
 arch/x86/kvm/x86.c             |  1 -
 virt/kvm/kvm_main.c            |  1 +
 9 files changed, 5 insertions(+), 17 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index fc5736839edd..6f85e1b321dd 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1396,7 +1396,10 @@ or its flags may be modified, but it may not be resized.
 Memory for the region is taken starting at the address denoted by the
 field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
-anonymous memory, ordinary files, and hugetlbfs.
+anonymous memory, ordinary files, and hugetlbfs.  Changes in the backing
+of the memory region are automatically reflected into the guest.
+For example, an mmap() that affects the region will be made visible
+immediately.  Another example is madvise(MADV_DROP).
 
 On architectures that support a form of address tagging, userspace_addr must
 be an untagged address.
@@ -1412,11 +1415,6 @@ use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
 to make a new slot read-only.  In this case, writes to this memory will be
 posted to userspace as KVM_EXIT_MMIO exits.
 
-When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
-the memory region are automatically reflected into the guest.  For example, an
-mmap() that affects the region will be made visible immediately.  Another
-example is madvise(MADV_DROP).
-
 For TDX guest, deleting/moving memory region loses guest memory contents.
 Read only region isn't supported.  Only as-id 0 is supported.
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 29f0326f7e00..410ffd41fd73 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -358,7 +358,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_USER_MEMORY:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ARM_PSCI:
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 63fd40530aa9..5282158b8122 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -118,7 +118,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_IMMEDIATE_EXIT:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_MP_STATE:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index b0fb92fda4d4..29d9f630edfb 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1035,7 +1035,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_READONLY_MEM:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_IMMEDIATE_EXIT:
 		r = 1;
 		break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3da40ea8c562..00302399fc37 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -623,11 +623,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
 		       !kvmppc_hv_ops->enable_nested(NULL));
 		break;
-#endif
-	case KVM_CAP_SYNC_MMU:
-		r = 1;
-		break;
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_HTAB_FD:
 		r = hv_enabled;
 		break;
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 7cbd2340c190..58bce57dc55b 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -181,7 +181,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_USER_MEMORY:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_READONLY_MEM:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7a175d86cef0..bc7d6fa66eaf 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -601,7 +601,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
-	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_S390_UCONTROL
 	case KVM_CAP_S390_UCONTROL:
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3fb64905d190..a03530795707 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4805,7 +4805,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
-	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IOEVENTFD:
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29ee01747347..1bc1da66b4b0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4870,6 +4870,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
+	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
-- 
cgit v1.2.3


From 6996a2d2d0a64808c19c98002aeb5d9d1b2df6a4 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 27 Feb 2026 03:55:35 +0000
Subject: udp: Unhash auto-bound connected sk from 4-tuple hash table when
 disconnected.

Let's say we bind() an UDP socket to the wildcard address with a
non-zero port, connect() it to an address, and disconnect it from
the address.

bind() sets SOCK_BINDPORT_LOCK on sk->sk_userlocks (but not
SOCK_BINDADDR_LOCK), and connect() calls udp_lib_hash4() to put
the socket into the 4-tuple hash table.

Then, __udp_disconnect() calls sk->sk_prot->rehash(sk).

It computes a new hash based on the wildcard address and moves
the socket to a new slot in the 4-tuple hash table, leaving a
garbage in the chain that no packet hits.

Let's remove such a socket from 4-tuple hash table when disconnected.

Note that udp_sk(sk)->udp_portaddr_hash needs to be udpated after
udp_hash4_dec(hslot2) in udp_unhash4().

Fixes: 78c91ae2c6de ("ipv4/udp: Add 4-tuple hash for connected socket")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260227035547.3321327-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 014fdfdd331b..b60fad393e18 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2287,7 +2287,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 				     udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		nhslot2 = udp_hashslot2(udptable, newhash);
-		udp_sk(sk)->udp_portaddr_hash = newhash;
 
 		if (hslot2 != nhslot2 ||
 		    rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -2321,19 +2320,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 		if (udp_hashed4(sk)) {
 			spin_lock_bh(&hslot->lock);
 
-			udp_rehash4(udptable, sk, newhash4);
-			if (hslot2 != nhslot2) {
-				spin_lock(&hslot2->lock);
-				udp_hash4_dec(hslot2);
-				spin_unlock(&hslot2->lock);
-
-				spin_lock(&nhslot2->lock);
-				udp_hash4_inc(nhslot2);
-				spin_unlock(&nhslot2->lock);
+			if (inet_rcv_saddr_any(sk)) {
+				udp_unhash4(udptable, sk);
+			} else {
+				udp_rehash4(udptable, sk, newhash4);
+				if (hslot2 != nhslot2) {
+					spin_lock(&hslot2->lock);
+					udp_hash4_dec(hslot2);
+					spin_unlock(&hslot2->lock);
+
+					spin_lock(&nhslot2->lock);
+					udp_hash4_inc(nhslot2);
+					spin_unlock(&nhslot2->lock);
+				}
 			}
 
 			spin_unlock_bh(&hslot->lock);
 		}
+
+		udp_sk(sk)->udp_portaddr_hash = newhash;
 	}
 }
 EXPORT_IPV6_MOD(udp_lib_rehash);
-- 
cgit v1.2.3


From 026dfef287c07f37d4d4eef7a0b5a4bfdb29b32d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 26 Feb 2026 16:33:59 -0800
Subject: tcp: give up on stronger sk_rcvbuf checks (for now)

We hit another corner case which leads to TcpExtTCPRcvQDrop

Connections which send RPCs in the 20-80kB range over loopback
experience spurious drops. The exact conditions for most of
the drops I investigated are that:
 - socket exchanged >1MB of data so its not completely fresh
 - rcvbuf is around 128kB (default, hasn't grown)
 - there is ~60kB of data in rcvq
 - skb > 64kB arrives

The sum of skb->len (!) of both of the skbs (the one already
in rcvq and the arriving one) is larger than rwnd.
My suspicion is that this happens because __tcp_select_window()
rounds the rwnd up to (1 << wscale) if less than half of
the rwnd has been consumed.

Eric suggests that given the number of Fixes we already have
pointing to 1d2fbaad7cd8 it's probably time to give up on it,
until a bigger revamp of rmem management.

Also while we could risk tweaking the rwnd math, there are other
drops on workloads I investigated, after the commit in question,
not explained by this phenomenon.

Suggested-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/20260225122355.585fd57b@kernel.org
Fixes: 1d2fbaad7cd8 ("tcp: stronger sk_rcvbuf checks")
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260227003359.2391017-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6404e53382ca..7b03f2460751 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5374,25 +5374,11 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
-/* Check if this incoming skb can be added to socket receive queues
- * while satisfying sk->sk_rcvbuf limit.
- *
- * In theory we should use skb->truesize, but this can cause problems
- * when applications use too small SO_RCVBUF values.
- * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio,
- * allowing RWIN to be close to available space.
- * Whenever the receive queue gets full, we can receive a small packet
- * filling RWIN, but with a high skb->truesize, because most NIC use 4K page
- * plus sk_buff metadata even when receiving less than 1500 bytes of payload.
- *
- * Note that we use skb->len to decide to accept or drop this packet,
- * but sk->sk_rmem_alloc is the sum of all skb->truesize.
- */
 static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
 {
 	unsigned int rmem = atomic_read(&sk->sk_rmem_alloc);
 
-	return rmem + skb->len <= sk->sk_rcvbuf;
+	return rmem <= sk->sk_rcvbuf;
 }
 
 static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
-- 
cgit v1.2.3


From 1cc93c48b5d7add5ea038860539893ce1310d72d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 26 Feb 2026 19:34:46 -0800
Subject: selftests/net: packetdrill: remove tests for tcp_rcv_*big

Since commit 1d2fbaad7cd8 ("tcp: stronger sk_rcvbuf checks")
has been reverted we need to remove the corresponding tests.

Link: https://lore.kernel.org/20260227003359.2391017-1-kuba@kernel.org
Link: https://patch.msgid.link/20260227033446.2596457-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_big_endseq.pkt         | 44 ----------------------
 .../selftests/net/packetdrill/tcp_rcv_toobig.pkt   | 33 ----------------
 2 files changed, 77 deletions(-)
 delete mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
 delete mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
deleted file mode 100644
index 3848b419e68c..000000000000
--- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
---mss=1000
-
-`./defaults.sh`
-
-    0 `nstat -n`
-
-// Establish a connection.
-   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
-   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
-   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
-   +0 bind(3, ..., ...) = 0
-   +0 listen(3, 1) = 0
-
-   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
-   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
-  +.1 < . 1:1(0) ack 1 win 257
-
-  +0 accept(3, ..., ...) = 4
-
-  +0 < P. 1:4001(4000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +0 < P. 4001:54001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +1 < P. 5001:55001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
-  +0 < P. 70001:80001(10000) ack 1 win 257
-  +0 > .  1:1(0) ack 4001 win 5000
-
-  +0 read(4, ..., 100000) = 4000
-
-// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
-  +0 < P. 4001:54001(50000) ack 1 win 257
-  +0 > .  1:1(0) ack 54001 win 0
-
-// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
-+0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
deleted file mode 100644
index f575c0ff89da..000000000000
--- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt
+++ /dev/null
@@ -1,33 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
---mss=1000
-
-`./defaults.sh`
-
-    0 `nstat -n`
-
-// Establish a connection.
-   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
-   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
-   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0
-   +0 bind(3, ..., ...) = 0
-   +0 listen(3, 1) = 0
-
-   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
-   +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0>
-  +.1 < . 1:1(0) ack 1 win 257
-
-   +0 accept(3, ..., ...) = 4
-
-   +0 < P. 1:20001(20000) ack 1 win 257
- +.04 > .  1:1(0) ack 20001 win 18000
-
-   +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0
-   +0 < P. 20001:80001(60000) ack 1 win 257
-   +0 > .  1:1(0) ack 20001 win 18000
-
-   +0 read(4, ..., 20000) = 20000
-// A too big packet is accepted if the receive queue is empty
-   +0 < P. 20001:80001(60000) ack 1 win 257
-   +0 > .  1:1(0) ack 80001 win 0
-
-- 
cgit v1.2.3


From 60abb0ac11dccd6b98fd9182bc5f85b621688861 Mon Sep 17 00:00:00 2001
From: "Nikhil P. Rao" <nikhil.rao@amd.com>
Date: Wed, 25 Feb 2026 00:00:26 +0000
Subject: xsk: Fix fragment node deletion to prevent buffer leak

After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"),
the list_node field is reused for both the xskb pool list and the buffer
free list, this causes a buffer leak as described below.

xp_free() checks if a buffer is already on the free list using
list_empty(&xskb->list_node). When list_del() is used to remove a node
from the xskb pool list, it doesn't reinitialize the node pointers.
This means list_empty() will return false even after the node has been
removed, causing xp_free() to incorrectly skip adding the buffer to the
free list.

Fix this by using list_del_init() instead of list_del() in all fragment
handling paths, this ensures the list node is reinitialized after removal,
allowing the list_empty() to work correctly.

Fixes: b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node")
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-2-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 6 +++---
 net/xdp/xsk.c              | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 242e34f771cc..aefc368449d5 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -122,7 +122,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 		goto out;
 
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 		xp_free(pos);
 	}
 
@@ -157,7 +157,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
 					struct xdp_buff_xsk, list_node);
 	if (frag) {
-		list_del(&frag->list_node);
+		list_del_init(&frag->list_node);
 		ret = &frag->xdp;
 	}
 
@@ -168,7 +168,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	list_del(&xskb->list_node);
+	list_del_init(&xskb->list_node);
 }
 
 static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3b46bc635c43..be882a8d473c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -186,7 +186,7 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
 			goto err;
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From f7387d6579d65efd490a864254101cb665f2e7a7 Mon Sep 17 00:00:00 2001
From: "Nikhil P. Rao" <nikhil.rao@amd.com>
Date: Wed, 25 Feb 2026 00:00:27 +0000
Subject: xsk: Fix zero-copy AF_XDP fragment drop

AF_XDP should ensure that only a complete packet is sent to application.
In the zero-copy case, if the Rx queue gets full as fragments are being
enqueued, the remaining fragments are dropped.

For the multi-buffer case, add a check to ensure that the Rx queue has
enough space for all fragments of a packet before starting to enqueue
them.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-3-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xdp/xsk.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index be882a8d473c..6149f6a79897 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,25 +167,31 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	struct xdp_buff_xsk *pos, *tmp;
 	struct list_head *xskb_list;
 	u32 contd = 0;
+	u32 num_desc;
 	int err;
 
-	if (frags)
-		contd = XDP_PKT_CONTD;
+	if (likely(!frags)) {
+		err = __xsk_rcv_zc(xs, xskb, len, contd);
+		if (err)
+			goto err;
+		return 0;
+	}
 
-	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err)
+	contd = XDP_PKT_CONTD;
+	num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1;
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		err = -ENOBUFS;
 		goto err;
-	if (likely(!frags))
-		return 0;
+	}
 
+	__xsk_rcv_zc(xs, xskb, len, contd);
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
 		if (list_is_singular(xskb_list))
 			contd = 0;
 		len = pos->xdp.data_end - pos->xdp.data;
-		err = __xsk_rcv_zc(xs, pos, len, contd);
-		if (err)
-			goto err;
+		__xsk_rcv_zc(xs, pos, len, contd);
 		list_del_init(&pos->list_node);
 	}
 
-- 
cgit v1.2.3


From 74badb9c20b1a9c02a95c735c6d3cd6121679c93 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 26 Feb 2026 21:58:12 -0800
Subject: dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ
 handler

Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ
handler") introduces a range check for if_id to avoid an out-of-bounds
access. If an out-of-bounds if_id is detected, the interrupt status is
not cleared. This may result in an interrupt storm.

Clear the interrupt status after detecting an out-of-bounds if_id to avoid
the problem.

Found by an experimental AI code review agent at Google.

Fixes: 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler")
Cc: Junrui Luo <moonafterrain@outlook.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/20260227055812.1777915-1-linux@roeck-us.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index fc0e0f36186e..52c1cb9cb7e0 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 	if_id = (status & 0xFFFF0000) >> 16;
 	if (if_id >= ethsw->sw_attr.num_ifs) {
 		dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id);
-		goto out;
+		goto out_clear;
 	}
 	port_priv = ethsw->ports[if_id];
 
@@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 			dpaa2_switch_port_connect_mac(port_priv);
 	}
 
+out_clear:
 	err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    DPSW_IRQ_INDEX_IF, status);
 	if (err)
-- 
cgit v1.2.3


From 101bacb303e89dc2e0640ae6a5e0fb97c4eb45bb Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 25 Feb 2026 20:32:40 +0800
Subject: atm: lec: fix null-ptr-deref in lec_arp_clear_vccs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

syzkaller reported a null-ptr-deref in lec_arp_clear_vccs().
This issue can be easily reproduced using the syzkaller reproducer.

In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by
multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc).
When the underlying VCC is closed, lec_vcc_close() iterates over all
ARP entries and calls lec_arp_clear_vccs() for each matched entry.

For example, when lec_vcc_close() iterates through the hlists in
priv->lec_arp_empty_ones or other ARP tables:

1. In the first iteration, for the first matched ARP entry sharing the VCC,
lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back)
and sets vcc->user_back to NULL.
2. In the second iteration, for the next matched ARP entry sharing the same
VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from
vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it
via `vcc->pop = vpriv->old_pop`, leading to a null-ptr-deref crash.

Fix this by adding a null check for vpriv before dereferencing
it. If vpriv is already NULL, it means the VCC has been cleared
by a previous call, so we can safely skip the cleanup and just
clear the entry's vcc/recv_vcc pointers.

The entire cleanup block (including vcc_release_async()) is placed inside
the vpriv guard because a NULL vpriv indicates the VCC has already been
fully released by a prior iteration — repeating the teardown would
redundantly set flags and trigger callbacks on an already-closing socket.

The Fixes tag points to the initial commit because the entry->vcc path has
been vulnerable since the original code. The entry->recv_vcc path was later
added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back")
with the same pattern, and both paths are fixed here.

Reported-by: syzbot+72e3ea390c305de0e259@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68c95a83.050a0220.3c6139.0e5c.GAE@google.com/T/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260225123250.189289-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/lec.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index a107375c0629..fb93c6e1c329 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 		struct net_device *dev = (struct net_device *)vcc->proto_data;
 
-		vcc->pop = vpriv->old_pop;
-		if (vpriv->xoff)
-			netif_wake_queue(dev);
-		kfree(vpriv);
-		vcc->user_back = NULL;
-		vcc->push = entry->old_push;
-		vcc_release_async(vcc, -EPIPE);
+		if (vpriv) {
+			vcc->pop = vpriv->old_pop;
+			if (vpriv->xoff)
+				netif_wake_queue(dev);
+			kfree(vpriv);
+			vcc->user_back = NULL;
+			vcc->push = entry->old_push;
+			vcc_release_async(vcc, -EPIPE);
+		}
 		entry->vcc = NULL;
 	}
 	if (entry->recv_vcc) {
 		struct atm_vcc *vcc = entry->recv_vcc;
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 
-		kfree(vpriv);
-		vcc->user_back = NULL;
+		if (vpriv) {
+			kfree(vpriv);
+			vcc->user_back = NULL;
 
-		entry->recv_vcc->push = entry->old_recv_push;
-		vcc_release_async(entry->recv_vcc, -EPIPE);
+			entry->recv_vcc->push = entry->old_recv_push;
+			vcc_release_async(entry->recv_vcc, -EPIPE);
+		}
 		entry->recv_vcc = NULL;
 	}
 }
-- 
cgit v1.2.3


From 9197e5949a41cfb5d44a6b8a860766266340d558 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Sat, 28 Feb 2026 11:56:03 +0900
Subject: firewire: ohci: initialize page array to use alloc_pages_bulk()
 correctly

The call of alloc_pages_bulk() skips to fill entries of page array when
the entries already have values. While, 1394 OHCI PCI driver passes the
page array without initializing. It could cause invalid state at PFN
validation in vmap().

Fixes: f2ae92780ab9 ("firewire: ohci: split page allocation from dma mapping")
Reported-by: John Ogness <john.ogness@linutronix.de>
Reported-and-tested-by: Harald Arnesen <linux@skogtun.org>
Reported-and-tested-by: David Gow <david@davidgow.net>
Closes: https://lore.kernel.org/lkml/87tsv1vig5.fsf@jogness.linutronix.de/
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/firewire/ohci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 1c868c1e4a49..8153d62c58f0 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -848,7 +848,7 @@ static int ar_context_init(struct ar_context *ctx, struct fw_ohci *ohci,
 {
 	struct device *dev = ohci->card.device;
 	unsigned int i;
-	struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES];
+	struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES] = { NULL };
 	dma_addr_t dma_addrs[AR_BUFFERS];
 	void *vaddr;
 	struct descriptor *d;
-- 
cgit v1.2.3


From dff8e3c025862001956b8edb29c1287c9efcd902 Mon Sep 17 00:00:00 2001
From: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Date: Wed, 4 Feb 2026 10:51:40 +0530
Subject: cpupower: fix swapped power/energy unit labels

Fix error where microWatts and microJoules units were interchanged.

Signed-off-by: Kaushlendra Kumar <kaushlendra.kumar@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/powercap-info.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/power/cpupower/utils/powercap-info.c b/tools/power/cpupower/utils/powercap-info.c
index 3ea4486f1a0e..e53033488218 100644
--- a/tools/power/cpupower/utils/powercap-info.c
+++ b/tools/power/cpupower/utils/powercap-info.c
@@ -38,11 +38,11 @@ static int powercap_print_one_zone(struct powercap_zone *zone)
 	printf(" (%s)\n", mode ? "enabled" : "disabled");
 
 	if (zone->has_power_uw)
-		printf(_("%sPower can be monitored in micro Jules\n"),
+		printf(_("%sPower can be monitored in micro Watts\n"),
 		       pr_prefix);
 
 	if (zone->has_energy_uj)
-		printf(_("%sPower can be monitored in micro Watts\n"),
+		printf(_("%sPower can be monitored in micro Jules\n"),
 		       pr_prefix);
 
 	printf("\n");
-- 
cgit v1.2.3


From 147792c395db870756a0dc87ce656c75ae7ab7e8 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 26 Feb 2026 15:53:56 +0530
Subject: net: ti: icssg-prueth: Fix ping failure after offload mode setup when
 link speed is not 1G

When both eth interfaces with links up are added to a bridge or hsr
interface, ping fails if the link speed is not 1Gbps (e.g., 100Mbps).

The issue is seen because when switching to offload (bridge/hsr) mode,
prueth_emac_restart() restarts the firmware and clears DRAM with
memset_io(), setting all memory to 0. This includes PORT_LINK_SPEED_OFFSET
which firmware reads for link speed. The value 0 corresponds to
FW_LINK_SPEED_1G (0x00), so for 1Gbps links the default value is correct
and ping works. For 100Mbps links, the firmware needs FW_LINK_SPEED_100M
(0x01) but gets 0 instead, causing ping to fail. The function
emac_adjust_link() is called to reconfigure, but it detects no state change
(emac->link is still 1, speed/duplex match PHY) so new_state remains false
and icssg_config_set_speed() is never called to correct the firmware speed
value.

The fix resets emac->link to 0 before calling emac_adjust_link() in
prueth_emac_common_start(). This forces new_state=true, ensuring
icssg_config_set_speed() is called to write the correct speed value to
firmware memory.

Fixes: 06feac15406f ("net: ti: icssg-prueth: Fix emac link speed handling")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20260226102356.2141871-1-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 0939994c932f..42a881bee109 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -273,6 +273,14 @@ static int prueth_emac_common_start(struct prueth *prueth)
 		if (ret)
 			goto disable_class;
 
+		/* Reset link state to force reconfiguration in
+		 * emac_adjust_link(). Without this, if the link was already up
+		 * before restart, emac_adjust_link() won't detect any state
+		 * change and will skip critical configuration like writing
+		 * speed to firmware.
+		 */
+		emac->link = 0;
+
 		mutex_lock(&emac->ndev->phydev->lock);
 		emac_adjust_link(emac->ndev);
 		mutex_unlock(&emac->ndev->phydev->lock);
-- 
cgit v1.2.3


From 9439a661c2e80485406ce2c90b107ca17858382d Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Thu, 26 Feb 2026 22:37:53 +0530
Subject: amd-xgbe: fix MAC_TCR_SS register width for 2.5G and 10M speeds

Extend the MAC_TCR_SS (Speed Select) register field width from 2 bits
to 3 bits to properly support all speed settings.

The MAC_TCR register's SS field encoding requires 3 bits to represent
all supported speeds:
  - 0x00: 10Gbps (XGMII)
  - 0x02: 2.5Gbps (GMII) / 100Mbps
  - 0x03: 1Gbps / 10Mbps
  - 0x06: 2.5Gbps (XGMII) - P100a only

With only 2 bits, values 0x04-0x07 cannot be represented, which breaks
2.5G XGMII mode on newer platforms and causes incorrect speed select
values to be programmed.

Fixes: 07445f3c7ca1 ("amd-xgbe: Add support for 10 Mbps speed")
Co-developed-by: Guruvendra Punugupati <Guruvendra.Punugupati@amd.com>
Signed-off-by: Guruvendra Punugupati <Guruvendra.Punugupati@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260226170753.250312-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 711f295eb777..80c2c27ac9dc 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -431,7 +431,7 @@
 #define MAC_SSIR_SSINC_INDEX		16
 #define MAC_SSIR_SSINC_WIDTH		8
 #define MAC_TCR_SS_INDEX		29
-#define MAC_TCR_SS_WIDTH		2
+#define MAC_TCR_SS_WIDTH		3
 #define MAC_TCR_TE_INDEX		0
 #define MAC_TCR_TE_WIDTH		1
 #define MAC_TCR_VNE_INDEX		24
-- 
cgit v1.2.3


From 1ac22c8eae81366101597d48360718dff9b9d980 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Mon, 23 Feb 2026 15:27:28 -0800
Subject: scsi: core: Fix refcount leak for tagset_refcnt

This leak will cause a hang when tearing down the SCSI host. For example,
iscsid hangs with the following call trace:

[130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured

PID: 2528     TASK: ffff9d0408974e00  CPU: 3    COMMAND: "iscsid"
 #0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4
 #1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f
 #2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0
 #3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f
 #4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b
 #5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp]
 #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi]
 #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi]
 #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6
 #9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef

Fixes: 8fe4ce5836e9 ("scsi: core: Fix a use-after-free")
Cc: stable@vger.kernel.org
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223232728.93350-1-junxiao.bi@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_scan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 60c06fa4ec32..2cfcf1f5d6a4 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -361,6 +361,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * since we use this queue depth most of times.
 	 */
 	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
+		kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
 		put_device(&starget->dev);
 		kfree(sdev);
 		goto out;
-- 
cgit v1.2.3


From dbd53975ed4132d161b6a97ebe785a262380182d Mon Sep 17 00:00:00 2001
From: Ranjan Kumar <ranjan.kumar@broadcom.com>
Date: Wed, 25 Feb 2026 13:56:22 +0530
Subject: scsi: mpi3mr: Clear reset history on ready and recheck state after
 timeout

The driver retains reset history even after the IOC has successfully
reached the READY state. That leaves stale reset information active during
normal operation and can mislead recovery and diagnostics.  In addition, if
the IOC becomes READY just as the ready timeout loop exits, the driver
still follows the failure path and may retry or report failure incorrectly.

Clear reset history once READY is confirmed so driver state matches actual
IOC status. After the timeout loop, recheck the IOC state and treat READY
as success instead of failing.

Signed-off-by: Ranjan Kumar <ranjan.kumar@broadcom.com>
Link: https://patch.msgid.link/20260225082622.82588-1-ranjan.kumar@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr_fw.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 5875065e2849..c744210cc901 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -1618,6 +1618,7 @@ retry_bring_ioc_ready:
 			ioc_info(mrioc,
 			    "successfully transitioned to %s state\n",
 			    mpi3mr_iocstate_name(ioc_state));
+			mpi3mr_clear_reset_history(mrioc);
 			return 0;
 		}
 		ioc_status = readl(&mrioc->sysif_regs->ioc_status);
@@ -1637,6 +1638,15 @@ retry_bring_ioc_ready:
 		elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000;
 	} while (elapsed_time_sec < mrioc->ready_timeout);
 
+	ioc_state = mpi3mr_get_iocstate(mrioc);
+	if (ioc_state == MRIOC_STATE_READY) {
+		ioc_info(mrioc,
+		    "successfully transitioned to %s state after %llu seconds\n",
+		    mpi3mr_iocstate_name(ioc_state), elapsed_time_sec);
+		mpi3mr_clear_reset_history(mrioc);
+		return 0;
+	}
+
 out_failed:
 	elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000;
 	if ((retry < 2) && (elapsed_time_sec < (mrioc->ready_timeout - 60))) {
-- 
cgit v1.2.3


From 80bf3b28d32b431f84f244a8469488eb6d96afbb Mon Sep 17 00:00:00 2001
From: Florian Fuchs <fuchsfl@gmail.com>
Date: Fri, 27 Feb 2026 19:18:23 +0100
Subject: scsi: devinfo: Add BLIST_SKIP_IO_HINTS for Iomega ZIP

The Iomega ZIP 100 (Z100P2) can't process IO Advice Hints Grouping mode
page query. It immediately switches to the status phase 0xb8 after
receiving the subpage code 0x05 of MODE_SENSE_10 command, which fails
imm_out() and turns into DID_ERROR of this command, which leads to unusable
device. This was tested with an Iomega ZIP 100 (Z100P2) connected with a
StarTech PEX1P2 AX99100 PCIe parallel port card.

Prior to this fix, Test Unit Ready fails and the drive can't be used:
        IMM: returned SCSI status b8
        sd 7:0:6:0: [sdh] Test Unit Ready failed: Result: hostbyte=0x01 driverbyte=DRIVER_OK

Signed-off-by: Florian Fuchs <fuchsfl@gmail.com>
Link: https://patch.msgid.link/20260227181823.892932-1-fuchsfl@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_devinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index 0dada89d8d99..68a992494b12 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -190,7 +190,7 @@ static struct {
 	{"IBM", "2076", NULL, BLIST_NO_VPD_SIZE},
 	{"IBM", "2105", NULL, BLIST_RETRY_HWERROR},
 	{"iomega", "jaz 1GB", "J.86", BLIST_NOTQ | BLIST_NOLUN},
-	{"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN},
+	{"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN | BLIST_SKIP_IO_HINTS},
 	{"IOMEGA", "Io20S         *F", NULL, BLIST_KEY},
 	{"INSITE", "Floptical   F*8I", NULL, BLIST_KEY},
 	{"INSITE", "I325VM", NULL, BLIST_KEY},
-- 
cgit v1.2.3


From 14d4ac19d1895397532eec407433c5d74d9da53b Mon Sep 17 00:00:00 2001
From: Prithvi Tambewagh <activprithvi@gmail.com>
Date: Mon, 16 Feb 2026 11:50:02 +0530
Subject: scsi: target: Fix recursive locking in __configfs_open_file()

In flush_write_buffer, &p->frag_sem is acquired and then the loaded store
function is called, which, here, is target_core_item_dbroot_store().  This
function called filp_open(), following which these functions were called
(in reverse order), according to the call trace:

  down_read
  __configfs_open_file
  do_dentry_open
  vfs_open
  do_open
  path_openat
  do_filp_open
  file_open_name
  filp_open
  target_core_item_dbroot_store
  flush_write_buffer
  configfs_write_iter

target_core_item_dbroot_store() tries to validate the new file path by
trying to open the file path provided to it; however, in this case, the bug
report shows:

db_root: not a directory: /sys/kernel/config/target/dbroot

indicating that the same configfs file was tried to be opened, on which it
is currently working on. Thus, it is trying to acquire frag_sem semaphore
of the same file of which it already holds the semaphore obtained in
flush_write_buffer(), leading to acquiring the semaphore in a nested manner
and a possibility of recursive locking.

Fix this by modifying target_core_item_dbroot_store() to use kern_path()
instead of filp_open() to avoid opening the file using filesystem-specific
function __configfs_open_file(), and further modifying it to make this fix
compatible.

Reported-by: syzbot+f6e8174215573a84b797@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f6e8174215573a84b797
Tested-by: syzbot+f6e8174215573a84b797@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Prithvi Tambewagh <activprithvi@gmail.com>
Reviewed-by: Dmitry Bogdanov <d.bogdanov@yadro.com>
Link: https://patch.msgid.link/20260216062002.61937-1-activprithvi@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_configfs.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 17608ea39d5a..a1c91d4515bc 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -108,8 +108,8 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 					const char *page, size_t count)
 {
 	ssize_t read_bytes;
-	struct file *fp;
 	ssize_t r = -EINVAL;
+	struct path path = {};
 
 	mutex_lock(&target_devices_lock);
 	if (target_devices) {
@@ -131,17 +131,14 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 		db_root_stage[read_bytes - 1] = '\0';
 
 	/* validate new db root before accepting it */
-	fp = filp_open(db_root_stage, O_RDONLY, 0);
-	if (IS_ERR(fp)) {
+	r = kern_path(db_root_stage, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (r) {
 		pr_err("db_root: cannot open: %s\n", db_root_stage);
+		if (r == -ENOTDIR)
+			pr_err("db_root: not a directory: %s\n", db_root_stage);
 		goto unlock;
 	}
-	if (!S_ISDIR(file_inode(fp)->i_mode)) {
-		filp_close(fp, NULL);
-		pr_err("db_root: not a directory: %s\n", db_root_stage);
-		goto unlock;
-	}
-	filp_close(fp, NULL);
+	path_put(&path);
 
 	strscpy(db_root, db_root_stage);
 	pr_debug("Target_Core_ConfigFS: db_root set to %s\n", db_root);
-- 
cgit v1.2.3


From 4478e8eeb87120c11e90041864c2233238b2155a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 26 Feb 2026 11:17:49 -0800
Subject: lib/crypto: tests: Depend on library options rather than selecting
 them

The convention for KUnit tests is to have the test kconfig options
visible only when the code they depend on is already enabled.  This way
only the tests that are relevant to the particular kernel build can be
enabled, either manually or via KUNIT_ALL_TESTS.

Update lib/crypto/tests/Kconfig to follow that convention, i.e. depend
on the corresponding library options rather than selecting them.  This
fixes an issue where enabling KUNIT_ALL_TESTS enabled non-test code.

This does mean that it becomes a bit more difficult to enable *all* the
crypto library tests (which is what I do as a maintainer of the code),
since doing so will now require enabling other options that select the
libraries.  Regardless, we should follow the standard KUnit convention.
I'll also add a .kunitconfig file that does enable all these options.

Note: currently most of the crypto library options are selected by
visible options in crypto/Kconfig, which can be used to enable them
without too much trouble.  If in the future we end up with more cases
like CRYPTO_LIB_CURVE25519 which is selected only by WIREGUARD (thus
making CRYPTO_LIB_CURVE25519_KUNIT_TEST effectively depend on WIREGUARD
after this commit), we could consider adding a new kconfig option that
enables all the library code specifically for testing.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/r/CAMuHMdULzMdxuTVfg8_4jdgzbzjfx-PHkcgbGSthcUx_sHRNMg@mail.gmail.com
Fixes: 4dcf6caddaa0 ("lib/crypto: tests: Add KUnit tests for SHA-224 and SHA-256")
Fixes: 571eaeddb67d ("lib/crypto: tests: Add KUnit tests for SHA-384 and SHA-512")
Fixes: 6dd4d9f7919e ("lib/crypto: tests: Add KUnit tests for Poly1305")
Fixes: 66b130607908 ("lib/crypto: tests: Add KUnit tests for SHA-1 and HMAC-SHA1")
Fixes: d6b6aac0cdb4 ("lib/crypto: tests: Add KUnit tests for MD5 and HMAC-MD5")
Fixes: afc4e4a5f122 ("lib/crypto: tests: Migrate Curve25519 self-test to KUnit")
Fixes: 6401fd334ddf ("lib/crypto: tests: Add KUnit tests for BLAKE2b")
Fixes: 15c64c47e484 ("lib/crypto: tests: Add SHA3 kunit tests")
Fixes: b3aed551b3fc ("lib/crypto: tests: Add KUnit tests for POLYVAL")
Fixes: ed894faccb8d ("lib/crypto: tests: Add KUnit tests for ML-DSA verification")
Fixes: 7246fe6cd644 ("lib/crypto: tests: Add KUnit tests for NH")
Cc: stable@vger.kernel.org
Reviewed-by: David Gow <david@davidgow.net>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260226191749.39397-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/tests/Kconfig | 35 ++++++++++++-----------------------
 1 file changed, 12 insertions(+), 23 deletions(-)

diff --git a/lib/crypto/tests/Kconfig b/lib/crypto/tests/Kconfig
index 4970463ea0aa..0de289b429a9 100644
--- a/lib/crypto/tests/Kconfig
+++ b/lib/crypto/tests/Kconfig
@@ -2,10 +2,9 @@
 
 config CRYPTO_LIB_BLAKE2B_KUNIT_TEST
 	tristate "KUnit tests for BLAKE2b" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_BLAKE2B
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_BLAKE2B
 	help
 	  KUnit tests for the BLAKE2b cryptographic hash function.
 
@@ -14,71 +13,64 @@ config CRYPTO_LIB_BLAKE2S_KUNIT_TEST
 	depends on KUNIT
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	# No need to select CRYPTO_LIB_BLAKE2S here, as that option doesn't
+	# No need to depend on CRYPTO_LIB_BLAKE2S here, as that option doesn't
 	# exist; the BLAKE2s code is always built-in for the /dev/random driver.
 	help
 	  KUnit tests for the BLAKE2s cryptographic hash function.
 
 config CRYPTO_LIB_CURVE25519_KUNIT_TEST
 	tristate "KUnit tests for Curve25519" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_CURVE25519
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_CURVE25519
 	help
 	  KUnit tests for the Curve25519 Diffie-Hellman function.
 
 config CRYPTO_LIB_MD5_KUNIT_TEST
 	tristate "KUnit tests for MD5" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_MD5
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_MD5
 	help
 	  KUnit tests for the MD5 cryptographic hash function and its
 	  corresponding HMAC.
 
 config CRYPTO_LIB_MLDSA_KUNIT_TEST
 	tristate "KUnit tests for ML-DSA" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_MLDSA
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_MLDSA
 	help
 	  KUnit tests for the ML-DSA digital signature algorithm.
 
 config CRYPTO_LIB_NH_KUNIT_TEST
 	tristate "KUnit tests for NH" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_NH
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
-	select CRYPTO_LIB_NH
 	help
 	  KUnit tests for the NH almost-universal hash function.
 
 config CRYPTO_LIB_POLY1305_KUNIT_TEST
 	tristate "KUnit tests for Poly1305" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_POLY1305
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_POLY1305
 	help
 	  KUnit tests for the Poly1305 library functions.
 
 config CRYPTO_LIB_POLYVAL_KUNIT_TEST
 	tristate "KUnit tests for POLYVAL" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_POLYVAL
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_POLYVAL
 	help
 	  KUnit tests for the POLYVAL library functions.
 
 config CRYPTO_LIB_SHA1_KUNIT_TEST
 	tristate "KUnit tests for SHA-1" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA1
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA1
 	help
 	  KUnit tests for the SHA-1 cryptographic hash function and its
 	  corresponding HMAC.
@@ -87,10 +79,9 @@ config CRYPTO_LIB_SHA1_KUNIT_TEST
 # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA256).
 config CRYPTO_LIB_SHA256_KUNIT_TEST
 	tristate "KUnit tests for SHA-224 and SHA-256" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA256
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA256
 	help
 	  KUnit tests for the SHA-224 and SHA-256 cryptographic hash functions
 	  and their corresponding HMACs.
@@ -99,20 +90,18 @@ config CRYPTO_LIB_SHA256_KUNIT_TEST
 # included, for consistency with the naming used elsewhere (e.g. CRYPTO_SHA512).
 config CRYPTO_LIB_SHA512_KUNIT_TEST
 	tristate "KUnit tests for SHA-384 and SHA-512" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA512
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA512
 	help
 	  KUnit tests for the SHA-384 and SHA-512 cryptographic hash functions
 	  and their corresponding HMACs.
 
 config CRYPTO_LIB_SHA3_KUNIT_TEST
 	tristate "KUnit tests for SHA-3" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && CRYPTO_LIB_SHA3
 	default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS
 	select CRYPTO_LIB_BENCHMARK_VISIBLE
-	select CRYPTO_LIB_SHA3
 	help
 	  KUnit tests for the SHA3 cryptographic hash and XOF functions,
 	  including SHA3-224, SHA3-256, SHA3-384, SHA3-512, SHAKE128 and
-- 
cgit v1.2.3


From 48a5c36577ebe0144f8ede70e59b59ea18b75089 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sat, 28 Feb 2026 01:48:19 +0800
Subject: iio: adc: ti-ads1119: Fix unbalanced pm reference count in
 ds1119_single_conversion()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In ads1119_single_conversion(), if pm_runtime_resume_and_get() fails,
the code jumps to the pdown label, which calls
pm_runtime_put_autosuspend().

Since pm_runtime_resume_and_get() automatically decrements the usage
counter on failure, the subsequent call to pm_runtime_put_autosuspend()
causes an unbalanced reference counter.

Fixes: a9306887eba4 ("iio: adc: ti-ads1119: Add driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: João Paulo Gonçalves <jpaulo.silvagoncalves@gmail.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads1119.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c
index c9cedc59cdcd..4454f28b2b58 100644
--- a/drivers/iio/adc/ti-ads1119.c
+++ b/drivers/iio/adc/ti-ads1119.c
@@ -274,7 +274,7 @@ static int ads1119_single_conversion(struct ads1119_state *st,
 
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
-		goto pdown;
+		return ret;
 
 	ret = ads1119_configure_channel(st, mux, gain, datarate);
 	if (ret)
-- 
cgit v1.2.3


From c53bca092486809d266b5921b9e6f9df2688fc26 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Fri, 27 Feb 2026 21:54:29 +0800
Subject: iio: pressure: abp2030pa: Remove IRQF_ONESHOT from devm_request_irq()

Since commit aef30c8d569c ("genirq: Warn about using IRQF_ONESHOT
without a threaded handler"), the IRQ core checks IRQF_ONESHOT flag
in IRQ request and gives a warning if there is no threaded handler.

Remove IRQF_ONESHOT from devm_request_irq().

Fixes: 47d323ce1e89 ("iio: pressure: add Honeywell ABP2 driver")
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Tested-by: Petre Rodan <petre.rodan@subdimension.ro>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/abp2030pa.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/pressure/abp2030pa.c b/drivers/iio/pressure/abp2030pa.c
index 4ca056a73cef..b44f1bf4c633 100644
--- a/drivers/iio/pressure/abp2030pa.c
+++ b/drivers/iio/pressure/abp2030pa.c
@@ -520,7 +520,7 @@ int abp2_common_probe(struct device *dev, const struct abp2_ops *ops, int irq)
 	data->p_offset = div_s64(odelta * data->pmin, pdelta) - data->outmin;
 
 	if (data->irq > 0) {
-		ret = devm_request_irq(dev, irq, abp2_eoc_handler, IRQF_ONESHOT,
+		ret = devm_request_irq(dev, irq, abp2_eoc_handler, 0,
 				       dev_name(dev), data);
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From 0206dd36418c104c0b3dea4ed7047e21eccb30b0 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 27 Feb 2026 15:33:30 +0200
Subject: iio: adc: ade9000: move mutex init before IRQ registration

Move devm_mutex_init() before ade9000_request_irq() calls so that
st->lock is initialized before any handler that depends on it can run.

Fixes: 81de7b4619fc ("iio: adc: add ade9000 support")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ade9000.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/adc/ade9000.c b/drivers/iio/adc/ade9000.c
index db085dc5e526..c62c6480dd0a 100644
--- a/drivers/iio/adc/ade9000.c
+++ b/drivers/iio/adc/ade9000.c
@@ -1706,19 +1706,19 @@ static int ade9000_probe(struct spi_device *spi)
 
 	init_completion(&st->reset_completion);
 
-	ret = ade9000_request_irq(dev, "irq0", ade9000_irq0_thread, indio_dev);
+	ret = devm_mutex_init(dev, &st->lock);
 	if (ret)
 		return ret;
 
-	ret = ade9000_request_irq(dev, "irq1", ade9000_irq1_thread, indio_dev);
+	ret = ade9000_request_irq(dev, "irq0", ade9000_irq0_thread, indio_dev);
 	if (ret)
 		return ret;
 
-	ret = ade9000_request_irq(dev, "dready", ade9000_dready_thread, indio_dev);
+	ret = ade9000_request_irq(dev, "irq1", ade9000_irq1_thread, indio_dev);
 	if (ret)
 		return ret;
 
-	ret = devm_mutex_init(dev, &st->lock);
+	ret = ade9000_request_irq(dev, "dready", ade9000_dready_thread, indio_dev);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From bd66aa1c8b8cabf459064a46d3430a5ec5138418 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 27 Feb 2026 14:43:05 +0200
Subject: iio: accel: adxl380: fix FIFO watermark bit 8 always written as 0

FIELD_PREP(BIT(0), fifo_samples & BIT(8)) produces either 0 or 256,
and since FIELD_PREP masks to bit 0, 256 & 1 evaluates to 0. Use !!
to convert the result to a proper 0-or-1 value.

Fixes: df36de13677a ("iio: accel: add ADXL380 driver")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl380.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/accel/adxl380.c b/drivers/iio/accel/adxl380.c
index 8fab2fdbe147..a51d1d61c412 100644
--- a/drivers/iio/accel/adxl380.c
+++ b/drivers/iio/accel/adxl380.c
@@ -877,7 +877,7 @@ static int adxl380_set_fifo_samples(struct adxl380_state *st)
 	ret = regmap_update_bits(st->regmap, ADXL380_FIFO_CONFIG_0_REG,
 				 ADXL380_FIFO_SAMPLES_8_MSK,
 				 FIELD_PREP(ADXL380_FIFO_SAMPLES_8_MSK,
-					    (fifo_samples & BIT(8))));
+					    !!(fifo_samples & BIT(8))));
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 86133fb1ec36b2f5cec29d71fbae84877c3a1358 Mon Sep 17 00:00:00 2001
From: Giorgi Tchankvetadze <giorgitchankvetadze1997@gmail.com>
Date: Thu, 26 Feb 2026 18:07:02 +0400
Subject: iio: adc: ade9000: fix wrong register in CALIBBIAS case for active
 power

The switch statement in ade9000_write_raw() attempts to match
chan->address against ADE9000_REG_AWATTOS (0x00F) to dispatch
the calibration offset write for active power channels. However,
chan->address is set via ADE9000_ADDR_ADJUST(ADE9000_REG_AWATT,
num), so after masking the phase bits, tmp holds
ADE9000_REG_AWATT (0x210), which never matches 0x00F.

As a result, writing IIO_CHAN_INFO_CALIBBIAS for IIO_POWER always
falls through to the default case and returns -EINVAL, making
active power offset calibration silently broken.

Fix this by matching against ADE9000_REG_AWATT instead, which is
the actual base address stored in chan->address for watt channels.

Reference:ADE9000 datasheet (Rev. B), AWATTOS is the offset correction
register at 0x00F (p. 44), while AWATT is the total active power
register at 0x210 (p. 48).

Fixes: 81de7b4619fc ("iio: adc: add ade9000 support")
Signed-off-by: Giorgi Tchankvetadze <giorgitchankvetadze1997@gmail.com>
Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ade9000.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ade9000.c b/drivers/iio/adc/ade9000.c
index c62c6480dd0a..945a159e5de6 100644
--- a/drivers/iio/adc/ade9000.c
+++ b/drivers/iio/adc/ade9000.c
@@ -1123,7 +1123,7 @@ static int ade9000_write_raw(struct iio_dev *indio_dev,
 			tmp &= ~ADE9000_PHASE_C_POS_BIT;
 
 			switch (tmp) {
-			case ADE9000_REG_AWATTOS:
+			case ADE9000_REG_AWATT:
 				return regmap_write(st->regmap,
 						    ADE9000_ADDR_ADJUST(ADE9000_REG_AWATTOS,
 									chan->channel), val);
-- 
cgit v1.2.3


From 57b207e38d414a27fda9fff638a0d3e7ef16b917 Mon Sep 17 00:00:00 2001
From: Giorgi Tchankvetadze <giorgitchankvetadze1997@gmail.com>
Date: Tue, 24 Feb 2026 17:23:55 +0400
Subject: iio: adc: ade9000: fix wrong return type in streaming push

The else branch of ade9000_iio_push_streaming() incorrectly returns
IRQ_HANDLED on regmap_write failure. This function returns int (0 on
success, negative errno on failure), so IRQ_HANDLED (1) would be
misinterpreted as a non-error by callers.

Return ret instead, consistent with every other error path in the
function.

Fixes: 81de7b4619fc ("iio: adc: add ade9000 support")
Signed-off-by: Giorgi Tchankvetadze <giorgitchankvetadze1997@gmail.com>
Reviewed-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ade9000.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ade9000.c b/drivers/iio/adc/ade9000.c
index 945a159e5de6..1abbfdfcd554 100644
--- a/drivers/iio/adc/ade9000.c
+++ b/drivers/iio/adc/ade9000.c
@@ -787,7 +787,7 @@ static int ade9000_iio_push_streaming(struct iio_dev *indio_dev)
 				   ADE9000_MIDDLE_PAGE_BIT);
 		if (ret) {
 			dev_err_ratelimited(dev, "IRQ0 WFB write fail");
-			return IRQ_HANDLED;
+			return ret;
 		}
 
 		ade9000_configure_scan(indio_dev, ADE9000_REG_WF_BUFF);
-- 
cgit v1.2.3


From b403981da8a26f57f07859a9704392b1183e2a6e Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Wed, 25 Feb 2026 22:48:57 +0800
Subject: iio: dac: mcp47feb02: Fix mutex used before initialization

The mcp47feb02_parse_fw() function uses data->lock, but the mutex was
initialized after this function in probe path.

Since mcp47feb02_parse_fw() is only called from probe(), remove the lock.

Fixes: bf394cc80369 ("iio: dac: adding support for Microchip MCP47FEB02")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/mcp47feb02.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/iio/dac/mcp47feb02.c b/drivers/iio/dac/mcp47feb02.c
index b218f0c3a0bd..08fb85359697 100644
--- a/drivers/iio/dac/mcp47feb02.c
+++ b/drivers/iio/dac/mcp47feb02.c
@@ -955,8 +955,6 @@ static int mcp47feb02_parse_fw(struct iio_dev *indio_dev,
 	u32 num_channels;
 	u8 chan_idx = 0;
 
-	guard(mutex)(&data->lock);
-
 	num_channels = device_get_child_node_count(dev);
 	if (num_channels > chip_features->phys_channels)
 		return dev_err_probe(dev, -EINVAL, "More channels than the chip supports\n");
-- 
cgit v1.2.3


From 630748afa7030b272b7bee5df857e7bcf132ed51 Mon Sep 17 00:00:00 2001
From: Francesco Lavra <flavra@baylibre.com>
Date: Wed, 25 Feb 2026 11:06:00 +0100
Subject: iio: imu: st_lsm6dsx: Set FIFO ODR for accelerometer and gyroscope
 only

The st_lsm6dsx_set_fifo_odr() function, which is called when enabling and
disabling the hardware FIFO, checks the contents of the hw->settings->batch
array at index sensor->id, and then sets the current ODR value in sensor
registers that depend on whether the register address is set in the above
array element. This logic is valid for internal sensors only, i.e. the
accelerometer and gyroscope; however, since commit c91c1c844ebd ("iio: imu:
st_lsm6dsx: add i2c embedded controller support"), this function is called
also when configuring the hardware FIFO for external sensors (i.e. sensors
accessed through the sensor hub functionality), which can result in
unrelated device registers being written.

Add a check to the beginning of st_lsm6dsx_set_fifo_odr() so that it does
not touch any registers unless it is called for internal sensors.

Fixes: c91c1c844ebd ("iio: imu: st_lsm6dsx: add i2c embedded controller support")
Signed-off-by: Francesco Lavra <flavra@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 55d877745575..1ee2fc5f5f1f 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -225,6 +225,10 @@ static int st_lsm6dsx_set_fifo_odr(struct st_lsm6dsx_sensor *sensor,
 	const struct st_lsm6dsx_reg *batch_reg;
 	u8 data;
 
+	/* Only internal sensors have a FIFO ODR configuration register. */
+	if (sensor->id >= ARRAY_SIZE(hw->settings->batch))
+		return 0;
+
 	batch_reg = &hw->settings->batch[sensor->id];
 	if (batch_reg->addr) {
 		int val;
-- 
cgit v1.2.3


From 679c04c10d65d32a3f269e696b22912ff0a001b9 Mon Sep 17 00:00:00 2001
From: Francesco Lavra <flavra@baylibre.com>
Date: Wed, 25 Feb 2026 11:06:01 +0100
Subject: iio: imu: st_lsm6dsx: Set buffer sampling frequency for accelerometer
 only

The st_lsm6dsx_hwfifo_odr_store() function, which is called when userspace
writes the buffer sampling frequency sysfs attribute, calls
st_lsm6dsx_check_odr(), which accesses the odr_table array at index
`sensor->id`; since this array is only 2 entries long, an access for any
sensor type other than accelerometer or gyroscope is an out-of-bounds
access.

The motivation for being able to set a buffer frequency different from the
sensor sampling frequency is to support use cases that need accurate event
detection (which requires a high sampling frequency) while retrieving
sensor data at low frequency. Since all the supported event types are
generated from acceleration data only, do not create the buffer sampling
frequency attribute for sensor types other than the accelerometer.

Fixes: 6b648a36c200 ("iio: imu: st_lsm6dsx: Decouple sensor ODR from FIFO batch data rate")
Signed-off-by: Francesco Lavra <flavra@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
index 1ee2fc5f5f1f..5b28a3ffcc3d 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c
@@ -862,12 +862,21 @@ int st_lsm6dsx_fifo_setup(struct st_lsm6dsx_hw *hw)
 	int i, ret;
 
 	for (i = 0; i < ST_LSM6DSX_ID_MAX; i++) {
+		const struct iio_dev_attr **attrs;
+
 		if (!hw->iio_devs[i])
 			continue;
 
+		/*
+		 * For the accelerometer, allow setting FIFO sampling frequency
+		 * values different from the sensor sampling frequency, which
+		 * may be needed to keep FIFO data rate low while sampling
+		 * acceleration data at high rates for accurate event detection.
+		 */
+		attrs = i == ST_LSM6DSX_ID_ACC ? st_lsm6dsx_buffer_attrs : NULL;
 		ret = devm_iio_kfifo_buffer_setup_ext(hw->dev, hw->iio_devs[i],
 						      &st_lsm6dsx_buffer_ops,
-						      st_lsm6dsx_buffer_attrs);
+						      attrs);
 		if (ret)
 			return ret;
 	}
-- 
cgit v1.2.3


From edb11a1aef4011a4b7b22cc3c3396c6fe371f4a6 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Tue, 24 Feb 2026 16:48:15 -0600
Subject: iio: gyro: mpu3050: Fix incorrect free_irq() variable

The handler for the IRQ part of this driver is mpu3050->trig but,
in the teardown free_irq() is called with handler mpu3050.

Use correct IRQ handler when calling free_irq().

Fixes: 3904b28efb2c7 ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index 317e7b217ec6..8df1f524d342 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -1269,7 +1269,7 @@ void mpu3050_common_remove(struct device *dev)
 	pm_runtime_disable(dev);
 	iio_triggered_buffer_cleanup(indio_dev);
 	if (mpu3050->irq)
-		free_irq(mpu3050->irq, mpu3050);
+		free_irq(mpu3050->irq, mpu3050->trig);
 	iio_device_unregister(indio_dev);
 	mpu3050_power_down(mpu3050);
 }
-- 
cgit v1.2.3


From 4216db1043a3be72ef9c2b7b9f393d7fa72496e6 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Tue, 24 Feb 2026 16:48:16 -0600
Subject: iio: gyro: mpu3050: Fix irq resource leak

The interrupt handler is setup but only a few lines down if
iio_trigger_register() fails the function returns without properly
releasing the handler.

Add cleanup goto to resolve resource leak.

Detected by Smatch:
drivers/iio/gyro/mpu3050-core.c:1128 mpu3050_trigger_probe() warn:
'irq' from request_threaded_irq() not released on lines: 1124.

Fixes: 3904b28efb2c7 ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index 8df1f524d342..d2f0899ac46b 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -1129,11 +1129,16 @@ static int mpu3050_trigger_probe(struct iio_dev *indio_dev, int irq)
 
 	ret = iio_trigger_register(mpu3050->trig);
 	if (ret)
-		return ret;
+		goto err_iio_trigger;
 
 	indio_dev->trig = iio_trigger_get(mpu3050->trig);
 
 	return 0;
+
+err_iio_trigger:
+	free_irq(mpu3050->irq, mpu3050->trig);
+
+	return ret;
 }
 
 int mpu3050_common_probe(struct device *dev,
-- 
cgit v1.2.3


From 4c05799449108fb0e0a6bd30e65fffc71e60db4d Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Tue, 24 Feb 2026 16:48:17 -0600
Subject: iio: gyro: mpu3050: Move iio_device_register() to correct location

iio_device_register() should be at the end of the probe function to
prevent race conditions.

Place iio_device_register() at the end of the probe function and place
iio_device_unregister() accordingly.

Fixes: 3904b28efb2c7 ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Suggested-by: Jonathan Cameron <jic23@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index d2f0899ac46b..2e92daf047bd 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -1226,12 +1226,6 @@ int mpu3050_common_probe(struct device *dev,
 		goto err_power_down;
 	}
 
-	ret = iio_device_register(indio_dev);
-	if (ret) {
-		dev_err(dev, "device register failed\n");
-		goto err_cleanup_buffer;
-	}
-
 	dev_set_drvdata(dev, indio_dev);
 
 	/* Check if we have an assigned IRQ to use as trigger */
@@ -1254,9 +1248,20 @@ int mpu3050_common_probe(struct device *dev,
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_put(dev);
 
+	ret = iio_device_register(indio_dev);
+	if (ret) {
+		dev_err(dev, "device register failed\n");
+		goto err_iio_device_register;
+	}
+
 	return 0;
 
-err_cleanup_buffer:
+err_iio_device_register:
+	pm_runtime_get_sync(dev);
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	if (irq)
+		free_irq(mpu3050->irq, mpu3050->trig);
 	iio_triggered_buffer_cleanup(indio_dev);
 err_power_down:
 	mpu3050_power_down(mpu3050);
@@ -1269,13 +1274,13 @@ void mpu3050_common_remove(struct device *dev)
 	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 	struct mpu3050 *mpu3050 = iio_priv(indio_dev);
 
+	iio_device_unregister(indio_dev);
 	pm_runtime_get_sync(dev);
 	pm_runtime_put_noidle(dev);
 	pm_runtime_disable(dev);
 	iio_triggered_buffer_cleanup(indio_dev);
 	if (mpu3050->irq)
 		free_irq(mpu3050->irq, mpu3050->trig);
-	iio_device_unregister(indio_dev);
 	mpu3050_power_down(mpu3050);
 }
 
-- 
cgit v1.2.3


From d14116f6529fa085b1a1b1f224dc9604e4d2a29c Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Tue, 24 Feb 2026 16:48:18 -0600
Subject: iio: gyro: mpu3050: Fix out-of-sequence free_irq()

The triggered buffer is initialized before the IRQ is requested. The
removal path currently calls iio_triggered_buffer_cleanup() before
free_irq(). This violates the expected LIFO.

Place free_irq() in the correct location relative to
iio_triggered_buffer_cleanup().

Fixes: 3904b28efb2c7 ("iio: gyro: Add driver for the MPU-3050 gyroscope")
Suggested-by: Jonathan Cameron <jic23@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/gyro/mpu3050-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index 2e92daf047bd..d84e04e4b431 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -1278,9 +1278,9 @@ void mpu3050_common_remove(struct device *dev)
 	pm_runtime_get_sync(dev);
 	pm_runtime_put_noidle(dev);
 	pm_runtime_disable(dev);
-	iio_triggered_buffer_cleanup(indio_dev);
 	if (mpu3050->irq)
 		free_irq(mpu3050->irq, mpu3050->trig);
+	iio_triggered_buffer_cleanup(indio_dev);
 	mpu3050_power_down(mpu3050);
 }
 
-- 
cgit v1.2.3


From 20c2a46da4c65ac9c84f2876e2369a260b50e95b Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Feb 2026 14:45:13 +0800
Subject: iio: adc: ad4062: Replace IRQF_ONESHOT with IRQF_NO_THREAD

In ad4062_request_irq(), when request irq for "gp1", the code uses
IRQF_ONESHOT flag, which is not appropriate for a primary handler
that does not have a secondary threaded handler.

And since commit aef30c8d569c ("genirq: Warn about using IRQF_ONESHOT
without a threaded handler"), the IRQ core checks IRQF_ONESHOT flag
in IRQ request and gives a warning if there is no threaded handler.

Since there is no threaded handler, replace devm_request_threaded_irq
with devm_request_irq, and replace IRQF_ONESHOT with IRQF_NO_THREAD.

Also remove an extraneous semicolon at the end of
ad4062_write_raw_dispatch().

Found by code review, compile pass.

Fixes: d5284402d28f ("iio: adc: Add support for ad4062")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad4062.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/adc/ad4062.c b/drivers/iio/adc/ad4062.c
index dd4ad32aa6f5..8b03736d55fc 100644
--- a/drivers/iio/adc/ad4062.c
+++ b/drivers/iio/adc/ad4062.c
@@ -719,10 +719,8 @@ static int ad4062_request_irq(struct iio_dev *indio_dev)
 	}
 	st->gpo_irq[1] = true;
 
-	return devm_request_threaded_irq(dev, ret,
-					 ad4062_irq_handler_drdy,
-					 NULL, IRQF_ONESHOT, indio_dev->name,
-					 indio_dev);
+	return devm_request_irq(dev, ret, ad4062_irq_handler_drdy,
+				IRQF_NO_THREAD, indio_dev->name, indio_dev);
 }
 
 static const struct iio_trigger_ops ad4062_trigger_ops = {
@@ -955,7 +953,7 @@ static int ad4062_write_raw_dispatch(struct ad4062_state *st, int val, int val2,
 	default:
 		return -EINVAL;
 	}
-};
+}
 
 static int ad4062_write_raw(struct iio_dev *indio_dev,
 			    struct iio_chan_spec const *chan, int val,
-- 
cgit v1.2.3


From c47ac75f5f24020cc0c8b835457a7637ad450939 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 20 Feb 2026 14:45:14 -0800
Subject: iio: hid-sensors: Use software trigger

Recent changes linux mainline resulted in warning:
"genirq: Warn about using IRQF_ONESHOT without a threaded handler"
when HID sensor hub is used.

When INDIO_BUFFER_TRIGGERED is used, the core attaches a poll function
when enabling the buffer. This poll function uses request_threaded_irq()
with both bottom half and top half handlers. But when using HID
sensor hub, bottom half (thread handler) is not registered.

In HID sensors, once a sensor is powered on, the hub collects samples
and pushes data to the host when programmed thresholds are met. When
this data is received for a sensor, it is pushed using
iio_push_to_buffers_with_ts().

The sensor is powered ON or OFF based on the trigger callback
set_trigger_state() when the poll function is attached. During the call
to iio_triggered_buffer_setup_ext(), the HID sensor specifies only a
handler function but provides no thread handler, as there is no data
to read from the hub in thread context. Internally, this results in
calling request_threaded_irq(). Recent kernel changes now warn when
request_threaded_irq() is called without a thread handler.

To address this issue, fundamental changes are required to avoid using
iio_triggered_buffer_setup_ext(). HID sensors can use
INDIO_BUFFER_SOFTWARE instead of INDIO_BUFFER_TRIGGERED, as this can
work in trigger-less mode.

In this approach, when user space opens the buffer, the sensor is powered
on, and when the buffer is closed, the sensor is powered off using
iio_buffer_setup_ops callbacks.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 .../iio/common/hid-sensors/hid-sensor-trigger.c    | 48 ++++++++++++++--------
 1 file changed, 30 insertions(+), 18 deletions(-)

diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 5540e2d28f4a..417c4ab8c1b2 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -14,6 +14,7 @@
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/sysfs.h>
+#include <linux/iio/kfifo_buf.h>
 #include "hid-sensor-trigger.h"
 
 static ssize_t _hid_sensor_set_report_latency(struct device *dev,
@@ -202,12 +203,21 @@ static void hid_sensor_set_power_work(struct work_struct *work)
 		_hid_sensor_power_state(attrb, true);
 }
 
-static int hid_sensor_data_rdy_trigger_set_state(struct iio_trigger *trig,
-						bool state)
+static int buffer_postenable(struct iio_dev *indio_dev)
 {
-	return hid_sensor_power_state(iio_trigger_get_drvdata(trig), state);
+	return hid_sensor_power_state(iio_device_get_drvdata(indio_dev), 1);
 }
 
+static int buffer_predisable(struct iio_dev *indio_dev)
+{
+	return hid_sensor_power_state(iio_device_get_drvdata(indio_dev), 0);
+}
+
+static const struct iio_buffer_setup_ops hid_sensor_buffer_ops = {
+	.postenable = buffer_postenable,
+	.predisable = buffer_predisable,
+};
+
 void hid_sensor_remove_trigger(struct iio_dev *indio_dev,
 			       struct hid_sensor_common *attrb)
 {
@@ -219,14 +229,9 @@ void hid_sensor_remove_trigger(struct iio_dev *indio_dev,
 	cancel_work_sync(&attrb->work);
 	iio_trigger_unregister(attrb->trigger);
 	iio_trigger_free(attrb->trigger);
-	iio_triggered_buffer_cleanup(indio_dev);
 }
 EXPORT_SYMBOL_NS(hid_sensor_remove_trigger, "IIO_HID");
 
-static const struct iio_trigger_ops hid_sensor_trigger_ops = {
-	.set_trigger_state = &hid_sensor_data_rdy_trigger_set_state,
-};
-
 int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name,
 				struct hid_sensor_common *attrb)
 {
@@ -239,25 +244,34 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name,
 	else
 		fifo_attrs = NULL;
 
-	ret = iio_triggered_buffer_setup_ext(indio_dev,
-					     &iio_pollfunc_store_time, NULL,
-					     IIO_BUFFER_DIRECTION_IN,
-					     NULL, fifo_attrs);
+	indio_dev->modes = INDIO_DIRECT_MODE | INDIO_HARDWARE_TRIGGERED;
+
+	ret = devm_iio_kfifo_buffer_setup_ext(&indio_dev->dev, indio_dev,
+					      &hid_sensor_buffer_ops,
+					      fifo_attrs);
 	if (ret) {
-		dev_err(&indio_dev->dev, "Triggered Buffer Setup Failed\n");
+		dev_err(&indio_dev->dev, "Kfifo Buffer Setup Failed\n");
 		return ret;
 	}
 
+	/*
+	 * The current user space in distro "iio-sensor-proxy" is not working in
+	 * trigerless mode and it expects
+	 * /sys/bus/iio/devices/iio:device0/trigger/current_trigger.
+	 * The change replacing iio_triggered_buffer_setup_ext() with
+	 * devm_iio_kfifo_buffer_setup_ext() will not create attribute without
+	 * registering a trigger with INDIO_HARDWARE_TRIGGERED.
+	 * So the below code fragment is still required.
+	 */
+
 	trig = iio_trigger_alloc(indio_dev->dev.parent,
 				 "%s-dev%d", name, iio_device_id(indio_dev));
 	if (trig == NULL) {
 		dev_err(&indio_dev->dev, "Trigger Allocate Failed\n");
-		ret = -ENOMEM;
-		goto error_triggered_buffer_cleanup;
+		return -ENOMEM;
 	}
 
 	iio_trigger_set_drvdata(trig, attrb);
-	trig->ops = &hid_sensor_trigger_ops;
 	ret = iio_trigger_register(trig);
 
 	if (ret) {
@@ -284,8 +298,6 @@ error_unreg_trigger:
 	iio_trigger_unregister(trig);
 error_free_trig:
 	iio_trigger_free(trig);
-error_triggered_buffer_cleanup:
-	iio_triggered_buffer_cleanup(indio_dev);
 	return ret;
 }
 EXPORT_SYMBOL_NS(hid_sensor_setup_trigger, "IIO_HID");
-- 
cgit v1.2.3


From 773ef9f95385bae52dcb7fd129fefba3a71a04db Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 14 Feb 2026 16:33:54 -0600
Subject: iio: imu: bno055: fix BNO055_SCAN_CH_COUNT off by one

Fix an off-by-one error in the BNO055_SCAN_CH_COUNT macro. The count
is derived by taking the difference of the last and first register
addresses, dividing by the size of each channel (2 bytes). It needs to
also add 1 to account for the fact that the count is inclusive of both
the first and last channels.

Thanks to the aligned_s64 timestamp field, there was already extra
padding in the buffer, so there were no runtime issues caused by this
bug.

Fixes: 4aefe1c2bd0c ("iio: imu: add Bosch Sensortec BNO055 core driver")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/bno055/bno055.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/imu/bno055/bno055.c b/drivers/iio/imu/bno055/bno055.c
index 303bc308f80a..c96fec2ebb3e 100644
--- a/drivers/iio/imu/bno055/bno055.c
+++ b/drivers/iio/imu/bno055/bno055.c
@@ -64,7 +64,7 @@
 #define BNO055_GRAVITY_DATA_X_LSB_REG	0x2E
 #define BNO055_GRAVITY_DATA_Y_LSB_REG	0x30
 #define BNO055_GRAVITY_DATA_Z_LSB_REG	0x32
-#define BNO055_SCAN_CH_COUNT ((BNO055_GRAVITY_DATA_Z_LSB_REG - BNO055_ACC_DATA_X_LSB_REG) / 2)
+#define BNO055_SCAN_CH_COUNT ((BNO055_GRAVITY_DATA_Z_LSB_REG - BNO055_ACC_DATA_X_LSB_REG) / 2 + 1)
 #define BNO055_TEMP_REG			0x34
 #define BNO055_CALIB_STAT_REG		0x35
 #define BNO055_CALIB_STAT_MAGN_SHIFT 0
-- 
cgit v1.2.3


From 11439c4635edd669ae435eec308f4ab8a0804808 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 1 Mar 2026 15:39:31 -0800
Subject: Linux 7.0-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index e944c6e71e81..2446085983f7 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 54a86cf48eaa6d1ab5130d756b718775e81e1748 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 5 Feb 2026 00:25:37 +0000
Subject: ASoC: fsl_easrc: Fix event generation in fsl_easrc_iec958_put_bits()

ALSA controls should return 1 if the value in the control changed but the
control put operation fsl_easrc_iec958_put_bits() unconditionally returns
0, causing ALSA to not generate any change events. This is detected by
mixer-test with large numbers of messages in the form:

    No event generated for Context 3 IEC958 CS5
    Context 3 IEC958 CS5.0 orig 5224 read 5225, is_volatile 0

Add a suitable check.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260205-asoc-fsl-easrc-fix-events-v1-1-39d4c766918b@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_easrc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c
index e64a0d97afd0..5b6204923e8a 100644
--- a/sound/soc/fsl/fsl_easrc.c
+++ b/sound/soc/fsl/fsl_easrc.c
@@ -52,10 +52,13 @@ static int fsl_easrc_iec958_put_bits(struct snd_kcontrol *kcontrol,
 	struct soc_mreg_control *mc =
 		(struct soc_mreg_control *)kcontrol->private_value;
 	unsigned int regval = ucontrol->value.integer.value[0];
+	int ret;
+
+	ret = (easrc_priv->bps_iec958[mc->regbase] != regval);
 
 	easrc_priv->bps_iec958[mc->regbase] = regval;
 
-	return 0;
+	return ret;
 }
 
 static int fsl_easrc_iec958_get_bits(struct snd_kcontrol *kcontrol,
-- 
cgit v1.2.3


From 31ddc62c1cd92e51b9db61d7954b85ae2ec224da Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 5 Feb 2026 00:25:38 +0000
Subject: ASoC: fsl_easrc: Fix event generation in fsl_easrc_iec958_set_reg()

ALSA controls should return 1 if the value in the control changed but the
control put operation fsl_easrc_set_reg() only returns 0 or a negative
error code, causing ALSA to not generate any change events. Add a suitable
check by using regmap_update_bits_check() with the underlying regmap, this
is more clearly and simply correct than trying to verify that one of the
generic ops is exactly equivalent to this one.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260205-asoc-fsl-easrc-fix-events-v1-2-39d4c766918b@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_easrc.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/sound/soc/fsl/fsl_easrc.c b/sound/soc/fsl/fsl_easrc.c
index 5b6204923e8a..6c56134c60cc 100644
--- a/sound/soc/fsl/fsl_easrc.c
+++ b/sound/soc/fsl/fsl_easrc.c
@@ -96,14 +96,17 @@ static int fsl_easrc_set_reg(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
 	struct soc_mreg_control *mc =
 		(struct soc_mreg_control *)kcontrol->private_value;
+	struct fsl_asrc *easrc = snd_soc_component_get_drvdata(component);
 	unsigned int regval = ucontrol->value.integer.value[0];
+	bool changed;
 	int ret;
 
-	ret = snd_soc_component_write(component, mc->regbase, regval);
-	if (ret < 0)
+	ret = regmap_update_bits_check(easrc->regmap, mc->regbase,
+				       GENMASK(31, 0), regval, &changed);
+	if (ret != 0)
 		return ret;
 
-	return 0;
+	return changed;
 }
 
 #define SOC_SINGLE_REG_RW(xname, xreg) \
-- 
cgit v1.2.3


From 9351cf3fd92dc1349bb75f2f7f7324607dcf596f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:01:37 +0000
Subject: ASoC: cs35l56: Only patch ASP registers if the DAI is part of a
 DAIlink

Move the ASP register patches to a separate struct and apply this from the
ASP DAI probe() function so that the registers are only patched if the DAI
is part of a DAI link.

Some systems use the ASP as a special-purpose interconnect and on these
systems the ASP registers are configured by a third party (the firmware,
the BIOS, or another device using the amp's secondary host control
interface).

If the machine driver does not hook up the ASP DAI then the ASP registers
must be omitted from the patch to prevent overwriting the third party
configuration.

If the machine driver includes the ASP DAI in a DAI link, this implies that
the machine driver and higher components (such as alsa-ucm) are taking
ownership of the ASP. In this case the ASP registers are patched to known
defaults and the machine driver should configure the ASP.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226110137.1664562-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  1 +
 sound/soc/codecs/cs35l56-shared.c | 16 +++++++++++++++-
 sound/soc/codecs/cs35l56.c        |  8 ++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index ae1e1489b671..28f9f5940ab6 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -406,6 +406,7 @@ extern const char * const cs35l56_cal_set_status_text[3];
 extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
 extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
 
+int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base);
 int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
 int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
 int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 4707f28bfca2..af87ebae98cb 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -26,7 +26,7 @@
 
 #include "cs35l56.h"
 
-static const struct reg_sequence cs35l56_patch[] = {
+static const struct reg_sequence cs35l56_asp_patch[] = {
 	/*
 	 * Firmware can change these to non-defaults to satisfy SDCA.
 	 * Ensure that they are at known defaults.
@@ -43,6 +43,20 @@ static const struct reg_sequence cs35l56_patch[] = {
 	{ CS35L56_ASP1TX2_INPUT,		0x00000000 },
 	{ CS35L56_ASP1TX3_INPUT,		0x00000000 },
 	{ CS35L56_ASP1TX4_INPUT,		0x00000000 },
+};
+
+int cs35l56_set_asp_patch(struct cs35l56_base *cs35l56_base)
+{
+	return regmap_register_patch(cs35l56_base->regmap, cs35l56_asp_patch,
+				     ARRAY_SIZE(cs35l56_asp_patch));
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_set_asp_patch, "SND_SOC_CS35L56_SHARED");
+
+static const struct reg_sequence cs35l56_patch[] = {
+	/*
+	 * Firmware can change these to non-defaults to satisfy SDCA.
+	 * Ensure that they are at known defaults.
+	 */
 	{ CS35L56_SWIRE_DP3_CH1_INPUT,		0x00000018 },
 	{ CS35L56_SWIRE_DP3_CH2_INPUT,		0x00000019 },
 	{ CS35L56_SWIRE_DP3_CH3_INPUT,		0x00000029 },
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 2ff8b172b76e..3bf9e8fc34a2 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -348,6 +348,13 @@ static int cs35l56_dsp_event(struct snd_soc_dapm_widget *w,
 	return wm_adsp_event(w, kcontrol, event);
 }
 
+static int cs35l56_asp_dai_probe(struct snd_soc_dai *codec_dai)
+{
+	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
+
+	return cs35l56_set_asp_patch(&cs35l56->base);
+}
+
 static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
@@ -552,6 +559,7 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai,
 }
 
 static const struct snd_soc_dai_ops cs35l56_ops = {
+	.probe = cs35l56_asp_dai_probe,
 	.set_fmt = cs35l56_asp_dai_set_fmt,
 	.set_tdm_slot = cs35l56_asp_dai_set_tdm_slot,
 	.hw_params = cs35l56_asp_dai_hw_params,
-- 
cgit v1.2.3


From 986841dcad257615a6e3f89231bb38e1f3506b77 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Wed, 25 Feb 2026 17:12:10 +0800
Subject: ASoC: rt1321: fix DMIC ch2/3 mask issue

This patch fixed the DMIC ch2/3 mask missing problem.

Signed-off-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20260225091210.3648905-1-shumingf@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1320-sdw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c
index 50f65662e143..8bb7e8497c72 100644
--- a/sound/soc/codecs/rt1320-sdw.c
+++ b/sound/soc/codecs/rt1320-sdw.c
@@ -2629,7 +2629,7 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream,
 	struct sdw_port_config port_config;
 	struct sdw_port_config dmic_port_config[2];
 	struct sdw_stream_runtime *sdw_stream;
-	int retval;
+	int retval, num_channels;
 	unsigned int sampling_rate;
 
 	dev_dbg(dai->dev, "%s %s", __func__, dai->name);
@@ -2661,7 +2661,8 @@ static int rt1320_sdw_hw_params(struct snd_pcm_substream *substream,
 				dmic_port_config[1].num = 10;
 				break;
 			case RT1321_DEV_ID:
-				dmic_port_config[0].ch_mask = BIT(0) | BIT(1);
+				num_channels = params_channels(params);
+				dmic_port_config[0].ch_mask = GENMASK(num_channels - 1, 0);
 				dmic_port_config[0].num = 8;
 				break;
 			default:
-- 
cgit v1.2.3


From 70eddf6a0a3fc6d3ab6f77251676da97cc7f12ae Mon Sep 17 00:00:00 2001
From: Oliver Freyermuth <o.freyermuth@googlemail.com>
Date: Tue, 24 Feb 2026 20:02:24 +0100
Subject: ASoC: Intel: sof_sdw: Add quirk for Alienware Area 51 (2025) 0CCD SKU

This adds the necessary quirk for the Alienware 18 Area 51 (2025).
Complements commit 1b03391d073d ("ASoC: Intel: sof_sdw: Add quirk
for Alienware Area 51 (2025) 0CCC SKU").

Signed-off-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Tested-by: Oliver Freyermuth <o.freyermuth@googlemail.com>
Link: https://patch.msgid.link/20260224190224.30630-1-o.freyermuth@googlemail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index f230991f5f8e..c18ec607e029 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -763,6 +763,14 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 		},
 		.driver_data = (void *)(SOC_SDW_CODEC_SPKR),
 	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0CCD")
+		},
+		.driver_data = (void *)(SOC_SDW_CODEC_SPKR),
+	},
 	/* Pantherlake devices*/
 	{
 		.callback = sof_sdw_quirk_cb,
-- 
cgit v1.2.3


From fd13fc700e3e239826a46448bf7f01847dd26f5a Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Tue, 24 Feb 2026 13:03:07 +0000
Subject: ASoC: amd: acp: Add ACP6.3 match entries for Cirrus Logic parts

This adds some match entries for a few system configurations:

cs42l43 link 0 UID 0
cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs42l45 link 1 UID 0
cs35l63 link 0 UID 0
cs35l63 link 0 UID 2
cs35l63 link 0 UID 4
cs35l63 link 0 UID 6

cs42l45 link 0 UID 0
cs35l63 link 1 UID 0
cs35l63 link 1 UID 1

cs42l45 link 0 UID 0
cs35l63 link 1 UID 1
cs35l63 link 1 UID 3

cs42l45 link 1 UID 0
cs35l63 link 0 UID 0
cs35l63 link 0 UID 1

cs42l43 link 1 UID 0
cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs35l56 link 1 UID 0
cs35l56 link 1 UID 1
cs35l56 link 1 UID 2
cs35l56 link 1 UID 3

cs35l63 link 0 UID 0
cs35l63 link 0 UID 2
cs35l63 link 0 UID 4
cs35l63 link 0 UID 6

cs42l43 link 0 UID 1

cs42l43b link 0 UID 1

cs42l45 link 0 UID 0

cs42l45 link 1 UID 0

Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com>
Link: https://patch.msgid.link/20260224130307.526626-1-simont@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/amd-acp63-acpi-match.c | 413 +++++++++++++++++++++++++++++++
 1 file changed, 413 insertions(+)

diff --git a/sound/soc/amd/acp/amd-acp63-acpi-match.c b/sound/soc/amd/acp/amd-acp63-acpi-match.c
index 9b6a49c051cd..1dbbaba3c75b 100644
--- a/sound/soc/amd/acp/amd-acp63-acpi-match.c
+++ b/sound/soc/amd/acp/amd-acp63-acpi-match.c
@@ -30,6 +30,20 @@ static const struct snd_soc_acpi_endpoint spk_r_endpoint = {
 	.group_id = 1
 };
 
+static const struct snd_soc_acpi_endpoint spk_2_endpoint = {
+	.num = 0,
+	.aggregated = 1,
+	.group_position = 2,
+	.group_id = 1
+};
+
+static const struct snd_soc_acpi_endpoint spk_3_endpoint = {
+	.num = 0,
+	.aggregated = 1,
+	.group_position = 3,
+	.group_id = 1
+};
+
 static const struct snd_soc_acpi_adr_device rt711_rt1316_group_adr[] = {
 	{
 		.adr = 0x000030025D071101ull,
@@ -103,6 +117,345 @@ static const struct snd_soc_acpi_adr_device rt722_0_single_adr[] = {
 	}
 };
 
+static const struct snd_soc_acpi_endpoint cs42l43_endpoints[] = {
+	{ /* Jack Playback Endpoint */
+		.num = 0,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* DMIC Capture Endpoint */
+		.num = 1,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* Jack Capture Endpoint */
+		.num = 2,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	{ /* Speaker Playback Endpoint */
+		.num = 3,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l56x4_l1u3210_adr[] = {
+	{
+		.adr = 0x00013301FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013201FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00013101FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00013001FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l0u01_adr[] = {
+	{
+		.adr = 0x00003001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00003101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l1u01_adr[] = {
+	{
+		.adr = 0x00013001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x2_l1u13_adr[] = {
+	{
+		.adr = 0x00013101FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013301FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs35l63x4_l0u0246_adr[] = {
+	{
+		.adr = 0x00003001FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00003201FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00003401FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00003601FA356301ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l0u0_adr[] = {
+	{
+		.adr = 0x00003001FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l0u1_adr[] = {
+	{
+		.adr = 0x00003101FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43b_l0u1_adr[] = {
+	{
+		.adr = 0x00003101FA2A3B01ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l43_l1u0_cs35l56x4_l1u0123_adr[] = {
+	{
+		.adr = 0x00013001FA424301ull,
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints),
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l43"
+	},
+	{
+		.adr = 0x00013001FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "AMP1"
+	},
+	{
+		.adr = 0x00013101FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "AMP2"
+	},
+	{
+		.adr = 0x00013201FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_2_endpoint,
+		.name_prefix = "AMP3"
+	},
+	{
+		.adr = 0x00013301FA355601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_3_endpoint,
+		.name_prefix = "AMP4"
+	},
+};
+
+static const struct snd_soc_acpi_adr_device cs42l45_l0u0_adr[] = {
+	{
+		.adr = 0x00003001FA424501ull,
+		/* Re-use endpoints, but cs42l45 has no speaker */
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1,
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l45"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device cs42l45_l1u0_adr[] = {
+	{
+		.adr = 0x00013001FA424501ull,
+		/* Re-use endpoints, but cs42l45 has no speaker */
+		.num_endpoints = ARRAY_SIZE(cs42l43_endpoints) - 1,
+		.endpoints = cs42l43_endpoints,
+		.name_prefix = "cs42l45"
+	}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs35l56x4_l1u3210[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr),
+		.adr_d = cs35l56x4_l1u3210_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs35l63x4_l0u0246[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr),
+		.adr_d = cs35l63x4_l0u0246_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u1[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43_l0u1_adr),
+		.adr_d = cs42l43_l0u1_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43b_l0u1[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43b_l0u1_adr),
+		.adr_d = cs42l43b_l0u1_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l0u0_cs35l56x4_l1u3210[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l43_l0u0_adr),
+		.adr_d = cs42l43_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l56x4_l1u3210_adr),
+		.adr_d = cs35l56x4_l1u3210_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l43_l1u0_cs35l56x4_l1u0123[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l43_l1u0_cs35l56x4_l1u0123_adr),
+		.adr_d = cs42l43_l1u0_cs35l56x4_l1u0123_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u01[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l1u01_adr),
+		.adr_d = cs35l63x2_l1u01_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l0u0_cs35l63x2_l1u13[] = {
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs42l45_l0u0_adr),
+		.adr_d = cs42l45_l0u0_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l1u13_adr),
+		.adr_d = cs35l63x2_l1u13_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x2_l0u01[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x2_l0u01_adr),
+		.adr_d = cs35l63x2_l0u01_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr acp63_cs42l45_l1u0_cs35l63x4_l0u0246[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(cs42l45_l1u0_adr),
+		.adr_d = cs42l45_l1u0_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(cs35l63x4_l0u0246_adr),
+		.adr_d = cs35l63x4_l0u0246_adr,
+	},
+	{}
+};
+
 static const struct snd_soc_acpi_link_adr acp63_rt722_only[] = {
 	{
 		.mask = BIT(0),
@@ -135,6 +488,66 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp63_sdw_machines[] = {
 		.links = acp63_4_in_1_sdca,
 		.drv_name = "amd_sdw",
 	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l43_l0u0_cs35l56x4_l1u3210,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l1u0_cs35l63x4_l0u0246,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l0u0_cs35l63x2_l1u01,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l0u0_cs35l63x2_l1u13,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0) | BIT(1),
+		.links = acp63_cs42l45_l1u0_cs35l63x2_l0u01,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs42l43_l1u0_cs35l56x4_l1u0123,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs35l56x4_l1u3210,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs35l63x4_l0u0246,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l43_l0u1,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l43b_l0u1,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(0),
+		.links = acp63_cs42l45_l0u0,
+		.drv_name = "amd_sdw",
+	},
+	{
+		.link_mask = BIT(1),
+		.links = acp63_cs42l45_l1u0,
+		.drv_name = "amd_sdw",
+	},
 	{},
 };
 EXPORT_SYMBOL(snd_soc_acpi_amd_acp63_sdw_machines);
-- 
cgit v1.2.3


From ca5056f5a78ce62588878d138e8141f01d70e61b Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 26 Feb 2026 11:35:11 +0000
Subject: ASoC: cs35l56: Suppress pointless warning about number of GPIO pulls

In cs35l56_process_xu_onchip_speaker_id() the warning that the number
of pulls != number of GPIOs should only be printed if pulls are defined.

Pull settings are optional because there would normally be an external
resistor providing the pull. The warning would still be true if pulls
are not defined, but in that case is just log noise.

While we're changing that block of code, also fix the indenting of the
arguments to the dev_warn().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20260226113511.1768838-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 3bf9e8fc34a2..37909a319f88 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -1625,9 +1625,9 @@ static int cs35l56_process_xu_onchip_speaker_id(struct cs35l56_private *cs35l56,
 	if (num_pulls < 0)
 		return num_pulls;
 
-	if (num_pulls != num_gpios) {
+	if (num_pulls && (num_pulls != num_gpios)) {
 		dev_warn(cs35l56->base.dev, "%s count(%d) != %s count(%d)\n",
-			pull_name, num_pulls, gpio_name, num_gpios);
+			 pull_name, num_pulls, gpio_name, num_gpios);
 	}
 
 	ret = cs35l56_check_and_save_onchip_spkid_gpios(&cs35l56->base,
-- 
cgit v1.2.3


From 23942b71f07cc99e39d9216a5b370df494759d8c Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Feb 2026 02:24:34 +0800
Subject: regulator: mt6363: Fix incorrect and redundant IRQ disposal in probe

In mt6363_regulator_probe(), devm_add_action_or_reset() is used to
automatically dispose of the IRQ mapping if the probe fails or the
device is removed.

The manual call to irq_dispose_mapping() in the error path was redundant
as the reset action already triggers mt6363_irq_remove(). Furthermore,
the manual call incorrectly passed the hardware IRQ number (info->hwirq)
instead of the virtual IRQ mapping (info->virq).

Remove the redundant and incorrect manual disposal.

Fixes: 3c36965df808 ("regulator: Add support for MediaTek MT6363 SPMI PMIC Regulators")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260223-mt6363-v1-1-c99a2e8ac621@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mt6363-regulator.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/regulator/mt6363-regulator.c b/drivers/regulator/mt6363-regulator.c
index 03af5fa53600..0aebcbda0a19 100644
--- a/drivers/regulator/mt6363-regulator.c
+++ b/drivers/regulator/mt6363-regulator.c
@@ -899,10 +899,8 @@ static int mt6363_regulator_probe(struct platform_device *pdev)
 					     "Failed to map IRQ%d\n", info->hwirq);
 
 		ret = devm_add_action_or_reset(dev, mt6363_irq_remove, &info->virq);
-		if (ret) {
-			irq_dispose_mapping(info->hwirq);
+		if (ret)
 			return ret;
-		}
 
 		config.driver_data = info;
 		INIT_DELAYED_WORK(&info->oc_work, mt6363_oc_irq_enable_work);
-- 
cgit v1.2.3


From 7d0bf050a58747bb8f977a6281e63660a66d1c81 Mon Sep 17 00:00:00 2001
From: ChenXiaoSong <chenxiaosong@kylinos.cn>
Date: Sat, 21 Feb 2026 08:07:12 +0000
Subject: smb/client: make SMB2 maperror KUnit tests a separate module

Build the SMB2 maperror KUnit tests as `smb2maperror_test.ko`.

Link: https://lore.kernel.org/linux-cifs/20260210081040.4156383-1-geert@linux-m68k.org/
Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/Makefile            |  2 ++
 fs/smb/client/smb2glob.h          | 12 ++++++++++++
 fs/smb/client/smb2maperror.c      | 28 +++++++++++++++-------------
 fs/smb/client/smb2maperror_test.c | 12 +++++++++---
 4 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile
index 3abd357d6df6..26b6105f04d1 100644
--- a/fs/smb/client/Makefile
+++ b/fs/smb/client/Makefile
@@ -56,4 +56,6 @@ $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c
 quiet_cmd_gen_smb2_mapping = GEN     $@
       cmd_gen_smb2_mapping = perl $(src)/gen_smb2_mapping $< $@
 
+obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o
+
 clean-files	+= smb2_mapping_table.c
diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h
index e56e4d402f13..19da74b1edab 100644
--- a/fs/smb/client/smb2glob.h
+++ b/fs/smb/client/smb2glob.h
@@ -46,4 +46,16 @@ enum smb2_compound_ops {
 #define END_OF_CHAIN 4
 #define RELATED_REQUEST 8
 
+/*
+ *****************************************************************
+ * Struct definitions go here
+ *****************************************************************
+ */
+
+struct status_to_posix_error {
+	__u32 smb2_status;
+	int posix_error;
+	char *status_string;
+};
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index cd036365201f..f4cff44e2796 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -8,7 +8,6 @@
  *
  */
 #include <linux/errno.h>
-#include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifs_debug.h"
 #include "smb2proto.h"
@@ -16,12 +15,6 @@
 #include "../common/smb2status.h"
 #include "trace.h"
 
-struct status_to_posix_error {
-	__u32 smb2_status;
-	int posix_error;
-	char *status_string;
-};
-
 static const struct status_to_posix_error smb2_error_map_table[] = {
 /*
  * Automatically generated by the `gen_smb2_mapping` script,
@@ -115,10 +108,19 @@ int __init smb2_init_maperror(void)
 	return 0;
 }
 
-#define SMB_CLIENT_KUNIT_AVAILABLE \
-	((IS_MODULE(CONFIG_CIFS) && IS_ENABLED(CONFIG_KUNIT)) || \
-	 (IS_BUILTIN(CONFIG_CIFS) && IS_BUILTIN(CONFIG_KUNIT)))
+#if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
+/* Previous prototype for eliminating the build warning. */
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
+
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status)
+{
+	return smb2_get_err_map(smb2_status);
+}
+EXPORT_SYMBOL_GPL(smb2_get_err_map_test);
+
+const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table;
+EXPORT_SYMBOL_GPL(smb2_error_map_table_test);
 
-#if SMB_CLIENT_KUNIT_AVAILABLE && IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
-#include "smb2maperror_test.c"
-#endif /* CONFIG_SMB_KUNIT_TESTS */
+unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table);
+EXPORT_SYMBOL_GPL(smb2_error_map_num);
+#endif
diff --git a/fs/smb/client/smb2maperror_test.c b/fs/smb/client/smb2maperror_test.c
index 38ea6b846a99..8c47dea7a2c1 100644
--- a/fs/smb/client/smb2maperror_test.c
+++ b/fs/smb/client/smb2maperror_test.c
@@ -9,13 +9,18 @@
  */
 
 #include <kunit/test.h>
+#include "smb2glob.h"
+
+const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
+extern const struct status_to_posix_error *smb2_error_map_table_test;
+extern unsigned int smb2_error_map_num;
 
 static void
 test_cmp_map(struct kunit *test, const struct status_to_posix_error *expect)
 {
 	const struct status_to_posix_error *result;
 
-	result = smb2_get_err_map(expect->smb2_status);
+	result = smb2_get_err_map_test(expect->smb2_status);
 	KUNIT_EXPECT_PTR_NE(test, NULL, result);
 	KUNIT_EXPECT_EQ(test, expect->smb2_status, result->smb2_status);
 	KUNIT_EXPECT_EQ(test, expect->posix_error, result->posix_error);
@@ -26,8 +31,8 @@ static void maperror_test_check_search(struct kunit *test)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(smb2_error_map_table); i++)
-		test_cmp_map(test, &smb2_error_map_table[i]);
+	for (i = 0; i < smb2_error_map_num; i++)
+		test_cmp_map(test, &smb2_error_map_table_test[i]);
 }
 
 static struct kunit_case maperror_test_cases[] = {
@@ -43,3 +48,4 @@ static struct kunit_suite maperror_suite = {
 kunit_test_suite(maperror_suite);
 
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests of SMB2 maperror");
-- 
cgit v1.2.3


From 6f0402539b7da2b941a5a43754c15e53ac3cc276 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Wed, 25 Feb 2026 04:10:59 +0000
Subject: smb: update some doc references

To make it easier to locate the documentation during development.

Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.h | 7 +++++--
 fs/smb/server/smb2pdu.h | 5 ++++-
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index 78bb99f29d38..30d70097fe2f 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -224,7 +224,7 @@ struct smb2_file_reparse_point_info {
 	__le32 Tag;
 } __packed;
 
-/* See MS-FSCC 2.4.21 */
+/* See MS-FSCC 2.4.26 */
 struct smb2_file_id_information {
 	__le64	VolumeSerialNumber;
 	__u64  PersistentFileId; /* opaque endianness */
@@ -251,7 +251,10 @@ struct smb2_file_id_extd_directory_info {
 
 extern char smb2_padding[7];
 
-/* equivalent of the contents of SMB3.1.1 POSIX open context response */
+/*
+ * See POSIX-SMB2 2.2.14.2.16
+ * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md
+ */
 struct create_posix_rsp {
 	u32 nlink;
 	u32 reparse_tag;
diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h
index 257c6d26df26..8b6eafb70dca 100644
--- a/fs/smb/server/smb2pdu.h
+++ b/fs/smb/server/smb2pdu.h
@@ -83,7 +83,10 @@ struct create_durable_rsp {
 	} Data;
 } __packed;
 
-/* equivalent of the contents of SMB3.1.1 POSIX open context response */
+/*
+ * See POSIX-SMB2 2.2.14.2.16
+ * Link: https://gitlab.com/samba-team/smb3-posix-spec/-/blob/master/smb3_posix_extensions.md
+ */
 struct create_posix_rsp {
 	struct create_context_hdr ccontext;
 	__u8    Name[16];
-- 
cgit v1.2.3


From 0d10393d5eac33cbd92f7a41fddca12c41d3cb7e Mon Sep 17 00:00:00 2001
From: Roshan Kumar <roshaen09@gmail.com>
Date: Sun, 1 Mar 2026 10:56:38 +0000
Subject: xfrm: iptfs: validate inner IPv4 header length in IPTFS payload

Add validation of the inner IPv4 packet tot_len and ihl fields parsed
from decrypted IPTFS payloads in __input_process_payload(). A crafted
ESP packet containing an inner IPv4 header with tot_len=0 causes an
infinite loop: iplen=0 leads to capturelen=min(0, remaining)=0, so the
data offset never advances and the while(data < tail) loop never
terminates, spinning forever in softirq context.

Reject inner IPv4 packets where tot_len < ihl*4 or ihl*4 < sizeof(struct
iphdr), which catches both the tot_len=0 case and malformed ihl values.
The normal IP stack performs this validation in ip_rcv_core(), but IPTFS
extracts and processes inner packets before they reach that layer.

Reported-by: Roshan Kumar <roshaen09@gmail.com>
Fixes: 6c82d2433671 ("xfrm: iptfs: add basic receive packet (tunnel egress) handling")
Cc: stable@vger.kernel.org
Signed-off-by: Roshan Kumar <roshaen09@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_iptfs.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 3b6d7284fc70..0747d1cfa333 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -991,6 +991,11 @@ static bool __input_process_payload(struct xfrm_state *x, u32 data,
 
 			iplen = be16_to_cpu(iph->tot_len);
 			iphlen = iph->ihl << 2;
+			if (iplen < iphlen || iphlen < sizeof(*iph)) {
+				XFRM_INC_STATS(net,
+					       LINUX_MIB_XFRMINHDRERROR);
+				goto done;
+			}
 			protocol = cpu_to_be16(ETH_P_IP);
 			XFRM_MODE_SKB_CB(skbseq->root_skb)->tos = iph->tos;
 		} else if (iph->version == 0x6) {
-- 
cgit v1.2.3


From 8a9ebe8c3ca4c5bdad8f010656f4c2155da589fd Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 28 Feb 2026 17:48:22 -0800
Subject: gpio: timberdale: repair kernel-doc comments

Use a ':' after struct member names to avoid kernel-doc warnings:

Warning: include/linux/timb_gpio.h:22 struct member 'gpio_base' not
 described in 'timbgpio_platform_data'
Warning: include/linux/timb_gpio.h:22 struct member 'nr_pins' not
 described in 'timbgpio_platform_data'
Warning: include/linux/timb_gpio.h:22 struct member 'irq_base' not
 described in 'timbgpio_platform_data'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260301014822.3133268-1-rdunlap@infradead.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 include/linux/timb_gpio.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/timb_gpio.h b/include/linux/timb_gpio.h
index 3faf5a6bb13e..74f5e73bf6db 100644
--- a/include/linux/timb_gpio.h
+++ b/include/linux/timb_gpio.h
@@ -9,10 +9,10 @@
 
 /**
  * struct timbgpio_platform_data - Platform data of the Timberdale GPIO driver
- * @gpio_base		The number of the first GPIO pin, set to -1 for
+ * @gpio_base:		The number of the first GPIO pin, set to -1 for
  *			dynamic number allocation.
- * @nr_pins		Number of pins that is supported by the hardware (1-32)
- * @irq_base		If IRQ is supported by the hardware, this is the base
+ * @nr_pins:		Number of pins that is supported by the hardware (1-32)
+ * @irq_base:		If IRQ is supported by the hardware, this is the base
  *			number of IRQ:s. One IRQ per pin will be used. Set to
  *			-1 if IRQ:s is not supported.
  */
-- 
cgit v1.2.3


From 48647d3f9a644d1e81af6558102d43cdb260597b Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2026 10:42:30 +0100
Subject: slab: distinguish lock and trylock for sheaf_flush_main()

sheaf_flush_main() can be called from __pcs_replace_full_main() where
it's fine if the trylock fails, and pcs_flush_all() where it's not
expected to and for some flush callers (when destroying the cache or
memory hotremove) it would be actually a problem if it failed and left
the main sheaf not flushed. The flush callers can however safely use
local_lock() instead of trylock.

The trylock failure should not happen in practice on !PREEMPT_RT, but
can happen on PREEMPT_RT. The impact is limited in practice because when
a trylock fails in the kmem_cache_destroy() path, it means someone is
using the cache while destroying it, which is a bug on its own. The memory
hotremove path is unlikely to be employed in a production RT config, but
it's possible.

To fix this, split the function into sheaf_flush_main() (using
local_lock()) and sheaf_try_flush_main() (using local_trylock()) where
both call __sheaf_flush_main_batch() to flush a single batch of objects.
This will also allow lockdep to verify our context assumptions.

The problem was raised in an off-list question by Marcelo.

Fixes: 2d517aa09bbc ("slab: add opt-in caching layer of percpu sheaves")
Cc: stable@vger.kernel.org
Reported-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Link: https://patch.msgid.link/20260211-b4-sheaf-flush-v1-1-4e7f492f0055@suse.cz
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 47 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 0c906fefc31b..b1e9f16ba435 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2858,19 +2858,19 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p);
  * object pointers are moved to a on-stack array under the lock. To bound the
  * stack usage, limit each batch to PCS_BATCH_MAX.
  *
- * returns true if at least partially flushed
+ * Must be called with s->cpu_sheaves->lock locked, returns with the lock
+ * unlocked.
+ *
+ * Returns how many objects are remaining to be flushed
  */
-static bool sheaf_flush_main(struct kmem_cache *s)
+static unsigned int __sheaf_flush_main_batch(struct kmem_cache *s)
 {
 	struct slub_percpu_sheaves *pcs;
 	unsigned int batch, remaining;
 	void *objects[PCS_BATCH_MAX];
 	struct slab_sheaf *sheaf;
-	bool ret = false;
 
-next_batch:
-	if (!local_trylock(&s->cpu_sheaves->lock))
-		return ret;
+	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
 	sheaf = pcs->main;
@@ -2888,10 +2888,37 @@ next_batch:
 
 	stat_add(s, SHEAF_FLUSH, batch);
 
-	ret = true;
+	return remaining;
+}
 
-	if (remaining)
-		goto next_batch;
+static void sheaf_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+
+	do {
+		local_lock(&s->cpu_sheaves->lock);
+
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
+}
+
+/*
+ * Returns true if the main sheaf was at least partially flushed.
+ */
+static bool sheaf_try_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+	bool ret = false;
+
+	do {
+		if (!local_trylock(&s->cpu_sheaves->lock))
+			return ret;
+
+		ret = true;
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
 
 	return ret;
 }
@@ -5704,7 +5731,7 @@ alloc_empty:
 	if (put_fail)
 		 stat(s, BARN_PUT_FAIL);
 
-	if (!sheaf_flush_main(s))
+	if (!sheaf_try_flush_main(s))
 		return NULL;
 
 	if (!local_trylock(&s->cpu_sheaves->lock))
-- 
cgit v1.2.3


From c35636e91e392e1540949bbc67932167cb48bc3a Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 18 Feb 2026 11:58:06 +0100
Subject: can: bcm: fix locking for bcm_op runtime updates

Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
added a locking for some variables that can be modified at runtime when
updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup().

Usually the RX_SETUP only handles and filters incoming traffic with one
exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is
sent when a specific RTR frame is received. Therefore the rx bcm_op uses
bcm_can_tx() which uses the bcm_tx_lock that was only initialized in
bcm_tx_setup(). Add the missing spin_lock_init() when allocating the
bcm_op in bcm_rx_setup() to handle the RTR case properly.

Fixes: c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates")
Reported-by: syzbot+5b11eccc403dd1cea9f8@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-can/699466e4.a70a0220.2c38d7.00ff.GAE@google.com/
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260218-bcm_spin_lock_init-v1-1-592634c8a5b5@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index b7324e9c955b..fd9fa072881e 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
+		spin_lock_init(&op->bcm_tx_lock);
 		op->can_id = msg_head->can_id;
 		op->nframes = msg_head->nframes;
 		op->cfsiz = CFSIZ(msg_head->flags);
-- 
cgit v1.2.3


From c77bfbdd6aac31b152ee81522cd90ad1de18738f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 26 Jan 2026 11:45:40 +0100
Subject: can: dummy_can: dummy_can_init(): fix packet statistics

The former implementation was only counting the tx_packets value but not
the tx_bytes as the skb was dropped on driver layer.

Enable CAN echo support (IFF_ECHO) in dummy_can_init(), which activates the
code for setting and retrieving the echo SKB and counts the tx_bytes
correctly.

Fixes: 816cf430e84b ("can: add dummy_can driver")
Cc: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20260126104540.21024-1-socketcan@hartkopp.net
[mkl: make commit message imperative]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dummy_can.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c
index 41953655e3d3..cd23de488edc 100644
--- a/drivers/net/can/dummy_can.c
+++ b/drivers/net/can/dummy_can.c
@@ -241,6 +241,7 @@ static int __init dummy_can_init(void)
 
 	dev->netdev_ops = &dummy_can_netdev_ops;
 	dev->ethtool_ops = &dummy_can_ethtool_ops;
+	dev->flags |= IFF_ECHO; /* enable echo handling */
 	priv = netdev_priv(dev);
 	priv->can.bittiming_const = &dummy_can_bittiming_const;
 	priv->can.bitrate_max = 20 * MEGA /* BPS */;
-- 
cgit v1.2.3


From ab3f894de216f4a62adc3b57e9191888cbf26885 Mon Sep 17 00:00:00 2001
From: Alban Bedel <alban.bedel@lht.dlh.de>
Date: Mon, 9 Feb 2026 15:47:05 +0100
Subject: can: mcp251x: fix deadlock in error path of mcp251x_open

The mcp251x_open() function call free_irq() in its error path with the
mpc_lock mutex held. But if an interrupt already occurred the
interrupt handler will be waiting for the mpc_lock and free_irq() will
deadlock waiting for the handler to finish.

This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can:
mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but
for the error path.

To solve this issue move the call to free_irq() after the lock is
released. Setting `priv->force_quit = 1` beforehand ensure that the IRQ
handler will exit right away once it acquired the lock.

Signed-off-by: Alban Bedel <alban.bedel@lht.dlh.de>
Link: https://patch.msgid.link/20260209144706.2261954-1-alban.bedel@lht.dlh.de
Fixes: bf66f3736a94 ("can: mcp251x: Move to threaded interrupts instead of workqueues.")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/mcp251x.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index fa97adf25b73..bb7782582f40 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
+	bool release_irq = false;
 	unsigned long flags = 0;
 	int ret;
 
@@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net)
 	return 0;
 
 out_free_irq:
-	free_irq(spi->irq, priv);
+	/* The IRQ handler might be running, and if so it will be waiting
+	 * for the lock. But free_irq() must wait for the handler to finish
+	 * so calling it here would deadlock.
+	 *
+	 * Setting priv->force_quit will let the handler exit right away
+	 * without any access to the hardware. This make it safe to call
+	 * free_irq() after the lock is released.
+	 */
+	priv->force_quit = 1;
+	release_irq = true;
+
 	mcp251x_hw_sleep(spi);
 out_close:
 	mcp251x_power_enable(priv->transceiver, 0);
 	close_candev(net);
 	mutex_unlock(&priv->mcp_lock);
+	if (release_irq)
+		free_irq(spi->irq, priv);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 189645ba9cd9c1eed45151aacaae4347c1eb86a7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 28 Feb 2026 17:48:11 -0800
Subject: gpio: nomadik: repair some kernel-doc comments

Avoid these kernel-doc warnings by:
- adding short descriptions for enums
- using correct (matching) struct names in kernel-doc short descriptions
- using the correct struct member name for @nfunctions

Warning: include/linux/gpio/gpio-nomadik.h:116 missing initial short
 description on line: * enum prcm_gpiocr_reg_index
Warning: include/linux/gpio/gpio-nomadik.h:125 missing initial short
 description on line: * enum prcm_gpiocr_altcx_index
Warning: include/linux/gpio/gpio-nomadik.h:146 expecting prototype for
 struct prcm_gpio_altcx. Prototype was for struct prcm_gpiocr_altcx instead
Warning: include/linux/gpio/gpio-nomadik.h:156 expecting prototype for
 struct prcm_gpio_altcx_pin_desc. Prototype was for
 struct prcm_gpiocr_altcx_pin_desc instead
Warning: include/linux/gpio/gpio-nomadik.h:212 struct member 'nfunctions'
 not described in 'nmk_pinctrl_soc_data'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260301014811.3133250-1-rdunlap@infradead.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 include/linux/gpio/gpio-nomadik.h | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/include/linux/gpio/gpio-nomadik.h b/include/linux/gpio/gpio-nomadik.h
index 592a774a53cd..8061b9826361 100644
--- a/include/linux/gpio/gpio-nomadik.h
+++ b/include/linux/gpio/gpio-nomadik.h
@@ -114,8 +114,7 @@ struct nmk_gpio_chip {
 }
 
 /**
- * enum prcm_gpiocr_reg_index
- * Used to reference an PRCM GPIOCR register address.
+ * enum prcm_gpiocr_reg_index - Used to reference a PRCM GPIOCR register address.
  */
 enum prcm_gpiocr_reg_index {
 	PRCM_IDX_GPIOCR1,
@@ -123,8 +122,7 @@ enum prcm_gpiocr_reg_index {
 	PRCM_IDX_GPIOCR3
 };
 /**
- * enum prcm_gpiocr_altcx_index
- * Used to reference an Other alternate-C function.
+ * enum prcm_gpiocr_altcx_index - Used to reference an Other alternate-C function.
  */
 enum prcm_gpiocr_altcx_index {
 	PRCM_IDX_GPIOCR_ALTC1,
@@ -135,7 +133,7 @@ enum prcm_gpiocr_altcx_index {
 };
 
 /**
- * struct prcm_gpio_altcx - Other alternate-C function
+ * struct prcm_gpiocr_altcx - Other alternate-C function
  * @used: other alternate-C function availability
  * @reg_index: PRCM GPIOCR register index used to control the function
  * @control_bit: PRCM GPIOCR bit used to control the function
@@ -147,7 +145,7 @@ struct prcm_gpiocr_altcx {
 } __packed;
 
 /**
- * struct prcm_gpio_altcx_pin_desc - Other alternate-C pin
+ * struct prcm_gpiocr_altcx_pin_desc - Other alternate-C pin
  * @pin: The pin number
  * @altcx: array of other alternate-C[1-4] functions
  */
@@ -193,7 +191,7 @@ struct nmk_pingroup {
  *		numbering.
  * @npins:	The number of entries in @pins.
  * @functions:	The functions supported on this SoC.
- * @nfunction:	The number of entries in @functions.
+ * @nfunctions:	The number of entries in @functions.
  * @groups:	An array describing all pin groups the pin SoC supports.
  * @ngroups:	The number of entries in @groups.
  * @altcx_pins:	The pins that support Other alternate-C function on this SoC
-- 
cgit v1.2.3


From 5f4338e5633dc034a81000b2516a78cfb51c601d Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Mon, 2 Mar 2026 14:12:17 +0530
Subject: ALSA: hda/hdmi: Add Tegra238 HDA codec device ID

Add Tegra238 HDA codec device in hda_device_id list.

Signed-off-by: Sheetal <sheetal@nvidia.com>
Link: https://patch.msgid.link/20260302084217.3135982-1-sheetal@nvidia.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/hdmi/tegrahdmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/hdmi/tegrahdmi.c b/sound/hda/codecs/hdmi/tegrahdmi.c
index 5f6fe31aa202..ebb6410a4831 100644
--- a/sound/hda/codecs/hdmi/tegrahdmi.c
+++ b/sound/hda/codecs/hdmi/tegrahdmi.c
@@ -299,6 +299,7 @@ static const struct hda_device_id snd_hda_id_tegrahdmi[] = {
 	HDA_CODEC_ID_MODEL(0x10de002f, "Tegra194 HDMI/DP2",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0030, "Tegra194 HDMI/DP3",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0031, "Tegra234 HDMI/DP",	MODEL_TEGRA234),
+	HDA_CODEC_ID_MODEL(0x10de0032, "Tegra238 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0033, "SoC 33 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0034, "Tegra264 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0035, "SoC 35 HDMI/DP",	MODEL_TEGRA234),
-- 
cgit v1.2.3


From 968b098220e393a10488b6a5dddb302b2eaedf66 Mon Sep 17 00:00:00 2001
From: Ziyi Guo <n7l8m4@u.northwestern.edu>
Date: Fri, 13 Feb 2026 20:39:27 +0000
Subject: can: esd_usb: add endpoint type validation

esd_usb_probe() constructs bulk pipes for two endpoints without
verifying their transfer types:

  - usb_rcvbulkpipe(dev->udev, 1) for RX (version reply, async RX data)
  - usb_sndbulkpipe(dev->udev, 2) for TX (version query, CAN frames)

A malformed USB device can present these endpoints with transfer types
that differ from what the driver assumes, triggering the WARNING in
usb_submit_urb().

Use usb_find_common_endpoints() to discover and validate the first
bulk IN and bulk OUT endpoints at probe time, before any allocation.
Found pipes are saved to struct esd_usb and code uses them directly
instead of making pipes in place.

Similar to
- commit 136bed0bfd3b ("can: mcba_usb: properly check endpoint type")
  which established the usb_find_common_endpoints() + stored pipes
  pattern for CAN USB drivers.

Fixes: 96d8e90382dc ("can: Add driver for esd CAN-USB/2 device")
Suggested-by: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Ziyi Guo <n7l8m4@u.northwestern.edu>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/20260213203927.599163-1-n7l8m4@u.northwestern.edu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/esd_usb.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 2892a68f510a..d257440fa01f 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -272,6 +272,9 @@ struct esd_usb {
 
 	struct usb_anchor rx_submitted;
 
+	unsigned int rx_pipe;
+	unsigned int tx_pipe;
+
 	int net_count;
 	u32 version;
 	int rxinitdone;
@@ -537,7 +540,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb)
 	}
 
 resubmit_urb:
-	usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1),
+	usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe,
 			  urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE,
 			  esd_usb_read_bulk_callback, dev);
 
@@ -626,9 +629,7 @@ static int esd_usb_send_msg(struct esd_usb *dev, union esd_usb_msg *msg)
 {
 	int actual_length;
 
-	return usb_bulk_msg(dev->udev,
-			    usb_sndbulkpipe(dev->udev, 2),
-			    msg,
+	return usb_bulk_msg(dev->udev, dev->tx_pipe, msg,
 			    msg->hdr.len * sizeof(u32), /* convert to # of bytes */
 			    &actual_length,
 			    1000);
@@ -639,12 +640,8 @@ static int esd_usb_wait_msg(struct esd_usb *dev,
 {
 	int actual_length;
 
-	return usb_bulk_msg(dev->udev,
-			    usb_rcvbulkpipe(dev->udev, 1),
-			    msg,
-			    sizeof(*msg),
-			    &actual_length,
-			    1000);
+	return usb_bulk_msg(dev->udev, dev->rx_pipe, msg,
+			    sizeof(*msg), &actual_length, 1000);
 }
 
 static int esd_usb_setup_rx_urbs(struct esd_usb *dev)
@@ -677,8 +674,7 @@ static int esd_usb_setup_rx_urbs(struct esd_usb *dev)
 
 		urb->transfer_dma = buf_dma;
 
-		usb_fill_bulk_urb(urb, dev->udev,
-				  usb_rcvbulkpipe(dev->udev, 1),
+		usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe,
 				  buf, ESD_USB_RX_BUFFER_SIZE,
 				  esd_usb_read_bulk_callback, dev);
 		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
@@ -903,7 +899,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb,
 	/* hnd must not be 0 - MSB is stripped in txdone handling */
 	msg->tx.hnd = BIT(31) | i; /* returned in TX done message */
 
-	usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf,
+	usb_fill_bulk_urb(urb, dev->udev, dev->tx_pipe, buf,
 			  msg->hdr.len * sizeof(u32), /* convert to # of bytes */
 			  esd_usb_write_bulk_callback, context);
 
@@ -1298,10 +1294,16 @@ done:
 static int esd_usb_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
+	struct usb_endpoint_descriptor *ep_in, *ep_out;
 	struct esd_usb *dev;
 	union esd_usb_msg *msg;
 	int i, err;
 
+	err = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out,
+					NULL, NULL);
+	if (err)
+		return err;
+
 	dev = kzalloc_obj(*dev);
 	if (!dev) {
 		err = -ENOMEM;
@@ -1309,6 +1311,8 @@ static int esd_usb_probe(struct usb_interface *intf,
 	}
 
 	dev->udev = interface_to_usbdev(intf);
+	dev->rx_pipe = usb_rcvbulkpipe(dev->udev, ep_in->bEndpointAddress);
+	dev->tx_pipe = usb_sndbulkpipe(dev->udev, ep_out->bEndpointAddress);
 
 	init_usb_anchor(&dev->rx_submitted);
 
-- 
cgit v1.2.3


From 38a01c9700b0dcafe97dfa9dc7531bf4a245deff Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:51:17 +0100
Subject: can: ems_usb: ems_usb_read_bulk_callback(): check the proper length
 of a message

When looking at the data in a USB urb, the actual_length is the size of
the buffer passed to the driver, not the transfer_buffer_length which is
set by the driver as the max size of the buffer.

When parsing the messages in ems_usb_read_bulk_callback() properly check
the size both at the beginning of parsing the message to make sure it is
big enough for the expected structure, and at the end of the message to
make sure we don't overflow past the end of the buffer for the next
message.

Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022316-answering-strainer-a5db@gregkh
Fixes: 702171adeed3 ("ems_usb: Added support for EMS CPC-USB/ARM7 CAN/USB interface")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ems_usb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 4c219a5b139b..9b25dda7c183 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 		start = CPC_HEADER_SIZE;
 
 		while (msg_count) {
+			if (start + CPC_MSG_HEADER_LEN > urb->actual_length) {
+				netdev_err(netdev, "format error\n");
+				break;
+			}
+
 			msg = (struct ems_cpc_msg *)&ibuf[start];
 
 			switch (msg->type) {
@@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 			start += CPC_MSG_HEADER_LEN + msg->length;
 			msg_count--;
 
-			if (start > urb->transfer_buffer_length) {
+			if (start > urb->actual_length) {
 				netdev_err(netdev, "format error\n");
 				break;
 			}
-- 
cgit v1.2.3


From 1e446fd0582ad8be9f6dafb115fc2e7245f9bea7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:30:20 +0100
Subject: can: ucan: Fix infinite loop from zero-length messages

If a broken ucan device gets a message with the message length field set
to 0, then the driver will loop for forever in
ucan_read_bulk_callback(), hanging the system.  If the length is 0, just
skip the message and go on to the next one.

This has been fixed in the kvaser_usb driver in the past in commit
0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in
command parsers"), so there must be some broken devices out there like
this somewhere.

Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022319-huff-absurd-6a18@gregkh
Fixes: 9f2d3eae88d2 ("can: ucan: add driver for Theobroma Systems UCAN devices")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ucan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index c79508b1c43e..0ea0ac75e42f 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -748,7 +748,7 @@ static void ucan_read_bulk_callback(struct urb *urb)
 		len = le16_to_cpu(m->len);
 
 		/* check sanity (length of content) */
-		if (urb->actual_length - pos < len) {
+		if ((len == 0) || (urb->actual_length - pos < len)) {
 			netdev_warn(up->netdev,
 				    "invalid message (short; no data; l:%d)\n",
 				    urb->actual_length);
-- 
cgit v1.2.3


From 5eaad4f768266f1f17e01232ffe2ef009f8129b7 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 17:39:20 +0100
Subject: can: usb: etas_es58x: correctly anchor the urb in the read bulk
 callback

When submitting an urb, that is using the anchor pattern, it needs to be
anchored before submitting it otherwise it could be leaked if
usb_kill_anchored_urbs() is called.  This logic is correctly done
elsewhere in the driver, except in the read bulk callback so do that
here also.

Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Tested-by: Vincent Mailhol <mailhol@kernel.org>
Link: https://patch.msgid.link/2026022320-poser-stiffly-9d84@gregkh
Fixes: 8537257874e9 ("can: etas_es58x: add core support for ETAS ES58X CAN USB interfaces")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/etas_es58x/es58x_core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c
index 2d248deb69dc..b259f6109808 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_core.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_core.c
@@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb)
 	}
 
  resubmit_urb:
+	usb_anchor_urb(urb, &es58x_dev->rx_urbs);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV) {
 		for (i = 0; i < es58x_dev->num_can_ch; i++)
 			if (es58x_dev->netdev[i])
 				netif_device_detach(es58x_dev->netdev[i]);
-	} else if (ret)
+	} else
 		dev_err_ratelimited(dev,
 				    "Failed resubmitting read bulk urb: %pe\n",
 				    ERR_PTR(ret));
-- 
cgit v1.2.3


From 7299b1b39a255f6092ce4ec0b65f66e9d6a357af Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:30 +0100
Subject: can: usb: f81604: handle short interrupt urb messages properly

If an interrupt urb is received that is not the correct length, properly
detect it and don't attempt to treat the data as valid.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022331-opal-evaluator-a928@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index 76578063ac82..c61bd30d1765 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -620,6 +620,12 @@ static void f81604_read_int_callback(struct urb *urb)
 		netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__,
 			    ERR_PTR(urb->status));
 
+	if (urb->actual_length < sizeof(*data)) {
+		netdev_warn(netdev, "%s: short int URB: %u < %zu\n",
+			    __func__, urb->actual_length, sizeof(*data));
+		goto resubmit_urb;
+	}
+
 	switch (urb->status) {
 	case 0: /* success */
 		break;
-- 
cgit v1.2.3


From 51f94780720fa90c424f67e3e9784cb8ef8190e5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:31 +0100
Subject: can: usb: f81604: handle bulk write errors properly

If a write urb fails then more needs to be done other than just logging
the message, otherwise the transmission could be stalled.  Properly
increment the error counters and wake up the queues so that data will
continue to flow.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022334-slackness-dynamic-9195@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index c61bd30d1765..1cc927d79b6a 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -880,9 +880,27 @@ static void f81604_write_bulk_callback(struct urb *urb)
 	if (!netif_device_present(netdev))
 		return;
 
-	if (urb->status)
-		netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__,
-			    ERR_PTR(urb->status));
+	if (!urb->status)
+		return;
+
+	switch (urb->status) {
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+		return;
+	default:
+		break;
+	}
+
+	if (net_ratelimit())
+		netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__,
+			   ERR_PTR(urb->status));
+
+	can_free_echo_skb(netdev, 0, NULL);
+	netdev->stats.tx_dropped++;
+	netdev->stats.tx_errors++;
+
+	netif_wake_queue(netdev);
 }
 
 static void f81604_clear_reg_work(struct work_struct *work)
-- 
cgit v1.2.3


From 952caa5da10bed22be09612433964f6877ba0dde Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:10:32 +0100
Subject: can: usb: f81604: correctly anchor the urb in the read bulk callback

When submitting an urb, that is using the anchor pattern, it needs to be
anchored before submitting it otherwise it could be leaked if
usb_kill_anchored_urbs() is called.  This logic is correctly done
elsewhere in the driver, except in the read bulk callback so do that
here also.

Cc: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>
Cc: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Vincent Mailhol <mailhol@kernel.org>
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022334-starlight-scaling-2cea@gregkh
Fixes: 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/f81604.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c
index 1cc927d79b6a..f12318268e46 100644
--- a/drivers/net/can/usb/f81604.c
+++ b/drivers/net/can/usb/f81604.c
@@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb)
 {
 	struct f81604_can_frame *frame = urb->transfer_buffer;
 	struct net_device *netdev = urb->context;
+	struct f81604_port_priv *priv = netdev_priv(netdev);
 	int ret;
 
 	if (!netif_device_present(netdev))
@@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb)
 	f81604_process_rx_packet(netdev, frame);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev,
 			   "%s: failed to resubmit read bulk urb: %pe\n",
 			   __func__, ERR_PTR(ret));
@@ -652,10 +658,15 @@ static void f81604_read_int_callback(struct urb *urb)
 		f81604_handle_tx(priv, data);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n",
 			   __func__, ERR_PTR(ret));
 }
-- 
cgit v1.2.3


From 4ca191cec17a997d0e3b2cd312f3a884288acc27 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Wed, 4 Feb 2026 09:01:00 -0600
Subject: x86/boot/sev: Move SEV decompressor variables into the .data section

As part of the work to remove the dependency on calling into the decompressor
code (startup_64()) for a UEFI boot, a call to rmpadjust() was removed from
sev_enable() in favor of checking the value of the snp_vmpl variable.

When booting through a non-UEFI path and calling startup_64(), the call to
sev_enable() is performed before the BSS section is zeroed. With the removal
of the rmpadjust() call and the corresponding check of the return code, the
snp_vmpl variable is checked.

Since the kernel is running at VMPL0, the snp_vmpl variable will not have been
set and should be the default value of 0.  However, since the call occurs
before the BSS is zeroed, the snp_vmpl variable may not actually be zero,
which will cause the guest boot to fail.

Since the decompressor relocates itself, the BSS would need to be cleared both
before and after the relocation, but this would, in effect, cause all of the
changes to BSS variables before relocation to be lost after relocation.

Instead, move the snp_vmpl variable into the .data section so that it is
initialized and the value made safe during relocation. As a pre-caution
against future changes, move other SEV-related decompressor variables into the
.data section, too.

Fixes: 68a501d7fd82 ("x86/boot: Drop redundant RMPADJUST in SEV SVSM presence check")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Changyuan Lyu <changyuanl@google.com>
Tested-by: Kevin Hui <kevinhui@meta.com>
Tested-by: Changyuan Lyu <changyuanl@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/5648b7de5b0a5d0dfef3785f9582b718678c6448.1770217260.git.thomas.lendacky@amd.com
---
 arch/x86/boot/compressed/sev.c     | 8 ++++----
 arch/x86/boot/startup/sev-shared.c | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index c8c1464b3a56..46b54720d91d 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -28,17 +28,17 @@
 #include "sev.h"
 
 static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
-struct ghcb *boot_ghcb;
+struct ghcb *boot_ghcb __section(".data");
 
 #undef __init
 #define __init
 
 #define __BOOT_COMPRESSED
 
-u8 snp_vmpl;
-u16 ghcb_version;
+u8 snp_vmpl __section(".data");
+u16 ghcb_version __section(".data");
 
-u64 boot_svsm_caa_pa;
+u64 boot_svsm_caa_pa __section(".data");
 
 /* Include code for early handlers */
 #include "../../boot/startup/sev-shared.c"
diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c
index a0fa8bb2b945..d9ac3a929d33 100644
--- a/arch/x86/boot/startup/sev-shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -31,7 +31,7 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
-bool sev_snp_needs_sfw;
+bool sev_snp_needs_sfw __section(".data");
 
 void __noreturn
 sev_es_terminate(unsigned int set, unsigned int reason)
-- 
cgit v1.2.3


From 9073428bb204d921ae15326bb7d4558d9d269aab Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@amd.com>
Date: Tue, 3 Feb 2026 16:24:03 -0600
Subject: x86/sev: Allow IBPB-on-Entry feature for SNP guests

The SEV-SNP IBPB-on-Entry feature does not require a guest-side
implementation. It was added in Zen5 h/w, after the first SNP Zen
implementation, and thus was not accounted for when the initial set of SNP
features were added to the kernel.

In its abundant precaution, commit

  8c29f0165405 ("x86/sev: Add SEV-SNP guest feature negotiation support")

included SEV_STATUS' IBPB-on-Entry bit as a reserved bit, thereby masking
guests from using the feature.

Allow guests to make use of IBPB-on-Entry when supported by the hypervisor, as
the bit is now architecturally defined and safe to expose.

Fixes: 8c29f0165405 ("x86/sev: Add SEV-SNP guest feature negotiation support")
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: stable@kernel.org
Link: https://patch.msgid.link/20260203222405.4065706-2-kim.phillips@amd.com
---
 arch/x86/boot/compressed/sev.c   | 1 +
 arch/x86/coco/sev/core.c         | 1 +
 arch/x86/include/asm/msr-index.h | 5 ++++-
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 46b54720d91d..e468476e9e4a 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -188,6 +188,7 @@ bool sev_es_check_ghcb_fault(unsigned long address)
 				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
 				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
 				 MSR_AMD64_SNP_SECURE_AVIC |		\
+				 MSR_AMD64_SNP_RESERVED_BITS19_22 |	\
 				 MSR_AMD64_SNP_RESERVED_MASK)
 
 #ifdef CONFIG_AMD_SECURE_AVIC
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 907981b94c40..7ed3da998489 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -89,6 +89,7 @@ static const char * const sev_status_feat_names[] = {
 	[MSR_AMD64_SNP_VMSA_REG_PROT_BIT]	= "VMSARegProt",
 	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
 	[MSR_AMD64_SNP_SECURE_AVIC_BIT]		= "SecureAVIC",
+	[MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT]	= "IBPBOnEntry",
 };
 
 /*
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index da5275d8eda6..6673601246b3 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -740,7 +740,10 @@
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
 #define MSR_AMD64_SNP_SECURE_AVIC_BIT	18
 #define MSR_AMD64_SNP_SECURE_AVIC	BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT)
-#define MSR_AMD64_SNP_RESV_BIT		19
+#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19)
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT	23
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY	BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		24
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
 #define MSR_AMD64_SAVIC_CONTROL		0xc0010138
 #define MSR_AMD64_SAVIC_EN_BIT		0
-- 
cgit v1.2.3


From 2df6162785f31f1bbb598cfc3b08e4efc88f80b6 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 19 Feb 2026 13:57:34 +0100
Subject: can: gs_usb: gs_can_open(): always configure bitrates before starting
 device

So far the driver populated the struct can_priv::do_set_bittiming() and
struct can_priv::fd::do_set_data_bittiming() callbacks.

Before bringing up the interface, user space has to configure the bitrates.
With these callbacks the configuration is directly forwarded into the CAN
hardware. Then the interface can be brought up.

An ifdown-ifup cycle (without changing the bit rates) doesn't re-configure
the bitrates in the CAN hardware. This leads to a problem with the
CANable-2.5 [1] firmware, which resets the configured bit rates during
ifdown.

To fix the problem remove both bit timing callbacks and always configure
the bitrates in the struct net_device_ops::ndo_open() callback.

[1] https://github.com/Elmue/CANable-2.5-firmware-Slcan-and-Candlelight

Cc: stable@vger.kernel.org
Fixes: d08e973a77d1 ("can: gs_usb: Added support for the GS_USB CAN devices")
Link: https://patch.msgid.link/20260219-gs_usb-always-configure-bitrates-v2-1-671f8ba5b0a5@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index 9d27d6f0c0b5..ec9a7cbbbc69 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -772,9 +772,8 @@ device_detach:
 	}
 }
 
-static int gs_usb_set_bittiming(struct net_device *netdev)
+static int gs_usb_set_bittiming(struct gs_can *dev)
 {
-	struct gs_can *dev = netdev_priv(netdev);
 	struct can_bittiming *bt = &dev->can.bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
@@ -791,9 +790,8 @@ static int gs_usb_set_bittiming(struct net_device *netdev)
 				    GFP_KERNEL);
 }
 
-static int gs_usb_set_data_bittiming(struct net_device *netdev)
+static int gs_usb_set_data_bittiming(struct gs_can *dev)
 {
-	struct gs_can *dev = netdev_priv(netdev);
 	struct can_bittiming *bt = &dev->can.fd.data_bittiming;
 	struct gs_device_bittiming dbt = {
 		.prop_seg = cpu_to_le32(bt->prop_seg),
@@ -1057,6 +1055,20 @@ static int gs_can_open(struct net_device *netdev)
 	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 		flags |= GS_CAN_MODE_HW_TIMESTAMP;
 
+	rc = gs_usb_set_bittiming(dev);
+	if (rc) {
+		netdev_err(netdev, "failed to set bittiming: %pe\n", ERR_PTR(rc));
+		goto out_usb_kill_anchored_urbs;
+	}
+
+	if (ctrlmode & CAN_CTRLMODE_FD) {
+		rc = gs_usb_set_data_bittiming(dev);
+		if (rc) {
+			netdev_err(netdev, "failed to set data bittiming: %pe\n", ERR_PTR(rc));
+			goto out_usb_kill_anchored_urbs;
+		}
+	}
+
 	/* finally start device */
 	dev->can.state = CAN_STATE_ERROR_ACTIVE;
 	dm.flags = cpu_to_le32(flags);
@@ -1370,7 +1382,6 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 	dev->can.state = CAN_STATE_STOPPED;
 	dev->can.clock.freq = le32_to_cpu(bt_const.fclk_can);
 	dev->can.bittiming_const = &dev->bt_const;
-	dev->can.do_set_bittiming = gs_usb_set_bittiming;
 
 	dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC;
 
@@ -1394,7 +1405,6 @@ static struct gs_can *gs_make_candev(unsigned int channel,
 		 * GS_CAN_FEATURE_BT_CONST_EXT is set.
 		 */
 		dev->can.fd.data_bittiming_const = &dev->bt_const;
-		dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming;
 	}
 
 	if (feature & GS_CAN_FEATURE_TERMINATION) {
-- 
cgit v1.2.3


From 7e1e6d6845329adb2da75110a061557e9c26d9b7 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 12 Feb 2026 11:30:00 -0500
Subject: dt-bindings: net: can: nxp,sja1000: add reference to
 mc-peripheral-props.yaml

Add a reference to mc-peripheral-props.yaml to allow vendor-specific
properties for memory access timings.

Fix below CHECK_DTBS warings:
arch/arm/boot/dts/nxp/imx/imx27-phytec-phycore-rdk.dtb: can@4,0 (nxp,sja1000): Unevaluated properties are not allowed ('fsl,weim-cs-timing' was unexpected)
        from schema $id: http://devicetree.org/schemas/net/can/nxp,sja1000.yaml

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260212163000.1195586-1-Frank.Li@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
index ec0c2168e4b9..6bcfff970117 100644
--- a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
+++ b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml
@@ -87,6 +87,7 @@ required:
 
 allOf:
   - $ref: can-controller.yaml#
+  - $ref: /schemas/memory-controllers/mc-peripheral-props.yaml
   - if:
       properties:
         compatible:
-- 
cgit v1.2.3


From d973b1039ccde6b241b438d53297edce4de45b5c Mon Sep 17 00:00:00 2001
From: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Date: Sat, 21 Feb 2026 17:28:04 +0100
Subject: wifi: rsi: Don't default to -EOPNOTSUPP in rsi_mac80211_config

This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected
behavior from the driver - other drivers default to 0 too.

Fixes: 0a44dfc07074 ("wifi: mac80211: simplify non-chanctx drivers")
Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Link: https://patch.msgid.link/20260221-rsi-config-ret-v1-1-9a8f805e2f31@puri.sm
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/rsi/rsi_91x_mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 8c8e074a3a70..c7ae8031436a 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
 	struct ieee80211_conf *conf = &hw->conf;
-	int status = -EOPNOTSUPP;
+	int status = 0;
 
 	mutex_lock(&common->mutex);
 
-- 
cgit v1.2.3


From a8df7892a9f42b2e2d5851f8835c734bd7fe8ad4 Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Mon, 2 Mar 2026 14:23:22 +0530
Subject: ASoC: dt-bindings: tegra: Add compatible for Tegra238 sound card

Tegra238 requires different PLLA and PLLA_OUT0 clock rates compared to
other Tegra platforms. Add Tegra238 compatible string to the APE
tegra-audio-graph-card bindings.

Signed-off-by: Sheetal <sheetal@nvidia.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260302085323.3139571-2-sheetal@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml         | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
index da89523ccf5f..92bc3ef56f2c 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra-audio-graph-card.yaml
@@ -23,6 +23,7 @@ properties:
     enum:
       - nvidia,tegra210-audio-graph-card
       - nvidia,tegra186-audio-graph-card
+      - nvidia,tegra238-audio-graph-card
       - nvidia,tegra264-audio-graph-card
 
   clocks:
-- 
cgit v1.2.3


From 2d85ecd6fb0eb2fee0ffa040ec1ddea57b09bc38 Mon Sep 17 00:00:00 2001
From: Franz Schnyder <franz.schnyder@toradex.com>
Date: Wed, 18 Feb 2026 11:25:14 +0100
Subject: regulator: pf9453: Respect IRQ trigger settings from firmware

The datasheet specifies, that the IRQ_B pin is pulled low when any
unmasked interrupt bit status is changed, and it is released high once
the application processor reads the INT1 register. As it specifies a
level-low behavior, it should not force a falling-edge interrupt.

Remove the IRQF_TRIGGER_FALLING to not force the falling-edge interrupt
and instead rely on the flag from the device tree.

Fixes: 0959b6706325 ("regulator: pf9453: add PMIC PF9453 support")
Cc: stable@vger.kernel.org
Signed-off-by: Franz Schnyder <franz.schnyder@toradex.com>
Link: https://patch.msgid.link/20260218102518.238943-2-fra.schnyder@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pf9453-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/pf9453-regulator.c b/drivers/regulator/pf9453-regulator.c
index 779a6fdb0574..eed3055d1c1c 100644
--- a/drivers/regulator/pf9453-regulator.c
+++ b/drivers/regulator/pf9453-regulator.c
@@ -809,7 +809,7 @@ static int pf9453_i2c_probe(struct i2c_client *i2c)
 	}
 
 	ret = devm_request_threaded_irq(pf9453->dev, pf9453->irq, NULL, pf9453_irq_handler,
-					(IRQF_TRIGGER_FALLING | IRQF_ONESHOT),
+					IRQF_ONESHOT,
 					"pf9453-irq", pf9453);
 	if (ret)
 		return dev_err_probe(pf9453->dev, ret, "Failed to request IRQ: %d\n", pf9453->irq);
-- 
cgit v1.2.3


From e176ad7b57a1a15ece213251b7f3103bd929e26c Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Mon, 2 Mar 2026 13:24:52 +0100
Subject: dt-bindings: hwmon: sl28cpld: Drop sa67mcu compatible

I was just informed that this product is discontinued (without being
ever released to the market). Pull the plug and let's not waste any more
maintainers time and revert commit 0f6eae86e626 ("dt-bindings: hwmon:
sl28cpld: add sa67mcu compatible").

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Michael Walle <mwalle@kernel.org>
Link: https://lore.kernel.org/r/20260302122540.1377444-8-mwalle@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
index 966b221b6caa..5803a1770cad 100644
--- a/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
+++ b/Documentation/devicetree/bindings/hwmon/kontron,sl28cpld-hwmon.yaml
@@ -16,7 +16,6 @@ description: |
 properties:
   compatible:
     enum:
-      - kontron,sa67mcu-hwmon
       - kontron,sl28cpld-fan
 
   reg:
-- 
cgit v1.2.3


From cdc8a1e11f4d5b480ec750e28010c357185b95a6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 14 Jan 2026 16:45:46 -0800
Subject: drm/xe: Do not preempt fence signaling CS instructions

If a batch buffer is complete, it makes little sense to preempt the
fence signaling instructions in the ring, as the largest portion of the
work (the batch buffer) is already done and fence signaling consists of
only a few instructions. If these instructions are preempted, the GuC
would need to perform a context switch just to signal the fence, which
is costly and delays fence signaling. Avoid this scenario by disabling
preemption immediately after the BB start instruction and re-enabling it
after executing the fence signaling instructions.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Carlos Santa <carlos.santa@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patch.msgid.link/20260115004546.58060-1-matthew.brost@intel.com
(cherry picked from commit 2bcbf2dcde0c839a73af664a3c77d4e77d58a3eb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_ring_ops.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 248620b0901d..53d420d72164 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -280,6 +280,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -345,6 +348,9 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -397,6 +403,9 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	i = emit_render_cache_flush(job, dw, i);
 
 	if (job->user_fence.used)
-- 
cgit v1.2.3


From e377182f0266f46f02d01838e6bde67b9dac0d66 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Wed, 25 Feb 2026 01:34:49 +0000
Subject: drm/xe/configfs: Free ctx_restore_mid_bb in release

ctx_restore_mid_bb memory is allocated in wa_bb_store(), but
xe_config_device_release() only frees ctx_restore_post_bb.

Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation
when the configfs device is removed.

Fixes: b30d5de3d40c ("drm/xe/configfs: Add mid context restore bb")
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Nitin Gote <nitin.r.gote@intel.com>
Link: https://patch.msgid.link/20260225013448.3547687-2-shuicheng.lin@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index c59b1414df22..7fd07d1280bb 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -830,6 +830,7 @@ static void xe_config_device_release(struct config_item *item)
 
 	mutex_destroy(&dev->lock);
 
+	kfree(dev->config.ctx_restore_mid_bb[0].cs);
 	kfree(dev->config.ctx_restore_post_bb[0].cs);
 	kfree(dev);
 }
-- 
cgit v1.2.3


From 99f9b5343cae80eb0dfe050baf6c86d722b3ba2e Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Thu, 26 Feb 2026 22:26:58 +0100
Subject: drm/xe/queue: Call fini on exec queue creation fail

Every call to queue init should have a corresponding fini call.
Skipping this would mean skipping removal of the queue from GuC list
(which is part of guc_id allocation). A damaged queue stored in
exec_queue_lookup list would lead to invalid memory reference,
sooner or later.

Call fini to free guc_id. This must be done before any internal
LRCs are freed.

Since the finalization with this extra call became very similar to
__xe_exec_queue_fini(), reuse that. To make this reuse possible,
alter xe_lrc_put() so it can survive NULL parameters, like other
similar functions.

v2: Reuse _xe_exec_queue_fini(). Make xe_lrc_put() aware of NULLs.

Fixes: 3c1fa4aa60b1 ("drm/xe: Move queue init before LRC creation")
Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com> (v1)
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20260226212701.2937065-2-tomasz.lis@intel.com
(cherry picked from commit 393e5fea6f7d7054abc2c3d97a4cfe8306cd6079)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 23 +++++++++++------------
 drivers/gpu/drm/xe/xe_lrc.h        |  3 ++-
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0ddae7fcfc97..8ecdf949f9e4 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -266,6 +266,16 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 	return q;
 }
 
+static void __xe_exec_queue_fini(struct xe_exec_queue *q)
+{
+	int i;
+
+	q->ops->fini(q);
+
+	for (i = 0; i < q->width; ++i)
+		xe_lrc_put(q->lrc[i]);
+}
+
 static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags)
 {
 	int i, err;
@@ -320,21 +330,10 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q, u32 exec_queue_flags)
 	return 0;
 
 err_lrc:
-	for (i = i - 1; i >= 0; --i)
-		xe_lrc_put(q->lrc[i]);
+	__xe_exec_queue_fini(q);
 	return err;
 }
 
-static void __xe_exec_queue_fini(struct xe_exec_queue *q)
-{
-	int i;
-
-	q->ops->fini(q);
-
-	for (i = 0; i < q->width; ++i)
-		xe_lrc_put(q->lrc[i]);
-}
-
 struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm,
 					   u32 logical_mask, u16 width,
 					   struct xe_hw_engine *hwe, u32 flags,
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index c307a3fd9ea2..c1c615447c85 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -75,7 +75,8 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
  */
 static inline void xe_lrc_put(struct xe_lrc *lrc)
 {
-	kref_put(&lrc->refcount, xe_lrc_destroy);
+	if (lrc)
+		kref_put(&lrc->refcount, xe_lrc_destroy);
 }
 
 /**
-- 
cgit v1.2.3


From da46b5dfef48658d03347cda21532bcdbb521e67 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Sun, 1 Mar 2026 16:22:07 -0800
Subject: blktrace: fix __this_cpu_read/write in preemptible context

tracing_record_cmdline() internally uses __this_cpu_read() and
__this_cpu_write() on the per-CPU variable trace_cmdline_save, and
trace_save_cmdline() explicitly asserts preemption is disabled via
lockdep_assert_preemption_disabled(). These operations are only safe
when preemption is off, as they were designed to be called from the
scheduler context (probe_wakeup_sched_switch() / probe_wakeup()).

__blk_add_trace() was calling tracing_record_cmdline(current) early in
the blk_tracer path, before ring buffer reservation, from process
context where preemption is fully enabled. This triggers the following
using blktests/blktrace/002:

blktrace/002 (blktrace ftrace corruption with sysfs trace)   [failed]
    runtime  0.367s  ...  0.437s
    something found in dmesg:
    [   81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
    [   81.239580] null_blk: disk nullb1 created
    [   81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
    [   81.362842] caller is tracing_record_cmdline+0x10/0x40
    [   81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G                 N  7.0.0-rc1lblk+ #84 PREEMPT(full)
    [   81.362877] Tainted: [N]=TEST
    [   81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
    [   81.362881] Call Trace:
    [   81.362884]  <TASK>
    [   81.362886]  dump_stack_lvl+0x8d/0xb0
    ...
    (See '/mnt/sda/blktests/results/nodev/blktrace/002.dmesg' for the entire message)

[   81.211018] run blktests blktrace/002 at 2026-02-25 22:24:33
[   81.239580] null_blk: disk nullb1 created
[   81.357294] BUG: using __this_cpu_read() in preemptible [00000000] code: dd/2516
[   81.362842] caller is tracing_record_cmdline+0x10/0x40
[   81.362872] CPU: 16 UID: 0 PID: 2516 Comm: dd Tainted: G                 N  7.0.0-rc1lblk+ #84 PREEMPT(full)
[   81.362877] Tainted: [N]=TEST
[   81.362878] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
[   81.362881] Call Trace:
[   81.362884]  <TASK>
[   81.362886]  dump_stack_lvl+0x8d/0xb0
[   81.362895]  check_preemption_disabled+0xce/0xe0
[   81.362902]  tracing_record_cmdline+0x10/0x40
[   81.362923]  __blk_add_trace+0x307/0x5d0
[   81.362934]  ? lock_acquire+0xe0/0x300
[   81.362940]  ? iov_iter_extract_pages+0x101/0xa30
[   81.362959]  blk_add_trace_bio+0x106/0x1e0
[   81.362968]  submit_bio_noacct_nocheck+0x24b/0x3a0
[   81.362979]  ? lockdep_init_map_type+0x58/0x260
[   81.362988]  submit_bio_wait+0x56/0x90
[   81.363009]  __blkdev_direct_IO_simple+0x16c/0x250
[   81.363026]  ? __pfx_submit_bio_wait_endio+0x10/0x10
[   81.363038]  ? rcu_read_lock_any_held+0x73/0xa0
[   81.363051]  blkdev_read_iter+0xc1/0x140
[   81.363059]  vfs_read+0x20b/0x330
[   81.363083]  ksys_read+0x67/0xe0
[   81.363090]  do_syscall_64+0xbf/0xf00
[   81.363102]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   81.363106] RIP: 0033:0x7f281906029d
[   81.363111] Code: 31 c0 e9 c6 fe ff ff 50 48 8d 3d 66 63 0a 00 e8 59 ff 01 00 66 0f 1f 84 00 00 00 00 00 80 3d 41 33 0e 00 00 74 17 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 5b c3 66 2e 0f 1f 84 00 00 00 00 00 48 83 ec
[   81.363113] RSP: 002b:00007ffca127dd48 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[   81.363120] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f281906029d
[   81.363122] RDX: 0000000000001000 RSI: 0000559f8bfae000 RDI: 0000000000000000
[   81.363123] RBP: 0000000000001000 R08: 0000002863a10a81 R09: 00007f281915f000
[   81.363124] R10: 00007f2818f77b60 R11: 0000000000000246 R12: 0000559f8bfae000
[   81.363126] R13: 0000000000000000 R14: 0000000000000000 R15: 000000000000000a
[   81.363142]  </TASK>

The same BUG fires from blk_add_trace_plug(), blk_add_trace_unplug(),
and blk_add_trace_rq() paths as well.

The purpose of tracing_record_cmdline() is to cache the task->comm for
a given PID so that the trace can later resolve it. It is only
meaningful when a trace event is actually being recorded. Ring buffer
reservation via ring_buffer_lock_reserve() disables preemption, and
preemption remains disabled until the event is committed :-

__blk_add_trace()
       	__trace_buffer_lock_reserve()
       		__trace_buffer_lock_reserve()
       			ring_buffer_lock_reserve()
       				preempt_disable_notrace();  <---

With this fix blktests for blktrace pass:

  blktests (master) # ./check blktrace
  blktrace/001 (blktrace zone management command tracing)      [passed]
      runtime  3.650s  ...  3.647s
  blktrace/002 (blktrace ftrace corruption with sysfs trace)   [passed]
      runtime  0.411s  ...  0.384s

Fixes: 7ffbd48d5cab ("tracing: Cache comms only after an event occurred")
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/trace/blktrace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index e6988929ead2..18a9b84cc768 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -383,8 +383,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	cpu = raw_smp_processor_id();
 
 	if (blk_tracer) {
-		tracing_record_cmdline(current);
-
 		buffer = blk_tr->array_buffer.buffer;
 		trace_ctx = tracing_gen_ctx_flags(0);
 		switch (bt->version) {
@@ -419,6 +417,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 		if (!event)
 			return;
 
+		tracing_record_cmdline(current);
 		switch (bt->version) {
 		case 1:
 			record_blktrace_event(ring_buffer_event_data(event),
-- 
cgit v1.2.3


From c36e28becd0586ac98318fd335e5e91d19cd2623 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 2 Mar 2026 14:32:04 +0000
Subject: io_uring/net: reject SEND_VECTORIZED when unsupported

IORING_SEND_VECTORIZED with registered buffers is not implemented but
could be. Don't silently ignore the flag in this case but reject it with
an error. It only affects sendzc as normal sends don't support
registered buffers.

Fixes: 6f02527729bd3 ("io_uring/net: Allow to do vectorized send")
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/net.c b/io_uring/net.c
index 8576c6cb2236..d27adbe3f20b 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -375,6 +375,8 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		kmsg->msg.msg_namelen = addr_len;
 	}
 	if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+		if (sr->flags & IORING_SEND_VECTORIZED)
+			return -EINVAL;
 		req->flags |= REQ_F_IMPORT_BUFFER;
 		return 0;
 	}
-- 
cgit v1.2.3


From 539d1b47e935e8384977dd7e5cec370c08b7a644 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Sun, 1 Mar 2026 18:29:43 +0530
Subject: block: break pcpu_alloc_mutex dependency on freeze_lock

While nr_hw_update allocates tagset tags it acquires ->pcpu_alloc_mutex
after ->freeze_lock is acquired or queue is frozen. This potentially
creates a circular dependency involving ->fs_reclaim if reclaim is
triggered simultaneously in a code path which first acquires ->pcpu_
alloc_mutex. As the queue is already frozen while nr_hw_queue update
allocates tagsets, the reclaim can't forward progress and thus it could
cause a potential deadlock as reported in lockdep splat[1].

Fix this by pre-allocating tagset tags before we freeze queue during
nr_hw_queue update. Later the allocated tagset tags could be safely
installed and used after queue is frozen.

Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/all/CAHj4cs8F=OV9s3La2kEQ34YndgfZP-B5PHS4Z8_b9euKG6J4mw@mail.gmail.com/ [1]
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Reviewed-by: Yu Kuai <yukuai@fnnas.com>
[axboe: fix brace style issue]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 45 ++++++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 15 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d5602ff62c7c..0b182013016a 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -4793,38 +4793,45 @@ static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
-static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
-				       int new_nr_hw_queues)
+static struct blk_mq_tags **blk_mq_prealloc_tag_set_tags(
+				struct blk_mq_tag_set *set,
+				int new_nr_hw_queues)
 {
 	struct blk_mq_tags **new_tags;
 	int i;
 
 	if (set->nr_hw_queues >= new_nr_hw_queues)
-		goto done;
+		return NULL;
 
 	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
 				GFP_KERNEL, set->numa_node);
 	if (!new_tags)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	if (set->tags)
 		memcpy(new_tags, set->tags, set->nr_hw_queues *
 		       sizeof(*set->tags));
-	kfree(set->tags);
-	set->tags = new_tags;
 
 	for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) {
-		if (!__blk_mq_alloc_map_and_rqs(set, i)) {
-			while (--i >= set->nr_hw_queues)
-				__blk_mq_free_map_and_rqs(set, i);
-			return -ENOMEM;
+		if (blk_mq_is_shared_tags(set->flags)) {
+			new_tags[i] = set->shared_tags;
+		} else {
+			new_tags[i] = blk_mq_alloc_map_and_rqs(set, i,
+					set->queue_depth);
+			if (!new_tags[i])
+				goto out_unwind;
 		}
 		cond_resched();
 	}
 
-done:
-	set->nr_hw_queues = new_nr_hw_queues;
-	return 0;
+	return new_tags;
+out_unwind:
+	while (--i >= set->nr_hw_queues) {
+		if (!blk_mq_is_shared_tags(set->flags))
+			blk_mq_free_map_and_rqs(set, new_tags[i], i);
+	}
+	kfree(new_tags);
+	return ERR_PTR(-ENOMEM);
 }
 
 /*
@@ -5113,6 +5120,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	unsigned int memflags;
 	int i;
 	struct xarray elv_tbl;
+	struct blk_mq_tags **new_tags;
 	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5147,11 +5155,18 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		if (blk_mq_elv_switch_none(q, &elv_tbl))
 			goto switch_back;
 
+	new_tags = blk_mq_prealloc_tag_set_tags(set, nr_hw_queues);
+	if (IS_ERR(new_tags))
+		goto switch_back;
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue_nomemsave(q);
 	queues_frozen = true;
-	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
-		goto switch_back;
+	if (new_tags) {
+		kfree(set->tags);
+		set->tags = new_tags;
+	}
+	set->nr_hw_queues = nr_hw_queues;
 
 fallback:
 	blk_mq_update_queue_map(set);
-- 
cgit v1.2.3


From b570f37a2ce480be26c665345c5514686a8a0274 Mon Sep 17 00:00:00 2001
From: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Date: Tue, 10 Feb 2026 12:56:53 +0100
Subject: mm: Fix a hmm_range_fault() livelock / starvation problem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If hmm_range_fault() fails a folio_trylock() in do_swap_page,
trying to acquire the lock of a device-private folio for migration,
to ram, the function will spin until it succeeds grabbing the lock.

However, if the process holding the lock is depending on a work
item to be completed, which is scheduled on the same CPU as the
spinning hmm_range_fault(), that work item might be starved and
we end up in a livelock / starvation situation which is never
resolved.

This can happen, for example if the process holding the
device-private folio lock is stuck in
   migrate_device_unmap()->lru_add_drain_all()
sinc lru_add_drain_all() requires a short work-item
to be run on all online cpus to complete.

A prerequisite for this to happen is:
a) Both zone device and system memory folios are considered in
   migrate_device_unmap(), so that there is a reason to call
   lru_add_drain_all() for a system memory folio while a
   folio lock is held on a zone device folio.
b) The zone device folio has an initial mapcount > 1 which causes
   at least one migration PTE entry insertion to be deferred to
   try_to_migrate(), which can happen after the call to
   lru_add_drain_all().
c) No or voluntary only preemption.

This all seems pretty unlikely to happen, but indeed is hit by
the "xe_exec_system_allocator" igt test.

Resolve this by waiting for the folio to be unlocked if the
folio_trylock() fails in do_swap_page().

Rename migration_entry_wait_on_locked() to
softleaf_entry_wait_unlock() and update its documentation to
indicate the new use-case.

Future code improvements might consider moving
the lru_add_drain_all() call in migrate_device_unmap() to be
called *after* all pages have migration entries inserted.
That would eliminate also b) above.

v2:
- Instead of a cond_resched() in hmm_range_fault(),
  eliminate the problem by waiting for the folio to be unlocked
  in do_swap_page() (Alistair Popple, Andrew Morton)
v3:
- Add a stub migration_entry_wait_on_locked() for the
  !CONFIG_MIGRATION case. (Kernel Test Robot)
v4:
- Rename migrate_entry_wait_on_locked() to
  softleaf_entry_wait_on_locked() and update docs (Alistair Popple)
v5:
- Add a WARN_ON_ONCE() for the !CONFIG_MIGRATION
  version of softleaf_entry_wait_on_locked().
- Modify wording around function names in the commit message
  (Andrew Morton)

Suggested-by: Alistair Popple <apopple@nvidia.com>
Fixes: 1afaeb8293c9 ("mm/migrate: Trylock device page in do_swap_page")
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: linux-mm@kvack.org
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.15+
Reviewed-by: John Hubbard <jhubbard@nvidia.com> #v3
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Link: https://patch.msgid.link/20260210115653.92413-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit a69d1ab971a624c6f112cea61536569d579c3215)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 include/linux/migrate.h | 10 +++++++++-
 mm/filemap.c            | 15 ++++++++++-----
 mm/memory.c             |  3 ++-
 mm/migrate.c            |  8 ++++----
 mm/migrate_device.c     |  2 +-
 5 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 26ca00c325d9..d5af2b7f577b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 		struct folio *dst, struct folio *src);
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 		__releases(ptl);
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
@@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag
 	return -ENOSYS;
 }
 
+static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+	__releases(ptl)
+{
+	WARN_ON_ONCE(1);
+
+	spin_unlock(ptl);
+}
+
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/mm/filemap.c b/mm/filemap.c
index 6cd7974d4ada..406cef06b684 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1379,14 +1379,16 @@ repeat:
 
 #ifdef CONFIG_MIGRATION
 /**
- * migration_entry_wait_on_locked - Wait for a migration entry to be removed
- * @entry: migration swap entry.
+ * softleaf_entry_wait_on_locked - Wait for a migration entry or
+ * device_private entry to be removed.
+ * @entry: migration or device_private swap entry.
  * @ptl: already locked ptl. This function will drop the lock.
  *
- * Wait for a migration entry referencing the given page to be removed. This is
+ * Wait for a migration entry referencing the given page, or device_private
+ * entry referencing a dvice_private page to be unlocked. This is
  * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except
  * this can be called without taking a reference on the page. Instead this
- * should be called while holding the ptl for the migration entry referencing
+ * should be called while holding the ptl for @entry referencing
  * the page.
  *
  * Returns after unlocking the ptl.
@@ -1394,7 +1396,7 @@ repeat:
  * This follows the same logic as folio_wait_bit_common() so see the comments
  * there.
  */
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	__releases(ptl)
 {
 	struct wait_page_queue wait_page;
@@ -1428,6 +1430,9 @@ void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	 * If a migration entry exists for the page the migration path must hold
 	 * a valid reference to the page, and it must take the ptl to remove the
 	 * migration entry. So the page is valid until the ptl is dropped.
+	 * Similarly any path attempting to drop the last reference to a
+	 * device-private page needs to grab the ptl to remove the device-private
+	 * entry.
 	 */
 	spin_unlock(ptl);
 
diff --git a/mm/memory.c b/mm/memory.c
index 07778814b4a8..2f815a34d924 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4763,7 +4763,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				unlock_page(vmf->page);
 				put_page(vmf->page);
 			} else {
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				pte_unmap(vmf->pte);
+				softleaf_entry_wait_on_locked(entry, vmf->ptl);
 			}
 		} else if (softleaf_is_hwpoison(entry)) {
 			ret = VM_FAULT_HWPOISON;
diff --git a/mm/migrate.c b/mm/migrate.c
index 1bf2cf8c44dd..2c3d489ecf51 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -500,7 +500,7 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	if (!softleaf_is_migration(entry))
 		goto out;
 
-	migration_entry_wait_on_locked(entry, ptl);
+	softleaf_entry_wait_on_locked(entry, ptl);
 	return;
 out:
 	spin_unlock(ptl);
@@ -532,10 +532,10 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, p
 		 * If migration entry existed, safe to release vma lock
 		 * here because the pgtable page won't be freed without the
 		 * pgtable lock released.  See comment right above pgtable
-		 * lock release in migration_entry_wait_on_locked().
+		 * lock release in softleaf_entry_wait_on_locked().
 		 */
 		hugetlb_vma_unlock_read(vma);
-		migration_entry_wait_on_locked(entry, ptl);
+		softleaf_entry_wait_on_locked(entry, ptl);
 		return;
 	}
 
@@ -553,7 +553,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	ptl = pmd_lock(mm, pmd);
 	if (!pmd_is_migration_entry(*pmd))
 		goto unlock;
-	migration_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
+	softleaf_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
 	return;
 unlock:
 	spin_unlock(ptl);
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 0a8b31939640..8079676c8f1f 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -176,7 +176,7 @@ static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start,
 		}
 
 		if (softleaf_is_migration(entry)) {
-			migration_entry_wait_on_locked(entry, ptl);
+			softleaf_entry_wait_on_locked(entry, ptl);
 			spin_unlock(ptl);
 			return -EAGAIN;
 		}
-- 
cgit v1.2.3


From 03464a48cc8636b6de2febbc5ef39093a9a15e82 Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Tue, 10 Feb 2026 21:10:26 +0800
Subject: MAINTAINERS: Update email address for David Gow

Update my email address for KUnit related things in MAINTAINERS (and add
an entry to .mailmap so nothing gets lost).

Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..7d27cd78cfdb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -214,6 +214,7 @@ Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org>
 Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
 David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
+David Gow <david@davidgow.net> <davidgow@google.com>
 David Heidelberg <david@ixit.cz> <d.okias@gmail.com>
 David Hildenbrand <david@kernel.org> <david@redhat.com>
 David Rheinsberg <david@readahead.eu> <dh.herrmann@gmail.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..372ee16c24f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13943,7 +13943,7 @@ F:	fs/smb/server/
 
 KERNEL UNIT TESTING FRAMEWORK (KUnit)
 M:	Brendan Higgins <brendan.higgins@linux.dev>
-M:	David Gow <davidgow@google.com>
+M:	David Gow <david@davidgow.net>
 R:	Rae Moar <raemoar63@gmail.com>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
@@ -14763,7 +14763,7 @@ F:	drivers/misc/lis3lv02d/
 F:	drivers/platform/x86/hp/hp_accel.c
 
 LIST KUNIT TEST
-M:	David Gow <davidgow@google.com>
+M:	David Gow <david@davidgow.net>
 L:	linux-kselftest@vger.kernel.org
 L:	kunit-dev@googlegroups.com
 S:	Maintained
-- 
cgit v1.2.3


From 7dd34dfc8dfa92a7244242098110388367996ac3 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 24 Feb 2026 19:37:56 +0900
Subject: rust: kunit: fix warning when !CONFIG_PRINTK

If `CONFIG_PRINTK` is not set, then the following warnings are issued
during build:

  warning: unused variable: `args`
    --> ../rust/kernel/kunit.rs:16:12
    |
  16 | pub fn err(args: fmt::Arguments<'_>) {
    |            ^^^^ help: if this is intentional, prefix it with an underscore: `_args`
    |
    = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default

  warning: unused variable: `args`
    --> ../rust/kernel/kunit.rs:32:13
    |
  32 | pub fn info(args: fmt::Arguments<'_>) {
    |             ^^^^ help: if this is intentional, prefix it with an underscore: `_args`

Fix this by adding a no-op assignment using `args` when `CONFIG_PRINTK`
is not set.

Fixes: a66d733da801 ("rust: support running Rust documentation tests as KUnit ones")
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: David Gow <david@davidgow.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 rust/kernel/kunit.rs | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs
index f93f24a60bdd..a1edf7491579 100644
--- a/rust/kernel/kunit.rs
+++ b/rust/kernel/kunit.rs
@@ -14,6 +14,10 @@ use crate::prelude::*;
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn err(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]
@@ -30,6 +34,10 @@ pub fn err(args: fmt::Arguments<'_>) {
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn info(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]
-- 
cgit v1.2.3


From 40804c4974b8df2adab72f6475d343eaff72b7f6 Mon Sep 17 00:00:00 2001
From: Shuvam Pandey <shuvampandey1@gmail.com>
Date: Thu, 26 Feb 2026 21:14:10 +0545
Subject: kunit: tool: copy caller args in run_kernel to prevent mutation

run_kernel() appended KUnit flags directly to the caller-provided args
list. When exec_tests() calls run_kernel() repeatedly (e.g. with
--run_isolated), each call mutated the same list, causing later runs
to inherit stale filter_glob values and duplicate kunit.enable flags.

Fix this by copying args at the start of run_kernel(). Add a regression
test that calls run_kernel() twice with the same list and verifies the
original remains unchanged.

Fixes: ff9e09a3762f ("kunit: tool: support running each suite/test separately")
Signed-off-by: Shuvam Pandey <shuvampandey1@gmail.com>
Reviewed-by: David Gow <david@davidgow.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/kunit/kunit_kernel.py    |  6 ++++--
 tools/testing/kunit/kunit_tool_test.py | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 260d8d9aa1db..2998e1bc088b 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -346,8 +346,10 @@ class LinuxSourceTree:
 		return self.validate_config(build_dir)
 
 	def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]:
-		if not args:
-			args = []
+		# Copy to avoid mutating the caller-supplied list. exec_tests() reuses
+		# the same args across repeated run_kernel() calls (e.g. --run_isolated),
+		# so appending to the original would accumulate stale flags on each call.
+		args = list(args) if args else []
 		if filter_glob:
 			args.append('kunit.filter_glob=' + filter_glob)
 		if filter:
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index b67408147c1f..f6383884c599 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -503,6 +503,32 @@ class LinuxSourceTreeTest(unittest.TestCase):
 			with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile:
 				self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output')
 
+	def test_run_kernel_args_not_mutated(self):
+		"""Verify run_kernel() copies args so callers can reuse them."""
+		start_calls = []
+
+		def fake_start(start_args, unused_build_dir):
+			start_calls.append(list(start_args))
+			return subprocess.Popen(['printf', 'KTAP version 1\n'],
+						text=True, stdout=subprocess.PIPE)
+
+		with tempfile.TemporaryDirectory('') as build_dir:
+			tree = kunit_kernel.LinuxSourceTree(build_dir,
+					kunitconfig_paths=[os.devnull])
+			with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \
+			     mock.patch.object(kunit_kernel.subprocess, 'call'):
+				kernel_args = ['mem=1G']
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test1'):
+					pass
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test2'):
+					pass
+				self.assertEqual(kernel_args, ['mem=1G'],
+					'run_kernel() should not modify caller args')
+				self.assertIn('kunit.filter_glob=suite.test1', start_calls[0])
+				self.assertIn('kunit.filter_glob=suite.test2', start_calls[1])
+
 	def test_build_reconfig_no_config(self):
 		with tempfile.TemporaryDirectory('') as build_dir:
 			with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f:
-- 
cgit v1.2.3


From b11b9b6751b2cd74960dccd91667c5117fce743c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Feb 2026 10:48:53 +0100
Subject: kunit: reduce stack usage in kunit_run_tests()

Some of the recent changes to the kunit framework caused the stack usage
for kunit_run_tests() to grow higher than most other kernel functions,
which triggers a warning when CONFIG_FRAME_WARN is set to a relatively
low value:

lib/kunit/test.c: In function 'kunit_run_tests':
lib/kunit/test.c:801:1: error: the frame size of 1312 bytes is larger than 1280 bytes [-Werror=frame-larger-than=]

Split out the inner loop into a separate function to ensure that each
function remains under the limit, and pass the kunit_result_stats
structures by reference to avoid excessive copies.

Fixed checkpatch warnings at commit time:
Shuah Khan <skhan@linuxfoundation.org>

Cc: Carlos Llamas <cmllamas@google.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 lib/kunit/test.c | 231 ++++++++++++++++++++++++++++++-------------------------
 1 file changed, 125 insertions(+), 106 deletions(-)

diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 62eb529824c6..41e1c89799b6 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -94,7 +94,7 @@ struct kunit_result_stats {
 	unsigned long total;
 };
 
-static bool kunit_should_print_stats(struct kunit_result_stats stats)
+static bool kunit_should_print_stats(struct kunit_result_stats *stats)
 {
 	if (kunit_stats_enabled == 0)
 		return false;
@@ -102,11 +102,11 @@ static bool kunit_should_print_stats(struct kunit_result_stats stats)
 	if (kunit_stats_enabled == 2)
 		return true;
 
-	return (stats.total > 1);
+	return (stats->total > 1);
 }
 
 static void kunit_print_test_stats(struct kunit *test,
-				   struct kunit_result_stats stats)
+				   struct kunit_result_stats *stats)
 {
 	if (!kunit_should_print_stats(stats))
 		return;
@@ -115,10 +115,10 @@ static void kunit_print_test_stats(struct kunit *test,
 		  KUNIT_SUBTEST_INDENT
 		  "# %s: pass:%lu fail:%lu skip:%lu total:%lu",
 		  test->name,
-		  stats.passed,
-		  stats.failed,
-		  stats.skipped,
-		  stats.total);
+		  stats->passed,
+		  stats->failed,
+		  stats->skipped,
+		  stats->total);
 }
 
 /* Append formatted message to log. */
@@ -600,26 +600,26 @@ static void kunit_run_case_catch_errors(struct kunit_suite *suite,
 }
 
 static void kunit_print_suite_stats(struct kunit_suite *suite,
-				    struct kunit_result_stats suite_stats,
-				    struct kunit_result_stats param_stats)
+				    struct kunit_result_stats *suite_stats,
+				    struct kunit_result_stats *param_stats)
 {
 	if (kunit_should_print_stats(suite_stats)) {
 		kunit_log(KERN_INFO, suite,
 			  "# %s: pass:%lu fail:%lu skip:%lu total:%lu",
 			  suite->name,
-			  suite_stats.passed,
-			  suite_stats.failed,
-			  suite_stats.skipped,
-			  suite_stats.total);
+			  suite_stats->passed,
+			  suite_stats->failed,
+			  suite_stats->skipped,
+			  suite_stats->total);
 	}
 
 	if (kunit_should_print_stats(param_stats)) {
 		kunit_log(KERN_INFO, suite,
 			  "# Totals: pass:%lu fail:%lu skip:%lu total:%lu",
-			  param_stats.passed,
-			  param_stats.failed,
-			  param_stats.skipped,
-			  param_stats.total);
+			  param_stats->passed,
+			  param_stats->failed,
+			  param_stats->skipped,
+			  param_stats->total);
 	}
 }
 
@@ -681,13 +681,116 @@ static void kunit_init_parent_param_test(struct kunit_case *test_case, struct ku
 	}
 }
 
-int kunit_run_tests(struct kunit_suite *suite)
+static noinline_for_stack void
+kunit_run_param_test(struct kunit_suite *suite, struct kunit_case *test_case,
+		     struct kunit *test,
+		     struct kunit_result_stats *suite_stats,
+		     struct kunit_result_stats *total_stats,
+		     struct kunit_result_stats *param_stats)
 {
 	char param_desc[KUNIT_PARAM_DESC_SIZE];
+	const void *curr_param;
+
+	kunit_init_parent_param_test(test_case, test);
+	if (test_case->status == KUNIT_FAILURE) {
+		kunit_update_stats(param_stats, test->status);
+		return;
+	}
+	/* Get initial param. */
+	param_desc[0] = '\0';
+	/* TODO: Make generate_params try-catch */
+	curr_param = test_case->generate_params(test, NULL, param_desc);
+	test_case->status = KUNIT_SKIPPED;
+	kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
+		  "KTAP version 1\n");
+	kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
+		  "# Subtest: %s", test_case->name);
+	if (test->params_array.params &&
+	    test_case->generate_params == kunit_array_gen_params) {
+		kunit_log(KERN_INFO, test, KUNIT_SUBTEST_INDENT
+			  KUNIT_SUBTEST_INDENT "1..%zd\n",
+			  test->params_array.num_params);
+	}
+
+	while (curr_param) {
+		struct kunit param_test = {
+			.param_value = curr_param,
+			.param_index = ++test->param_index,
+			.parent = test,
+		};
+		kunit_init_test(&param_test, test_case->name, NULL);
+		param_test.log = test_case->log;
+		kunit_run_case_catch_errors(suite, test_case, &param_test);
+
+		if (param_desc[0] == '\0') {
+			snprintf(param_desc, sizeof(param_desc),
+				 "param-%d", param_test.param_index);
+		}
+
+		kunit_print_ok_not_ok(&param_test, KUNIT_LEVEL_CASE_PARAM,
+				      param_test.status,
+				      param_test.param_index,
+				      param_desc,
+				      param_test.status_comment);
+
+		kunit_update_stats(param_stats, param_test.status);
+
+		/* Get next param. */
+		param_desc[0] = '\0';
+		curr_param = test_case->generate_params(test, curr_param,
+							param_desc);
+	}
+	/*
+	 * TODO: Put into a try catch. Since we don't need suite->exit
+	 * for it we can't reuse kunit_try_run_cleanup for this yet.
+	 */
+	if (test_case->param_exit)
+		test_case->param_exit(test);
+	/* TODO: Put this kunit_cleanup into a try-catch. */
+	kunit_cleanup(test);
+}
+
+static noinline_for_stack void
+kunit_run_one_test(struct kunit_suite *suite, struct kunit_case *test_case,
+		   struct kunit_result_stats *suite_stats,
+		   struct kunit_result_stats *total_stats)
+{
+	struct kunit test = { .param_value = NULL, .param_index = 0 };
+	struct kunit_result_stats param_stats = { 0 };
+
+	kunit_init_test(&test, test_case->name, test_case->log);
+	if (test_case->status == KUNIT_SKIPPED) {
+		/* Test marked as skip */
+		test.status = KUNIT_SKIPPED;
+		kunit_update_stats(&param_stats, test.status);
+	} else if (!test_case->generate_params) {
+		/* Non-parameterised test. */
+		test_case->status = KUNIT_SKIPPED;
+		kunit_run_case_catch_errors(suite, test_case, &test);
+		kunit_update_stats(&param_stats, test.status);
+	} else {
+		kunit_run_param_test(suite, test_case, &test, suite_stats,
+				     total_stats, &param_stats);
+	}
+	kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE);
+
+	kunit_print_test_stats(&test, &param_stats);
+
+	kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status,
+			      kunit_test_case_num(suite, test_case),
+			      test_case->name,
+			      test.status_comment);
+
+	kunit_update_stats(suite_stats, test_case->status);
+	kunit_accumulate_stats(total_stats, param_stats);
+}
+
+
+int kunit_run_tests(struct kunit_suite *suite)
+{
 	struct kunit_case *test_case;
 	struct kunit_result_stats suite_stats = { 0 };
 	struct kunit_result_stats total_stats = { 0 };
-	const void *curr_param;
 
 	/* Taint the kernel so we know we've run tests. */
 	add_taint(TAINT_TEST, LOCKDEP_STILL_OK);
@@ -703,97 +806,13 @@ int kunit_run_tests(struct kunit_suite *suite)
 
 	kunit_print_suite_start(suite);
 
-	kunit_suite_for_each_test_case(suite, test_case) {
-		struct kunit test = { .param_value = NULL, .param_index = 0 };
-		struct kunit_result_stats param_stats = { 0 };
-
-		kunit_init_test(&test, test_case->name, test_case->log);
-		if (test_case->status == KUNIT_SKIPPED) {
-			/* Test marked as skip */
-			test.status = KUNIT_SKIPPED;
-			kunit_update_stats(&param_stats, test.status);
-		} else if (!test_case->generate_params) {
-			/* Non-parameterised test. */
-			test_case->status = KUNIT_SKIPPED;
-			kunit_run_case_catch_errors(suite, test_case, &test);
-			kunit_update_stats(&param_stats, test.status);
-		} else {
-			kunit_init_parent_param_test(test_case, &test);
-			if (test_case->status == KUNIT_FAILURE) {
-				kunit_update_stats(&param_stats, test.status);
-				goto test_case_end;
-			}
-			/* Get initial param. */
-			param_desc[0] = '\0';
-			/* TODO: Make generate_params try-catch */
-			curr_param = test_case->generate_params(&test, NULL, param_desc);
-			test_case->status = KUNIT_SKIPPED;
-			kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
-				  "KTAP version 1\n");
-			kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT
-				  "# Subtest: %s", test_case->name);
-			if (test.params_array.params &&
-			    test_case->generate_params == kunit_array_gen_params) {
-				kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT
-					  KUNIT_SUBTEST_INDENT "1..%zd\n",
-					  test.params_array.num_params);
-			}
-
-			while (curr_param) {
-				struct kunit param_test = {
-					.param_value = curr_param,
-					.param_index = ++test.param_index,
-					.parent = &test,
-				};
-				kunit_init_test(&param_test, test_case->name, NULL);
-				param_test.log = test_case->log;
-				kunit_run_case_catch_errors(suite, test_case, &param_test);
-
-				if (param_desc[0] == '\0') {
-					snprintf(param_desc, sizeof(param_desc),
-						 "param-%d", param_test.param_index);
-				}
-
-				kunit_print_ok_not_ok(&param_test, KUNIT_LEVEL_CASE_PARAM,
-						      param_test.status,
-						      param_test.param_index,
-						      param_desc,
-						      param_test.status_comment);
-
-				kunit_update_stats(&param_stats, param_test.status);
-
-				/* Get next param. */
-				param_desc[0] = '\0';
-				curr_param = test_case->generate_params(&test, curr_param,
-									param_desc);
-			}
-			/*
-			 * TODO: Put into a try catch. Since we don't need suite->exit
-			 * for it we can't reuse kunit_try_run_cleanup for this yet.
-			 */
-			if (test_case->param_exit)
-				test_case->param_exit(&test);
-			/* TODO: Put this kunit_cleanup into a try-catch. */
-			kunit_cleanup(&test);
-		}
-test_case_end:
-		kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE);
-
-		kunit_print_test_stats(&test, param_stats);
-
-		kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status,
-				      kunit_test_case_num(suite, test_case),
-				      test_case->name,
-				      test.status_comment);
-
-		kunit_update_stats(&suite_stats, test_case->status);
-		kunit_accumulate_stats(&total_stats, param_stats);
-	}
+	kunit_suite_for_each_test_case(suite, test_case)
+		kunit_run_one_test(suite, test_case, &suite_stats, &total_stats);
 
 	if (suite->suite_exit)
 		suite->suite_exit(suite);
 
-	kunit_print_suite_stats(suite, suite_stats, total_stats);
+	kunit_print_suite_stats(suite, &suite_stats, &total_stats);
 suite_end:
 	kunit_print_suite_end(suite);
 
-- 
cgit v1.2.3


From 9adfcef334bf9c6ef68eaecfca5f45d18614efe0 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 2 Mar 2026 17:14:39 +0800
Subject: sched_ext: Use READ_ONCE() for the read side of dsq->nr update

scx_bpf_dsq_nr_queued() reads dsq->nr via READ_ONCE() without holding
any lock, making dsq->nr a lock-free concurrently accessed variable.
However, dsq_mod_nr(), the sole writer of dsq->nr, only uses
WRITE_ONCE() on the write side without the matching READ_ONCE() on the
read side:

    WRITE_ONCE(dsq->nr, dsq->nr + delta);
                        ^^^^^^^
                        plain read -- KCSAN data race

The KCSAN documentation requires that if one accessor uses READ_ONCE()
or WRITE_ONCE() on a variable to annotate lock-free access, all other
accesses must also use the appropriate accessor. A plain read on the
right-hand side of WRITE_ONCE() leaves the pair incomplete and will
trigger KCSAN warnings.

Fix by using READ_ONCE() for the read side of the update:

    WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta);

This is consistent with scx_bpf_dsq_nr_queued() and makes the
concurrent access annotation complete and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 9280381f8923..4c2cf0d7d495 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -976,8 +976,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a,
 
 static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
 {
-	/* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
-	WRITE_ONCE(dsq->nr, dsq->nr + delta);
+	/*
+	 * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE()
+	 * on the read side and WRITE_ONCE() on the write side to properly
+	 * annotate the concurrent lockless access and avoid KCSAN warnings.
+	 */
+	WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta);
 }
 
 static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p)
-- 
cgit v1.2.3


From 494eaf4651975127d34d5ae6555c72dedba092c9 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 2 Mar 2026 17:14:40 +0800
Subject: sched_ext: Replace naked scx_root dereferences in kobject callbacks

scx_attr_ops_show() and scx_uevent() access scx_root->ops.name directly.
This is problematic for two reasons:

1. The file-level comment explicitly identifies naked scx_root
   dereferences as a temporary measure that needs to be replaced
   with proper per-instance access.

2. scx_attr_events_show(), the neighboring sysfs show function in
   the same group, already uses the correct pattern:

       struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);

   Having inconsistent access patterns in the same sysfs/uevent
   group is error-prone.

The kobject embedded in struct scx_sched is initialized as:

    kobject_init_and_add(&sch->kobj, &scx_ktype, NULL, "root");

so container_of(kobj, struct scx_sched, kobj) correctly retrieves
the owning scx_sched instance in both callbacks.

Replace the naked scx_root dereferences with container_of()-based
access, consistent with scx_attr_events_show() and in preparation
for proper multi-instance scx_sched support.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4c2cf0d7d495..a566d2cc8a43 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3712,7 +3712,9 @@ static void scx_kobj_release(struct kobject *kobj)
 static ssize_t scx_attr_ops_show(struct kobject *kobj,
 				 struct kobj_attribute *ka, char *buf)
 {
-	return sysfs_emit(buf, "%s\n", scx_root->ops.name);
+	struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return sysfs_emit(buf, "%s\n", sch->ops.name);
 }
 SCX_ATTR(ops);
 
@@ -3756,7 +3758,9 @@ static const struct kobj_type scx_ktype = {
 
 static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
-	return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name);
+	const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj);
+
+	return add_uevent_var(env, "SCXOPS=%s", sch->ops.name);
 }
 
 static const struct kset_uevent_ops scx_uevent_ops = {
-- 
cgit v1.2.3


From af4e9ef3d78420feb8fe58cd9a1ab80c501b3c08 Mon Sep 17 00:00:00 2001
From: David Laight <david.laight.linux@gmail.com>
Date: Mon, 2 Mar 2026 13:27:51 +0000
Subject: uaccess: Fix scoped_user_read_access() for 'pointer to const'

If a 'const struct foo __user *ptr' is used for the address passed to
scoped_user_read_access() then you get a warning/error

  uaccess.h:691:1: error: initialization discards 'const' qualifier from pointer target type [-Werror=discarded-qualifiers]

for the

  void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl)

assignment.

Fix by using 'auto' for both _tmpptr and the redeclaration of uptr.
Replace the CLASS() with explicit __cleanup() functions on uptr.

Fixes: e497310b4ffb ("uaccess: Provide scoped user access regions")
Signed-off-by: David Laight <david.laight.linux@gmail.com>
Reviewed-and-tested-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/uaccess.h | 54 ++++++++++++++++++-------------------------------
 1 file changed, 20 insertions(+), 34 deletions(-)

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1f3804245c06..809e4f7dfdbd 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { }
 /* Define RW variant so the below _mode macro expansion works */
 #define masked_user_rw_access_begin(u)	masked_user_access_begin(u)
 #define user_rw_access_begin(u, s)	user_access_begin(u, s)
-#define user_rw_access_end()		user_access_end()
 
 /* Scoped user access */
-#define USER_ACCESS_GUARD(_mode)				\
-static __always_inline void __user *				\
-class_user_##_mode##_begin(void __user *ptr)			\
-{								\
-	return ptr;						\
-}								\
-								\
-static __always_inline void					\
-class_user_##_mode##_end(void __user *ptr)			\
-{								\
-	user_##_mode##_access_end();				\
-}								\
-								\
-DEFINE_CLASS(user_ ##_mode## _access, void __user *,		\
-	     class_user_##_mode##_end(_T),			\
-	     class_user_##_mode##_begin(ptr), void __user *ptr)	\
-								\
-static __always_inline class_user_##_mode##_access_t		\
-class_user_##_mode##_access_ptr(void __user *scope)		\
-{								\
-	return scope;						\
-}
 
-USER_ACCESS_GUARD(read)
-USER_ACCESS_GUARD(write)
-USER_ACCESS_GUARD(rw)
-#undef USER_ACCESS_GUARD
+/* Cleanup wrapper functions */
+static __always_inline void __scoped_user_read_access_end(const void *p)
+{
+	user_read_access_end();
+};
+static __always_inline void __scoped_user_write_access_end(const void *p)
+{
+	user_write_access_end();
+};
+static __always_inline void __scoped_user_rw_access_end(const void *p)
+{
+	user_access_end();
+};
 
 /**
  * __scoped_user_access_begin - Start a scoped user access
@@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw)
  *
  * Don't use directly. Use scoped_masked_user_$MODE_access() instead.
  */
-#define __scoped_user_access(mode, uptr, size, elbl)					\
-for (bool done = false; !done; done = true)						\
-	for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \
-	     !done; done = true)							\
-		for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true)	\
-			/* Force modified pointer usage within the scope */		\
-			for (const typeof(uptr) uptr = _tmpptr; !done; done = true)
+#define __scoped_user_access(mode, uptr, size, elbl)				\
+for (bool done = false; !done; done = true)					\
+	for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl);	\
+	     !done; done = true)						\
+		/* Force modified pointer usage within the scope */		\
+		for (const auto uptr  __cleanup(__scoped_user_##mode##_access_end) = \
+		     _tmpptr; !done; done = true)
 
 /**
  * scoped_user_read_access_size - Start a scoped user read access with given size
-- 
cgit v1.2.3


From 3ebc98c1ae7efda949a015990280a097f4a5453a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Mon, 2 Mar 2026 09:16:22 +0100
Subject: ftrace: Add missing ftrace_lock to update_ftrace_direct_add/del

Ihor and Kumar reported splat from ftrace_get_addr_curr [1], which happened
because of the missing ftrace_lock in update_ftrace_direct_add/del functions
allowing concurrent access to ftrace internals.

The ftrace_update_ops function must be guarded by ftrace_lock, adding that.

Fixes: 05dc5e9c1fe1 ("ftrace: Add update_ftrace_direct_add function")
Fixes: 8d2c1233f371 ("ftrace: Add update_ftrace_direct_del function")
Reported-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Closes: https://lore.kernel.org/bpf/1b58ffb2-92ae-433a-ba46-95294d6edea2@linux.dev/
Tested-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20260302081622.165713-1-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/ftrace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..8baf61c9be6d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6404,6 +6404,7 @@ int update_ftrace_direct_add(struct ftrace_ops *ops, struct ftrace_hash *hash)
 			new_filter_hash = old_filter_hash;
 		}
 	} else {
+		guard(mutex)(&ftrace_lock);
 		err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH);
 		/*
 		 * new_filter_hash is dup-ed, so we need to release it anyway,
@@ -6530,6 +6531,7 @@ int update_ftrace_direct_del(struct ftrace_ops *ops, struct ftrace_hash *hash)
 			ops->func_hash->filter_hash = NULL;
 		}
 	} else {
+		guard(mutex)(&ftrace_lock);
 		err = ftrace_update_ops(ops, new_filter_hash, EMPTY_HASH);
 		/*
 		 * new_filter_hash is dup-ed, so we need to release it anyway,
-- 
cgit v1.2.3


From f8211e95dfda702ba81ea2e3e7a8c6c967f385fa Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 2 Mar 2026 09:02:39 -0800
Subject: Documentation: KVM: Formalizing taking vcpu->mutex *outside* of
 kvm->slots_lock

Explicitly document the ordering of vcpu->mutex being taken *outside* of
kvm->slots_lock.  While somewhat unintuitive since vCPUs conceptually have
narrower scope than VMs, the scope of the owning object (vCPU versus VM)
doesn't automatically carry over to the lock.  In this case, vcpu->mutex
has far broader scope than kvm->slots_lock.  As Paolo put it, it's a
"don't worry about multiple ioctls at the same time" mutex that's intended
to be taken at the outer edges of KVM.

More importantly, arm64 and x86 have gained flows that take kvm->slots_lock
inside of vcpu->mutex.  x86's kvm_inhibit_apic_access_page() is particularly
nasty, as slots_lock is taken quite deep within KVM_RUN, i.e. simply
swapping the ordering isn't an option.

Commit to the vcpu->mutex => kvm->slots_lock ordering, as vcpu->mutex
really is intended to be a "top-level" lock, whereas kvm->slots_lock is
"just" a helper lock.

Opportunistically document that vcpu->mutex is also taken outside of
slots_arch_lock, e.g. when allocating shadow roots on x86 (which is the
entire reason slots_arch_lock exists, as shadow roots must be allocated
while holding kvm->srcu)

  kvm_mmu_new_pgd()
  |
  -> kvm_mmu_reload()
     |
     -> kvm_mmu_load()
        |
        -> mmu_alloc_shadow_roots()
           |
           -> mmu_first_shadow_root_alloc()

but also when manipulating memslots in vCPU context, e.g. when inhibiting
the APIC-access page via the aforementioned kvm_inhibit_apic_access_page()

  kvm_inhibit_apic_access_page()
  |
  -> __x86_set_memory_region()
     |
     -> kvm_set_internal_memslot()
        |
        -> kvm_set_memory_region()
           |
           -> kvm_set_memslot()

Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://patch.msgid.link/20260302170239.596810-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/locking.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index ae8bce7fecbe..662231e958a0 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -17,6 +17,8 @@ The acquisition orders for mutexes are as follows:
 
 - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
 
+- vcpu->mutex is taken outside kvm->slots_lock and kvm->slots_arch_lock
+
 - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
   them together is quite rare.
 
-- 
cgit v1.2.3


From 36f6d4db3c5cb0f58fb02b1f54f9e86522d2f918 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 3 Mar 2026 00:00:04 +0800
Subject: iio: adc: ti-ads1119: Replace IRQF_ONESHOT with IRQF_NO_THREAD

As there is no threaded handler, replace devm_request_threaded_irq()
with devm_request_irq(), and as the handler calls iio_trigger_poll()
which may not be called from a threaded handler replace IRQF_ONESHOT
with IRQF_NO_THREAD.

Since commit aef30c8d569c ("genirq: Warn about using IRQF_ONESHOT
without a threaded handler"), the IRQ core checks IRQF_ONESHOT flag
in IRQ request and gives a warning if there is no threaded handler.

Fixes: a9306887eba4 ("iio: adc: ti-ads1119: Add driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads1119.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c
index 4454f28b2b58..7f771c7023b8 100644
--- a/drivers/iio/adc/ti-ads1119.c
+++ b/drivers/iio/adc/ti-ads1119.c
@@ -735,10 +735,8 @@ static int ads1119_probe(struct i2c_client *client)
 		return dev_err_probe(dev, ret, "Failed to setup IIO buffer\n");
 
 	if (client->irq > 0) {
-		ret = devm_request_threaded_irq(dev, client->irq,
-						ads1119_irq_handler,
-						NULL, IRQF_ONESHOT,
-						"ads1119", indio_dev);
+		ret = devm_request_irq(dev, client->irq, ads1119_irq_handler,
+				       IRQF_NO_THREAD, "ads1119", indio_dev);
 		if (ret)
 			return dev_err_probe(dev, ret,
 					     "Failed to allocate irq\n");
-- 
cgit v1.2.3


From 56bd57e7b161f75535df91b229b0b2c64c6e5581 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 28 Feb 2026 14:02:22 -0600
Subject: iio: add IIO_DECLARE_QUATERNION() macro

Add a new IIO_DECLARE_QUATERNION() macro that is used to declare the
field in an IIO buffer struct that contains a quaternion vector.

Quaternions are currently the only IIO data type that uses the .repeat
feature of struct iio_scan_type. This has an implicit rule that the
element in the buffer must be aligned to the entire size of the repeated
element. This macro will make that requirement explicit. Since this is
the only user, we just call the macro IIO_DECLARE_QUATERNION() instead
of something more generic.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index a9ecff191bd9..2c91b7659ce9 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -931,6 +931,18 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
 #define IIO_DECLARE_DMA_BUFFER_WITH_TS(type, name, count) \
 	__IIO_DECLARE_BUFFER_WITH_TS(type, name, count) __aligned(IIO_DMA_MINALIGN)
 
+/**
+ * IIO_DECLARE_QUATERNION() - Declare a quaternion element
+ * @type: element type of the individual vectors
+ * @name: identifier name
+ *
+ * Quaternions are a vector composed of 4 elements (W, X, Y, Z). Use this macro
+ * to declare a quaternion element in a struct to ensure proper alignment in
+ * an IIO buffer.
+ */
+#define IIO_DECLARE_QUATERNION(type, name) \
+	type name[4] __aligned(sizeof(type) * 4)
+
 struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv);
 
 /* The information at the returned address is guaranteed to be cacheline aligned */
-- 
cgit v1.2.3


From 50d4cc74b8a720a9682a9c94f7e62a5de6b2ed3a Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 28 Feb 2026 14:02:23 -0600
Subject: iio: orientation: hid-sensor-rotation: fix quaternion alignment

Restore the alignment of sampled_vals to 16 bytes by using
IIO_DECLARE_QUATERNION(). This field contains a quaternion value which
has scan_type.repeat = 4 and storagebits = 32. So the alignment must
be 16 bytes to match the assumptions of iio_storage_bytes_for_si() and
also to not break userspace.

Reported-by: Lixu Zhang <lixu.zhang@intel.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221077
Fixes: b31a74075cb4 ("iio: orientation: hid-sensor-rotation: remove unnecessary alignment")
Tested-by: Lixu Zhang <lixu.zhang@intel.com>
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/orientation/hid-sensor-rotation.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c
index e759f91a710a..6806481873be 100644
--- a/drivers/iio/orientation/hid-sensor-rotation.c
+++ b/drivers/iio/orientation/hid-sensor-rotation.c
@@ -19,7 +19,7 @@ struct dev_rot_state {
 	struct hid_sensor_common common_attributes;
 	struct hid_sensor_hub_attribute_info quaternion;
 	struct {
-		s32 sampled_vals[4];
+		IIO_DECLARE_QUATERNION(s32, sampled_vals);
 		aligned_s64 timestamp;
 	} scan;
 	int scale_pre_decml;
-- 
cgit v1.2.3


From 800ca7b88a0c0eba6fa721e043eb3ed5b10ecc4f Mon Sep 17 00:00:00 2001
From: Saket Dumbre <saket.dumbre@intel.com>
Date: Sat, 21 Feb 2026 12:36:39 +0100
Subject: ACPICA: Update the _CPC definition to match ACPI 6.6

Update the _CPC definition to also support return package sub-type of
a Package (with Integer and Buffer) as per ACPI Spec 6.6.

Link: https://github.com/acpica/acpica/commit/17a761944cc2
Signed-off-by: Saket Dumbre <saket.dumbre@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/2829238.mvXUDI8C0e@rafael.j.wysocki
---
 drivers/acpi/acpica/acpredef.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 5f70b196e0aa..6c9b5bf7d392 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -379,8 +379,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 
 	{{"_CPC", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (Ints/Bufs) */
-	PACKAGE_INFO(ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER, 0,
-		     0, 0, 0),
+	PACKAGE_INFO(ACPI_PTYPE1_VAR,
+		     ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER |
+		     ACPI_RTYPE_PACKAGE, 0, 0, 0, 0),
 
 	{{"_CR3", METHOD_0ARGS,	/* ACPI 6.0 */
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
-- 
cgit v1.2.3


From fdb12c8a24a453bdd6759979b6ef1e04ebd4beb4 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 27 Feb 2026 22:40:48 -0700
Subject: kbuild: Leave objtool binary around with 'make clean'

The difference between 'make clean' and 'make mrproper' is documented in
'make help' as:

  clean     - Remove most generated files but keep the config and
              enough build support to build external modules
  mrproper  - Remove all generated files + config + various backup files

After commit 68b4fe32d737 ("kbuild: Add objtool to top-level clean
target"), running 'make clean' then attempting to build an external
module with the resulting build directory fails with

  $ make ARCH=x86_64 O=build clean

  $ make -C build M=... MO=...
  ...
  /bin/sh: line 1: .../build/tools/objtool/objtool: No such file or directory

as 'make clean' removes the objtool binary.

Split the objtool clean target into mrproper and clean like Kbuild does
and remove all generated artifacts with 'make clean' except for the
objtool binary, which is removed with 'make mrproper'. To avoid a small
race when running the objtool clean target through both objtool_mrproper
and objtool_clean when running 'make mrproper', modify objtool's clean
up find command to avoid using find's '-delete' command by piping the
files into 'xargs rm -f' like the rest of Kbuild does.

Cc: stable@vger.kernel.org
Fixes: 68b4fe32d737 ("kbuild: Add objtool to top-level clean target")
Reported-by: Michal Suchanek <msuchanek@suse.de>
Closes: https://lore.kernel.org/20260225112633.6123-1-msuchanek@suse.de/
Reported-by: Rainer Fiebig <jrf@mailbox.org>
Closes: https://lore.kernel.org/62d12399-76e5-3d40-126a-7490b4795b17@mailbox.org/
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Tested-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20260227-avoid-objtool-binary-removal-clean-v1-1-122f3e55eae9@kernel.org
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 Makefile               | 8 ++++----
 tools/objtool/Makefile | 8 +++++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index e944c6e71e81..d76d706a5580 100644
--- a/Makefile
+++ b/Makefile
@@ -1497,13 +1497,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),)
 	$(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean
 endif
 
-PHONY += objtool_clean
+PHONY += objtool_clean objtool_mrproper
 
 objtool_O = $(abspath $(objtree))/tools/objtool
 
-objtool_clean:
+objtool_clean objtool_mrproper:
 ifneq ($(wildcard $(objtool_O)),)
-	$(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) clean
+	$(Q)$(MAKE) -sC $(abs_srctree)/tools/objtool O=$(objtool_O) srctree=$(abs_srctree) $(patsubst objtool_%,%,$@)
 endif
 
 tools/: FORCE
@@ -1686,7 +1686,7 @@ PHONY += $(mrproper-dirs) mrproper
 $(mrproper-dirs):
 	$(Q)$(MAKE) $(clean)=$(patsubst _mrproper_%,%,$@)
 
-mrproper: clean $(mrproper-dirs)
+mrproper: clean objtool_mrproper $(mrproper-dirs)
 	$(call cmd,rmfiles)
 	@find . $(RCS_FIND_IGNORE) \
 		\( -name '*.rmeta' \) \
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6964175abdfd..76bcd4e85de3 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -142,13 +142,15 @@ $(LIBSUBCMD)-clean:
 	$(Q)$(RM) -r -- $(LIBSUBCMD_OUTPUT)
 
 clean: $(LIBSUBCMD)-clean
-	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
-	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
+	$(Q)find $(OUTPUT) \( -name '*.o' -o -name '\.*.cmd' -o -name '\.*.d' \) -type f -print | xargs $(RM)
 	$(Q)$(RM) $(OUTPUT)arch/x86/lib/cpu-feature-names.c $(OUTPUT)fixdep
 	$(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.objtool
 	$(Q)$(RM) -r -- $(OUTPUT)feature
 
+mrproper: clean
+	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
+
 FORCE:
 
-.PHONY: clean FORCE
+.PHONY: clean mrproper FORCE
-- 
cgit v1.2.3


From c28b3ec3ca034fd1abc832fef46ce36eb13f8fad Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Fri, 27 Feb 2026 12:26:04 -0700
Subject: drm/amd/display: Use mpc.preblend flag to indicate 3D LUT

[WHAT]
New ASIC's 3D LUT is indicated by mpc.preblend.

Fixes: 0de2b1afea8d ("drm/amd/display: add 3D LUT colorop")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 43175f6164d32cb96362d16e357689f74298145c)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c   | 6 ++++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index 2ba98f384685..cd1e58b8defc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1706,6 +1706,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	struct dc_transfer_func *tf = &dc_plane_state->in_shaper_func;
 	struct drm_atomic_state *state = plane_state->state;
 	const struct amdgpu_device *adev = drm_to_adev(colorop->dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	const struct drm_device *dev = colorop->dev;
 	const struct drm_color_lut32 *lut3d;
 	uint32_t lut3d_size;
@@ -1722,7 +1723,7 @@ __set_dm_plane_colorop_3dlut(struct drm_plane_state *plane_state,
 	}
 
 	if (colorop_state && !colorop_state->bypass && colorop->type == DRM_COLOROP_3D_LUT) {
-		if (!adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+		if (!has_3dlut) {
 			drm_dbg(dev, "3D LUT is not supported by hardware\n");
 			return -EINVAL;
 		}
@@ -1875,6 +1876,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	struct drm_colorop *colorop = plane_state->color_pipeline;
 	struct drm_device *dev = plane_state->plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 
 	/* 1D Curve - DEGAM TF */
@@ -1907,7 +1909,7 @@ amdgpu_dm_plane_set_colorop_properties(struct drm_plane_state *plane_state,
 	if (ret)
 		return ret;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D Curve & LUT - SHAPER TF & LUT */
 		colorop = colorop->next;
 		if (!colorop) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
index f25c0ede7199..d59ba82d3d7c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
@@ -60,6 +60,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 	struct drm_colorop *ops[MAX_COLOR_PIPELINE_OPS];
 	struct drm_device *dev = plane->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 	int ret;
 	int i = 0;
 
@@ -112,7 +113,7 @@ int amdgpu_dm_initialize_default_pipeline(struct drm_plane *plane, struct drm_pr
 
 	i++;
 
-	if (adev->dm.dc->caps.color.dpp.hw_3d_lut) {
+	if (has_3dlut) {
 		/* 1D curve - SHAPER TF */
 		ops[i] = kzalloc_obj(*ops[0]);
 		if (!ops[i]) {
-- 
cgit v1.2.3


From a4fa2355e0add57253468ef13bd08f11285f3b6e Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Fri, 27 Feb 2026 12:30:38 -0700
Subject: drm/amd/display: Enable DEGAMMA and reject COLOR_PIPELINE+DEGAMMA_LUT

[WHAT]
Create DEGAMMA properties even if color pipeline is enabled, and enforce
the mutual exclusion in atomic check by rejecting any commit that
attempts to enable both COLOR_PIPELINE on the plane and DEGAMMA_LUT on
the CRTC simultaneously.

Fixes: 18a4127e9315 ("drm/amd/display: Disable CRTC degamma when color pipeline is enabled")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4963
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 196a6aa727f1f15eb54dda5e60a41543ea9397ee)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c  | 16 ++++++++--------
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c |  8 ++++++++
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 130190e8a1b2..304437c2284d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -765,15 +765,15 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	dm->adev->mode_info.crtcs[crtc_index] = acrtc;
 
 	/* Don't enable DRM CRTC degamma property for
-	 * 1. Degamma is replaced by color pipeline.
-	 * 2. DCE since it doesn't support programmable degamma anywhere.
-	 * 3. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * 1. DCE since it doesn't support programmable degamma anywhere.
+	 * 2. DCN401 since pre-blending degamma LUT doesn't apply to cursor.
+	 * Note: DEGAMMA properties are created even if the primary plane has the
+	 * COLOR_PIPELINE property. User space can use either the DEGAMMA properties
+	 * or the COLOR_PIPELINE property. An atomic commit which attempts to enable
+	 * both is rejected.
 	 */
-	if (plane->color_pipeline_property)
-		has_degamma = false;
-	else
-		has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
-			      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
+	has_degamma = dm->adev->dm.dc->caps.color.dpp.dcn_arch &&
+		      dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01;
 
 	drm_crtc_enable_color_mgmt(&acrtc->base, has_degamma ? MAX_COLOR_LUT_ENTRIES : 0,
 				   true, MAX_COLOR_LUT_ENTRIES);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 70587e5a8d46..127207e18dcb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1256,6 +1256,14 @@ static int amdgpu_dm_plane_atomic_check(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
+	/* Reject commits that attempt to use both COLOR_PIPELINE and CRTC DEGAMMA_LUT */
+	if (new_plane_state->color_pipeline && new_crtc_state->degamma_lut) {
+		drm_dbg_atomic(plane->dev,
+			       "[PLANE:%d:%s] COLOR_PIPELINE and CRTC DEGAMMA_LUT cannot be enabled simultaneously\n",
+			       plane->base.id, plane->name);
+		return -EINVAL;
+	}
+
 	ret = amdgpu_dm_plane_fill_dc_scaling_info(adev, new_plane_state, &scaling_info);
 	if (ret)
 		return ret;
-- 
cgit v1.2.3


From 389c2024cab817366e6b8345f679f41064fa94d6 Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Sat, 21 Feb 2026 10:47:59 +0530
Subject: drm/amdgpu: Enable DPG support for VCN5

This will set DPG flags for enabling power gating on GFX11_5_4

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Pratik Vishwakarma <Pratik.Vishwakarma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a503c266d70d3363ba6bffb883cd6ecdb092670c)
---
 drivers/gpu/drm/amd/amdgpu/soc21.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 8122a5cacf07..a0ad1f8a76f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -858,7 +858,9 @@ static int soc21_common_early_init(struct amdgpu_ip_block *ip_block)
 			AMD_CG_SUPPORT_IH_CG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
-		adev->pg_flags = AMD_PG_SUPPORT_VCN |
+		adev->pg_flags = AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG_DPG |
 			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_GFX_PG;
 		adev->external_rev_id = adev->rev_id + 0x1;
-- 
cgit v1.2.3


From 30d937f63bd19bbcaafa4b892eb251f8bbbf04ef Mon Sep 17 00:00:00 2001
From: Dillon Varone <Dillon.Varone@amd.com>
Date: Wed, 18 Feb 2026 14:34:28 -0500
Subject: drm/amd/display: Fallback to boot snapshot for dispclk

[WHY & HOW]
If the dentist is unavailable, fallback to reading CLKIP via the boot
snapshot to get the current dispclk.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Dillon Varone <Dillon.Varone@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2ab77600d1e55a042c02437326d3c7563e853c6c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index b91517b9fedc..eb198d52a115 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -72,7 +72,11 @@ void dcn401_initialize_min_clocks(struct dc *dc)
 		 * audio corruption. Read current DISPCLK from DENTIST and request the same
 		 * freq to ensure that the timing is valid and unchanged.
 		 */
-		clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		if (dc->clk_mgr->funcs->get_dispclk_from_dentist) {
+			clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
+		} else {
+			clocks->dispclk_khz = dc->clk_mgr->boot_snapshot.dispclk * 1000;
+		}
 	}
 	clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000;
 	clocks->fclk_p_state_change_support = true;
-- 
cgit v1.2.3


From 3b46d61890632c8f8b117147b6923bff4b42ccb7 Mon Sep 17 00:00:00 2001
From: Vladimir Yakovlev <vovchkir@gmail.com>
Date: Tue, 3 Mar 2026 01:20:17 +0300
Subject: spi: spi-dw-dma: fix print error log when wait finish transaction

If an error occurs, the device may not have a current message. In this
case, the system will crash.

In this case, it's better to use dev from the struct ctlr (struct spi_controller*).

Signed-off-by: Vladimir Yakovlev <vovchkir@gmail.com>
Link: https://patch.msgid.link/20260302222017.992228-2-vovchkir@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw-dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c
index 65adec7c7524..fe726b9b1780 100644
--- a/drivers/spi/spi-dw-dma.c
+++ b/drivers/spi/spi-dw-dma.c
@@ -271,7 +271,7 @@ static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed)
 					 msecs_to_jiffies(ms));
 
 	if (ms == 0) {
-		dev_err(&dws->ctlr->cur_msg->spi->dev,
+		dev_err(&dws->ctlr->dev,
 			"DMA transaction timed out\n");
 		return -ETIMEDOUT;
 	}
-- 
cgit v1.2.3


From 20d6f07004d639967dcb00994d56ce6d16118e9e Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 28 Feb 2026 20:01:40 -0800
Subject: lib/crypto: tests: Add a .kunitconfig file

Add a .kunitconfig file to the lib/crypto/ directory so that the crypto
library tests can be run more easily using kunit.py.  Example with UML:

    tools/testing/kunit/kunit.py run --kunitconfig=lib/crypto

Example with QEMU:

    tools/testing/kunit/kunit.py run --kunitconfig=lib/crypto --arch=arm64 --make_options LLVM=1

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260301040140.490310-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/.kunitconfig | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 lib/crypto/.kunitconfig

diff --git a/lib/crypto/.kunitconfig b/lib/crypto/.kunitconfig
new file mode 100644
index 000000000000..6b2ce28ae509
--- /dev/null
+++ b/lib/crypto/.kunitconfig
@@ -0,0 +1,34 @@
+CONFIG_KUNIT=y
+
+# These kconfig options select all the CONFIG_CRYPTO_LIB_* symbols that have a
+# corresponding KUnit test.  Those symbols cannot be directly enabled here,
+# since they are hidden symbols.
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ADIANTUM=y
+CONFIG_CRYPTO_BLAKE2B=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_CRYPTO_HCTR2=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MLDSA=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_SHA3=y
+CONFIG_INET=y
+CONFIG_IPV6=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_WIREGUARD=y
+
+CONFIG_CRYPTO_LIB_BLAKE2B_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_BLAKE2S_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_CURVE25519_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_MD5_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_MLDSA_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_NH_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_POLY1305_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_POLYVAL_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA1_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA256_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA512_KUNIT_TEST=y
+CONFIG_CRYPTO_LIB_SHA3_KUNIT_TEST=y
-- 
cgit v1.2.3


From 5d75c7bcc40a90f77f315e1c91dfb2f1b189a435 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:05 +0100
Subject: crypto: Clean up help text for CRYPTO_BLAKE2B

Btrfs stopped using this BLAKE2b implementation in commit
fe11ac191ce0ad91 ("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/98b983d2f2bddf0e5e8e1c970446c3c64527ef89.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index e2b4106ac961..8bc95e69faa5 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -876,8 +876,6 @@ config CRYPTO_BLAKE2B
 	  - blake2b-384
 	  - blake2b-512
 
-	  Used by the btrfs filesystem.
-
 	  See https://blake2.net for further information.
 
 config CRYPTO_CMAC
-- 
cgit v1.2.3


From a70d9d655fd0549dd7cd9de437eb3fbe2e78c8ab Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:06 +0100
Subject: crypto: Clean up help text for CRYPTO_SHA256

NFS, Ceph, SMB, and Btrfs stopped using this SHA-256 implementation in
commits c2c90a8b2620626c ("nfsd: use SHA-256 library API instead of
crypto_shash API"), 27c0a7b05d13a0dc ("libceph: Use HMAC-SHA256 library
instead of crypto_shash"), 924067ef183bd17f ("ksmbd: Use HMAC-SHA256
library for message signing and key generation"), and fe11ac191ce0ad91
("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/bf8e1c229b36fc5349e29701e962d0dfd4fd21b6.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 8bc95e69faa5..c84fda3acdbd 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -963,7 +963,6 @@ config CRYPTO_SHA256
 	  10118-3), including HMAC support.
 
 	  This is required for IPsec AH (XFRM_AH) and IPsec ESP (XFRM_ESP).
-	  Used by the btrfs filesystem, Ceph, NFS, and SMB.
 
 config CRYPTO_SHA512
 	tristate "SHA-384 and SHA-512"
-- 
cgit v1.2.3


From a9ad29b7ad6c5e36ffa543ceb3c4439e63186339 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:07 +0100
Subject: crypto: Clean up help text for CRYPTO_XXHASH

Btrfs stopped using this xxHash implementation in commit
fe11ac191ce0ad91 ("btrfs: switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/3b632975201074ccaa129f4901a66aff87b19742.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index c84fda3acdbd..49293b656aff 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1036,8 +1036,6 @@ config CRYPTO_XXHASH
 
 	  Extremely fast, working at speeds close to RAM limits.
 
-	  Used by the btrfs filesystem.
-
 endmenu
 
 menu "CRCs (cyclic redundancy checks)"
-- 
cgit v1.2.3


From 0ef6eb10f2e0fe38bb795b2ecdb01b8c9b536ea8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:08 +0100
Subject: crypto: Clean up help text for CRYPTO_CRC32C

Ext4, jbd2, iSCSI, NVMeoF/TCP, and Btrfs stopped using this CRC32c
implementation in commits f2b4fa19647e18a2 ("ext4: switch to using the
crc32c library"), dd348f054b24a3f5 ("jbd2: switch to using the crc32c
library"), 92186c1455a2d356 ("scsi: iscsi_tcp: Switch to using the
crc32c library"), 427fff9aff295e2c ("nvme-tcp: use crc32c() and
skb_copy_and_crc32c_datagram_iter()"), and fe11ac191ce0ad91 ("btrfs:
switch to library APIs for checksums").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/f567add7840bc612382237b3e76f3a8bdbd671e6.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 49293b656aff..5e66de2948ed 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1053,8 +1053,6 @@ config CRYPTO_CRC32C
 	  on Communications, Vol. 41, No. 6, June 1993, selected for use with
 	  iSCSI.
 
-	  Used by btrfs, ext4, jbd2, NVMeoF/TCP, and iSCSI.
-
 config CRYPTO_CRC32
 	tristate "CRC32"
 	select CRYPTO_HASH
-- 
cgit v1.2.3


From f33ac74f9cc1cdadd3921246832b2084a5dec53a Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 26 Feb 2026 15:46:09 +0100
Subject: crypto: Clean up help text for CRYPTO_CRC32

F2fs and RoCEv2 stopped using this CRC32 implementation in commits
3ca4bec40ee211cd ("f2fs: switch to using the crc32 library") and
ccca5e8aa1457231 ("RDMA/rxe: switch to using the crc32 library").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/0f76ebf05bb1b6ca50db97988f9ac20944534b4c.1772116160.git.geert+renesas@glider.be
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 5e66de2948ed..b4bb85e8e226 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1060,8 +1060,6 @@ config CRYPTO_CRC32
 	help
 	  CRC32 CRC algorithm (IEEE 802.3)
 
-	  Used by RoCEv2 and f2fs.
-
 endmenu
 
 menu "Compression"
-- 
cgit v1.2.3


From 7cbe98f7bef965241a5908d50d557008cf998aee Mon Sep 17 00:00:00 2001
From: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Date: Sun, 1 Mar 2026 18:13:14 -0300
Subject: net: dsa: realtek: rtl8365mb: fix rtl8365mb_phy_ocp_write return
 value

Function rtl8365mb_phy_ocp_write() always returns 0, even when an error
occurs during register access. This patch fixes the return value to
propagate the actual error code from regmap operations.

Link: https://lore.kernel.org/netdev/a2dfde3c-d46f-434b-9d16-1e251e449068@yahoo.com/
Fixes: 2796728460b8 ("net: dsa: realtek: rtl8365mb: serialize indirect PHY register access")
Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260301-realtek_namiltd_fix1-v1-1-43a6bb707f9c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8365mb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index c575e164368c..f938a3f701cc 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy,
 out:
 	rtl83xx_unlock(priv);
 
-	return 0;
+	return ret;
 }
 
 static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum)
-- 
cgit v1.2.3


From 3f10543c5bdd11568d1a54f5b1d955f5652e3095 Mon Sep 17 00:00:00 2001
From: Simon Baatz <gmbnomis@gmail.com>
Date: Sun, 1 Mar 2026 09:41:33 +0100
Subject: selftests/net: packetdrill: restore tcp_rcv_big_endseq.pkt

Commit 1cc93c48b5d7 ("selftests/net: packetdrill: remove tests for
tcp_rcv_*big") removed the test for the reverted commit 1d2fbaad7cd8
("tcp: stronger sk_rcvbuf checks") but also the one for commit
9ca48d616ed7 ("tcp: do not accept packets beyond window").

Restore the test with the necessary adaptation: expect a delayed ACK
instead of an immediate one, since tcp_can_ingest() does not fail
anymore for the last data packet.

Signed-off-by: Simon Baatz <gmbnomis@gmail.com>
Link: https://patch.msgid.link/20260301-tcp_rcv_big_endseq-v1-1-86ab7415ab58@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/packetdrill/tcp_rcv_big_endseq.pkt         | 44 ++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
new file mode 100644
index 000000000000..6c0f32c40f19
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh`
+
+    0 `nstat -n`
+
+// Establish a connection.
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0>
+  +.1 < . 1:1(0) ack 1 win 257
+
+  +0 accept(3, ..., ...) = 4
+
+  +0 < P. 1:4001(4000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 4001:54001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +1 < P. 5001:55001(50000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW
+  +0 < P. 70001:80001(10000) ack 1 win 257
+  +0 > .  1:1(0) ack 4001 win 5000
+
+  +0 read(4, ..., 100000) = 4000
+
+// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd
+  +0 < P. 4001:54001(50000) ack 1 win 257
+   * > .  1:1(0) ack 54001 win 0
+
+// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times.
++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "`
-- 
cgit v1.2.3


From 1939d9816dbfc057508267f0c5214f9478fbd6d1 Mon Sep 17 00:00:00 2001
From: Arthur Kiyanovski <akiyano@amazon.com>
Date: Sun, 1 Mar 2026 19:16:51 +0000
Subject: MAINTAINERS: ena: update AMAZON ETHERNET maintainers

Remove Shay Agroskin and Saeed Bishara.
Promote David Arinzon to maintainer.

Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Link: https://patch.msgid.link/20260301191652.5916-1-akiyano@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2265e2c9bfbe..7829ff2180ae 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -993,10 +993,8 @@ F:	Documentation/devicetree/bindings/thermal/amazon,al-thermal.yaml
 F:	drivers/thermal/thermal_mmio.c
 
 AMAZON ETHERNET DRIVERS
-M:	Shay Agroskin <shayagr@amazon.com>
 M:	Arthur Kiyanovski <akiyano@amazon.com>
-R:	David Arinzon <darinzon@amazon.com>
-R:	Saeed Bishara <saeedb@amazon.com>
+M:	David Arinzon <darinzon@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/device_drivers/ethernet/amazon/ena.rst
-- 
cgit v1.2.3


From a300000233a9ff842e2fb450fb9a79f7827a586d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 21 Feb 2026 12:45:25 -0800
Subject: fsverity: add dependency on 64K or smaller pages

Currently, all filesystems that support fsverity (ext4, f2fs, and btrfs)
cache the Merkle tree in the pagecache at a 64K aligned offset after the
end of the file data.  This offset needs to be a multiple of the page
size, which is guaranteed only when the page size is 64K or smaller.

64K was chosen to be the "largest reasonable page size".  But it isn't
the largest *possible* page size: the hexagon and powerpc ports of Linux
support 256K pages, though that configuration is rarely used.

For now, just disable support for FS_VERITY in these odd configurations
to ensure it isn't used in cases where it would have incorrect behavior.

Fixes: 671e67b47e9f ("fs-verity: add Kconfig and the helper functions for hashing")
Reported-by: Christoph Hellwig <hch@lst.de>
Closes: https://lore.kernel.org/r/20260119063349.GA643@lst.de
Reviewed-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lore.kernel.org/r/20260221204525.30426-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 fs/verity/Kconfig | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 76d1c5971b82..b20882963ffb 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -2,6 +2,9 @@
 
 config FS_VERITY
 	bool "FS Verity (read-only file-based authenticity protection)"
+	# Filesystems cache the Merkle tree at a 64K aligned offset in the
+	# pagecache.  That approach assumes the page size is at most 64K.
+	depends on PAGE_SHIFT <= 16
 	select CRYPTO_HASH_INFO
 	select CRYPTO_LIB_SHA256
 	select CRYPTO_LIB_SHA512
-- 
cgit v1.2.3


From 93992667d0ab695ac30ceec91a516fd4bf725d75 Mon Sep 17 00:00:00 2001
From: Rong Zhang <i@rong.moe>
Date: Tue, 3 Mar 2026 01:32:59 +0800
Subject: ALSA: doc: usb-audio: Add doc for QUIRK_FLAG_SKIP_IFACE_SETUP

QUIRK_FLAG_SKIP_IFACE_SETUP was introduced into usb-audio before without
appropriate documentation, so add it.

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Cc: stable@vger.kernel.org
Signed-off-by: Rong Zhang <i@rong.moe>
Link: https://patch.msgid.link/20260302173300.322673-1-i@rong.moe
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/alsa-configuration.rst | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index 0a4eaa7d66dd..55b845d38236 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -2372,6 +2372,10 @@ quirk_flags
           audible volume
         * bit 25: ``mixer_capture_min_mute``
           Similar to bit 24 but for capture streams
+        * bit 26: ``skip_iface_setup``
+          Skip the probe-time interface setup (usb_set_interface,
+          init_pitch, init_sample_rate); redundant with
+          snd_usb_endpoint_prepare() at stream-open time
 
 This module supports multiple devices, autoprobe and hotplugging.
 
-- 
cgit v1.2.3


From 83307aebe6a1a4fddf5dec6071716ce251da9cc9 Mon Sep 17 00:00:00 2001
From: wangdicheng <wangdicheng@kylinos.cn>
Date: Tue, 3 Mar 2026 13:42:42 +0800
Subject: ALSA: hda/senary: Use codec->core.afg for GPIO access

Replace the hardcoded GPIO node ID (0x01) with codec->core.afg.
This follows the standard HDA driver practice and makes the driver
more robust against different hardware configurations.

Signed-off-by: wangdicheng <wangdicheng@kylinos.cn>
Link: https://patch.msgid.link/20260303054242.318062-1-wangdich9700@163.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/senarytech.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/hda/codecs/senarytech.c b/sound/hda/codecs/senarytech.c
index 3a50d4b3a064..8822d4dc5e36 100644
--- a/sound/hda/codecs/senarytech.c
+++ b/sound/hda/codecs/senarytech.c
@@ -19,9 +19,6 @@
 #include "hda_jack.h"
 #include "generic.h"
 
-/* GPIO node ID */
-#define SENARY_GPIO_NODE	0x01
-
 struct senary_spec {
 	struct hda_gen_spec gen;
 
@@ -123,11 +120,11 @@ static void senary_init_gpio_led(struct hda_codec *codec)
 	unsigned int mask = spec->gpio_mute_led_mask | spec->gpio_mic_led_mask;
 
 	if (mask) {
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_MASK,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_MASK,
 				    mask);
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DIRECTION,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DIRECTION,
 				    mask);
-		snd_hda_codec_write(codec, SENARY_GPIO_NODE, 0, AC_VERB_SET_GPIO_DATA,
+		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DATA,
 				    spec->gpio_led);
 	}
 }
-- 
cgit v1.2.3


From 8fb54c7307f6add04246d2f7845e42ecd41950fe Mon Sep 17 00:00:00 2001
From: MeiChia Chiu <MeiChia.Chiu@mediatek.com>
Date: Tue, 3 Mar 2026 13:47:25 +0800
Subject: wifi: mac80211: fix missing ieee80211_eml_params member
 initialization

The missing initialization causes driver to misinterpret the EML control bitmap,
resulting in incorrect link bitmap handling.

Fixes: 0d95280a2d54e ("wifi: mac80211: Add eMLSR/eMLMR action frame parsing support")
Signed-off-by: MeiChia Chiu <MeiChia.Chiu@mediatek.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260303054725.471548-1-MeiChia.Chiu@mediatek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/eht.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c
index 75096b2195d2..078e1e23d8d1 100644
--- a/net/mac80211/eht.c
+++ b/net/mac80211/eht.c
@@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata,
 	u8 *ptr = mgmt->u.action.u.eml_omn.variable;
 	struct ieee80211_eml_params eml_params = {
 		.link_id = status->link_id,
+		.control = control,
 	};
 	struct sta_info *sta;
 	int opt_len = 0;
-- 
cgit v1.2.3


From 398c0c8bbc8f5a9d2f43863275a427a9d3720b6f Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Mon, 2 Mar 2026 16:59:55 -0500
Subject: dt-bindings: auxdisplay: ht16k33: Use unevaluatedProperties to fix
 common property warning

Change additionalProperties to unevaluatedProperties because it refs to
/schemas/input/matrix-keymap.yaml.

Fix below CHECK_DTBS warnings:
arch/arm/boot/dts/nxp/imx/imx6dl-victgo.dtb: keypad@70 (holtek,ht16k33): 'keypad,num-columns', 'keypad,num-rows' do not match any of the regexes: '^pinctrl-[0-9]+$'
        from schema $id: http://devicetree.org/schemas/auxdisplay/holtek,ht16k33.yaml#

Fixes: f12b457c6b25c ("dt-bindings: auxdisplay: ht16k33: Convert to json-schema")
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml b/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml
index b90eec2077b4..fe1272e86467 100644
--- a/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml
+++ b/Documentation/devicetree/bindings/auxdisplay/holtek,ht16k33.yaml
@@ -66,7 +66,7 @@ then:
   required:
     - refresh-rate-hz
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
cgit v1.2.3


From 3f27958b729a2337336a6b50e0d9aee5fbbce816 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Tue, 3 Mar 2026 14:09:58 +0800
Subject: sched_ext: Use READ_ONCE() for plain reads of scx_watchdog_timeout

scx_watchdog_timeout is written with WRITE_ONCE() in scx_enable():

    WRITE_ONCE(scx_watchdog_timeout, timeout);

However, three read-side accesses use plain reads without the matching
READ_ONCE():

    /* check_rq_for_timeouts() - L2824 */
    last_runnable + scx_watchdog_timeout

    /* scx_watchdog_workfn() - L2852 */
    scx_watchdog_timeout / 2

    /* scx_enable() - L5179 */
    scx_watchdog_timeout / 2

The KCSAN documentation requires that if one accessor uses WRITE_ONCE()
to annotate lock-free access, all other accesses must also use the
appropriate accessor. Plain reads alongside WRITE_ONCE() leave the pair
incomplete and can trigger KCSAN warnings.

Note that scx_tick() already uses the correct READ_ONCE() annotation:

    last_check + READ_ONCE(scx_watchdog_timeout)

Fix the three remaining plain reads to match, making all accesses to
scx_watchdog_timeout consistently annotated and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index a566d2cc8a43..2ba69b302368 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2739,7 +2739,7 @@ static bool check_rq_for_timeouts(struct rq *rq)
 		unsigned long last_runnable = p->scx.runnable_at;
 
 		if (unlikely(time_after(jiffies,
-					last_runnable + scx_watchdog_timeout))) {
+					last_runnable + READ_ONCE(scx_watchdog_timeout)))) {
 			u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);
 
 			scx_exit(sch, SCX_EXIT_ERROR_STALL, 0,
@@ -2767,7 +2767,7 @@ static void scx_watchdog_workfn(struct work_struct *work)
 		cond_resched();
 	}
 	queue_delayed_work(system_unbound_wq, to_delayed_work(work),
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 }
 
 void scx_tick(struct rq *rq)
@@ -5081,7 +5081,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	WRITE_ONCE(scx_watchdog_timeout, timeout);
 	WRITE_ONCE(scx_watchdog_timestamp, jiffies);
 	queue_delayed_work(system_unbound_wq, &scx_watchdog_work,
-			   scx_watchdog_timeout / 2);
+			   READ_ONCE(scx_watchdog_timeout) / 2);
 
 	/*
 	 * Once __scx_enabled is set, %current can be switched to SCX anytime.
-- 
cgit v1.2.3


From 9af832c0a76eedce169c4c6360e4e20d8a0c9ab1 Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:15 +0800
Subject: tools/sched_ext: Add -fms-extensions to bpf build flags

Similar to commit 835a50753579 ("selftests/bpf: Add -fms-extensions to
bpf build flags") and commit 639f58a0f480 ("bpftool: Fix build warnings
due to MS extensions")

The kernel is now built with -fms-extensions, therefore
generated vmlinux.h contains types like:
struct aes_key {
        struct aes_enckey;
        union aes_invkey_arch inv_k;
};

struct ns_common {
	...
        union {
                struct ns_tree;
                struct callback_head ns_rcu;
        };
};

Which raise warning like below when building scx scheduler:

tools/sched_ext/build/include/vmlinux.h:50533:3: warning:
declaration does not declare anything [-Wmissing-declarations]
 50533 |                 struct ns_tree;
       |                 ^
Fix it by using -fms-extensions and -Wno-microsoft-anon-tag flags
to build bpf programs that #include "vmlinux.h"

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/sched_ext/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile
index 47ad7444677e..21554f089692 100644
--- a/tools/sched_ext/Makefile
+++ b/tools/sched_ext/Makefile
@@ -122,6 +122,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     -I../../include							\
 	     $(call get_sys_includes,$(CLANG))					\
 	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building
-- 
cgit v1.2.3


From 01a867c2e090cb440c8f27158e8650c8ddefec8e Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:16 +0800
Subject: selftests/sched_ext: Add -fms-extensions to bpf build flags

Similar to commit 835a50753579 ("selftests/bpf: Add -fms-extensions to
bpf build flags") and commit 639f58a0f480 ("bpftool: Fix build warnings
due to MS extensions")

Fix "declaration does not declare anything" warning by using
-fms-extensions and -Wno-microsoft-anon-tag flags to build bpf programs
that #include "vmlinux.h"

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/Makefile | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 2c601a7eaff5..006300ac6dff 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
 	     $(CLANG_SYS_INCLUDES) 						\
 	     -Wall -Wno-compare-distinct-pointer-types				\
 	     -Wno-incompatible-function-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
 	     -O2 -mcpu=v3
 
 # sort removes libbpf duplicates when not cross-building
-- 
cgit v1.2.3


From 75ad51825933575906394d0d5db04586b02db00a Mon Sep 17 00:00:00 2001
From: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Date: Tue, 3 Mar 2026 15:23:17 +0800
Subject: selftests/sched_ext: Fix peek_dsq.bpf.c compile error for clang 17

When compiling sched_ext selftests using clang 17.0.6, it raised
compiler crash and build error:

Error at line 68: Unsupport signed division for DAG: 0x55b2f9a60240:
i64 = sdiv 0x55b2f9a609b0, Constant:i64<100>, peek_dsq.bpf.c:68:25 @[
peek_dsq.bpf.c:95:4 @[ peek_dsq.bpf.c:169:8 @[ peek
_dsq.bpf.c:140:6 ] ] ]Please convert to unsigned div/mod

After digging, it's not a compiler error, clang supported Signed division
only when using -mcpu=v4, while we use -mcpu=v3 currently, the better way
is to use unsigned div, see [1] for details.

[1] https://github.com/llvm/llvm-project/issues/70433

Signed-off-by: Zhao Mengmeng <zhaomengmeng@kylinos.cn>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/peek_dsq.bpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
index a3faf5bb49d6..784f2f6c1af9 100644
--- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
@@ -58,14 +58,14 @@ static void record_peek_result(long pid)
 {
 	u32 slot_key;
 	long *slot_pid_ptr;
-	int ix;
+	u32 ix;
 
 	if (pid <= 0)
 		return;
 
 	/* Find an empty slot or one with the same PID */
 	bpf_for(ix, 0, 10) {
-		slot_key = (pid + ix) % MAX_SAMPLES;
+		slot_key = ((u64)pid + ix) % MAX_SAMPLES;
 		slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key);
 		if (!slot_pid_ptr)
 			continue;
-- 
cgit v1.2.3


From 08d9a4580f71120be3c5b221af32dca00a48ceb0 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Fri, 20 Feb 2026 14:19:59 +0530
Subject: tee: shm: Remove refcounting of kernel pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Earlier TEE subsystem assumed to refcount all the memory pages to be
shared with TEE implementation to be refcounted. However, the slab
allocations within the kernel don't allow refcounting kernel pages.

It is rather better to trust the kernel clients to not free pages while
being shared with TEE implementation. Hence, remove refcounting of kernel
pages from register_shm_helper() API.

Fixes: b9c0e49abfca ("mm: decline to manipulate the refcount on a slab page")
Reported-by: Marco Felsch <m.felsch@pengutronix.de>
Reported-by: Sven Püschel <s.pueschel@pengutronix.de>
Signed-off-by: Matthew Wilcox <willy@infradead.org>
Co-developed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Tested-by: Sven Püschel <s.pueschel@pengutronix.de>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/tee_shm.c | 27 ---------------------------
 1 file changed, 27 deletions(-)

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 6c5b9e352e5e..e9ea9f80cfd9 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -23,29 +23,11 @@ struct tee_shm_dma_mem {
 	struct page *page;
 };
 
-static void shm_put_kernel_pages(struct page **pages, size_t page_count)
-{
-	size_t n;
-
-	for (n = 0; n < page_count; n++)
-		put_page(pages[n]);
-}
-
-static void shm_get_kernel_pages(struct page **pages, size_t page_count)
-{
-	size_t n;
-
-	for (n = 0; n < page_count; n++)
-		get_page(pages[n]);
-}
-
 static void release_registered_pages(struct tee_shm *shm)
 {
 	if (shm->pages) {
 		if (shm->flags & TEE_SHM_USER_MAPPED)
 			unpin_user_pages(shm->pages, shm->num_pages);
-		else
-			shm_put_kernel_pages(shm->pages, shm->num_pages);
 
 		kfree(shm->pages);
 	}
@@ -477,13 +459,6 @@ register_shm_helper(struct tee_context *ctx, struct iov_iter *iter, u32 flags,
 		goto err_put_shm_pages;
 	}
 
-	/*
-	 * iov_iter_extract_kvec_pages does not get reference on the pages,
-	 * get a reference on them.
-	 */
-	if (iov_iter_is_kvec(iter))
-		shm_get_kernel_pages(shm->pages, num_pages);
-
 	shm->offset = off;
 	shm->size = len;
 	shm->num_pages = num_pages;
@@ -499,8 +474,6 @@ register_shm_helper(struct tee_context *ctx, struct iov_iter *iter, u32 flags,
 err_put_shm_pages:
 	if (!iov_iter_is_kvec(iter))
 		unpin_user_pages(shm->pages, shm->num_pages);
-	else
-		shm_put_kernel_pages(shm->pages, shm->num_pages);
 err_free_shm_pages:
 	kfree(shm->pages);
 err_free_shm:
-- 
cgit v1.2.3


From 7ae0d8f1abbbba6f98cac735145e1206927c67d9 Mon Sep 17 00:00:00 2001
From: wangdicheng <wangdicheng@kylinos.cn>
Date: Tue, 3 Mar 2026 16:15:16 +0800
Subject: ALSA: hda/senary: Ensure EAPD is enabled during init

The driver sets spec->gen.own_eapd_ctl to take manual control of the
EAPD (External Amplifier). However, senary_init does not turn on the
EAPD, while senary_shutdown turns it off.

Since the generic driver skips EAPD handling when own_eapd_ctl is set,
the EAPD remains off after initialization (e.g., after resume), leaving
the codec in a non-functional state.

Explicitly call senary_auto_turn_eapd in senary_init to ensure the EAPD
is enabled and the codec is functional.

Signed-off-by: wangdicheng <wangdicheng@kylinos.cn>
Link: https://patch.msgid.link/20260303081516.583438-1-wangdich9700@163.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/senarytech.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/hda/codecs/senarytech.c b/sound/hda/codecs/senarytech.c
index 8822d4dc5e36..6239a25bb8f3 100644
--- a/sound/hda/codecs/senarytech.c
+++ b/sound/hda/codecs/senarytech.c
@@ -25,6 +25,7 @@ struct senary_spec {
 	/* extra EAPD pins */
 	unsigned int num_eapds;
 	hda_nid_t eapds[4];
+	bool dynamic_eapd;
 	hda_nid_t mute_led_eapd;
 
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
@@ -131,8 +132,12 @@ static void senary_init_gpio_led(struct hda_codec *codec)
 
 static int senary_init(struct hda_codec *codec)
 {
+	struct senary_spec *spec = codec->spec;
+
 	snd_hda_gen_init(codec);
 	senary_init_gpio_led(codec);
+	if (!spec->dynamic_eapd)
+		senary_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT);
 
 	return 0;
-- 
cgit v1.2.3


From 479d589b40b836442bbdadc3fdb37f001bb67f26 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 26 Feb 2026 16:03:01 +0800
Subject: bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is
 loaded

bond_option_mode_set() already rejects mode changes that would make a
loaded XDP program incompatible via bond_xdp_check().  However,
bond_option_xmit_hash_policy_set() has no such guard.

For 802.3ad and balance-xor modes, bond_xdp_check() returns false when
xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually
absent due to hardware offload.  This means a user can:

1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode
   with a compatible xmit_hash_policy (e.g. layer2+3).
2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.

This leaves bond->xdp_prog set but bond_xdp_check() now returning false
for the same device.  When the bond is later destroyed, dev_xdp_uninstall()
calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits
the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering:

WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL))

Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an
XDP program is loaded on a bond in 802.3ad or balance-xor mode.

commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP")
introduced bond_xdp_check() which returns false for 802.3ad/balance-xor
modes when xmit_hash_policy is vlan+srcmac.  The check was wired into
bond_xdp_set() to reject XDP attachment with an incompatible policy, but
the symmetric path -- preventing xmit_hash_policy from being changed to an
incompatible value after XDP is already loaded -- was left unguarded in
bond_option_xmit_hash_policy_set().

Note:
commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode")
later added a similar guard to bond_option_mode_set(), but
bond_option_xmit_hash_policy_set() remained unprotected.

Reported-by: syzbot+5a287bcdc08104bc3132@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6995aff6.050a0220.2eeac1.014e.GAE@google.com/T/
Fixes: 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP")
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260226080306.98766-2-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c    | 9 +++++++--
 drivers/net/bonding/bond_options.c | 2 ++
 include/net/bonding.h              | 1 +
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a1de08ee3815..14ed91391fcc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-bool bond_xdp_check(struct bonding *bond, int mode)
+bool __bond_xdp_check(int mode, int xmit_policy)
 {
 	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
@@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 		/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
 		 * payload is not in the packet due to hardware offload.
 		 */
-		if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
+		if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
 			return true;
 		fallthrough;
 	default:
@@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 	}
 }
 
+bool bond_xdp_check(struct bonding *bond, int mode)
+{
+	return __bond_xdp_check(mode, bond->params.xmit_policy);
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index dcee384c2f06..7380cc4ee75a 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1575,6 +1575,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond,
 static int bond_option_xmit_hash_policy_set(struct bonding *bond,
 					    const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value))
+		return -EOPNOTSUPP;
 	netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.xmit_policy = newval->value;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 4ad5521e7731..395c6e281c5f 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool __bond_xdp_check(int mode, int xmit_policy);
 bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);
-- 
cgit v1.2.3


From 181cafbd8a01d22f3078a84f079c4a7cc0653068 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 26 Feb 2026 16:03:02 +0800
Subject: selftests/bpf: add test for xdp_bonding xmit_hash_policy compat

Add a selftest to verify that changing xmit_hash_policy to vlan+srcmac
is rejected when a native XDP program is loaded on a bond in 802.3ad
mode.  Without the fix in bond_option_xmit_hash_policy_set(), the change
succeeds silently, creating an inconsistent state that triggers a kernel
WARNING in dev_xdp_uninstall() when the bond is torn down.

The test attaches native XDP to a bond0 (802.3ad, layer2+3), then
attempts to switch xmit_hash_policy to vlan+srcmac and asserts the
operation fails.  It also verifies the change succeeds after XDP is
detached, confirming the rejection is specific to the XDP-loaded state.

Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260226080306.98766-3-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../testing/selftests/bpf/prog_tests/xdp_bonding.c | 58 ++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index fb952703653e..e8ea26464349 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -610,6 +610,61 @@ out:
 	system("ip link del bond");
 }
 
+/*
+ * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a
+ * native XDP program is loaded on a bond in 802.3ad or balance-xor mode.
+ * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely
+ * changing the policy creates an inconsistency that triggers a WARNING in
+ * dev_xdp_uninstall() during device teardown.
+ */
+static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons)
+{
+	struct nstoken *nstoken = NULL;
+	int bond_ifindex = -1;
+	int xdp_fd, err;
+
+	SYS(out, "ip netns add ns_xmit_policy");
+	nstoken = open_netns("ns_xmit_policy");
+	if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy"))
+		goto out;
+
+	/* 802.3ad with layer2+3 policy: native XDP is supported */
+	SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3");
+	SYS(out, "ip link add veth0 type veth peer name veth0p");
+	SYS(out, "ip link set veth0 master bond0");
+	SYS(out, "ip link set bond0 up");
+
+	bond_ifindex = if_nametoindex("bond0");
+	if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex"))
+		goto out;
+
+	xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog);
+	if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd"))
+		goto out;
+
+	err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL);
+	if (!ASSERT_OK(err, "attach XDP to bond0"))
+		goto out;
+
+	/* With XDP loaded, switching to vlan+srcmac must be rejected */
+	err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null");
+	ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail");
+
+	/* Detach XDP first, then the same change must succeed */
+	ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL),
+		  "detach XDP from bond0");
+
+	bond_ifindex = -1;
+	err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null");
+	ASSERT_OK(err, "vlan+srcmac change without XDP should succeed");
+
+out:
+	if (bond_ifindex > 0)
+		bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL);
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del ns_xmit_policy");
+}
+
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
@@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void)
 				test_case->xmit_policy);
 	}
 
+	if (test__start_subtest("xdp_bonding_xmit_policy_compat"))
+		test_xdp_bonding_xmit_policy_compat(&skeletons);
+
 	if (test__start_subtest("xdp_bonding_redirect_multi"))
 		test_xdp_bonding_redirect_multi(&skeletons);
 
-- 
cgit v1.2.3


From 18c04a808c436d629d5812ce883e3822a5f5a47f Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:57 +0000
Subject: octeon_ep: Relocate counter updates before NAPI

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion,
and replace napi_complete with napi_complete_done.

Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly
   synchronized.
napi_complete_done (vs napi_complete) allows for better
interrupt coalescing.

Fixes: 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-2-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeon_ep/octep_main.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index ec55eb2a6c04..bb5f21b33508 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -554,12 +554,12 @@ static void octep_clean_irqs(struct octep_device *oct)
 }
 
 /**
- * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -575,7 +575,17 @@ static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
-	wmb();
+	smp_wmb();
+}
+
+/**
+ * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+{
 	writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -601,7 +611,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
-	napi_complete(napi);
+	octep_update_pkt(ioq_vector->iq, ioq_vector->oq);
+	napi_complete_done(napi, rx_done);
 	octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 	return rx_done;
 }
-- 
cgit v1.2.3


From 43b3160cb639079a15daeb5f080120afbfbfc918 Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:58 +0000
Subject: octeon_ep: avoid compiler and IQ/OQ reordering

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx
variable access to prevent compiler optimization and reordering.
Additionally, ensure IO queue OUT/IN_CNT registers are flushed
by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count,
etc., causing stale values to be used when calculating packets to process
or register updates to send to hardware. The Octeon hardware requires a
read-back after writing to OUT_CNT/IN_CNT registers to ensure the write
has been flushed through any posted write buffers before the interrupt
resend bit is set. Without this, we have observed cases where the hardware
didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler
from performing optimizations like caching in registers, load tearing etc.

Fixes: 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-3-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/marvell/octeon_ep/octep_main.c    | 21 ++++++++++-------
 drivers/net/ethernet/marvell/octeon_ep/octep_rx.c  | 27 +++++++++++++++-------
 2 files changed, 32 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index bb5f21b33508..028dd55604ea 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -561,17 +561,22 @@ static void octep_clean_irqs(struct octep_device *oct)
  */
 static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
index f2a7c6a76c74..74de19166488 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c
@@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 				      struct octep_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
 
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
 	 * reached half its max value.
@@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 	u16 rx_ol_flags;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_device *oct = oq->octep_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_oq_process_rx(oct, oq,
 						       pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 
-- 
cgit v1.2.3


From 2ae7d20fb24f598f60faa8f6ecc856dac782261a Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:13:59 +0000
Subject: octeon_ep_vf: Relocate counter updates before NAPI

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion.
Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly
   synchronized.

Fixes: 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-4-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c   | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 562fe945b422..0e76f671a226 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -286,12 +286,13 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 }
 
 /**
- * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
+
+static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -308,6 +309,17 @@ static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *
 
 	/* Flush the previous wrties before writing to RESEND bit */
 	smp_wmb();
+}
+
+/**
+ * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq,
+				    struct octep_vf_oq *oq)
+{
 	writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -333,6 +345,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
+	octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq);
 	if (likely(napi_complete_done(napi, rx_done)))
 		octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 
-- 
cgit v1.2.3


From 6c73126ecd1080351b468fe43353b2f705487f44 Mon Sep 17 00:00:00 2001
From: Vimlesh Kumar <vimleshk@marvell.com>
Date: Fri, 27 Feb 2026 09:14:00 +0000
Subject: octeon_ep_vf: avoid compiler and IQ/OQ reordering

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx
variable access to prevent compiler optimization and reordering.
Additionally, ensure IO queue OUT/IN_CNT registers are flushed
by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count,
etc., causing stale values to be used when calculating packets to process
or register updates to send to hardware. The Octeon hardware requires a
read-back after writing to OUT_CNT/IN_CNT registers to ensure the write
has been flushed through any posted write buffers before the interrupt
resend bit is set. Without this, we have observed cases where the hardware
didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler
from performing optimizations like caching in registers, load tearing etc.

Fixes: 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
Signed-off-by: Sathesh Edara <sedara@marvell.com>
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Signed-off-by: Vimlesh Kumar <vimleshk@marvell.com>
Link: https://patch.msgid.link/20260227091402.1773833-5-vimleshk@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeon_ep_vf/octep_vf_main.c  | 21 +++++++++-------
 .../ethernet/marvell/octeon_ep_vf/octep_vf_rx.c    | 28 +++++++++++++++-------
 2 files changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
index 0e76f671a226..7f1b93cffb98 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c
@@ -294,17 +294,22 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 
 static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
index 6f865dbbba6c..b579d5b545c4 100644
--- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
+++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c
@@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 					 struct octep_vf_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
+
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
@@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 	struct sk_buff *skb;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_vf_device *oct = oq->octep_vf_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_vf_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_vf_oq_process_rx(oct, oq,
 							  pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 
-- 
cgit v1.2.3


From d98c24617a831e92e7224a07dcaed2dd0b02af96 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:24 -0800
Subject: wifi: cw1200: Fix locking in error paths

cw1200_wow_suspend() must only return with priv->conf_mutex locked if it
returns zero. This mutex must be unlocked if an error is returned. Add
mutex_unlock() calls to the error paths from which that call is missing.
This has been detected by the Clang thread-safety analyzer.

Fixes: a910e4a94f69 ("cw1200: add driver for the ST-E CW1100 & CW1200 WLAN chipsets")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223220102.2158611-25-bart.vanassche@linux.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/st/cw1200/pm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c
index 120f0379f81d..84eb15d729c7 100644
--- a/drivers/net/wireless/st/cw1200/pm.c
+++ b/drivers/net/wireless/st/cw1200/pm.c
@@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		wiphy_err(priv->hw->wiphy,
 			  "PM request failed: %d. WoW is disabled.\n", ret);
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EBUSY;
 	}
 
 	/* Force resume if event is coming from the device. */
 	if (atomic_read(&priv->bh_rx)) {
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EAGAIN;
 	}
 
-- 
cgit v1.2.3


From 72c6df8f284b3a49812ce2ac136727ace70acc7c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 23 Feb 2026 14:00:25 -0800
Subject: wifi: wlcore: Fix a locking bug

Make sure that wl->mutex is locked before it is unlocked. This has been
detected by the Clang thread-safety analyzer.

Fixes: 45aa7f071b06 ("wlcore: Use generic runtime pm calls for wowlan elp configuration")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260223220102.2158611-26-bart.vanassche@linux.dev
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wlcore/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 17dd417756f2..1c340a4a0930 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -1875,6 +1875,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		     wl->wow_enabled);
 	WARN_ON(!wl->wow_enabled);
 
+	mutex_lock(&wl->mutex);
+
 	ret = pm_runtime_force_resume(wl->dev);
 	if (ret < 0) {
 		wl1271_error("ELP wakeup failure!");
@@ -1891,8 +1893,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		run_irq_work = true;
 	spin_unlock_irqrestore(&wl->wl_lock, flags);
 
-	mutex_lock(&wl->mutex);
-
 	/* test the recovery flag before calling any SDIO functions */
 	pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS,
 				    &wl->flags);
-- 
cgit v1.2.3


From 60862846308627e9e15546bb647a00de44deb27b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:14 +0100
Subject: wifi: mt76: mt7996: Fix possible oob access in
 mt7996_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes: 98686cd21624c ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-1-b0f6d1ad4850@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 2560e2f46e89..d4f3ee943b47 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -800,6 +800,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
 		if (is_mt7990(&dev->mt76))
-- 
cgit v1.2.3


From c41a9abd6ae31d130e8f332e7c8800c4c866234b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:15 +0100
Subject: wifi: mt76: mt7925: Fix possible oob access in
 mt7925_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes: c948b5da6bbec ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-2-b0f6d1ad4850@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index 871b67101976..0d9435900423 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -668,6 +668,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ)
 		tid = MT_TX_ADDBA;
-- 
cgit v1.2.3


From 4e10a730d1b511ff49723371ed6d694dd1b2c785 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 26 Feb 2026 20:11:16 +0100
Subject: wifi: mt76: Fix possible oob access in
 mt76_connac2_mac_write_txwi_80211()

Check frame length before accessing the mgmt fields in
mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob
access.

Fixes: 577dbc6c656d ("mt76: mt7915: enable offloading of sequence number assignment")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260226-mt76-addba-req-oob-access-v1-3-b0f6d1ad4850@kernel.org
[fix check to also cover mgmt->u.action.u.addba_req.capab,
correct Fixes tag]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index 3304b5971be0..b41ca1410da9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -413,6 +413,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + 1 + 2 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
 		u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab);
-- 
cgit v1.2.3


From 710f5c76580306cdb9ec51fac8fcf6a8faff7821 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 27 Feb 2026 17:26:03 +0000
Subject: indirect_call_wrapper: do not reevaluate function pointer

We have an increasing number of READ_ONCE(xxx->function)
combined with INDIRECT_CALL_[1234]() helpers.

Unfortunately this forces INDIRECT_CALL_[1234]() to read
xxx->function many times, which is not what we wanted.

Fix these macros so that xxx->function value is not reloaded.

$ scripts/bloat-o-meter -t vmlinux.0 vmlinux
add/remove: 0/0 grow/shrink: 1/65 up/down: 122/-1084 (-962)
Function                                     old     new   delta
ip_push_pending_frames                        59     181    +122
ip6_finish_output                            687     681      -6
__udp_enqueue_schedule_skb                  1078    1072      -6
ioam6_output                                2319    2312      -7
xfrm4_rcv_encap_finish2                       64      56      -8
xfrm4_output                                 297     289      -8
vrf_ip_local_out                             278     270      -8
vrf_ip6_local_out                            278     270      -8
seg6_input_finish                             64      56      -8
rpl_output                                   700     692      -8
ipmr_forward_finish                          124     116      -8
ip_forward_finish                            143     135      -8
ip6mr_forward2_finish                        100      92      -8
ip6_forward_finish                            73      65      -8
input_action_end_bpf                        1091    1083      -8
dst_input                                     52      44      -8
__xfrm6_output                               801     793      -8
__xfrm4_output                                83      75      -8
bpf_input                                    500     491      -9
__tcp_check_space                            530     521      -9
input_action_end_dt6                         291     280     -11
vti6_tnl_xmit                               1634    1622     -12
bpf_xmit                                    1203    1191     -12
rpl_input                                    497     483     -14
rawv6_send_hdrinc                           1355    1341     -14
ndisc_send_skb                              1030    1016     -14
ipv6_srh_rcv                                1377    1363     -14
ip_send_unicast_reply                       1253    1239     -14
ip_rcv_finish                                226     212     -14
ip6_rcv_finish                               300     286     -14
input_action_end_x_core                      205     191     -14
input_action_end_x                           355     341     -14
input_action_end_t                           205     191     -14
input_action_end_dx6_finish                  127     113     -14
input_action_end_dx4_finish                  373     359     -14
input_action_end_dt4                         426     412     -14
input_action_end_core                        186     172     -14
input_action_end_b6_encap                    292     278     -14
input_action_end_b6                          198     184     -14
igmp6_send                                  1332    1318     -14
ip_sublist_rcv                               864     848     -16
ip6_sublist_rcv                             1091    1075     -16
ipv6_rpl_srh_rcv                            1937    1920     -17
xfrm_policy_queue_process                   1246    1228     -18
seg6_output_core                             903     885     -18
mld_sendpack                                 856     836     -20
NF_HOOK                                      756     736     -20
vti_tunnel_xmit                             1447    1426     -21
input_action_end_dx6                         664     642     -22
input_action_end                            1502    1480     -22
sock_sendmsg_nosec                           134     111     -23
ip6mr_forward2                               388     364     -24
sock_recvmsg_nosec                           134     109     -25
seg6_input_core                              836     810     -26
ip_send_skb                                  172     146     -26
ip_local_out                                 140     114     -26
ip6_local_out                                140     114     -26
__sock_sendmsg                               162     136     -26
__ip_queue_xmit                             1196    1170     -26
__ip_finish_output                           405     379     -26
ipmr_queue_fwd_xmit                          373     346     -27
sock_recvmsg                                 173     145     -28
ip6_xmit                                    1635    1607     -28
xfrm_output_resume                          1418    1389     -29
ip_build_and_send_pkt                        625     591     -34
dst_output                                   504     432     -72
Total: Before=25217686, After=25216724, chg -0.00%

Fixes: 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up indirect calls of builtin")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260227172603.1700433-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/indirect_call_wrapper.h | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index 35227d47cfc9..dc272b514a01 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -16,22 +16,26 @@
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
 	({								\
-		likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__);	\
+		typeof(f) __f1 = (f);					\
+		likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_2(f, f2, f1, ...)					\
 	({								\
-		likely(f == f2) ? f2(__VA_ARGS__) :			\
-				  INDIRECT_CALL_1(f, f1, __VA_ARGS__);	\
+		typeof(f) __f2 = (f);					\
+		likely(__f2 == f2) ? f2(__VA_ARGS__) :			\
+				  INDIRECT_CALL_1(__f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_3(f, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f3) ? f3(__VA_ARGS__) :				\
-				  INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f3 = (f);						\
+		likely(__f3 == f3) ? f3(__VA_ARGS__) :				\
+				  INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__);	\
 	})
 #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...)					\
 	({									\
-		likely(f == f4) ? f4(__VA_ARGS__) :				\
-				  INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__);	\
+		typeof(f) __f4 = (f);						\
+		likely(__f4 == f4) ? f4(__VA_ARGS__) :				\
+				  INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__);	\
 	})
 
 #define INDIRECT_CALLABLE_DECLARE(f)	f
-- 
cgit v1.2.3


From 6a877ececd6daa002a9a0002cd0fbca6592a9244 Mon Sep 17 00:00:00 2001
From: Allison Henderson <achender@kernel.org>
Date: Fri, 27 Feb 2026 13:23:36 -0700
Subject: net/rds: Fix circular locking dependency in rds_tcp_tune

syzbot reported a circular locking dependency in rds_tcp_tune() where
sk_net_refcnt_upgrade() is called while holding the socket lock:

======================================================
WARNING: possible circular locking dependency detected
======================================================
kworker/u10:8/15040 is trying to acquire lock:
ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0},
at: __kmalloc_cache_noprof+0x4b/0x6f0

but task is already holding lock:
ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0},
at: rds_tcp_tune+0xd7/0x930

The issue occurs because sk_net_refcnt_upgrade() performs memory
allocation (via get_net_track() -> ref_tracker_alloc()) while the
socket lock is held, creating a circular dependency with fs_reclaim.

Fix this by moving sk_net_refcnt_upgrade() outside the socket lock
critical section. This is safe because the fields modified by the
sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not
accessed by any concurrent code path at this point.

v2:
  - Corrected fixes tag
  - check patch line wrap nits
  - ai commentary nits

Reported-by: syzbot+2e2cf5331207053b8106@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2e2cf5331207053b8106
Fixes: 3a58f13a881e ("net: rds: acquire refcount on TCP sockets")
Signed-off-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260227202336.167757-1-achender@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rds/tcp.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 04f310255692..654e23d13e3d 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock)
 	struct rds_tcp_net *rtn;
 
 	tcp_sock_set_nodelay(sock->sk);
-	lock_sock(sk);
 	/* TCP timer functions might access net namespace even after
 	 * a process which created this net namespace terminated.
 	 */
 	if (!sk->sk_net_refcnt) {
-		if (!maybe_get_net(net)) {
-			release_sock(sk);
+		if (!maybe_get_net(net))
 			return false;
-		}
+		/*
+		 * sk_net_refcnt_upgrade() must be called before lock_sock()
+		 * because it does a GFP_KERNEL allocation, which can trigger
+		 * fs_reclaim and create a circular lock dependency with the
+		 * socket lock.  The fields it modifies (sk_net_refcnt,
+		 * ns_tracker) are not accessed by any concurrent code path
+		 * at this point.
+		 */
 		sk_net_refcnt_upgrade(sk);
 		put_net(net);
 	}
+	lock_sock(sk);
 	rtn = net_generic(net, rds_tcp_netid);
 	if (rtn->sndbuf_size > 0) {
 		sk->sk_sndbuf = rtn->sndbuf_size;
-- 
cgit v1.2.3


From 9de68394a61528d40f575c3e6719cc75c56f62c3 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 2 Mar 2026 01:25:44 +0100
Subject: Revert "driver core: enforce device_lock for driver_match_device()"

This reverts commit dc23806a7c47 ("driver core: enforce device_lock for
driver_match_device()") and commit 289b14592cef ("driver core: fix
inverted "locked" suffix of driver_match_device()").

While technically correct, there is a major downside to this approach:

When a device is already present in the system and a driver is
registered on the same bus, we iterate over all devices registered on
this bus to see if one of them matches. If we come across an already
bound one where the corresponding driver crashed while holding the
device lock (e.g. in probe()) we can't make any progress anymore.

However, drivers are typically the least tested code in the kernel and
hence it is a case that is likely to happen regularly. Besides hurting
developer ergonomics, it potentially decreases chances of shutting
things down cleanly and obtaining logs in production environments as
well [1].

This came up in the context of a firewire bug, which only in combination
with the reverted commit, caused the machine to hang [2]. Additionally,
it was observed in [3].

Thus, revert commit dc23806a7c47 ("driver core: enforce device_lock for
driver_match_device()") and add a brief note clarifying that an
implementer of struct bus_type must not expect match() to be called with
the device lock held.

Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1]
Link: https://lore.kernel.org/all/67f655bb-4d81-4609-b008-68d200255dd2@davidgow.net/ [2]
Link: https://lore.kernel.org/lkml/CALbr=LZ4v7N=tO1vgOsyj9AS+XuNbn6kG-QcF+PacdMjSo0iyw@mail.gmail.com/ [3]
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Closes: https://lore.kernel.org/driver-core/CAHk-=wgJ_L1C=HjcYJotg_zrZEmiLFJaoic+PWthjuQrutrfJw@mail.gmail.com/
Reviewed-by: Gui-Dong Han <hanguidong02@gmail.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260302002545.19389-1-dakr@kernel.org
[ Add additional Link: reference. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/base.h        | 11 +----------
 drivers/base/dd.c          |  2 +-
 include/linux/device/bus.h |  2 ++
 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/base/base.h b/drivers/base/base.h
index 79d031d2d845..1af95ac68b77 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -179,19 +179,10 @@ void device_release_driver_internal(struct device *dev, const struct device_driv
 void driver_detach(const struct device_driver *drv);
 void driver_deferred_probe_del(struct device *dev);
 void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf);
-static inline int driver_match_device_locked(const struct device_driver *drv,
-					     struct device *dev)
-{
-	device_lock_assert(dev);
-
-	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
-}
-
 static inline int driver_match_device(const struct device_driver *drv,
 				      struct device *dev)
 {
-	guard(device)(dev);
-	return driver_match_device_locked(drv, dev);
+	return drv->bus->match ? drv->bus->match(dev, drv) : 1;
 }
 
 static inline void dev_sync_state(struct device *dev)
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 0354f209529c..bea8da5f8a3a 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -928,7 +928,7 @@ static int __device_attach_driver(struct device_driver *drv, void *_data)
 	bool async_allowed;
 	int ret;
 
-	ret = driver_match_device_locked(drv, dev);
+	ret = driver_match_device(drv, dev);
 	if (ret == 0) {
 		/* no match */
 		return 0;
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 99c3c83ea520..63de5f053c33 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -35,6 +35,8 @@ struct fwnode_handle;
  *		otherwise. It may also return error code if determining that
  *		the driver supports the device is not possible. In case of
  *		-EPROBE_DEFER it will queue the device for deferred probing.
+ *		Note: This callback may be invoked with or without the device
+ *		lock held.
  * @uevent:	Called when a device is added, removed, or a few other things
  *		that generate uevents to add the environment variables.
  * @probe:	Called when a new device or driver add to this bus, and callback
-- 
cgit v1.2.3


From 1a86a1f7d88996085934139fa4c063b6299a2dd3 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Fri, 27 Feb 2026 22:19:37 +0000
Subject: net: Fix rcu_tasks stall in threaded busypoll

I was debugging a NIC driver when I noticed that when I enable
threaded busypoll, bpftrace hangs when starting up. dmesg showed:

  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 10658 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 40793 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 131273 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 402058 jiffies old.
  INFO: rcu_tasks detected stalls on tasks:
  00000000769f52cd: .N nvcsw: 2/2 holdout: 1 idle_cpu: -1/64
  task:napi/eth2-8265  state:R  running task     stack:0     pid:48300 tgid:48300 ppid:2      task_flags:0x208040 flags:0x00004000
  Call Trace:
   <TASK>
   ? napi_threaded_poll_loop+0x27c/0x2c0
   ? __pfx_napi_threaded_poll+0x10/0x10
   ? napi_threaded_poll+0x26/0x80
   ? kthread+0xfa/0x240
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork+0x31/0x50
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork_asm+0x1a/0x30
   </TASK>

The cause is that in threaded busypoll, the main loop is in
napi_threaded_poll rather than napi_threaded_poll_loop, where the
latter rarely iterates more than once within its loop. For
rcu_softirq_qs_periodic inside napi_threaded_poll_loop to report its
qs state, the last_qs must be 100ms behind, and this can't happen
because napi_threaded_poll_loop rarely iterates in threaded busypoll,
and each time napi_threaded_poll_loop is called last_qs is reset to
latest jiffies.

This patch changes so that in threaded busypoll, last_qs is saved
in the outer napi_threaded_poll, and whether busy_poll_last_qs
is NULL indicates whether napi_threaded_poll_loop is called for
busypoll. This way last_qs would not reset to latest jiffies on
each invocation of napi_threaded_poll_loop.

Fixes: c18d4b190a46 ("net: Extend NAPI threaded polling to allow kthread based busy polling")
Cc: stable@vger.kernel.org
Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20260227221937.1060857-1-zhuyifei@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c1a9f7fdcffa..4af4cf2d63a4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7794,11 +7794,12 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
-static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
+static void napi_threaded_poll_loop(struct napi_struct *napi,
+				    unsigned long *busy_poll_last_qs)
 {
+	unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies;
 	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
-	unsigned long last_qs = jiffies;
 
 	for (;;) {
 		bool repoll = false;
@@ -7827,12 +7828,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 		/* When busy poll is enabled, the old packets are not flushed in
 		 * napi_complete_done. So flush them here.
 		 */
-		if (busy_poll)
+		if (busy_poll_last_qs)
 			gro_flush_normal(&napi->gro, HZ >= 1000);
 		local_bh_enable();
 
 		/* Call cond_resched here to avoid watchdog warnings. */
-		if (repoll || busy_poll) {
+		if (repoll || busy_poll_last_qs) {
 			rcu_softirq_qs_periodic(last_qs);
 			cond_resched();
 		}
@@ -7840,11 +7841,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 		if (!repoll)
 			break;
 	}
+
+	if (busy_poll_last_qs)
+		*busy_poll_last_qs = last_qs;
 }
 
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	unsigned long last_qs = jiffies;
 	bool want_busy_poll;
 	bool in_busy_poll;
 	unsigned long val;
@@ -7862,7 +7867,7 @@ static int napi_threaded_poll(void *data)
 			assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state,
 				   want_busy_poll);
 
-		napi_threaded_poll_loop(napi, want_busy_poll);
+		napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL);
 	}
 
 	return 0;
@@ -13175,7 +13180,7 @@ static void run_backlog_napi(unsigned int cpu)
 {
 	struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
 
-	napi_threaded_poll_loop(&sd->backlog, false);
+	napi_threaded_poll_loop(&sd->backlog, NULL);
 }
 
 static void backlog_napi_setup(unsigned int cpu)
-- 
cgit v1.2.3


From d1a196e0a6dcddd03748468a0e9e3100790fc85c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 12:30:51 +0100
Subject: platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

set_new_password() hex dumps the entire buffer, which contains plaintext
password data, including current and new passwords. Remove the hex dump
to avoid leaking credentials.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Cc: stable@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20260303113050.58127-2-thorsten.blum@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
index 86ec962aace9..e586f7957946 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c
@@ -93,7 +93,6 @@ int set_new_password(const char *password_type, const char *new)
 	if (ret < 0)
 		goto out;
 
-	print_hex_dump_bytes("set new password data: ", DUMP_PREFIX_NONE, buffer, buffer_size);
 	ret = call_password_interface(wmi_priv.password_attr_wdev, buffer, buffer_size);
 	/* on success copy the new password to current password */
 	if (!ret)
-- 
cgit v1.2.3


From 63dc2c34a91642d9ae615a9609841fa317a36c92 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Thu, 22 Jan 2026 18:06:14 +0800
Subject: x86/xen: Build identity mapping page tables dynamically for XENPV

After commit 47ffe0578aee ("x86/pvh: Add 64bit relocation page tables"),
the PVH entry uses a new set of page tables instead of the
preconstructed page tables in head64.S. Since those preconstructed page
tables are only used in XENPV now and XENPV does not actually need the
preconstructed identity page tables directly, they can be filled in
xen_setup_kernel_pagetable(). Therefore, build the identity mapping page
table dynamically to remove the preconstructed page tables and make the
code cleaner.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: "Borislav Petkov (AMD)" <bp@alien8.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <453981eae7e8158307f971d1632d5023adbe03c3.1769074722.git.houwenlong.hwl@antgroup.com>
---
 arch/x86/include/asm/pgtable_64.h |  2 --
 arch/x86/kernel/head_64.S         | 28 ----------------------------
 arch/x86/xen/mmu_pv.c             |  9 +++++++++
 3 files changed, 9 insertions(+), 30 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index f06e5d6a2747..ce45882ccd07 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -19,10 +19,8 @@
 extern p4d_t level4_kernel_pgt[512];
 extern p4d_t level4_ident_pgt[512];
 extern pud_t level3_kernel_pgt[512];
-extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
-extern pmd_t level2_ident_pgt[512];
 extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
 extern pgd_t init_top_pgt[];
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 21816b48537c..85d4a5094f6b 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -616,38 +616,10 @@ SYM_DATA(early_recursion_flag, .long 0)
 
 	.data
 
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_PVH)
-SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.org    init_top_pgt + L4_PAGE_OFFSET*8, 0
-	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.org    init_top_pgt + L4_START_KERNEL*8, 0
-	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
-	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-	.fill	PTI_USER_PGD_FILL,8,0
-SYM_DATA_END(init_top_pgt)
-
-SYM_DATA_START_PAGE_ALIGNED(level3_ident_pgt)
-	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
-	.fill	511, 8, 0
-SYM_DATA_END(level3_ident_pgt)
-SYM_DATA_START_PAGE_ALIGNED(level2_ident_pgt)
-	/*
-	 * Since I easily can, map the first 1G.
-	 * Don't set NX because code runs from these pages.
-	 *
-	 * Note: This sets _PAGE_GLOBAL despite whether
-	 * the CPU supports it or it is enabled.  But,
-	 * the CPU should ignore the bit.
-	 */
-	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
-SYM_DATA_END(level2_ident_pgt)
-#else
 SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
 	.fill	512,8,0
 	.fill	PTI_USER_PGD_FILL,8,0
 SYM_DATA_END(init_top_pgt)
-#endif
 
 SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
 	.fill	511,8,0
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index aa6755385887..50172d64aed6 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -105,6 +105,9 @@ pte_t xen_make_pte_init(pteval_t pte);
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
 #endif
 
+static pud_t level3_ident_pgt[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t level2_ident_pgt[PTRS_PER_PMD] __page_aligned_bss;
+
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
  * Also protects non-atomic updates of current_pages and balloon lists.
@@ -1777,6 +1780,12 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Zap identity mapping */
 	init_top_pgt[0] = __pgd(0);
 
+	init_top_pgt[pgd_index(__PAGE_OFFSET_BASE_L4)].pgd =
+		__pa_symbol(level3_ident_pgt) + _KERNPG_TABLE_NOENC;
+	init_top_pgt[pgd_index(__START_KERNEL_map)].pgd =
+		__pa_symbol(level3_kernel_pgt) + _PAGE_TABLE_NOENC;
+	level3_ident_pgt[0].pud = __pa_symbol(level2_ident_pgt) + _KERNPG_TABLE_NOENC;
+
 	/* Pre-constructed entries are in pfn, so convert to mfn */
 	/* L4[273] -> level3_ident_pgt  */
 	/* L4[511] -> level3_kernel_pgt */
-- 
cgit v1.2.3


From 8b57227d59a86fc06d4f09de08f98133680f2cae Mon Sep 17 00:00:00 2001
From: David Thomson <dt@linux-mail.net>
Date: Tue, 24 Feb 2026 09:37:11 +0000
Subject: xen/acpi-processor: fix _CST detection using undersized evaluation
 buffer

read_acpi_id() attempts to evaluate _CST using a stack buffer of
sizeof(union acpi_object) (48 bytes), but _CST returns a nested Package
of sub-Packages (one per C-state, each containing a register descriptor,
type, latency, and power) requiring hundreds of bytes. The evaluation
always fails with AE_BUFFER_OVERFLOW.

On modern systems using FFH/MWAIT entry (where pblk is zero), this
causes the function to return before setting the acpi_id_cst_present
bit. In check_acpi_ids(), flags.power is then zero for all Phase 2 CPUs
(physical CPUs beyond dom0's vCPU count), so push_cxx_to_hypervisor() is
never called for them.

On a system with dom0_max_vcpus=2 and 8 physical CPUs, only PCPUs 0-1
receive C-state data. PCPUs 2-7 are stuck in C0/C1 idle, unable to
enter C2/C3. This costs measurable wall power (4W observed on an Intel
Core Ultra 7 265K with Xen 4.20).

The function never uses the _CST return value -- it only needs to know
whether _CST exists. Replace the broken acpi_evaluate_object() call with
acpi_has_method(), which correctly detects _CST presence using
acpi_get_handle() without any buffer allocation. This brings C-state
detection to parity with the P-state path, which already works correctly
for Phase 2 CPUs.

Fixes: 59a568029181 ("xen/acpi-processor: C and P-state driver that uploads said data to hypervisor.")
Signed-off-by: David Thomson <dt@linux-mail.net>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260224093707.19679-1-dt@linux-mail.net>
---
 drivers/xen/xen-acpi-processor.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index f2e8eaf684ba..8d1860bd5d57 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -379,11 +379,8 @@ read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv)
 			 acpi_psd[acpi_id].domain);
 	}
 
-	status = acpi_evaluate_object(handle, "_CST", NULL, &buffer);
-	if (ACPI_FAILURE(status)) {
-		if (!pblk)
-			return AE_OK;
-	}
+	if (!pblk && !acpi_has_method(handle, "_CST"))
+		return AE_OK;
 	/* .. and it has a C-state */
 	__set_bit(acpi_id, acpi_id_cst_present);
 
-- 
cgit v1.2.3


From b8c460a045985a8cb7a7c34912d2db91afee242f Mon Sep 17 00:00:00 2001
From: kexinsun <kexinsun@smail.nju.edu.cn>
Date: Tue, 24 Feb 2026 10:24:24 +0800
Subject: x86/xen: update outdated comment

The function xen_flush_tlb_others() was renamed xen_flush_tlb_multi()
by commit 4ce94eabac16 ("x86/mm/tlb: Flush remote and local TLBs
concurrently").  Update the comment accordingly.

Signed-off-by: kexinsun <kexinsun@smail.nju.edu.cn>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260224022424.1718-1-kexinsun@smail.nju.edu.cn>
---
 arch/x86/xen/enlighten_pv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index b74ff8bc7f2a..fde5f44460ee 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -392,7 +392,7 @@ static void __init xen_init_capabilities(void)
 
 	/*
 	 * Xen PV would need some work to support PCID: CR3 handling as well
-	 * as xen_flush_tlb_others() would need updating.
+	 * as xen_flush_tlb_multi() would need updating.
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 
-- 
cgit v1.2.3


From 7271cb98e4981e32c9b2a5f9eb5ad0cd0cdd5bf3 Mon Sep 17 00:00:00 2001
From: Hou Wenlong <houwenlong.hwl@antgroup.com>
Date: Sun, 1 Mar 2026 13:04:52 +0800
Subject: x86/PVH: Use boot params to pass RSDP address in start_info page

After commit e6e094e053af75 ("x86/acpi, x86/boot: Take RSDP address from
boot params if available"), the RSDP address can be passed in boot
params. Therefore, store the RSDP address in start_info page into boot
params in the PVH entry instead of registering a different callback.
This removes an absolute reference during the PVH entry and is more
standardized.

Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <76675c4d49d3a8f72252076812ef8f22276230c2.1772282441.git.houwenlong.hwl@antgroup.com>
---
 arch/x86/platform/pvh/enlighten.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 2263885d16ba..f2053cbe9b0c 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -25,11 +25,6 @@ struct hvm_start_info __initdata pvh_start_info;
 
 const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info);
 
-static u64 __init pvh_get_root_pointer(void)
-{
-	return pvh_start_info.rsdp_paddr;
-}
-
 /*
  * Xen guests are able to obtain the memory map from the hypervisor via the
  * HYPERVISOR_memory_op hypercall.
@@ -95,7 +90,7 @@ static void __init init_pvh_bootparams(bool xen_guest)
 	pvh_bootparams.hdr.version = (2 << 8) | 12;
 	pvh_bootparams.hdr.type_of_loader = ((xen_guest ? 0x9 : 0xb) << 4) | 0;
 
-	x86_init.acpi.get_root_pointer = pvh_get_root_pointer;
+	pvh_bootparams.acpi_rsdp_addr = pvh_start_info.rsdp_paddr;
 }
 
 /*
-- 
cgit v1.2.3


From 27990181031fdcdbe0f7c46011f6404e5d116386 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 3 Mar 2026 14:17:07 +0000
Subject: ASoC: SDCA: Add allocation failure check for Entity name

Currently find_sdca_entity_iot() can allocate a string for the
Entity name but it doesn't check if that allocation succeeded.
Add the missing NULL check after the allocation.

Fixes: 48fa77af2f4a ("ASoC: SDCA: Add terminal type into input/output widget name")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260303141707.3841635-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdca/sdca_functions.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c
index 95b67bb904c3..e0ed593697ba 100644
--- a/sound/soc/sdca/sdca_functions.c
+++ b/sound/soc/sdca/sdca_functions.c
@@ -1156,9 +1156,12 @@ static int find_sdca_entity_iot(struct device *dev,
 	if (!terminal->is_dataport) {
 		const char *type_name = sdca_find_terminal_name(terminal->type);
 
-		if (type_name)
+		if (type_name) {
 			entity->label = devm_kasprintf(dev, GFP_KERNEL, "%s %s",
 						       entity->label, type_name);
+			if (!entity->label)
+				return -ENOMEM;
+		}
 	}
 
 	ret = fwnode_property_read_u32(entity_node,
-- 
cgit v1.2.3


From 00fd9aad55e7ced494a738a07662155d058b872f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 3 Mar 2026 15:26:31 +0100
Subject: Revert "ACPI: PM: Let acpi_dev_pm_attach() skip devices without ACPI
 PM"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Revert commit 88fad6ce090b ("ACPI: PM: Let acpi_dev_pm_attach() skip
devices without ACPI PM") that introduced a SoundWire suspend regression
[1].

It is actually not true that the commit above doesn't make a functional
difference because acpi_subsys_suspend(), for example, may resume
devices in runtime-suspend which affects the subsequent handling of
those devices during the suspend transition.  For this reason, the
devices that were handled by the ACPI PM domain before that commit may
be handled differently now which may lead to suspend-resume issues.

Fixes: 88fad6ce090b ("ACPI: PM: Let acpi_dev_pm_attach() skip devices without ACPI PM")
Reported-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Closes: https://github.com/thesofproject/linux/pull/5677#issuecomment-3984375077 [1]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/2829615.mvXUDI8C0e@rafael.j.wysocki
---
 drivers/acpi/device_pm.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index f2579611e0a5..aa55ecfc2923 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1456,15 +1456,6 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	if (!adev || !acpi_match_device_ids(adev, special_pm_ids))
 		return 0;
 
-	/*
-	 * Skip devices whose ACPI companions don't support power management and
-	 * don't have a wakeup GPE.
-	 */
-	if (!acpi_device_power_manageable(adev) && !acpi_device_can_wakeup(adev)) {
-		dev_dbg(dev, "No ACPI power management or wakeup GPE\n");
-		return 0;
-	}
-
 	/*
 	 * Only attach the power domain to the first device if the
 	 * companion is shared by multiple. This is to prevent doing power
-- 
cgit v1.2.3


From b85cfdf46b2402a9e57d6b7d43e2c977f9554645 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Mon, 9 Feb 2026 18:00:14 +0000
Subject: btrfs: print-tree: add remap tree definitions

Add the definitions for the remap tree to print-tree.c, so that we get
more useful information if a tree is dumped to dmesg.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/print-tree.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index f189bf09ce6a..b7dfe877cf8d 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -38,6 +38,7 @@ static const struct root_name_map root_map[] = {
 	{ BTRFS_BLOCK_GROUP_TREE_OBJECTID,	"BLOCK_GROUP_TREE"	},
 	{ BTRFS_DATA_RELOC_TREE_OBJECTID,	"DATA_RELOC_TREE"	},
 	{ BTRFS_RAID_STRIPE_TREE_OBJECTID,	"RAID_STRIPE_TREE"	},
+	{ BTRFS_REMAP_TREE_OBJECTID,		"REMAP_TREE"		},
 };
 
 const char *btrfs_root_name(const struct btrfs_key *key, char *buf)
@@ -415,6 +416,9 @@ static void key_type_string(const struct btrfs_key *key, char *buf, int buf_size
 		[BTRFS_UUID_KEY_SUBVOL]			= "UUID_KEY_SUBVOL",
 		[BTRFS_UUID_KEY_RECEIVED_SUBVOL]	= "UUID_KEY_RECEIVED_SUBVOL",
 		[BTRFS_RAID_STRIPE_KEY]			= "RAID_STRIPE",
+		[BTRFS_IDENTITY_REMAP_KEY]		= "IDENTITY_REMAP",
+		[BTRFS_REMAP_KEY]			= "REMAP",
+		[BTRFS_REMAP_BACKREF_KEY]		= "REMAP_BACKREF",
 	};
 
 	if (key->type == 0 && key->objectid == BTRFS_FREE_SPACE_OBJECTID)
@@ -435,6 +439,7 @@ void btrfs_print_leaf(const struct extent_buffer *l)
 	struct btrfs_extent_data_ref *dref;
 	struct btrfs_shared_data_ref *sref;
 	struct btrfs_dev_extent *dev_extent;
+	struct btrfs_remap_item *remap;
 	struct btrfs_key key;
 
 	if (!l)
@@ -569,6 +574,11 @@ void btrfs_print_leaf(const struct extent_buffer *l)
 			print_raid_stripe_key(l, btrfs_item_size(l, i),
 				btrfs_item_ptr(l, i, struct btrfs_stripe_extent));
 			break;
+		case BTRFS_REMAP_KEY:
+		case BTRFS_REMAP_BACKREF_KEY:
+			remap = btrfs_item_ptr(l, i, struct btrfs_remap_item);
+			pr_info("\t\taddress %llu\n", btrfs_remap_address(l, remap));
+			break;
 		}
 	}
 }
-- 
cgit v1.2.3


From b8883b61f2fc50dcf22938cbed40fec05020552f Mon Sep 17 00:00:00 2001
From: Sun YangKai <sunk67188@gmail.com>
Date: Mon, 9 Feb 2026 20:53:39 +0800
Subject: btrfs: hold space_info->lock when clearing periodic reclaim ready

btrfs_set_periodic_reclaim_ready() requires space_info->lock to be held,
as enforced by lockdep_assert_held(). However, btrfs_reclaim_sweep() was
calling it after do_reclaim_sweep() returns, at which point
space_info->lock is no longer held.

Fix this by explicitly acquiring space_info->lock before clearing the
periodic reclaim ready flag in btrfs_reclaim_sweep().

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208182556.891815-1-clm@meta.com/
Fixes: 19eff93dc738 ("btrfs: fix periodic reclaim condition")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Sun YangKai <sunk67188@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/space-info.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index bb5aac7ee9d2..36bfd2385b2a 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -2194,8 +2194,11 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info)
 		if (!btrfs_should_periodic_reclaim(space_info))
 			continue;
 		for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) {
-			if (do_reclaim_sweep(space_info, raid))
+			if (do_reclaim_sweep(space_info, raid)) {
+				spin_lock(&space_info->lock);
 				btrfs_set_periodic_reclaim_ready(space_info, false);
+				spin_unlock(&space_info->lock);
+			}
 		}
 	}
 }
-- 
cgit v1.2.3


From 17da926ca8757cc0432ce3e13230759894a6b017 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Tue, 24 Feb 2026 13:51:13 +0100
Subject: btrfs: zoned: move btrfs_zoned_reserve_data_reloc_bg() after kthread
 start

btrfs_zoned_reserve_data_reloc_bg() is called on each mount of a file
system and allocates a new block-group, to assign it to be the dedicated
relocation target, if no pre-existing usable block-group for this task is
found.

If for some reason the transaction is aborted, btrfs_end_transaction()
will wake up the transaction kthread. But the transaction kthread is not
yet initialized at the time btrfs_zoned_reserve_data_reloc_bg() is
called, leading to the following NULL-pointer dereference:

  RSP: 0018:ffffc9000c617c98 EFLAGS: 00010046
  RAX: 0000000000000000 RBX: 000000000000073c RCX: 0000000000000002
  RDX: 0000000000000001 RSI: 0000000000000003 RDI: 0000000000000001
  RBP: 0000000000000207 R08: ffffffff8223c71d R09: 0000000000000635
  R10: ffff888108588000 R11: 0000000000000003 R12: 0000000000000003
  R13: 000000000000073c R14: 0000000000000000 R15: ffff888114dd6000
  FS:  00007f2993745840(0000) GS:ffff8882b508d000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000000000000073c CR3: 0000000121a82006 CR4: 0000000000770eb0
  PKRU: 55555554
  Call Trace:
   <TASK>
   try_to_wake_up (./include/linux/spinlock.h:557 kernel/sched/core.c:4106)
   __btrfs_end_transaction (fs/btrfs/transaction.c:1115 (discriminator 2))
   btrfs_zoned_reserve_data_reloc_bg (fs/btrfs/zoned.c:2840)
   open_ctree (fs/btrfs/disk-io.c:3588)
   btrfs_get_tree.cold (fs/btrfs/super.c:982 fs/btrfs/super.c:1944 fs/btrfs/super.c:2087 fs/btrfs/super.c:2121)
   vfs_get_tree (fs/super.c:1752)
   __do_sys_fsconfig (fs/fsopen.c:231 fs/fsopen.c:295 fs/fsopen.c:473)
   do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
   entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)
  RIP: 0033:0x7f299392740e

Move the call to btrfs_zoned_reserve_data_reloc_bg() after the
transaction_kthread has been initialized to fix this problem.

Fixes: 694ce5e143d6 ("btrfs: zoned: reserve data_reloc block group on mount")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 49987334dd15..2aeb85e3ece9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3594,7 +3594,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		}
 	}
 
-	btrfs_zoned_reserve_data_reloc_bg(fs_info);
 	btrfs_free_zone_cache(fs_info);
 
 	btrfs_check_active_zone_reservation(fs_info);
@@ -3622,6 +3621,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_cleaner;
 	}
 
+	/*
+	 * Starts a transaction, must be called after the transaction kthread
+	 * is initialized.
+	 */
+	btrfs_zoned_reserve_data_reloc_bg(fs_info);
+
 	ret = btrfs_read_qgroup_config(fs_info);
 	if (ret)
 		goto fail_trans_kthread;
-- 
cgit v1.2.3


From 5131fa077f9bb386a1b901bf5b247041f0ec8f80 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Tue, 24 Feb 2026 14:25:35 -0800
Subject: btrfs: set BTRFS_ROOT_ORPHAN_CLEANUP during subvol create

We have recently observed a number of subvolumes with broken dentries.
ls-ing the parent dir looks like:

drwxrwxrwt 1 root root 16 Jan 23 16:49 .
drwxr-xr-x 1 root root 24 Jan 23 16:48 ..
d????????? ? ?    ?     ?            ? broken_subvol

and similarly stat-ing the file fails.

In this state, deleting the subvol fails with ENOENT, but attempting to
create a new file or subvol over it errors out with EEXIST and even
aborts the fs. Which leaves us a bit stuck.

dmesg contains a single notable error message reading:
"could not do orphan cleanup -2"

2 is ENOENT and the error comes from the failure handling path of
btrfs_orphan_cleanup(), with the stack leading back up to
btrfs_lookup().

btrfs_lookup
btrfs_lookup_dentry
btrfs_orphan_cleanup // prints that message and returns -ENOENT

After some detailed inspection of the internal state, it became clear
that:
- there are no orphan items for the subvol
- the subvol is otherwise healthy looking, it is not half-deleted or
  anything, there is no drop progress, etc.
- the subvol was created a while ago and does the meaningful first
  btrfs_orphan_cleanup() call that sets BTRFS_ROOT_ORPHAN_CLEANUP much
  later.
- after btrfs_orphan_cleanup() fails, btrfs_lookup_dentry() returns -ENOENT,
  which results in a negative dentry for the subvolume via
  d_splice_alias(NULL, dentry), leading to the observed behavior. The
  bug can be mitigated by dropping the dentry cache, at which point we
  can successfully delete the subvolume if we want.

i.e.,
btrfs_lookup()
  btrfs_lookup_dentry()
    if (!sb_rdonly(inode->vfs_inode)->vfs_inode)
    btrfs_orphan_cleanup(sub_root)
      test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP)
      btrfs_search_slot() // finds orphan item for inode N
      ...
      prints "could not do orphan cleanup -2"
  if (inode == ERR_PTR(-ENOENT))
    inode = NULL;
  return d_splice_alias(NULL, dentry) // NEGATIVE DENTRY for valid subvolume

btrfs_orphan_cleanup() does test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP)
on the root when it runs, so it cannot run more than once on a given
root, so something else must run concurrently. However, the obvious
routes to deleting an orphan when nlinks goes to 0 should not be able to
run without first doing a lookup into the subvolume, which should run
btrfs_orphan_cleanup() and set the bit.

The final important observation is that create_subvol() calls
d_instantiate_new() but does not set BTRFS_ROOT_ORPHAN_CLEANUP, so if
the dentry cache gets dropped, the next lookup into the subvolume will
make a real call into btrfs_orphan_cleanup() for the first time. This
opens up the possibility of concurrently deleting the inode/orphan items
but most typical evict() paths will be holding a reference on the parent
dentry (child dentry holds parent->d_lockref.count via dget in
d_alloc(), released in __dentry_kill()) and prevent the parent from
being removed from the dentry cache.

The one exception is delayed iputs. Ordered extent creation calls
igrab() on the inode. If the file is unlinked and closed while those
refs are held, iput() in __dentry_kill() decrements i_count but does
not trigger eviction (i_count > 0). The child dentry is freed and the
subvol dentry's d_lockref.count drops to 0, making it evictable while
the inode is still alive.

Since there are two races (the race between writeback and unlink and
the race between lookup and delayed iputs), and there are too many moving
parts, the following three diagrams show the complete picture.
(Only the second and third are races)

Phase 1:
Create Subvol in dentry cache without BTRFS_ROOT_ORPHAN_CLEANUP set

btrfs_mksubvol()
  lookup_one_len()
    __lookup_slow()
      d_alloc_parallel()
        __d_alloc() // d_lockref.count = 1
  create_subvol(dentry)
    // doesn't touch the bit..
    d_instantiate_new(dentry, inode) // dentry in cache with d_lockref.count == 1

Phase 2:
Create a delayed iput for a file in the subvol but leave the subvol in
state where its dentry can be evicted (d_lockref.count == 0)

T1 (task)                    T2 (writeback)                   T3 (OE workqueue)

write() // dirty pages
                              btrfs_writepages()
                                btrfs_run_delalloc_range()
                                  cow_file_range()
                                    btrfs_alloc_ordered_extent()
                                      igrab() // i_count: 1 -> 2
btrfs_unlink_inode()
  btrfs_orphan_add()
close()
  __fput()
    dput()
      finish_dput()
        __dentry_kill()
          dentry_unlink_inode()
            iput() // 2 -> 1
          --parent->d_lockref.count // 1 -> 0; evictable
                                                                finish_ordered_fn()
                                                                  btrfs_finish_ordered_io()
                                                                    btrfs_put_ordered_extent()
                                                                      btrfs_add_delayed_iput()

Phase 3:
Once the delayed iput is pending and the subvol dentry is evictable,
the shrinker can free it, causing the next lookup to go through
btrfs_lookup() and call btrfs_orphan_cleanup() for the first time.
If the cleaner kthread processes the delayed iput concurrently, the
two race:

  T1 (shrinker)              T2 (cleaner kthread)                          T3 (lookup)

  super_cache_scan()
    prune_dcache_sb()
      __dentry_kill()
      // subvol dentry freed
                              btrfs_run_delayed_iputs()
                                iput()  // i_count -> 0
                                  evict()  // sets I_FREEING
                                    btrfs_evict_inode()
                                      // truncation loop
                                                                            btrfs_lookup()
                                                                              btrfs_lookup_dentry()
                                                                                btrfs_orphan_cleanup()
                                                                                  // first call (bit never set)
                                                                                  btrfs_iget()
                                                                                    // blocks on I_FREEING

                                      btrfs_orphan_del()
                                      // inode freed
                                                                                    // returns -ENOENT
                                                                                  btrfs_del_orphan_item()
                                                                                    // -ENOENT
                                                                                // "could not do orphan cleanup -2"
                                                                            d_splice_alias(NULL, dentry)
                                                                            // negative dentry for valid subvol

The most straightforward fix is to ensure the invariant that a dentry
for a subvolume can exist if and only if that subvolume has
BTRFS_ROOT_ORPHAN_CLEANUP set on its root (and is known to have no
orphans or ran btrfs_orphan_cleanup()).

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dadf9bf30f08..1d22c5c05b50 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -672,6 +672,13 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 		goto out;
 	}
 
+	/*
+	 * Subvolumes have orphans cleaned on first dentry lookup. A new
+	 * subvolume cannot have any orphans, so we should set the bit before we
+	 * add the subvolume dentry to the dentry cache, so that it is in the
+	 * same state as a subvolume after first lookup.
+	 */
+	set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &new_root->state);
 	d_instantiate_new(dentry, new_inode_args.inode);
 	new_inode_args.inode = NULL;
 
-- 
cgit v1.2.3


From 5f25805303e201f3afaff0a90f7c7ce257468704 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 2 Mar 2026 19:03:34 +0100
Subject: s390/xor: Fix xor_xc_5() inline assembly

xor_xc_5() contains a larl 1,2f that is not used by the asm and is not
declared as a clobber. This can corrupt a compiler-allocated value in %r1
and lead to miscompilation. Remove the instruction.

Fixes: 745600ed6965 ("s390/lib: Use exrl instead of ex in xor functions")
Cc: stable@vger.kernel.org
Reviewed-by: Juergen Christ <jchrist@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 1721b73b7803..a4d8b51beb95 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -96,7 +96,6 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1,
 		     const unsigned long * __restrict p5)
 {
 	asm volatile(
-		"	larl	1,2f\n"
 		"	aghi	%0,-1\n"
 		"	jm	6f\n"
 		"	srlg	0,%0,8\n"
-- 
cgit v1.2.3


From f775276edc0c505dc0f782773796c189f31a1123 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:34:58 +0100
Subject: s390/xor: Fix xor_xc_2() inline assembly constraints

The inline assembly constraints for xor_xc_2() are incorrect. "bytes",
"p1", and "p2" are input operands, while all three of them are modified
within the inline assembly. Given that the function consists only of this
inline assembly it seems unlikely that this may cause any problems, however
fix this in any case.

Fixes: 2cfc5f9ce7f5 ("s390/xor: optimized xor routing using the XC instruction")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-2-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index a4d8b51beb95..81c0235c0466 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -28,8 +28,8 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1,
 		"	j	3f\n"
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:"
-		: : "d" (bytes), "a" (p1), "a" (p2)
-		: "0", "cc", "memory");
+		: "+d" (bytes), "+a" (p1), "+a" (p2)
+		: : "0", "cc", "memory");
 }
 
 static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1,
-- 
cgit v1.2.3


From 87ff6da3001b2a35d241c5d965b82536f6418277 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:34:59 +0100
Subject: s390/xor: Improve inline assembly constraints

The inline assembly constraint for the "bytes" operand is "d" for all xor()
inline assemblies. "d" means that any register from 0 to 15 can be used. If
the compiler would use register 0 then the exrl instruction would not or
the value of "bytes" into the executed instruction - resulting in an
incorrect result.

However all the xor() inline assemblies make hard-coded use of register 0,
and it is correctly listed in the clobber list, so that this cannot happen.

Given that this is quite subtle use the better "a" constraint, which
excludes register 0 from register allocation in any case.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-3-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/lib/xor.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c
index 81c0235c0466..5363e4c2462d 100644
--- a/arch/s390/lib/xor.c
+++ b/arch/s390/lib/xor.c
@@ -28,7 +28,7 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1,
 		"	j	3f\n"
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2)
+		: "+a" (bytes), "+a" (p1), "+a" (p2)
 		: : "0", "cc", "memory");
 }
 
@@ -54,7 +54,7 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1,
 		"2:	xc	0(1,%1),0(%2)\n"
 		"3:	xc	0(1,%1),0(%3)\n"
 		"4:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
 		: : "0", "cc", "memory");
 }
 
@@ -85,7 +85,7 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1,
 		"3:	xc	0(1,%1),0(%3)\n"
 		"4:	xc	0(1,%1),0(%4)\n"
 		"5:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
 		: : "0", "cc", "memory");
 }
 
@@ -121,7 +121,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1,
 		"4:	xc	0(1,%1),0(%4)\n"
 		"5:	xc	0(1,%1),0(%5)\n"
 		"6:"
-		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
+		: "+a" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
 		  "+a" (p5)
 		: : "0", "cc", "memory");
 }
-- 
cgit v1.2.3


From 674c5ff0f440a051ebf299d29a4c013133d81a65 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 2 Mar 2026 14:35:00 +0100
Subject: s390/stackleak: Fix __stackleak_poison() inline assembly constraint

The __stackleak_poison() inline assembly comes with a "count" operand where
the "d" constraint is used. "count" is used with the exrl instruction and
"d" means that the compiler may allocate any register from 0 to 15.

If the compiler would allocate register 0 then the exrl instruction would
not or the value of "count" into the executed instruction - resulting in a
stackframe which is only partially poisoned.

Use the correct "a" constraint, which excludes register 0 from register
allocation.

Fixes: 2a405f6bb3a5 ("s390/stackleak: provide fast __stackleak_poison() implementation")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260302133500.1560531-4-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/processor.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index cc187afa07b3..78195ee5e99f 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -159,7 +159,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low,
 		"	j	4f\n"
 		"3:	mvc	8(1,%[addr]),0(%[addr])\n"
 		"4:"
-		: [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp)
+		: [addr] "+&a" (erase_low), [count] "+&a" (count), [tmp] "=&a" (tmp)
 		: [poison] "d" (poison)
 		: "memory", "cc"
 		);
-- 
cgit v1.2.3


From b2840e33127ce0eea880504b7f133e780f567a9b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 25 Feb 2026 11:59:58 -0800
Subject: btrfs: add missing RCU unlock in error path in
 try_release_subpage_extent_buffer()

Call rcu_read_lock() before exiting the loop in
try_release_subpage_extent_buffer() because there is a rcu_read_unlock()
call past the loop.

This has been detected by the Clang thread-safety analyzer.

Fixes: ad580dfa388f ("btrfs: fix subpage deadlock in try_release_subpage_extent_buffer()")
CC: stable@vger.kernel.org # 6.18+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3df399dc8856..051309e90079 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4494,6 +4494,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 		 */
 		if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
 			spin_unlock(&eb->refs_lock);
+			rcu_read_lock();
 			break;
 		}
 
-- 
cgit v1.2.3


From ae1238b77feafa2f7f10bcd0432a99e098a98ec6 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Wed, 25 Feb 2026 10:36:06 +0000
Subject: btrfs: read key again after incrementing slot in
 move_existing_remaps()

Fix move_existing_remaps() so that if we increment the slot because the
key we encounter isn't a REMAP_BACKREF, we don't reuse the objectid and
offset of the old item.

Link: https://lore.kernel.org/linux-btrfs/20260125123908.2096548-1-clm@meta.com/
Reported-by: Chris Mason <clm@fb.com>
Fixes: bbea42dfb91f ("btrfs: move existing remaps before relocating block group")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cdb53c0b26ec..fcfbe1b1dab4 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4399,6 +4399,8 @@ static int move_existing_remaps(struct btrfs_fs_info *fs_info,
 
 				leaf = path->nodes[0];
 			}
+
+			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 		}
 
 		remap = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_remap_item);
-- 
cgit v1.2.3


From 2d1ababdedd4ba38867c2500eb7f95af5ddeeef7 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 26 Feb 2026 11:05:43 +0000
Subject: btrfs: fix transaction abort on file creation due to name hash
 collision

If we attempt to create several files with names that result in the same
hash, we have to pack them in same dir item and that has a limit inherent
to the leaf size. However if we reach that limit, we trigger a transaction
abort and turns the filesystem into RO mode. This allows for a malicious
user to disrupt a system, without the need to have administration
privileges/capabilities.

Reproducer:

  $ cat exploit-hash-collisions.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi

  # Use smallest node size to make the test faster and require fewer file
  # names that result in hash collision.
  mkfs.btrfs -f --nodesize 4K $DEV
  mount $DEV $MNT

  # List of names that result in the same crc32c hash for btrfs.
  declare -a names=(
   'foobar'
   '%a8tYkxfGMLWRGr55QSeQc4PBNH9PCLIvR6jZnkDtUUru1t@RouaUe_L:@xGkbO3nCwvLNYeK9vhE628gss:T$yZjZ5l-Nbd6CbC$M=hqE-ujhJICXyIxBvYrIU9-TDC'
   'AQci3EUB%shMsg-N%frgU:02ByLs=IPJU0OpgiWit5nexSyxZDncY6WB:=zKZuk5Zy0DD$Ua78%MelgBuMqaHGyKsJUFf9s=UW80PcJmKctb46KveLSiUtNmqrMiL9-Y0I_l5Fnam04CGIg=8@U:Z'
   'CvVqJpJzueKcuA$wqwePfyu7VxuWNN3ho$p0zi2H8QFYK$7YlEqOhhb%:hHgjhIjW5vnqWHKNP4'
   'ET:vk@rFU4tsvMB0$C_p=xQHaYZjvoF%-BTc%wkFW8yaDAPcCYoR%x$FH5O:'
   'HwTon%v7SGSP4FE08jBwwiu5aot2CFKXHTeEAa@38fUcNGOWvE@Mz6WBeDH_VooaZ6AgsXPkVGwy9l@@ZbNXabUU9csiWrrOp0MWUdfi$EZ3w9GkIqtz7I_eOsByOkBOO'
   'Ij%2VlFGXSuPvxJGf5UWy6O@1svxGha%b@=%wjkq:CIgE6u7eJOjmQY5qTtxE2Rjbis9@us'
   'KBkjG5%9R8K9sOG8UTnAYjxLNAvBmvV5vz3IiZaPmKuLYO03-6asI9lJ_j4@6Xo$KZicaLWJ3Pv8XEwVeUPMwbHYWwbx0pYvNlGMO9F:ZhHAwyctnGy%_eujl%WPd4U2BI7qooOSr85J-C2V$LfY'
   'NcRfDfuUQ2=zP8K3CCF5dFcpfiOm6mwenShsAb_F%n6GAGC7fT2JFFn:c35X-3aYwoq7jNX5$ZJ6hI3wnZs$7KgGi7wjulffhHNUxAT0fRRLF39vJ@NvaEMxsMO'
   'Oj42AQAEzRoTxa5OuSKIr=A_lwGMy132v4g3Pdq1GvUG9874YseIFQ6QU'
   'Ono7avN5GjC:_6dBJ_'
   'WHmN2gnmaN-9dVDy4aWo:yNGFzz8qsJyJhWEWcud7$QzN2D9R0efIWWEdu5kwWr73NZm4=@CoCDxrrZnRITr-kGtU_cfW2:%2_am'
   'WiFnuTEhAG9FEC6zopQmj-A-$LDQ0T3WULz%ox3UZAPybSV6v1Z$b4L_XBi4M4BMBtJZpz93r9xafpB77r:lbwvitWRyo$odnAUYlYMmU4RvgnNd--e=I5hiEjGLETTtaScWlQp8mYsBovZwM2k'
   'XKyH=OsOAF3p%uziGF_ZVr$ivrvhVgD@1u%5RtrV-gl_vqAwHkK@x7YwlxX3qT6WKKQ%PR56NrUBU2dOAOAdzr2=5nJuKPM-T-$ZpQfCL7phxQbUcb:BZOTPaFExc-qK-gDRCDW2'
   'd3uUR6OFEwZr%ns1XH_@tbxA@cCPmbBRLdyh7p6V45H$P2$F%w0RqrD3M0g8aGvWpoTFMiBdOTJXjD:JF7=h9a_43xBywYAP%r$SPZi%zDg%ql-KvkdUCtF9OLaQlxmd'
   'ePTpbnit%hyNm@WELlpKzNZYOzOTf8EQ$sEfkMy1VOfIUu3coyvIr13-Y7Sv5v-Ivax2Go_GQRFMU1b3362nktT9WOJf3SpT%z8sZmM3gvYQBDgmKI%%RM-G7hyrhgYflOw%z::ZRcv5O:lDCFm'
   'evqk743Y@dvZAiG5J05L_ROFV@$2%rVWJ2%3nxV72-W7$e$-SK3tuSHA2mBt$qloC5jwNx33GmQUjD%akhBPu=VJ5g$xhlZiaFtTrjeeM5x7dt4cHpX0cZkmfImndYzGmvwQG:$euFYmXn$_2rA9mKZ'
   'gkgUtnihWXsZQTEkrMAWIxir09k3t7jk_IK25t1:cy1XWN0GGqC%FrySdcmU7M8MuPO_ppkLw3=Dfr0UuBAL4%GFk2$Ma10V1jDRGJje%Xx9EV2ERaWKtjpwiZwh0gCSJsj5UL7CR8RtW5opCVFKGGy8Cky'
   'hNgsG_8lNRik3PvphqPm0yEH3P%%fYG:kQLY=6O-61Wa6nrV_WVGR6TLB09vHOv%g4VQRP8Gzx7VXUY1qvZyS'
   'isA7JVzN12xCxVPJZ_qoLm-pTBuhjjHMvV7o=F:EaClfYNyFGlsfw-Kf%uxdqW-kwk1sPl2vhbjyHU1A6$hz'
   'kiJ_fgcdZFDiOptjgH5PN9-PSyLO4fbk_:u5_2tz35lV_iXiJ6cx7pwjTtKy-XGaQ5IefmpJ4N_ZqGsqCsKuqOOBgf9LkUdffHet@Wu'
   'lvwtxyhE9:%Q3UxeHiViUyNzJsy:fm38pg_b6s25JvdhOAT=1s0$pG25x=LZ2rlHTszj=gN6M4zHZYr_qrB49i=pA--@WqWLIuX7o1S_SfS@2FSiUZN'
   'rC24cw3UBDZ=5qJBUMs9e$=S4Y94ni%Z8639vnrGp=0Hv4z3dNFL0fBLmQ40=EYIY:Z=SLc@QLMSt2zsss2ZXrP7j4='
   'uwGl2s-fFrf@GqS=DQqq2I0LJSsOmM%xzTjS:lzXguE3wChdMoHYtLRKPvfaPOZF2fER@j53evbKa7R%A7r4%YEkD=kicJe@SFiGtXHbKe4gCgPAYbnVn'
   'UG37U6KKua2bgc:IHzRs7BnB6FD:2Mt5Cc5NdlsW%$1tyvnfz7S27FvNkroXwAW:mBZLA1@qa9WnDbHCDmQmfPMC9z-Eq6QT0jhhPpqyymaD:R02ghwYo%yx7SAaaq-:x33LYpei$5g8DMl3C'
   'y2vjek0FE1PDJC0qpfnN:x8k2wCFZ9xiUF2ege=JnP98R%wxjKkdfEiLWvQzmnW'
   '8-HCSgH5B%K7P8_jaVtQhBXpBk:pE-$P7ts58U0J@iR9YZntMPl7j$s62yAJO@_9eanFPS54b=UTw$94C-t=HLxT8n6o9P=QnIxq-f1=Ne2dvhe6WbjEQtc'
   'YPPh:IFt2mtR6XWSmjHptXL_hbSYu8bMw-JP8@PNyaFkdNFsk$M=xfL6LDKCDM-mSyGA_2MBwZ8Dr4=R1D%7-mCaaKGxb990jzaagRktDTyp'
   '9hD2ApKa_t_7x-a@GCG28kY:7$M@5udI1myQ$x5udtggvagmCQcq9QXWRC5hoB0o-_zHQUqZI5rMcz_kbMgvN5jr63LeYA4Cj-c6F5Ugmx6DgVf@2Jqm%MafecpgooqreJ53P-QTS'
  )

  # Now create files with all those names in the same parent directory.
  # It should not fail since a 4K leaf has enough space for them.
  for name in "${names[@]}"; do
       touch $MNT/$name
  done

  # Now add one more file name that causes a crc32c hash collision.
  # This should fail, but it should not turn the filesystem into RO mode
  # (which could be exploited by malicious users) due to a transaction
  # abort.
  touch $MNT/'W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt'

  # Check that we are able to create another file, with a name that does not cause
  # a crc32c hash collision.
  echo -n "hello world" > $MNT/baz

  # Unmount and mount again, verify file baz exists and with the right content.
  umount $MNT
  mount $DEV $MNT
  echo "File baz content: $(cat $MNT/baz)"

  umount $MNT

When running the reproducer:

  $ ./exploit-hash-collisions.sh
  (...)
  touch: cannot touch '/mnt/sdi/W6tIm-VK2@BGC@IBfcgg6j_p:pxp_QUqtWpGD5Ok_GmijKOJJt': Value too large for defined data type
  ./exploit-hash-collisions.sh: line 57: /mnt/sdi/baz: Read-only file system
  cat: /mnt/sdi/baz: No such file or directory
  File baz content:

And the transaction abort stack trace in dmesg/syslog:

  $ dmesg
  (...)
  [758240.509761] ------------[ cut here ]------------
  [758240.510668] BTRFS: Transaction aborted (error -75)
  [758240.511577] WARNING: fs/btrfs/inode.c:6854 at btrfs_create_new_inode+0x805/0xb50 [btrfs], CPU#6: touch/888644
  [758240.513513] Modules linked in: btrfs dm_zero (...)
  [758240.523221] CPU: 6 UID: 0 PID: 888644 Comm: touch Tainted: G        W           6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full)
  [758240.524621] Tainted: [W]=WARN
  [758240.525037] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
  [758240.526331] RIP: 0010:btrfs_create_new_inode+0x80b/0xb50 [btrfs]
  [758240.527093] Code: 0f 82 cf (...)
  [758240.529211] RSP: 0018:ffffce64418fbb48 EFLAGS: 00010292
  [758240.529935] RAX: 00000000ffffffd3 RBX: 0000000000000000 RCX: 00000000ffffffb5
  [758240.531040] RDX: 0000000d04f33e06 RSI: 00000000ffffffb5 RDI: ffffffffc0919dd0
  [758240.531920] RBP: ffffce64418fbc10 R08: 0000000000000000 R09: 00000000ffffffb5
  [758240.532928] R10: 0000000000000000 R11: ffff8e52c0000000 R12: ffff8e53eee7d0f0
  [758240.533818] R13: ffff8e57f70932a0 R14: ffff8e5417629568 R15: 0000000000000000
  [758240.534664] FS:  00007f1959a2a740(0000) GS:ffff8e5b27cae000(0000) knlGS:0000000000000000
  [758240.535821] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [758240.536644] CR2: 00007f1959b10ce0 CR3: 000000012a2cc005 CR4: 0000000000370ef0
  [758240.537517] Call Trace:
  [758240.537828]  <TASK>
  [758240.538099]  btrfs_create_common+0xbf/0x140 [btrfs]
  [758240.538760]  path_openat+0x111a/0x15b0
  [758240.539252]  do_filp_open+0xc2/0x170
  [758240.539699]  ? preempt_count_add+0x47/0xa0
  [758240.540200]  ? __virt_addr_valid+0xe4/0x1a0
  [758240.540800]  ? __check_object_size+0x1b3/0x230
  [758240.541661]  ? alloc_fd+0x118/0x180
  [758240.542315]  do_sys_openat2+0x70/0xd0
  [758240.543012]  __x64_sys_openat+0x50/0xa0
  [758240.543723]  do_syscall_64+0x50/0xf20
  [758240.544462]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [758240.545397] RIP: 0033:0x7f1959abc687
  [758240.546019] Code: 48 89 fa (...)
  [758240.548522] RSP: 002b:00007ffe16ff8690 EFLAGS: 00000202 ORIG_RAX: 0000000000000101
  [758240.566278] RAX: ffffffffffffffda RBX: 00007f1959a2a740 RCX: 00007f1959abc687
  [758240.567068] RDX: 0000000000000941 RSI: 00007ffe16ffa333 RDI: ffffffffffffff9c
  [758240.567860] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  [758240.568707] R10: 00000000000001b6 R11: 0000000000000202 R12: 0000561eec7c4b90
  [758240.569712] R13: 0000561eec7c311f R14: 00007ffe16ffa333 R15: 0000000000000000
  [758240.570758]  </TASK>
  [758240.571040] ---[ end trace 0000000000000000 ]---
  [758240.571681] BTRFS: error (device sdi state A) in btrfs_create_new_inode:6854: errno=-75 unknown
  [758240.572899] BTRFS info (device sdi state EA): forced readonly

Fix this by checking for hash collision, and if the adding a new name is
possible, early in btrfs_create_new_inode() before we do any tree updates,
so that we don't need to abort the transaction if we cannot add the new
name due to the leaf size limit.

A test case for fstests will be sent soon.

Fixes: caae78e03234 ("btrfs: move common inode creation code into btrfs_create_new_inode()")
CC: stable@vger.kernel.org # 6.1+
Reviewed-by: Boris Burkov <boris@bur.io>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d28d55beaacd..b409efe1857e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6610,6 +6610,25 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 	int ret;
 	bool xa_reserved = false;
 
+	if (!args->orphan && !args->subvol) {
+		/*
+		 * Before anything else, check if we can add the name to the
+		 * parent directory. We want to avoid a dir item overflow in
+		 * case we have an existing dir item due to existing name
+		 * hash collisions. We do this check here before we call
+		 * btrfs_add_link() down below so that we can avoid a
+		 * transaction abort (which could be exploited by malicious
+		 * users).
+		 *
+		 * For subvolumes we already do this in btrfs_mksubvol().
+		 */
+		ret = btrfs_check_dir_item_collision(BTRFS_I(dir)->root,
+						     btrfs_ino(BTRFS_I(dir)),
+						     name);
+		if (ret < 0)
+			return ret;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-- 
cgit v1.2.3


From e1b18b959025e6b5dbad668f391f65d34b39595a Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 23 Feb 2026 16:19:31 +0000
Subject: btrfs: fix transaction abort when snapshotting received subvolumes

Currently a user can trigger a transaction abort by snapshotting a
previously received snapshot a bunch of times until we reach a
BTRFS_UUID_KEY_RECEIVED_SUBVOL item overflow (the maximum item size we
can store in a leaf). This is very likely not common in practice, but
if it happens, it turns the filesystem into RO mode. The snapshot, send
and set_received_subvol and subvol_setflags (used by receive) don't
require CAP_SYS_ADMIN, just inode_owner_or_capable(). A malicious user
could use this to turn a filesystem into RO mode and disrupt a system.

Reproducer script:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/sdi
  MNT=/mnt/sdi

  # Use smallest node size to make the test faster.
  mkfs.btrfs -f --nodesize 4K $DEV
  mount $DEV $MNT

  # Create a subvolume and set it to RO so that it can be used for send.
  btrfs subvolume create $MNT/sv
  touch $MNT/sv/foo
  btrfs property set $MNT/sv ro true

  # Send and receive the subvolume into snaps/sv.
  mkdir $MNT/snaps
  btrfs send $MNT/sv | btrfs receive $MNT/snaps

  # Now snapshot the received subvolume, which has a received_uuid, a
  # lot of times to trigger the leaf overflow.
  total=500
  for ((i = 1; i <= $total; i++)); do
      echo -ne "\rCreating snapshot $i/$total"
      btrfs subvolume snapshot -r $MNT/snaps/sv $MNT/snaps/sv_$i > /dev/null
  done
  echo

  umount $MNT

When running the test:

  $ ./test.sh
  (...)
  Create subvolume '/mnt/sdi/sv'
  At subvol /mnt/sdi/sv
  At subvol sv
  Creating snapshot 496/500ERROR: Could not create subvolume: Value too large for defined data type
  Creating snapshot 497/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 498/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 499/500ERROR: Could not create subvolume: Read-only file system
  Creating snapshot 500/500ERROR: Could not create subvolume: Read-only file system

And in dmesg/syslog:

  $ dmesg
  (...)
  [251067.627338] BTRFS warning (device sdi): insert uuid item failed -75 (0x4628b21c4ac8d898, 0x2598bee2b1515c91) type 252!
  [251067.629212] ------------[ cut here ]------------
  [251067.630033] BTRFS: Transaction aborted (error -75)
  [251067.630871] WARNING: fs/btrfs/transaction.c:1907 at create_pending_snapshot.cold+0x52/0x465 [btrfs], CPU#10: btrfs/615235
  [251067.632851] Modules linked in: btrfs dm_zero (...)
  [251067.644071] CPU: 10 UID: 0 PID: 615235 Comm: btrfs Tainted: G        W           6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full)
  [251067.646165] Tainted: [W]=WARN
  [251067.646733] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
  [251067.648735] RIP: 0010:create_pending_snapshot.cold+0x55/0x465 [btrfs]
  [251067.649984] Code: f0 48 0f (...)
  [251067.653313] RSP: 0018:ffffce644908fae8 EFLAGS: 00010292
  [251067.653987] RAX: 00000000ffffff01 RBX: ffff8e5639e63a80 RCX: 00000000ffffffd3
  [251067.655042] RDX: ffff8e53faa76b00 RSI: 00000000ffffffb5 RDI: ffffffffc0919750
  [251067.656077] RBP: ffffce644908fbd8 R08: 0000000000000000 R09: ffffce644908f820
  [251067.657068] R10: ffff8e5adc1fffa8 R11: 0000000000000003 R12: ffff8e53c0431bd0
  [251067.658050] R13: ffff8e5414593600 R14: ffff8e55efafd000 R15: 00000000ffffffb5
  [251067.659019] FS:  00007f2a4944b3c0(0000) GS:ffff8e5b27dae000(0000) knlGS:0000000000000000
  [251067.660115] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [251067.660943] CR2: 00007ffc5aa57898 CR3: 00000005813a2003 CR4: 0000000000370ef0
  [251067.661972] Call Trace:
  [251067.662292]  <TASK>
  [251067.662653]  create_pending_snapshots+0x97/0xc0 [btrfs]
  [251067.663413]  btrfs_commit_transaction+0x26e/0xc00 [btrfs]
  [251067.664257]  ? btrfs_qgroup_convert_reserved_meta+0x35/0x390 [btrfs]
  [251067.665238]  ? _raw_spin_unlock+0x15/0x30
  [251067.665837]  ? record_root_in_trans+0xa2/0xd0 [btrfs]
  [251067.666531]  btrfs_mksubvol+0x330/0x580 [btrfs]
  [251067.667145]  btrfs_mksnapshot+0x74/0xa0 [btrfs]
  [251067.667827]  __btrfs_ioctl_snap_create+0x194/0x1d0 [btrfs]
  [251067.668595]  btrfs_ioctl_snap_create_v2+0x107/0x130 [btrfs]
  [251067.669479]  btrfs_ioctl+0x1580/0x2690 [btrfs]
  [251067.670093]  ? count_memcg_events+0x6d/0x180
  [251067.670849]  ? handle_mm_fault+0x1a0/0x2a0
  [251067.671652]  __x64_sys_ioctl+0x92/0xe0
  [251067.672406]  do_syscall_64+0x50/0xf20
  [251067.673129]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [251067.674096] RIP: 0033:0x7f2a495648db
  [251067.674812] Code: 00 48 89 (...)
  [251067.678227] RSP: 002b:00007ffc5aa57840 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  [251067.679691] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f2a495648db
  [251067.681145] RDX: 00007ffc5aa588b0 RSI: 0000000050009417 RDI: 0000000000000004
  [251067.682511] RBP: 0000000000000002 R08: 0000000000000000 R09: 0000000000000000
  [251067.683842] R10: 000000000000000a R11: 0000000000000246 R12: 00007ffc5aa59910
  [251067.685176] R13: 00007ffc5aa588b0 R14: 0000000000000004 R15: 0000000000000006
  [251067.686524]  </TASK>
  [251067.686972] ---[ end trace 0000000000000000 ]---
  [251067.687890] BTRFS: error (device sdi state A) in create_pending_snapshot:1907: errno=-75 unknown
  [251067.689049] BTRFS info (device sdi state EA): forced readonly
  [251067.689054] BTRFS warning (device sdi state EA): Skipping commit of aborted transaction.
  [251067.690119] BTRFS: error (device sdi state EA) in cleanup_transaction:2043: errno=-75 unknown
  [251067.702028] BTRFS info (device sdi state EA): last unmount of filesystem 46dc3975-30a2-4a69-a18f-418b859cccda

Fix this by ignoring -EOVERFLOW errors from btrfs_uuid_tree_add() in the
snapshot creation code when attempting to add the
BTRFS_UUID_KEY_RECEIVED_SUBVOL item. This is OK because it's not critical
and we are still able to delete the snapshot, as snapshot/subvolume
deletion ignores if a BTRFS_UUID_KEY_RECEIVED_SUBVOL is missing (see
inode.c:btrfs_delete_subvolume()). As for send/receive, we can still do
send/receive operations since it always peeks the first root ID in the
existing BTRFS_UUID_KEY_RECEIVED_SUBVOL (it could peek any since all
snapshots have the same content), and even if the key is missing, it
falls back to searching by BTRFS_UUID_KEY_SUBVOL key.

A test case for fstests will be sent soon.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Boris Burkov <boris@bur.io>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/transaction.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 463238ca8a4d..8d887ffcdba1 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1905,6 +1905,22 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  objectid);
+		/*
+		 * We are creating of lot of snapshots of the same root that was
+		 * received (has a received UUID) and reached a leaf's limit for
+		 * an item. We can safely ignore this and avoid a transaction
+		 * abort. A deletion of this snapshot will still work since we
+		 * ignore if an item with a BTRFS_UUID_KEY_RECEIVED_SUBVOL key
+		 * is missing (see btrfs_delete_subvolume()). Send/receive will
+		 * work too since it peeks the first root id from the existing
+		 * item (it could peek any), and in case it's missing it
+		 * falls back to search by BTRFS_UUID_KEY_SUBVOL keys.
+		 * Creation of a snapshot does not require CAP_SYS_ADMIN, so
+		 * we don't want users triggering transaction aborts, either
+		 * intentionally or not.
+		 */
+		if (ret == -EOVERFLOW)
+			ret = 0;
 		if (unlikely(ret && ret != -EEXIST)) {
 			btrfs_abort_transaction(trans, ret);
 			goto fail;
-- 
cgit v1.2.3


From 87f2c46003fce4d739138aab4af1942b1afdadac Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 26 Feb 2026 23:41:07 +0000
Subject: btrfs: fix transaction abort on set received ioctl due to item
 overflow

If the set received ioctl fails due to an item overflow when attempting to
add the BTRFS_UUID_KEY_RECEIVED_SUBVOL we have to abort the transaction
since we did some metadata updates before.

This means that if a user calls this ioctl with the same received UUID
field for a lot of subvolumes, we will hit the overflow, trigger the
transaction abort and turn the filesystem into RO mode. A malicious user
could exploit this, and this ioctl does not even requires that a user
has admin privileges (CAP_SYS_ADMIN), only that he/she owns the subvolume.

Fix this by doing an early check for item overflow before starting a
transaction. This is also race safe because we are holding the subvol_sem
semaphore in exclusive (write) mode.

A test case for fstests will follow soon.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c     | 21 +++++++++++++++++++--
 fs/btrfs/uuid-tree.c | 38 ++++++++++++++++++++++++++++++++++++++
 fs/btrfs/uuid-tree.h |  2 ++
 3 files changed, 59 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1d22c5c05b50..56d17eedaf90 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3929,6 +3929,25 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 		goto out;
 	}
 
+	received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
+				       BTRFS_UUID_SIZE);
+
+	/*
+	 * Before we attempt to add the new received uuid, check if we have room
+	 * for it in case there's already an item. If the size of the existing
+	 * item plus this root's ID (u64) exceeds the maximum item size, we can
+	 * return here without the need to abort a transaction. If we don't do
+	 * this check, the btrfs_uuid_tree_add() call below would fail with
+	 * -EOVERFLOW and result in a transaction abort. Malicious users could
+	 * exploit this to turn the fs into RO mode.
+	 */
+	if (received_uuid_changed && !btrfs_is_empty_uuid(sa->uuid)) {
+		ret = btrfs_uuid_tree_check_overflow(fs_info, sa->uuid,
+						     BTRFS_UUID_KEY_RECEIVED_SUBVOL);
+		if (ret < 0)
+			goto out;
+	}
+
 	/*
 	 * 1 - root item
 	 * 2 - uuid items (received uuid + subvol uuid)
@@ -3944,8 +3963,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 	sa->rtime.sec = ct.tv_sec;
 	sa->rtime.nsec = ct.tv_nsec;
 
-	received_uuid_changed = memcmp(root_item->received_uuid, sa->uuid,
-				       BTRFS_UUID_SIZE);
 	if (received_uuid_changed &&
 	    !btrfs_is_empty_uuid(root_item->received_uuid)) {
 		ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid,
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index f24c14b9bb2f..43c17a1d3451 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -199,6 +199,44 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8
 	return 0;
 }
 
+/*
+ * Check if we can add one root ID to a UUID key.
+ * If the key does not yet exists, we can, otherwise only if extended item does
+ * not exceeds the maximum item size permitted by the leaf size.
+ *
+ * Returns 0 on success, negative value on error.
+ */
+int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info,
+				   const u8 *uuid, u8 type)
+{
+	BTRFS_PATH_AUTO_FREE(path);
+	int ret;
+	u32 item_size;
+	struct btrfs_key key;
+
+	if (WARN_ON_ONCE(!fs_info->uuid_root))
+		return -EINVAL;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	btrfs_uuid_to_key(uuid, type, &key);
+	ret = btrfs_search_slot(NULL, fs_info->uuid_root, &key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	item_size = btrfs_item_size(path->nodes[0], path->slots[0]);
+
+	if (sizeof(struct btrfs_item) + item_size + sizeof(u64) >
+	    BTRFS_LEAF_DATA_SIZE(fs_info))
+		return -EOVERFLOW;
+
+	return 0;
+}
+
 static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type,
 			       u64 subid)
 {
diff --git a/fs/btrfs/uuid-tree.h b/fs/btrfs/uuid-tree.h
index c60ad20325cc..02b235a3653f 100644
--- a/fs/btrfs/uuid-tree.h
+++ b/fs/btrfs/uuid-tree.h
@@ -12,6 +12,8 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, const u8 *uuid, u8 typ
 			u64 subid);
 int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, const u8 *uuid, u8 type,
 			u64 subid);
+int btrfs_uuid_tree_check_overflow(struct btrfs_fs_info *fs_info,
+				   const u8 *uuid, u8 type);
 int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info);
 int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info);
 int btrfs_uuid_scan_kthread(void *data);
-- 
cgit v1.2.3


From 0f475ee0ebce5c9492b260027cd95270191675fa Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 00:02:33 +0000
Subject: btrfs: abort transaction on failure to update root in the received
 subvol ioctl

If we failed to update the root we don't abort the transaction, which is
wrong since we already used the transaction to remove an item from the
uuid tree.

Fixes: dd5f9615fc5c ("Btrfs: maintain subvolume items in the UUID tree")
CC: stable@vger.kernel.org # 3.12+
Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 56d17eedaf90..5805ac2078f2 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3984,7 +3984,8 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 
 	ret = btrfs_update_root(trans, fs_info->tree_root,
 				&root->root_key, &root->root_item);
-	if (ret < 0) {
+	if (unlikely(ret < 0)) {
+		btrfs_abort_transaction(trans, ret);
 		btrfs_end_transaction(trans);
 		goto out;
 	}
-- 
cgit v1.2.3


From 8dd0e6807b54a2411ed7263018139c60d1406e39 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 00:05:08 +0000
Subject: btrfs: remove unnecessary transaction abort in the received subvol
 ioctl

If we fail to remove an item from the uuid tree, we don't need to abort
the transaction since we have not done any change before. So remove that
transaction abort.

Reviewed-by: Anand Jain <asj@kernel.org>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5805ac2078f2..7d86e9c8909e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3969,7 +3969,6 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
 					  btrfs_root_id(root));
 		if (unlikely(ret && ret != -ENOENT)) {
-		        btrfs_abort_transaction(trans, ret);
 		        btrfs_end_transaction(trans);
 		        goto out;
 		}
-- 
cgit v1.2.3


From 0749cab6174dc035b1628fb6db03abf758cfda6f Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 27 Feb 2026 12:09:47 +0000
Subject: btrfs: remove duplicated definition of btrfs_printk_in_rcu()

It's defined twice in a row for the !CONFIG_PRINTK case, so remove one
of the duplicates.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/messages.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h
index 943e53980945..c8e92efce405 100644
--- a/fs/btrfs/messages.h
+++ b/fs/btrfs/messages.h
@@ -28,9 +28,6 @@ void _btrfs_printk(const struct btrfs_fs_info *fs_info, unsigned int level, cons
 
 #else
 
-#define btrfs_printk_in_rcu(fs_info, level, fmt, args...)		\
-	btrfs_no_printk(fs_info, fmt, ##args)
-
 #define btrfs_printk_in_rcu(fs_info, level, fmt, args...)		\
 	btrfs_no_printk(fs_info, fmt, ##args)
 
-- 
cgit v1.2.3


From 1336b579f6079fb8520be03624fcd9ba443c930b Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Tue, 3 Mar 2026 22:35:30 +0800
Subject: sched_ext: Remove redundant css_put() in scx_cgroup_init()

The iterator css_for_each_descendant_pre() walks the cgroup hierarchy
under cgroup_lock(). It does not increment the reference counts on
yielded css structs.

According to the cgroup documentation, css_put() should only be used
to release a reference obtained via css_get() or css_tryget_online().
Since the iterator does not use either of these to acquire a reference,
calling css_put() in the error path of scx_cgroup_init() causes a
refcount underflow.

Remove the unbalanced css_put() to prevent a potential Use-After-Free
(UAF) vulnerability.

Fixes: 819513666966 ("sched_ext: Add cgroup support")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2ba69b302368..eab6e09b6442 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3589,7 +3589,6 @@ static int scx_cgroup_init(struct scx_sched *sch)
 		ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL,
 				      css->cgroup, &args);
 		if (ret) {
-			css_put(css);
 			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
-- 
cgit v1.2.3


From 2185904ff8b5da76a4353e5d1236caa78e0d98e3 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Fri, 20 Feb 2026 12:32:27 +0530
Subject: powerpc/pci: Initialize msi_addr_mask for OF-created PCI devices

Recent changes replaced the use of no_64bit_msi with msi_addr_mask.  As a
result, msi_addr_mask is now expected to be initialized to DMA_BIT_MASK(64)
when a pci_dev is set up. However, this initialization was missed on
powerpc due to differences in the device initialization path compared to
other (x86) architecture. Due to this, now PCI device probe method fails on
powerpc system.

On powerpc systems, struct pci_dev instances are created from device tree
nodes via of_create_pci_dev(). Because msi_addr_mask was not initialized
there, it remained zero. Later, during MSI setup, msi_verify_entries()
validates the programmed MSI address against pdev->msi_addr_mask. Since the
mask was not set correctly, the validation fails, causing PCI driver probe
failures for devices on powerpc systems.

Initialize pdev->msi_addr_mask to DMA_BIT_MASK(64) in of_create_pci_dev()
so that MSI address validation succeeds and device probe works as expected.

Fixes: 386ced19e9a3 ("PCI/MSI: Convert the boolean no_64bit_msi flag to a DMA address mask")
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Tested-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Vivian Wang <wangruikang@iscas.ac.cn>
Acked-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260220070239.1693303-2-nilay@linux.ibm.com
---
 arch/powerpc/kernel/pci_of_scan.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 756043dd06e9..fb9fbf0d1796 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -212,6 +212,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	dev->error_state = pci_channel_io_normal;
 	dev->dma_mask = 0xffffffff;
 
+	/*
+	 * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit
+	 * if MSI (rather than MSI-X) capability does not have
+	 * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver.
+	 */
+	dev->msi_addr_mask = DMA_BIT_MASK(64);
+
 	/* Early fixups, before probing the BARs */
 	pci_fixup_device(pci_fixup_early, dev);
 
-- 
cgit v1.2.3


From 147dae12985947cdb9e1918142f06482c5077a81 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Fri, 20 Feb 2026 12:32:28 +0530
Subject: sparc/PCI: Initialize msi_addr_mask for OF-created PCI devices

Recent changes replaced the use of no_64bit_msi with msi_addr_mask, which
is now expected to be initialized to DMA_BIT_MASK(64) during PCI device
setup. On SPARC systems, this initialization was inadvertently missed for
devices instantiated from device tree nodes, leaving msi_addr_mask unset
for OF-created pci_dev instances. As a result, MSI address validation fails
during probe, causing affected devices to fail initialization.

Initialize pdev->msi_addr_mask to DMA_BIT_MASK(64) in of_create_pci_dev()
so that MSI address validation succeeds and PCI device probing works as
expected.

Fixes: 386ced19e9a3 ("PCI/MSI: Convert the boolean no_64bit_msi flag to a DMA address mask")
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Han Gao <gaohan@iscas.ac.cn> # SPARC Enterprise T5220
Tested-by: Nathaniel Roach <nroach44@nroach44.id.au> # SPARC T5-2
Reviewed-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260220070239.1693303-3-nilay@linux.ibm.com
---
 arch/sparc/kernel/pci.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 7e41574634b3..1603d50fdcad 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -355,6 +355,13 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 	dev->error_state = pci_channel_io_normal;
 	dev->dma_mask = 0xffffffff;
 
+	/*
+	 * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit
+	 * if MSI (rather than MSI-X) capability does not have
+	 * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver.
+	 */
+	dev->msi_addr_mask = DMA_BIT_MASK(64);
+
 	if (of_node_name_eq(node, "pci")) {
 		/* a PCI-PCI bridge */
 		dev->hdr_type = PCI_HEADER_TYPE_BRIDGE;
-- 
cgit v1.2.3


From 19d2f0b97a131198efc2c4ca3eb7f980bba8c2b4 Mon Sep 17 00:00:00 2001
From: Alison Schofield <alison.schofield@intel.com>
Date: Thu, 26 Feb 2026 10:44:36 -0800
Subject: cxl/port: Fix use after free of parent_port in cxl_detach_ep()

cxl_detach_ep() is called during bottom-up removal when all CXL memory
devices beneath a switch port have been removed. For each port in the
hierarchy it locks both the port and its parent, removes the endpoint,
and if the port is now empty, marks it dead and unregisters the port
by calling delete_switch_port(). There are two places during this work
where the parent_port may be used after freeing:

First, a concurrent detach may have already processed a port by the
time a second worker finds it via bus_find_device(). Without pinning
parent_port, it may already be freed when we discover port->dead and
attempt to unlock the parent_port. In a production kernel that's a
silent memory corruption, with lock debug, it looks like this:

[]DEBUG_LOCKS_WARN_ON(__owner_task(owner) != get_current())
[]WARNING: kernel/locking/mutex.c:949 at __mutex_unlock_slowpath+0x1ee/0x310
[]Call Trace:
[]mutex_unlock+0xd/0x20
[]cxl_detach_ep+0x180/0x400 [cxl_core]
[]devm_action_release+0x10/0x20
[]devres_release_all+0xa8/0xe0
[]device_unbind_cleanup+0xd/0xa0
[]really_probe+0x1a6/0x3e0

Second, delete_switch_port() releases three devm actions registered
against parent_port. The last of those is unregister_port() and it
calls device_unregister() on the child port, which can cascade. If
parent_port is now also empty the device core may unregister and free
it too. So by the time delete_switch_port() returns, parent_port may
be free, and the subsequent device_unlock(&parent_port->dev) operates
on freed memory. The kernel log looks same as above, with a different
offset in cxl_detach_ep().

Both of these issues stem from the absence of a lifetime guarantee
between a child port and its parent port.

Establish a lifetime rule for ports: child ports hold a reference to
their parent device until release. Take the reference when the port
is allocated and drop it when released. This ensures the parent is
valid for the full lifetime of the child and eliminates the use after
free window in cxl_detach_ep().

This is easily reproduced with a reload of cxl_acpi in QEMU with CXL
devices present.

Fixes: 2345df54249c ("cxl/memdev: Fix endpoint port removal")
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Li Ming <ming.li@zohomail.com>
Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20260226184439.1732841-1-alison.schofield@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/port.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 0c5957d1d329..c5aacd7054f1 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -552,10 +552,13 @@ static void cxl_port_release(struct device *dev)
 	xa_destroy(&port->dports);
 	xa_destroy(&port->regions);
 	ida_free(&cxl_port_ida, port->id);
-	if (is_cxl_root(port))
+
+	if (is_cxl_root(port)) {
 		kfree(to_cxl_root(port));
-	else
+	} else {
+		put_device(dev->parent);
 		kfree(port);
+	}
 }
 
 static ssize_t decoders_committed_show(struct device *dev,
@@ -707,6 +710,7 @@ static struct cxl_port *cxl_port_alloc(struct device *uport_dev,
 		struct cxl_port *iter;
 
 		dev->parent = &parent_port->dev;
+		get_device(dev->parent);
 		port->depth = parent_port->depth + 1;
 		port->parent_dport = parent_dport;
 
-- 
cgit v1.2.3


From 50ad1a31bed898787e12b73cb5716fe7960cdde4 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Sat, 21 Feb 2026 07:21:55 +0100
Subject: cpupower: Add support for setting EPP via systemd service

Extend the systemd service so that it can be used for tuning the Energy
Performance Preference (EPP) as well. Available options can be read from
/sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences.
The desired one can then be set in cpupower-service.conf.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/cpupower-service.conf | 5 +++++
 tools/power/cpupower/cpupower.sh           | 6 ++++++
 2 files changed, 11 insertions(+)

diff --git a/tools/power/cpupower/cpupower-service.conf b/tools/power/cpupower/cpupower-service.conf
index 02eabe8e3614..abbb46967565 100644
--- a/tools/power/cpupower/cpupower-service.conf
+++ b/tools/power/cpupower/cpupower-service.conf
@@ -30,3 +30,8 @@
 # its policy for the relative importance of performance versus energy savings to
 # the processor. See man CPUPOWER-SET(1) for additional details
 #PERF_BIAS=
+
+# Set the Energy Performance Preference
+# Available options can be read from
+# /sys/devices/system/cpu/cpufreq/policy0/energy_performance_available_preferences
+#EPP=
diff --git a/tools/power/cpupower/cpupower.sh b/tools/power/cpupower/cpupower.sh
index a37dd4cfdb2b..6283e8bf275d 100644
--- a/tools/power/cpupower/cpupower.sh
+++ b/tools/power/cpupower/cpupower.sh
@@ -23,4 +23,10 @@ then
     cpupower set -b "$PERF_BIAS" > /dev/null || ESTATUS=1
 fi
 
+# apply Energy Performance Preference
+if test -n "$EPP"
+then
+    cpupower set -e "$EPP" > /dev/null || ESTATUS=1
+fi
+
 exit $ESTATUS
-- 
cgit v1.2.3


From 3817b1d34432d3d83a61576719570d04c341b7cd Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Mon, 9 Feb 2026 11:24:41 +0800
Subject: cpupower: Add intel_pstate turbo boost support for Intel platforms

On modern Intel platforms, the intel_pstate driver is commonly used and
it provides turbo boost control via
/sys/devices/system/cpu/intel_pstate/no_turbo.

However, cpupower doesn't handle this. it
1. shows turbo boost as "active" blindly for Intel platforms
2. controls turbo boost functionality via the generic
   /sys/devices/system/cpu/cpufreq/boost sysfs interface only.

Enhance the cpupower tool to ensure the "--boost" command works
seamlessly on Intel platforms with intel_pstate driver running.

Without this patch,
   $ echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo
   1
   $ sudo cpupower frequency-info --boost
   analyzing CPU 21:
     boost state support:
       Supported: yes
       Active: yes
   $ sudo cpupower set --boost 0
   Error setting turbo-boost
   $ sudo cpupower set --boost 1
   Error setting turbo-boost

With this patch,
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   0
   $ sudo cpupower set --boost 0
   $ sudo cpupower frequency-info --boost
   analyzing CPU 21:
     boost state support:
       Supported: yes
       Active: no
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   1
   $ sudo cpupower set --boost 1
   $ sudo cpupower frequency-info --boost
   analyzing CPU 28:
     boost state support:
       Supported: yes
       Active: yes
   $ cat /sys/devices/system/cpu/intel_pstate/no_turbo
   0

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/cpupower-set.c    |  6 +++-
 tools/power/cpupower/utils/helpers/helpers.h |  5 +++-
 tools/power/cpupower/utils/helpers/misc.c    | 41 ++++++++++++++++++++++++++--
 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index c2117e5650dd..550a942e72ce 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -124,7 +124,11 @@ int cmd_set(int argc, char **argv)
 	}
 
 	if (params.turbo_boost) {
-		ret = cpupower_set_turbo_boost(turbo_boost);
+		if (cpupower_cpu_info.vendor == X86_VENDOR_INTEL)
+			ret = cpupower_set_intel_turbo_boost(turbo_boost);
+		else
+			ret = cpupower_set_generic_turbo_boost(turbo_boost);
+
 		if (ret)
 			fprintf(stderr, "Error setting turbo-boost\n");
 	}
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 82ea62bdf5a2..a3ad80b9c2c2 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -104,7 +104,7 @@ extern struct cpupower_cpu_info cpupower_cpu_info;
 /* cpuid and cpuinfo helpers  **************************/
 
 int cpufreq_has_generic_boost_support(bool *active);
-int cpupower_set_turbo_boost(int turbo_boost);
+int cpupower_set_generic_turbo_boost(int turbo_boost);
 
 /* X86 ONLY ****************************************/
 #if defined(__i386__) || defined(__x86_64__)
@@ -143,6 +143,7 @@ extern int decode_pstates(unsigned int cpu, int boost_states,
 
 int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
 				  int *active, int *states);
+int cpupower_set_intel_turbo_boost(int turbo_boost);
 
 /* AMD P-State stuff **************************/
 bool cpupower_amd_pstate_enabled(void);
@@ -189,6 +190,8 @@ static inline int cpupower_set_amd_pstate_mode(char *mode)
 static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
 						int *active, int *states)
 { return -1; }
+static inline int cpupower_set_intel_turbo_boost(int turbo_boost)
+{ return -1; }
 
 static inline bool cpupower_amd_pstate_enabled(void)
 { return false; }
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index 166dc1e470ea..eebfc79a4889 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -19,6 +19,9 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active,
 {
 	int ret;
 	unsigned long long val;
+	char linebuf[MAX_LINE_LEN];
+	char path[SYSFS_PATH_MAX];
+	char *endp;
 
 	*support = *active = *states = 0;
 
@@ -42,8 +45,42 @@ int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active,
 		}
 	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_AMD_PSTATE) {
 		amd_pstate_boost_init(cpu, support, active);
-	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA)
+	} else if (cpupower_cpu_info.caps & CPUPOWER_CAP_INTEL_IDA) {
 		*support = *active = 1;
+
+		snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo");
+
+		if (!is_valid_path(path))
+			return 0;
+
+		if (cpupower_read_sysfs(path, linebuf, MAX_LINE_LEN) == 0)
+			return -1;
+
+		val = strtol(linebuf, &endp, 0);
+		if (endp == linebuf || errno == ERANGE)
+			return -1;
+
+		*active = !val;
+	}
+	return 0;
+}
+
+int cpupower_set_intel_turbo_boost(int turbo_boost)
+{
+	char path[SYSFS_PATH_MAX];
+	char linebuf[2] = {};
+
+	snprintf(path, sizeof(path), PATH_TO_CPU "intel_pstate/no_turbo");
+
+	/* Fallback to generic solution when intel_pstate driver not running */
+	if (!is_valid_path(path))
+		return cpupower_set_generic_turbo_boost(turbo_boost);
+
+	snprintf(linebuf, sizeof(linebuf), "%d", !turbo_boost);
+
+	if (cpupower_write_sysfs(path, linebuf, 2) <= 0)
+		return -1;
+
 	return 0;
 }
 
@@ -274,7 +311,7 @@ void print_speed(unsigned long speed, int no_rounding)
 	}
 }
 
-int cpupower_set_turbo_boost(int turbo_boost)
+int cpupower_set_generic_turbo_boost(int turbo_boost)
 {
 	char path[SYSFS_PATH_MAX];
 	char linebuf[2] = {};
-- 
cgit v1.2.3


From 20f644f42e3b8e729d3c3199d48e75c0b257de8f Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Wed, 25 Feb 2026 13:11:57 +0530
Subject: drm/msm/a6xx: Fix the bogus protect error on X2-85

Update the X2-85 gpu's register protect count configuration with the
correct count_max value to avoid blocking the entire MMIO region from the
UMD.

Protect configurations are a bit complicated on A8xx. There are 2 set of
protect registers with different counts: Global and Pipe-specific. The
last-span-unbound feature is available only on the Pipe-specific protect
registers. Due to this, we cannot use the BUILD_BUG sanity check for A8x
protect configurations, so remove the A840 entry from there.

Fixes: 01ff3bf27215 ("drm/msm/a8xx: Add support for Adreno X2-85 GPU")
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/706944/
Message-ID: <20260225-glymur-protect-fix-v1-1-0deddedf9277@oss.qualcomm.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_catalog.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
index 550a53a7865e..38561f26837e 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
@@ -1759,7 +1759,7 @@ static const u32 x285_protect_regs[] = {
 	A6XX_PROTECT_NORDWR(0x27c06, 0x0000),
 };
 
-DECLARE_ADRENO_PROTECT(x285_protect, 64);
+DECLARE_ADRENO_PROTECT(x285_protect, 15);
 
 static const struct adreno_reglist_pipe a840_nonctxt_regs[] = {
 	{ REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) },
@@ -1966,5 +1966,4 @@ static inline __always_unused void __build_asserts(void)
 	BUILD_BUG_ON(a660_protect.count > a660_protect.count_max);
 	BUILD_BUG_ON(a690_protect.count > a690_protect.count_max);
 	BUILD_BUG_ON(a730_protect.count > a730_protect.count_max);
-	BUILD_BUG_ON(a840_protect.count > a840_protect.count_max);
 }
-- 
cgit v1.2.3


From e4eb6e4dd6348dd00e19c2275e3fbaed304ca3bd Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Thu, 26 Feb 2026 10:57:11 +0100
Subject: drm/msm: Fix dma_free_attrs() buffer size

The gpummu->table buffer is alloc'd with size TABLE_SIZE + 32 in
a2xx_gpummu_new() but freed with size TABLE_SIZE in
a2xx_gpummu_destroy().

Change the free size to match the allocation.

Fixes: c2052a4e5c99 ("drm/msm: implement a2xx mmu")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707340/
Message-ID: <20260226095714.12126-2-fourier.thomas@gmail.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a2xx_gpummu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
index 0407c9bc8c1b..4467b04527cd 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
@@ -78,7 +78,7 @@ static void a2xx_gpummu_destroy(struct msm_mmu *mmu)
 {
 	struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu);
 
-	dma_free_attrs(mmu->dev, TABLE_SIZE, gpummu->table, gpummu->pt_base,
+	dma_free_attrs(mmu->dev, TABLE_SIZE + 32, gpummu->table, gpummu->pt_base,
 		DMA_ATTR_FORCE_CONTIGUOUS);
 
 	kfree(gpummu);
-- 
cgit v1.2.3


From 3875ceb592d3cb23dc932165cc1eeb74cf4dc319 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 15:48:56 -0800
Subject: crypto: testmgr - Fix stale references to aes-generic

Due to commit a2484474272e ("crypto: aes - Replace aes-generic with
wrapper around lib"), the "aes-generic" driver name has been replaced
with "aes-lib".  Update a couple testmgr entries that were added
concurrently with this change.

Fixes: a22d48cbe558 ("crypto: testmgr - Add test vectors for authenc(hmac(sha224),cbc(aes))")
Fixes: 030218dedee2 ("crypto: testmgr - Add test vectors for authenc(hmac(sha384),cbc(aes))")
Acked-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Link: https://lore.kernel.org/r/20260302234856.30569-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/testmgr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 49b607f65f63..4985411dedae 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -4132,7 +4132,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 	}, {
 		.alg = "authenc(hmac(sha224),cbc(aes))",
-		.generic_driver = "authenc(hmac-sha224-lib,cbc(aes-generic))",
+		.generic_driver = "authenc(hmac-sha224-lib,cbc(aes-lib))",
 		.test = alg_test_aead,
 		.suite = {
 			.aead = __VECS(hmac_sha224_aes_cbc_tv_temp)
@@ -4194,7 +4194,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 	}, {
 		.alg = "authenc(hmac(sha384),cbc(aes))",
-		.generic_driver = "authenc(hmac-sha384-lib,cbc(aes-generic))",
+		.generic_driver = "authenc(hmac-sha384-lib,cbc(aes-lib))",
 		.test = alg_test_aead,
 		.suite = {
 			.aead = __VECS(hmac_sha384_aes_cbc_tv_temp)
-- 
cgit v1.2.3


From eef33aa44935d001747ca97703c08dd6f9031162 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Wed, 3 Dec 2025 14:29:48 +0100
Subject: ice: fix adding AQ LLDP filter for VF

The referenced commit came from a misunderstanding of the FW LLDP filter
AQ (Admin Queue) command due to the error in the internal documentation.
Contrary to the assumptions in the original commit, VFs can be added and
deleted from this filter without any problems. Introduced dev_info message
proved to be useful, so reverting the whole commit does not make sense.

Without this fix, trusted VFs do not receive LLDP traffic, if there is an
AQ LLDP filter on PF. When trusted VF attempts to add an LLDP multicast
MAC address, the following message can be seen in dmesg on host:

ice 0000:33:00.0: Failed to add Rx LLDP rule on VSI 20 error: -95

Revert checking VSI type when adding LLDP filter through AQ.

Fixes: 4d5a1c4e6d49 ("ice: do not add LLDP-specific filter if not necessary")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 6cd63190f55d..74fe74225277 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -6391,7 +6391,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 	struct ice_aqc_lldp_filter_ctrl *cmd;
 	struct libie_aq_desc desc;
 
-	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
+	if (!ice_fw_supports_lldp_fltr_ctrl(hw))
 		return -EOPNOTSUPP;
 
 	cmd = libie_aq_raw(&desc);
-- 
cgit v1.2.3


From 326256c0a72d4877cec1d4df85357da106233128 Mon Sep 17 00:00:00 2001
From: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Date: Tue, 13 Jan 2026 20:38:16 +0100
Subject: ice: reintroduce retry mechanism for indirect AQ

Add retry mechanism for indirect Admin Queue (AQ) commands. To do so we
need to keep the command buffer.

This technically reverts commit 43a630e37e25
("ice: remove unused buffer copy code in ice_sq_send_cmd_retry()"),
but combines it with a fix in the logic by using a kmemdup() call,
making it more robust and less likely to break in the future due to
programmer error.

Cc: Michal Schmidt <mschmidt@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 3056df93f7a8 ("ice: Re-send some AQ commands, as result of EBUSY AQ error")
Signed-off-by: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Co-developed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Signed-off-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 74fe74225277..fd32c318d3f5 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1841,6 +1841,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 {
 	struct libie_aq_desc desc_cpy;
 	bool is_cmd_for_retry;
+	u8 *buf_cpy = NULL;
 	u8 idx = 0;
 	u16 opcode;
 	int status;
@@ -1850,8 +1851,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	memset(&desc_cpy, 0, sizeof(desc_cpy));
 
 	if (is_cmd_for_retry) {
-		/* All retryable cmds are direct, without buf. */
-		WARN_ON(buf);
+		if (buf) {
+			buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL);
+			if (!buf_cpy)
+				return -ENOMEM;
+		}
 
 		memcpy(&desc_cpy, desc, sizeof(desc_cpy));
 	}
@@ -1863,12 +1867,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		    hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY)
 			break;
 
+		if (buf_cpy)
+			memcpy(buf, buf_cpy, buf_size);
 		memcpy(desc, &desc_cpy, sizeof(desc_cpy));
-
 		msleep(ICE_SQ_SEND_DELAY_TIME_MS);
 
 	} while (++idx < ICE_SQ_SEND_MAX_EXECUTE);
 
+	kfree(buf_cpy);
 	return status;
 }
 
-- 
cgit v1.2.3


From fb4903b3354aed4a2301180cf991226f896c87ed Mon Sep 17 00:00:00 2001
From: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Date: Tue, 13 Jan 2026 20:38:17 +0100
Subject: ice: fix retry for AQ command 0x06EE

Executing ethtool -m can fail reporting a netlink I/O error while firmware
link management holds the i2c bus used to communicate with the module.

According to Intel(R) Ethernet Controller E810 Datasheet Rev 2.8 [1]
Section 3.3.10.4 Read/Write SFF EEPROM (0x06EE)
request should to be retried upon receiving EBUSY from firmware.

Commit e9c9692c8a81 ("ice: Reimplement module reads used by ethtool")
implemented it only for part of ice_get_module_eeprom(), leaving all other
calls to ice_aq_sff_eeprom() vulnerable to returning early on getting
EBUSY without retrying.

Remove the retry loop from ice_get_module_eeprom() and add Admin Queue
(AQ) command with opcode 0x06EE to the list of commands that should be
retried on receiving EBUSY from firmware.

Cc: stable@vger.kernel.org
Fixes: e9c9692c8a81 ("ice: Reimplement module reads used by ethtool")
Signed-off-by: Jakub Staniszewski <jakub.staniszewski@linux.intel.com>
Co-developed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Signed-off-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://www.intel.com/content/www/us/en/content-details/613875/intel-ethernet-controller-e810-datasheet.html [1]
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c  |  1 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 35 +++++++++++-----------------
 2 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index fd32c318d3f5..ce11fea122d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode)
 	case ice_aqc_opc_lldp_stop:
 	case ice_aqc_opc_lldp_start:
 	case ice_aqc_opc_lldp_filter_ctrl:
+	case ice_aqc_opc_sff_eeprom:
 		return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3c1a084c2a4b..29e341251754 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4509,7 +4509,7 @@ ice_get_module_eeprom(struct net_device *netdev,
 	u8 addr = ICE_I2C_EEPROM_DEV_ADDR;
 	struct ice_hw *hw = &pf->hw;
 	bool is_sfp = false;
-	unsigned int i, j;
+	unsigned int i;
 	u16 offset = 0;
 	u8 page = 0;
 	int status;
@@ -4551,26 +4551,19 @@ ice_get_module_eeprom(struct net_device *netdev,
 		if (page == 0 || !(data[0x2] & 0x4)) {
 			u32 copy_len;
 
-			/* If i2c bus is busy due to slow page change or
-			 * link management access, call can fail. This is normal.
-			 * So we retry this a few times.
-			 */
-			for (j = 0; j < 4; j++) {
-				status = ice_aq_sff_eeprom(hw, 0, addr, offset, page,
-							   !is_sfp, value,
-							   SFF_READ_BLOCK_SIZE,
-							   0, NULL);
-				netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n",
-					   addr, offset, page, is_sfp,
-					   value[0], value[1], value[2], value[3],
-					   value[4], value[5], value[6], value[7],
-					   status);
-				if (status) {
-					usleep_range(1500, 2500);
-					memset(value, 0, SFF_READ_BLOCK_SIZE);
-					continue;
-				}
-				break;
+			status = ice_aq_sff_eeprom(hw, 0, addr, offset, page,
+						   !is_sfp, value,
+						   SFF_READ_BLOCK_SIZE,
+						   0, NULL);
+			netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n",
+				   addr, offset, page, is_sfp,
+				   value[0], value[1], value[2], value[3],
+				   value[4], value[5], value[6], value[7],
+				   ERR_PTR(status));
+			if (status) {
+				netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n",
+					   __func__, ERR_PTR(status));
+				return status;
 			}
 
 			/* Make sure we have enough room for the new block */
-- 
cgit v1.2.3


From fe868b499d16f55bbeea89992edb98043c9de416 Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Thu, 22 Jan 2026 03:26:44 +0000
Subject: ice: Fix memory leak in ice_set_ringparam()

In ice_set_ringparam, tx_rings and xdp_rings are allocated before
rx_rings. If the allocation of rx_rings fails, the code jumps to
the done label leaking both tx_rings and xdp_rings. Furthermore, if
the setup of an individual Rx ring fails during the loop, the code jumps
to the free_tx label which releases tx_rings but leaks xdp_rings.

Fix this by introducing a free_xdp label and updating the error paths to
ensure both xdp_rings and tx_rings are properly freed if rx_rings
allocation or setup fails.

Compile tested only. Issue found using a prototype static analysis tool
and code review.

Fixes: fcea6f3da546 ("ice: Add stats and ethtool support")
Fixes: efc2214b6047 ("ice: Add support for XDP")
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 29e341251754..b9be10b58856 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3332,7 +3332,7 @@ process_rx:
 	rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq);
 	if (!rx_rings) {
 		err = -ENOMEM;
-		goto done;
+		goto free_xdp;
 	}
 
 	ice_for_each_rxq(vsi, i) {
@@ -3359,7 +3359,7 @@ rx_unwind:
 			}
 			kfree(rx_rings);
 			err = -ENOMEM;
-			goto free_tx;
+			goto free_xdp;
 		}
 	}
 
@@ -3411,6 +3411,13 @@ process_link:
 	}
 	goto done;
 
+free_xdp:
+	if (xdp_rings) {
+		ice_for_each_xdp_txq(vsi, i)
+			ice_free_tx_ring(&xdp_rings[i]);
+		kfree(xdp_rings);
+	}
+
 free_tx:
 	/* error cleanup if the Rx allocations failed after getting Tx */
 	if (tx_rings) {
-- 
cgit v1.2.3


From 636cc3bd12f499c74eaf5dc9a7d5b832f1bb24ed Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 11 Feb 2026 10:11:40 +0100
Subject: libie: don't unroll if fwlog isn't supported

The libie_fwlog_deinit() function can be called during driver unload
even when firmware logging was never properly initialized. This led to call
trace:

[  148.576156] Oops: Oops: 0000 [#1] SMP NOPTI
[  148.576167] CPU: 80 UID: 0 PID: 12843 Comm: rmmod Kdump: loaded Not tainted 6.17.0-rc7next-queue-3oct-01915-g06d79d51cf51 #1 PREEMPT(full)
[  148.576177] Hardware name: HPE ProLiant DL385 Gen10 Plus/ProLiant DL385 Gen10 Plus, BIOS A42 07/18/2020
[  148.576182] RIP: 0010:__dev_printk+0x16/0x70
[  148.576196] Code: 1f 44 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 41 55 41 54 49 89 d4 55 48 89 fd 53 48 85 f6 74 3c <4c> 8b 6e 50 48 89 f3 4d 85 ed 75 03 4c 8b 2e 48 89 df e8 f3 27 98
[  148.576204] RSP: 0018:ffffd2fd7ea17a48 EFLAGS: 00010202
[  148.576211] RAX: ffffd2fd7ea17aa0 RBX: ffff8eb288ae2000 RCX: 0000000000000000
[  148.576217] RDX: ffffd2fd7ea17a70 RSI: 00000000000000c8 RDI: ffffffffb68d3d88
[  148.576222] RBP: ffffffffb68d3d88 R08: 0000000000000000 R09: 0000000000000000
[  148.576227] R10: 00000000000000c8 R11: ffff8eb2b1a49400 R12: ffffd2fd7ea17a70
[  148.576231] R13: ffff8eb3141fb000 R14: ffffffffc1215b48 R15: ffffffffc1215bd8
[  148.576236] FS:  00007f5666ba6740(0000) GS:ffff8eb2472b9000(0000) knlGS:0000000000000000
[  148.576242] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  148.576247] CR2: 0000000000000118 CR3: 000000011ad17000 CR4: 0000000000350ef0
[  148.576252] Call Trace:
[  148.576258]  <TASK>
[  148.576269]  _dev_warn+0x7c/0x96
[  148.576290]  libie_fwlog_deinit+0x112/0x117 [libie_fwlog]
[  148.576303]  ixgbe_remove+0x63/0x290 [ixgbe]
[  148.576342]  pci_device_remove+0x42/0xb0
[  148.576354]  device_release_driver_internal+0x19c/0x200
[  148.576365]  driver_detach+0x48/0x90
[  148.576372]  bus_remove_driver+0x6d/0xf0
[  148.576383]  pci_unregister_driver+0x2e/0xb0
[  148.576393]  ixgbe_exit_module+0x1c/0xd50 [ixgbe]
[  148.576430]  __do_sys_delete_module.isra.0+0x1bc/0x2e0
[  148.576446]  do_syscall_64+0x7f/0x980

It can be reproduced by trying to unload ixgbe driver in recovery mode.

Fix that by checking if fwlog is supported before doing unroll.

Fixes: 641585bc978e ("ixgbe: fwlog support for e610")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/libie/fwlog.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c
index 79020d990859..4d0c8370386b 100644
--- a/drivers/net/ethernet/intel/libie/fwlog.c
+++ b/drivers/net/ethernet/intel/libie/fwlog.c
@@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog)
 {
 	int status;
 
+	/* if FW logging isn't supported it means no configuration was done */
+	if (!libie_fwlog_supported(fwlog))
+		return;
+
 	/* make sure FW logging is disabled to not put the FW in a weird state
 	 * for the next driver load
 	 */
-- 
cgit v1.2.3


From b84852170153671bb0fa6737a6e48370addd8e1a Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Tue, 10 Feb 2026 15:57:14 +0000
Subject: iavf: fix netdev->max_mtu to respect actual hardware limit

iavf sets LIBIE_MAX_MTU as netdev->max_mtu, ignoring vf_res->max_mtu
from PF [1]. This allows setting an MTU beyond the actual hardware
limit, causing TX queue timeouts [2].

Set correct netdev->max_mtu using vf_res->max_mtu from the PF.

Note that currently PF drivers such as ice/i40e set the frame size in
vf_res->max_mtu, not MTU. Convert vf_res->max_mtu to MTU before setting
netdev->max_mtu.

[1]
 # ip -j -d link show $DEV | jq '.[0].max_mtu'
 16356

[2]
 iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 1: transmit queue 0 timed out 5692 ms
 iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex
 iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 6: transmit queue 3 timed out 5312 ms
 iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex
 ...

Fixes: 5fa4caff59f2 ("iavf: switch to Page Pool")
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index bceaf4b1b85d..86c1964f42e1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	netdev->watchdog_timeo = 5 * HZ;
 
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = LIBIE_MAX_MTU;
+
+	/* PF/VF API: vf_res->max_mtu is max frame size (not MTU).
+	 * Convert to MTU.
+	 */
+	if (!adapter->vf_res->max_mtu) {
+		netdev->max_mtu = LIBIE_MAX_MTU;
+	} else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU ||
+		   adapter->vf_res->max_mtu >
+			   LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) {
+		netdev_warn_once(adapter->netdev,
+				 "invalid max frame size %d from PF, using default MTU %d",
+				 adapter->vf_res->max_mtu, LIBIE_MAX_MTU);
+		netdev->max_mtu = LIBIE_MAX_MTU;
+	} else {
+		netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN;
+	}
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
 		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
-- 
cgit v1.2.3


From d4c13ab36273a8c318ba06799793cc1f5d9c6fa1 Mon Sep 17 00:00:00 2001
From: Vivek Behera <vivek.behera@siemens.com>
Date: Thu, 22 Jan 2026 15:16:52 +0100
Subject: igb: Fix trigger of incorrect irq in igb_xsk_wakeup

The current implementation in the igb_xsk_wakeup expects
the Rx and Tx queues to share the same irq. This would lead
to triggering of incorrect irq in split irq configuration.
This patch addresses this issue which could impact environments
with 2 active cpu cores
or when the number of queues is reduced to 2 or less

cat /proc/interrupts | grep eno2
 167:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 0-edge      eno2
 168:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 1-edge      eno2-rx-0
 169:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 2-edge      eno2-rx-1
 170:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 3-edge      eno2-tx-0
 171:          0          0          0          0 IR-PCI-MSIX-0000:08:00.0
 4-edge      eno2-tx-1

Furthermore it uses the flags input argument to trigger either rx, tx or
both rx and tx irqs as specified in the ndo_xsk_wakeup api documentation

Fixes: 80f6ccf9f116 ("igb: Introduce XSK data structures and helpers")
Signed-off-by: Vivek Behera <vivek.behera@siemens.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Saritha Sanigani <sarithax.sanigani@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_xsk.c | 38 +++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
index 30ce5fbb5b77..ce4a7b58cad2 100644
--- a/drivers/net/ethernet/intel/igb/igb_xsk.c
+++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
@@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool)
 	return nb_pkts < budget;
 }
 
+static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector)
+{
+	u32 eics = 0;
+
+	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
+		eics = q_vector->eims_value;
+
+	return eics;
+}
+
 int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
 	struct igb_adapter *adapter = netdev_priv(dev);
@@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 
 	ring = adapter->tx_ring[qid];
 
-	if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
-		return -ENETDOWN;
-
 	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
-	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
+	if (flags & XDP_WAKEUP_TX) {
+		if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags))
+			return -ENETDOWN;
+
+		eics |= igb_sw_irq_prep(ring->q_vector);
+	}
+
+	if (flags & XDP_WAKEUP_RX) {
+		/* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector
+		 * and NAPI is shared between RX and TX.
+		 * If NAPI is already running it would be marked as missed
+		 * from the TX path, making this RX call a NOP
+		 */
+		ring = adapter->rx_ring[qid];
+		eics |= igb_sw_irq_prep(ring->q_vector);
+	}
+
+	if (eics) {
 		/* Cause software interrupt */
-		if (adapter->flags & IGB_FLAG_HAS_MSIX) {
-			eics |= ring->q_vector->eims_value;
+		if (adapter->flags & IGB_FLAG_HAS_MSIX)
 			wr32(E1000_EICS, eics);
-		} else {
+		else
 			wr32(E1000_ICS, E1000_ICS_RXDMT0);
-		}
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 554a1c34c11a057d01819ce9bb04653a8ffc8071 Mon Sep 17 00:00:00 2001
From: Vivek Behera <vivek.behera@siemens.com>
Date: Tue, 20 Jan 2026 08:52:16 +0100
Subject: igc: Fix trigger of incorrect irq in igc_xsk_wakeup function

This patch addresses the issue where the igc_xsk_wakeup function
was triggering an incorrect IRQ for tx-0 when the i226 is configured
with only 2 combined queues or in an environment with 2 active CPU cores.
This prevented XDP Zero-copy send functionality in such split IRQ
configurations.

The fix implements the correct logic for extracting q_vectors saved
during rx and tx ring allocation and utilizes flags provided by the
ndo_xsk_wakeup API to trigger the appropriate IRQ.

Fixes: fc9df2a0b520 ("igc: Enable RX via AF_XDP zero-copy")
Fixes: 15fd021bc427 ("igc: Add Tx hardware timestamp request for AF_XDP zero-copy packet")
Signed-off-by: Vivek Behera <vivek.behera@siemens.com>
Reviewed-by: Jacob Keller <jacob.keller@intel.com>
Reviewed-by: Aleksandr loktinov <aleksandr.loktionov@intel.com>
Reviewed-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 34 ++++++++++++++++++++++---------
 drivers/net/ethernet/intel/igc/igc_ptp.c  |  3 ++-
 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 27e5c2109138..b2e8d0c0f827 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	return nxmit;
 }
 
-static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter,
-					struct igc_q_vector *q_vector)
+static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector)
 {
-	struct igc_hw *hw = &adapter->hw;
 	u32 eics = 0;
 
-	eics |= q_vector->eims_value;
-	wr32(IGC_EICS, eics);
+	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
+		eics = q_vector->eims_value;
+
+	return eics;
 }
 
 int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
-	struct igc_q_vector *q_vector;
+	struct igc_hw *hw = &adapter->hw;
 	struct igc_ring *ring;
+	u32 eics = 0;
 
 	if (test_bit(__IGC_DOWN, &adapter->state))
 		return -ENETDOWN;
 
 	if (!igc_xdp_is_enabled(adapter))
 		return -ENXIO;
-
+	/* Check if queue_id is valid. Tx and Rx queue numbers are always same */
 	if (queue_id >= adapter->num_rx_queues)
 		return -EINVAL;
 
@@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	if (!ring->xsk_pool)
 		return -ENXIO;
 
-	q_vector = adapter->q_vector[queue_id];
-	if (!napi_if_scheduled_mark_missed(&q_vector->napi))
-		igc_trigger_rxtxq_interrupt(adapter, q_vector);
+	if (flags & XDP_WAKEUP_RX)
+		eics |= igc_sw_irq_prep(ring->q_vector);
+
+	if (flags & XDP_WAKEUP_TX) {
+		/* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector
+		 * and NAPI is shared between RX and TX.
+		 * If NAPI is already running it would be marked as missed
+		 * from the RX path, making this TX call a NOP
+		 */
+		ring = adapter->tx_ring[queue_id];
+		eics |= igc_sw_irq_prep(ring->q_vector);
+	}
+
+	if (eics)
+		/* Cause software interrupt */
+		wr32(IGC_EICS, eics);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 7aae83c108fd..44ee19386766 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter,
 		tstamp->buffer_type = 0;
 
 		/* Trigger txrx interrupt for transmit completion */
-		igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0);
+		igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index,
+			       XDP_WAKEUP_TX);
 
 		return;
 	}
-- 
cgit v1.2.3


From b06ccbabe2506fd70b9167a644978b049150224a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 3 Mar 2026 01:01:15 -1000
Subject: sched_ext: Fix starvation of scx_enable() under fair-class saturation

During scx_enable(), the READY -> ENABLED task switching loop changes the
calling thread's sched_class from fair to ext. Since fair has higher
priority than ext, saturating fair-class workloads can indefinitely starve
the enable thread, hanging the system. This was introduced when the enable
path switched from preempt_disable() to scx_bypass() which doesn't protect
against fair-class starvation. Note that the original preempt_disable()
protection wasn't complete either - in partial switch modes, the calling
thread could still be starved after preempt_enable() as it may have been
switched to ext class.

Fix it by offloading the enable body to a dedicated system-wide RT
(SCHED_FIFO) kthread which cannot be starved by either fair or ext class
tasks. scx_enable() lazily creates the kthread on first use and passes the
ops pointer through a struct scx_enable_cmd containing the kthread_work,
then synchronously waits for completion.

The workfn runs on a different kthread from sch->helper (which runs
disable_work), so it can safely flush disable_work on the error path
without deadlock.

Fixes: 8c2090c504e9 ("sched_ext: Initialize in bypass mode")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 66 +++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 56 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index eab6e09b6442..ba51969718f5 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4975,20 +4975,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 	return 0;
 }
 
-static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+/*
+ * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid
+ * starvation. During the READY -> ENABLED task switching loop, the calling
+ * thread's sched_class gets switched from fair to ext. As fair has higher
+ * priority than ext, the calling thread can be indefinitely starved under
+ * fair-class saturation, leading to a system hang.
+ */
+struct scx_enable_cmd {
+	struct kthread_work	work;
+	struct sched_ext_ops	*ops;
+	int			ret;
+};
+
+static void scx_enable_workfn(struct kthread_work *work)
 {
+	struct scx_enable_cmd *cmd =
+		container_of(work, struct scx_enable_cmd, work);
+	struct sched_ext_ops *ops = cmd->ops;
 	struct scx_sched *sch;
 	struct scx_task_iter sti;
 	struct task_struct *p;
 	unsigned long timeout;
 	int i, cpu, ret;
 
-	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
-			   cpu_possible_mask)) {
-		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
-		return -EINVAL;
-	}
-
 	mutex_lock(&scx_enable_mutex);
 
 	if (scx_enable_state() != SCX_DISABLED) {
@@ -5205,13 +5215,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 
 	atomic_long_inc(&scx_enable_seq);
 
-	return 0;
+	cmd->ret = 0;
+	return;
 
 err_free_ksyncs:
 	free_kick_syncs();
 err_unlock:
 	mutex_unlock(&scx_enable_mutex);
-	return ret;
+	cmd->ret = ret;
+	return;
 
 err_disable_unlock_all:
 	scx_cgroup_unlock();
@@ -5230,7 +5242,41 @@ err_disable:
 	 */
 	scx_error(sch, "scx_enable() failed (%d)", ret);
 	kthread_flush_work(&sch->disable_work);
-	return 0;
+	cmd->ret = 0;
+}
+
+static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+{
+	static struct kthread_worker *helper;
+	static DEFINE_MUTEX(helper_mutex);
+	struct scx_enable_cmd cmd;
+
+	if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
+			   cpu_possible_mask)) {
+		pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n");
+		return -EINVAL;
+	}
+
+	if (!READ_ONCE(helper)) {
+		mutex_lock(&helper_mutex);
+		if (!helper) {
+			helper = kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(helper)) {
+				helper = NULL;
+				mutex_unlock(&helper_mutex);
+				return -ENOMEM;
+			}
+			sched_set_fifo(helper->task);
+		}
+		mutex_unlock(&helper_mutex);
+	}
+
+	kthread_init_work(&cmd.work, scx_enable_workfn);
+	cmd.ops = ops;
+
+	kthread_queue_work(READ_ONCE(helper), &cmd.work);
+	kthread_flush_work(&cmd.work);
+	return cmd.ret;
 }
 
 
-- 
cgit v1.2.3


From 56145d237385ca0e7ca9ff7b226aaf2eb8ef368b Mon Sep 17 00:00:00 2001
From: Lang Xu <xulang@uniontech.com>
Date: Tue, 3 Mar 2026 17:52:17 +0800
Subject: bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim

The root cause of this bug is that when 'bpf_link_put' reduces the
refcount of 'shim_link->link.link' to zero, the resource is considered
released but may still be referenced via 'tr->progs_hlist' in
'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in
'bpf_shim_tramp_link_release' is deferred. During this window, another
process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.

Based on Martin KaFai Lau's suggestions, I have created a simple patch.

To fix this:
   Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'.
   Only increment the refcount if it is not already zero.

Testing:
   I verified the fix by adding a delay in
   'bpf_shim_tramp_link_release' to make the bug easier to trigger:

static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
	/* ... */
	if (!shim_link->trampoline)
		return;

+	msleep(100);
	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link,
		shim_link->trampoline, NULL));
	bpf_trampoline_put(shim_link->trampoline);
}

Before the patch, running a PoC easily reproduced the crash(almost 100%)
with a call trace similar to KaiyanM's report.
After the patch, the bug no longer occurs even after millions of
iterations.

Fixes: 69fd337a975c ("bpf: per-cgroup lsm flavor")
Reported-by: Kaiyan Mei <M202472210@hust.edu.cn>
Closes: https://lore.kernel.org/bpf/3c4ebb0b.46ff8.19abab8abe2.Coremail.kaiyanm@hust.edu.cn/
Signed-off-by: Lang Xu <xulang@uniontech.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/279EEE1BA1DDB49D+20260303095217.34436-1-xulang@uniontech.com
---
 kernel/bpf/trampoline.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 84db9e658e52..f02254a21585 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1002,10 +1002,8 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
 	mutex_lock(&tr->mutex);
 
 	shim_link = cgroup_shim_find(tr, bpf_func);
-	if (shim_link) {
+	if (shim_link && !IS_ERR(bpf_link_inc_not_zero(&shim_link->link.link))) {
 		/* Reusing existing shim attached by the other program. */
-		bpf_link_inc(&shim_link->link.link);
-
 		mutex_unlock(&tr->mutex);
 		bpf_trampoline_put(tr); /* bpf_trampoline_get above */
 		return 0;
-- 
cgit v1.2.3


From 12c43a062acb0ac137fc2a4a106d4d084b8c5416 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:11 +0000
Subject: smb/client: fix buffer size for smb311_posix_qinfo in
 smb2_compound_op()

Use `sizeof(struct smb311_posix_qinfo)` instead of sizeof its pointer,
so the allocated buffer matches the actual struct size.

Fixes: 6a5f6592a0b6 ("SMB311: Add support for query info using posix extensions (level 100)")
Reported-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 195a38fd61e8..1c4663ed7e69 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -325,7 +325,7 @@ replay_again:
 							  cfile->fid.volatile_fid,
 							  SMB_FIND_FILE_POSIX_INFO,
 							  SMB2_O_INFO_FILE, 0,
-							  sizeof(struct smb311_posix_qinfo *) +
+							  sizeof(struct smb311_posix_qinfo) +
 							  (PATH_MAX * 2) +
 							  (sizeof(struct smb_sid) * 2), 0, NULL);
 			} else {
@@ -335,7 +335,7 @@ replay_again:
 							  COMPOUND_FID,
 							  SMB_FIND_FILE_POSIX_INFO,
 							  SMB2_O_INFO_FILE, 0,
-							  sizeof(struct smb311_posix_qinfo *) +
+							  sizeof(struct smb311_posix_qinfo) +
 							  (PATH_MAX * 2) +
 							  (sizeof(struct smb_sid) * 2), 0, NULL);
 			}
-- 
cgit v1.2.3


From 9621b996e4db1dbc2b3dc5d5910b7d6179397320 Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:12 +0000
Subject: smb/client: fix buffer size for smb311_posix_qinfo in
 SMB311_posix_query_info()

SMB311_posix_query_info() is currently unused, but it may still be used in
some stable versions, so these changes are submitted as a separate patch.

Use `sizeof(struct smb311_posix_qinfo)` instead of sizeof its pointer,
so the allocated buffer matches the actual struct size.

Fixes: b1bc1874b885 ("smb311: Add support for SMB311 query info (non-compounded)")
Reported-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 04e361ed2356..8a1fcc097606 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3996,7 +3996,7 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			u64 persistent_fid, u64 volatile_fid,
 			struct smb311_posix_qinfo *data, u32 *plen)
 {
-	size_t output_len = sizeof(struct smb311_posix_qinfo *) +
+	size_t output_len = sizeof(struct smb311_posix_qinfo) +
 			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);
 	*plen = 0;
 
-- 
cgit v1.2.3


From 8098179dc981c361c4ff238bc3935329a93bbdfb Mon Sep 17 00:00:00 2001
From: ZhangGuoDong <zhangguodong@kylinos.cn>
Date: Tue, 3 Mar 2026 15:13:13 +0000
Subject: smb/client: remove unused SMB311_posix_query_info()

It is currently unused, as now we are doing compounding instead
(see smb2_query_path_info()).

Signed-off-by: ZhangGuoDong <zhangguodong@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c   | 18 ------------------
 fs/smb/client/smb2proto.h |  3 ---
 2 files changed, 21 deletions(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 8a1fcc097606..c43ca74e8704 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3989,24 +3989,6 @@ int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			  NULL);
 }
 
-#if 0
-/* currently unused, as now we are doing compounding instead (see smb311_posix_query_path_info) */
-int
-SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
-			u64 persistent_fid, u64 volatile_fid,
-			struct smb311_posix_qinfo *data, u32 *plen)
-{
-	size_t output_len = sizeof(struct smb311_posix_qinfo) +
-			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);
-	*plen = 0;
-
-	return query_info(xid, tcon, persistent_fid, volatile_fid,
-			  SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0,
-			  output_len, sizeof(struct smb311_posix_qinfo), (void **)&data, plen);
-	/* Note caller must free "data" (passed in above). It may be allocated in query_info call */
-}
-#endif
-
 int
 SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 	       u64 persistent_fid, u64 volatile_fid,
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 881e42cf66ce..230bb1e9f4e1 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -167,9 +167,6 @@ int SMB2_flush_init(const unsigned int xid, struct smb_rqst *rqst,
 		    struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 		    u64 persistent_fid, u64 volatile_fid);
 void SMB2_flush_free(struct smb_rqst *rqst);
-int SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
-			    u64 persistent_fid, u64 volatile_fid,
-			    struct smb311_posix_qinfo *data, u32 *plen);
 int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 		    u64 persistent_fid, u64 volatile_fid,
 		    struct smb2_file_all_info *data);
-- 
cgit v1.2.3


From 3ac88a9948792b092a4b11323e2abd1ecbe0cc68 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Tue, 24 Feb 2026 11:25:34 +0900
Subject: rust: str: make NullTerminatedFormatter public

If `CONFIG_BLOCK` is disabled, the following warnings are displayed
during build:

  warning: struct `NullTerminatedFormatter` is never constructed
    --> ../rust/kernel/str.rs:667:19
      |
  667 | pub(crate) struct NullTerminatedFormatter<'a> {
      |                   ^^^^^^^^^^^^^^^^^^^^^^^
      |
      = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default

  warning: associated function `new` is never used
    --> ../rust/kernel/str.rs:673:19
      |
  671 | impl<'a> NullTerminatedFormatter<'a> {
      | ------------------------------------ associated function in this implementation
  672 |     /// Create a new [`Self`] instance.
  673 |     pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {

Fix them by making `NullTerminatedFormatter` public, as it could be
useful for drivers anyway.

Fixes: cdde7a1951ff ("rust: str: introduce `NullTerminatedFormatter`")
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260224-nullterminatedformatter-v1-1-5bef7b9b3d4c@nvidia.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/str.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs
index fa87779d2253..3f8918764640 100644
--- a/rust/kernel/str.rs
+++ b/rust/kernel/str.rs
@@ -664,13 +664,13 @@ impl fmt::Write for Formatter<'_> {
 ///
 /// * The first byte of `buffer` is always zero.
 /// * The length of `buffer` is at least 1.
-pub(crate) struct NullTerminatedFormatter<'a> {
+pub struct NullTerminatedFormatter<'a> {
     buffer: &'a mut [u8],
 }
 
 impl<'a> NullTerminatedFormatter<'a> {
     /// Create a new [`Self`] instance.
-    pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {
+    pub fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> {
         *(buffer.first_mut()?) = 0;
 
         // INVARIANT:
-- 
cgit v1.2.3


From 2ffb4f5c2ccb2fa1c049dd11899aee7967deef5a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 1 Mar 2026 11:45:48 -0800
Subject: ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu()

l3mdev_master_dev_rcu() can return NULL when the slave device is being
un-slaved from a VRF. All other callers deal with this, but we lost
the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu()
with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on
device with address").

  KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f]
  RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418)
  Call Trace:
   ip6_pol_route (net/ipv6/route.c:2318)
   fib6_rule_lookup (net/ipv6/fib6_rules.c:115)
   ip6_route_output_flags (net/ipv6/route.c:2607)
   vrf_process_v6_outbound (drivers/net/vrf.c:437)

I was tempted to rework the un-slaving code to clear the flag first
and insert synchronize_rcu() before we remove the upper. But looks like
the explicit fallback to loopback_dev is an established pattern.
And I guess avoiding the synchronize_rcu() is nice, too.

Fixes: 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address")
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260301194548.927324-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 85df25c36409..7db0c837196c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
 		 */
 		if (netif_is_l3_slave(dev) &&
 		    !rt6_need_strict(&res->f6i->fib6_dst.addr))
-			dev = l3mdev_master_dev_rcu(dev);
+			dev = l3mdev_master_dev_rcu(dev) ? :
+			      dev_net(dev)->loopback_dev;
 		else if (!netif_is_l3_master(dev))
 			dev = dev_net(dev)->loopback_dev;
 		/* last case is netif_is_l3_master(dev) is true in which
-- 
cgit v1.2.3


From 67edfec516d30d3e62925c397be4a1e5185802fc Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 12:36:00 -0800
Subject: net/tcp-ao: Fix MAC comparison to be constant-time

To prevent timing attacks, MACs need to be compared in constant
time.  Use the appropriate helper function for this.

Fixes: 0a3a809089eb ("net/tcp: Verify inbound TCP-AO signed segments")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20260302203600.13561-1-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/Kconfig  | 1 +
 net/ipv4/tcp_ao.c | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index b71c22475c51..3ab6247be585 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -748,6 +748,7 @@ config TCP_SIGPOOL
 config TCP_AO
 	bool "TCP: Authentication Option (RFC5925)"
 	select CRYPTO
+	select CRYPTO_LIB_UTILS
 	select TCP_SIGPOOL
 	depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64)
 	help
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 4980caddb0fc..a97cdf3e6af4 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) "TCP: " fmt
 
 #include <crypto/hash.h>
+#include <crypto/utils.h>
 #include <linux/inetdevice.h>
 #include <linux/tcp.h>
 
@@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb,
 	/* XXX: make it per-AF callback? */
 	tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key,
 			(phash - (u8 *)th), sne);
-	if (memcmp(phash, hash_buf, maclen)) {
+	if (crypto_memneq(phash, hash_buf, maclen)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
 		atomic64_inc(&info->counters.pkt_bad);
 		atomic64_inc(&key->pkt_bad);
-- 
cgit v1.2.3


From 4ee7fa6cf78ff26d783d39e2949d14c4c1cd5e7f Mon Sep 17 00:00:00 2001
From: Yung Chih Su <yuuchihsu@gmail.com>
Date: Mon, 2 Mar 2026 14:02:47 +0800
Subject: net: ipv4: fix ARM64 alignment fault in multipath hash seed

`struct sysctl_fib_multipath_hash_seed` contains two u32 fields
(user_seed and mp_seed), making it an 8-byte structure with a 4-byte
alignment requirement.

In `fib_multipath_hash_from_keys()`, the code evaluates the entire
struct atomically via `READ_ONCE()`:

    mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;

While this silently works on GCC by falling back to unaligned regular
loads which the ARM64 kernel tolerates, it causes a fatal kernel panic
when compiled with Clang and LTO enabled.

Commit e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire
when CONFIG_LTO=y") strengthens `READ_ONCE()` to use Load-Acquire
instructions (`ldar` / `ldapr`) to prevent compiler reordering bugs
under Clang LTO. Since the macro evaluates the full 8-byte struct,
Clang emits a 64-bit `ldar` instruction. ARM64 architecture strictly
requires `ldar` to be naturally aligned, thus executing it on a 4-byte
aligned address triggers a strict Alignment Fault (FSC = 0x21).

Fix the read side by moving the `READ_ONCE()` directly to the `u32`
member, which emits a safe 32-bit `ldar Wn`.

Furthermore, Eric Dumazet pointed out that `WRITE_ONCE()` on the entire
struct in `proc_fib_multipath_hash_set_seed()` is also flawed. Analysis
shows that Clang splits this 8-byte write into two separate 32-bit
`str` instructions. While this avoids an alignment fault, it destroys
atomicity and exposes a tear-write vulnerability. Fix this by
explicitly splitting the write into two 32-bit `WRITE_ONCE()`
operations.

Finally, add the missing `READ_ONCE()` when reading `user_seed` in
`proc_fib_multipath_hash_seed()` to ensure proper pairing and
concurrency safety.

Fixes: 4ee2a8cace3f ("net: ipv4: Add a sysctl to set multipath hash seed")
Signed-off-by: Yung Chih Su <yuuchihsu@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260302060247.7066-1-yuuchihsu@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_fib.h       | 2 +-
 net/ipv4/sysctl_net_ipv4.c | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b4495c38e0a0..318593743b6e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net,
 	siphash_aligned_key_t hash_key;
 	u32 mp_seed;
 
-	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;
+	mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed);
 	fib_multipath_hash_construct_key(&hash_key, mp_seed);
 
 	return flow_hash_from_keys_seed(keys, &hash_key);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 643763bc2142..5654cc9c8a0b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed)
 			    proc_fib_multipath_hash_rand_seed),
 	};
 
-	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new);
+	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed);
+	WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed);
 }
 
 static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write,
@@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write
 	int ret;
 
 	mphs = &net->ipv4.sysctl_fib_multipath_hash_seed;
-	user_seed = mphs->user_seed;
+	user_seed = READ_ONCE(mphs->user_seed);
 
 	tmp = *table;
 	tmp.data = &user_seed;
-- 
cgit v1.2.3


From 5af6e8b54927f7a8d3c7fd02b1bdc09e93d5c079 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 2 Mar 2026 03:40:46 -0800
Subject: netconsole: fix sysdata_release_enabled_show checking wrong flag

sysdata_release_enabled_show() checks SYSDATA_TASKNAME instead of
SYSDATA_RELEASE, causing the configfs release_enabled attribute to
reflect the taskname feature state rather than the release feature
state. This is a copy-paste error from the adjacent
sysdata_taskname_enabled_show() function.

The corresponding _store function already uses the correct
SYSDATA_RELEASE flag.

Fixes: 343f90227070 ("netconsole: implement configfs for release_enabled")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260302-sysdata_release_fix-v1-1-e5090f677c7c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 2db116fb1a7c..3c9acd6e49e8 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -617,7 +617,7 @@ static ssize_t sysdata_release_enabled_show(struct config_item *item,
 	bool release_enabled;
 
 	dynamic_netconsole_mutex_lock();
-	release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME);
+	release_enabled = !!(nt->sysdata_fields & SYSDATA_RELEASE);
 	dynamic_netconsole_mutex_unlock();
 
 	return sysfs_emit(buf, "%d\n", release_enabled);
-- 
cgit v1.2.3


From e2f27363aa6d983504c6836dd0975535e2e9dba0 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Mon, 2 Mar 2026 09:51:24 +0530
Subject: amd-xgbe: fix sleep while atomic on suspend/resume

The xgbe_powerdown() and xgbe_powerup() functions use spinlocks
(spin_lock_irqsave) while calling functions that may sleep:
- napi_disable() can sleep waiting for NAPI polling to complete
- flush_workqueue() can sleep waiting for pending work items

This causes a "BUG: scheduling while atomic" error during suspend/resume
cycles on systems using the AMD XGBE Ethernet controller.

The spinlock protection in these functions is unnecessary as these
functions are called from suspend/resume paths which are already serialized
by the PM core

Fix this by removing the spinlock. Since only code that takes this lock
is xgbe_powerdown() and xgbe_powerup(), remove it completely.

Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260302042124.1386445-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c  | 10 ----------
 drivers/net/ethernet/amd/xgbe/xgbe-main.c |  1 -
 drivers/net/ethernet/amd/xgbe/xgbe.h      |  3 ---
 3 files changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 62bb4b8a68e1..8b79d88480db 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1120,7 +1120,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	unsigned long flags;
 
 	DBGPR("-->xgbe_powerdown\n");
 
@@ -1131,8 +1130,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&pdata->lock, flags);
-
 	if (caller == XGMAC_DRIVER_CONTEXT)
 		netif_device_detach(netdev);
 
@@ -1148,8 +1145,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 
 	pdata->power_down = 1;
 
-	spin_unlock_irqrestore(&pdata->lock, flags);
-
 	DBGPR("<--xgbe_powerdown\n");
 
 	return 0;
@@ -1159,7 +1154,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	unsigned long flags;
 
 	DBGPR("-->xgbe_powerup\n");
 
@@ -1170,8 +1164,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&pdata->lock, flags);
-
 	pdata->power_down = 0;
 
 	xgbe_napi_enable(pdata, 0);
@@ -1186,8 +1178,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 
 	xgbe_start_timers(pdata);
 
-	spin_unlock_irqrestore(&pdata->lock, flags);
-
 	DBGPR("<--xgbe_powerup\n");
 
 	return 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index d1f0419edb23..7d45ea22a02e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -76,7 +76,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev)
 	pdata->netdev = netdev;
 	pdata->dev = dev;
 
-	spin_lock_init(&pdata->lock);
 	spin_lock_init(&pdata->xpcs_lock);
 	mutex_init(&pdata->rss_mutex);
 	spin_lock_init(&pdata->tstamp_lock);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 1269b8ce9249..e1d7d7150e16 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1004,9 +1004,6 @@ struct xgbe_prv_data {
 	unsigned int pp3;
 	unsigned int pp4;
 
-	/* Overall device lock */
-	spinlock_t lock;
-
 	/* XPCS indirect addressing lock */
 	spinlock_t xpcs_lock;
 	unsigned int xpcs_window_def_reg;
-- 
cgit v1.2.3


From 7f5d8e63f3d4dc952548502a2227de780cbcd21f Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 2 Mar 2026 11:50:20 -0800
Subject: MAINTAINERS: update the skge/sky2 maintainers

Mark the skge and sky2 drivers as orphan.
I no longer have any Marvell/SysKonnect boards to test with and
mail to Mirko Lindner bounced because Marvell sold off that divsion.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://patch.msgid.link/20260302195120.187183-1-stephen@networkplumber.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7829ff2180ae..bee85351120e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15372,10 +15372,8 @@ F:	drivers/crypto/marvell/
 F:	include/linux/soc/marvell/octeontx2/
 
 MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
-M:	Mirko Lindner <mlindner@marvell.com>
-M:	Stephen Hemminger <stephen@networkplumber.org>
 L:	netdev@vger.kernel.org
-S:	Odd fixes
+S:	Orphan
 F:	drivers/net/ethernet/marvell/sk*
 
 MARVELL LIBERTAS WIRELESS DRIVER
-- 
cgit v1.2.3


From 46d0d6f50dab706637f4c18a470aac20a21900d3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 2 Mar 2026 12:34:09 -0800
Subject: net/tcp-md5: Fix MAC comparison to be constant-time

To prevent timing attacks, MACs need to be compared in constant
time.  Use the appropriate helper function for this.

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Fixes: 658ddaaf6694 ("tcp: md5: RST: getting md5 key from listener")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Link: https://patch.msgid.link/20260302203409.13388-1-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/Kconfig    | 1 +
 net/ipv4/tcp.c      | 3 ++-
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 3 ++-
 4 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 3ab6247be585..df922f9f5289 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -762,6 +762,7 @@ config TCP_AO
 config TCP_MD5SIG
 	bool "TCP: MD5 Signature Option support (RFC2385)"
 	select CRYPTO_LIB_MD5
+	select CRYPTO_LIB_UTILS
 	help
 	  RFC2385 specifies a method of giving MD5 protection to TCP sessions.
 	  Its main (only?) use is to protect BGP sessions between core routers
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8cdc26e8ad68..202a4e57a218 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -244,6 +244,7 @@
 #define pr_fmt(fmt) "TCP: " fmt
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -4970,7 +4971,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 	else
 		tp->af_specific->calc_md5_hash(newhash, key, NULL, skb);
-	if (memcmp(hash_location, newhash, 16) != 0) {
+	if (crypto_memneq(hash_location, newhash, 16)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
 		trace_tcp_hash_md5_mismatch(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d53d39be291a..910c25cb24e1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -88,6 +88,7 @@
 #include <linux/skbuff_ref.h>
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 
 #include <trace/events/tcp.h>
 
@@ -839,7 +840,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 			goto out;
 
 		tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
-		if (memcmp(md5_hash_location, newhash, 16) != 0)
+		if (crypto_memneq(md5_hash_location, newhash, 16))
 			goto out;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e46a0efae012..5195a46b951e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -68,6 +68,7 @@
 #include <linux/seq_file.h>
 
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 
 #include <trace/events/tcp.h>
 
@@ -1048,7 +1049,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
 		key.type = TCP_KEY_MD5;
 
 		tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb);
-		if (memcmp(md5_hash_location, newhash, 16) != 0)
+		if (crypto_memneq(md5_hash_location, newhash, 16))
 			goto out;
 	}
 #endif
-- 
cgit v1.2.3


From 9e7dc228bb6d4afa74dd6bab4f3aad43126cc2db Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Wed, 4 Mar 2026 01:42:57 +0100
Subject: io_uring/mock: Fix typo in help text
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the spelling of "subsystem".

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index e95d43457851..74f07212db85 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1897,7 +1897,7 @@ config IO_URING_MOCK_FILE
 	default n
 	depends on IO_URING
 	help
-	  Enable mock files for io_uring subststem testing. The ABI might
+	  Enable mock files for io_uring subsystem testing. The ABI might
 	  still change, so it's still experimental and should only be enabled
 	  for specific test purposes.
 
-- 
cgit v1.2.3


From 26bc83b88bbbf054f0980a4a42047a8d1e210e4c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Tue, 17 Feb 2026 20:27:02 -0800
Subject: smb: client: Compare MACs in constant time

To prevent timing attacks, MAC comparisons need to be constant-time.
Replace the memcmp() with the correct function, crypto_memneq().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1encrypt.c   | 3 ++-
 fs/smb/client/smb2transport.c | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb1encrypt.c b/fs/smb/client/smb1encrypt.c
index 0dbbce2431ff..bf10fdeeedca 100644
--- a/fs/smb/client/smb1encrypt.c
+++ b/fs/smb/client/smb1encrypt.c
@@ -11,6 +11,7 @@
 
 #include <linux/fips.h>
 #include <crypto/md5.h>
+#include <crypto/utils.h>
 #include "cifsproto.h"
 #include "smb1proto.h"
 #include "cifs_debug.h"
@@ -131,7 +132,7 @@ int cifs_verify_signature(struct smb_rqst *rqst,
 /*	cifs_dump_mem("what we think it should be: ",
 		      what_we_think_sig_should_be, 16); */
 
-	if (memcmp(server_response_sig, what_we_think_sig_should_be, 8))
+	if (crypto_memneq(server_response_sig, what_we_think_sig_should_be, 8))
 		return -EACCES;
 	else
 		return 0;
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 8b9000a83181..81be2b226e26 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -20,6 +20,7 @@
 #include <linux/highmem.h>
 #include <crypto/aead.h>
 #include <crypto/sha2.h>
+#include <crypto/utils.h>
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "smb2proto.h"
@@ -617,7 +618,8 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE)) {
+	if (crypto_memneq(server_response_sig, shdr->Signature,
+			  SMB2_SIGNATURE_SIZE)) {
 		cifs_dbg(VFS, "sign fail cmd 0x%x message id 0x%llx\n",
 			shdr->Command, shdr->MessageId);
 		return -EACCES;
-- 
cgit v1.2.3


From 6ca8379b5d36e22b04e6315c3e49a6083377c862 Mon Sep 17 00:00:00 2001
From: Shengming Hu <hu.shengming@zte.com.cn>
Date: Sat, 21 Feb 2026 11:30:07 +0800
Subject: fgraph: Fix thresh_return clear per-task notrace

When tracing_thresh is enabled, function graph tracing uses
trace_graph_thresh_return() as the return handler. Unlike
trace_graph_return(), it did not clear the per-task TRACE_GRAPH_NOTRACE
flag set by the entry handler for set_graph_notrace addresses. This could
leave the task permanently in "notrace" state and effectively disable
function graph tracing for that task.

Mirror trace_graph_return()'s per-task notrace handling by clearing
TRACE_GRAPH_NOTRACE and returning early when set.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260221113007819YgrZsMGABff4Rc-O_fZxL@zte.com.cn
Fixes: b84214890a9bc ("function_graph: Move graph notrace bit to shadow stack global var")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3d8239fee004..817d0f1696b6 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -400,14 +400,15 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops,
 				      struct ftrace_regs *fregs)
 {
+	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
 	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
 
-	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
-		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
+	if (*task_var & TRACE_GRAPH_NOTRACE) {
+		*task_var &= ~TRACE_GRAPH_NOTRACE;
 		return;
 	}
 
-- 
cgit v1.2.3


From b96d0c59cdbb2a22b2545f6f3d5c6276b05761dd Mon Sep 17 00:00:00 2001
From: Shengming Hu <hu.shengming@zte.com.cn>
Date: Sat, 21 Feb 2026 11:33:14 +0800
Subject: fgraph: Fix thresh_return nosleeptime double-adjust

trace_graph_thresh_return() called handle_nosleeptime() and then delegated
to trace_graph_return(), which calls handle_nosleeptime() again. When
sleep-time accounting is disabled this double-adjusts calltime and can
produce bogus durations (including underflow).

Fix this by computing rettime once, applying handle_nosleeptime() only
once, using the adjusted calltime for threshold comparison, and writing
the return event directly via __trace_graph_return() when the threshold is
met.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260221113314048jE4VRwIyZEALiYByGK0My@zte.com.cn
Fixes: 3c9880f3ab52b ("ftrace: Use a running sleeptime instead of saving on shadow stack")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 817d0f1696b6..0d2d3a2ea7dd 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -403,8 +403,12 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct fgraph_times *ftimes;
 	struct trace_array *tr;
+	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	int size;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (*task_var & TRACE_GRAPH_NOTRACE) {
@@ -419,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	tr = gops->private;
 	handle_nosleeptime(tr, trace, ftimes, size);
 
-	if (tracing_thresh &&
-	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
+	calltime = ftimes->calltime;
+
+	if (tracing_thresh && (rettime - calltime < tracing_thresh))
 		return;
-	else
-		trace_graph_return(trace, gops, fregs);
+
+	trace_ctx = tracing_gen_ctx();
+	__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 }
 
 static struct fgraph_ops funcgraph_ops = {
-- 
cgit v1.2.3


From 0a663b764dbdf135a126284f454c9f01f95a87d4 Mon Sep 17 00:00:00 2001
From: Huiwen He <hehuiwen@kylinos.cn>
Date: Tue, 24 Feb 2026 10:35:44 +0800
Subject: tracing: Fix syscall events activation by ensuring refcount hits zero

When multiple syscall events are specified in the kernel command line
(e.g., trace_event=syscalls:sys_enter_openat,syscalls:sys_enter_close),
they are often not captured after boot, even though they appear enabled
in the tracing/set_event file.

The issue stems from how syscall events are initialized. Syscall
tracepoints require the global reference count (sys_tracepoint_refcount)
to transition from 0 to 1 to trigger the registration of the syscall
work (TIF_SYSCALL_TRACEPOINT) for tasks, including the init process (pid 1).

The current implementation of early_enable_events() with disable_first=true
used an interleaved sequence of "Disable A -> Enable A -> Disable B -> Enable B".
If multiple syscalls are enabled, the refcount never drops to zero,
preventing the 0->1 transition that triggers actual registration.

Fix this by splitting early_enable_events() into two distinct phases:
1. Disable all events specified in the buffer.
2. Enable all events specified in the buffer.

This ensures the refcount hits zero before re-enabling, allowing syscall
events to be properly activated during early boot.

The code is also refactored to use a helper function to avoid logic
duplication between the disable and enable phases.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260224023544.1250787-1-hehuiwen@kylinos.cn
Fixes: ce1039bd3a89 ("tracing: Fix enabling of syscall events on the command line")
Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 52 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 37 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9928da636c9d..9c7f26cbe171 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -4668,26 +4668,22 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
-__init void
-early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+/*
+ * Helper function to enable or disable a comma-separated list of events
+ * from the bootup buffer.
+ */
+static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable)
 {
 	char *token;
-	int ret;
-
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
 
+	while ((token = strsep(&buf, ","))) {
 		if (*token) {
-			/* Restarting syscalls requires that we stop them first */
-			if (disable_first)
+			if (enable) {
+				if (ftrace_set_clr_event(tr, token, 1))
+					pr_warn("Failed to enable trace event: %s\n", token);
+			} else {
 				ftrace_set_clr_event(tr, token, 0);
-
-			ret = ftrace_set_clr_event(tr, token, 1);
-			if (ret)
-				pr_warn("Failed to enable trace event: %s\n", token);
+			}
 		}
 
 		/* Put back the comma to allow this to be called again */
@@ -4696,6 +4692,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
 	}
 }
 
+/**
+ * early_enable_events - enable events from the bootup buffer
+ * @tr: The trace array to enable the events in
+ * @buf: The buffer containing the comma separated list of events
+ * @disable_first: If true, disable all events in @buf before enabling them
+ *
+ * This function enables events from the bootup buffer. If @disable_first
+ * is true, it will first disable all events in the buffer before enabling
+ * them.
+ *
+ * For syscall events, which rely on a global refcount to register the
+ * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must
+ * ensure the refcount hits zero before re-enabling them. A simple
+ * "disable then enable" per-event is not enough if multiple syscalls are
+ * used, as the refcount will stay above zero. Thus, we need a two-phase
+ * approach: disable all, then enable all.
+ */
+__init void
+early_enable_events(struct trace_array *tr, char *buf, bool disable_first)
+{
+	if (disable_first)
+		__early_set_events(tr, buf, false);
+
+	__early_set_events(tr, buf, true);
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();
-- 
cgit v1.2.3


From cc337974cd1084f9821179eb66f4e470d9fd2ed8 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 2 Mar 2026 21:35:46 -0500
Subject: ftrace: Disable preemption in the tracepoint callbacks handling
 filtered pids

When function trace PID filtering is enabled, the function tracer will
attach a callback to the fork tracepoint as well as the exit tracepoint
that will add the forked child PID to the PID filtering list as well as
remove the PID that is exiting.

Commit a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of
__DO_TRACE_CALL() with SRCU-fast") removed the disabling of preemption
when calling tracepoint callbacks.

The callbacks used for the PID filtering accounting depended on preemption
being disabled, and now the trigger a "suspicious RCU usage" warning message.

Make them explicitly disable preemption.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260302213546.156e3e4f@gandalf.local.home
Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/ftrace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 827fb9a0bf0d..2f72af0357e5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
@@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->function_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
-- 
cgit v1.2.3


From a5dd6f58666f22ae16b98a2177bebc3340d38fe9 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 3 Mar 2026 21:57:38 -0500
Subject: tracing: Disable preemption in the tracepoint callbacks handling
 filtered pids

Filtering PIDs for events triggered the following during selftests:

[37] event tracing - restricts events based on pid notrace filtering
[  155.874095]
[  155.874869] =============================
[  155.876037] WARNING: suspicious RCU usage
[  155.877287] 7.0.0-rc1-00004-g8cd473a19bc7 #7 Not tainted
[  155.879263] -----------------------------
[  155.882839] kernel/trace/trace_events.c:1057 suspicious rcu_dereference_check() usage!
[  155.889281]
[  155.889281] other info that might help us debug this:
[  155.889281]
[  155.894519]
[  155.894519] rcu_scheduler_active = 2, debug_locks = 1
[  155.898068] no locks held by ftracetest/4364.
[  155.900524]
[  155.900524] stack backtrace:
[  155.902645] CPU: 1 UID: 0 PID: 4364 Comm: ftracetest Not tainted 7.0.0-rc1-00004-g8cd473a19bc7 #7 PREEMPT(lazy)
[  155.902648] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[  155.902651] Call Trace:
[  155.902655]  <TASK>
[  155.902659]  dump_stack_lvl+0x67/0x90
[  155.902665]  lockdep_rcu_suspicious+0x154/0x1a0
[  155.902672]  event_filter_pid_sched_process_fork+0x9a/0xd0
[  155.902678]  kernel_clone+0x367/0x3a0
[  155.902689]  __x64_sys_clone+0x116/0x140
[  155.902696]  do_syscall_64+0x158/0x460
[  155.902700]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  155.902702]  ? trace_irq_disable+0x1d/0xc0
[  155.902709]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  155.902711] RIP: 0033:0x4697c3
[  155.902716] Code: 1f 84 00 00 00 00 00 64 48 8b 04 25 10 00 00 00 45 31 c0 31 d2 31 f6 bf 11 00 20 01 4c 8d 90 d0 02 00 00 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 89 c2 85 c0 75 2c 64 48 8b 04 25 10 00 00
[  155.902718] RSP: 002b:00007ffc41150428 EFLAGS: 00000246 ORIG_RAX: 0000000000000038
[  155.902721] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004697c3
[  155.902722] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011
[  155.902724] RBP: 0000000000000000 R08: 0000000000000000 R09: 000000003fccf990
[  155.902725] R10: 000000003fccd690 R11: 0000000000000246 R12: 0000000000000001
[  155.902726] R13: 000000003fce8103 R14: 0000000000000001 R15: 0000000000000000
[  155.902733]  </TASK>
[  155.902747]

The tracepoint callbacks recently were changed to allow preemption. The
event PID filtering callbacks that were attached to the fork and exit
tracepoints expected preemption disabled in order to access the RCU
protected PID lists.

Add a guard(preempt)() to protect the references to the PID list.

Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260303215738.6ab275af@fedora
Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast")
Link: https://patch.msgid.link/20260303131706.96057f61a48a34c43ce1e396@kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9c7f26cbe171..b7343fdfd7b0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_raw(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, NULL, task);
 
@@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data,
 	struct trace_pid_list *pid_list;
 	struct trace_array *tr = data;
 
+	guard(preempt)();
 	pid_list = rcu_dereference_sched(tr->filtered_pids);
 	trace_filter_add_remove_task(pid_list, self, task);
 
-- 
cgit v1.2.3


From e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Fri, 27 Feb 2026 10:58:42 +0800
Subject: tracing: Fix WARN_ON in tracing_buffers_mmap_close

When a process forks, the child process copies the parent's VMAs but the
user_mapped reference count is not incremented. As a result, when both the
parent and child processes exit, tracing_buffers_mmap_close() is called
twice. On the second call, user_mapped is already 0, causing the function to
return -ENODEV and triggering a WARN_ON.

Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set.
But this is only a hint, and the application can call
madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the
application does that, it can trigger this issue on fork.

Fix it by incrementing the user_mapped reference count without re-mapping
the pages in the VMA's open callback.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://patch.msgid.link/20260227025842.1085206-1-wangqing7171@gmail.com
Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer")
Reported-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=3b5dd2030fe08afdf65d
Tested-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 21 +++++++++++++++++++++
 kernel/trace/trace.c        | 13 +++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 876358cfe1b1..d862fa610270 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
 
 int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		    struct vm_area_struct *vma);
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
 #endif /* _LINUX_RING_BUFFER_H */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f16f053ef77d..17d0ea0cc3e6 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 23de3719f495..1e7c032a72d2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };
-- 
cgit v1.2.3


From b9e7e3ea605f23d342c67fc5bded99bcaa32d93b Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Tue, 6 Jan 2026 18:40:19 +0100
Subject: powerpc/e500: Always use 64 bits PTE

Today there are two PTE formats for e500:
- The 64 bits format, used
 - On 64 bits kernel
 - On 32 bits kernel with 64 bits physical addresses
 - On 32 bits kernel with support of huge pages
- The 32 bits format, used in other cases

Maintaining two PTE formats means unnecessary maintenance burden
because every change needs to be implemented and tested for both
formats.

Remove the 32 bits PTE format. The memory usage increase due to
larger PTEs is minimal (approx. 0,1% of memory).

This also means that from now on huge pages are supported also
with 32 bits physical addresses.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/04a658209ea78dcc0f3dbde6b2c29cf1939adfe9.1767721208.git.chleroy@kernel.org
---
 arch/powerpc/include/asm/nohash/32/pgtable.h  |  4 +-
 arch/powerpc/include/asm/nohash/32/pte-85xx.h | 59 ---------------------------
 arch/powerpc/include/asm/pgtable-types.h      |  2 +-
 arch/powerpc/kernel/head_85xx.S               | 46 +--------------------
 arch/powerpc/platforms/Kconfig.cputype        |  4 +-
 5 files changed, 5 insertions(+), 110 deletions(-)
 delete mode 100644 arch/powerpc/include/asm/nohash/32/pte-85xx.h

diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 2d71e4b7cd09..496ecc65ac25 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -120,10 +120,8 @@
 
 #if defined(CONFIG_44x)
 #include <asm/nohash/32/pte-44x.h>
-#elif defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
-#include <asm/nohash/pte-e500.h>
 #elif defined(CONFIG_PPC_85xx)
-#include <asm/nohash/32/pte-85xx.h>
+#include <asm/nohash/pte-e500.h>
 #elif defined(CONFIG_PPC_8xx)
 #include <asm/nohash/32/pte-8xx.h>
 #endif
diff --git a/arch/powerpc/include/asm/nohash/32/pte-85xx.h b/arch/powerpc/include/asm/nohash/32/pte-85xx.h
deleted file mode 100644
index 14d64b4f3f14..000000000000
--- a/arch/powerpc/include/asm/nohash/32/pte-85xx.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_32_PTE_85xx_H
-#define _ASM_POWERPC_NOHASH_32_PTE_85xx_H
-#ifdef __KERNEL__
-
-/* PTE bit definitions for Freescale BookE SW loaded TLB MMU based
- * processors
- *
-   MMU Assist Register 3:
-
-   32 33 34 35 36  ... 50 51 52 53 54 55 56 57 58 59 60 61 62 63
-   RPN......................  0  0 U0 U1 U2 U3 UX SX UW SW UR SR
-
-   - PRESENT *must* be in the bottom two bits because swap PTEs use
-     the top 30 bits.
-
-*/
-
-/* Definitions for FSL Book-E Cores */
-#define _PAGE_READ	0x00001	/* H: Read permission (SR) */
-#define _PAGE_PRESENT	0x00002	/* S: PTE contains a translation */
-#define _PAGE_WRITE	0x00004	/* S: Write permission (SW) */
-#define _PAGE_DIRTY	0x00008	/* S: Page dirty */
-#define _PAGE_EXEC	0x00010	/* H: SX permission */
-#define _PAGE_ACCESSED	0x00020	/* S: Page referenced */
-
-#define _PAGE_ENDIAN	0x00040	/* H: E bit */
-#define _PAGE_GUARDED	0x00080	/* H: G bit */
-#define _PAGE_COHERENT	0x00100	/* H: M bit */
-#define _PAGE_NO_CACHE	0x00200	/* H: I bit */
-#define _PAGE_WRITETHRU	0x00400	/* H: W bit */
-#define _PAGE_SPECIAL	0x00800 /* S: Special page */
-
-#define _PMD_PRESENT	0
-#define _PMD_PRESENT_MASK (PAGE_MASK)
-#define _PMD_BAD	(~PAGE_MASK)
-#define _PMD_USER	0
-
-#define _PTE_NONE_MASK	0
-
-#define PTE_WIMGE_SHIFT (6)
-
-/*
- * We define 2 sets of base prot bits, one for basic pages (ie,
- * cacheable kernel and user pages) and one for non cacheable
- * pages. We always set _PAGE_COHERENT when SMP is enabled or
- * the processor might need it for DMA coherency.
- */
-#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
-#if defined(CONFIG_SMP) || defined(CONFIG_PPC_E500MC)
-#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
-#else
-#define _PAGE_BASE	(_PAGE_BASE_NC)
-#endif
-
-#include <asm/pgtable-masks.h>
-
-#endif /* __KERNEL__ */
-#endif /*  _ASM_POWERPC_NOHASH_32_PTE_FSL_85xx_H */
diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h
index f3086e39e7d2..e8dec885b6e4 100644
--- a/arch/powerpc/include/asm/pgtable-types.h
+++ b/arch/powerpc/include/asm/pgtable-types.h
@@ -49,7 +49,7 @@ static inline unsigned long pud_val(pud_t x)
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
-#if defined(CONFIG_PPC_85xx) && defined(CONFIG_PTE_64BIT)
+#if defined(CONFIG_PPC_85xx)
 typedef struct { unsigned long long pgd; } pgd_t;
 
 static inline unsigned long long pgd_val(pgd_t x)
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index f9a73fae6464..8867596d35ad 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -305,7 +305,6 @@ set_ivor:
  *   r12 is pointer to the pte
  *   r10 is the pshift from the PGD, if we're a hugepage
  */
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_HUGETLB_PAGE
 #define FIND_PTE	\
 	rlwinm	r12, r13, 14, 18, 28;	/* Compute pgdir/pmd offset */	\
@@ -329,15 +328,6 @@ set_ivor:
 	rlwimi	r12, r13, 23, 20, 28;	/* Compute pte address */	\
 	lwz	r11, 4(r12);		/* Get pte entry */
 #endif /* HUGEPAGE */
-#else /* !PTE_64BIT */
-#define FIND_PTE	\
-	rlwimi	r11, r13, 12, 20, 29;	/* Create L1 (pgdir/pmd) address */	\
-	lwz	r11, 0(r11);		/* Get L1 entry */			\
-	rlwinm.	r12, r11, 0, 0, 19;	/* Extract L2 (pte) base address */	\
-	beq	2f;			/* Bail if no table */			\
-	rlwimi	r12, r13, 22, 20, 29;	/* Compute PTE address */		\
-	lwz	r11, 0(r12);		/* Get Linux PTE */
-#endif
 
 /*
  * Interrupt vector entry code
@@ -473,21 +463,15 @@ END_BTB_FLUSH_SECTION
 4:
 	FIND_PTE
 
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT|_PAGE_BAP_SR
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT|_PAGE_READ|_PAGE_ACCESSED
-#endif
 	andc.	r13,r13,r11		/* Check permission */
 
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
 	subf	r13,r11,r12		/* create false data dep */
 	lwzx	r13,r11,r13		/* Get upper pte bits */
 #else
 	lwz	r13,0(r12)		/* Get upper pte bits */
-#endif
 #endif
 
 	bne	2f			/* Bail if permission/valid mismatch */
@@ -552,12 +536,8 @@ END_BTB_FLUSH_SECTION
 
 	FIND_PTE
 	/* Make up the required permissions for kernel code */
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_SX
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#endif
 	b	4f
 
 	/* Get the PGD for the current thread */
@@ -573,23 +553,17 @@ END_BTB_FLUSH_SECTION
 
 	FIND_PTE
 	/* Make up the required permissions for user code */
-#ifdef CONFIG_PTE_64BIT
 	li	r13,_PAGE_PRESENT | _PAGE_BAP_UX
 	oris	r13,r13,_PAGE_ACCESSED@h
-#else
-	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#endif
 
 4:
 	andc.	r13,r13,r11		/* Check permission */
 
-#ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
 	subf	r13,r11,r12		/* create false data dep */
 	lwzx	r13,r11,r13		/* Get upper pte bits */
 #else
 	lwz	r13,0(r12)		/* Get upper pte bits */
-#endif
 #endif
 
 	bne	2f			/* Bail if permission mismatch */
@@ -683,7 +657,7 @@ interrupt_end:
  *	r10 - tsize encoding (if HUGETLB_PAGE) or available to use
  *	r11 - TLB (info from Linux PTE)
  *	r12 - available to use
- *	r13 - upper bits of PTE (if PTE_64BIT) or available to use
+ *	r13 - upper bits of PTE
  *	CR5 - results of addr >= PAGE_OFFSET
  *	MAS0, MAS1 - loaded with proper value when we get here
  *	MAS2, MAS3 - will need additional info from Linux PTE
@@ -751,7 +725,6 @@ finish_tlb_load:
 	 * here we (properly should) assume have the appropriate value.
 	 */
 finish_tlb_load_cont:
-#ifdef CONFIG_PTE_64BIT
 	rlwinm	r12, r11, 32-2, 26, 31	/* Move in perm bits */
 	andi.	r10, r11, _PAGE_DIRTY
 	bne	1f
@@ -764,26 +737,9 @@ BEGIN_MMU_FTR_SECTION
 	srwi	r10, r13, 12		/* grab RPN[12:31] */
 	mtspr	SPRN_MAS7, r10
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
-#else
-	li	r10, (_PAGE_EXEC | _PAGE_READ)
-	mr	r13, r11
-	rlwimi	r10, r11, 31, 29, 29	/* extract _PAGE_DIRTY into SW */
-	and	r12, r11, r10
-	mcrf	cr0, cr5		/* Test for user page */
-	slwi	r10, r12, 1
-	or	r10, r10, r12
-	rlwinm	r10, r10, 0, ~_PAGE_EXEC	/* Clear SX on user pages */
-	isellt	r12, r10, r12
-	rlwimi	r13, r12, 0, 20, 31	/* Get RPN from PTE, merge w/ perms */
-	mtspr	SPRN_MAS3, r13
-#endif
 
 	mfspr	r12, SPRN_MAS2
-#ifdef CONFIG_PTE_64BIT
 	rlwimi	r12, r11, 32-19, 27, 31	/* extract WIMGE from pte */
-#else
-	rlwimi	r12, r11, 26, 27, 31	/* extract WIMGE from pte */
-#endif
 #ifdef CONFIG_HUGETLB_PAGE
 	beq	6, 3f			/* don't mask if page isn't huge */
 	li	r13, 1
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index f399917c17bd..bac02c83bb3e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -276,7 +276,7 @@ config PPC_BOOK3S
 config PPC_E500
 	select FSL_EMB_PERFMON
 	bool
-	select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
+	select ARCH_SUPPORTS_HUGETLBFS
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
 	select PPC_KUEP
@@ -337,7 +337,7 @@ config BOOKE
 config PTE_64BIT
 	bool
 	depends on 44x || PPC_E500 || PPC_86xx
-	default y if PHYS_64BIT
+	default y if PPC_E500 || PHYS_64BIT
 
 config PHYS_64BIT
 	bool 'Large physical address support' if PPC_E500 || PPC_86xx
-- 
cgit v1.2.3


From 0ee95a1d458630272d0415d0ffa9424fcb606c90 Mon Sep 17 00:00:00 2001
From: "Christophe Leroy (CS GROUP)" <chleroy@kernel.org>
Date: Tue, 3 Feb 2026 08:30:41 +0100
Subject: powerpc/uaccess: Fix inline assembly for clang build on PPC32

Test robot reports the following error with clang-16.0.6:

   In file included from kernel/rseq.c:75:
   include/linux/rseq_entry.h:141:3: error: invalid operand for instruction
                   unsafe_get_user(offset, &ucs->post_commit_offset, efault);
                   ^
   include/linux/uaccess.h:608:2: note: expanded from macro 'unsafe_get_user'
           arch_unsafe_get_user(x, ptr, local_label);      \
           ^
   arch/powerpc/include/asm/uaccess.h:518:2: note: expanded from macro 'arch_unsafe_get_user'
           __get_user_size_goto(__gu_val, __gu_addr, sizeof(*(p)), e); \
           ^
   arch/powerpc/include/asm/uaccess.h:284:2: note: expanded from macro '__get_user_size_goto'
           __get_user_size_allowed(x, ptr, size, __gus_retval);    \
           ^
   arch/powerpc/include/asm/uaccess.h:275:10: note: expanded from macro '__get_user_size_allowed'
           case 8: __get_user_asm2(x, (u64 __user *)ptr, retval);  break;  \
                   ^
   arch/powerpc/include/asm/uaccess.h:258:4: note: expanded from macro '__get_user_asm2'
                   "       li %1+1,0\n"                    \
                    ^
   <inline asm>:7:5: note: instantiated into assembly here
           li 31+1,0
              ^
   1 error generated.

On PPC32, for 64 bits vars a pair of registers is used. Usually the
lower register in the pair is the high part and the higher register is
the low part. GCC uses r3/r4 ... r11/r12 ... r14/r15 ... r30/r31

In older kernel code inline assembly was using %1 and %1+1 to represent
64 bits values. However here it looks like clang uses r31 as high part,
allthough r32 doesn't exist hence the error.

Allthoug %1+1 should work, most places now use %L1 instead of %1+1, so
let's do the same here.

With that change, the build doesn't fail anymore and a disassembly shows
clang uses r17/r18 and r31/r14 pair when GCC would have used r16/r17 and
r30/r31:

	Disassembly of section .fixup:

	00000000 <.fixup>:
	   0:	38 a0 ff f2 	li      r5,-14
	   4:	3a 20 00 00 	li      r17,0
	   8:	3a 40 00 00 	li      r18,0
	   c:	48 00 00 00 	b       c <.fixup+0xc>
				c: R_PPC_REL24	.text+0xbc
	  10:	38 a0 ff f2 	li      r5,-14
	  14:	3b e0 00 00 	li      r31,0
	  18:	39 c0 00 00 	li      r14,0
	  1c:	48 00 00 00 	b       1c <.fixup+0x1c>
				1c: R_PPC_REL24	.text+0x144

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602021825.otcItxGi-lkp@intel.com/
Fixes: c20beffeec3c ("powerpc/uaccess: Use flexible addressing with __put_user()/__get_user()")
Signed-off-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Acked-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/8ca3a657a650e497a96bfe7acde2f637dadab344.1770103646.git.chleroy@kernel.org
---
 arch/powerpc/include/asm/uaccess.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index ba1d878c3f40..570b3d91e2e4 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -255,7 +255,7 @@ __gus_failed:								\
 		".section .fixup,\"ax\"\n"		\
 		"4:	li %0,%3\n"			\
 		"	li %1,0\n"			\
-		"	li %1+1,0\n"			\
+		"	li %L1,0\n"			\
 		"	b 3b\n"				\
 		".previous\n"				\
 		EX_TABLE(1b, 4b)			\
-- 
cgit v1.2.3


From 0706178339974d4332a782ba851cb6694bd210fe Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 28 Jan 2026 08:02:20 -0600
Subject: powerpc: dts: fsl: Drop unused .dtsi files

These files are not included by anything and therefore don't get built or
tested.

There's also no upstream driver for the interlaken-lac stuff.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260128140222.1627203-1-robh@kernel.org
---
 .../boot/dts/fsl/interlaken-lac-portals.dtsi       | 156 ---------------------
 arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi      |  45 ------
 arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi  |  43 ------
 .../dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi   |  80 -----------
 4 files changed, 324 deletions(-)
 delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
 delete mode 100644 arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi

diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
deleted file mode 100644
index 9cffccf4e07e..000000000000
--- a/arch/powerpc/boot/dts/fsl/interlaken-lac-portals.dtsi
+++ /dev/null
@@ -1,156 +0,0 @@
-/* T4240 Interlaken LAC Portal device tree stub with 24 portals.
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#address-cells = <0x1>;
-#size-cells = <0x1>;
-compatible = "fsl,interlaken-lac-portals";
-
-lportal0: lac-portal@0 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x0 0x1000>;
-};
-
-lportal1: lac-portal@1000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x1000 0x1000>;
-};
-
-lportal2: lac-portal@2000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x2000 0x1000>;
-};
-
-lportal3: lac-portal@3000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x3000 0x1000>;
-};
-
-lportal4: lac-portal@4000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x4000 0x1000>;
-};
-
-lportal5: lac-portal@5000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x5000 0x1000>;
-};
-
-lportal6: lac-portal@6000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x6000 0x1000>;
-};
-
-lportal7: lac-portal@7000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x7000 0x1000>;
-};
-
-lportal8: lac-portal@8000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x8000 0x1000>;
-};
-
-lportal9: lac-portal@9000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x9000 0x1000>;
-};
-
-lportal10: lac-portal@A000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xA000 0x1000>;
-};
-
-lportal11: lac-portal@B000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xB000 0x1000>;
-};
-
-lportal12: lac-portal@C000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xC000 0x1000>;
-};
-
-lportal13: lac-portal@D000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xD000 0x1000>;
-};
-
-lportal14: lac-portal@E000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xE000 0x1000>;
-};
-
-lportal15: lac-portal@F000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0xF000 0x1000>;
-};
-
-lportal16: lac-portal@10000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x10000 0x1000>;
-};
-
-lportal17: lac-portal@11000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x11000 0x1000>;
-};
-
-lportal18: lac-portal@1200 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x12000 0x1000>;
-};
-
-lportal19: lac-portal@13000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x13000 0x1000>;
-};
-
-lportal20: lac-portal@14000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x14000 0x1000>;
-};
-
-lportal21: lac-portal@15000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x15000 0x1000>;
-};
-
-lportal22: lac-portal@16000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x16000 0x1000>;
-};
-
-lportal23: lac-portal@17000 {
-	compatible = "fsl,interlaken-lac-portal-v1.0";
-	reg = <0x17000 0x1000>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi b/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
deleted file mode 100644
index e8208720ac0e..000000000000
--- a/arch/powerpc/boot/dts/fsl/interlaken-lac.dtsi
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * T4 Interlaken Look-aside Controller (LAC) device tree stub
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-lac: lac@229000 {
-	compatible = "fsl,interlaken-lac";
-	reg = <0x229000 0x1000>;
-	interrupts = <16 2 1 18>;
-};
-
-lac-hv@228000 {
-	compatible = "fsl,interlaken-lac-hv";
-	reg = <0x228000 0x1000>;
-	fsl,non-hv-node = <&lac>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi b/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
deleted file mode 100644
index 1cf0b77b1efe..000000000000
--- a/arch/powerpc/boot/dts/fsl/pq3-mpic-message-B.dtsi
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * PQ3 MPIC Message (Group B) device tree stub [ controller @ offset 0x42400 ]
- *
- * Copyright 2012 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-message@42400 {
-	compatible = "fsl,mpic-v3.1-msgr";
-	reg = <0x42400 0x200>;
-	interrupts = <
-		0xb4 2 0 0
-		0xb5 2 0 0
-		0xb6 2 0 0
-		0xb7 2 0 0>;
-};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
deleted file mode 100644
index 71eb75e82c2e..000000000000
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0-10g-1-best-effort.dtsi
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * QorIQ FMan v3 1g port #1 device tree stub [ controller @ offset 0x400000 ]
- *
- * Copyright 2012 - 2015 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *	 notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *	 notice, this list of conditions and the following disclaimer in the
- *	 documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *	 names of its contributors may be used to endorse or promote products
- *	 derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-fman@400000 {
-	fman0_rx_0x09: port@89000 {
-		cell-index = <0x9>;
-		compatible = "fsl,fman-v3-port-rx";
-		reg = <0x89000 0x1000>;
-		fsl,fman-10g-port;
-		fsl,fman-best-effort-port;
-	};
-
-	fman0_tx_0x29: port@a9000 {
-		cell-index = <0x29>;
-		compatible = "fsl,fman-v3-port-tx";
-		reg = <0xa9000 0x1000>;
-		fsl,fman-10g-port;
-		fsl,fman-best-effort-port;
-	};
-
-	ethernet@e2000 {
-		cell-index = <1>;
-		compatible = "fsl,fman-memac";
-		reg = <0xe2000 0x1000>;
-		fsl,fman-ports = <&fman0_rx_0x09 &fman0_tx_0x29>;
-		ptp-timer = <&ptp_timer0>;
-		pcsphy-handle = <&pcsphy1>, <&qsgmiia_pcs1>;
-		pcs-handle-names = "sgmii", "qsgmii";
-	};
-
-	mdio@e1000 {
-		qsgmiia_pcs1: ethernet-pcs@1 {
-			compatible = "fsl,lynx-pcs";
-			reg = <1>;
-		};
-	};
-
-	mdio@e3000 {
-		#address-cells = <1>;
-		#size-cells = <0>;
-		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
-		reg = <0xe3000 0x1000>;
-		fsl,erratum-a011043; /* must ignore read errors */
-
-		pcsphy1: ethernet-phy@0 {
-			reg = <0x0>;
-		};
-	};
-};
-- 
cgit v1.2.3


From 6fc5d63c6ff5fe5e5beea3e7fe2ca3058351ae99 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 29 Oct 2025 12:40:46 -0500
Subject: powerpc/prom_init: Fixup missing #size-cells on PowerMac media-bay
 nodes

Similar to other PowerMac mac-io devices, the media-bay node is missing the
"#size-cells" property.

Depends-on: commit 045b14ca5c36 ("of: WARN on deprecated #address-cells/#size-cells handling")
Reported-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20251029174047.1620073-1-robh@kernel.org
---
 arch/powerpc/kernel/prom_init.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 827c958677f8..f26e80cbc615 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2893,7 +2893,8 @@ static void __init fixup_device_tree_pmac(void)
 	for (node = 0; prom_next_node(&node); ) {
 		type[0] = '\0';
 		prom_getprop(node, "device_type", type, sizeof(type));
-		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s"))
+		if (prom_strcmp(type, "escc") && prom_strcmp(type, "i2s") &&
+		    prom_strcmp(type, "media-bay"))
 			continue;
 
 		if (prom_getproplen(node, "#size-cells") != PROM_ERROR)
-- 
cgit v1.2.3


From 20197b967a6a29dab81495f25a988515bda84cfe Mon Sep 17 00:00:00 2001
From: Sourabh Jain <sourabhjain@linux.ibm.com>
Date: Wed, 24 Dec 2025 20:42:57 +0530
Subject: powerpc/kexec/core: use big-endian types for crash variables

Use explicit word-sized big-endian types for kexec and crash related
variables. This makes the endianness unambiguous and avoids type
mismatches that trigger sparse warnings.

The change addresses sparse warnings like below (seen on both 32-bit
and 64-bit builds):

CHECK   ../arch/powerpc/kexec/core.c
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] crashk_base
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] crashk_size
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned long long static [addressable] [toplevel] mem_limit
sparse:    got restricted __be32 [usertype]
sparse: warning: incorrect type in assignment (different base types)
sparse:    expected unsigned int static [addressable] [toplevel] [usertype] kernel_end
sparse:    got restricted __be32 [usertype]

No functional change intended.

Fixes: ea961a828fe7 ("powerpc: Fix endian issues in kexec and crash dump code")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202512221405.VHPKPjnp-lkp@intel.com/
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20251224151257.28672-1-sourabhjain@linux.ibm.com
---
 arch/powerpc/kexec/core.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 104c05520bf0..dc44f11be353 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -23,6 +23,7 @@
 #include <asm/firmware.h>
 
 #define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG)
+#define __be_word __PASTE(__be, BITS_PER_LONG)
 
 #ifdef CONFIG_CRASH_DUMP
 void machine_crash_shutdown(struct pt_regs *regs)
@@ -146,25 +147,25 @@ int __init overlaps_crashkernel(unsigned long start, unsigned long size)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static phys_addr_t crashk_base;
-static phys_addr_t crashk_size;
-static unsigned long long mem_limit;
+static __be_word crashk_base;
+static __be_word crashk_size;
+static __be_word mem_limit;
 
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &crashk_base
 };
 
 static struct property crashk_size_prop = {
 	.name = "linux,crashkernel-size",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &crashk_size,
 };
 
 static struct property memory_limit_prop = {
 	.name = "linux,memory-limit",
-	.length = sizeof(unsigned long long),
+	.length = sizeof(__be_word),
 	.value = &mem_limit,
 };
 
@@ -193,11 +194,11 @@ static void __init export_crashk_values(struct device_node *node)
 }
 #endif /* CONFIG_CRASH_RESERVE */
 
-static phys_addr_t kernel_end;
+static __be_word kernel_end;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
-	.length = sizeof(phys_addr_t),
+	.length = sizeof(__be_word),
 	.value = &kernel_end,
 };
 
-- 
cgit v1.2.3


From 04e707cb77c272cb0bb2e2e3c5c7f844d804a089 Mon Sep 17 00:00:00 2001
From: Sourabh Jain <sourabhjain@linux.ibm.com>
Date: Fri, 27 Feb 2026 22:48:01 +0530
Subject: powerpc/crash: adjust the elfcorehdr size

With crash hotplug support enabled, additional memory is allocated to
the elfcorehdr kexec segment to accommodate resources added during
memory hotplug events. However, the kdump FDT is not updated with the
same size, which can result in elfcorehdr corruption in the kdump
kernel.

Update elf_headers_sz (the kimage member representing the size of the
elfcorehdr kexec segment) to reflect the total memory allocated for the
elfcorehdr segment instead of the elfcorehdr buffer size at the time of
kdump load. This allows of_kexec_alloc_and_setup_fdt() to reserve the
full elfcorehdr memory in the kdump FDT and prevents elfcorehdr
corruption.

Fixes: 849599b702ef8 ("powerpc/crash: add crash memory hotplug support")
Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260227171801.2238847-1-sourabhjain@linux.ibm.com
---
 arch/powerpc/kexec/file_load_64.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index e7ef8b2a2554..5f6d50e4c3d4 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -450,6 +450,11 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 	kbuf->buffer = headers;
 	kbuf->mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf->bufsz = headers_sz;
+
+	/*
+	 * Account for extra space required to accommodate additional memory
+	 * ranges in elfcorehdr due to memory hotplug events.
+	 */
 	kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem);
 	kbuf->top_down = false;
 
@@ -460,7 +465,14 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf)
 	}
 
 	image->elf_load_addr = kbuf->mem;
-	image->elf_headers_sz = headers_sz;
+
+	/*
+	 * If CONFIG_CRASH_HOTPLUG is enabled, the elfcorehdr kexec segment
+	 * memsz can be larger than bufsz. Always initialize elf_headers_sz
+	 * with memsz. This ensures the correct size is reserved for elfcorehdr
+	 * memory in the FDT prepared for kdump.
+	 */
+	image->elf_headers_sz = kbuf->memsz;
 	image->elf_headers = headers;
 out:
 	kfree(cmem);
-- 
cgit v1.2.3


From fbdfa8da05b6ae44114fc4f9b3e83e1736fd411c Mon Sep 17 00:00:00 2001
From: Naveen Anandhan <mr.navi8680@gmail.com>
Date: Sat, 28 Feb 2026 13:17:35 +0530
Subject: selftests: tc-testing: fix list_categories() crash on list type

list_categories() builds a set directly from the 'category'
field of each test case. Since 'category' is a list,
set(map(...)) attempts to insert lists into a set, which
raises:

  TypeError: unhashable type: 'list'

Flatten category lists and collect unique category names
using set.update() instead.

Signed-off-by: Naveen Anandhan <mr.navi8680@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tdc_helper.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py
index 0440d252c4c5..bc447ca57333 100644
--- a/tools/testing/selftests/tc-testing/tdc_helper.py
+++ b/tools/testing/selftests/tc-testing/tdc_helper.py
@@ -38,10 +38,14 @@ def list_test_cases(testlist):
 
 
 def list_categories(testlist):
-    """ Show all categories that are present in a test case file. """
-    categories = set(map(lambda x: x['category'], testlist))
+    """Show all unique categories present in the test cases."""
+    categories = set()
+    for t in testlist:
+        if 'category' in t:
+            categories.update(t['category'])
+
     print("Available categories:")
-    print(", ".join(str(s) for s in categories))
+    print(", ".join(sorted(categories)))
     print("")
 
 
-- 
cgit v1.2.3


From 29a3edd7004bb635d299fb9bc6f0ea4ef13ed5a2 Mon Sep 17 00:00:00 2001
From: Jacob Moroni <jmoroni@google.com>
Date: Fri, 27 Feb 2026 15:27:43 +0000
Subject: RDMA/irdma: Fix double free related to rereg_user_mr

If IB_MR_REREG_TRANS is set during rereg_user_mr, the
umem will be released and a new one will be allocated
in irdma_rereg_mr_trans. If any step of irdma_rereg_mr_trans
fails after the new umem is allocated, it releases the umem,
but does not set iwmr->region to NULL. The problem is that
this failure is propagated to the user, who will then call
ibv_dereg_mr (as they should). Then, the dereg_mr path will
see a non-NULL umem and attempt to call ib_umem_release again.

Fix this by setting iwmr->region to NULL after ib_umem_release.

Fixed: 5ac388db27c4 ("RDMA/irdma: Add support to re-register a memory region")
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Link: https://patch.msgid.link/20260227152743.1183388-1-jmoroni@google.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 7251cd7a2147..a20d25585993 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -3723,6 +3723,7 @@ static int irdma_rereg_mr_trans(struct irdma_mr *iwmr, u64 start, u64 len,
 
 err:
 	ib_umem_release(region);
+	iwmr->region = NULL;
 	return err;
 }
 
-- 
cgit v1.2.3


From a08aaf3968aec5d05cd32c801b8cc0c61da69c41 Mon Sep 17 00:00:00 2001
From: Abhijit Gangurde <abhijit.gangurde@amd.com>
Date: Fri, 27 Feb 2026 11:48:09 +0530
Subject: RDMA/ionic: Preserve and set Ethernet source MAC after
 ib_ud_header_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ionic_build_hdr() populated the Ethernet source MAC (hdr->eth.smac_h) by
passing the header’s storage directly to rdma_read_gid_l2_fields().
However, ib_ud_header_init() is called after that and re-initializes the
UD header, which wipes the previously written smac_h. As a result, packets
are emitted with an zero source MAC address on the wire.

Correct the source MAC by reading the GID-derived smac into a temporary
buffer and copy it after ib_ud_header_init() completes.

Fixes: e8521822c733 ("RDMA/ionic: Register device ops for control path")
Cc: stable@vger.kernel.org # 6.18
Signed-off-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://patch.msgid.link/20260227061809.2979990-1-abhijit.gangurde@amd.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/ionic/ionic_controlpath.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/ionic/ionic_controlpath.c b/drivers/infiniband/hw/ionic/ionic_controlpath.c
index 4842931f5316..a5671da3db64 100644
--- a/drivers/infiniband/hw/ionic/ionic_controlpath.c
+++ b/drivers/infiniband/hw/ionic/ionic_controlpath.c
@@ -508,6 +508,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev,
 {
 	const struct ib_global_route *grh;
 	enum rdma_network_type net;
+	u8 smac[ETH_ALEN];
 	u16 vlan;
 	int rc;
 
@@ -518,7 +519,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev,
 
 	grh = rdma_ah_read_grh(attr);
 
-	rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, &hdr->eth.smac_h[0]);
+	rc = rdma_read_gid_l2_fields(grh->sgid_attr, &vlan, smac);
 	if (rc)
 		return rc;
 
@@ -536,6 +537,7 @@ static int ionic_build_hdr(struct ionic_ibdev *dev,
 	if (rc)
 		return rc;
 
+	ether_addr_copy(hdr->eth.smac_h, smac);
 	ether_addr_copy(hdr->eth.dmac_h, attr->roce.dmac);
 
 	if (net == RDMA_NETWORK_IPV4) {
-- 
cgit v1.2.3


From 5c3daa5301693d2e5364483a3405649a0fdaed98 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 2 Mar 2026 22:31:44 +0800
Subject: power: sequencing: pcie-m2: Fix device node reference leak in probe

In pwrseq_pcie_m2_probe(), ctx->of_node acquires an explicit reference
to the device node using of_node_get(), but there is no corresponding
of_node_put() in the driver's error handling paths or removal.

Since the ctx is tied to the lifecycle of the platform device, there
is no need to hold an additional reference to the device's own of_node.

Fixes: 52e7b5bd62ba ("power: sequencing: Add the Power Sequencing driver for the PCIe M.2 connectors")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260302-m2-v1-1-a6533e18aa69@gmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/power/sequencing/pwrseq-pcie-m2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c
index d31a7dd8b35c..dadb4aad9d5d 100644
--- a/drivers/power/sequencing/pwrseq-pcie-m2.c
+++ b/drivers/power/sequencing/pwrseq-pcie-m2.c
@@ -109,7 +109,7 @@ static int pwrseq_pcie_m2_probe(struct platform_device *pdev)
 	if (!ctx)
 		return -ENOMEM;
 
-	ctx->of_node = of_node_get(dev->of_node);
+	ctx->of_node = dev_of_node(dev);
 	ctx->pdata = device_get_match_data(dev);
 	if (!ctx->pdata)
 		return dev_err_probe(dev, -ENODEV,
-- 
cgit v1.2.3


From b3b1d3ae1d87bc9398fb715c945968bf4c75a09a Mon Sep 17 00:00:00 2001
From: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Date: Wed, 4 Mar 2026 08:22:59 +0100
Subject: ata: libata-core: Disable LPM on ST1000DM010-2EP102

According to a user report, the ST1000DM010-2EP102 has problems with LPM,
causing random system freezes. The drive belongs to the same BarraCuda
family as the ST2000DM008-2FR102 which has the same issue.

Cc: stable@vger.kernel.org
Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Reported-by: Filippo Baiamonte <filippo.ba03@bugzilla.kernel.org>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221163
Signed-off-by: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index ccbf320524da..76b012f544ea 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4189,6 +4189,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 						ATA_QUIRK_FIRMWARE_WARN },
 
 	/* Seagate disks with LPM issues */
+	{ "ST1000DM010-2EP102",	NULL,		ATA_QUIRK_NOLPM },
 	{ "ST2000DM008-2FR102",	NULL,		ATA_QUIRK_NOLPM },
 
 	/* drives which fail FPDMA_AA activation (some may freeze afterwards)
-- 
cgit v1.2.3


From 6270b8ac2f41858952074b23c2d3d9aa2fe1bfa9 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 26 Feb 2026 07:46:46 +0900
Subject: xfs: remove scratch field from struct xfs_gc_bio

The scratch field in struct xfs_gc_bio is unused. Remove it.

Fixes: 102f444b57b3 ("xfs: rework zone GC buffer management")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_gc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 7efeecd2d85f..309f70098524 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -96,7 +96,6 @@ struct xfs_gc_bio {
 	 */
 	xfs_fsblock_t			old_startblock;
 	xfs_daddr_t			new_daddr;
-	struct xfs_zone_scratch		*scratch;
 
 	/* Are we writing to a sequential write required zone? */
 	bool				is_seq;
@@ -779,7 +778,6 @@ xfs_zone_gc_split_write(
 	ihold(VFS_I(chunk->ip));
 	split_chunk->ip = chunk->ip;
 	split_chunk->is_seq = chunk->is_seq;
-	split_chunk->scratch = chunk->scratch;
 	split_chunk->offset = chunk->offset;
 	split_chunk->len = split_len;
 	split_chunk->old_startblock = chunk->old_startblock;
-- 
cgit v1.2.3


From 0ca1a8331c0fa5e57844e003a5d667a15b1e002c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 2 Mar 2026 09:31:58 -0800
Subject: xfs: fix race between healthmon unmount and read_iter

xfs/1879 on one of my test VMs got stuck due to the xfs_io healthmon
subcommand sleeping in wait_event_interruptible at:

 xfs_healthmon_read_iter+0x558/0x5f8 [xfs]
 vfs_read+0x248/0x320
 ksys_read+0x78/0x120

Looking at xfs_healthmon_read_iter, in !O_NONBLOCK mode it will sleep
until the mount cookie == DETACHED_MOUNT_COOKIE, there are events
waiting to be formatted, or there are formatted events in the read
buffer that could be copied to userspace.

Poking into the running kernel, I see that there are zero events in the
list, the read buffer is empty, and the mount cookie is indeed in
DETACHED state.  IOWs, xfs_healthmon_has_eventdata should have returned
true, but instead we're asleep waiting for a wakeup.

I think what happened here is that xfs_healthmon_read_iter and
xfs_healthmon_unmount were racing with each other, and _read_iter lost
the race.  _unmount queued an unmount event, which woke up _read_iter.
It found, formatted, and copied the event out to userspace.  That
cleared out the pending event list and emptied the read buffer.  xfs_io
then called read() again, so _has_eventdata decided that we should sleep
on the empty event queue.

Next, _unmount called xfs_healthmon_detach, which set the mount cookie
to DETACHED.  Unfortunately, it didn't call wake_up_all on the hm, so
the wait_event_interruptible in the _read_iter thread remains asleep.
That's why the test stalled.

Fix this by moving the wake_up_all call to xfs_healthmon_detach.

Fixes: b3a289a2a9397b ("xfs: create event queuing, formatting, and discovery infrastructure")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_healthmon.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c
index 4a06d6632f65..26c325d34bd1 100644
--- a/fs/xfs/xfs_healthmon.c
+++ b/fs/xfs/xfs_healthmon.c
@@ -141,6 +141,16 @@ xfs_healthmon_detach(
 	hm->mount_cookie = DETACHED_MOUNT_COOKIE;
 	spin_unlock(&xfs_healthmon_lock);
 
+	/*
+	 * Wake up any readers that might remain.  This can happen if unmount
+	 * races with the healthmon fd owner entering ->read_iter, having
+	 * already emptied the event queue.
+	 *
+	 * In the ->release case there shouldn't be any readers because the
+	 * only users of the waiter are read and poll.
+	 */
+	wake_up_all(&hm->wait);
+
 	trace_xfs_healthmon_detach(hm);
 	xfs_healthmon_put(hm);
 }
@@ -1027,13 +1037,6 @@ xfs_healthmon_release(
 	 * process can create another health monitor file.
 	 */
 	xfs_healthmon_detach(hm);
-
-	/*
-	 * Wake up any readers that might be left.  There shouldn't be any
-	 * because the only users of the waiter are read and poll.
-	 */
-	wake_up_all(&hm->wait);
-
 	xfs_healthmon_put(hm);
 	return 0;
 }
-- 
cgit v1.2.3


From aac9b27f7c1f2b2cf7f50a9ca633ecbbcaf22af9 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 3 Mar 2026 11:03:42 +0100
Subject: ata: libata: cancel pending work after clearing deferred_qc

Syzbot reported a WARN_ON() in ata_scsi_deferred_qc_work(), caused by
ap->ops->qc_defer() returning non-zero before issuing the deferred qc.

ata_scsi_schedule_deferred_qc() is called during each command completion.
This function will check if there is a deferred QC, and if
ap->ops->qc_defer() returns zero, meaning that it is possible to queue the
deferred qc at this time (without being deferred), then it will queue the
work which will issue the deferred qc.

Once the work get to run, which can potentially be a very long time after
the work was scheduled, there is a WARN_ON() if ap->ops->qc_defer() returns
non-zero.

While we hold the ap->lock both when assigning and clearing deferred_qc,
and the work itself holds the ap->lock, the code currently does not cancel
the work after clearing the deferred qc.

This means that the following scenario can happen:
1) One or several NCQ commands are queued.
2) A non-NCQ command is queued, gets stored in ap->deferred_qc.
3) Last NCQ command gets completed, work is queued to issue the deferred
   qc.
4) Timeout or error happens, ap->deferred_qc is cleared. The queued work is
   currently NOT canceled.
5) Port is reset.
6) One or several NCQ commands are queued.
7) A non-NCQ command is queued, gets stored in ap->deferred_qc.
8) Work is finally run. Yet at this time, there is still NCQ commands in
   flight.

The work in 8) really belongs to the non-NCQ command in 2), not to the
non-NCQ command in 7). The reason why the work is executed when it is not
supposed to, is because it was never canceled when ap->deferred_qc was
cleared in 4). Thus, ensure that we always cancel the work after clearing
ap->deferred_qc.

Another potential fix would have been to let ata_scsi_deferred_qc_work() do
nothing if ap->ops->qc_defer() returns non-zero. However, canceling the
work when clearing ap->deferred_qc seems slightly more logical, as we hold
the ap->lock when clearing ap->deferred_qc, so we know that the work cannot
be holding the lock. (The function could be waiting for the lock, but that
is okay since it will do nothing if ap->deferred_qc is not set.)

Reported-by: syzbot+bcaf842a1e8ead8dfb89@syzkaller.appspotmail.com
Fixes: 0ea84089dbf6 ("ata: libata-scsi: avoid Non-NCQ command starvation")
Fixes: eddb98ad9364 ("ata: libata-eh: correctly handle deferred qc timeouts")
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-eh.c   | 1 +
 drivers/ata/libata-scsi.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index b373cceb95d2..563432400f72 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -659,6 +659,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 			 */
 			WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE);
 			ap->deferred_qc = NULL;
+			cancel_work(&ap->deferred_qc_work);
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_finish_cmd(scmd, &ap->eh_done_q);
 		} else if (i < ATA_MAX_QUEUE) {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c0dd75a0287c..ad798e5246b4 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1699,6 +1699,7 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap)
 
 	scmd = qc->scsicmd;
 	ap->deferred_qc = NULL;
+	cancel_work(&ap->deferred_qc_work);
 	ata_qc_free(qc);
 	scmd->result = (DID_SOFT_ERROR << 16);
 	scsi_done(scmd);
-- 
cgit v1.2.3


From fb1091febd668398aa84c161b8d9a1834321e021 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Mon, 2 Mar 2026 10:55:37 +0100
Subject: mm/slab: allow sheaf refill if blocking is not allowed

Ming Lei reported [1] a regression in the ublk null target benchmark due
to sheaves. The profile shows that the alloc_from_pcs() fastpath fails
and allocations fall back to ___slab_alloc(). It also shows the
allocations happen through mempool_alloc().

The strategy of mempool_alloc() is to call the underlying allocator
(here slab) without __GFP_DIRECT_RECLAIM first. This does not play well
with __pcs_replace_empty_main() checking for gfpflags_allow_blocking()
to decide if it should refill an empty sheaf or fallback to the
slowpath, so we end up falling back.

We could change the mempool strategy but there might be other paths
doing the same ting. So instead allow sheaf refill when blocking is not
allowed, changing the condition to gfpflags_allow_spinning(). The
original condition was unnecessarily restrictive.

Note this doesn't fully resolve the regression [1] as another component
of that are memoryless nodes, which is to be addressed separately.

Reported-by: Ming Lei <ming.lei@redhat.com>
Fixes: e47c897a2949 ("slab: add sheaves to most caches")
Link: https://lore.kernel.org/all/aZ0SbIqaIkwoW2mB@fedora/ [1]
Link: https://patch.msgid.link/20260302095536.34062-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index b1e9f16ba435..20cb4f3b636d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4567,7 +4567,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	struct slab_sheaf *empty = NULL;
 	struct slab_sheaf *full;
 	struct node_barn *barn;
-	bool can_alloc;
+	bool allow_spin;
 
 	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
@@ -4588,8 +4588,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return NULL;
 	}
 
-	full = barn_replace_empty_sheaf(barn, pcs->main,
-					gfpflags_allow_spinning(gfp));
+	allow_spin = gfpflags_allow_spinning(gfp);
+
+	full = barn_replace_empty_sheaf(barn, pcs->main, allow_spin);
 
 	if (full) {
 		stat(s, BARN_GET);
@@ -4599,9 +4600,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 
 	stat(s, BARN_GET_FAIL);
 
-	can_alloc = gfpflags_allow_blocking(gfp);
-
-	if (can_alloc) {
+	if (allow_spin) {
 		if (pcs->spare) {
 			empty = pcs->spare;
 			pcs->spare = NULL;
@@ -4611,8 +4610,9 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	}
 
 	local_unlock(&s->cpu_sheaves->lock);
+	pcs = NULL;
 
-	if (!can_alloc)
+	if (!allow_spin)
 		return NULL;
 
 	if (empty) {
@@ -4632,11 +4632,8 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	if (!full)
 		return NULL;
 
-	/*
-	 * we can reach here only when gfpflags_allow_blocking
-	 * so this must not be an irq
-	 */
-	local_lock(&s->cpu_sheaves->lock);
+	if (!local_trylock(&s->cpu_sheaves->lock))
+		goto barn_put;
 	pcs = this_cpu_ptr(s->cpu_sheaves);
 
 	/*
@@ -4667,6 +4664,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 		return pcs;
 	}
 
+barn_put:
 	barn_put_full_sheaf(barn, full);
 	stat(s, BARN_PUT);
 
-- 
cgit v1.2.3


From 6432f15c818cb30eec7c4ca378ecdebd9796f741 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Tue, 3 Mar 2026 22:57:22 +0900
Subject: mm/slab: change stride type from unsigned short to unsigned int

Commit 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
defined the type of slab->stride as unsigned short, because the author
initially planned to store stride within the lower 16 bits of the
page_type field, but later stored it in unused bits in the counters
field instead.

However, the idea of having only 2-byte stride turned out to be a
serious mistake. On systems with 64k pages, order-1 pages are 128k,
which is larger than USHRT_MAX. It triggers a debug warning because
s->size is 128k while stride, truncated to 2 bytes, becomes zero:

  ------------[ cut here ]------------
  Warning! stride (0) != s->size (131072)
  WARNING: mm/slub.c:2231 at alloc_slab_obj_exts_early.constprop.0+0x524/0x534, CPU#6: systemd-sysctl/307
  Modules linked in:
  CPU: 6 UID: 0 PID: 307 Comm: systemd-sysctl Not tainted 7.0.0-rc1+ #6 PREEMPTLAZY
  Hardware name: IBM,9009-22A POWER9 (architected) 0x4e0202 0xf000005 of:IBM,FW950.E0 (VL950_179) hv:phyp pSeries
  NIP:  c0000000008a9ac0 LR: c0000000008a9abc CTR: 0000000000000000
  REGS: c0000000141f7390 TRAP: 0700   Not tainted  (7.0.0-rc1+)
  MSR:  8000000000029033 <SF,EE,ME,IR,DR,RI,LE>  CR: 28004400  XER: 00000005
  CFAR: c000000000279318 IRQMASK: 0
  GPR00: c0000000008a9abc c0000000141f7630 c00000000252a300 c00000001427b200
  GPR04: 0000000000000004 0000000000000000 c000000000278fd0 0000000000000000
  GPR08: fffffffffffe0000 0000000000000000 0000000000000000 0000000022004400
  GPR12: c000000000f644b0 c000000017ff8f00 0000000000000000 0000000000000000
  GPR16: 0000000000000000 c0000000141f7aa0 0000000000000000 c0000000141f7a88
  GPR20: 0000000000000000 0000000000400cc0 ffffffffffffffff c00000001427b180
  GPR24: 0000000000000004 00000000000c0cc0 c000000004e89a20 c00000005de90011
  GPR28: 0000000000010010 c00000005df00000 c000000006017f80 c00c000000177a00
  NIP [c0000000008a9ac0] alloc_slab_obj_exts_early.constprop.0+0x524/0x534
  LR [c0000000008a9abc] alloc_slab_obj_exts_early.constprop.0+0x520/0x534
  Call Trace:
  [c0000000141f7630] [c0000000008a9abc] alloc_slab_obj_exts_early.constprop.0+0x520/0x534 (unreliable)
  [c0000000141f76c0] [c0000000008aafbc] allocate_slab+0x154/0x94c
  [c0000000141f7760] [c0000000008b41c0] refill_objects+0x124/0x16c
  [c0000000141f77c0] [c0000000008b4be0] __pcs_replace_empty_main+0x2b0/0x444
  [c0000000141f7810] [c0000000008b9600] __kvmalloc_node_noprof+0x840/0x914
  [c0000000141f7900] [c000000000a3dd40] seq_read_iter+0x60c/0xb00
  [c0000000141f7a10] [c000000000b36b24] proc_reg_read_iter+0x154/0x1fc
  [c0000000141f7a50] [c0000000009cee7c] vfs_read+0x39c/0x4e4
  [c0000000141f7b30] [c0000000009d0214] ksys_read+0x9c/0x180
  [c0000000141f7b90] [c00000000003a8d0] system_call_exception+0x1e0/0x4b0
  [c0000000141f7e50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec

This leads to slab_obj_ext() returning the first slabobj_ext or all
objects and confuses the reference counting of object cgroups [1] and
memory (un)charging for memory cgroups [2].

Fortunately, the counters field has 32 unused bits instead of 16
on 64-bit CPUs, which is wide enough to hold any value of s->size.
Change the type to unsigned int.

Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Closes: https://lore.kernel.org/lkml/ca241daa-e7e7-4604-a48d-de91ec9184a5@linux.ibm.com [1]
Closes: https://lore.kernel.org/all/ddff7c7d-c0c3-4780-808f-9a83268bbf0c@linux.ibm.com [2]
Fixes: 7a8e71bc619d ("mm/slab: use stride to access slabobj_ext")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260303135722.2680521-1-harry.yoo@oracle.com
Reviewed-by: Hao Li <hao.li@linux.dev>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slab.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/mm/slab.h b/mm/slab.h
index f6ef862b60ef..e9ab292acd22 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -59,7 +59,7 @@ struct freelist_counters {
 					 * to save memory. In case ->stride field is not available,
 					 * such optimizations are disabled.
 					 */
-					unsigned short stride;
+					unsigned int stride;
 #endif
 				};
 			};
@@ -559,20 +559,20 @@ static inline void put_slab_obj_exts(unsigned long obj_exts)
 }
 
 #ifdef CONFIG_64BIT
-static inline void slab_set_stride(struct slab *slab, unsigned short stride)
+static inline void slab_set_stride(struct slab *slab, unsigned int stride)
 {
 	slab->stride = stride;
 }
-static inline unsigned short slab_get_stride(struct slab *slab)
+static inline unsigned int slab_get_stride(struct slab *slab)
 {
 	return slab->stride;
 }
 #else
-static inline void slab_set_stride(struct slab *slab, unsigned short stride)
+static inline void slab_set_stride(struct slab *slab, unsigned int stride)
 {
 	VM_WARN_ON_ONCE(stride != sizeof(struct slabobj_ext));
 }
-static inline unsigned short slab_get_stride(struct slab *slab)
+static inline unsigned int slab_get_stride(struct slab *slab)
 {
 	return sizeof(struct slabobj_ext);
 }
-- 
cgit v1.2.3


From 0fb59eaca18f1254ecdce34354eec3cb1b3b5e10 Mon Sep 17 00:00:00 2001
From: Shawn Lin <shawn.lin@rock-chips.com>
Date: Wed, 25 Feb 2026 10:55:01 +0800
Subject: pmdomain: rockchip: Fix PD_VCODEC for RK3588

>From the RK3588 TRM Table 7-1 RK3588 Voltage Domain and Power Domain Summary,
PD_RKVDEC0/1 and PD_VENC0/1 rely on VD_VCODEC which require extra voltages to
be applied, otherwise it breaks RK3588-evb1-v10 board after vdec support landed[1].
The panic looks like below:

  rockchip-pm-domain fd8d8000.power-management:power-controller: failed to set domain 'rkvdec0' on, val=0
  rockchip-pm-domain fd8d8000.power-management:power-controller: failed to set domain 'rkvdec1' on, val=0
  ...
  Hardware name: Rockchip RK3588S EVB1 V10 Board (DT)
  Workqueue: pm genpd_power_off_work_fn
  Call trace:
  show_stack+0x18/0x24 (C)
  dump_stack_lvl+0x40/0x84
  dump_stack+0x18/0x24
  vpanic+0x1ec/0x4fc
  vpanic+0x0/0x4fc
  check_panic_on_warn+0x0/0x94
  arm64_serror_panic+0x6c/0x78
  do_serror+0xc4/0xcc
  el1h_64_error_handler+0x3c/0x5c
  el1h_64_error+0x6c/0x70
  regmap_mmio_read32le+0x18/0x24 (P)
  regmap_bus_reg_read+0xfc/0x130
  regmap_read+0x188/0x1ac
  regmap_read+0x54/0x78
  rockchip_pd_power+0xcc/0x5f0
  rockchip_pd_power_off+0x1c/0x4c
  genpd_power_off+0x84/0x120
  genpd_power_off+0x1b4/0x260
  genpd_power_off_work_fn+0x38/0x58
  process_scheduled_works+0x194/0x2c4
  worker_thread+0x2ac/0x3d8
  kthread+0x104/0x124
  ret_from_fork+0x10/0x20
  SMP: stopping secondary CPUs
  Kernel Offset: disabled
  CPU features: 0x3000000,000e0005,40230521,0400720b
  Memory Limit: none
  ---[ end Kernel panic - not syncing: Asynchronous SError Interrupt ]---

Chaoyi pointed out the PD_VCODEC is the parent of PD_RKVDEC0/1 and PD_VENC0/1, so checking
the PD_VCODEC is enough.

[1] https://lore.kernel.org/linux-rockchip/20251020212009.8852-2-detlev.casanova@collabora.com/

Fixes: db6df2e3fc16 ("pmdomain: rockchip: add regulator support")
Cc: stable@vger.kernel.org
Suggested-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Signed-off-by: Shawn Lin <shawn.lin@rock-chips.com>
Reviewed-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/rockchip/pm-domains.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pmdomain/rockchip/pm-domains.c b/drivers/pmdomain/rockchip/pm-domains.c
index 997e93c12951..44d34840ede7 100644
--- a/drivers/pmdomain/rockchip/pm-domains.c
+++ b/drivers/pmdomain/rockchip/pm-domains.c
@@ -1311,7 +1311,7 @@ static const struct rockchip_domain_info rk3576_pm_domains[] = {
 static const struct rockchip_domain_info rk3588_pm_domains[] = {
 	[RK3588_PD_GPU]		= DOMAIN_RK3588("gpu",     0x0, BIT(0),  0,       0x0, 0,       BIT(1),  0x0, BIT(0),  BIT(0),  false, true),
 	[RK3588_PD_NPU]		= DOMAIN_RK3588("npu",     0x0, BIT(1),  BIT(1),  0x0, 0,       0,       0x0, 0,       0,       false, true),
-	[RK3588_PD_VCODEC]	= DOMAIN_RK3588("vcodec",  0x0, BIT(2),  BIT(2),  0x0, 0,       0,       0x0, 0,       0,       false, false),
+	[RK3588_PD_VCODEC]	= DOMAIN_RK3588("vcodec",  0x0, BIT(2),  BIT(2),  0x0, 0,       0,       0x0, 0,       0,       false, true),
 	[RK3588_PD_NPUTOP]	= DOMAIN_RK3588("nputop",  0x0, BIT(3),  0,       0x0, BIT(11), BIT(2),  0x0, BIT(1),  BIT(1),  false, false),
 	[RK3588_PD_NPU1]	= DOMAIN_RK3588("npu1",    0x0, BIT(4),  0,       0x0, BIT(12), BIT(3),  0x0, BIT(2),  BIT(2),  false, false),
 	[RK3588_PD_NPU2]	= DOMAIN_RK3588("npu2",    0x0, BIT(5),  0,       0x0, BIT(13), BIT(4),  0x0, BIT(3),  BIT(3),  false, false),
-- 
cgit v1.2.3


From 3d1973a0c76a78a4728cff13648a188ed486cf44 Mon Sep 17 00:00:00 2001
From: Jan Stancek <jstancek@redhat.com>
Date: Wed, 25 Feb 2026 20:30:23 +0100
Subject: x86/boot: Handle relative CONFIG_EFI_SBAT_FILE file paths

CONFIG_EFI_SBAT_FILE can be a relative path. When compiling using a different
output directory (O=) the build currently fails because it can't find the
filename set in CONFIG_EFI_SBAT_FILE:

  arch/x86/boot/compressed/sbat.S: Assembler messages:
  arch/x86/boot/compressed/sbat.S:6: Error: file not found: kernel.sbat

Add $(srctree) as include dir for sbat.o.

  [ bp: Massage commit message. ]

Fixes: 61b57d35396a ("x86/efi: Implement support for embedding SBAT data for x86")
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/f4eda155b0cef91d4d316b4e92f5771cb0aa7187.1772047658.git.jstancek@redhat.com
---
 arch/x86/boot/compressed/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 68f9d7a1683b..b8b2b7bea1d3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -113,6 +113,7 @@ vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o
 
 ifdef CONFIG_EFI_SBAT
 $(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE)
+AFLAGS_sbat.o += -I $(srctree)
 endif
 
 $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
-- 
cgit v1.2.3


From fbb143e4a6efa4a175e856fc898754b06cb13c4f Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 4 Mar 2026 07:19:55 +0000
Subject: ASoC: dt-bindings: renesas,rz-ssi: Document RZ/G3L SoC

Document RZ/G3L SSIF-2 bindings. The RZ/G3L SSIF-2 IP is identical to one
found on the RZ/G2L SoC.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20260304072000.6787-1-biju.das.jz@bp.renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
index e4cdbf2202b9..1394f78281fc 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
+++ b/Documentation/devicetree/bindings/sound/renesas,rz-ssi.yaml
@@ -20,6 +20,7 @@ properties:
           - renesas,r9a07g044-ssi  # RZ/G2{L,LC}
           - renesas,r9a07g054-ssi  # RZ/V2L
           - renesas,r9a08g045-ssi  # RZ/G3S
+          - renesas,r9a08g046-ssi  # RZ/G3L
       - const: renesas,rz-ssi
 
   reg:
-- 
cgit v1.2.3


From 325291b20f8a6f14b9c82edbf5d12e4e71f6adaa Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Wed, 4 Mar 2026 14:32:55 +0800
Subject: ASoC: amd: yc: Add DMI quirk for ASUS EXPERTBOOK PM1503CDA

Add a DMI quirk for the ASUS EXPERTBOOK PM1503CDA fixing the
issue where the internal microphone was not detected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221070
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260304063255.139331-1-zhangheng@kylinos.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 7af4daeb4c6f..1324543b42d7 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -710,6 +710,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"),
+		}
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From cfc69c2e6c699c96949f7b0455195b0bfb7dc715 Mon Sep 17 00:00:00 2001
From: Charles Haithcock <chaithco@redhat.com>
Date: Fri, 27 Feb 2026 18:41:15 -0700
Subject: i2c: i801: Revert "i2c: i801: replace acpi_lock with I2C bus lock"

This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1.

Under rare circumstances, multiple udev threads can collect i801 device
info on boot and walk i801_acpi_io_handler somewhat concurrently. The
first will note the area is reserved by acpi to prevent further touches.
This ultimately causes the area to be deregistered. The second will
enter i801_acpi_io_handler after the area is unregistered but before a
check can be made that the area is unregistered. i2c_lock_bus relies on
the now unregistered area containing lock_ops to lock the bus. The end
result is a kernel panic on boot with the following backtrace;

[   14.971872] ioatdma 0000:09:00.2: enabling device (0100 -> 0102)
[   14.971873] BUG: kernel NULL pointer dereference, address: 0000000000000000
[   14.971880] #PF: supervisor read access in kernel mode
[   14.971884] #PF: error_code(0x0000) - not-present page
[   14.971887] PGD 0 P4D 0
[   14.971894] Oops: 0000 [#1] PREEMPT SMP PTI
[   14.971900] CPU: 5 PID: 956 Comm: systemd-udevd Not tainted 5.14.0-611.5.1.el9_7.x86_64 #1
[   14.971905] Hardware name: XXXXXXXXXXXXXXXXXXXXXXX BIOS 1.20.10.SV91 01/30/2023
[   14.971908] RIP: 0010:i801_acpi_io_handler+0x2d/0xb0 [i2c_i801]
[   14.971929] Code: 00 00 49 8b 40 20 41 57 41 56 4d 8b b8 30 04 00 00 49 89 ce 41 55 41 89 d5 41 54 49 89 f4 be 02 00 00 00 55 4c 89 c5 53 89 fb <48> 8b 00 4c 89 c7 e8 18 61 54 e9 80 bd 80 04 00 00 00 75 09 4c 3b
[   14.971933] RSP: 0018:ffffbaa841483838 EFLAGS: 00010282
[   14.971938] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9685e01ba568
[   14.971941] RDX: 0000000000000008 RSI: 0000000000000002 RDI: 0000000000000000
[   14.971944] RBP: ffff9685ca22f028 R08: ffff9685ca22f028 R09: ffff9685ca22f028
[   14.971948] R10: 000000000000000b R11: 0000000000000580 R12: 0000000000000580
[   14.971951] R13: 0000000000000008 R14: ffff9685e01ba568 R15: ffff9685c222f000
[   14.971954] FS:  00007f8287c0ab40(0000) GS:ffff96a47f940000(0000) knlGS:0000000000000000
[   14.971959] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   14.971963] CR2: 0000000000000000 CR3: 0000000168090001 CR4: 00000000003706f0
[   14.971966] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   14.971968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   14.971972] Call Trace:
[   14.971977]  <TASK>
[   14.971981]  ? show_trace_log_lvl+0x1c4/0x2df
[   14.971994]  ? show_trace_log_lvl+0x1c4/0x2df
[   14.972003]  ? acpi_ev_address_space_dispatch+0x16e/0x3c0
[   14.972014]  ? __die_body.cold+0x8/0xd
[   14.972021]  ? page_fault_oops+0x132/0x170
[   14.972028]  ? exc_page_fault+0x61/0x150
[   14.972036]  ? asm_exc_page_fault+0x22/0x30
[   14.972045]  ? i801_acpi_io_handler+0x2d/0xb0 [i2c_i801]
[   14.972061]  acpi_ev_address_space_dispatch+0x16e/0x3c0
[   14.972069]  ? __pfx_i801_acpi_io_handler+0x10/0x10 [i2c_i801]
[   14.972085]  acpi_ex_access_region+0x5b/0xd0
[   14.972093]  acpi_ex_field_datum_io+0x73/0x2e0
[   14.972100]  acpi_ex_read_data_from_field+0x8e/0x230
[   14.972106]  acpi_ex_resolve_node_to_value+0x23d/0x310
[   14.972114]  acpi_ds_evaluate_name_path+0xad/0x110
[   14.972121]  acpi_ds_exec_end_op+0x321/0x510
[   14.972127]  acpi_ps_parse_loop+0xf7/0x680
[   14.972136]  acpi_ps_parse_aml+0x17a/0x3d0
[   14.972143]  acpi_ps_execute_method+0x137/0x270
[   14.972150]  acpi_ns_evaluate+0x1f4/0x2e0
[   14.972158]  acpi_evaluate_object+0x134/0x2f0
[   14.972164]  acpi_evaluate_integer+0x50/0xe0
[   14.972173]  ? vsnprintf+0x24b/0x570
[   14.972181]  acpi_ac_get_state.part.0+0x23/0x70
[   14.972189]  get_ac_property+0x4e/0x60
[   14.972195]  power_supply_show_property+0x90/0x1f0
[   14.972205]  add_prop_uevent+0x29/0x90
[   14.972213]  power_supply_uevent+0x109/0x1d0
[   14.972222]  dev_uevent+0x10e/0x2f0
[   14.972228]  uevent_show+0x8e/0x100
[   14.972236]  dev_attr_show+0x19/0x40
[   14.972246]  sysfs_kf_seq_show+0x9b/0x100
[   14.972253]  seq_read_iter+0x120/0x4b0
[   14.972262]  ? selinux_file_permission+0x106/0x150
[   14.972273]  vfs_read+0x24f/0x3a0
[   14.972284]  ksys_read+0x5f/0xe0
[   14.972291]  do_syscall_64+0x5f/0xe0
...

The kernel panic is mitigated by setting limiting the count of udev
children to 1. Revert to using the acpi_lock to continue protecting
marking the area as owned by firmware without relying on a lock in
a potentially unmapped region of memory.

Fixes: f707d6b9e7c1 ("i2c: i801: replace acpi_lock with I2C bus lock")
Signed-off-by: Charles Haithcock <chaithco@redhat.com>
[wsa: added Fixes-tag and updated comment stating the importance of the lock]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-i801.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 9e1789725edf..32a3cef02c7b 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -310,9 +310,10 @@ struct i801_priv {
 
 	/*
 	 * If set to true the host controller registers are reserved for
-	 * ACPI AML use.
+	 * ACPI AML use. Needs extra protection by acpi_lock.
 	 */
 	bool acpi_reserved;
+	struct mutex acpi_lock;
 };
 
 #define FEATURE_SMBUS_PEC	BIT(0)
@@ -894,8 +895,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
 	int hwpec, ret;
 	struct i801_priv *priv = i2c_get_adapdata(adap);
 
-	if (priv->acpi_reserved)
+	mutex_lock(&priv->acpi_lock);
+	if (priv->acpi_reserved) {
+		mutex_unlock(&priv->acpi_lock);
 		return -EBUSY;
+	}
 
 	pm_runtime_get_sync(&priv->pci_dev->dev);
 
@@ -935,6 +939,7 @@ out:
 	iowrite8(SMBHSTSTS_INUSE_STS | STATUS_FLAGS, SMBHSTSTS(priv));
 
 	pm_runtime_put_autosuspend(&priv->pci_dev->dev);
+	mutex_unlock(&priv->acpi_lock);
 	return ret;
 }
 
@@ -1465,7 +1470,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
 	 * further access from the driver itself. This device is now owned
 	 * by the system firmware.
 	 */
-	i2c_lock_bus(&priv->adapter, I2C_LOCK_SEGMENT);
+	mutex_lock(&priv->acpi_lock);
 
 	if (!priv->acpi_reserved && i801_acpi_is_smbus_ioport(priv, address)) {
 		priv->acpi_reserved = true;
@@ -1485,7 +1490,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
 	else
 		status = acpi_os_write_port(address, (u32)*value, bits);
 
-	i2c_unlock_bus(&priv->adapter, I2C_LOCK_SEGMENT);
+	mutex_unlock(&priv->acpi_lock);
 
 	return status;
 }
@@ -1545,6 +1550,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	priv->adapter.dev.parent = &dev->dev;
 	acpi_use_parent_companion(&priv->adapter.dev);
 	priv->adapter.retries = 3;
+	mutex_init(&priv->acpi_lock);
 
 	priv->pci_dev = dev;
 	priv->features = id->driver_data;
-- 
cgit v1.2.3


From 6932256d3a3764f3a5e06e2cb8603be45b6a9fef Mon Sep 17 00:00:00 2001
From: Gerd Rausch <gerd.rausch@oracle.com>
Date: Wed, 25 Feb 2026 15:37:49 -0800
Subject: time/jiffies: Fix sysctl file error on configurations where USER_HZ <
 HZ

Commit 2dc164a48e6fd ("sysctl: Create converter functions with two new
macros") incorrectly returns error to user space when jiffies sysctl
converter is used. The old overflow check got replaced with an
unconditional one:
     +    if (USER_HZ < HZ)
     +        return -EINVAL;
which will always be true on configurations with "USER_HZ < HZ".

Remove the check; it is no longer needed as clock_t_to_jiffies() returns
ULONG_MAX for the overflow case and proc_int_u2k_conv_uop() checks for
"> INT_MAX" after conversion

Fixes: 2dc164a48e6fd ("sysctl: Create converter functions with two new macros")
Reported-by: Colm Harrington <colm.harrington@oracle.com>
Signed-off-by: Gerd Rausch <gerd.rausch@oracle.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 kernel/time/jiffies.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a5c7d15fce72..9daf8c5d9687 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies);
 int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ)
-		return -EINVAL;
 	return proc_dointvec_conv(table, dir, buffer, lenp, ppos,
 				  do_proc_int_conv_userhz_jiffies);
 }
-- 
cgit v1.2.3


From debc1a492b2695d05973994fb0f796dbd9ceaae6 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 3 Mar 2026 15:34:20 -0800
Subject: iomap: don't mark folio uptodate if read IO has bytes pending

If a folio has ifs metadata attached to it and the folio is partially
read in through an async IO helper with the rest of it then being read
in through post-EOF zeroing or as inline data, and the helper
successfully finishes the read first, then post-EOF zeroing / reading
inline will mark the folio as uptodate in iomap_set_range_uptodate().

This is a problem because when the read completion path later calls
iomap_read_end(), it will call folio_end_read(), which sets the uptodate
bit using XOR semantics. Calling folio_end_read() on a folio that was
already marked uptodate clears the uptodate bit.

Fix this by not marking the folio as uptodate if the read IO has bytes
pending. The folio uptodate state will be set in the read completion
path through iomap_end_read() -> folio_end_read().

Reported-by: Wei Gao <wegao@suse.com>
Suggested-by: Sasha Levin <sashal@kernel.org>
Tested-by: Wei Gao <wegao@suse.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Cc: stable@vger.kernel.org # v6.19
Link: https://lore.kernel.org/linux-fsdevel/aYbmy8JdgXwsGaPP@autotest-wegao.qe.prg2.suse.org/
Fixes: b2f35ac4146d ("iomap: add caller-provided callbacks for read and readahead")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20260303233420.874231-2-joannelkoong@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index bc82083e420a..00f0efaf12b2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -80,18 +80,27 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off,
 {
 	struct iomap_folio_state *ifs = folio->private;
 	unsigned long flags;
-	bool uptodate = true;
+	bool mark_uptodate = true;
 
 	if (folio_test_uptodate(folio))
 		return;
 
 	if (ifs) {
 		spin_lock_irqsave(&ifs->state_lock, flags);
-		uptodate = ifs_set_range_uptodate(folio, ifs, off, len);
+		/*
+		 * If a read with bytes pending is in progress, we must not call
+		 * folio_mark_uptodate(). The read completion path
+		 * (iomap_read_end()) will call folio_end_read(), which uses XOR
+		 * semantics to set the uptodate bit. If we set it here, the XOR
+		 * in folio_end_read() will clear it, leaving the folio not
+		 * uptodate.
+		 */
+		mark_uptodate = ifs_set_range_uptodate(folio, ifs, off, len) &&
+				!ifs->read_bytes_pending;
 		spin_unlock_irqrestore(&ifs->state_lock, flags);
 	}
 
-	if (uptodate)
+	if (mark_uptodate)
 		folio_mark_uptodate(folio);
 }
 
-- 
cgit v1.2.3


From ace7dcc8181373a0338efa1686c5e36eb121dff2 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 25 Feb 2026 09:42:20 +0200
Subject: drm/dp: Add definition for Panel Replay full-line granularity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP specification is saying value 0xff 0xff in PANEL REPLAY SELECTIVE UPDATE
X GRANULARITY CAPABILITY registers (0xb2 and 0xb3) means full-line
granularity. Add definition for this.

Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/20260225074221.1744330-1-jouni.hogander@intel.com
(cherry picked from commit b93311673263bb98a200ab1cb6304f969bdada5c)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 include/drm/display/drm_dp.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h
index e4eebabab975..8b15d3eeb716 100644
--- a/include/drm/display/drm_dp.h
+++ b/include/drm/display/drm_dp.h
@@ -571,6 +571,8 @@
 # define DP_PANEL_REPLAY_LINK_OFF_SUPPORTED_IN_PR_AFTER_ADAPTIVE_SYNC_SDP	(1 << 7)
 
 #define DP_PANEL_REPLAY_CAP_X_GRANULARITY		0xb2
+# define DP_PANEL_REPLAY_FULL_LINE_GRANULARITY		0xffff
+
 #define DP_PANEL_REPLAY_CAP_Y_GRANULARITY		0xb4
 
 /* Link Configuration */
-- 
cgit v1.2.3


From a99cac460ddeb3705cb54a8421339f351586b25d Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 25 Feb 2026 09:42:21 +0200
Subject: drm/i915/psr: Fix for Panel Replay X granularity DPCD register
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP specification is saying value 0xff 0xff in PANEL REPLAY SELECTIVE UPDATE
X GRANULARITY CAPABILITY registers (0xb2 and 0xb3) means full-line
granularity. Take this into account when handling Panel Replay X
granularity informed by the panel.

Fixes: 1cc854647450 ("drm/i915/psr: Use SU granularity information available in intel_connector")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7284
Tested-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patch.msgid.link/20260225074221.1744330-2-jouni.hogander@intel.com
(cherry picked from commit f5c8f824a495e849492f09a43bd965a8f4d86cb2)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 62208ffc5101..4ce1173a2e91 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1307,9 +1307,14 @@ static bool psr2_granularity_check(struct intel_crtc_state *crtc_state,
 	u16 sink_y_granularity = crtc_state->has_panel_replay ?
 		connector->dp.panel_replay_caps.su_y_granularity :
 		connector->dp.psr_caps.su_y_granularity;
-	u16 sink_w_granularity =  crtc_state->has_panel_replay ?
-		connector->dp.panel_replay_caps.su_w_granularity :
-		connector->dp.psr_caps.su_w_granularity;
+	u16 sink_w_granularity;
+
+	if (crtc_state->has_panel_replay)
+		sink_w_granularity = connector->dp.panel_replay_caps.su_w_granularity ==
+			DP_PANEL_REPLAY_FULL_LINE_GRANULARITY ?
+			crtc_hdisplay : connector->dp.panel_replay_caps.su_w_granularity;
+	else
+		sink_w_granularity = connector->dp.psr_caps.su_w_granularity;
 
 	/* PSR2 HW only send full lines so we only need to validate the width */
 	if (crtc_hdisplay % sink_w_granularity)
-- 
cgit v1.2.3


From 531bb98a030cc1073bd7ed9a502c0a3a781e92ee Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 4 Mar 2026 12:37:43 +0000
Subject: io_uring/zcrx: use READ_ONCE with user shared RQEs

Refill queue entries are shared with the user space, use READ_ONCE when
reading them.

Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider");
Cc: stable@vger.kernel.org
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 19b287d21f4b..0461edebb042 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -927,11 +927,12 @@ static inline bool io_parse_rqe(struct io_uring_zcrx_rqe *rqe,
 				struct io_zcrx_ifq *ifq,
 				struct net_iov **ret_niov)
 {
+	__u64 off = READ_ONCE(rqe->off);
 	unsigned niov_idx, area_idx;
 	struct io_zcrx_area *area;
 
-	area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT;
-	niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift;
+	area_idx = off >> IORING_ZCRX_AREA_SHIFT;
+	niov_idx = (off & ~IORING_ZCRX_AREA_MASK) >> ifq->niov_shift;
 
 	if (unlikely(rqe->__pad || area_idx))
 		return false;
-- 
cgit v1.2.3


From d320f160aa5ff36cdf83c645cca52b615e866e32 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 2 Mar 2026 09:30:02 -0800
Subject: iomap: reject delalloc mappings during writeback

Filesystems should never provide a delayed allocation mapping to
writeback; they're supposed to allocate the space before replying.
This can lead to weird IO errors and crashes in the block layer if the
filesystem is being malicious, or if it hadn't set iomap->dev because
it's a delalloc mapping.

Fix this by failing writeback on delalloc mappings.  Currently no
filesystems actually misbehave in this manner, but we ought to be
stricter about things like that.

Cc: stable@vger.kernel.org # v5.5
Fixes: 598ecfbaa742ac ("iomap: lift the xfs writeback code to iomap")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/20260302173002.GL13829@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/ioend.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
index 4d1ef8a2cee9..60546fa14dfe 100644
--- a/fs/iomap/ioend.c
+++ b/fs/iomap/ioend.c
@@ -215,17 +215,18 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 	WARN_ON_ONCE(!folio->private && map_len < dirty_len);
 
 	switch (wpc->iomap.type) {
-	case IOMAP_INLINE:
-		WARN_ON_ONCE(1);
-		return -EIO;
+	case IOMAP_UNWRITTEN:
+		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
+		break;
+	case IOMAP_MAPPED:
+		break;
 	case IOMAP_HOLE:
 		return map_len;
 	default:
-		break;
+		WARN_ON_ONCE(1);
+		return -EIO;
 	}
 
-	if (wpc->iomap.type == IOMAP_UNWRITTEN)
-		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
 	if (wpc->iomap.flags & IOMAP_F_SHARED)
 		ioend_flags |= IOMAP_IOEND_SHARED;
 	if (folio_test_dropbehind(folio))
-- 
cgit v1.2.3


From a99d34e5ecb9a8f2212ee5a01140313bb115f9be Mon Sep 17 00:00:00 2001
From: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Date: Wed, 11 Feb 2026 11:41:59 +0100
Subject: Revert "drm/pagemap: Disable device-to-device migration"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With commit
a69d1ab971a6 ("mm: Fix a hmm_range_fault() livelock / starvation problem")
device-to-device migration is not functional again and the
disabling can be reverted.

Add the above commit as a Fixes: tag in order for the revert to not
take place unless that commit is present.

This reverts commit 10dd1eaa80a56d3cf6d7c36b5269c8fed617f001.

Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: b570f37a2ce4 ("mm: Fix a hmm_range_fault() livelock / starvation problem")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260211104159.114947-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 1a3c0049b3f56278c9caf2784c53f6ab435fd12c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Rodrigo updated Fixes tag]
---
 drivers/gpu/drm/drm_pagemap.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index bdc79140875c..862675ac5bb2 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -480,18 +480,8 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 		.start		= start,
 		.end		= end,
 		.pgmap_owner	= pagemap->owner,
-		/*
-		 * FIXME: MIGRATE_VMA_SELECT_DEVICE_PRIVATE intermittently
-		 * causes 'xe_exec_system_allocator --r *race*no*' to trigger aa
-		 * engine reset and a hard hang due to getting stuck on a folio
-		 * lock. This should work and needs to be root-caused. The only
-		 * downside of not selecting MIGRATE_VMA_SELECT_DEVICE_PRIVATE
-		 * is that device-to-device migrations won’t work; instead,
-		 * memory will bounce through system memory. This path should be
-		 * rare and only occur when the madvise attributes of memory are
-		 * changed or atomics are being used.
-		 */
-		.flags		= MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT,
+		.flags		= MIGRATE_VMA_SELECT_SYSTEM | MIGRATE_VMA_SELECT_DEVICE_COHERENT |
+		MIGRATE_VMA_SELECT_DEVICE_PRIVATE,
 	};
 	unsigned long i, npages = npages_in_range(start, end);
 	unsigned long own_pages = 0, migrated_pages = 0;
-- 
cgit v1.2.3


From b3368ecca9538b88ddf982ea99064860fd5add97 Mon Sep 17 00:00:00 2001
From: Zhanjun Dong <zhanjun.dong@intel.com>
Date: Fri, 20 Feb 2026 17:53:08 -0500
Subject: drm/xe/gsc: Fix GSC proxy cleanup on early initialization failure

xe_gsc_proxy_remove undoes what is done in both xe_gsc_proxy_init and
xe_gsc_proxy_start; however, if we fail between those 2 calls, it is
possible that the HW forcewake access hasn't been initialized yet and so
we hit errors when the cleanup code tries to write GSC register. To
avoid that, split the cleanup in 2 functions so that the HW cleanup is
only called if the HW setup was completed successfully.

Since the HW cleanup (interrupt disabling) is now removed from
xe_gsc_proxy_remove, the cleanup on error paths in xe_gsc_proxy_start
must be updated to disable interrupts before returning.

Fixes: ff6cd29b690b ("drm/xe: Cleanup unwind of gt initialization")
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patch.msgid.link/20260220225308.101469-1-zhanjun.dong@intel.com
(cherry picked from commit 2b37c401b265c07b46408b5cb36a4b757c9b5060)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gsc_proxy.c | 43 +++++++++++++++++++++++++++++++--------
 drivers/gpu/drm/xe/xe_gsc_types.h |  2 ++
 2 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c
index 42438b21f235..707db650a2ae 100644
--- a/drivers/gpu/drm/xe/xe_gsc_proxy.c
+++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c
@@ -435,15 +435,11 @@ static int proxy_channel_alloc(struct xe_gsc *gsc)
 	return 0;
 }
 
-static void xe_gsc_proxy_remove(void *arg)
+static void xe_gsc_proxy_stop(struct xe_gsc *gsc)
 {
-	struct xe_gsc *gsc = arg;
 	struct xe_gt *gt = gsc_to_gt(gsc);
 	struct xe_device *xe = gt_to_xe(gt);
 
-	if (!gsc->proxy.component_added)
-		return;
-
 	/* disable HECI2 IRQs */
 	scoped_guard(xe_pm_runtime, xe) {
 		CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FW_GSC);
@@ -455,6 +451,30 @@ static void xe_gsc_proxy_remove(void *arg)
 	}
 
 	xe_gsc_wait_for_worker_completion(gsc);
+	gsc->proxy.started = false;
+}
+
+static void xe_gsc_proxy_remove(void *arg)
+{
+	struct xe_gsc *gsc = arg;
+	struct xe_gt *gt = gsc_to_gt(gsc);
+	struct xe_device *xe = gt_to_xe(gt);
+
+	if (!gsc->proxy.component_added)
+		return;
+
+	/*
+	 * GSC proxy start is an async process that can be ongoing during
+	 * Xe module load/unload. Using devm managed action to register
+	 * xe_gsc_proxy_stop could cause issues if Xe module unload has
+	 * already started when the action is registered, potentially leading
+	 * to the cleanup being called at the wrong time. Therefore, instead
+	 * of registering a separate devm action to undo what is done in
+	 * proxy start, we call it from here, but only if the start has
+	 * completed successfully (tracked with the 'started' flag).
+	 */
+	if (gsc->proxy.started)
+		xe_gsc_proxy_stop(gsc);
 
 	component_del(xe->drm.dev, &xe_gsc_proxy_component_ops);
 	gsc->proxy.component_added = false;
@@ -510,6 +530,7 @@ int xe_gsc_proxy_init(struct xe_gsc *gsc)
  */
 int xe_gsc_proxy_start(struct xe_gsc *gsc)
 {
+	struct xe_gt *gt = gsc_to_gt(gsc);
 	int err;
 
 	/* enable the proxy interrupt in the GSC shim layer */
@@ -521,12 +542,18 @@ int xe_gsc_proxy_start(struct xe_gsc *gsc)
 	 */
 	err = xe_gsc_proxy_request_handler(gsc);
 	if (err)
-		return err;
+		goto err_irq_disable;
 
 	if (!xe_gsc_proxy_init_done(gsc)) {
-		xe_gt_err(gsc_to_gt(gsc), "GSC FW reports proxy init not completed\n");
-		return -EIO;
+		xe_gt_err(gt, "GSC FW reports proxy init not completed\n");
+		err = -EIO;
+		goto err_irq_disable;
 	}
 
+	gsc->proxy.started = true;
 	return 0;
+
+err_irq_disable:
+	gsc_proxy_irq_toggle(gsc, false);
+	return err;
 }
diff --git a/drivers/gpu/drm/xe/xe_gsc_types.h b/drivers/gpu/drm/xe/xe_gsc_types.h
index 97c056656df0..5aaa2a75861f 100644
--- a/drivers/gpu/drm/xe/xe_gsc_types.h
+++ b/drivers/gpu/drm/xe/xe_gsc_types.h
@@ -58,6 +58,8 @@ struct xe_gsc {
 		struct mutex mutex;
 		/** @proxy.component_added: whether the component has been added */
 		bool component_added;
+		/** @proxy.started: whether the proxy has been started */
+		bool started;
 		/** @proxy.bo: object to store message to and from the GSC */
 		struct xe_bo *bo;
 		/** @proxy.to_gsc: map of the memory used to send messages to the GSC */
-- 
cgit v1.2.3


From 89865e6dc8487b627302bdced3f965cd0c406835 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Fri, 27 Feb 2026 08:43:41 -0800
Subject: drm/xe/xe2_hpg: Correct implementation of Wa_16025250150

Wa_16025250150 asks us to set five register fields of the register to
0x1 each.  However we were just OR'ing this into the existing register
value (which has a default of 0x4 for each nibble-sized field) resulting
in final field values of 0x5 instead of the desired 0x1.  Correct the
RTP programming (use FIELD_SET instead of SET) to ensure each field is
assigned to exactly the value we want.

Cc: Aradhya Bhatia <aradhya.bhatia@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Cc: stable@vger.kernel.org # v6.16+
Fixes: 7654d51f1fd8 ("drm/xe/xe2hpg: Add Wa_16025250150")
Reviewed-by: Ngai-Mint Kwan <ngai-mint.kwan@linux.intel.com>
Link: https://patch.msgid.link/20260227164341.3600098-2-matthew.d.roper@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit d139209ef88e48af1f6731cd45440421c757b6b5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index c7b1bd79ab17..462c2fa712e0 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -241,12 +241,13 @@ static const struct xe_rtp_entry_sr gt_was[] = {
 
 	{ XE_RTP_NAME("16025250150"),
 	  XE_RTP_RULES(GRAPHICS_VERSION(2001)),
-	  XE_RTP_ACTIONS(SET(LSN_VC_REG2,
-			     LSN_LNI_WGT(1) |
-			     LSN_LNE_WGT(1) |
-			     LSN_DIM_X_WGT(1) |
-			     LSN_DIM_Y_WGT(1) |
-			     LSN_DIM_Z_WGT(1)))
+	  XE_RTP_ACTIONS(FIELD_SET(LSN_VC_REG2,
+				   LSN_LNI_WGT_MASK | LSN_LNE_WGT_MASK |
+				   LSN_DIM_X_WGT_MASK | LSN_DIM_Y_WGT_MASK |
+				   LSN_DIM_Z_WGT_MASK,
+				   LSN_LNI_WGT(1) | LSN_LNE_WGT(1) |
+				   LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) |
+				   LSN_DIM_Z_WGT(1)))
 	},
 
 	/* Xe2_HPM */
-- 
cgit v1.2.3


From 3091723785def05ebfe6a50866f87a044ae314ba Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Wed, 4 Feb 2026 17:28:11 +0000
Subject: drm/xe/reg_sr: Fix leak on xa_store failure

Free the newly allocated entry when xa_store() fails to avoid a memory
leak on the error path.

v2: use goto fail_free. (Bala)

Fixes: e5283bd4dfec ("drm/xe/reg_sr: Remove register pool")
Cc: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patch.msgid.link/20260204172810.1486719-2-shuicheng.lin@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 6bc6fec71ac45f52db609af4e62bdb96b9f5fadb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_reg_sr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c
index 2e5c78940b41..a07be161cfa2 100644
--- a/drivers/gpu/drm/xe/xe_reg_sr.c
+++ b/drivers/gpu/drm/xe/xe_reg_sr.c
@@ -98,10 +98,12 @@ int xe_reg_sr_add(struct xe_reg_sr *sr,
 	*pentry = *e;
 	ret = xa_err(xa_store(&sr->xa, idx, pentry, GFP_KERNEL));
 	if (ret)
-		goto fail;
+		goto fail_free;
 
 	return 0;
 
+fail_free:
+	kfree(pentry);
 fail:
 	xe_gt_err(gt,
 		  "discarding save-restore reg %04lx (clear: %08x, set: %08x, masked: %s, mcr: %s): ret=%d\n",
-- 
cgit v1.2.3


From 0cfe9c4838f1147713f6b5c02094cd4dc0c598fa Mon Sep 17 00:00:00 2001
From: Varun Gupta <varun.gupta@intel.com>
Date: Mon, 23 Feb 2026 23:21:45 +0530
Subject: drm/xe: Fix memory leak in xe_vm_madvise_ioctl

When check_bo_args_are_sane() validation fails, jump to the new
free_vmas cleanup label to properly free the allocated resources.
This ensures proper cleanup in this error path.

Fixes: 293032eec4ba ("drm/xe/bo: Update atomic_access attribute on madvise")
Cc: stable@vger.kernel.org # v6.18+
Reviewed-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Varun Gupta <varun.gupta@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260223175145.1532801-1-varun.gupta@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
(cherry picked from commit 29bd06faf727a4b76663e4be0f7d770e2d2a7965)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 95bf53cc29e3..bc39a9a9790c 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -453,7 +453,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 						    madvise_range.num_vmas,
 						    args->atomic.val)) {
 				err = -EINVAL;
-				goto madv_fini;
+				goto free_vmas;
 			}
 		}
 
@@ -490,6 +490,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 err_fini:
 	if (madvise_range.has_bo_vmas)
 		drm_exec_fini(&exec);
+free_vmas:
 	kfree(madvise_range.vmas);
 	madvise_range.vmas = NULL;
 madv_fini:
-- 
cgit v1.2.3


From 8da8df43124128e0478beadb58faa9cab56a3f13 Mon Sep 17 00:00:00 2001
From: Yang Xiuwei <yangxiuwei@kylinos.cn>
Date: Wed, 4 Mar 2026 12:51:19 +0800
Subject: block: use __bio_add_page in bio_copy_kern

Since the bio is allocated with the exact number of pages needed via
blk_rq_map_bio_alloc(), and the loop iterates exactly that many times,
bio_add_page() cannot fail due to insufficient space.  Switch to
__bio_add_page() and remove the dead error handling code.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Yang Xiuwei <yangxiuwei@kylinos.cn>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/blk-map.c b/block/blk-map.c
index 4533094d9458..c6fa2238d578 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -398,8 +398,7 @@ static struct bio *bio_copy_kern(struct request *rq, void *data, unsigned int le
 		if (op_is_write(op))
 			memcpy(page_address(page), p, bytes);
 
-		if (bio_add_page(bio, page, bytes, 0) < bytes)
-			break;
+		__bio_add_page(bio, page, bytes, 0);
 
 		len -= bytes;
 		p += bytes;
-- 
cgit v1.2.3


From cfdf6456c0aca337ff05cb1eb6e6f453e1d9dea1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Feb 2026 09:08:14 -0300
Subject: tools headers: Sync uapi/linux/prctl.h with the kernel source

To pick up the changes in these csets:

  5ca243f6e3c30b97 ("prctl: add arch-agnostic prctl()s for indirect branch tracking")
  28621ec2d46c6adf ("rseq: Add prctl() to enable time slice extensions")

That don't introduced these new prctls:

  $ tools/perf/trace/beauty/prctl_option.sh > before.txt
  $ cp include/uapi/linux/prctl.h tools/perf/trace/beauty/include/uapi/linux/prctl.h
  $ tools/perf/trace/beauty/prctl_option.sh > after.txt
  $ diff -u before.txt after.txt
  --- before.txt	2026-02-27 09:07:16.435611457 -0300
  +++ after.txt	2026-02-27 09:07:28.189816531 -0300
  @@ -73,6 +73,10 @@
   	[76] = "LOCK_SHADOW_STACK_STATUS",
   	[77] = "TIMER_CREATE_RESTORE_IDS",
   	[78] = "FUTEX_HASH",
  +	[79] = "RSEQ_SLICE_EXTENSION",
  +	[80] = "GET_INDIR_BR_LP_STATUS",
  +	[81] = "SET_INDIR_BR_LP_STATUS",
  +	[82] = "LOCK_INDIR_BR_LP_STATUS",
   };
   static const char *prctl_set_mm_options[] = {
   	[1] = "START_CODE",
  $

That now will be used to decode the syscall option and also to compose
filters, for instance:

  [root@five ~]# perf trace -e syscalls:sys_enter_prctl --filter option==SET_NAME
       0.000 Isolated Servi/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23f13b7aee)
       0.032 DOM Worker/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23deb25670)
       7.920 :3474328/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fbb10)
       7.935 StreamT~s #374/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fb970)
       8.400 Isolated Servi/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24bab10)
       8.418 StreamT~s #374/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24ba970)
  ^C[root@five ~]#

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/prctl.h include/uapi/linux/prctl.h

Please see tools/include/uapi/README for further details.

Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 37 ++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 51c4e8c82b1e..55b0446fff9d 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -386,4 +386,41 @@ struct prctl_mm_map {
 # define PR_FUTEX_HASH_SET_SLOTS	1
 # define PR_FUTEX_HASH_GET_SLOTS	2
 
+/* RSEQ time slice extensions */
+#define PR_RSEQ_SLICE_EXTENSION			79
+# define PR_RSEQ_SLICE_EXTENSION_GET		1
+# define PR_RSEQ_SLICE_EXTENSION_SET		2
+/*
+ * Bits for RSEQ_SLICE_EXTENSION_GET/SET
+ * PR_RSEQ_SLICE_EXT_ENABLE:	Enable
+ */
+# define PR_RSEQ_SLICE_EXT_ENABLE		0x01
+
+/*
+ * Get the current indirect branch tracking configuration for the current
+ * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS.
+ */
+#define PR_GET_INDIR_BR_LP_STATUS      80
+
+/*
+ * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will
+ * enable cpu feature for user thread, to track all indirect branches and ensure
+ * they land on arch defined landing pad instruction.
+ * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction.
+ * arch64 - If enabled, an indirect branch must land on a BTI instruction.
+ * riscv - If enabled, an indirect branch must land on an lpad instruction.
+ * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect
+ * branches will no more be tracked by cpu to land on arch defined landing pad
+ * instruction.
+ */
+#define PR_SET_INDIR_BR_LP_STATUS      81
+# define PR_INDIR_BR_LP_ENABLE		   (1UL << 0)
+
+/*
+ * Prevent further changes to the specified indirect branch tracking
+ * configuration.  All bits may be locked via this call, including
+ * undefined bits.
+ */
+#define PR_LOCK_INDIR_BR_LP_STATUS      82
+
 #endif /* _LINUX_PRCTL_H */
-- 
cgit v1.2.3


From f079ff37324accb91c6247b59e249ebc22bf55f5 Mon Sep 17 00:00:00 2001
From: Changqing Li <changqing.li@windriver.com>
Date: Mon, 28 Jul 2025 17:31:53 +0800
Subject: tools build: Make in-target rule robust against too long argument
 error

The command length of in-target scales with the depth of the directory
times the number of objects in the Makefile.

When there are many objects, and O=[absolute_path] is set, and the
absolute_path is relatively long.

It is possible that this line "$(call if_changed,$(host)ld_multi)" will
report error: "make[4]: /bin/sh: Argument list too long"

For example, build perf tools with O=/long/output/path

Like built-in.a and *.mod rules in scripts/Makefile.build, add
$(objpredix)/ by the shell command instead of by Make's builtin
function.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Changqing Li <changqing.li@windriver.com>
Cc: Charlie Jenkins <charlie@rivosinc.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile.build | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 60e65870eae1..ad69efdd4e85 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -70,11 +70,13 @@ quiet_cmd_gen = GEN     $@
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD      $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
-                     $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
+                     printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                     xargs $(LD) -r -o $@,rm -f $@; $(AR) rcs $@)
 
 quiet_cmd_host_ld_multi = HOSTLD  $@
       cmd_host_ld_multi = $(if $(strip $(obj-y)),\
-                          $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
+                          printf "$(objprefix)%s " $(patsubst $(objprefix)%,%,$(filter $(obj-y),$^)) | \
+                          xargs $(HOSTLD) -r -o $@,rm -f $@; $(HOSTAR) rcs $@)
 
 rust_common_cmd = \
 	$(RUSTC) $(rust_flags) \
-- 
cgit v1.2.3


From b6712d91f8f5a289f642c208083a8f5c27b8ab90 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Tue, 3 Mar 2026 13:15:01 -0800
Subject: perf build: Prevent "argument list too long" error

Due to a recent change, building perf may result in a build error when
it is trying to "prune orphans".

The file list passed to "rm" may exceed what the shell can handle.

The build will then abort with an error like this:

    TEST    [...]/arm64/build/linux-custom/tools/perf/pmu-events/metric_test.log
  make[5]: /bin/sh: Argument list too long
  make[5]: *** [pmu-events/Build:217: prune_orphans] Error 127
  make[5]: *** Waiting for unfinished jobs....
  make[4]: *** [Makefile.perf:773: [...]/tools/perf/pmu-events/pmu-events-in.o] Error 2
  make[4]: *** Waiting for unfinished jobs....
  make[3]: *** [Makefile.perf:289: sub-make] Error 2

Processing the arguments via "xargs", instead of passing the list of
files directly to "rm" via the shell, prevents this issue.

Fixes: 36a1b0061a584430 ("perf build: Reduce pmu-events related copying and mkdirs")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/Build | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 63c65788d442..dc5f94862a3b 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -214,7 +214,8 @@ ifneq ($(strip $(ORPHAN_FILES)),)
 quiet_cmd_rm  = RM      $^
 
 prune_orphans: $(ORPHAN_FILES)
-	$(Q)$(call echo-cmd,rm)rm -f $^
+	# The list of files can be long. Use xargs to prevent issues.
+	$(Q)$(call echo-cmd,rm)echo "$^" | xargs rm -f
 
 JEVENTS_DEPS += prune_orphans
 endif
-- 
cgit v1.2.3


From 212dd8477653fe72c2a6a99143cd662f6430cf4f Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 27 Feb 2026 15:51:42 +0000
Subject: arm64: Silence sparse warnings caused by the type casting in
 (cmp)xchg

The arm64 xchg/cmpxchg() wrappers cast the arguments to (unsigned long)
prior to invoking the static inline functions implementing the
operation. Some restrictive type annotations (e.g. __bitwise) lead to
sparse warnings like below:

sparse warnings: (new ones prefixed by >>)
   fs/crypto/bio.c:67:17: sparse: sparse: cast from restricted blk_status_t
>> fs/crypto/bio.c:67:17: sparse: sparse: cast to restricted blk_status_t

Force the casting in the arm64 xchg/cmpxchg() wrappers to silence
sparse.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602230947.uNRsPyBn-lkp@intel.com/
Link: https://lore.kernel.org/r/202602230947.uNRsPyBn-lkp@intel.com/
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cmpxchg.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index d7a540736741..6cf3cd6873f5 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -91,8 +91,9 @@ __XCHG_GEN(_mb)
 #define __xchg_wrapper(sfx, ptr, x)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret = (__force __typeof__(*(ptr)))				\
+		__arch_xchg##sfx((__force unsigned long)(x), (ptr),	\
+				  sizeof(*(ptr)));			\
 	__ret;								\
 })
 
@@ -175,9 +176,10 @@ __CMPXCHG_GEN(_mb)
 #define __cmpxchg_wrapper(sfx, ptr, o, n)				\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__cmpxchg##sfx((ptr), (unsigned long)(o),		\
-				(unsigned long)(n), sizeof(*(ptr)));	\
+	__ret = (__force __typeof__(*(ptr)))				\
+		__cmpxchg##sfx((ptr), (__force unsigned long)(o),	\
+				(__force unsigned long)(n),		\
+				sizeof(*(ptr)));			\
 	__ret;								\
 })
 
-- 
cgit v1.2.3


From 82169dace41cbaa951341b0f80f4570be3b2dec0 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 18 Feb 2026 10:52:04 +0100
Subject: xenbus: add xenbus_device parameter to xenbus_read_driver_state()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to prepare checking the xenbus device status in
xenbus_read_driver_state(), add the pointer to struct xenbus_device
as a parameter.

Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: "Martin K. Petersen" <martin.petersen@oracle.com> # SCSI
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>	# drivers/pci/xen-pcifront.c
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260218095205.453657-2-jgross@suse.com>
---
 drivers/net/xen-netfront.c                 | 34 +++++++++++++++---------------
 drivers/pci/xen-pcifront.c                 |  8 +++----
 drivers/scsi/xen-scsifront.c               |  2 +-
 drivers/xen/xen-pciback/xenbus.c           | 10 ++++-----
 drivers/xen/xenbus/xenbus_client.c         |  4 +++-
 drivers/xen/xenbus/xenbus_probe.c          |  6 +++---
 drivers/xen/xenbus/xenbus_probe_frontend.c |  2 +-
 include/xen/xenbus.h                       |  3 ++-
 8 files changed, 36 insertions(+), 33 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 7c2220366623..e2da977c9c50 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1646,7 +1646,7 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	/* avoid the race with XDP headroom adjustment */
 	wait_event(module_wq,
-		   xenbus_read_driver_state(np->xbdev->otherend) ==
+		   xenbus_read_driver_state(np->xbdev, np->xbdev->otherend) ==
 		   XenbusStateReconfigured);
 	np->netfront_xdp_enabled = true;
 
@@ -1764,9 +1764,9 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	do {
 		xenbus_switch_state(dev, XenbusStateInitialising);
 		err = wait_event_timeout(module_wq,
-				 xenbus_read_driver_state(dev->otherend) !=
+				 xenbus_read_driver_state(dev, dev->otherend) !=
 				 XenbusStateClosed &&
-				 xenbus_read_driver_state(dev->otherend) !=
+				 xenbus_read_driver_state(dev, dev->otherend) !=
 				 XenbusStateUnknown, XENNET_TIMEOUT);
 	} while (!err);
 
@@ -2627,31 +2627,31 @@ static void xennet_bus_close(struct xenbus_device *dev)
 {
 	int ret;
 
-	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+	if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed)
 		return;
 	do {
 		xenbus_switch_state(dev, XenbusStateClosing);
 		ret = wait_event_timeout(module_wq,
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosing ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosed ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateUnknown,
-				   XENNET_TIMEOUT);
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosing ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosed ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateUnknown,
+				XENNET_TIMEOUT);
 	} while (!ret);
 
-	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+	if (xenbus_read_driver_state(dev, dev->otherend) == XenbusStateClosed)
 		return;
 
 	do {
 		xenbus_switch_state(dev, XenbusStateClosed);
 		ret = wait_event_timeout(module_wq,
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateClosed ||
-				   xenbus_read_driver_state(dev->otherend) ==
-				   XenbusStateUnknown,
-				   XENNET_TIMEOUT);
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateClosed ||
+				xenbus_read_driver_state(dev, dev->otherend) ==
+				XenbusStateUnknown,
+				XENNET_TIMEOUT);
 	} while (!ret);
 }
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 11636634ae51..cd22bf984024 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -856,7 +856,7 @@ static void pcifront_try_connect(struct pcifront_device *pdev)
 	int err;
 
 	/* Only connect once */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitialised)
 		return;
 
@@ -876,7 +876,7 @@ static int pcifront_try_disconnect(struct pcifront_device *pdev)
 	enum xenbus_state prev_state;
 
 
-	prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+	prev_state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename);
 
 	if (prev_state >= XenbusStateClosing)
 		goto out;
@@ -895,7 +895,7 @@ out:
 
 static void pcifront_attach_devices(struct pcifront_device *pdev)
 {
-	if (xenbus_read_driver_state(pdev->xdev->nodename) ==
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) ==
 	    XenbusStateReconfiguring)
 		pcifront_connect(pdev);
 }
@@ -909,7 +909,7 @@ static int pcifront_detach_devices(struct pcifront_device *pdev)
 	struct pci_dev *pci_dev;
 	char str[64];
 
-	state = xenbus_read_driver_state(pdev->xdev->nodename);
+	state = xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename);
 	if (state == XenbusStateInitialised) {
 		dev_dbg(&pdev->xdev->dev, "Handle skipped connect.\n");
 		/* We missed Connected and need to initialize. */
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 924025305753..ef74d4da5ab0 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -1175,7 +1175,7 @@ static void scsifront_backend_changed(struct xenbus_device *dev,
 			return;
 		}
 
-		if (xenbus_read_driver_state(dev->nodename) ==
+		if (xenbus_read_driver_state(dev, dev->nodename) ==
 		    XenbusStateInitialised)
 			scsifront_do_lun_hotplug(info, VSCSIFRONT_OP_ADD_LUN);
 
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index b11e401f1b1e..4bd1c7a8957e 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -149,12 +149,12 @@ static int xen_pcibk_attach(struct xen_pcibk_device *pdev)
 
 	mutex_lock(&pdev->dev_lock);
 	/* Make sure we only do this setup once */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitialised)
 		goto out;
 
 	/* Wait for frontend to state that it has published the configuration */
-	if (xenbus_read_driver_state(pdev->xdev->otherend) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->otherend) !=
 	    XenbusStateInitialised)
 		goto out;
 
@@ -374,7 +374,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev,
 	dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n");
 
 	mutex_lock(&pdev->dev_lock);
-	if (xenbus_read_driver_state(pdev->xdev->nodename) != state)
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) != state)
 		goto out;
 
 	err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d",
@@ -572,7 +572,7 @@ static int xen_pcibk_setup_backend(struct xen_pcibk_device *pdev)
 	/* It's possible we could get the call to setup twice, so make sure
 	 * we're not already connected.
 	 */
-	if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+	if (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename) !=
 	    XenbusStateInitWait)
 		goto out;
 
@@ -662,7 +662,7 @@ static void xen_pcibk_be_watch(struct xenbus_watch *watch,
 	struct xen_pcibk_device *pdev =
 	    container_of(watch, struct xen_pcibk_device, be_watch);
 
-	switch (xenbus_read_driver_state(pdev->xdev->nodename)) {
+	switch (xenbus_read_driver_state(pdev->xdev, pdev->xdev->nodename)) {
 	case XenbusStateInitWait:
 		xen_pcibk_setup_backend(pdev);
 		break;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 2dc874fb5506..e502435145ae 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -931,12 +931,14 @@ static int xenbus_unmap_ring_hvm(struct xenbus_device *dev, void *vaddr)
 
 /**
  * xenbus_read_driver_state - read state from a store path
+ * @dev: xenbus device pointer
  * @path: path for driver
  *
  * Returns: the state of the driver rooted at the given store path, or
  * XenbusStateUnknown if no state can be read.
  */
-enum xenbus_state xenbus_read_driver_state(const char *path)
+enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
+					   const char *path)
 {
 	enum xenbus_state result;
 	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 9f9011cd7447..2eed06ba5d38 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -191,7 +191,7 @@ void xenbus_otherend_changed(struct xenbus_watch *watch,
 		return;
 	}
 
-	state = xenbus_read_driver_state(dev->otherend);
+	state = xenbus_read_driver_state(dev, dev->otherend);
 
 	dev_dbg(&dev->dev, "state is %d, (%s), %s, %s\n",
 		state, xenbus_strstate(state), dev->otherend_watch.node, path);
@@ -364,7 +364,7 @@ void xenbus_dev_remove(struct device *_dev)
 	 * closed.
 	 */
 	if (!drv->allow_rebind ||
-	    xenbus_read_driver_state(dev->nodename) == XenbusStateClosing)
+	    xenbus_read_driver_state(dev, dev->nodename) == XenbusStateClosing)
 		xenbus_switch_state(dev, XenbusStateClosed);
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_remove);
@@ -514,7 +514,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 	size_t stringlen;
 	char *tmpstring;
 
-	enum xenbus_state state = xenbus_read_driver_state(nodename);
+	enum xenbus_state state = xenbus_read_driver_state(NULL, nodename);
 
 	if (state != XenbusStateInitialising) {
 		/* Device is not new, so ignore it.  This can happen if a
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index f04707d1f667..ca04609730df 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -253,7 +253,7 @@ static int print_device_status(struct device *dev, void *data)
 	} else if (xendev->state < XenbusStateConnected) {
 		enum xenbus_state rstate = XenbusStateUnknown;
 		if (xendev->otherend)
-			rstate = xenbus_read_driver_state(xendev->otherend);
+			rstate = xenbus_read_driver_state(xendev, xendev->otherend);
 		pr_warn("Timeout connecting to device: %s (local state %d, remote state %d)\n",
 			xendev->nodename, xendev->state, rstate);
 	}
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index c94caf852aea..15319da65b7f 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -228,7 +228,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr);
 int xenbus_alloc_evtchn(struct xenbus_device *dev, evtchn_port_t *port);
 int xenbus_free_evtchn(struct xenbus_device *dev, evtchn_port_t port);
 
-enum xenbus_state xenbus_read_driver_state(const char *path);
+enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
+					   const char *path);
 
 __printf(3, 4)
 void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...);
-- 
cgit v1.2.3


From e2dcf9065536ab4a1b00828ff0d19f7d282dfecc Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 18 Feb 2026 10:52:05 +0100
Subject: xen/xenbus: better handle backend crash
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the backend domain crashes, coordinated device cleanup is not
possible (as it involves waiting for the backend state change). In that
case, toolstack forcefully removes frontend xenstore entries.
xenbus_dev_changed() handles this case, and triggers device cleanup.
It's possible that toolstack manages to connect new device in that
place, before xenbus_dev_changed() notices the old one is missing. If
that happens, new one won't be probed and will forever remain in
XenbusStateInitialising.

Fix this by checking the frontend's state in Xenstore. In case it has
been reset to XenbusStateInitialising by Xen tools, consider this
being the result of an unplug+plug operation.

It's important that cleanup on such unplug doesn't modify Xenstore
entries (especially the "state" key) as it belong to the new device
to be probed - changing it would derail establishing connection to the
new backend (most likely, closing the device before it was even
connected). Handle this case by setting new xenbus_device->vanished
flag to true, and check it before changing state entry.

And even if xenbus_dev_changed() correctly detects the device was
forcefully removed, the cleanup handling is still racy. Since this whole
handling doesn't happened in a single Xenstore transaction, it's possible
that toolstack might put a new device there already. Avoid re-creating
the state key (which in the case of loosing the race would actually
close newly attached device).

The problem does not apply to frontend domain crash, as this case
involves coordinated cleanup.

Problem originally reported at
https://lore.kernel.org/xen-devel/aOZvivyZ9YhVWDLN@mail-itl/T/#t,
including reproduction steps.

Based-on-patch-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260218095205.453657-3-jgross@suse.com>
---
 drivers/xen/xenbus/xenbus_client.c | 13 +++++++++++--
 drivers/xen/xenbus/xenbus_probe.c  | 36 ++++++++++++++++++++++++++++++++++++
 include/xen/xenbus.h               |  1 +
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index e502435145ae..19672b08a680 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -226,8 +226,9 @@ __xenbus_switch_state(struct xenbus_device *dev,
 	struct xenbus_transaction xbt;
 	int current_state;
 	int err, abort;
+	bool vanished = false;
 
-	if (state == dev->state)
+	if (state == dev->state || dev->vanished)
 		return 0;
 
 again:
@@ -242,6 +243,10 @@ again:
 	err = xenbus_scanf(xbt, dev->nodename, "state", "%d", &current_state);
 	if (err != 1)
 		goto abort;
+	if (current_state != dev->state && current_state == XenbusStateInitialising) {
+		vanished = true;
+		goto abort;
+	}
 
 	err = xenbus_printf(xbt, dev->nodename, "state", "%d", state);
 	if (err) {
@@ -256,7 +261,7 @@ abort:
 		if (err == -EAGAIN && !abort)
 			goto again;
 		xenbus_switch_fatal(dev, depth, err, "ending transaction");
-	} else
+	} else if (!vanished)
 		dev->state = state;
 
 	return 0;
@@ -941,6 +946,10 @@ enum xenbus_state xenbus_read_driver_state(const struct xenbus_device *dev,
 					   const char *path)
 {
 	enum xenbus_state result;
+
+	if (dev && dev->vanished)
+		return XenbusStateUnknown;
+
 	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
 	if (err)
 		result = XenbusStateUnknown;
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 2eed06ba5d38..eb260eceb4d2 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -444,6 +444,9 @@ static void xenbus_cleanup_devices(const char *path, struct bus_type *bus)
 		info.dev = NULL;
 		bus_for_each_dev(bus, NULL, &info, cleanup_dev);
 		if (info.dev) {
+			dev_warn(&info.dev->dev,
+				 "device forcefully removed from xenstore\n");
+			info.dev->vanished = true;
 			device_unregister(&info.dev->dev);
 			put_device(&info.dev->dev);
 		}
@@ -659,6 +662,39 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 		return;
 
 	dev = xenbus_device_find(root, &bus->bus);
+	/*
+	 * Backend domain crash results in not coordinated frontend removal,
+	 * without going through XenbusStateClosing. If this is a new instance
+	 * of the same device Xen tools will have reset the state to
+	 * XenbusStateInitializing.
+	 * It might be that the backend crashed early during the init phase of
+	 * device setup, in which case the known state would have been
+	 * XenbusStateInitializing. So test the backend domid to match the
+	 * saved one. In case the new backend happens to have the same domid as
+	 * the old one, we can just carry on, as there is no inconsistency
+	 * resulting in this case.
+	 */
+	if (dev && !strcmp(bus->root, "device")) {
+		enum xenbus_state state = xenbus_read_driver_state(dev, dev->nodename);
+		unsigned int backend = xenbus_read_unsigned(root, "backend-id",
+							    dev->otherend_id);
+
+		if (state == XenbusStateInitialising &&
+		    (state != dev->state || backend != dev->otherend_id)) {
+			/*
+			 * State has been reset, assume the old one vanished
+			 * and new one needs to be probed.
+			 */
+			dev_warn(&dev->dev,
+				 "state reset occurred, reconnecting\n");
+			dev->vanished = true;
+		}
+		if (dev->vanished) {
+			device_unregister(&dev->dev);
+			put_device(&dev->dev);
+			dev = NULL;
+		}
+	}
 	if (!dev)
 		xenbus_probe_node(bus, type, root);
 	else
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 15319da65b7f..8ca15743af7f 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -80,6 +80,7 @@ struct xenbus_device {
 	const char *devicetype;
 	const char *nodename;
 	const char *otherend;
+	bool vanished;
 	int otherend_id;
 	struct xenbus_watch otherend_watch;
 	struct device dev;
-- 
cgit v1.2.3


From c25c4aa3f79a488cc270507935a29c07dc6bddfc Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 27 Feb 2026 18:53:06 +0000
Subject: arm64: mm: Add PTE_DIRTY back to PAGE_KERNEL* to fix
 kexec/hibernation

Commit 143937ca51cc ("arm64, mm: avoid always making PTE dirty in
pte_mkwrite()") changed pte_mkwrite_novma() to only clear PTE_RDONLY
when PTE_DIRTY is set. This was to allow writable-clean PTEs for swap
pages that haven't actually been written.

However, this broke kexec and hibernation for some platforms. Both go
through trans_pgd_create_copy() -> _copy_pte(), which calls
pte_mkwrite_novma() to make the temporary linear-map copy fully
writable. With the updated pte_mkwrite_novma(), read-only kernel pages
(without PTE_DIRTY) remain read-only in the temporary mapping.
While such behaviour is fine for user pages where hardware DBM or
trapping will make them writeable, subsequent in-kernel writes by the
kexec relocation code will fault.

Add PTE_DIRTY back to all _PAGE_KERNEL* protection definitions. This was
the case prior to 5.4, commit aa57157be69f ("arm64: Ensure
VM_WRITE|VM_SHARED ptes are clean by default"). With the kernel
linear-map PTEs always having PTE_DIRTY set, pte_mkwrite_novma()
correctly clears PTE_RDONLY.

Fixes: 143937ca51cc ("arm64, mm: avoid always making PTE dirty in pte_mkwrite()")
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: stable@vger.kernel.org
Reported-by: Jianpeng Chang <jianpeng.chang.cn@windriver.com>
Link: https://lore.kernel.org/r/20251204062722.3367201-1-jianpeng.chang.cn@windriver.com
Cc: Will Deacon <will@kernel.org>
Cc: Huang, Ying <ying.huang@linux.alibaba.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Huang Ying <ying.huang@linux.alibaba.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable-prot.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2b32639160de..f560e6420267 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -50,11 +50,11 @@
 
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
-#define _PAGE_KERNEL		(PROT_NORMAL)
-#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
-#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
-#define _PAGE_KERNEL_EXEC	(PROT_NORMAL & ~PTE_PXN)
-#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
+#define _PAGE_KERNEL		(PROT_NORMAL | PTE_DIRTY)
+#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC	((PROT_NORMAL & ~PTE_PXN) | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT | PTE_DIRTY)
 
 #define _PAGE_SHARED		(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define _PAGE_SHARED_EXEC	(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
-- 
cgit v1.2.3


From 30f998c992c9d32a5c2774ec1b624339483db19d Mon Sep 17 00:00:00 2001
From: Dmitrii Dolgov <9erthalion6@gmail.com>
Date: Thu, 26 Feb 2026 17:59:59 +0100
Subject: tools build: Fix rust cross compilation

Currently no target is specified to compile rust code when needed, which
breaks cross compilation. E.g. for arm64:

      LD      /tmp/build/tests/workloads/perf-test-in.o
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    [...repeated...]
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a(code_with_type.code_with_type.d12f4324cb53c560-cgu.0.rcgu.o): Relocations in generic ELF (EM: 62)
    aarch64-linux-gnu-ld: /tmp/build/tests/workloads/code_with_type.a: error adding symbols: file in wrong format
    make[5]: *** [/perf/tools/build/Makefile.build:162: /tmp/build/tests/workloads/perf-test-in.o] Error 1
    make[4]: *** [/perf/tools/build/Makefile.build:156: workloads] Error 2
    make[3]: *** [/perf/tools/build/Makefile.build:156: tests] Error 2
    make[2]: *** [Makefile.perf:785: /tmp/build/perf-test-in.o] Error 2
    make[2]: *** Waiting for unfinished jobs....
    make[1]: *** [Makefile.perf:289: sub-make] Error 2
    make: *** [Makefile:76: all] Error 2

Detect required target and pass it via rust_flags to the compiler.

Note that CROSS_COMPILE might be different from what rust compiler
expects, since it may omit the target vendor value, e.g.
"aarch64-linux-gnu" instead of "aarch64-unknown-linux-gnu".

Thus explicitly map supported CROSS_COMPILE values to corresponding Rust
versions, as suggested by Miguel Ojeda.

Tested using arm64 cross-compilation example from [1].

Fixes: 2e05bb52a12d3cdb ("perf test workload: Add code_with_type test workload")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Levi Zim <i@kxxt.dev>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nicolas Schier <nsc@kernel.org>
Link: https://perfwiki.github.io/main/arm64-cross-compilation-dockerfile/ [1]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Build.include  |  9 +++++++++
 tools/perf/Makefile.config | 18 ++++++++++++++++++
 tools/perf/Makefile.perf   |  2 +-
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/tools/build/Build.include b/tools/build/Build.include
index e45b2eb0d24a..cd0baa7a168d 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -98,6 +98,15 @@ c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1))
 c_flags   = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2))
 cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
 
+###
+# Rust flags to be used on rule definition, includes:
+# - global $(RUST_FLAGS)
+# - per target Rust flags
+# - per object Rust flags
+rust_flags_1 = $(RUST_FLAGS) $(RUST_FLAGS_$(basetarget).o) $(RUST_FLAGS_$(obj))
+rust_flags_2 = $(filter-out $(RUST_FLAGS_REMOVE_$(basetarget).o), $(rust_flags_1))
+rust_flags   = $(filter-out $(RUST_FLAGS_REMOVE_$(obj)), $(rust_flags_2))
+
 ###
 ## HOSTCC C flags
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index a8dc72cfe48e..15fbba9f4ca8 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1163,6 +1163,24 @@ ifndef NO_RUST
     CFLAGS += -DHAVE_RUST_SUPPORT
     $(call detected,CONFIG_RUST_SUPPORT)
   endif
+
+  ifneq ($(CROSS_COMPILE),)
+    RUST_TARGET_FLAGS_arm	:= arm-unknown-linux-gnueabi
+    RUST_TARGET_FLAGS_arm64	:= aarch64-unknown-linux-gnu
+    RUST_TARGET_FLAGS_m68k	:= m68k-unknown-linux-gnu
+    RUST_TARGET_FLAGS_mips	:= mipsel-unknown-linux-gnu
+    RUST_TARGET_FLAGS_powerpc	:= powerpc64le-unknown-linux-gnu
+    RUST_TARGET_FLAGS_riscv	:= riscv64gc-unknown-linux-gnu
+    RUST_TARGET_FLAGS_s390	:= s390x-unknown-linux-gnu
+    RUST_TARGET_FLAGS_x86	:= x86_64-unknown-linux-gnu
+    RUST_TARGET_FLAGS_x86_64	:= x86_64-unknown-linux-gnu
+
+    ifeq ($(RUST_TARGET_FLAGS_$(ARCH)),)
+      $(error Unknown rust cross compilation architecture $(ARCH))
+    endif
+
+    RUST_FLAGS += --target=$(RUST_TARGET_FLAGS_$(ARCH))
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 11b63bafdb23..f7b936deeaa2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -274,7 +274,7 @@ ifeq ($(PYLINT),1)
   PYLINT := $(shell which pylint 2> /dev/null)
 endif
 
-export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
+export srctree OUTPUT RM CC CXX RUSTC LD AR CFLAGS CXXFLAGS RUST_FLAGS V BISON FLEX AWK
 export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK MYPY PYLINT
 
 include $(srctree)/tools/build/Makefile.include
-- 
cgit v1.2.3


From 6036165ab1851ee28cedea592ee0393b77bfd0c0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:41:12 -0300
Subject: perf beauty: Sync linux/mount.h copy with the kernel sources

To pick the changes from:

  9b8a0ba68246a61d ("mount: add OPEN_TREE_NAMESPACE")
  0e5032237ee55301 ("statmount: accept fd as a parameter")

That doesn't change anything in tools this time as nothing that is
harvested by the beauty scripts got changed:

  $ ls -1 tools/perf/trace/beauty/*mount*sh
  tools/perf/trace/beauty/fsmount.sh
  tools/perf/trace/beauty/mount_flags.sh
  tools/perf/trace/beauty/move_mount_flags.sh
  $

This addresses this perf build warning.

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/mount.h include/uapi/linux/mount.h

Please see tools/include/uapi/README for further details.

Cc: Christian Brauner <brauner@kernel.org>
Cc: Bhavik Sachdev <b.sachdev1904@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/mount.h | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index 5d3f8c9e3a62..d9d86598d100 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -61,7 +61,8 @@
 /*
  * open_tree() flags.
  */
-#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLONE		(1 << 0)	/* Clone the target tree and attach the clone */
+#define OPEN_TREE_NAMESPACE	(1 << 1)	/* Clone the target tree into a new mount namespace */
 #define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
 
 /*
@@ -197,7 +198,10 @@ struct statmount {
  */
 struct mnt_id_req {
 	__u32 size;
-	__u32 mnt_ns_fd;
+	union {
+		__u32 mnt_ns_fd;
+		__u32 mnt_fd;
+	};
 	__u64 mnt_id;
 	__u64 param;
 	__u64 mnt_ns_id;
@@ -232,4 +236,9 @@ struct mnt_id_req {
 #define LSMT_ROOT		0xffffffffffffffff	/* root mount */
 #define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
 
+/*
+ * @flag bits for statmount(2)
+ */
+#define STATMOUNT_BY_FD		0x00000001U	/* want mountinfo for given fd */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
-- 
cgit v1.2.3


From e367679f167e46372cafca9cd903d60f84aa5e72 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:46:01 -0300
Subject: perf beauty: Sync UAPI linux/fs.h with kernel sources

To pick up changes from:

  0e6b7eae1fded85f ("fs: add FS_XFLAG_VERITY for fs-verity files")

These are used to beautify fs syscall arguments, albeit the changes in
this update are not affecting those beautifiers.

This addresses these tools/perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h

Please see tools/include/uapi/README.

Cc: Andrey Albershteyn <aalbersh@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/fs.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 66ca526cf786..70b2b661f42c 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -253,6 +253,7 @@ struct file_attr {
 #define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
 #define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
 #define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_VERITY		0x00020000	/* fs-verity enabled */
 #define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
 
 /* the read-only stuff doesn't really belong here, but any other place is
-- 
cgit v1.2.3


From 3abbb7cae8d8bffae3516d885cde9f13c6ceb833 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: perf beauty: Update the arch/x86/include/asm/irq_vectors.h copy with
 the kernel sources

To pick up the change in:

  a1fab3e69d9d0e9b ("x86/irq: Fix comment on IRQ vector layout")

That just adds one comment, so no changes in perf tooling, just silences
this build warning:

  diff -u tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h arch/x86/include/asm/irq_vectors.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
index 6e1d5b955aae..85253fc8e384 100644
--- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
+++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
@@ -77,6 +77,7 @@
  */
 #define IRQ_WORK_VECTOR			0xf6
 
+/* IRQ vector for PMIs when running a guest with a mediated PMU. */
 #define PERF_GUEST_MEDIATED_PMI_VECTOR	0xf5
 
 #define DEFERRED_ERROR_VECTOR		0xf4
-- 
cgit v1.2.3


From ecd5a2fd4c7495a1a923c754c47cdd500f5b30df Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: perf beauty: Update the linux/perf_event.h copy with the kernel
 sources

Update it as one comment got realigned, probably in a merge, so no
changes in perf tooling, just silences this build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 76e9d0664d0c..fd10aa8d697f 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1396,7 +1396,7 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L4			0x0004 /* L4 */
 #define PERF_MEM_LVLNUM_L2_MHB			0x0005 /* L2 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_MSC			0x0006 /* Memory-side Cache */
-#define PERF_MEM_LVLNUM_L0			0x0007   /* L0 */
+#define PERF_MEM_LVLNUM_L0			0x0007 /* L0 */
 #define PERF_MEM_LVLNUM_UNC			0x0008 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL			0x0009 /* CXL */
 #define PERF_MEM_LVLNUM_IO			0x000a /* I/O */
-- 
cgit v1.2.3


From c3320153769f05fd7fe9d840cb555dd3080ae424 Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Fri, 27 Feb 2026 19:19:28 -0500
Subject: nvme: fix memory allocation in nvme_pr_read_keys()

nvme_pr_read_keys() takes num_keys from userspace and uses it to
calculate the allocation size for rse via struct_size(). The upper
limit is PR_KEYS_MAX (64K).

A malicious or buggy userspace can pass a large num_keys value that
results in a 4MB allocation attempt at most, causing a warning in
the page allocator when the order exceeds MAX_PAGE_ORDER.

To fix this, use kvzalloc() instead of kzalloc().

This bug has the same reasoning and fix with the patch below:
https://lore.kernel.org/linux-block/20251212013510.3576091-1-kartikey406@gmail.com/

Warning log:
WARNING: mm/page_alloc.c:5216 at __alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216, CPU#1: syz-executor117/272
Modules linked in:
CPU: 1 UID: 0 PID: 272 Comm: syz-executor117 Not tainted 6.19.0 #1 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
RIP: 0010:__alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216
Code: ff 83 bd a8 fe ff ff 0a 0f 86 69 fb ff ff 0f b6 1d f9 f9 c4 04 80 fb 01 0f 87 3b 76 30 ff 83 e3 01 75 09 c6 05 e4 f9 c4 04 01 <0f> 0b 48 c7 85 70 fe ff ff 00 00 00 00 e9 8f fd ff ff 31 c0 e9 0d
RSP: 0018:ffffc90000fcf450 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff920001f9ea0
RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000040dc0
RBP: ffffc90000fcf648 R08: ffff88800b6c3380 R09: 0000000000000001
R10: ffffc90000fcf840 R11: ffff88807ffad280 R12: 0000000000000000
R13: 0000000000040dc0 R14: 0000000000000001 R15: ffffc90000fcf620
FS:  0000555565db33c0(0000) GS:ffff8880be26c000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000002000000c CR3: 0000000003b72000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 alloc_pages_mpol+0x236/0x4d0 mm/mempolicy.c:2486
 alloc_frozen_pages_noprof+0x149/0x180 mm/mempolicy.c:2557
 ___kmalloc_large_node+0x10c/0x140 mm/slub.c:5598
 __kmalloc_large_node_noprof+0x25/0xc0 mm/slub.c:5629
 __do_kmalloc_node mm/slub.c:5645 [inline]
 __kmalloc_noprof+0x483/0x6f0 mm/slub.c:5669
 kmalloc_noprof include/linux/slab.h:961 [inline]
 kzalloc_noprof include/linux/slab.h:1094 [inline]
 nvme_pr_read_keys+0x8f/0x4c0 drivers/nvme/host/pr.c:245
 blkdev_pr_read_keys block/ioctl.c:456 [inline]
 blkdev_common_ioctl+0x1b71/0x29b0 block/ioctl.c:730
 blkdev_ioctl+0x299/0x700 block/ioctl.c:786
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x1bf/0x220 fs/ioctl.c:583
 x64_sys_call+0x1280/0x21b0 mnt/fuzznvme_1/fuzznvme/linux-build/v6.19/./arch/x86/include/generated/asm/syscalls_64.h:17
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x71/0x330 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7fb893d3108d
Code: 28 c3 e8 46 1e 00 00 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffff61f2f38 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffff61f3138 RCX: 00007fb893d3108d
RDX: 0000000020000040 RSI: 00000000c01070ce RDI: 0000000000000003
RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffff61f3138
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
R13: 00007ffff61f3128 R14: 00007fb893dae530 R15: 0000000000000001
 </TASK>

Fixes: 5fd96a4e15de (nvme: Add pr_ops read_keys support)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index ad2ecc2f49a9..fe7dbe264815 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -242,7 +242,7 @@ static int nvme_pr_read_keys(struct block_device *bdev,
 	if (rse_len > U32_MAX)
 		return -EINVAL;
 
-	rse = kzalloc(rse_len, GFP_KERNEL);
+	rse = kvzalloc(rse_len, GFP_KERNEL);
 	if (!rse)
 		return -ENOMEM;
 
@@ -267,7 +267,7 @@ static int nvme_pr_read_keys(struct block_device *bdev,
 	}
 
 free_rse:
-	kfree(rse);
+	kvfree(rse);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 916a9f385d81a65f7209614742208b8a923434bd Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 11:49:24 -0300
Subject: tools headers: Update the linux/gfp_types.h copy with the kernel
 sources

To pick up the changes in:

  f3ec502b6755a3bf ("mm/slab: mark alloc tags empty for sheaves allocated with __GFP_NO_OBJ_EXT")
  241b3a09639c317b ("mm: clarify GFP_ATOMIC/GFP_NOWAIT doc-comment")

That just adds some comments, so no changes in perf tooling, just silences
this build warning:

Warning: Kernel ABI header differences:
  diff -u tools/include/linux/gfp_types.h include/linux/gfp_types.h

Please see tools/include/uapi/README.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/gfp_types.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h
index 3de43b12209e..6c75df30a281 100644
--- a/tools/include/linux/gfp_types.h
+++ b/tools/include/linux/gfp_types.h
@@ -139,6 +139,8 @@ enum {
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  *
  * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
+ * mark_obj_codetag_empty() should be called upon freeing for objects allocated
+ * with this flag to indicate that their NULL tags are expected and normal.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
@@ -309,8 +311,10 @@ enum {
  *
  * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
  * watermark is applied to allow access to "atomic reserves".
- * The current implementation doesn't support NMI and few other strict
- * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
+ * The current implementation doesn't support NMI, nor contexts that disable
+ * preemption under PREEMPT_RT. This includes raw_spin_lock() and plain
+ * preempt_disable() - see "Memory allocation" in
+ * Documentation/core-api/real-time/differences.rst for more info.
  *
  * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
  * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
@@ -321,6 +325,7 @@ enum {
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
  * reclaim, start physical IO or use any filesystem callback.  It is very
  * likely to fail to allocate memory, even for very small allocations.
+ * The same restrictions on calling contexts apply as for %GFP_ATOMIC.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.
-- 
cgit v1.2.3


From 9cd284105bb77b063b61523f62096e853b8b890b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:32:19 -0300
Subject: tools headers UAPI: Sync linux/kvm.h with the kernel sources

To pick the changes in:

  f7ab71f178d56447 ("KVM: s390: Add explicit padding to struct kvm_s390_keyop")
  0ee4ddc1647b8b3b ("KVM: s390: Storage key manipulation IOCTL")
  fa9893fadbc245e1 ("KVM: Introduce KVM_EXIT_SNP_REQ_CERTS for SNP certificate-fetching")
  f174a9ffcd48d78a ("KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots")

That just rebuilds perf, as these patches add just one new KVM ioctl,
but for S390, that is not being considered by tools/perf/trace/beauty/kvm_ioctl.sh
so far.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index dddb781b0507..65500f5db379 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -135,6 +135,12 @@ struct kvm_xen_exit {
 	} u;
 };
 
+struct kvm_exit_snp_req_certs {
+	__u64 gpa;
+	__u64 npages;
+	__u64 ret;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -180,6 +186,8 @@ struct kvm_xen_exit {
 #define KVM_EXIT_MEMORY_FAULT     39
 #define KVM_EXIT_TDX              40
 #define KVM_EXIT_ARM_SEA          41
+#define KVM_EXIT_ARM_LDST64B      42
+#define KVM_EXIT_SNP_REQ_CERTS    43
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -402,7 +410,7 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
-		/* KVM_EXIT_ARM_NISV */
+		/* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */
 		struct {
 			__u64 esr_iss;
 			__u64 fault_ipa;
@@ -482,6 +490,8 @@ struct kvm_run {
 			__u64 gva;
 			__u64 gpa;
 		} arm_sea;
+		/* KVM_EXIT_SNP_REQ_CERTS */
+		struct kvm_exit_snp_req_certs snp_req_certs;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -974,6 +984,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_GUEST_MEMFD_FLAGS 244
 #define KVM_CAP_ARM_SEA_TO_USER 245
 #define KVM_CAP_S390_USER_OPEREXEC 246
+#define KVM_CAP_S390_KEYOP 247
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1219,6 +1230,16 @@ struct kvm_vfio_spapr_tce {
 	__s32	tablefd;
 };
 
+#define KVM_S390_KEYOP_ISKE 0x01
+#define KVM_S390_KEYOP_RRBE 0x02
+#define KVM_S390_KEYOP_SSKE 0x03
+struct kvm_s390_keyop {
+	__u64 guest_addr;
+	__u8  key;
+	__u8  operation;
+	__u8  pad[6];
+};
+
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.
@@ -1238,6 +1259,7 @@ struct kvm_vfio_spapr_tce {
 #define KVM_S390_UCAS_MAP        _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
 #define KVM_S390_UCAS_UNMAP      _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
 #define KVM_S390_VCPU_FAULT	 _IOW(KVMIO, 0x52, unsigned long)
+#define KVM_S390_KEYOP           _IOWR(KVMIO, 0x53, struct kvm_s390_keyop)
 
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP        _IO(KVMIO,   0x60)
-- 
cgit v1.2.3


From 48084cc153a5b0fbf0aa98d47670d3be0b9f64d5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:40 +0100
Subject: x86/numa: Store extra copy of numa_nodes_parsed

The topology setup code needs to know the total number of physical
nodes enumerated in SRAT; however NUMA_EMU can cause the existing
numa_nodes_parsed bitmap to be fictitious. Therefore, keep a copy of
the bitmap specifically to retain the physical node count.

Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110059.889884023@infradead.org
---
 arch/x86/include/asm/numa.h | 6 ++++++
 arch/x86/mm/numa.c          | 8 ++++++++
 arch/x86/mm/srat.c          | 2 ++
 3 files changed, 16 insertions(+)

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 53ba39ce010c..a9063f332fa6 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -22,6 +22,7 @@ extern int numa_off;
  */
 extern s16 __apicid_to_node[MAX_LOCAL_APIC];
 extern nodemask_t numa_nodes_parsed __initdata;
+extern nodemask_t numa_phys_nodes_parsed __initdata;
 
 static inline void set_apicid_to_node(int apicid, s16 node)
 {
@@ -48,6 +49,7 @@ extern void __init init_cpu_to_node(void);
 extern void numa_add_cpu(unsigned int cpu);
 extern void numa_remove_cpu(unsigned int cpu);
 extern void init_gi_nodes(void);
+extern int num_phys_nodes(void);
 #else	/* CONFIG_NUMA */
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
@@ -55,6 +57,10 @@ static inline void init_cpu_to_node(void)		{ }
 static inline void numa_add_cpu(unsigned int cpu)	{ }
 static inline void numa_remove_cpu(unsigned int cpu)	{ }
 static inline void init_gi_nodes(void)			{ }
+static inline int num_phys_nodes(void)
+{
+	return 1;
+}
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 7a97327140df..99d0a9332c14 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -48,6 +48,8 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = {
 	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
 };
 
+nodemask_t numa_phys_nodes_parsed __initdata;
+
 int numa_cpu_node(int cpu)
 {
 	u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
@@ -57,6 +59,11 @@ int numa_cpu_node(int cpu)
 	return NUMA_NO_NODE;
 }
 
+int __init num_phys_nodes(void)
+{
+	return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES);
+}
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
@@ -210,6 +217,7 @@ static int __init dummy_numa_init(void)
 	       0LLU, PFN_PHYS(max_pfn) - 1);
 
 	node_set(0, numa_nodes_parsed);
+	node_set(0, numa_phys_nodes_parsed);
 	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
 
 	return 0;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 6f8e0f21c710..44ca66651756 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -57,6 +57,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 	}
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
 	pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node);
 }
 
@@ -97,6 +98,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 
 	set_apicid_to_node(apic_id, node);
 	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
 	pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node);
 }
 
-- 
cgit v1.2.3


From ae6730ff42b3a13d94b405edeb5e40108b6d21b6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:41 +0100
Subject: x86/topo: Add topology_num_nodes_per_package()

Use the MADT and SRAT table data to compute __num_nodes_per_package.

Specifically, SRAT has already been parsed in x86_numa_init(), which is called
before acpi_boot_init() which parses MADT. So both are available in
topology_init_possible_cpus().

This number is useful to divinate the various Intel CoD/SNC and AMD NPS modes,
since the platforms are failing to provide this otherwise.

Doing it this way is independent of the number of online CPUs and
other such shenanigans.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.004091624@infradead.org
---
 arch/x86/include/asm/topology.h |  6 ++++++
 arch/x86/kernel/cpu/common.c    |  3 +++
 arch/x86/kernel/cpu/topology.c  | 13 +++++++++++--
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 1fadf0cf520c..0ba9bdb99871 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -155,6 +155,7 @@ extern unsigned int __max_logical_packages;
 extern unsigned int __max_threads_per_core;
 extern unsigned int __num_threads_per_package;
 extern unsigned int __num_cores_per_package;
+extern unsigned int __num_nodes_per_package;
 
 const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c);
 enum x86_topology_cpu_type get_topology_cpu_type(struct cpuinfo_x86 *c);
@@ -179,6 +180,11 @@ static inline unsigned int topology_num_threads_per_package(void)
 	return __num_threads_per_package;
 }
 
+static inline unsigned int topology_num_nodes_per_package(void)
+{
+	return __num_nodes_per_package;
+}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level);
 #else
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1c3261cae40c..a8ff4376c286 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -95,6 +95,9 @@ EXPORT_SYMBOL(__max_dies_per_package);
 unsigned int __max_logical_packages __ro_after_init = 1;
 EXPORT_SYMBOL(__max_logical_packages);
 
+unsigned int __num_nodes_per_package __ro_after_init = 1;
+EXPORT_SYMBOL(__num_nodes_per_package);
+
 unsigned int __num_cores_per_package __ro_after_init = 1;
 EXPORT_SYMBOL(__num_cores_per_package);
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 23190a786d31..eafcb1fc185a 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -31,6 +31,7 @@
 #include <asm/mpspec.h>
 #include <asm/msr.h>
 #include <asm/smp.h>
+#include <asm/numa.h>
 
 #include "cpu.h"
 
@@ -492,11 +493,19 @@ void __init topology_init_possible_cpus(void)
 	set_nr_cpu_ids(allowed);
 
 	cnta = domain_weight(TOPO_PKG_DOMAIN);
-	cntb = domain_weight(TOPO_DIE_DOMAIN);
 	__max_logical_packages = cnta;
+
+	pr_info("Max. logical packages: %3u\n", __max_logical_packages);
+
+	cntb = num_phys_nodes();
+	__num_nodes_per_package = DIV_ROUND_UP(cntb, cnta);
+
+	pr_info("Max. logical nodes:    %3u\n", cntb);
+	pr_info("Num. nodes per package:%3u\n", __num_nodes_per_package);
+
+	cntb = domain_weight(TOPO_DIE_DOMAIN);
 	__max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta));
 
-	pr_info("Max. logical packages: %3u\n", cnta);
 	pr_info("Max. logical dies:     %3u\n", cntb);
 	pr_info("Max. dies per package: %3u\n", __max_dies_per_package);
 
-- 
cgit v1.2.3


From 717b64d58cff6fb97f97be07e382ed7641167a56 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:42 +0100
Subject: x86/topo: Replace x86_has_numa_in_package

.. with the brand spanking new topology_num_nodes_per_package().

Having the topology setup determine this value during MADT/SRAT parsing before
SMP bringup avoids having to detect this situation when building the SMP
topology masks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.123701837@infradead.org
---
 arch/x86/kernel/smpboot.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5cd6950ab672..db3e481cdbb2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -468,13 +468,6 @@ static int x86_cluster_flags(void)
 }
 #endif
 
-/*
- * Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
- * Sub-NUMA Clustering have this.
- */
-static bool x86_has_numa_in_package;
-
 static struct sched_domain_topology_level x86_topology[] = {
 	SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT),
 #ifdef CONFIG_SCHED_CLUSTER
@@ -496,7 +489,7 @@ static void __init build_sched_topology(void)
 	 * PKG domain since the NUMA domains will auto-magically create the
 	 * right spanning domains based on the SLIT.
 	 */
-	if (x86_has_numa_in_package) {
+	if (topology_num_nodes_per_package() > 1) {
 		unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2;
 
 		memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom]));
@@ -550,7 +543,7 @@ int arch_sched_node_distance(int from, int to)
 	case INTEL_GRANITERAPIDS_X:
 	case INTEL_ATOM_DARKMONT_X:
 
-		if (!x86_has_numa_in_package || topology_max_packages() == 1 ||
+		if (topology_max_packages() == 1 || topology_num_nodes_per_package() == 1 ||
 		    d < REMOTE_DISTANCE)
 			return d;
 
@@ -606,7 +599,7 @@ void set_cpu_sibling_map(int cpu)
 		o = &cpu_data(i);
 
 		if (match_pkg(c, o) && !topology_same_node(c, o))
-			x86_has_numa_in_package = true;
+			WARN_ON_ONCE(topology_num_nodes_per_package() == 1);
 
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(topology_sibling_cpumask, cpu, i);
-- 
cgit v1.2.3


From 528d89a4707e5bfd86e30823c45dbb66877df900 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 3 Mar 2026 11:55:43 +0100
Subject: x86/topo: Fix SNC topology mess

Per 4d6dd05d07d0 ("sched/topology: Fix sched domain build error for GNR, CWF in
SNC-3 mode"), the original crazy SNC-3 SLIT table was:

node distances:
node     0    1    2    3    4    5
    0:   10   15   17   21   28   26
    1:   15   10   15   23   26   23
    2:   17   15   10   26   23   21
    3:   21   28   26   10   15   17
    4:   23   26   23   15   10   15
    5:   26   23   21   17   15   10

And per:

  https://lore.kernel.org/lkml/20250825075642.GQ3245006@noisy.programming.kicks-ass.net/

The suggestion was to average the off-trace clusters to restore sanity.

However, 4d6dd05d07d0 implements this under various assumptions:

 - anything GNR/CWF with numa_in_package;
 - there will never be more than 2 packages;
 - the off-trace cluster will have distance >20

And then HPE shows up with a machine that matches the
Vendor-Family-Model checks but looks like this:

Here's an 8 socket (2 chassis) HPE system with SNC enabled:

node   0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15
  0:  10  12  16  16  16  16  18  18  40  40  40  40  40  40  40  40
  1:  12  10  16  16  16  16  18  18  40  40  40  40  40  40  40  40
  2:  16  16  10  12  18  18  16  16  40  40  40  40  40  40  40  40
  3:  16  16  12  10  18  18  16  16  40  40  40  40  40  40  40  40
  4:  16  16  18  18  10  12  16  16  40  40  40  40  40  40  40  40
  5:  16  16  18  18  12  10  16  16  40  40  40  40  40  40  40  40
  6:  18  18  16  16  16  16  10  12  40  40  40  40  40  40  40  40
  7:  18  18  16  16  16  16  12  10  40  40  40  40  40  40  40  40
  8:  40  40  40  40  40  40  40  40  10  12  16  16  16  16  18  18
  9:  40  40  40  40  40  40  40  40  12  10  16  16  16  16  18  18
 10:  40  40  40  40  40  40  40  40  16  16  10  12  18  18  16  16
 11:  40  40  40  40  40  40  40  40  16  16  12  10  18  18  16  16
 12:  40  40  40  40  40  40  40  40  16  16  18  18  10  12  16  16
 13:  40  40  40  40  40  40  40  40  16  16  18  18  12  10  16  16
 14:  40  40  40  40  40  40  40  40  18  18  16  16  16  16  10  12
 15:  40  40  40  40  40  40  40  40  18  18  16  16  16  16  12  10

 10 = Same chassis and socket
 12 = Same chassis and socket (SNC)
 16 = Same chassis and adjacent socket
 18 = Same chassis and non-adjacent socket
 40 = Different chassis

Turns out, the 'max 2 packages' thing is only relevant to the SNC-3 parts, the
smaller parts do 8 sockets (like usual). The above SLIT table is sane, but
violates the previous assumptions and trips a WARN.

Now that the topology code has a sensible measure of nodes-per-package, we can
use that to divinate the SNC mode at hand, and only fix up SNC-3 topologies.

There is a 'healthy' amount of paranoia code validating the assumptions on the
SLIT table, a simple pr_err(FW_BUG) print on failure and a fallback to using
the regular table. Lets see how long this lasts :-)

Fixes: 4d6dd05d07d0 ("sched/topology: Fix sched domain build error for GNR, CWF in SNC-3 mode")
Reported-by: Kyle Meyer <kyle.meyer@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
Link: https://patch.msgid.link/20260303110100.238361290@infradead.org
---
 arch/x86/kernel/smpboot.c | 190 ++++++++++++++++++++++++++++++++++------------
 1 file changed, 143 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index db3e481cdbb2..294a8ea60298 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -506,33 +506,149 @@ static void __init build_sched_topology(void)
 }
 
 #ifdef CONFIG_NUMA
-static int sched_avg_remote_distance;
-static int avg_remote_numa_distance(void)
+/*
+ * Test if the on-trace cluster at (N,N) is symmetric.
+ * Uses upper triangle iteration to avoid obvious duplicates.
+ */
+static bool slit_cluster_symmetric(int N)
 {
-	int i, j;
-	int distance, nr_remote, total_distance;
-
-	if (sched_avg_remote_distance > 0)
-		return sched_avg_remote_distance;
-
-	nr_remote = 0;
-	total_distance = 0;
-	for_each_node_state(i, N_CPU) {
-		for_each_node_state(j, N_CPU) {
-			distance = node_distance(i, j);
-
-			if (distance >= REMOTE_DISTANCE) {
-				nr_remote++;
-				total_distance += distance;
-			}
+	int u = topology_num_nodes_per_package();
+
+	for (int k = 0; k < u; k++) {
+		for (int l = k; l < u; l++) {
+			if (node_distance(N + k, N + l) !=
+			    node_distance(N + l, N + k))
+				return false;
 		}
 	}
-	if (nr_remote)
-		sched_avg_remote_distance = total_distance / nr_remote;
-	else
-		sched_avg_remote_distance = REMOTE_DISTANCE;
 
-	return sched_avg_remote_distance;
+	return true;
+}
+
+/*
+ * Return the package-id of the cluster, or ~0 if indeterminate.
+ * Each node in the on-trace cluster should have the same package-id.
+ */
+static u32 slit_cluster_package(int N)
+{
+	int u = topology_num_nodes_per_package();
+	u32 pkg_id = ~0;
+
+	for (int n = 0; n < u; n++) {
+		const struct cpumask *cpus = cpumask_of_node(N + n);
+		int cpu;
+
+		for_each_cpu(cpu, cpus) {
+			u32 id = topology_logical_package_id(cpu);
+
+			if (pkg_id == ~0)
+				pkg_id = id;
+			if (pkg_id != id)
+				return ~0;
+		}
+	}
+
+	return pkg_id;
+}
+
+/*
+ * Validate the SLIT table is of the form expected for SNC, specifically:
+ *
+ *  - each on-trace cluster should be symmetric,
+ *  - each on-trace cluster should have a unique package-id.
+ *
+ * If you NUMA_EMU on top of SNC, you get to keep the pieces.
+ */
+static bool slit_validate(void)
+{
+	int u = topology_num_nodes_per_package();
+	u32 pkg_id, prev_pkg_id = ~0;
+
+	for (int pkg = 0; pkg < topology_max_packages(); pkg++) {
+		int n = pkg * u;
+
+		/*
+		 * Ensure the on-trace cluster is symmetric and each cluster
+		 * has a different package id.
+		 */
+		if (!slit_cluster_symmetric(n))
+			return false;
+		pkg_id = slit_cluster_package(n);
+		if (pkg_id == ~0)
+			return false;
+		if (pkg && pkg_id == prev_pkg_id)
+			return false;
+
+		prev_pkg_id = pkg_id;
+	}
+
+	return true;
+}
+
+/*
+ * Compute a sanitized SLIT table for SNC; notably SNC-3 can end up with
+ * asymmetric off-trace clusters, reflecting physical assymmetries. However
+ * this leads to 'unfortunate' sched_domain configurations.
+ *
+ * For example dual socket GNR with SNC-3:
+ *
+ * node distances:
+ * node     0    1    2    3    4    5
+ *     0:   10   15   17   21   28   26
+ *     1:   15   10   15   23   26   23
+ *     2:   17   15   10   26   23   21
+ *     3:   21   28   26   10   15   17
+ *     4:   23   26   23   15   10   15
+ *     5:   26   23   21   17   15   10
+ *
+ * Fix things up by averaging out the off-trace clusters; resulting in:
+ *
+ * node     0    1    2    3    4    5
+ *     0:   10   15   17   24   24   24
+ *     1:   15   10   15   24   24   24
+ *     2:   17   15   10   24   24   24
+ *     3:   24   24   24   10   15   17
+ *     4:   24   24   24   15   10   15
+ *     5:   24   24   24   17   15   10
+ */
+static int slit_cluster_distance(int i, int j)
+{
+	static int slit_valid = -1;
+	int u = topology_num_nodes_per_package();
+	long d = 0;
+	int x, y;
+
+	if (slit_valid < 0) {
+		slit_valid = slit_validate();
+		if (!slit_valid)
+			pr_err(FW_BUG "SLIT table doesn't have the expected form for SNC -- fixup disabled!\n");
+		else
+			pr_info("Fixing up SNC SLIT table.\n");
+	}
+
+	/*
+	 * Is this a unit cluster on the trace?
+	 */
+	if ((i / u) == (j / u) || !slit_valid)
+		return node_distance(i, j);
+
+	/*
+	 * Off-trace cluster.
+	 *
+	 * Notably average out the symmetric pair of off-trace clusters to
+	 * ensure the resulting SLIT table is symmetric.
+	 */
+	x = i - (i % u);
+	y = j - (j % u);
+
+	for (i = x; i < x + u; i++) {
+		for (j = y; j < y + u; j++) {
+			d += node_distance(i, j);
+			d += node_distance(j, i);
+		}
+	}
+
+	return d / (2*u*u);
 }
 
 int arch_sched_node_distance(int from, int to)
@@ -542,34 +658,14 @@ int arch_sched_node_distance(int from, int to)
 	switch (boot_cpu_data.x86_vfm) {
 	case INTEL_GRANITERAPIDS_X:
 	case INTEL_ATOM_DARKMONT_X:
-
-		if (topology_max_packages() == 1 || topology_num_nodes_per_package() == 1 ||
-		    d < REMOTE_DISTANCE)
+		if (topology_max_packages() == 1 ||
+		    topology_num_nodes_per_package() < 3)
 			return d;
 
 		/*
-		 * With SNC enabled, there could be too many levels of remote
-		 * NUMA node distances, creating NUMA domain levels
-		 * including local nodes and partial remote nodes.
-		 *
-		 * Trim finer distance tuning for NUMA nodes in remote package
-		 * for the purpose of building sched domains. Group NUMA nodes
-		 * in the remote package in the same sched group.
-		 * Simplify NUMA domains and avoid extra NUMA levels including
-		 * different remote NUMA nodes and local nodes.
-		 *
-		 * GNR and CWF don't expect systems with more than 2 packages
-		 * and more than 2 hops between packages. Single average remote
-		 * distance won't be appropriate if there are more than 2
-		 * packages as average distance to different remote packages
-		 * could be different.
+		 * Handle SNC-3 asymmetries.
 		 */
-		WARN_ONCE(topology_max_packages() > 2,
-			  "sched: Expect only up to 2 packages for GNR or CWF, "
-			  "but saw %d packages when building sched domains.",
-			  topology_max_packages());
-
-		d = avg_remote_numa_distance();
+		return slit_cluster_distance(from, to);
 	}
 	return d;
 }
-- 
cgit v1.2.3


From 59674fc9d0bfd96ce8a776680ee1cf22c28c9ac7 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Tue, 3 Mar 2026 11:55:44 +0100
Subject: x86/resctrl: Fix SNC detection

Now that the x86 topology code has a sensible nodes-per-package
measure, that does not depend on the online status of CPUs, use this
to divinate the SNC mode.

Note that when Cluster on Die (CoD) is configured on older systems this
will also show multiple NUMA nodes per package. Intel Resource Director
Technology is incomaptible with CoD. Print a warning and do not use the
fixup MSR_RMID_SNC_CONFIG.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Link: https://patch.msgid.link/aaCxbbgjL6OZ6VMd@agluck-desk3
Link: https://patch.msgid.link/20260303110100.367976706@infradead.org
---
 arch/x86/kernel/cpu/resctrl/monitor.c | 36 +++++------------------------------
 1 file changed, 5 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index e6a154240b8d..9bd87bae4983 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -364,7 +364,7 @@ void arch_mon_domain_online(struct rdt_resource *r, struct rdt_l3_mon_domain *d)
 		msr_clear_bit(MSR_RMID_SNC_CONFIG, 0);
 }
 
-/* CPU models that support MSR_RMID_SNC_CONFIG */
+/* CPU models that support SNC and MSR_RMID_SNC_CONFIG */
 static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ICELAKE_X, 0),
 	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, 0),
@@ -375,40 +375,14 @@ static const struct x86_cpu_id snc_cpu_ids[] __initconst = {
 	{}
 };
 
-/*
- * There isn't a simple hardware bit that indicates whether a CPU is running
- * in Sub-NUMA Cluster (SNC) mode. Infer the state by comparing the
- * number of CPUs sharing the L3 cache with CPU0 to the number of CPUs in
- * the same NUMA node as CPU0.
- * It is not possible to accurately determine SNC state if the system is
- * booted with a maxcpus=N parameter. That distorts the ratio of SNC nodes
- * to L3 caches. It will be OK if system is booted with hyperthreading
- * disabled (since this doesn't affect the ratio).
- */
 static __init int snc_get_config(void)
 {
-	struct cacheinfo *ci = get_cpu_cacheinfo_level(0, RESCTRL_L3_CACHE);
-	const cpumask_t *node0_cpumask;
-	int cpus_per_node, cpus_per_l3;
-	int ret;
-
-	if (!x86_match_cpu(snc_cpu_ids) || !ci)
-		return 1;
+	int ret = topology_num_nodes_per_package();
 
-	cpus_read_lock();
-	if (num_online_cpus() != num_present_cpus())
-		pr_warn("Some CPUs offline, SNC detection may be incorrect\n");
-	cpus_read_unlock();
-
-	node0_cpumask = cpumask_of_node(cpu_to_node(0));
-
-	cpus_per_node = cpumask_weight(node0_cpumask);
-	cpus_per_l3 = cpumask_weight(&ci->shared_cpu_map);
-
-	if (!cpus_per_node || !cpus_per_l3)
+	if (ret > 1 && !x86_match_cpu(snc_cpu_ids)) {
+		pr_warn("CoD enabled system? Resctrl not supported\n");
 		return 1;
-
-	ret = cpus_per_l3 / cpus_per_node;
+	}
 
 	/* sanity check: Only valid results are 1, 2, 3, 4, 6 */
 	switch (ret) {
-- 
cgit v1.2.3


From 4ebe2b8cda7e91a30c1cf1d297605682540d4ad9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:47:03 -0300
Subject: tools headers x86 cpufeatures: Sync with the kernel sources

To pick the changes from:

  f24ef0093dd8cf60 ("KVM: x86: Advertise MOVRS CPUID to userspace")
  f49ecf5e110ab0ed ("x86/cpufeature: Replace X86_FEATURE_SYSENTER32 with X86_FEATURE_SYSFAST32")
  db5e82496492b489 ("KVM: SVM: Virtualize and advertise support for ERAPS")

This causes these perf files to be rebuilt and brings some X86_FEATURE
that may be used by:

      CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
      CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Please see tools/include/uapi/README for further details.

Cc: Amit Shah <amit.shah@amd.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index c3b53beb1300..dbe104df339b 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -84,7 +84,7 @@
 #define X86_FEATURE_PEBS		( 3*32+12) /* "pebs" Precise-Event Based Sampling */
 #define X86_FEATURE_BTS			( 3*32+13) /* "bts" Branch Trace Store */
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* syscall in IA32 userspace */
-#define X86_FEATURE_SYSENTER32		( 3*32+15) /* sysenter in IA32 userspace */
+#define X86_FEATURE_SYSFAST32		( 3*32+15) /* sysenter/syscall in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* "rep_good" REP microcode works well */
 #define X86_FEATURE_AMD_LBR_V2		( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */
 #define X86_FEATURE_CLEAR_CPU_BUF	( 3*32+18) /* Clear CPU buffers using VERW */
@@ -326,6 +326,7 @@
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* "lam" Linear Address Masking */
+#define X86_FEATURE_MOVRS		(12*32+31) /* MOVRS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
@@ -472,6 +473,7 @@
 #define X86_FEATURE_GP_ON_USER_CPUID	(20*32+17) /* User CPUID faulting */
 
 #define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
+#define X86_FEATURE_ERAPS		(20*32+24) /* Enhanced Return Address Predictor Security */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
-- 
cgit v1.2.3


From 1b3f004bac8e2c9e340ac237bd5b36b686ae63e8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 12:54:08 -0300
Subject: tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources

To pick the changes in:

  6517dfbcc918f970 ("KVM: x86: Add x2APIC "features" to control EOI broadcast suppression")
  20c3c4108d58f87c ("KVM: SEV: Add KVM_SEV_SNP_ENABLE_REQ_CERTS command")

This silences these perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Khushit Shah <khushit.shah@nutanix.com>
Cc: Michael Roth <michael.roth@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 7ceff6583652..846a63215ce1 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -503,6 +503,7 @@ struct kvm_sync_regs {
 #define KVM_X86_GRP_SEV			1
 #  define KVM_X86_SEV_VMSA_FEATURES	0
 #  define KVM_X86_SNP_POLICY_BITS	1
+#  define KVM_X86_SEV_SNP_REQ_CERTS	2
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -743,6 +744,7 @@ enum sev_cmd_id {
 	KVM_SEV_SNP_LAUNCH_START = 100,
 	KVM_SEV_SNP_LAUNCH_UPDATE,
 	KVM_SEV_SNP_LAUNCH_FINISH,
+	KVM_SEV_SNP_ENABLE_REQ_CERTS,
 
 	KVM_SEV_NR_MAX,
 };
@@ -914,8 +916,10 @@ struct kvm_sev_snp_launch_finish {
 	__u64 pad1[4];
 };
 
-#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+#define KVM_X2APIC_API_USE_32BIT_IDS			_BITULL(0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK		_BITULL(1)
+#define KVM_X2APIC_ENABLE_SUPPRESS_EOI_BROADCAST	_BITULL(2)
+#define KVM_X2APIC_DISABLE_SUPPRESS_EOI_BROADCAST	_BITULL(3)
 
 struct kvm_hyperv_eventfd {
 	__u32 conn_id;
-- 
cgit v1.2.3


From d658686a1331db3bb108ca079d76deb3208ed949 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@redhat.com>
Date: Mon, 2 Mar 2026 16:45:40 +0100
Subject: sched/deadline: Fix missing ENQUEUE_REPLENISH during PI de-boosting

Running stress-ng --schedpolicy 0 on an RT kernel on a big machine
might lead to the following WARNINGs (edited).

 sched: DL de-boosted task PID 22725: REPLENISH flag missing

 WARNING: CPU: 93 PID: 0 at kernel/sched/deadline.c:239 dequeue_task_dl+0x15c/0x1f8
 ... (running_bw underflow)
 Call trace:
  dequeue_task_dl+0x15c/0x1f8 (P)
  dequeue_task+0x80/0x168
  deactivate_task+0x24/0x50
  push_dl_task+0x264/0x2e0
  dl_task_timer+0x1b0/0x228
  __hrtimer_run_queues+0x188/0x378
  hrtimer_interrupt+0xfc/0x260
  ...

The problem is that when a SCHED_DEADLINE task (lock holder) is
changed to a lower priority class via sched_setscheduler(), it may
fail to properly inherit the parameters of potential DEADLINE donors
if it didn't already inherit them in the past (shorter deadline than
donor's at that time). This might lead to bandwidth accounting
corruption, as enqueue_task_dl() won't recognize the lock holder as
boosted.

The scenario occurs when:
1. A DEADLINE task (donor) blocks on a PI mutex held by another
   DEADLINE task (holder), but the holder doesn't inherit parameters
   (e.g., it already has a shorter deadline)
2. sched_setscheduler() changes the holder from DEADLINE to a lower
   class while still holding the mutex
3. The holder should now inherit DEADLINE parameters from the donor
   and be enqueued with ENQUEUE_REPLENISH, but this doesn't happen

Fix the issue by introducing __setscheduler_dl_pi(), which detects when
a DEADLINE (proper or boosted) task gets setscheduled to a lower
priority class. In case, the function makes the task inherit DEADLINE
parameters of the donoer (pi_se) and sets ENQUEUE_REPLENISH flag to
ensure proper bandwidth accounting during the next enqueue operation.

Fixes: 2279f540ea7d ("sched/deadline: Fix priority inheritance with multiple scheduling classes")
Reported-by: Bruno Goncalves <bgoncalv@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260302-upstream-fix-deadline-piboost-b4-v3-1-6ba32184a9e0@redhat.com
---
 kernel/sched/syscalls.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 6f10db3646e7..cadb0e9fe19b 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -284,6 +284,35 @@ static bool check_same_owner(struct task_struct *p)
 		uid_eq(cred->euid, pcred->uid));
 }
 
+#ifdef CONFIG_RT_MUTEXES
+static inline void __setscheduler_dl_pi(int newprio, int policy,
+			      struct task_struct *p,
+			      struct sched_change_ctx *scope)
+{
+	/*
+	 * In case a DEADLINE task (either proper or boosted) gets
+	 * setscheduled to a lower priority class, check if it neeeds to
+	 * inherit parameters from a potential pi_task. In that case make
+	 * sure replenishment happens with the next enqueue.
+	 */
+
+	if (dl_prio(newprio) && !dl_policy(policy)) {
+		struct task_struct *pi_task = rt_mutex_get_top_task(p);
+
+		if (pi_task) {
+			p->dl.pi_se = pi_task->dl.pi_se;
+			scope->flags |= ENQUEUE_REPLENISH;
+		}
+	}
+}
+#else /* !CONFIG_RT_MUTEXES */
+static inline void __setscheduler_dl_pi(int newprio, int policy,
+			      struct task_struct *p,
+			      struct sched_change_ctx *scope)
+{
+}
+#endif /* !CONFIG_RT_MUTEXES */
+
 #ifdef CONFIG_UCLAMP_TASK
 
 static int uclamp_validate(struct task_struct *p,
@@ -655,6 +684,7 @@ change:
 			__setscheduler_params(p, attr);
 			p->sched_class = next_class;
 			p->prio = newprio;
+			__setscheduler_dl_pi(newprio, policy, p, scope);
 		}
 		__setscheduler_uclamp(p, attr);
 
-- 
cgit v1.2.3


From b5ef09a77d0b5213268300eedd8a7d28b4e92d47 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Thu, 26 Feb 2026 17:03:07 -0800
Subject: x86/entry/vdso32: Work around libgcc unwinder bug

The unwinder code in libgcc has a long standing bug which causes it to
fail to pick up the signal frame CFI flag. This is a generic bug
across all platforms.

It affects the __kernel_sigreturn and __kernel_rt_sigreturn vdso entry
points on i386. The x86-64 kernel doesn't provide a sigreturn stub,
and so there is no kernel-provided code that is affected on x86-64.

libgcc does have a legacy fallback path which happens to work as long
as the bytes immediately before each of the sigreturn functions fall
outside any function. This patch adds a nop before the ALIGN to each
of the sigreturn stubs to ensure that this is, indeed, the case.

The rest of the patch is just a comment which documents the invariants
that need to be maintained for this legacy path to work correctly.

This is a manifest bug: in the current vdso, __kernel_vsyscall is a
multiple of 16 bytes long and thus __kernel_sigreturn does not have
any padding in front of it.

Closes: https://lore.kernel.org/lkml/f3412cc3e8f66d1853cc9d572c0f2fab076872b1.camel@xry111.site
Fixes: 884961618ee5 ("x86/entry/vdso32: Remove open-coded DWARF in sigreturn.S")
Reported-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050
Link: https://patch.msgid.link/20260227010308.310342-1-hpa@zytor.com
---
 arch/x86/entry/vdso/vdso32/sigreturn.S | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index b433353bc8e3..b33fcc501ba3 100644
--- a/arch/x86/entry/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
@@ -35,9 +35,38 @@
 #endif
 .endm
 
+/*
+ * WARNING:
+ *
+ * A bug in the libgcc unwinder as of at least gcc 15.2 (2026) means that
+ * the unwinder fails to recognize the signal frame flag.
+ *
+ * There is a hacky legacy fallback path in libgcc which ends up
+ * getting invoked instead. It happens to work as long as BOTH of the
+ * following conditions are true:
+ *
+ * 1. There is at least one byte before the each of the sigreturn
+ *    functions which falls outside any function. This is enforced by
+ *    an explicit nop instruction before the ALIGN.
+ * 2. The code sequences between the entry point up to and including
+ *    the int $0x80 below need to match EXACTLY. Do not change them
+ *    in any way. The exact byte sequences are:
+ *
+ *    __kernel_sigreturn:
+ *        0:   58                      pop    %eax
+ *        1:   b8 77 00 00 00          mov    $0x77,%eax
+ *        6:   cd 80                   int    $0x80
+ *
+ *    __kernel_rt_sigreturn:
+ *        0:   b8 ad 00 00 00          mov    $0xad,%eax
+ *        5:   cd 80                   int    $0x80
+ *
+ * For details, see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124050
+ */
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
 	ALIGN
 __kernel_sigreturn:
 	STARTPROC_SIGNAL_FRAME IA32_SIGFRAME_sigcontext
@@ -52,6 +81,7 @@ SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL)
 
 	.globl __kernel_rt_sigreturn
 	.type __kernel_rt_sigreturn,@function
+	nop			/* libgcc hack: see comment above */
 	ALIGN
 __kernel_rt_sigreturn:
 	STARTPROC_SIGNAL_FRAME IA32_RT_SIGFRAME_sigcontext
-- 
cgit v1.2.3


From 340cea84f691c5206561bb2e0147158fe02070be Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 4 Mar 2026 18:15:53 +0530
Subject: cifs: open files should not hold ref on superblock

Today whenever we deal with a file, in addition to holding
a reference on the dentry, we also get a reference on the
superblock. This happens in two cases:
1. when a new cinode is allocated
2. when an oplock break is being processed

The reasoning for holding the superblock ref was to make sure
that when umount happens, if there are users of inodes and
dentries, it does not try to clean them up and wait for the
last ref to superblock to be dropped by last of such users.

But the side effect of doing that is that umount silently drops
a ref on the superblock and we could have deferred closes and
lease breaks still holding these refs.

Ideally, we should ensure that all of these users of inodes and
dentries are cleaned up at the time of umount, which is what this
code is doing.

This code change allows these code paths to use a ref on the
dentry (and hence the inode). That way, umount is
ensured to clean up SMB client resources when it's the last
ref on the superblock (For ex: when same objects are shared).

The code change also moves the call to close all the files in
deferred close list to the umount code path. It also waits for
oplock_break workers to be flushed before calling
kill_anon_super (which eventually frees up those objects).

Fixes: 24261fc23db9 ("cifs: delay super block destruction until all cifsFileInfo objects are gone")
Fixes: 705c79101ccf ("smb: client: fix use-after-free in cifs_oplock_break")
Cc: <stable@vger.kernel.org>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c    |  7 +++++--
 fs/smb/client/cifsproto.h |  1 +
 fs/smb/client/file.c      | 11 -----------
 fs/smb/client/misc.c      | 42 ++++++++++++++++++++++++++++++++++++++++++
 fs/smb/client/trace.h     |  2 ++
 5 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 427558404aa5..b6e3db993cc6 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -332,10 +332,14 @@ static void cifs_kill_sb(struct super_block *sb)
 
 	/*
 	 * We need to release all dentries for the cached directories
-	 * before we kill the sb.
+	 * and close all deferred file handles before we kill the sb.
 	 */
 	if (cifs_sb->root) {
 		close_all_cached_dirs(cifs_sb);
+		cifs_close_all_deferred_files_sb(cifs_sb);
+
+		/* Wait for all pending oplock breaks to complete */
+		flush_workqueue(cifsoplockd_wq);
 
 		/* finally release root dentry */
 		dput(cifs_sb->root);
@@ -868,7 +872,6 @@ static void cifs_umount_begin(struct super_block *sb)
 	spin_unlock(&tcon->tc_lock);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	cifs_close_all_deferred_files(tcon);
 	/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
 	/* cancel_notify_requests(tcon); */
 	if (tcon->ses && tcon->ses->server) {
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 96d6b5325aa3..800a7e418c32 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -261,6 +261,7 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode);
 
 void cifs_close_all_deferred_files(struct cifs_tcon *tcon);
 
+void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb);
 void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon,
 					   struct dentry *dentry);
 
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index f3ddcdf406c8..cffcf82c1b69 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -711,8 +711,6 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	mutex_init(&cfile->fh_mutex);
 	spin_lock_init(&cfile->file_info_lock);
 
-	cifs_sb_active(inode->i_sb);
-
 	/*
 	 * If the server returned a read oplock and we have mandatory brlocks,
 	 * set oplock level to None.
@@ -767,7 +765,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
 	struct inode *inode = d_inode(cifs_file->dentry);
 	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	struct cifsLockInfo *li, *tmp;
-	struct super_block *sb = inode->i_sb;
 
 	/*
 	 * Delete any outstanding lock records. We'll lose them when the file
@@ -785,7 +782,6 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file)
 
 	cifs_put_tlink(cifs_file->tlink);
 	dput(cifs_file->dentry);
-	cifs_sb_deactive(sb);
 	kfree(cifs_file->symlink_target);
 	kfree(cifs_file);
 }
@@ -3163,12 +3159,6 @@ void cifs_oplock_break(struct work_struct *work)
 	__u64 persistent_fid, volatile_fid;
 	__u16 net_fid;
 
-	/*
-	 * Hold a reference to the superblock to prevent it and its inodes from
-	 * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put()
-	 * may release the last reference to the sb and trigger inode eviction.
-	 */
-	cifs_sb_active(sb);
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
 			TASK_UNINTERRUPTIBLE);
 
@@ -3253,7 +3243,6 @@ oplock_break_ack:
 	cifs_put_tlink(tlink);
 out:
 	cifs_done_oplock_break(cinode);
-	cifs_sb_deactive(sb);
 }
 
 static int cifs_swap_activate(struct swap_info_struct *sis,
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index bc24c92b8b95..2aff1cab6c31 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -28,6 +28,11 @@
 #include "fs_context.h"
 #include "cached_dir.h"
 
+struct tcon_list {
+	struct list_head entry;
+	struct cifs_tcon *tcon;
+};
+
 /* The xid serves as a useful identifier for each incoming vfs request,
    in a similar way to the mid which is useful to track each sent smb,
    and CurrentXid can also provide a running counter (although it
@@ -554,6 +559,43 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon)
 	}
 }
 
+void cifs_close_all_deferred_files_sb(struct cifs_sb_info *cifs_sb)
+{
+	struct rb_root *root = &cifs_sb->tlink_tree;
+	struct rb_node *node;
+	struct cifs_tcon *tcon;
+	struct tcon_link *tlink;
+	struct tcon_list *tmp_list, *q;
+	LIST_HEAD(tcon_head);
+
+	spin_lock(&cifs_sb->tlink_tree_lock);
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		tlink = rb_entry(node, struct tcon_link, tl_rbnode);
+		tcon = tlink_tcon(tlink);
+		if (IS_ERR(tcon))
+			continue;
+		tmp_list = kmalloc_obj(struct tcon_list, GFP_ATOMIC);
+		if (tmp_list == NULL)
+			break;
+		tmp_list->tcon = tcon;
+		/* Take a reference on tcon to prevent it from being freed */
+		spin_lock(&tcon->tc_lock);
+		++tcon->tc_count;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_get_close_defer_files);
+		spin_unlock(&tcon->tc_lock);
+		list_add_tail(&tmp_list->entry, &tcon_head);
+	}
+	spin_unlock(&cifs_sb->tlink_tree_lock);
+
+	list_for_each_entry_safe(tmp_list, q, &tcon_head, entry) {
+		cifs_close_all_deferred_files(tmp_list->tcon);
+		list_del(&tmp_list->entry);
+		cifs_put_tcon(tmp_list->tcon, netfs_trace_tcon_ref_put_close_defer_files);
+		kfree(tmp_list);
+	}
+}
+
 void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon,
 					   struct dentry *dentry)
 {
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 9228f95cae2b..acfbb63086ea 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -176,6 +176,7 @@
 	EM(netfs_trace_tcon_ref_get_cached_laundromat,	"GET Ch-Lau") \
 	EM(netfs_trace_tcon_ref_get_cached_lease_break,	"GET Ch-Lea") \
 	EM(netfs_trace_tcon_ref_get_cancelled_close,	"GET Cn-Cls") \
+	EM(netfs_trace_tcon_ref_get_close_defer_files,	"GET Cl-Def") \
 	EM(netfs_trace_tcon_ref_get_dfs_refer,		"GET DfsRef") \
 	EM(netfs_trace_tcon_ref_get_find,		"GET Find  ") \
 	EM(netfs_trace_tcon_ref_get_find_sess_tcon,	"GET FndSes") \
@@ -187,6 +188,7 @@
 	EM(netfs_trace_tcon_ref_put_cancelled_close,	"PUT Cn-Cls") \
 	EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \
 	EM(netfs_trace_tcon_ref_put_cancelled_mid,	"PUT Cn-Mid") \
+	EM(netfs_trace_tcon_ref_put_close_defer_files,	"PUT Cl-Def") \
 	EM(netfs_trace_tcon_ref_put_mnt_ctx,		"PUT MntCtx") \
 	EM(netfs_trace_tcon_ref_put_dfs_refer,		"PUT DfsRfr") \
 	EM(netfs_trace_tcon_ref_put_reconnect_server,	"PUT Reconn") \
-- 
cgit v1.2.3


From 0100e495cdf0436bd4ed2dc034d385b44cb5993c Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Sat, 21 Feb 2026 10:38:47 +0800
Subject: arm64: make runtime const not usable by modules

Similar as commit 284922f4c563 ("x86: uaccess: don't use runtime-const
rewriting in modules") does, make arm64's runtime const not usable by
modules too, to "make sure this doesn't get forgotten the next time
somebody wants to do runtime constant optimizations". The reason is
well explained in the above commit: "The runtime-const infrastructure
was never designed to handle the modular case, because the constant
fixup is only done at boot time for core kernel code."

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/runtime-const.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/runtime-const.h b/arch/arm64/include/asm/runtime-const.h
index be5915669d23..c3dbd3ae68f6 100644
--- a/arch/arm64/include/asm/runtime-const.h
+++ b/arch/arm64/include/asm/runtime-const.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef MODULE
+  #error "Cannot use runtime-const infrastructure from modules"
+#endif
+
 #include <asm/cacheflush.h>
 
 /* Sigh. You can still run arm64 in BE mode */
-- 
cgit v1.2.3


From 2b76e0cc7803e5ab561c875edaba7f6bbd87fbb0 Mon Sep 17 00:00:00 2001
From: Matthew Schwartz <matthew.schwartz@linux.dev>
Date: Mon, 2 Mar 2026 13:07:17 -0800
Subject: mmc: sdhci-pci-gli: fix GL9750 DMA write corruption

The GL9750 SD host controller has intermittent data corruption during
DMA write operations. The GM_BURST register's R_OSRC_Lmt field
(bits 17:16), which limits outstanding DMA read requests from system
memory, is not being cleared during initialization. The Windows driver
sets R_OSRC_Lmt to zero, limiting requests to the smallest unit.

Clear R_OSRC_Lmt to match the Windows driver behavior. This eliminates
write corruption verified with f3write/f3read tests while maintaining
DMA performance.

Cc: stable@vger.kernel.org
Fixes: e51df6ce668a ("mmc: host: sdhci-pci: Add Genesys Logic GL975x support")
Closes: https://lore.kernel.org/linux-mmc/33d12807-5c72-41ce-8679-57aa11831fad@linux.dev/
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Ben Chuang <ben.chuang@genesyslogic.com.tw>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pci-gli.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index b0f91cc9e40e..6e4084407662 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -68,6 +68,9 @@
 #define   GLI_9750_MISC_TX1_DLY_VALUE    0x5
 #define   SDHCI_GLI_9750_MISC_SSC_OFF    BIT(26)
 
+#define SDHCI_GLI_9750_GM_BURST_SIZE		  0x510
+#define   SDHCI_GLI_9750_GM_BURST_SIZE_R_OSRC_LMT  GENMASK(17, 16)
+
 #define SDHCI_GLI_9750_TUNING_CONTROL	          0x540
 #define   SDHCI_GLI_9750_TUNING_CONTROL_EN          BIT(4)
 #define   GLI_9750_TUNING_CONTROL_EN_ON             0x1
@@ -345,10 +348,16 @@ static void gli_set_9750(struct sdhci_host *host)
 	u32 misc_value;
 	u32 parameter_value;
 	u32 control_value;
+	u32 burst_value;
 	u16 ctrl2;
 
 	gl9750_wt_on(host);
 
+	/* clear R_OSRC_Lmt to avoid DMA write corruption */
+	burst_value = sdhci_readl(host, SDHCI_GLI_9750_GM_BURST_SIZE);
+	burst_value &= ~SDHCI_GLI_9750_GM_BURST_SIZE_R_OSRC_LMT;
+	sdhci_writel(host, burst_value, SDHCI_GLI_9750_GM_BURST_SIZE);
+
 	driving_value = sdhci_readl(host, SDHCI_GLI_9750_DRIVING);
 	pll_value = sdhci_readl(host, SDHCI_GLI_9750_PLL);
 	sw_ctrl_value = sdhci_readl(host, SDHCI_GLI_9750_SW_CTRL);
-- 
cgit v1.2.3


From 7a8464555d2e5f038758bb19e72ab4710b79e9cd Mon Sep 17 00:00:00 2001
From: zhidao su <soolaugust@gmail.com>
Date: Wed, 4 Mar 2026 13:37:30 +0800
Subject: sched_ext: Use WRITE_ONCE() for the write side of dsq->seq update

bpf_iter_scx_dsq_new() reads dsq->seq via READ_ONCE() without holding
any lock, making dsq->seq a lock-free concurrently accessed variable.
However, dispatch_enqueue(), the sole writer of dsq->seq, uses a plain
increment without the matching WRITE_ONCE() on the write side:

    dsq->seq++;
    ^^^^^^^^^^^
    plain write -- KCSAN data race

The KCSAN documentation requires that if one accessor uses READ_ONCE()
or WRITE_ONCE() on a variable to annotate lock-free access, all other
accesses must also use the appropriate accessor. A plain write leaves
the pair incomplete and will trigger KCSAN warnings.

Fix by using WRITE_ONCE() for the write side of the update:

    WRITE_ONCE(dsq->seq, dsq->seq + 1);

This is consistent with bpf_iter_scx_dsq_new() and makes the
concurrent access annotation complete and KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 1594987d637b..c56de568ed94 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1103,7 +1103,7 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	}
 
 	/* seq records the order tasks are queued, used by BPF DSQ iterator */
-	dsq->seq++;
+	WRITE_ONCE(dsq->seq, dsq->seq + 1);
 	p->scx.dsq_seq = dsq->seq;
 
 	dsq_mod_nr(dsq, 1);
-- 
cgit v1.2.3


From 77b310bb7b5ff8c017524df83292e0242ba89791 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Mon, 2 Feb 2026 11:13:30 -0800
Subject: cxl/region: Fix leakage in __construct_region()

Failing the first sysfs_update_group() needs to explicitly
kfree the resource as it is too early for cxl_region_iomem_release()
to do so.

Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Fixes: d6602e25819d (cxl/region: Add support to indicate region has extended linear cache)
Link: https://patch.msgid.link/20260202191330.245608-1-dave@stgolabs.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/region.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 42874948b589..c37ae0b28bbb 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -3854,8 +3854,10 @@ static int __construct_region(struct cxl_region *cxlr,
 	}
 
 	rc = sysfs_update_group(&cxlr->dev.kobj, &cxl_region_group);
-	if (rc)
+	if (rc) {
+		kfree(res);
 		return rc;
+	}
 
 	rc = insert_resource(cxlrd->res, res);
 	if (rc) {
-- 
cgit v1.2.3


From 405ca72dc589dd746e5ee5378bb9d9ee7f844010 Mon Sep 17 00:00:00 2001
From: Mickaël Salaün <mic@digikod.net>
Date: Tue, 3 Mar 2026 18:36:31 +0100
Subject: landlock: Fix formatting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Auto-format with clang-format -i security/landlock/*.[ch]

Cc: Günther Noack <gnoack@google.com>
Cc: Kees Cook <kees@kernel.org>
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Reviewed-by: Günther Noack <gnoack3000@gmail.com>
Link: https://lore.kernel.org/r/20260303173632.88040-1-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/domain.c  | 3 +--
 security/landlock/ruleset.c | 9 ++++-----
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/security/landlock/domain.c b/security/landlock/domain.c
index f5b78d4766cd..f0d83f43afa1 100644
--- a/security/landlock/domain.c
+++ b/security/landlock/domain.c
@@ -94,8 +94,7 @@ static struct landlock_details *get_current_details(void)
 	 * allocate with GFP_KERNEL_ACCOUNT because it is independent from the
 	 * caller.
 	 */
-	details =
-		kzalloc_flex(*details, exe_path, path_size);
+	details = kzalloc_flex(*details, exe_path, path_size);
 	if (!details)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
index 319873586385..73018dc8d6c7 100644
--- a/security/landlock/ruleset.c
+++ b/security/landlock/ruleset.c
@@ -32,9 +32,8 @@ static struct landlock_ruleset *create_ruleset(const u32 num_layers)
 {
 	struct landlock_ruleset *new_ruleset;
 
-	new_ruleset =
-		kzalloc_flex(*new_ruleset, access_masks, num_layers,
-			     GFP_KERNEL_ACCOUNT);
+	new_ruleset = kzalloc_flex(*new_ruleset, access_masks, num_layers,
+				   GFP_KERNEL_ACCOUNT);
 	if (!new_ruleset)
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&new_ruleset->usage, 1);
@@ -559,8 +558,8 @@ landlock_merge_ruleset(struct landlock_ruleset *const parent,
 	if (IS_ERR(new_dom))
 		return new_dom;
 
-	new_dom->hierarchy = kzalloc_obj(*new_dom->hierarchy,
-					 GFP_KERNEL_ACCOUNT);
+	new_dom->hierarchy =
+		kzalloc_obj(*new_dom->hierarchy, GFP_KERNEL_ACCOUNT);
 	if (!new_dom->hierarchy)
 		return ERR_PTR(-ENOMEM);
 
-- 
cgit v1.2.3


From 929553bbb4cdda9be22175e1adb4d5814b770855 Mon Sep 17 00:00:00 2001
From: Mickaël Salaün <mic@digikod.net>
Date: Tue, 17 Feb 2026 13:23:39 +0100
Subject: landlock: Fully release unused TSYNC work entries
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If task_work_add() failed, ctx->task is put but the tsync_works struct
is not reset to its previous state.  The first consequence is that the
kernel allocates memory for dying threads, which could lead to
user-accounted memory exhaustion (not very useful nor specific to this
case).  The second consequence is that task_work_cancel(), called by
cancel_tsync_works(), can dereference a NULL task pointer.

Fix this issues by keeping a consistent works->size wrt the added task
work.  This is done in a new tsync_works_trim() helper which also cleans
up the shared_ctx and work fields.

As a safeguard, add a pointer check to cancel_tsync_works() and update
tsync_works_release() accordingly.

Cc: Jann Horn <jannh@google.com>
Reviewed-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20260217122341.2359582-1-mic@digikod.net
[mic: Replace memset() with compound literal]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/tsync.c | 47 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c
index de01aa899751..3e44be4f66e3 100644
--- a/security/landlock/tsync.c
+++ b/security/landlock/tsync.c
@@ -203,6 +203,40 @@ static struct tsync_work *tsync_works_provide(struct tsync_works *s,
 	return ctx;
 }
 
+/**
+ * tsync_works_trim - Put the last tsync_work element
+ *
+ * @s: TSYNC works to trim.
+ *
+ * Put the last task and decrement the size of @s.
+ *
+ * This helper does not cancel a running task, but just reset the last element
+ * to zero.
+ */
+static void tsync_works_trim(struct tsync_works *s)
+{
+	struct tsync_work *ctx;
+
+	if (WARN_ON_ONCE(s->size <= 0))
+		return;
+
+	ctx = s->works[s->size - 1];
+
+	/*
+	 * For consistency, remove the task from ctx so that it does not look like
+	 * we handed it a task_work.
+	 */
+	put_task_struct(ctx->task);
+	*ctx = (typeof(*ctx)){};
+
+	/*
+	 * Cancel the tsync_works_provide() change to recycle the reserved memory
+	 * for the next thread, if any.  This also ensures that cancel_tsync_works()
+	 * and tsync_works_release() do not see any NULL task pointers.
+	 */
+	s->size--;
+}
+
 /*
  * tsync_works_grow_by - preallocates space for n more contexts in s
  *
@@ -276,7 +310,7 @@ static void tsync_works_release(struct tsync_works *s)
 	size_t i;
 
 	for (i = 0; i < s->size; i++) {
-		if (!s->works[i]->task)
+		if (WARN_ON_ONCE(!s->works[i]->task))
 			continue;
 
 		put_task_struct(s->works[i]->task);
@@ -379,16 +413,14 @@ static bool schedule_task_work(struct tsync_works *works,
 
 		init_task_work(&ctx->work, restrict_one_thread_callback);
 		err = task_work_add(thread, &ctx->work, TWA_SIGNAL);
-		if (err) {
+		if (unlikely(err)) {
 			/*
 			 * task_work_add() only fails if the task is about to exit.  We
 			 * checked that earlier, but it can happen as a race.  Resume
 			 * without setting an error, as the task is probably gone in the
-			 * next loop iteration.  For consistency, remove the task from ctx
-			 * so that it does not look like we handed it a task_work.
+			 * next loop iteration.
 			 */
-			put_task_struct(ctx->task);
-			ctx->task = NULL;
+			tsync_works_trim(works);
 
 			atomic_dec(&shared_ctx->num_preparing);
 			atomic_dec(&shared_ctx->num_unfinished);
@@ -412,6 +444,9 @@ static void cancel_tsync_works(struct tsync_works *works,
 	int i;
 
 	for (i = 0; i < works->size; i++) {
+		if (WARN_ON_ONCE(!works->works[i]->task))
+			continue;
+
 		if (!task_work_cancel(works->works[i]->task,
 				      &works->works[i]->work))
 			continue;
-- 
cgit v1.2.3


From bb8369ead40771b9550e5dbc287d6b707dd6c2b3 Mon Sep 17 00:00:00 2001
From: Mickaël Salaün <mic@digikod.net>
Date: Tue, 17 Feb 2026 13:23:40 +0100
Subject: landlock: Improve TSYNC types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Constify pointers when it makes sense.

Consistently use size_t for loops, especially to match works->size type.

Add new lines to improve readability.

Cc: Jann Horn <jannh@google.com>
Reviewed-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20260217122341.2359582-2-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/tsync.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c
index 3e44be4f66e3..1e738ef2cff5 100644
--- a/security/landlock/tsync.c
+++ b/security/landlock/tsync.c
@@ -290,13 +290,14 @@ static int tsync_works_grow_by(struct tsync_works *s, size_t n, gfp_t flags)
  * tsync_works_contains - checks for presence of task in s
  */
 static bool tsync_works_contains_task(const struct tsync_works *s,
-				      struct task_struct *task)
+				      const struct task_struct *task)
 {
 	size_t i;
 
 	for (i = 0; i < s->size; i++)
 		if (s->works[i]->task == task)
 			return true;
+
 	return false;
 }
 
@@ -318,6 +319,7 @@ static void tsync_works_release(struct tsync_works *s)
 
 	for (i = 0; i < s->capacity; i++)
 		kfree(s->works[i]);
+
 	kfree(s->works);
 	s->works = NULL;
 	s->size = 0;
@@ -329,7 +331,7 @@ static void tsync_works_release(struct tsync_works *s)
  */
 static size_t count_additional_threads(const struct tsync_works *works)
 {
-	struct task_struct *thread, *caller;
+	const struct task_struct *caller, *thread;
 	size_t n = 0;
 
 	caller = current;
@@ -368,7 +370,8 @@ static bool schedule_task_work(struct tsync_works *works,
 			       struct tsync_shared_context *shared_ctx)
 {
 	int err;
-	struct task_struct *thread, *caller;
+	const struct task_struct *caller;
+	struct task_struct *thread;
 	struct tsync_work *ctx;
 	bool found_more_threads = false;
 
@@ -438,10 +441,10 @@ static bool schedule_task_work(struct tsync_works *works,
  * shared_ctx->num_preparing and shared_ctx->num_unfished and mark the two
  * completions if needed, as if the task was never scheduled.
  */
-static void cancel_tsync_works(struct tsync_works *works,
+static void cancel_tsync_works(const struct tsync_works *works,
 			       struct tsync_shared_context *shared_ctx)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < works->size; i++) {
 		if (WARN_ON_ONCE(!works->works[i]->task))
-- 
cgit v1.2.3


From f8e2019c3bd1ea73ca25cd69a8141555243c9a11 Mon Sep 17 00:00:00 2001
From: Günther Noack <gnoack3000@gmail.com>
Date: Fri, 20 Feb 2026 17:06:27 +0100
Subject: samples/landlock: Bump ABI version to 8
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sample tool should print a warning if it is not running on a
kernel that provides the newest Landlock ABI version.

Link: https://lore.kernel.org/all/20260218.ufao5Vaefa2u@digikod.net/
Suggested-by: Mickaël Salaün <mic@digikod.net>
Signed-off-by: Günther Noack <gnoack3000@gmail.com>
Link: https://lore.kernel.org/r/20260220160627.53913-1-gnoack3000@gmail.com
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 samples/landlock/sandboxer.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c
index e7af02f98208..9f21088c0855 100644
--- a/samples/landlock/sandboxer.c
+++ b/samples/landlock/sandboxer.c
@@ -299,7 +299,7 @@ out_unset:
 
 /* clang-format on */
 
-#define LANDLOCK_ABI_LAST 7
+#define LANDLOCK_ABI_LAST 8
 
 #define XSTR(s) #s
 #define STR(s) XSTR(s)
@@ -436,7 +436,8 @@ int main(const int argc, char *const argv[], char *const *const envp)
 		/* Removes LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON for ABI < 7 */
 		supported_restrict_flags &=
 			~LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON;
-
+		__attribute__((fallthrough));
+	case 7:
 		/* Must be printed for any ABI < LANDLOCK_ABI_LAST. */
 		fprintf(stderr,
 			"Hint: You should update the running kernel "
-- 
cgit v1.2.3


From 50d7b4332f27762d24641970fc34bb68a2621926 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 23 Feb 2026 18:39:28 +0100
Subject: mm: memfd_luo: always make all folios uptodate

Patch series "mm: memfd_luo: fixes for folio flag preservation".

This series contains a couple fixes for flag preservation for memfd live
update.

The first patch fixes memfd preservation when fallocate() was used to
pre-allocate some pages.  For these memfds, all the writes to fallocated
pages touched after preserve were lost.

The second patch fixes dirty flag tracking.  If the dirty flag is not
tracked correctly, the next kernel might incorrectly reclaim some folios
under memory pressure, losing user data.  This is a theoretical bug that I
observed when reading the code, and haven't been able to reproduce it.


This patch (of 2):

When a folio is added to a shmem file via fallocate, it is not zeroed on
allocation.  This is done as a performance optimization since it is
possible the folio will never end up being used at all.  When the folio is
used, shmem checks for the uptodate flag, and if absent, zeroes the folio
(and sets the flag) before returning to user.

With LUO, the flags of each folio are saved at preserve time.  It is
possible to have a memfd with some folios fallocated but not uptodate.
For those, the uptodate flag doesn't get saved.  The folios might later
end up being used and become uptodate.  They would get passed to the next
kernel via KHO correctly since they did get preserved.  But they won't
have the MEMFD_LUO_FOLIO_UPTODATE flag.

This means that when the memfd is retrieved, the folios will be added to
the shmem file without the uptodate flag.  They will be zeroed before
first use, losing the data in those folios.

Since we take a big performance hit in allocating, zeroing, and pinning
all folios at prepare time anyway, take some more and zero all
non-uptodate ones too.

Later when there is a stronger need to make prepare faster, this can be
optimized.

To avoid racing with another uptodate operation, take the folio lock.

Link: https://lkml.kernel.org/r/20260223173931.2221759-2-pratyush@kernel.org
Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memfd_luo.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index e485b828d173..1c9510289312 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -152,10 +152,31 @@ static int memfd_luo_preserve_folios(struct file *file,
 		if (err)
 			goto err_unpreserve;
 
+		folio_lock(folio);
+
 		if (folio_test_dirty(folio))
 			flags |= MEMFD_LUO_FOLIO_DIRTY;
-		if (folio_test_uptodate(folio))
-			flags |= MEMFD_LUO_FOLIO_UPTODATE;
+
+		/*
+		 * If the folio is not uptodate, it was fallocated but never
+		 * used. Saving this flag at prepare() doesn't work since it
+		 * might change later when someone uses the folio.
+		 *
+		 * Since we have taken the performance penalty of allocating,
+		 * zeroing, and pinning all the folios in the holes, take a bit
+		 * more and zero all non-uptodate folios too.
+		 *
+		 * NOTE: For someone looking to improve preserve performance,
+		 * this is a good place to look.
+		 */
+		if (!folio_test_uptodate(folio)) {
+			folio_zero_range(folio, 0, folio_size(folio));
+			flush_dcache_folio(folio);
+			folio_mark_uptodate(folio);
+		}
+		flags |= MEMFD_LUO_FOLIO_UPTODATE;
+
+		folio_unlock(folio);
 
 		pfolio->pfn = folio_pfn(folio);
 		pfolio->flags = flags;
-- 
cgit v1.2.3


From 7e04bf1f33151a30e06a65b74b5f2c19fc2be128 Mon Sep 17 00:00:00 2001
From: "Pratyush Yadav (Google)" <pratyush@kernel.org>
Date: Mon, 23 Feb 2026 18:39:29 +0100
Subject: mm: memfd_luo: always dirty all folios

A dirty folio is one which has been written to.  A clean folio is its
opposite.  Since a clean folio has no user data, it can be freed under
memory pressure.

memfd preservation with LUO saves the flag at preserve().  This is
problematic.  The folio might get dirtied later.  Saving it at freeze()
also doesn't work, since the dirty bit from PTE is normally synced at
unmap and there might still be mappings of the file at freeze().

To see why this is a problem, say a folio is clean at preserve, but gets
dirtied later.  The serialized state of the folio will mark it as clean.
After retrieve, the next kernel will see the folio as clean and might try
to reclaim it under memory pressure.  This will result in losing user
data.

Mark all folios of the file as dirty, and always set the
MEMFD_LUO_FOLIO_DIRTY flag.  This comes with the side effect of making all
clean folios un-reclaimable.  This is a cost that has to be paid for
participants of live update.  It is not expected to be a common use case
to preserve a lot of clean folios anyway.

Since the value of pfolio->flags is a constant now, drop the flags
variable and set it directly.

Link: https://lkml.kernel.org/r/20260223173931.2221759-3-pratyush@kernel.org
Fixes: b3749f174d68 ("mm: memfd_luo: allow preserving memfd")
Signed-off-by: Pratyush Yadav (Google) <pratyush@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memfd_luo.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c
index 1c9510289312..b8edb9f981d7 100644
--- a/mm/memfd_luo.c
+++ b/mm/memfd_luo.c
@@ -146,7 +146,6 @@ static int memfd_luo_preserve_folios(struct file *file,
 	for (i = 0; i < nr_folios; i++) {
 		struct memfd_luo_folio_ser *pfolio = &folios_ser[i];
 		struct folio *folio = folios[i];
-		unsigned int flags = 0;
 
 		err = kho_preserve_folio(folio);
 		if (err)
@@ -154,8 +153,26 @@ static int memfd_luo_preserve_folios(struct file *file,
 
 		folio_lock(folio);
 
-		if (folio_test_dirty(folio))
-			flags |= MEMFD_LUO_FOLIO_DIRTY;
+		/*
+		 * A dirty folio is one which has been written to. A clean folio
+		 * is its opposite. Since a clean folio does not carry user
+		 * data, it can be freed by page reclaim under memory pressure.
+		 *
+		 * Saving the dirty flag at prepare() time doesn't work since it
+		 * can change later. Saving it at freeze() also won't work
+		 * because the dirty bit is normally synced at unmap and there
+		 * might still be a mapping of the file at freeze().
+		 *
+		 * To see why this is a problem, say a folio is clean at
+		 * preserve, but gets dirtied later. The pfolio flags will mark
+		 * it as clean. After retrieve, the next kernel might try to
+		 * reclaim this folio under memory pressure, losing user data.
+		 *
+		 * Unconditionally mark it dirty to avoid this problem. This
+		 * comes at the cost of making clean folios un-reclaimable after
+		 * live update.
+		 */
+		folio_mark_dirty(folio);
 
 		/*
 		 * If the folio is not uptodate, it was fallocated but never
@@ -174,12 +191,11 @@ static int memfd_luo_preserve_folios(struct file *file,
 			flush_dcache_folio(folio);
 			folio_mark_uptodate(folio);
 		}
-		flags |= MEMFD_LUO_FOLIO_UPTODATE;
 
 		folio_unlock(folio);
 
 		pfolio->pfn = folio_pfn(folio);
-		pfolio->flags = flags;
+		pfolio->flags = MEMFD_LUO_FOLIO_DIRTY | MEMFD_LUO_FOLIO_UPTODATE;
 		pfolio->index = folio->index;
 	}
 
-- 
cgit v1.2.3


From d210fdcac9c0d1380eab448aebc93f602c1cd4e6 Mon Sep 17 00:00:00 2001
From: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Date: Mon, 23 Feb 2026 17:10:59 -0800
Subject: mm/damon/core: clear walk_control on inactive context in damos_walk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

damos_walk() sets ctx->walk_control to the caller-provided control
structure before checking whether the context is running.  If the context
is inactive (damon_is_running() returns false), the function returns
-EINVAL without clearing ctx->walk_control.  This leaves a dangling
pointer to a stack-allocated structure that will be freed when the caller
returns.

This is structurally identical to the bug fixed in commit f9132fbc2e83
("mm/damon/core: remove call_control in inactive contexts") for
damon_call(), which had the same pattern of linking a control object and
returning an error without unlinking it.

The dangling walk_control pointer can cause:
1. Use-after-free if the context is later started and kdamond
   dereferences ctx->walk_control (e.g., in damos_walk_cancel()
   which writes to control->canceled and calls complete())
2. Permanent -EBUSY from subsequent damos_walk() calls, since the
   stale pointer is non-NULL

Nonetheless, the real user impact is quite restrictive.  The
use-after-free is impossible because there is no damos_walk() callers who
starts the context later.  The permanent -EBUSY can actually confuse
users, as DAMON is not running.  But the symptom is kept only while the
context is turned off.  Turning it on again will make DAMON internally
uses a newly generated damon_ctx object that doesn't have the invalid
damos_walk_control pointer, so everything will work fine again.

Fix this by clearing ctx->walk_control under walk_control_lock before
returning -EINVAL, mirroring the fix pattern from f9132fbc2e83.

Link: https://lkml.kernel.org/r/20260224011102.56033-1-sj@kernel.org
Fixes: bf0eaba0ff9c ("mm/damon/core: implement damos_walk()")
Reported-by: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Closes: https://lore.kernel.org/CPUPR80MB8171025468965E583EF2490F956CA@CPUPR80MB8171.lamprd80.prod.outlook.com
Signed-off-by: Raul Pazemecxas De Andrade <raul_pazemecxas@hotmail.com>
Signed-off-by: SeongJae Park <sj@kernel.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index adfc52fee9dc..c1d1091d307e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1562,8 +1562,13 @@ int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control)
 	}
 	ctx->walk_control = control;
 	mutex_unlock(&ctx->walk_control_lock);
-	if (!damon_is_running(ctx))
+	if (!damon_is_running(ctx)) {
+		mutex_lock(&ctx->walk_control_lock);
+		if (ctx->walk_control == control)
+			ctx->walk_control = NULL;
+		mutex_unlock(&ctx->walk_control_lock);
 		return -EINVAL;
+	}
 	wait_for_completion(&control->completion);
 	if (control->canceled)
 		return -ECANCELED;
-- 
cgit v1.2.3


From f4355d6bb39fc8e53d772fa0654c8441b214e349 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Tue, 24 Feb 2026 22:12:31 -0500
Subject: mm/cma: move put_page_testzero() out of VM_WARN_ON in cma_release()

When CONFIG_DEBUG_VM is not set, VM_WARN_ON is a NOP.  Putting any
statement with side effect inside it is incorrect.  Collect all
!put_page_testzero() results and check the sum using WARN instead after
the loop.  It restores the same check in free_contig_range() before commit
e0c1326779cc ("mm: page_alloc: add alloc_contig_frozen_{range,pages}()"),
the commit prior to the Fixes one.

Link: https://lkml.kernel.org/r/20260225031231.2352011-1-ziy@nvidia.com
Fixes: 9bda131c6093 ("mm: cma: add cma_alloc_frozen{_compound}()")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Ron Economos <re@w6rz.net>
Closes: https://lore.kernel.org/all/1b17c38f-30d3-4bb4-a7e1-e74b19ada885@w6rz.net/
Suggested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Debugged-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Tested-by: Ron Economos <re@w6rz.net>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/cma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/cma.c b/mm/cma.c
index 94b5da468a7d..15cc0ae76c8e 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -1013,6 +1013,7 @@ bool cma_release(struct cma *cma, const struct page *pages,
 		 unsigned long count)
 {
 	struct cma_memrange *cmr;
+	unsigned long ret = 0;
 	unsigned long i, pfn;
 
 	cmr = find_cma_memrange(cma, pages, count);
@@ -1021,7 +1022,9 @@ bool cma_release(struct cma *cma, const struct page *pages,
 
 	pfn = page_to_pfn(pages);
 	for (i = 0; i < count; i++, pfn++)
-		VM_WARN_ON(!put_page_testzero(pfn_to_page(pfn)));
+		ret += !put_page_testzero(pfn_to_page(pfn));
+
+	WARN(ret, "%lu pages are still in use!\n", ret);
 
 	__cma_release_frozen(cma, cmr, pages, count);
 
-- 
cgit v1.2.3


From 2d28ed588f8d7d0d41b0a4fad7f0d05e4bbf1797 Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Tue, 24 Feb 2026 16:24:34 -0800
Subject: Revert "ptdesc: remove references to folios from __pagetable_ctor()
 and pagetable_dtor()"

This change swapped out mod_node_page_state for lruvec_stat_add_folio.
But, these two APIs are not interchangeable: the lruvec version also
increments memcg stats, in addition to "global" pgdat stats.

So after this change, the "pagetables" memcg stat in memory.stat always
yields "0", which is a userspace visible regression.

I tried to look for a refactor where we add a variant of
lruvec_stat_mod_folio which takes a pgdat and a memcg instead of a folio,
to try to adhere to the spirit of the original patch.  But at the end of
the day this just means we have to call folio_memcg(ptdesc_folio(ptdesc))
anyway, which doesn't really accomplish much.

This regression is visible in master as well as 6.18 stable, so CC stable
too.

Link: https://lkml.kernel.org/r/20260225002434.2953895-1-axelrasmussen@google.com
Fixes: f0c92726e89f ("ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()")
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5be3d8a8f806..abb4963c1f06 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
 #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
-static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
-{
-	return compound_nr(ptdesc_page(ptdesc));
-}
-
 static inline void __pagetable_ctor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
-	__SetPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
+	__folio_set_pgtable(folio);
+	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
-	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct folio *folio = ptdesc_folio(ptdesc);
 
 	ptlock_free(ptdesc);
-	__ClearPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
+	__folio_clear_pgtable(folio);
+	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
 static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
-- 
cgit v1.2.3


From 5548dd7fa84510f7bbce67c35cc3b388c86aeddf Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Thu, 26 Feb 2026 01:31:11 +0200
Subject: tools/testing: fix testing/vma and testing/radix-tree build

Build of VMA and radix-tree tests is unhappy after the conversion of
kzalloc() to kzalloc_obj() in lib/idr.c:

  cc -I../shared -I. -I../../include -I../../arch/x86/include -I../../../lib -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined  -DNUM_VMA_FLAG_BITS=128 -DNUM_MM_FLAG_BITS=128   -c -o idr.o idr.c
  idr.c: In function `ida_alloc_range':
  idr.c:420:34: error: implicit declaration of function `kzalloc_obj'; did you mean `kzalloc_node'? [-Wimplicit-function-declaration]
    420 |                         bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                  ^~~~~~~~~~~
        |                                  kzalloc_node
  idr.c:420:32: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    420 |                         bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                ^
  idr.c:447:40: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    447 |                                 bitmap = kzalloc_obj(*bitmap, GFP_NOWAIT);
        |                                        ^
  idr.c:468:15: error: assignment to `struct ida_bitmap *' from `int' makes pointer from integer without a cast [-Wint-conversion]
    468 |         alloc = kzalloc_obj(*bitmap, gfp);
        |               ^
  make: *** [<builtin>: idr.o] Error 1

Import necessary macros from include/linux to tools/include/linux to fix
the compilation.

Link: https://lkml.kernel.org/r/20260225233111.2760752-1-rppt@kernel.org
Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/linux/gfp.h      |  4 ++++
 tools/include/linux/overflow.h | 19 +++++++++++++++++++
 tools/include/linux/slab.h     |  9 +++++++++
 3 files changed, 32 insertions(+)

diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h
index 6a10ff5f5be9..9e957b57b694 100644
--- a/tools/include/linux/gfp.h
+++ b/tools/include/linux/gfp.h
@@ -5,6 +5,10 @@
 #include <linux/types.h>
 #include <linux/gfp_types.h>
 
+/* Helper macro to avoid gfp flags if they are the default one */
+#define __default_gfp(a,...) a
+#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL)
+
 static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 {
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
index dcb0c1bf6866..3427d7880326 100644
--- a/tools/include/linux/overflow.h
+++ b/tools/include/linux/overflow.h
@@ -68,6 +68,25 @@
 	__builtin_mul_overflow(__a, __b, __d);	\
 })
 
+/**
+ * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX
+ * @factor1: first factor
+ * @factor2: second factor
+ *
+ * Returns: calculate @factor1 * @factor2, both promoted to size_t,
+ * with any overflow causing the return value to be SIZE_MAX. The
+ * lvalue must be size_t to avoid implicit type conversion.
+ */
+static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(factor1, factor2, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
 /**
  * array_size() - Calculate size of 2-dimensional array.
  *
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
index 94937a699402..6d8e9413d5a4 100644
--- a/tools/include/linux/slab.h
+++ b/tools/include/linux/slab.h
@@ -202,4 +202,13 @@ static inline unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf)
 	return sheaf->size;
 }
 
+#define __alloc_objs(KMALLOC, GFP, TYPE, COUNT)				\
+({									\
+	const size_t __obj_size = size_mul(sizeof(TYPE), COUNT);	\
+	(TYPE *)KMALLOC(__obj_size, GFP);				\
+})
+
+#define kzalloc_obj(P, ...) \
+	__alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1)
+
 #endif		/* _TOOLS_SLAB_H */
-- 
cgit v1.2.3


From ba4c3698e6963eacd8e7c86c13343631bfeabe55 Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Thu, 26 Feb 2026 11:54:21 +0900
Subject: zram: rename writeback_compressed device attr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename writeback_compressed attr to compressed_writeback to avoid possible
confusion and have more natural naming.  writeback_compressed may look
like an alternative version of writeback while in fact
writeback_compressed only sets a writeback property.  Make this
distinction more clear with a new compressed_writeback name.

This updates a feature which is new in 7.0-rcX.

Link: https://lkml.kernel.org/r/20260226025429.1042083-1-senozhatsky@chromium.org
Fixes: 4c1d61389e8e ("zram: introduce writeback_compressed device attribute")
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Suggested-by: Minchan Kim <minchan@kernel.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-block-zram  |  4 ++--
 Documentation/admin-guide/blockdev/zram.rst |  6 +++---
 drivers/block/zram/zram_drv.c               | 24 ++++++++++++------------
 drivers/block/zram/zram_drv.h               |  2 +-
 4 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index e538d4850d61..64c03010e951 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -151,11 +151,11 @@ Description:
 		The algorithm_params file is write-only and is used to setup
 		compression algorithm parameters.
 
-What:		/sys/block/zram<id>/writeback_compressed
+What:		/sys/block/zram<id>/compressed_writeback
 Date:		Decemeber 2025
 Contact:	Richard Chang <richardycc@google.com>
 Description:
-		The writeback_compressed device atrribute toggles compressed
+		The compressed_writeback device atrribute toggles compressed
 		writeback feature.
 
 What:		/sys/block/zram<id>/writeback_batch_size
diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst
index 94bb7f2245ee..451fa00d3004 100644
--- a/Documentation/admin-guide/blockdev/zram.rst
+++ b/Documentation/admin-guide/blockdev/zram.rst
@@ -216,7 +216,7 @@ writeback_limit   	WO	specifies the maximum amount of write IO zram
 writeback_limit_enable  RW	show and set writeback_limit feature
 writeback_batch_size	RW	show and set maximum number of in-flight
 				writeback operations
-writeback_compressed	RW	show and set compressed writeback feature
+compressed_writeback	RW	show and set compressed writeback feature
 comp_algorithm    	RW	show and change the compression algorithm
 algorithm_params	WO	setup compression algorithm parameters
 compact           	WO	trigger memory compaction
@@ -439,11 +439,11 @@ budget in next setting is user's job.
 By default zram stores written back pages in decompressed (raw) form, which
 means that writeback operation involves decompression of the page before
 writing it to the backing device.  This behavior can be changed by enabling
-`writeback_compressed` feature, which causes zram to write compressed pages
+`compressed_writeback` feature, which causes zram to write compressed pages
 to the backing device, thus avoiding decompression overhead.  To enable
 this feature, execute::
 
-	$ echo yes > /sys/block/zramX/writeback_compressed
+	$ echo yes > /sys/block/zramX/compressed_writeback
 
 Note that this feature should be configured before the `zramX` device is
 initialized.
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index bca33403fc8b..a324ede6206d 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -549,7 +549,7 @@ static ssize_t bd_stat_show(struct device *dev, struct device_attribute *attr,
 	return ret;
 }
 
-static ssize_t writeback_compressed_store(struct device *dev,
+static ssize_t compressed_writeback_store(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t len)
 {
@@ -564,12 +564,12 @@ static ssize_t writeback_compressed_store(struct device *dev,
 		return -EBUSY;
 	}
 
-	zram->wb_compressed = val;
+	zram->compressed_wb = val;
 
 	return len;
 }
 
-static ssize_t writeback_compressed_show(struct device *dev,
+static ssize_t compressed_writeback_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
@@ -577,7 +577,7 @@ static ssize_t writeback_compressed_show(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 
 	guard(rwsem_read)(&zram->dev_lock);
-	val = zram->wb_compressed;
+	val = zram->compressed_wb;
 
 	return sysfs_emit(buf, "%d\n", val);
 }
@@ -946,7 +946,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 		goto out;
 	}
 
-	if (zram->wb_compressed) {
+	if (zram->compressed_wb) {
 		/*
 		 * ZRAM_WB slots get freed, we need to preserve data required
 		 * for read decompression.
@@ -960,7 +960,7 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 	set_slot_flag(zram, index, ZRAM_WB);
 	set_slot_handle(zram, index, req->blk_idx);
 
-	if (zram->wb_compressed) {
+	if (zram->compressed_wb) {
 		if (huge)
 			set_slot_flag(zram, index, ZRAM_HUGE);
 		set_slot_size(zram, index, size);
@@ -1100,7 +1100,7 @@ static int zram_writeback_slots(struct zram *zram,
 		 */
 		if (!test_slot_flag(zram, index, ZRAM_PP_SLOT))
 			goto next;
-		if (zram->wb_compressed)
+		if (zram->compressed_wb)
 			err = read_from_zspool_raw(zram, req->page, index);
 		else
 			err = read_from_zspool(zram, req->page, index);
@@ -1429,7 +1429,7 @@ static void zram_async_read_endio(struct bio *bio)
 	 *
 	 * Keep the existing behavior for now.
 	 */
-	if (zram->wb_compressed == false) {
+	if (zram->compressed_wb == false) {
 		/* No decompression needed, complete the parent IO */
 		bio_endio(req->parent);
 		bio_put(bio);
@@ -1508,7 +1508,7 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page, u32 index,
 	flush_work(&req.work);
 	destroy_work_on_stack(&req.work);
 
-	if (req.error || zram->wb_compressed == false)
+	if (req.error || zram->compressed_wb == false)
 		return req.error;
 
 	return decompress_bdev_page(zram, page, index);
@@ -3007,7 +3007,7 @@ static DEVICE_ATTR_WO(writeback);
 static DEVICE_ATTR_RW(writeback_limit);
 static DEVICE_ATTR_RW(writeback_limit_enable);
 static DEVICE_ATTR_RW(writeback_batch_size);
-static DEVICE_ATTR_RW(writeback_compressed);
+static DEVICE_ATTR_RW(compressed_writeback);
 #endif
 #ifdef CONFIG_ZRAM_MULTI_COMP
 static DEVICE_ATTR_RW(recomp_algorithm);
@@ -3031,7 +3031,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_writeback_limit.attr,
 	&dev_attr_writeback_limit_enable.attr,
 	&dev_attr_writeback_batch_size.attr,
-	&dev_attr_writeback_compressed.attr,
+	&dev_attr_compressed_writeback.attr,
 #endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,
@@ -3091,7 +3091,7 @@ static int zram_add(void)
 	init_rwsem(&zram->dev_lock);
 #ifdef CONFIG_ZRAM_WRITEBACK
 	zram->wb_batch_size = 32;
-	zram->wb_compressed = false;
+	zram->compressed_wb = false;
 #endif
 
 	/* gendisk structure */
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 515a72d9c06f..f0de8f8218f5 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -133,7 +133,7 @@ struct zram {
 #ifdef CONFIG_ZRAM_WRITEBACK
 	struct file *backing_dev;
 	bool wb_limit_enable;
-	bool wb_compressed;
+	bool compressed_wb;
 	u32 wb_batch_size;
 	u64 bd_wb_limit;
 	struct block_device *bdev;
-- 
cgit v1.2.3


From a1e59fc6ee4ed8988ea4aeb9224e75d03175be9c Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Thu, 26 Feb 2026 17:56:30 +0530
Subject: mm/hugetlb.c: use __pa() instead of virt_to_phys() in early bootmem
 alloc code

Architecture like powerpc, checks for pfn_valid() in their virt_to_phys()
implementation (when CONFIG_DEBUG_VIRTUAL is enabled) [1].  Commit
d49004c5f0c1 "arch, mm: consolidate initialization of nodes, zones and
memory map" changed the order of initialization between
hugetlb_bootmem_alloc() and free_area_init().  This means, pfn_valid() can
now return false in alloc_bootmem() path, since sparse_init() is not yet
done.

Since, alloc_bootmem() uses memblock_alloc(.., MEMBLOCK_ALLOC_ACCESSIBLE),
this means these allocations are always going to happen below high_memory,
where __pa() should return valid physical addresses.  Hence this patch
converts the two callers of virt_to_phys() in alloc_bootmem() path to
__pa() to avoid this bootup warning:

 ------------[ cut here ]------------
 WARNING: arch/powerpc/include/asm/io.h:879 at virt_to_phys+0x44/0x1b8, CPU#0: swapper/0
 Modules linked in:
 <...>
 NIP [c000000000601584] virt_to_phys+0x44/0x1b8
 LR [c000000004075de4] alloc_bootmem+0x144/0x1a8
 Call Trace:
 [c000000004d1fb50] [c000000004075dd4] alloc_bootmem+0x134/0x1a8
 [c000000004d1fba0] [c000000004075fac] __alloc_bootmem_huge_page+0x164/0x230
 [c000000004d1fbe0] [c000000004030bc4] alloc_bootmem_huge_page+0x44/0x138
 [c000000004d1fc10] [c000000004076e48] hugetlb_hstate_alloc_pages+0x350/0x5ac
 [c000000004d1fd30] [c0000000040782f0] hugetlb_bootmem_alloc+0x15c/0x19c
 [c000000004d1fd70] [c00000000406d7b4] mm_core_init_early+0x7c/0xdf4
 [c000000004d1ff30] [c000000004011d84] start_kernel+0xac/0xc58
 [c000000004d1ffe0] [c00000000000e99c] start_here_common+0x1c/0x20

[1]: https://lore.kernel.org/linuxppc-dev/87tsv5h544.ritesh.list@gmail.com/

Link: https://lkml.kernel.org/r/b4a7d2c6c4c1dd81dddc904fc21f01303290a4b8.1772107852.git.riteshh@linux.ibm.com
Fixes: d49004c5f0c1 ("arch, mm: consolidate initialization of nodes, zones and memory map")
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0beb6e22bc26..327eaa4074d3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3101,7 +3101,7 @@ static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact)
 			 * extract the actual node first.
 			 */
 			if (m)
-				listnode = early_pfn_to_nid(PHYS_PFN(virt_to_phys(m)));
+				listnode = early_pfn_to_nid(PHYS_PFN(__pa(m)));
 		}
 
 		if (m) {
@@ -3160,7 +3160,7 @@ found:
 	 * The head struct page is used to get folio information by the HugeTLB
 	 * subsystem like zone id and node id.
 	 */
-	memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE),
+	memblock_reserved_mark_noinit(__pa((void *)m + PAGE_SIZE),
 		huge_page_size(h) - PAGE_SIZE);
 
 	return 1;
-- 
cgit v1.2.3


From dccd5ee2625d50239510bcd73ed78559005e00a3 Mon Sep 17 00:00:00 2001
From: Hao Li <hao.li@linux.dev>
Date: Thu, 26 Feb 2026 19:51:37 +0800
Subject: memcg: fix slab accounting in refill_obj_stock() trylock path

In the trylock path of refill_obj_stock(), mod_objcg_mlstate() should use
the real alloc/free bytes (i.e., nr_acct) for accounting, rather than
nr_bytes.

The user-visible impact is that the NR_SLAB_RECLAIMABLE_B and
NR_SLAB_UNRECLAIMABLE_B stats can end up being incorrect.

For example, if a user allocates a 6144-byte object, then before this
fix efill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=2048), even
though it should account for 6144 bytes (i.e., nr_acct).

When the user later frees the same object with kfree(),
refill_obj_stock() calls mod_objcg_mlstate(..., nr_bytes=6144).  This
ends up adding 6144 to the stats, but it should be applying -6144
(i.e., nr_acct) since the object is being freed.

Link: https://lkml.kernel.org/r/20260226115145.62903-1-hao.li@linux.dev
Fixes: 200577f69f29 ("memcg: objcg stock trylock without irq disabling")
Signed-off-by: Hao Li <hao.li@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a52da3a5e4fd..772bac21d155 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3086,7 +3086,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 
 	if (!local_trylock(&obj_stock.lock)) {
 		if (pgdat)
-			mod_objcg_mlstate(objcg, pgdat, idx, nr_bytes);
+			mod_objcg_mlstate(objcg, pgdat, idx, nr_acct);
 		nr_pages = nr_bytes >> PAGE_SHIFT;
 		nr_bytes = nr_bytes & (PAGE_SIZE - 1);
 		atomic_add(nr_bytes, &objcg->nr_charged_bytes);
-- 
cgit v1.2.3


From 06de173b138513087896f9cf090f30b35846518d Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Sun, 1 Mar 2026 10:09:02 +0800
Subject: MAINTAINERS: add RELAY entry

RELAYFS was originally developed by Tom Zanussi and Karim Yaghmour in
2005[1].  Jens Axboe converted it from filesystem into a generic API in
2006[2] and made it widely known through the notable I/O tracing tool
blktrace.  In the decade, there remain a few users scatterred across
different subsystems, like recently added wifi commit[3] that is an
example to show how to communicate between users and kernel.  Last year
I've already done some maintenance and added/corrected some diagnostic
counters.

At Tencent, we internally maintain RELAY as one of most crucial components
of network observibility platform which was shared a bit at LPC 2025[4][5]
and hopefully will be published in the paper this year.  RELAY has proven
highly efficient due to its inherent design essence.  This design becomes
the indispensable way to build a 7x24 platform monitoring various hot
paths even without any selectively sampling (yes, sampling is commonly
used to avoid the overall performance degradation).  One of the
recommended usages is to use its zerocopy function relay_reserve() to
transfer data in a raw format that can be recognized and parsed by the
corresponding application to userspace without introducing heavy locks and
complicated logic that appears in other types of approaches, like printk.
More details can be discovered by reading through the Documentation :)

Credits are given to the all the contributors and reviewers for
RELAY/RELAYFS in the past and future! Many thanks!

[1]: commit e82894f84dbb ("[PATCH] relayfs")
[2]: commit b86ff981a825 ("[PATCH] relay: migrate from relayfs to a generic relay API")
[3]: commit c1bf6959dd81 ("wifi: ath11k: Register relayfs entries for CFR dump")
[4]: https://lpc.events/event/19/contributions/2055/
[5]: https://lpc.events/event/19/contributions/2010/

Link: https://lkml.kernel.org/r/20260301020902.56476-1-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Jens Axboe <axboe@kernel.dk>
Cc: Andriy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Tom Zanussi <zanussi@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e4572a36afd2..0ecf11bab619 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22284,6 +22284,16 @@ L:	linux-wireless@vger.kernel.org
 S:	Orphan
 F:	drivers/net/wireless/rsi/
 
+RELAY
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Jens Axboe <axboe@kernel.dk>
+M:	Jason Xing <kernelxing@tencent.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	Documentation/filesystems/relay.rst
+F:	include/linux/relay.h
+F:	kernel/relay.c
+
 REGISTER MAP ABSTRACTION
 M:	Mark Brown <broonie@kernel.org>
 L:	linux-kernel@vger.kernel.org
-- 
cgit v1.2.3


From 431b04f0084d244569e81ca4216a40644b23b0c5 Mon Sep 17 00:00:00 2001
From: "Vlastimil Babka (SUSE)" <vbabka@kernel.org>
Date: Mon, 2 Mar 2026 11:13:46 +0100
Subject: MAINTAINERS: add co-maintainer and reviewer for SLAB ALLOCATOR

Promote Harry Yoo from reviewer to maintainer.  Harry's been involved in
slab development for multiple years now and doing a great job.

Add Hao Li as a new reviewer.  Hao has been doing very useful reviews for
a while now, so make it official and ensure the Cc's.

Link: https://lkml.kernel.org/r/20260302101345.36713-2-vbabka@kernel.org
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: Hao Li <hao.li@linux.dev>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0ecf11bab619..e510fbc6f882 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24361,11 +24361,12 @@ F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
 M:	Vlastimil Babka <vbabka@kernel.org>
+M:	Harry Yoo <harry.yoo@oracle.com>
 M:	Andrew Morton <akpm@linux-foundation.org>
+R:	Hao Li <hao.li@linux.dev>
 R:	Christoph Lameter <cl@gentwo.org>
 R:	David Rientjes <rientjes@google.com>
 R:	Roman Gushchin <roman.gushchin@linux.dev>
-R:	Harry Yoo <harry.yoo@oracle.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git
-- 
cgit v1.2.3


From 577a1f495fd78d8fb61b67ac3d3b595b01f6fcb0 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 2 Mar 2026 15:31:59 -0500
Subject: mm/huge_memory: fix a folio_split() race condition with
 folio_try_get()

During a pagecache folio split, the values in the related xarray should
not be changed from the original folio at xarray split time until all
after-split folios are well formed and stored in the xarray.  Current use
of xas_try_split() in __split_unmapped_folio() lets some after-split
folios show up at wrong indices in the xarray.  When these misplaced
after-split folios are unfrozen, before correct folios are stored via
__xa_store(), and grabbed by folio_try_get(), they are returned to
userspace at wrong file indices, causing data corruption.  More detailed
explanation is at the bottom.

The reproducer is at: https://github.com/dfinity/thp-madv-remove-test
It
1. creates a memfd,
2. forks,
3. in the child process, maps the file with large folios (via shmem code
   path) and reads the mapped file continuously with 16 threads,
4. in the parent process, uses madvise(MADV_REMOVE) to punch poles in the
   large folio.

Data corruption can be observed without the fix.  Basically, data from a
wrong page->index is returned.

Fix it by using the original folio in xas_try_split() calls, so that
folio_try_get() can get the right after-split folios after the original
folio is unfrozen.

Uniform split, split_huge_page*(), is not affected, since it uses
xas_split_alloc() and xas_split() only once and stores the original folio
in the xarray.  Change xas_split() used in uniform split branch to use the
original folio to avoid confusion.

Fixes below points to the commit introduces the code, but folio_split() is
used in a later commit 7460b470a131f ("mm/truncate: use folio_split() in
truncate operation").

More details:

For example, a folio f is split non-uniformly into f, f2, f3, f4 like
below:
+----------------+---------+----+----+
|       f        |    f2   | f3 | f4 |
+----------------+---------+----+----+
but the xarray would look like below after __split_unmapped_folio() is
done:
+----------------+---------+----+----+
|       f        |    f2   | f3 | f3 |
+----------------+---------+----+----+

After __split_unmapped_folio(), the code changes the xarray and unfreezes
after-split folios:

1. unfreezes f2, __xa_store(f2)
2. unfreezes f3, __xa_store(f3)
3. unfreezes f4, __xa_store(f4), which overwrites the second f3 to f4.
4. unfreezes f.

Meanwhile, a parallel filemap_get_entry() can read the second f3 from the
xarray and use folio_try_get() on it at step 2 when f3 is unfrozen. Then,
f3 is wrongly returned to user.

After the fix, the xarray looks like below after __split_unmapped_folio():
+----------------+---------+----+----+
|       f        |    f    | f  | f  |
+----------------+---------+----+----+
so that the race window no longer exists.

[ziy@nvidia.com: move comment, per David]
  Link: https://lkml.kernel.org/r/5C9FA053-A4C6-4615-BE05-74E47A6462B3@nvidia.com
Link: https://lkml.kernel.org/r/20260302203159.3208341-1-ziy@nvidia.com
Fixes: 00527733d0dc ("mm/huge_memory: add two new (not yet used) functions for folio_split()")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Bas van Dijk <bas@dfinity.org>
Closes: https://lore.kernel.org/all/CAKNNEtw5_kZomhkugedKMPOG-sxs5Q5OLumWJdiWXv+C9Yct0w@mail.gmail.com/
Tested-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8e2746ea74ad..912c248a3f7e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3631,6 +3631,7 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 	const bool is_anon = folio_test_anon(folio);
 	int old_order = folio_order(folio);
 	int start_order = split_type == SPLIT_TYPE_UNIFORM ? new_order : old_order - 1;
+	struct folio *old_folio = folio;
 	int split_order;
 
 	/*
@@ -3651,12 +3652,16 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 			 * uniform split has xas_split_alloc() called before
 			 * irq is disabled to allocate enough memory, whereas
 			 * non-uniform split can handle ENOMEM.
+			 * Use the to-be-split folio, so that a parallel
+			 * folio_try_get() waits on it until xarray is updated
+			 * with after-split folios and the original one is
+			 * unfrozen.
 			 */
-			if (split_type == SPLIT_TYPE_UNIFORM)
-				xas_split(xas, folio, old_order);
-			else {
+			if (split_type == SPLIT_TYPE_UNIFORM) {
+				xas_split(xas, old_folio, old_order);
+			} else {
 				xas_set_order(xas, folio->index, split_order);
-				xas_try_split(xas, folio, old_order);
+				xas_try_split(xas, old_folio, old_order);
 				if (xas_error(xas))
 					return xas_error(xas);
 			}
-- 
cgit v1.2.3


From 7392f8e4ea632622b2cd2086675ba022db238b3a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:52:29 -0800
Subject: uaccess: correct kernel-doc parameter format

Use the correct kernel-doc function parameter format to avoid kernel-doc
warnings:

Warning: include/linux/uaccess.h:814 function parameter 'uptr' not
 described in 'scoped_user_rw_access_size'
Warning: include/linux/uaccess.h:826 function parameter 'uptr' not
 described in 'scoped_user_rw_access'

Link: https://lkml.kernel.org/r/20260302005229.3471955-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/uaccess.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1f3804245c06..001cfef21b61 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -806,7 +806,7 @@ for (bool done = false; !done; done = true)						\
 
 /**
  * scoped_user_rw_access_size - Start a scoped user read/write access with given size
- * @uptr	Pointer to the user space address to read from and write to
+ * @uptr:	Pointer to the user space address to read from and write to
  * @size:	Size of the access starting from @uptr
  * @elbl:	Error label to goto when the access region is rejected
  *
@@ -817,7 +817,7 @@ for (bool done = false; !done; done = true)						\
 
 /**
  * scoped_user_rw_access - Start a scoped user read/write access
- * @uptr	Pointer to the user space address to read from and write to
+ * @uptr:	Pointer to the user space address to read from and write to
  * @elbl:	Error label to goto when the access region is rejected
  *
  * The size of the access starting from @uptr is determined via sizeof(*@uptr)).
-- 
cgit v1.2.3


From 599b4e290c8766b19378d85d4310c6ec8f90ade4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:52:22 -0800
Subject: mm/mmu_notifier: clean up mmu_notifier.h kernel-doc

Eliminate kernel-doc warnings in mmu_notifier.h:
- add a missing struct short description
- use the correct format for function parameters
- add missing function return comment sections

Warning: include/linux/mmu_notifier.h:236 missing initial short
 description on line: * struct mmu_interval_notifier_ops
Warning: include/linux/mmu_notifier.h:325 function parameter 'interval_sub'
 not described in 'mmu_interval_set_seq'
Warning: include/linux/mmu_notifier.h:325 function parameter 'cur_seq'
 not described in 'mmu_interval_set_seq'
Warning: include/linux/mmu_notifier.h:346 function parameter 'interval_sub'
 not described in 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:346 function parameter 'seq' not
 described in 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:346 No description found for return
 value of 'mmu_interval_read_retry'
Warning: include/linux/mmu_notifier.h:370 function parameter 'interval_sub'
 not described in 'mmu_interval_check_retry'
Warning: include/linux/mmu_notifier.h:370 function parameter 'seq' not
 described in 'mmu_interval_check_retry'
Warning: include/linux/mmu_notifier.h:370 No description found for return
 value of 'mmu_interval_check_retry'

Link: https://lkml.kernel.org/r/20260302005222.3470783-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmu_notifier.h | 31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 07a2bbaf86e9..8450e18a87c2 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -234,7 +234,7 @@ struct mmu_notifier {
 };
 
 /**
- * struct mmu_interval_notifier_ops
+ * struct mmu_interval_notifier_ops - callback for range notification
  * @invalidate: Upon return the caller must stop using any SPTEs within this
  *              range. This function can sleep. Return false only if sleeping
  *              was required but mmu_notifier_range_blockable(range) is false.
@@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub);
 
 /**
  * mmu_interval_set_seq - Save the invalidation sequence
- * @interval_sub - The subscription passed to invalidate
- * @cur_seq - The cur_seq passed to the invalidate() callback
+ * @interval_sub: The subscription passed to invalidate
+ * @cur_seq: The cur_seq passed to the invalidate() callback
  *
  * This must be called unconditionally from the invalidate callback of a
  * struct mmu_interval_notifier_ops under the same lock that is used to call
@@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_read_retry - End a read side critical section against a VA range
- * interval_sub: The subscription
- * seq: The return of the paired mmu_interval_read_begin()
+ * @interval_sub: The subscription
+ * @seq: The return of the paired mmu_interval_read_begin()
  *
  * This MUST be called under a user provided lock that is also held
  * unconditionally by op->invalidate() when it calls mmu_interval_set_seq().
@@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
  * Each call should be paired with a single mmu_interval_read_begin() and
  * should be used to conclude the read side.
  *
- * Returns true if an invalidation collided with this critical section, and
+ * Returns: true if an invalidation collided with this critical section, and
  * the caller should retry.
  */
 static inline bool
@@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub,
 
 /**
  * mmu_interval_check_retry - Test if a collision has occurred
- * interval_sub: The subscription
- * seq: The return of the matching mmu_interval_read_begin()
+ * @interval_sub: The subscription
+ * @seq: The return of the matching mmu_interval_read_begin()
  *
  * This can be used in the critical section between mmu_interval_read_begin()
- * and mmu_interval_read_retry().  A return of true indicates an invalidation
- * has collided with this critical region and a future
- * mmu_interval_read_retry() will return true.
- *
- * False is not reliable and only suggests a collision may not have
- * occurred. It can be called many times and does not have to hold the user
- * provided lock.
+ * and mmu_interval_read_retry().
  *
  * This call can be used as part of loops and other expensive operations to
  * expedite a retry.
+ * It can be called many times and does not have to hold the user
+ * provided lock.
+ *
+ * Returns: true indicates an invalidation has collided with this critical
+ * region and a future mmu_interval_read_retry() will return true.
+ * False is not reliable and only suggests a collision may not have
+ * occurred.
  */
 static inline bool
 mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub,
-- 
cgit v1.2.3


From b12bbe35c7c1e431f2fa01fe9291daa52fb7ab43 Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Date: Tue, 3 Mar 2026 19:50:25 +0000
Subject: MAINTAINERS, mailmap: update email address for Lorenzo Stoakes

I want to experiment with a new email setup, and using the @kernel.org
address is the easiest way to have flexibility on this.

Link: https://lkml.kernel.org/r/20260303195025.1170895-1-ljs@kernel.org
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    |  3 ++-
 MAINTAINERS | 20 ++++++++++----------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/.mailmap b/.mailmap
index c124a1306d26..fd062abdb133 100644
--- a/.mailmap
+++ b/.mailmap
@@ -491,7 +491,8 @@ Lior David <quic_liord@quicinc.com> <liord@codeaurora.org>
 Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@linaro.org>
 Loic Poulain <loic.poulain@oss.qualcomm.com> <loic.poulain@intel.com>
 Lorenzo Pieralisi <lpieralisi@kernel.org> <lorenzo.pieralisi@arm.com>
-Lorenzo Stoakes <lorenzo.stoakes@oracle.com> <lstoakes@gmail.com>
+Lorenzo Stoakes <ljs@kernel.org> <lstoakes@gmail.com>
+Lorenzo Stoakes <ljs@kernel.org> <lorenzo.stoakes@oracle.com>
 Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net>
 Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz>
 Lucas De Marchi <demarchi@kernel.org> <lucas.demarchi@intel.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index e510fbc6f882..a3b4e75ad1ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16654,7 +16654,7 @@ F:	mm/balloon.c
 MEMORY MANAGEMENT - CORE
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
@@ -16784,7 +16784,7 @@ F:	mm/workingset.c
 MEMORY MANAGEMENT - MISC
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Mike Rapoport <rppt@kernel.org>
@@ -16875,7 +16875,7 @@ R:	David Hildenbrand <david@kernel.org>
 R:	Michal Hocko <mhocko@kernel.org>
 R:	Qi Zheng <zhengqi.arch@bytedance.com>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/vmscan.c
@@ -16884,7 +16884,7 @@ F:	mm/workingset.c
 MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
@@ -16929,7 +16929,7 @@ F:	mm/swapfile.c
 MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@kernel.org>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Zi Yan <ziy@nvidia.com>
 R:	Baolin Wang <baolin.wang@linux.alibaba.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
@@ -16969,7 +16969,7 @@ F:	tools/testing/selftests/mm/uffd-*.[ch]
 
 MEMORY MANAGEMENT - RUST
 M:	Alice Ryhl <aliceryhl@google.com>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 L:	linux-mm@kvack.org
 L:	rust-for-linux@vger.kernel.org
@@ -16985,7 +16985,7 @@ F:	rust/kernel/page.rs
 MEMORY MAPPING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
 R:	Pedro Falcato <pfalcato@suse.de>
@@ -17015,7 +17015,7 @@ MEMORY MAPPING - LOCKING
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Suren Baghdasaryan <surenb@google.com>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Shakeel Butt <shakeel.butt@linux.dev>
 L:	linux-mm@kvack.org
@@ -17030,7 +17030,7 @@ F:	mm/mmap_lock.c
 MEMORY MAPPING - MADVISE (MEMORY ADVICE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+M:	Lorenzo Stoakes <ljs@kernel.org>
 M:	David Hildenbrand <david@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Jann Horn <jannh@google.com>
@@ -23183,7 +23183,7 @@ K:	\b(?i:rust)\b
 
 RUST [ALLOC]
 M:	Danilo Krummrich <dakr@kernel.org>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
+R:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Vlastimil Babka <vbabka@kernel.org>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Uladzislau Rezki <urezki@gmail.com>
-- 
cgit v1.2.3


From 68785c5e79e0fc1eacf63026fbba32be3867f410 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Wed, 25 Feb 2026 22:51:06 -0500
Subject: drm/amd/pm: remove invalid gpu_metrics.energy_accumulator on smu
 v13.0.x

v1:
The metrics->EnergyAccumulator field has been deprecated on newer pmfw.

v2:
add smu 13.0.0/13.0.7/13.0.10 support.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8de9edb35976fa56565dc8fbb5d1310e8e10187c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 8 +++++++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 3 ++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index e030f1e186cb..b32c053950c9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2034,6 +2034,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 			smu, SMU_DRIVER_TABLE_GPU_METRICS);
 	SmuMetricsExternal_t metrics_ext;
 	SmuMetrics_t *metrics = &metrics_ext.SmuMetrics;
+	uint32_t mp1_ver = amdgpu_ip_version(smu->adev, MP1_HWIP, 0);
 	int ret = 0;
 
 	ret = smu_cmn_get_metrics_table(smu,
@@ -2058,7 +2059,12 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+
+	if ((mp1_ver == IP_VERSION(13, 0, 0) && smu->smc_fw_version <= 0x004e1e00) ||
+	    (mp1_ver == IP_VERSION(13, 0, 10) && smu->smc_fw_version <= 0x00500800))
+		gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	else
+		gpu_metrics->energy_accumulator = UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_0_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index af0482c9caa7..f08cfa510a8a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2065,7 +2065,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu,
 					       metrics->Vcn1ActivityPercentage);
 
 	gpu_metrics->average_socket_power = metrics->AverageSocketPower;
-	gpu_metrics->energy_accumulator = metrics->EnergyAccumulator;
+	gpu_metrics->energy_accumulator = smu->smc_fw_version <= 0x00521400 ?
+		metrics->EnergyAccumulator : UINT_MAX;
 
 	if (metrics->AverageGfxActivity <= SMU_13_0_7_BUSY_THRESHOLD)
 		gpu_metrics->average_gfxclk_frequency = metrics->AverageGfxclkFrequencyPostDs;
-- 
cgit v1.2.3


From 2c1030f2e84885cc58bffef6af67d5b9d2e7098f Mon Sep 17 00:00:00 2001
From: Alysa Liu <Alysa.Liu@amd.com>
Date: Thu, 5 Feb 2026 11:21:45 -0500
Subject: drm/amdgpu: Fix use-after-free race in VM acquire

Replace non-atomic vm->process_info assignment with cmpxchg()
to prevent race when parent/child processes sharing a drm_file
both try to acquire the same VM after fork().

Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alysa Liu <Alysa.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c7c573275ec20db05be769288a3e3bb2250ec618)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 06c1913d5a3f..29b400cdd6d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1439,7 +1439,10 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
 		*process_info = info;
 	}
 
-	vm->process_info = *process_info;
+	if (cmpxchg(&vm->process_info, NULL, *process_info) != NULL) {
+		ret = -EINVAL;
+		goto already_acquired;
+	}
 
 	/* Validate page directory and attach eviction fence */
 	ret = amdgpu_bo_reserve(vm->root.bo, true);
@@ -1479,6 +1482,7 @@ validate_pd_fail:
 	amdgpu_bo_unreserve(vm->root.bo);
 reserve_pd_fail:
 	vm->process_info = NULL;
+already_acquired:
 	if (info) {
 		dma_fence_put(&info->eviction_fence->base);
 		*process_info = NULL;
-- 
cgit v1.2.3


From a145bbff6f53ab80757a15eba5ad2ba8e3bdc9dc Mon Sep 17 00:00:00 2001
From: sguttula <suresh.guttula@amd.com>
Date: Wed, 25 Feb 2026 13:57:01 +0530
Subject: drm/amdgpu/psp: Use Indirect access address for GFX to PSP mailbox

The reason the RAP is not granting access to 0x58200 is that
a dedicated RSMU slot would have to be spent for this address range,
and MPASP is close to running out of RSMU slots.

This will help to fix PSP TOC load failure during secureboot.
GFX Driver Need to use indirect access for SMN address regs.

Signed-off-by: sguttula <suresh.guttula@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9b822e26eea3899003aa8a89d5e2c4408e066e20)
---
 drivers/gpu/drm/amd/amdgpu/psp_v15_0.c               | 20 ++++++++++----------
 .../drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h   | 18 ++++++++++++++++++
 2 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
index 723ddae17644..73a709773e85 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v15_0.c
@@ -69,12 +69,12 @@ static int psp_v15_0_0_ring_stop(struct psp_context *psp,
 				   0x80000000, 0x80000000, false);
 	} else {
 		/* Write the ring destroy command*/
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64,
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64,
 			     GFX_CTRL_CMD_ID_DESTROY_RINGS);
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 		/* Wait for response flag (bit 31) */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 	}
 
@@ -116,7 +116,7 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 	} else {
 		/* Wait for sOS ready for ring creation */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x80000000, false);
 		if (ret) {
 			DRM_ERROR("Failed to wait for trust OS ready for ring creation\n");
@@ -125,23 +125,23 @@ static int psp_v15_0_0_ring_create(struct psp_context *psp,
 
 		/* Write low address of the ring to C2PMSG_69 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_69, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_69, psp_ring_reg);
 		/* Write high address of the ring to C2PMSG_70 */
 		psp_ring_reg = upper_32_bits(ring->ring_mem_mc_addr);
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_70, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_70, psp_ring_reg);
 		/* Write size of ring to C2PMSG_71 */
 		psp_ring_reg = ring->ring_size;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_71, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_71, psp_ring_reg);
 		/* Write the ring initialization command to C2PMSG_64 */
 		psp_ring_reg = ring_type;
 		psp_ring_reg = psp_ring_reg << 16;
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_64, psp_ring_reg);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64, psp_ring_reg);
 
 		/* there might be handshake issue with hardware which needs delay */
 		mdelay(20);
 
 		/* Wait for response flag (bit 31) in C2PMSG_64 */
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_SMN_C2PMSG_64),
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_64),
 				   0x80000000, 0x8000FFFF, false);
 	}
 
@@ -174,7 +174,7 @@ static uint32_t psp_v15_0_0_ring_get_wptr(struct psp_context *psp)
 	if (amdgpu_sriov_vf(adev))
 		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_102);
 	else
-		data = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67);
+		data = RREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67);
 
 	return data;
 }
@@ -188,7 +188,7 @@ static void psp_v15_0_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
 		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_101,
 			     GFX_CTRL_CMD_ID_CONSUME_CMD);
 	} else
-		WREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_67, value);
+		WREG32_SOC15(MP0, 0, regMPASP_PCRU1_MPASP_C2PMSG_67, value);
 }
 
 static const struct psp_funcs psp_v15_0_0_funcs = {
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
index 0e4c195297a4..fe97943b9b97 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_15_0_0_offset.h
@@ -82,6 +82,24 @@
 #define regMPASP_SMN_IH_SW_INT_CTRL                                                                     0x0142
 #define regMPASP_SMN_IH_SW_INT_CTRL_BASE_IDX                                                            0
 
+// addressBlock: mp_SmuMpASPPub_PcruDec
+// base address: 0x3800000
+#define regMPASP_PCRU1_MPASP_C2PMSG_64                                                   0x4280
+#define regMPASP_PCRU1_MPASP_C2PMSG_64_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_65                                                   0x4281
+#define regMPASP_PCRU1_MPASP_C2PMSG_65_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_66                                                   0x4282
+#define regMPASP_PCRU1_MPASP_C2PMSG_66_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_67                                                   0x4283
+#define regMPASP_PCRU1_MPASP_C2PMSG_67_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_68                                                   0x4284
+#define regMPASP_PCRU1_MPASP_C2PMSG_68_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_69                                                   0x4285
+#define regMPASP_PCRU1_MPASP_C2PMSG_69_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_70                                                   0x4286
+#define regMPASP_PCRU1_MPASP_C2PMSG_70_BASE_IDX                                          3
+#define regMPASP_PCRU1_MPASP_C2PMSG_71                                                   0x4287
+#define regMPASP_PCRU1_MPASP_C2PMSG_71_BASE_IDX                                          3
 
 // addressBlock: mp_SmuMp1_SmnDec
 // base address: 0x0
-- 
cgit v1.2.3


From 048c1c4e51715ffddd4189745c07f530f34fbe37 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Mon, 23 Feb 2026 12:41:32 +0000
Subject: drm/amdgpu/userq: Consolidate wait ioctl exit path

If we gate the fence destruction with a check telling us whether there are
valid pointers in there we can eliminate the need for dual, basically
identical, exit paths.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bea29bb0dd29012949cd44fdb122465a9fd5cf91)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 28 +++++--------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 7e9cf1868cc9..77969a6017a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -983,32 +983,14 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			r = -EFAULT;
 			goto free_fences;
 		}
-
-		kfree(fences);
-		kfree(fence_info);
 	}
 
-	drm_exec_fini(&exec);
-	for (i = 0; i < num_read_bo_handles; i++)
-		drm_gem_object_put(gobj_read[i]);
-	kfree(gobj_read);
-
-	for (i = 0; i < num_write_bo_handles; i++)
-		drm_gem_object_put(gobj_write[i]);
-	kfree(gobj_write);
-
-	kfree(timeline_points);
-	kfree(timeline_handles);
-	kfree(syncobj_handles);
-	kfree(bo_handles_write);
-	kfree(bo_handles_read);
-
-	return 0;
-
 free_fences:
-	while (num_fences-- > 0)
-		dma_fence_put(fences[num_fences]);
-	kfree(fences);
+	if (fences) {
+		while (num_fences-- > 0)
+			dma_fence_put(fences[num_fences]);
+		kfree(fences);
+	}
 free_fence_info:
 	kfree(fence_info);
 exec_fini:
-- 
cgit v1.2.3


From 65b5c326ce4103620c977b8dcb1699bdac4da143 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Mon, 2 Mar 2026 18:50:46 +0530
Subject: drm/amdgpu/userq: refcount userqueues to avoid any race conditions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To avoid race condition and avoid UAF cases, implement kref
based queues and protect the below operations using xa lock
a. Getting a queue from xarray
b. Increment/Decrement it's refcount

Every time some one want to access a queue, always get via
amdgpu_userq_get to make sure we have locks in place and get
the object if active.

A userqueue is destroyed on the last refcount is dropped which
typically would be via IOCTL or during fini.

v2: Add the missing drop in one the condition in the signal ioclt [Alex]

v3: remove the queue from the xarray first in the free queue ioctl path
    [Christian]

- Pass queue to the amdgpu_userq_put directly.
- make amdgpu_userq_put xa_lock free since we are doing put for each get
  only and final put is done via destroy and we remove the queue from xa
  with lock.
- use userq_put in fini too so cleanup is done fully.

v4: Use xa_erase directly rather than doing load and erase in free
    ioctl. Also remove some of the error logs which could be exploited
    by the user to flood the logs [Christian]

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4952189b284d4d847f92636bb42dd747747129c0)
Cc: <stable@vger.kernel.org> # 048c1c4e5171: drm/amdgpu/userq: Consolidate wait ioctl exit path
Cc: <stable@vger.kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c       | 116 +++++++++++++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h       |   4 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c |  14 ++-
 3 files changed, 95 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 9d67b770bcc2..7c450350847d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -446,8 +446,7 @@ static int amdgpu_userq_wait_for_last_fence(struct amdgpu_usermode_queue *queue)
 	return ret;
 }
 
-static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
-				 int queue_id)
+static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue)
 {
 	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
@@ -461,7 +460,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	uq_funcs->mqd_destroy(queue);
 	amdgpu_userq_fence_driver_free(queue);
 	/* Use interrupt-safe locking since IRQ handlers may access these XArrays */
-	xa_erase_irq(&uq_mgr->userq_xa, (unsigned long)queue_id);
 	xa_erase_irq(&adev->userq_doorbell_xa, queue->doorbell_index);
 	queue->userq_mgr = NULL;
 	list_del(&queue->userq_va_list);
@@ -470,12 +468,6 @@ static void amdgpu_userq_cleanup(struct amdgpu_usermode_queue *queue,
 	up_read(&adev->reset_domain->sem);
 }
 
-static struct amdgpu_usermode_queue *
-amdgpu_userq_find(struct amdgpu_userq_mgr *uq_mgr, int qid)
-{
-	return xa_load(&uq_mgr->userq_xa, qid);
-}
-
 void
 amdgpu_userq_ensure_ev_fence(struct amdgpu_userq_mgr *uq_mgr,
 			     struct amdgpu_eviction_fence_mgr *evf_mgr)
@@ -625,22 +617,13 @@ unref_bo:
 }
 
 static int
-amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
+amdgpu_userq_destroy(struct amdgpu_userq_mgr *uq_mgr, struct amdgpu_usermode_queue *queue)
 {
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_userq_mgr *uq_mgr = &fpriv->userq_mgr;
 	struct amdgpu_device *adev = uq_mgr->adev;
-	struct amdgpu_usermode_queue *queue;
 	int r = 0;
 
 	cancel_delayed_work_sync(&uq_mgr->resume_work);
 	mutex_lock(&uq_mgr->userq_mutex);
-	queue = amdgpu_userq_find(uq_mgr, queue_id);
-	if (!queue) {
-		drm_dbg_driver(adev_to_drm(uq_mgr->adev), "Invalid queue id to destroy\n");
-		mutex_unlock(&uq_mgr->userq_mutex);
-		return -EINVAL;
-	}
 	amdgpu_userq_wait_for_last_fence(queue);
 	/* Cancel any pending hang detection work and cleanup */
 	if (queue->hang_detect_fence) {
@@ -672,7 +655,7 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 		drm_warn(adev_to_drm(uq_mgr->adev), "trying to destroy a HW mapping userq\n");
 		queue->state = AMDGPU_USERQ_STATE_HUNG;
 	}
-	amdgpu_userq_cleanup(queue, queue_id);
+	amdgpu_userq_cleanup(queue);
 	mutex_unlock(&uq_mgr->userq_mutex);
 
 	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -680,6 +663,37 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
 	return r;
 }
 
+static void amdgpu_userq_kref_destroy(struct kref *kref)
+{
+	int r;
+	struct amdgpu_usermode_queue *queue =
+		container_of(kref, struct amdgpu_usermode_queue, refcount);
+	struct amdgpu_userq_mgr *uq_mgr = queue->userq_mgr;
+
+	r = amdgpu_userq_destroy(uq_mgr, queue);
+	if (r)
+		drm_file_err(uq_mgr->file, "Failed to destroy usermode queue %d\n", r);
+}
+
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid)
+{
+	struct amdgpu_usermode_queue *queue;
+
+	xa_lock(&uq_mgr->userq_xa);
+	queue = xa_load(&uq_mgr->userq_xa, qid);
+	if (queue)
+		kref_get(&queue->refcount);
+	xa_unlock(&uq_mgr->userq_xa);
+
+	return queue;
+}
+
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue)
+{
+	if (queue)
+		kref_put(&queue->refcount, amdgpu_userq_kref_destroy);
+}
+
 static int amdgpu_userq_priority_permit(struct drm_file *filp,
 					int priority)
 {
@@ -834,6 +848,9 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 		goto unlock;
 	}
 
+	/* drop this refcount during queue destroy */
+	kref_init(&queue->refcount);
+
 	/* Wait for mode-1 reset to complete */
 	down_read(&adev->reset_domain->sem);
 	r = xa_err(xa_store_irq(&adev->userq_doorbell_xa, index, queue, GFP_KERNEL));
@@ -985,7 +1002,9 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp)
 {
 	union drm_amdgpu_userq *args = data;
-	int r;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_usermode_queue *queue;
+	int r = 0;
 
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
@@ -1000,11 +1019,16 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 			drm_file_err(filp, "Failed to create usermode queue\n");
 		break;
 
-	case AMDGPU_USERQ_OP_FREE:
-		r = amdgpu_userq_destroy(filp, args->in.queue_id);
-		if (r)
-			drm_file_err(filp, "Failed to destroy usermode queue\n");
+	case AMDGPU_USERQ_OP_FREE: {
+		xa_lock(&fpriv->userq_mgr.userq_xa);
+		queue = __xa_erase(&fpriv->userq_mgr.userq_xa, args->in.queue_id);
+		xa_unlock(&fpriv->userq_mgr.userq_xa);
+		if (!queue)
+			return -ENOENT;
+
+		amdgpu_userq_put(queue);
 		break;
+	}
 
 	default:
 		drm_dbg_driver(dev, "Invalid user queue op specified: %d\n", args->in.op);
@@ -1023,16 +1047,23 @@ amdgpu_userq_restore_all(struct amdgpu_userq_mgr *uq_mgr)
 
 	/* Resume all the queues for this process */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		if (!amdgpu_userq_buffer_vas_mapped(queue)) {
 			drm_file_err(uq_mgr->file,
 				     "trying restore queue without va mapping\n");
 			queue->state = AMDGPU_USERQ_STATE_INVALID_VA;
+			amdgpu_userq_put(queue);
 			continue;
 		}
 
 		r = amdgpu_userq_restore_helper(queue);
 		if (r)
 			ret = r;
+
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1266,9 +1297,13 @@ amdgpu_userq_evict_all(struct amdgpu_userq_mgr *uq_mgr)
 	amdgpu_userq_detect_and_reset_queues(uq_mgr);
 	/* Try to unmap all the queues in this process ctx */
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
 		r = amdgpu_userq_preempt_helper(queue);
 		if (r)
 			ret = r;
+		amdgpu_userq_put(queue);
 	}
 
 	if (ret)
@@ -1301,16 +1336,24 @@ amdgpu_userq_wait_for_signal(struct amdgpu_userq_mgr *uq_mgr)
 	int ret;
 
 	xa_for_each(&uq_mgr->userq_xa, queue_id, queue) {
+		queue = amdgpu_userq_get(uq_mgr, queue_id);
+		if (!queue)
+			continue;
+
 		struct dma_fence *f = queue->last_fence;
 
-		if (!f || dma_fence_is_signaled(f))
+		if (!f || dma_fence_is_signaled(f)) {
+			amdgpu_userq_put(queue);
 			continue;
+		}
 		ret = dma_fence_wait_timeout(f, true, msecs_to_jiffies(100));
 		if (ret <= 0) {
 			drm_file_err(uq_mgr->file, "Timed out waiting for fence=%llu:%llu\n",
 				     f->context, f->seqno);
+			amdgpu_userq_put(queue);
 			return -ETIMEDOUT;
 		}
+		amdgpu_userq_put(queue);
 	}
 
 	return 0;
@@ -1361,20 +1404,23 @@ int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *f
 void amdgpu_userq_mgr_fini(struct amdgpu_userq_mgr *userq_mgr)
 {
 	struct amdgpu_usermode_queue *queue;
-	unsigned long queue_id;
+	unsigned long queue_id = 0;
+
+	for (;;) {
+		xa_lock(&userq_mgr->userq_xa);
+		queue = xa_find(&userq_mgr->userq_xa, &queue_id, ULONG_MAX,
+				XA_PRESENT);
+		if (queue)
+			__xa_erase(&userq_mgr->userq_xa, queue_id);
+		xa_unlock(&userq_mgr->userq_xa);
 
-	cancel_delayed_work_sync(&userq_mgr->resume_work);
+		if (!queue)
+			break;
 
-	mutex_lock(&userq_mgr->userq_mutex);
-	amdgpu_userq_detect_and_reset_queues(userq_mgr);
-	xa_for_each(&userq_mgr->userq_xa, queue_id, queue) {
-		amdgpu_userq_wait_for_last_fence(queue);
-		amdgpu_userq_unmap_helper(queue);
-		amdgpu_userq_cleanup(queue, queue_id);
+		amdgpu_userq_put(queue);
 	}
 
 	xa_destroy(&userq_mgr->userq_xa);
-	mutex_unlock(&userq_mgr->userq_mutex);
 	mutex_destroy(&userq_mgr->userq_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index 5845d8959034..736c1d38297c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -74,6 +74,7 @@ struct amdgpu_usermode_queue {
 	struct dentry		*debugfs_queue;
 	struct delayed_work hang_detect_work;
 	struct dma_fence *hang_detect_fence;
+	struct kref		refcount;
 
 	struct list_head	userq_va_list;
 };
@@ -112,6 +113,9 @@ struct amdgpu_db_info {
 	struct amdgpu_userq_obj	*db_obj;
 };
 
+struct amdgpu_usermode_queue *amdgpu_userq_get(struct amdgpu_userq_mgr *uq_mgr, u32 qid);
+void amdgpu_userq_put(struct amdgpu_usermode_queue *queue);
+
 int amdgpu_userq_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 
 int amdgpu_userq_mgr_init(struct amdgpu_userq_mgr *userq_mgr, struct drm_file *file_priv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 77969a6017a4..5239b06b9ab0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -466,7 +466,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_signal *args = data;
 	struct drm_gem_object **gobj_write = NULL;
 	struct drm_gem_object **gobj_read = NULL;
-	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_usermode_queue *queue = NULL;
 	struct amdgpu_userq_fence *userq_fence;
 	struct drm_syncobj **syncobj = NULL;
 	u32 *bo_handles_write, num_write_bo_handles;
@@ -553,7 +553,7 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	}
 
 	/* Retrieve the user queue */
-	queue = xa_load(&userq_mgr->userq_xa, args->queue_id);
+	queue = amdgpu_userq_get(userq_mgr, args->queue_id);
 	if (!queue) {
 		r = -ENOENT;
 		goto put_gobj_write;
@@ -648,6 +648,9 @@ free_syncobj:
 free_syncobj_handles:
 	kfree(syncobj_handles);
 
+	if (queue)
+		amdgpu_userq_put(queue);
+
 	return r;
 }
 
@@ -660,7 +663,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	struct drm_amdgpu_userq_wait *wait_info = data;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_userq_mgr *userq_mgr = &fpriv->userq_mgr;
-	struct amdgpu_usermode_queue *waitq;
+	struct amdgpu_usermode_queue *waitq = NULL;
 	struct drm_gem_object **gobj_write;
 	struct drm_gem_object **gobj_read;
 	struct dma_fence **fences = NULL;
@@ -926,7 +929,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 		 */
 		num_fences = dma_fence_dedup_array(fences, num_fences);
 
-		waitq = xa_load(&userq_mgr->userq_xa, wait_info->waitq_id);
+		waitq = amdgpu_userq_get(userq_mgr, wait_info->waitq_id);
 		if (!waitq) {
 			r = -EINVAL;
 			goto free_fences;
@@ -1014,5 +1017,8 @@ free_bo_handles_write:
 free_bo_handles_read:
 	kfree(bo_handles_read);
 
+	if (waitq)
+		amdgpu_userq_put(waitq);
+
 	return r;
 }
-- 
cgit v1.2.3


From e48a869957a70cc39b4090cd27c36a86f8db9b92 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Wed, 25 Feb 2026 09:51:35 +0100
Subject: timekeeping: Fix timex status validation for auxiliary clocks

The timekeeping_validate_timex() function validates the timex status
of an auxiliary system clock even when the status is not to be changed,
which causes unexpected errors for applications that make read-only
clock_adjtime() calls, or set some other timex fields, but without
clearing the status field.

Do the AUX-specific status validation only when the modes field contains
ADJ_STATUS, i.e. the application is actually trying to change the
status. This makes the AUX-specific clock_adjtime() behavior consistent
with CLOCK_REALTIME.

Fixes: 4eca49d0b621 ("timekeeping: Prepare do_adtimex() for auxiliary clocks")
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260225085231.276751-1-mlichvar@redhat.com
---
 kernel/time/timekeeping.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 91fa2003351c..c07e562ee4c1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2653,7 +2653,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux
 
 	if (aux_clock) {
 		/* Auxiliary clocks are similar to TAI and do not have leap seconds */
-		if (txc->status & (STA_INS | STA_DEL))
+		if (txc->modes & ADJ_STATUS &&
+		    txc->status & (STA_INS | STA_DEL))
 			return -EINVAL;
 
 		/* No TAI offset setting */
@@ -2661,7 +2662,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux
 			return -EINVAL;
 
 		/* No PPS support either */
-		if (txc->status & (STA_PPSFREQ | STA_PPSTIME))
+		if (txc->modes & ADJ_STATUS &&
+		    txc->status & (STA_PPSFREQ | STA_PPSTIME))
 			return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From da994db94e60f9a9411108ddf4d1836147ad4c9c Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Date: Fri, 20 Feb 2026 15:11:48 -0600
Subject: remoteproc: sysmon: Correct subsys_name_len type in QMI request

The QMI message encoder has up until recently read a single byte (as
elem_size == 1), but with the introduction of big endian support it's
become apparent that this field is expected to be a full u32 -
regardless of the size of the length in the encoded message (which is
what elem_size specifies).

The result is that the encoder now reads past the length byte and
rejects the unreasonably large length formed when including the
following 3 bytes from the subsys_name array.

Fix this by changing to the expected type.

Fixes: 1fb82ee806d1 ("remoteproc: qcom: Introduce sysmon")
Signed-off-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Reviewed-by: Chris Lew <christopher.lew@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260220-qmi-encode-invalid-length-v2-1-5674be35ab29@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/remoteproc/qcom_sysmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c
index cf10e8ecfb8f..3ceec1fd6d99 100644
--- a/drivers/remoteproc/qcom_sysmon.c
+++ b/drivers/remoteproc/qcom_sysmon.c
@@ -203,7 +203,7 @@ static const struct qmi_elem_info ssctl_shutdown_resp_ei[] = {
 };
 
 struct ssctl_subsys_event_req {
-	u8 subsys_name_len;
+	u32 subsys_name_len;
 	char subsys_name[SSCTL_SUBSYS_NAME_LENGTH];
 	u32 event;
 	u8 evt_driven_valid;
-- 
cgit v1.2.3


From 5b2a16ab0dbd090dc545c05ee79a077cc7a9c1e0 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@oss.qualcomm.com>
Date: Mon, 2 Feb 2026 16:56:11 +0100
Subject: arm64: dts: qcom: monaco: Fix UART10 pinconf

UART10 RTS and TX pins were incorrectly mapped to gpio84 and gpio85.
Correct them to gpio85 (RTS) and gpio86 (TX) to match the hardware
I/O mapping.

Fixes: 467284a3097f ("arm64: dts: qcom: qcs8300: Add QUPv3 configuration")
Signed-off-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260202155611.1568-1-loic.poulain@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/monaco.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/monaco.dtsi b/arch/arm64/boot/dts/qcom/monaco.dtsi
index 5d2df4305d1c..dbb2273b0ee8 100644
--- a/arch/arm64/boot/dts/qcom/monaco.dtsi
+++ b/arch/arm64/boot/dts/qcom/monaco.dtsi
@@ -6414,12 +6414,12 @@
 			};
 
 			qup_uart10_rts: qup-uart10-rts-state {
-				pins = "gpio84";
+				pins = "gpio85";
 				function = "qup1_se2";
 			};
 
 			qup_uart10_tx: qup-uart10-tx-state {
-				pins = "gpio85";
+				pins = "gpio86";
 				function = "qup1_se2";
 			};
 
-- 
cgit v1.2.3


From 170a4b21f49b3dcff3115b4c90758f0a0d77375a Mon Sep 17 00:00:00 2001
From: Olivier Sobrie <olivier@sobrie.be>
Date: Wed, 4 Mar 2026 22:20:39 +0100
Subject: hwmon: (max6639) fix inverted polarity

According to MAX6639 documentation:

  D1: PWM Output Polarity. PWM output is low at
  100% duty cycle when this bit is set to zero. PWM
  output is high at 100% duty cycle when this bit is set
  to 1.

Up to commit 0f33272b60ed ("hwmon: (max6639) : Update hwmon init using
info structure"), the polarity was set to high (0x2) when no platform
data was set. After the patch, the polarity register wasn't set anymore
if no platform data was specified. Nowadays, since commit 7506ebcd662b
("hwmon: (max6639) : Configure based on DT property"), it is always set
to low which doesn't match with the comment above and change the
behavior compared to versions prior 0f33272b60ed.

Fixes: 0f33272b60ed ("hwmon: (max6639) : Update hwmon init using info structure")
Signed-off-by: Olivier Sobrie <olivier@sobrie.be>
Link: https://lore.kernel.org/r/20260304212039.570274-1-olivier@sobrie.be
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/max6639.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c
index a0a1dbbda887..9a3c515efe2e 100644
--- a/drivers/hwmon/max6639.c
+++ b/drivers/hwmon/max6639.c
@@ -607,7 +607,7 @@ static int max6639_init_client(struct i2c_client *client,
 			return err;
 
 		/* Fans PWM polarity high by default */
-		err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x00);
+		err = regmap_write(data->regmap, MAX6639_REG_FAN_CONFIG2a(i), 0x02);
 		if (err)
 			return err;
 
-- 
cgit v1.2.3


From 6944e6d8a6d4c1e654de1da112da8fef1b30e623 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Thu, 5 Mar 2026 03:57:57 +0800
Subject: sched_ext/selftests: Fix format specifier and buffer length in
 file_write_long()

Use %ld (not %lu) for signed long, and pass the actual string length
returned by sprintf() to write_text() instead of sizeof(buf).

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/util.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c
index e47769c91918..2111329ed289 100644
--- a/tools/testing/selftests/sched_ext/util.c
+++ b/tools/testing/selftests/sched_ext/util.c
@@ -60,11 +60,11 @@ int file_write_long(const char *path, long val)
 	char buf[64];
 	int ret;
 
-	ret = sprintf(buf, "%lu", val);
+	ret = sprintf(buf, "%ld", val);
 	if (ret < 0)
 		return ret;
 
-	if (write_text(path, buf, sizeof(buf)) <= 0)
+	if (write_text(path, buf, ret) <= 0)
 		return -1;
 
 	return 0;
-- 
cgit v1.2.3


From 126fe7ef12ffe42fdc600fe22df733e96fa418ec Mon Sep 17 00:00:00 2001
From: Joe Damato <joe@dama.to>
Date: Mon, 2 Mar 2026 18:42:01 -0800
Subject: mailmap: Add entry for Joe Damato

My Fastly email address is no longer used. Add a mailmap entry to
reflect that.

Signed-off-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303024202.2526604-1-joe@dama.to
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index e1cf6bb85d33..a02e9aa9aed4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -396,6 +396,7 @@ Jiri Slaby <jirislaby@kernel.org> <xslaby@fi.muni.cz>
 Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com>
 Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com>
 Jishnu Prakash <quic_jprakash@quicinc.com> <jprakash@codeaurora.org>
+Joe Damato <joe@dama.to> <jdamato@fastly.com>
 Joel Granados <joel.granados@kernel.org> <j.granados@samsung.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
 Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
-- 
cgit v1.2.3


From 18b43bec5437914e3b51bb08dc6c6e7b0a2df4d1 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 3 Mar 2026 11:37:20 +0800
Subject: mailmap: reflect my gmail as default

Use my gmail instead so that I can easily handle those emails
that CC me.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://patch.msgid.link/20260303033720.84108-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index a02e9aa9aed4..7fefbcc82d1a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -348,6 +348,7 @@ Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
+Jason Xing <kerneljasonxing@gmail.com>  <kernelxing@tencent.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
-- 
cgit v1.2.3


From 25dd70a03b1f5f3aa71e1a5091ecd9cd2a13ee43 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Wed, 4 Mar 2026 15:51:17 -0800
Subject: hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read

The q54sj108a2_debugfs_read function suffers from a stack buffer overflow
due to incorrect arguments passed to bin2hex(). The function currently
passes 'data' as the destination and 'data_char' as the source.

Because bin2hex() converts each input byte into two hex characters, a
32-byte block read results in 64 bytes of output. Since 'data' is only
34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end
of the buffer onto the stack.

Additionally, the arguments were swapped: it was reading from the
zero-initialized 'data_char' and writing to 'data', resulting in
all-zero output regardless of the actual I2C read.

Fix this by:
1. Expanding 'data_char' to 66 bytes to safely hold the hex output.
2. Correcting the bin2hex() argument order and using the actual read count.
3. Using a pointer to select the correct output buffer for the final
   simple_read_from_buffer call.

Fixes: d014538aa385 ("hwmon: (pmbus) Driver for Delta power supplies Q54SJ108A2")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260304235116.1045-1-sanman.p211993@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/q54sj108a2.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/hwmon/pmbus/q54sj108a2.c b/drivers/hwmon/pmbus/q54sj108a2.c
index fc030ca34480..d5d60a9af8c5 100644
--- a/drivers/hwmon/pmbus/q54sj108a2.c
+++ b/drivers/hwmon/pmbus/q54sj108a2.c
@@ -79,7 +79,8 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf,
 	int idx = *idxp;
 	struct q54sj108a2_data *psu = to_psu(idxp, idx);
 	char data[I2C_SMBUS_BLOCK_MAX + 2] = { 0 };
-	char data_char[I2C_SMBUS_BLOCK_MAX + 2] = { 0 };
+	char data_char[I2C_SMBUS_BLOCK_MAX * 2 + 2] = { 0 };
+	char *out = data;
 	char *res;
 
 	switch (idx) {
@@ -150,27 +151,27 @@ static ssize_t q54sj108a2_debugfs_read(struct file *file, char __user *buf,
 		if (rc < 0)
 			return rc;
 
-		res = bin2hex(data, data_char, 32);
-		rc = res - data;
-
+		res = bin2hex(data_char, data, rc);
+		rc = res - data_char;
+		out = data_char;
 		break;
 	case Q54SJ108A2_DEBUGFS_FLASH_KEY:
 		rc = i2c_smbus_read_block_data(psu->client, PMBUS_FLASH_KEY_WRITE, data);
 		if (rc < 0)
 			return rc;
 
-		res = bin2hex(data, data_char, 4);
-		rc = res - data;
-
+		res = bin2hex(data_char, data, rc);
+		rc = res - data_char;
+		out = data_char;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	data[rc] = '\n';
+	out[rc] = '\n';
 	rc += 2;
 
-	return simple_read_from_buffer(buf, count, ppos, data, rc);
+	return simple_read_from_buffer(buf, count, ppos, out, rc);
 }
 
 static ssize_t q54sj108a2_debugfs_write(struct file *file, const char __user *buf,
-- 
cgit v1.2.3


From 7f083faf59d14c04e01ec05a7507f036c965acf8 Mon Sep 17 00:00:00 2001
From: Koichiro Den <den@valinux.co.jp>
Date: Sat, 28 Feb 2026 23:53:07 +0900
Subject: net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for
 lockless qdiscs

When shrinking the number of real tx queues,
netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush
qdiscs for queues which will no longer be used.

qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with
qdisc_lock(). However, for lockless qdiscs, the dequeue path is
serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so
qdisc_reset() can run concurrently with __qdisc_run() and free skbs
while they are still being dequeued, leading to UAF.

This can easily be reproduced on e.g. virtio-net by imposing heavy
traffic while frequently changing the number of queue pairs:

  iperf3 -ub0 -c $peer -t 0 &
  while :; do
    ethtool -L eth0 combined 1
    ethtool -L eth0 combined 2
  done

With KASAN enabled, this leads to reports like:

  BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760
  ...
  Call Trace:
   <TASK>
   ...
   __qdisc_run+0x133f/0x1760
   __dev_queue_xmit+0x248f/0x3550
   ip_finish_output2+0xa42/0x2110
   ip_output+0x1a7/0x410
   ip_send_skb+0x2e6/0x480
   udp_send_skb+0xb0a/0x1590
   udp_sendmsg+0x13c9/0x1fc0
   ...
   </TASK>

  Allocated by task 1270 on cpu 5 at 44.558414s:
   ...
   alloc_skb_with_frags+0x84/0x7c0
   sock_alloc_send_pskb+0x69a/0x830
   __ip_append_data+0x1b86/0x48c0
   ip_make_skb+0x1e8/0x2b0
   udp_sendmsg+0x13a6/0x1fc0
   ...

  Freed by task 1306 on cpu 3 at 44.558445s:
   ...
   kmem_cache_free+0x117/0x5e0
   pfifo_fast_reset+0x14d/0x580
   qdisc_reset+0x9e/0x5f0
   netif_set_real_num_tx_queues+0x303/0x840
   virtnet_set_channels+0x1bf/0x260 [virtio_net]
   ethnl_set_channels+0x684/0xae0
   ethnl_default_set_doit+0x31a/0x890
   ...

Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by
taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the
serialization model already used by dev_reset_queue().

Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state
reflects an empty queue, avoiding needless re-scheduling.

Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking")
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Link: https://patch.msgid.link/20260228145307.3955532-1-den@valinux.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sch_generic.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c3a7268b567e..d5d55cb21686 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -778,13 +778,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb)
 static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
 {
 	struct Qdisc *qdisc;
+	bool nolock;
 
 	for (; i < dev->num_tx_queues; i++) {
 		qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
 		if (qdisc) {
+			nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+			if (nolock)
+				spin_lock_bh(&qdisc->seqlock);
 			spin_lock_bh(qdisc_lock(qdisc));
 			qdisc_reset(qdisc);
 			spin_unlock_bh(qdisc_lock(qdisc));
+			if (nolock) {
+				clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+				clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
+				spin_unlock_bh(&qdisc->seqlock);
+			}
 		}
 	}
 }
-- 
cgit v1.2.3


From 165573e41f2f66ef98940cf65f838b2cb575d9d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 2 Mar 2026 20:55:27 +0000
Subject: tcp: secure_seq: add back ports to TS offset

This reverts 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets")

tcp_tw_recycle went away in 2017.

Zhouyan Deng reported off-path TCP source port leakage via
SYN cookie side-channel that can be fixed in multiple ways.

One of them is to bring back TCP ports in TS offset randomization.

As a bonus, we perform a single siphash() computation
to provide both an ISN and a TS offset.

Fixes: 28ee1b746f49 ("secure_seq: downgrade to per-host timestamp offsets")
Reported-by: Zhouyan Deng <dengzhouyan_nwpu@163.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260302205527.1982836-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/secure_seq.h | 45 ++++++++++++++++++++++-----
 include/net/tcp.h        |  6 ++--
 net/core/secure_seq.c    | 80 ++++++++++++++++++------------------------------
 net/ipv4/syncookies.c    | 11 +++++--
 net/ipv4/tcp_input.c     |  8 +++--
 net/ipv4/tcp_ipv4.c      | 37 ++++++++++------------
 net/ipv6/syncookies.c    | 11 +++++--
 net/ipv6/tcp_ipv6.c      | 37 ++++++++++------------
 8 files changed, 127 insertions(+), 108 deletions(-)

diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index cddebafb9f77..6f996229167b 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -5,16 +5,47 @@
 #include <linux/types.h>
 
 struct net;
+extern struct net init_net;
+
+union tcp_seq_and_ts_off {
+	struct {
+		u32 seq;
+		u32 ts_off;
+	};
+	u64 hash64;
+};
 
 u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
-u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
-		   __be16 sport, __be16 dport);
-u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr);
-u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
-		     __be16 sport, __be16 dport);
-u32 secure_tcpv6_ts_off(const struct net *net,
-			const __be32 *saddr, const __be32 *daddr);
+union tcp_seq_and_ts_off
+secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr,
+			  __be16 sport, __be16 dport);
+
+static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+				 __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr,
+				       sport, dport);
+
+	return ts.seq;
+}
+
+union tcp_seq_and_ts_off
+secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr,
+			    const __be32 *daddr,
+			    __be16 sport, __be16 dport);
+
+static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+				   __be16 sport, __be16 dport)
+{
+	union tcp_seq_and_ts_off ts;
+
+	ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr,
+					 sport, dport);
 
+	return ts.seq;
+}
 #endif /* _NET_SECURE_SEQ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eb8bf63fdafc..978eea2d5df0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -43,6 +43,7 @@
 #include <net/dst.h>
 #include <net/mptcp.h>
 #include <net/xfrm.h>
+#include <net/secure_seq.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
@@ -2464,8 +2465,9 @@ struct tcp_request_sock_ops {
 				       struct flowi *fl,
 				       struct request_sock *req,
 				       u32 tw_isn);
-	u32 (*init_seq)(const struct sk_buff *skb);
-	u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb);
+	union tcp_seq_and_ts_off (*init_seq_and_ts_off)(
+					const struct net *net,
+					const struct sk_buff *skb);
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 9a3965680451..6a6f2cda5aae 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -20,7 +20,6 @@
 #include <net/tcp.h>
 
 static siphash_aligned_key_t net_secret;
-static siphash_aligned_key_t ts_secret;
 
 #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ)
 
@@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void)
 {
 	net_get_random_once(&net_secret, sizeof(net_secret));
 }
-
-static __always_inline void ts_secret_init(void)
-{
-	net_get_random_once(&ts_secret, sizeof(ts_secret));
-}
 #endif
 
 #ifdef CONFIG_INET
@@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq)
 #endif
 
 #if IS_ENABLED(CONFIG_IPV6)
-u32 secure_tcpv6_ts_off(const struct net *net,
-			const __be32 *saddr, const __be32 *daddr)
-{
-	const struct {
-		struct in6_addr saddr;
-		struct in6_addr daddr;
-	} __aligned(SIPHASH_ALIGNMENT) combined = {
-		.saddr = *(struct in6_addr *)saddr,
-		.daddr = *(struct in6_addr *)daddr,
-	};
-
-	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
-		return 0;
-
-	ts_secret_init();
-	return siphash(&combined, offsetofend(typeof(combined), daddr),
-		       &ts_secret);
-}
-EXPORT_IPV6_MOD(secure_tcpv6_ts_off);
-
-u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
-		     __be16 sport, __be16 dport)
+union tcp_seq_and_ts_off
+secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr,
+			    const __be32 *daddr, __be16 sport, __be16 dport)
 {
 	const struct {
 		struct in6_addr saddr;
@@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
 		.sport = sport,
 		.dport = dport
 	};
-	u32 hash;
+	union tcp_seq_and_ts_off st;
 
 	net_secret_init();
-	hash = siphash(&combined, offsetofend(typeof(combined), dport),
-		       &net_secret);
-	return seq_scale(hash);
+
+	st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport),
+			    &net_secret);
+
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
+		st.ts_off = 0;
+
+	st.seq = seq_scale(st.seq);
+	return st;
 }
-EXPORT_SYMBOL(secure_tcpv6_seq);
+EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off);
 
 u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport)
@@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr)
-{
-	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
-		return 0;
-
-	ts_secret_init();
-	return siphash_2u32((__force u32)saddr, (__force u32)daddr,
-			    &ts_secret);
-}
-
 /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
  * but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
  * it would be easy enough to have the former function use siphash_4u32, passing
  * the arguments as separate u32.
  */
-u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
-		   __be16 sport, __be16 dport)
+union tcp_seq_and_ts_off
+secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr,
+			  __be16 sport, __be16 dport)
 {
-	u32 hash;
+	u32 ports = (__force u32)sport << 16 | (__force u32)dport;
+	union tcp_seq_and_ts_off st;
 
 	net_secret_init();
-	hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
-			    (__force u32)sport << 16 | (__force u32)dport,
-			    &net_secret);
-	return seq_scale(hash);
+
+	st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr,
+				 ports, &net_secret);
+
+	if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1)
+		st.ts_off = 0;
+
+	st.seq = seq_scale(st.seq);
+	return st;
 }
-EXPORT_SYMBOL_GPL(secure_tcp_seq);
+EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off);
 
 u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 061751aabc8e..fc3affd9c801 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
 	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcp_ts_off(net,
-					  ip_hdr(skb)->daddr,
-					  ip_hdr(skb)->saddr);
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcp_seq_and_ts_off(net,
+					       ip_hdr(skb)->daddr,
+					       ip_hdr(skb)->saddr,
+					       tcp_hdr(skb)->dest,
+					       tcp_hdr(skb)->source);
+		tsoff = st.ts_off;
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7b03f2460751..cba89733d121 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7646,6 +7646,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct sock *fastopen_sk = NULL;
+	union tcp_seq_and_ts_off st;
 	struct request_sock *req;
 	bool want_cookie = false;
 	struct dst_entry *dst;
@@ -7715,9 +7716,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (!dst)
 		goto drop_and_free;
 
+	if (tmp_opt.tstamp_ok || (!want_cookie && !isn))
+		st = af_ops->init_seq_and_ts_off(net, skb);
+
 	if (tmp_opt.tstamp_ok) {
 		tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
-		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
+		tcp_rsk(req)->ts_off = st.ts_off;
 	}
 	if (!want_cookie && !isn) {
 		int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
@@ -7739,7 +7743,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			goto drop_and_release;
 		}
 
-		isn = af_ops->init_seq(skb);
+		isn = st.seq;
 	}
 
 	tcp_ecn_create_request(req, skb, sk, dst);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 910c25cb24e1..c7b2463c2e25 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -105,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
 
 static DEFINE_MUTEX(tcp_exit_batch_mutex);
 
-static u32 tcp_v4_init_seq(const struct sk_buff *skb)
+static union tcp_seq_and_ts_off
+tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)
 {
-	return secure_tcp_seq(ip_hdr(skb)->daddr,
-			      ip_hdr(skb)->saddr,
-			      tcp_hdr(skb)->dest,
-			      tcp_hdr(skb)->source);
-}
-
-static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
-{
-	return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr);
+	return secure_tcp_seq_and_ts_off(net,
+					 ip_hdr(skb)->daddr,
+					 ip_hdr(skb)->saddr,
+					 tcp_hdr(skb)->dest,
+					 tcp_hdr(skb)->source);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -327,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len
 	rt = NULL;
 
 	if (likely(!tp->repair)) {
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcp_seq_and_ts_off(net,
+					       inet->inet_saddr,
+					       inet->inet_daddr,
+					       inet->inet_sport,
+					       usin->sin_port);
 		if (!tp->write_seq)
-			WRITE_ONCE(tp->write_seq,
-				   secure_tcp_seq(inet->inet_saddr,
-						  inet->inet_daddr,
-						  inet->inet_sport,
-						  usin->sin_port));
-		WRITE_ONCE(tp->tsoffset,
-			   secure_tcp_ts_off(net, inet->inet_saddr,
-					     inet->inet_daddr));
+			WRITE_ONCE(tp->write_seq, st.seq);
+		WRITE_ONCE(tp->tsoffset, st.ts_off);
 	}
 
 	atomic_set(&inet->inet_id, get_random_u16());
@@ -1677,8 +1675,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
 	.route_req	=	tcp_v4_route_req,
-	.init_seq	=	tcp_v4_init_seq,
-	.init_ts_off	=	tcp_v4_init_ts_off,
+	.init_seq_and_ts_off	=	tcp_v4_init_seq_and_ts_off,
 	.send_synack	=	tcp_v4_send_synack,
 };
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7e007f013ec8..4f6f0d751d6c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
 	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
 
 	if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
-		tsoff = secure_tcpv6_ts_off(net,
-					    ipv6_hdr(skb)->daddr.s6_addr32,
-					    ipv6_hdr(skb)->saddr.s6_addr32);
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcpv6_seq_and_ts_off(net,
+						 ipv6_hdr(skb)->daddr.s6_addr32,
+						 ipv6_hdr(skb)->saddr.s6_addr32,
+						 tcp_hdr(skb)->dest,
+						 tcp_hdr(skb)->source);
+		tsoff = st.ts_off;
 		tcp_opt.rcv_tsecr -= tsoff;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5195a46b951e..bb09d5ccf599 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -105,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static u32 tcp_v6_init_seq(const struct sk_buff *skb)
+static union tcp_seq_and_ts_off
+tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb)
 {
-	return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
-				ipv6_hdr(skb)->saddr.s6_addr32,
-				tcp_hdr(skb)->dest,
-				tcp_hdr(skb)->source);
-}
-
-static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb)
-{
-	return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32,
-				   ipv6_hdr(skb)->saddr.s6_addr32);
+	return secure_tcpv6_seq_and_ts_off(net,
+					   ipv6_hdr(skb)->daddr.s6_addr32,
+					   ipv6_hdr(skb)->saddr.s6_addr32,
+					   tcp_hdr(skb)->dest,
+					   tcp_hdr(skb)->source);
 }
 
 static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
@@ -320,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
 	sk_set_txhash(sk);
 
 	if (likely(!tp->repair)) {
+		union tcp_seq_and_ts_off st;
+
+		st = secure_tcpv6_seq_and_ts_off(net,
+						 np->saddr.s6_addr32,
+						 sk->sk_v6_daddr.s6_addr32,
+						 inet->inet_sport,
+						 inet->inet_dport);
 		if (!tp->write_seq)
-			WRITE_ONCE(tp->write_seq,
-				   secure_tcpv6_seq(np->saddr.s6_addr32,
-						    sk->sk_v6_daddr.s6_addr32,
-						    inet->inet_sport,
-						    inet->inet_dport));
-		tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32,
-						   sk->sk_v6_daddr.s6_addr32);
+			WRITE_ONCE(tp->write_seq, st.seq);
+		tp->tsoffset = st.ts_off;
 	}
 
 	if (tcp_fastopen_defer_connect(sk, &err))
@@ -817,8 +815,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
 	.route_req	=	tcp_v6_route_req,
-	.init_seq	=	tcp_v6_init_seq,
-	.init_ts_off	=	tcp_v6_init_ts_off,
+	.init_seq_and_ts_off	= tcp_v6_init_seq_and_ts_off,
 	.send_synack	=	tcp_v6_send_synack,
 };
 
-- 
cgit v1.2.3


From f7d92f11bd33a6eb49c7c812255ef4ab13681f0f Mon Sep 17 00:00:00 2001
From: Ian Ray <ian.ray@gehealthcare.com>
Date: Mon, 2 Mar 2026 18:32:37 +0200
Subject: net: nfc: nci: Fix zero-length proprietary notifications

NCI NFC controllers may have proprietary OIDs with zero-length payload.
One example is: drivers/nfc/nxp-nci/core.c, NXP_NCI_RF_TXLDO_ERROR_NTF.

Allow a zero length payload in proprietary notifications *only*.

Before:

-- >8 --
kernel: nci: nci_recv_frame: len 3
-- >8 --

After:

-- >8 --
kernel: nci: nci_recv_frame: len 3
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x23, plen=0
kernel: nci: nci_ntf_packet: unknown ntf opcode 0x123
kernel: nfc nfc0: NFC: RF transmitter couldn't start. Bad power and/or configuration?
-- >8 --

After fixing the hardware:

-- >8 --
kernel: nci: nci_recv_frame: len 27
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x5, plen=24
kernel: nci: nci_rf_intf_activated_ntf_packet: rf_discovery_id 1
-- >8 --

Fixes: d24b03535e5e ("nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet")
Signed-off-by: Ian Ray <ian.ray@gehealthcare.com>
Link: https://patch.msgid.link/20260302163238.140576-1-ian.ray@gehealthcare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6e9b76e2cc56..e95eef85971f 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1482,10 +1482,20 @@ static bool nci_valid_size(struct sk_buff *skb)
 	unsigned int hdr_size = NCI_CTRL_HDR_SIZE;
 
 	if (skb->len < hdr_size ||
-	    !nci_plen(skb->data) ||
 	    skb->len < hdr_size + nci_plen(skb->data)) {
 		return false;
 	}
+
+	if (!nci_plen(skb->data)) {
+		/* Allow zero length in proprietary notifications (0x20 - 0x3F). */
+		if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 &&
+		    nci_mt(skb->data) == NCI_MT_NTF_PKT)
+			return true;
+
+		/* Disallow zero length otherwise. */
+		return false;
+	}
+
 	return true;
 }
 
-- 
cgit v1.2.3


From a4c2b8be2e5329e7fac6e8f64ddcb8958155cfcb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Mar 2026 01:56:40 +0000
Subject: net_sched: sch_fq: clear q->band_pkt_count[] in fq_reset()

When/if a NIC resets, queues are deactivated by dev_deactivate_many(),
then reactivated when the reset operation completes.

fq_reset() removes all the skbs from various queues.

If we do not clear q->band_pkt_count[], these counters keep growing
and can eventually reach sch->limit, preventing new packets to be queued.

Many thanks to Praveen for discovering the root cause.

Fixes: 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling")
Diagnosed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260304015640.961780-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_fq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 80235e85f844..05084c9af48e 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -827,6 +827,7 @@ static void fq_reset(struct Qdisc *sch)
 	for (idx = 0; idx < FQ_BANDS; idx++) {
 		q->band_flows[idx].new_flows.first = NULL;
 		q->band_flows[idx].old_flows.first = NULL;
+		q->band_pkt_count[idx] = 0;
 	}
 	q->delayed		= RB_ROOT;
 	q->flows		= 0;
-- 
cgit v1.2.3


From 40bf00ec2ee271df5ba67593991760adf8b5d0ed Mon Sep 17 00:00:00 2001
From: Bobby Eshleman <bobbyeshleman@meta.com>
Date: Mon, 2 Mar 2026 16:32:56 -0800
Subject: net: devmem: use READ_ONCE/WRITE_ONCE on binding->dev

binding->dev is protected on the write-side in
mp_dmabuf_devmem_uninstall() against concurrent writes, but due to the
concurrent bare reads in net_devmem_get_binding() and
validate_xmit_unreadable_skb() it should be wrapped in a
READ_ONCE/WRITE_ONCE pair to make sure no compiler optimizations play
with the underlying register in unforeseen ways.

Doesn't present a critical bug because the known compiler optimizations
don't result in bad behavior. There is no tearing on u64, and load
omissions/invented loads would only break if additional binding->dev
references were inlined together (they aren't right now).

This just more strictly follows the linux memory model (i.e.,
"Lock-Protected Writes With Lockless Reads" in
tools/memory-model/Documentation/access-marking.txt).

Fixes: bd61848900bf ("net: devmem: Implement TX path")
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260302-devmem-membar-fix-v2-1-5b33c9cbc28b@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c    | 2 +-
 net/core/devmem.c | 6 ++++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4af4cf2d63a4..20610a192ec7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb,
 	if (shinfo->nr_frags > 0) {
 		niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0]));
 		if (net_is_devmem_iov(niov) &&
-		    net_devmem_iov_binding(niov)->dev != dev)
+		    READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev)
 			goto out_free;
 	}
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 8c9aad776bf4..69d79aee07ef 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
 	 * net_device.
 	 */
 	dst_dev = dst_dev_rcu(dst);
-	if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) {
+	if (unlikely(!dst_dev) ||
+	    unlikely(dst_dev != READ_ONCE(binding->dev))) {
 		err = -ENODEV;
 		goto out_unlock;
 	}
@@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv,
 			xa_erase(&binding->bound_rxqs, xa_idx);
 			if (xa_empty(&binding->bound_rxqs)) {
 				mutex_lock(&binding->lock);
-				binding->dev = NULL;
+				ASSERT_EXCLUSIVE_WRITER(binding->dev);
+				WRITE_ONCE(binding->dev, NULL);
 				mutex_unlock(&binding->lock);
 			}
 			break;
-- 
cgit v1.2.3


From 7bd4b0c4779f978a6528c9b7937d2ca18e936e2c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:41 -0800
Subject: nfc: nci: free skb on nci_transceive early error paths

nci_transceive() takes ownership of the skb passed by the caller,
but the -EPROTO, -EINVAL, and -EBUSY error paths return without
freeing it.

Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes
the nci/nci_dev selftest hits the error path occasionally in NIPA,
and kmemleak detects leaks:

unreferenced object 0xff11000015ce6a40 (size 640):
  comm "nci_dev", pid 3954, jiffies 4295441246
  hex dump (first 32 bytes):
    6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b  kkkk.......kkkkk
    6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
  backtrace (crc 7c40cc2a):
    kmem_cache_alloc_node_noprof+0x492/0x630
    __alloc_skb+0x11e/0x5f0
    alloc_skb_with_frags+0xc6/0x8f0
    sock_alloc_send_pskb+0x326/0x3f0
    nfc_alloc_send_skb+0x94/0x1d0
    rawsock_sendmsg+0x162/0x4c0
    do_syscall_64+0x117/0xfc0

Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e95eef85971f..e859b834c0f1 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1035,18 +1035,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	struct nci_conn_info *conn_info;
 
 	conn_info = ndev->rf_conn_info;
-	if (!conn_info)
+	if (!conn_info) {
+		kfree_skb(skb);
 		return -EPROTO;
+	}
 
 	pr_debug("target_idx %d, len %d\n", target->idx, skb->len);
 
 	if (!ndev->target_active_prot) {
 		pr_err("unable to exchange data, no active target\n");
+		kfree_skb(skb);
 		return -EINVAL;
 	}
 
-	if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+	if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) {
+		kfree_skb(skb);
 		return -EBUSY;
+	}
 
 	/* store cb and context to be used on receiving data */
 	conn_info->data_exchange_cb = cb;
-- 
cgit v1.2.3


From d42449d2c17cdf06d1f63268557450bd3f051e9a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:42 -0800
Subject: nfc: digital: free skb on digital_in_send error paths

digital_in_send() takes ownership of the skb passed by the caller
(nfc_data_exchange), make sure it's freed on all error paths.

Found looking around the real driver for similar bugs to the one
just fixed in nci.

Fixes: 2c66daecc409 ("NFC Digital: Add NFC-A technology support")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/digital_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index 3670bb33732e..7cb1e6aaae90 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	int rc;
 
 	data_exch = kzalloc_obj(*data_exch);
-	if (!data_exch)
+	if (!data_exch) {
+		kfree_skb(skb);
 		return -ENOMEM;
+	}
 
 	data_exch->cb = cb;
 	data_exch->cb_context = cb_context;
@@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 				 data_exch);
 
 exit:
-	if (rc)
+	if (rc) {
+		kfree_skb(skb);
 		kfree(data_exch);
+	}
 
 	return rc;
 }
-- 
cgit v1.2.3


From 66083581945bd5b8e99fe49b5aeb83d03f62d053 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:43 -0800
Subject: nfc: nci: complete pending data exchange on device close

In nci_close_device(), complete any pending data exchange before
closing. The data exchange callback (e.g.
rawsock_data_exchange_complete) holds a socket reference.

NIPA occasionally hits this leak:

unreferenced object 0xff1100000f435000 (size 2048):
  comm "nci_dev", pid 3954, jiffies 4295441245
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    27 00 01 40 00 00 00 00 00 00 00 00 00 00 00 00  '..@............
  backtrace (crc ec2b3c5):
    __kmalloc_noprof+0x4db/0x730
    sk_prot_alloc.isra.0+0xe4/0x1d0
    sk_alloc+0x36/0x760
    rawsock_create+0xd1/0x540
    nfc_sock_create+0x11f/0x280
    __sock_create+0x22d/0x630
    __sys_socket+0x115/0x1d0
    __x64_sys_socket+0x72/0xd0
    do_syscall_64+0x117/0xfc0
    entry_SYSCALL_64_after_hwframe+0x4b/0x53

Fixes: 38f04c6b1b68 ("NFC: protect nci_data_exchange transactions")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e859b834c0f1..43d871525dbc 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev)
 		flush_workqueue(ndev->cmd_wq);
 		timer_delete_sync(&ndev->cmd_timer);
 		timer_delete_sync(&ndev->data_timer);
+		if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+			nci_data_exchange_complete(ndev, NULL,
+						   ndev->cur_conn_id,
+						   -ENODEV);
 		mutex_unlock(&ndev->req_lock);
 		return 0;
 	}
@@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev)
 	flush_workqueue(ndev->cmd_wq);
 
 	timer_delete_sync(&ndev->cmd_timer);
+	timer_delete_sync(&ndev->data_timer);
+
+	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
+		nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id,
+					   -ENODEV);
 
 	/* Clear flags except NCI_UNREG */
 	ndev->flags &= BIT(NCI_UNREG);
-- 
cgit v1.2.3


From 0efdc02f4f6d52f8ca5d5889560f325a836ce0a8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:44 -0800
Subject: nfc: nci: clear NCI_DATA_EXCHANGE before calling completion callback

Move clear_bit(NCI_DATA_EXCHANGE) before invoking the data exchange
callback in nci_data_exchange_complete().

The callback (e.g. rawsock_data_exchange_complete) may immediately
schedule another data exchange via schedule_work(tx_work).  On a
multi-CPU system, tx_work can run and reach nci_transceive() before
the current nci_data_exchange_complete() clears the flag, causing
test_and_set_bit(NCI_DATA_EXCHANGE) to return -EBUSY and the new
transfer to fail.

This causes intermittent flakes in nci/nci_dev in NIPA:

  # #  RUN           NCI.NCI1_0.t4t_tag_read ...
  # # t4t_tag_read: Test terminated by timeout
  # #          FAIL  NCI.NCI1_0.t4t_tag_read
  # not ok 3 NCI.NCI1_0.t4t_tag_read

Fixes: 38f04c6b1b68 ("NFC: protect nci_data_exchange transactions")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/data.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index 78f4131af3cf..5f98c73db5af 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
 	if (!conn_info) {
 		kfree_skb(skb);
-		goto exit;
+		clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
+		return;
 	}
 
 	cb = conn_info->data_exchange_cb;
@@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	timer_delete_sync(&ndev->data_timer);
 	clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 
+	/* Mark the exchange as done before calling the callback.
+	 * The callback (e.g. rawsock_data_exchange_complete) may
+	 * want to immediately queue another data exchange.
+	 */
+	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
+
 	if (cb) {
 		/* forward skb to nfc core */
 		cb(cb_context, skb, err);
@@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 		/* no waiting callback, free skb */
 		kfree_skb(skb);
 	}
-
-exit:
-	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
 }
 
 /* ----------------- NCI TX Data ----------------- */
-- 
cgit v1.2.3


From d793458c45df2aed498d7f74145eab7ee22d25aa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 08:23:45 -0800
Subject: nfc: rawsock: cancel tx_work before socket teardown

In rawsock_release(), cancel any pending tx_work and purge the write
queue before orphaning the socket.  rawsock_tx_work runs on the system
workqueue and calls nfc_data_exchange which dereferences the NCI
device.  Without synchronization, tx_work can race with socket and
device teardown when a process is killed (e.g. by SIGKILL), leading
to use-after-free or leaked references.

Set SEND_SHUTDOWN first so that if tx_work is already running it will
see the flag and skip transmitting, then use cancel_work_sync to wait
for any in-progress execution to finish, and finally purge any
remaining queued skbs.

Fixes: 23b7869c0fd0 ("NFC: add the NFC socket raw protocol")
Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20260303162346.2071888-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/rawsock.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index b049022399ae..f7d7a599fade 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock)
 	if (sock->type == SOCK_RAW)
 		nfc_sock_unlink(&raw_sk_list, sk);
 
+	if (sk->sk_state == TCP_ESTABLISHED) {
+		/* Prevent rawsock_tx_work from starting new transmits and
+		 * wait for any in-progress work to finish.  This must happen
+		 * before the socket is orphaned to avoid a race where
+		 * rawsock_tx_work runs after the NCI device has been freed.
+		 */
+		sk->sk_shutdown |= SEND_SHUTDOWN;
+		cancel_work_sync(&nfc_rawsock(sk)->tx_work);
+		rawsock_write_queue_purge(sk);
+	}
+
 	sock_orphan(sk);
 	sock_put(sk);
 
-- 
cgit v1.2.3


From 8c09412e584d9bcc0e71d758ec1008d1c8d1a326 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 3 Mar 2026 11:56:02 +0100
Subject: selftests: mptcp: more stable simult_flows tests

By default, the netem qdisc can keep up to 1000 packets under its belly
to deal with the configured rate and delay. The simult flows test-case
simulates very low speed links, to avoid problems due to slow CPUs and
the TCP stack tend to transmit at a slightly higher rate than the
(virtual) link constraints.

All the above causes a relatively large amount of packets being enqueued
in the netem qdiscs - the longer the transfer, the longer the queue -
producing increasingly high TCP RTT samples and consequently increasingly
larger receive buffer size due to DRS.

When the receive buffer size becomes considerably larger than the needed
size, the tests results can flake, i.e. because minimal inaccuracy in the
pacing rate can lead to a single subflow usage towards the end of the
connection for a considerable amount of data.

Address the issue explicitly setting netem limits suitable for the
configured link speeds and unflake all the affected tests.

Fixes: 1a418cb8e888 ("mptcp: simult flow self-tests")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-1-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 806aaa7d2d61..d11a8b949aab 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -237,10 +237,13 @@ run_test()
 	for dev in ns2eth1 ns2eth2; do
 		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
 	done
-	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
-	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# keep the queued pkts number low, or the RTT estimator will see
+	# increasing latency over time.
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50
 
 	# time is measured in ms, account for transfer size, aggregated link speed
 	# and header overhead (10%)
-- 
cgit v1.2.3


From fb8d0bccb221080630efcd9660c9f9349e53cc9e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:03 +0100
Subject: mptcp: pm: avoid sending RM_ADDR over same subflow

RM_ADDR are sent over an active subflow, the first one in the subflows
list. There is then a high chance the initial subflow is picked. With
the in-kernel PM, when an endpoint is removed, a RM_ADDR is sent, then
linked subflows are closed. This is done for each active MPTCP
connection.

MPTCP endpoints are likely removed because the attached network is no
longer available or usable. In this case, it is better to avoid sending
this RM_ADDR over the subflow that is going to be removed, but prefer
sending it over another active and non stale subflow, if any.

This modification avoids situations where the other end is not notified
when a subflow is no longer usable: typically when the endpoint linked
to the initial subflow is removed, especially on the server side.

Fixes: 8dd5efb1f91b ("mptcp: send ack for rm_addr")
Cc: stable@vger.kernel.org
Reported-by: Frank Lorenz <lorenz-frank@web.de>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/612
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-2-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c | 55 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 7298836469b3..57a456690406 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 }
 
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
+			       const struct mptcp_rm_list *rm_list)
+{
+	u8 i, id = subflow_get_local_id(subflow);
+
+	for (i = 0; i < rm_list->nr; i++) {
+		if (rm_list->ids[i] == id)
+			return true;
+	}
+
+	return false;
+}
+
+static void
+mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
+				  const struct mptcp_rm_list *rm_list)
 {
-	struct mptcp_subflow_context *subflow, *alt = NULL;
+	struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
+		if (!__mptcp_subflow_active(subflow))
+			continue;
 
-			if (!alt)
-				alt = subflow;
+		if (unlikely(subflow->stale)) {
+			if (!stale)
+				stale = subflow;
+		} else if (unlikely(rm_list &&
+				    subflow_in_rm_list(subflow, rm_list))) {
+			if (!same_id)
+				same_id = subflow;
+		} else {
+			goto send_ack;
 		}
 	}
 
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
+	if (same_id)
+		subflow = same_id;
+	else if (stale)
+		subflow = stale;
+	else
+		return;
+
+send_ack:
+	mptcp_pm_send_ack(msk, subflow, false, false);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	mptcp_pm_addr_send_ack_avoid_list(msk, NULL);
 }
 
 int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack_avoid_list(msk, rm_list);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 560edd99b5f58b2d4bbe3c8e51e1eed68d887b0e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:04 +0100
Subject: selftests: mptcp: join: check RM_ADDR not sent over same subflow

This validates the previous commit: RM_ADDR were sent over the first
found active subflow which could be the same as the one being removed.
It is more likely to loose this notification.

For this check, RM_ADDR are explicitly dropped when trying to send them
over the initial subflow, when removing the endpoint attached to it. If
it is dropped, the test will complain because some RM_ADDR have not been
received.

Note that only the RM_ADDR are dropped, to allow the linked subflow to
be quickly and cleanly closed. To only drop those RM_ADDR, a cBPF byte
code is used. If the IPTables commands fail, that's OK, the tests will
continue to pass, but not validate this part. This can be ignored:
another subtest fully depends on such command, and will be marked as
skipped.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 8dd5efb1f91b ("mptcp: send ack for rm_addr")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-3-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 36 +++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index dc1f200aaa81..058ad5a13d24 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
 			       6 0 0 65535,
 			       6 0 0 0"
 
+# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption
+# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c &&
+#				  (ip[66] & 0xf0) == 0x40'"
+CBPF_MPTCP_SUBOPTION_RM_ADDR="13,
+			      48 0 0 0,
+			      84 0 0 240,
+			      21 0 9 64,
+			      48 0 0 32,
+			      84 0 0 240,
+			      21 0 6 192,
+			      48 0 0 53,
+			      21 0 4 12,
+			      48 0 0 66,
+			      84 0 0 240,
+			      21 0 1 64,
+			      6 0 0 65535,
+			      6 0 0 0"
+
 init_partial()
 {
 	capout=$(mktemp)
@@ -4217,6 +4235,14 @@ endpoint_tests()
 		chk_subflow_nr "after no reject" 3
 		chk_mptcp_info subflows 2 subflows 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		local i
 		for i in $(seq 3); do
 			pm_nl_del_endpoint $ns2 1 10.0.1.2
@@ -4229,6 +4255,7 @@ endpoint_tests()
 			chk_subflow_nr "after re-add id 0 ($i)" 3
 			chk_mptcp_info subflows 3 subflows 3
 		done
+		[ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1
 
 		mptcp_lib_kill_group_wait $tests_pid
 
@@ -4288,11 +4315,20 @@ endpoint_tests()
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		pm_nl_del_endpoint $ns1 42 10.0.1.1
 		sleep 0.5
 		chk_subflow_nr "after delete ID 0" 2
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
+		[ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1
 
 		pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
 		wait_mpj 4
-- 
cgit v1.2.3


From 579a752464a64cb5f9139102f0e6b90a1f595ceb Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:05 +0100
Subject: mptcp: pm: in-kernel: always mark signal+subflow endp as used

Syzkaller managed to find a combination of actions that was generating
this warning:

  msk->pm.local_addr_used == 0
  WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961
  Modules linked in:
  CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full)
  Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014
  RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline]
  RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline]
  RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210
  Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a
  RSP: 0018:ffffc90001663880 EFLAGS: 00010293
  RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff
  R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640
  R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650
  FS:  00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115
   genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
   genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210
   netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550
   genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
   netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
   netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344
   netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894
   sock_sendmsg_nosec net/socket.c:727 [inline]
   __sock_sendmsg+0xc9/0xf0 net/socket.c:742
   ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592
   ___sys_sendmsg+0x2de/0x320 net/socket.c:2646
   __sys_sendmsg net/socket.c:2678 [inline]
   __do_sys_sendmsg net/socket.c:2683 [inline]
   __se_sys_sendmsg net/socket.c:2681 [inline]
   __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f66346f826d
  Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d
  RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007
  RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8
  R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770
   </TASK>

The actions that caused that seem to be:

 - Set the MPTCP subflows limit to 0
 - Create an MPTCP endpoint with both the 'signal' and 'subflow' flags
 - Create a new MPTCP connection from a different address: an ADD_ADDR
   linked to the MPTCP endpoint will be sent ('signal' flag), but no
   subflows is initiated ('subflow' flag)
 - Remove the MPTCP endpoint

In this case, msk->pm.local_addr_used has been kept to 0 -- because no
subflows have been created -- but the corresponding bit in
msk->pm.id_avail_bitmap has been cleared when the ADD_ADDR has been
sent. This later causes a splat when removing the MPTCP endpoint because
msk->pm.local_addr_used has been kept to 0.

Now, if an endpoint has both the signal and subflow flags, but it is not
possible to create subflows because of the limits or the c-flag case,
then the local endpoint counter is still incremented: the endpoint is
used at the end. This avoids issues later when removing the endpoint and
calling __mark_subflow_endp_available(), which expects
msk->pm.local_addr_used to have been previously incremented if the
endpoint was marked as used according to msk->pm.id_avail_bitmap.

Note that signal_and_subflow variable is reset to false when the limits
and the c-flag case allows subflows creation. Also, local_addr_used is
only incremented for non ID0 subflows.

Fixes: 85df533a787b ("mptcp: pm: do not ignore 'subflow' if 'signal' flag is also set")
Cc: stable@vger.kernel.org
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/613
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-4-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_kernel.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index b5316a6c7d1b..b2b9df43960e 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -418,6 +418,15 @@ subflow:
 	}
 
 exit:
+	/* If an endpoint has both the signal and subflow flags, but it is not
+	 * possible to create subflows -- the 'while' loop body above never
+	 * executed --  then still mark the endp as used, which is somehow the
+	 * case. This avoids issues later when removing the endpoint and calling
+	 * __mark_subflow_endp_available(), which expects the increment here.
+	 */
+	if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id)
+		msk->pm.local_addr_used++;
+
 	mptcp_pm_nl_check_work_pending(msk);
 }
 
-- 
cgit v1.2.3


From 1777f349ff41b62dfe27454b69c27b0bc99ffca5 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 3 Mar 2026 11:56:06 +0100
Subject: selftests: mptcp: join: check removing signal+subflow endp

This validates the previous commit: endpoints with both the signal and
subflow flags should always be marked as used even if it was not
possible to create new subflows due to the MPTCP PM limits.

For this test, an extra endpoint is created with both the signal and the
subflow flags, and limits are set not to create extra subflows. In this
case, an ADD_ADDR is sent, but no subflows are created. Still, the local
endpoint is marked as used, and no warning is fired when removing the
endpoint, after having sent a RM_ADDR.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 85df533a787b ("mptcp: pm: do not ignore 'subflow' if 'signal' flag is also set")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260303-net-mptcp-misc-fixes-7-0-rc2-v1-5-4b5462b6f016@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 058ad5a13d24..a3144d7298a5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -2626,6 +2626,19 @@ remove_tests()
 		chk_rst_nr 0 0
 	fi
 
+	# signal+subflow with limits, remove
+	if reset "remove signal+subflow with limits"; then
+		pm_nl_set_limits $ns1 0 0
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow
+		pm_nl_set_limits $ns2 0 0
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 0 0 0
+		chk_add_nr 1 1
+		chk_rm_nr 1 0 invert
+		chk_rst_nr 0 0
+	fi
+
 	# addresses remove
 	if reset "remove addresses"; then
 		pm_nl_set_limits $ns1 3 3
-- 
cgit v1.2.3


From 35dfedce442c4060cfe5b98368bc9643fb995716 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:25 +0000
Subject: net: stmmac: Fix error handling in VLAN add and delete paths

stmmac_vlan_rx_add_vid() updates active_vlans and the VLAN hash
register before writing the HW filter entry. If the filter write
fails, it leaves a stale VID in active_vlans and the hash register.

stmmac_vlan_rx_kill_vid() has the reverse problem: it clears
active_vlans before removing the HW filter. On failure, the VID is
gone from active_vlans but still present in the HW filter table.

To fix this, reorder the operations to update the hash table first,
then attempt the HW filter operation. If the HW filter fails, roll
back both the active_vlans bitmap and the hash table by calling
stmmac_vlan_update() again.

Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-2-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e00aa42a1961..b6a127316ab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6794,9 +6794,13 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 
 	if (priv->hw->num_vlan) {
 		ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
-		if (ret)
+		if (ret) {
+			clear_bit(vid, priv->active_vlans);
+			stmmac_vlan_update(priv, is_double);
 			goto err_pm_put;
+		}
 	}
+
 err_pm_put:
 	pm_runtime_put(priv->device);
 
@@ -6820,15 +6824,21 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		is_double = true;
 
 	clear_bit(vid, priv->active_vlans);
+	ret = stmmac_vlan_update(priv, is_double);
+	if (ret) {
+		set_bit(vid, priv->active_vlans);
+		goto del_vlan_error;
+	}
 
 	if (priv->hw->num_vlan) {
 		ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
-		if (ret)
+		if (ret) {
+			set_bit(vid, priv->active_vlans);
+			stmmac_vlan_update(priv, is_double);
 			goto del_vlan_error;
+		}
 	}
 
-	ret = stmmac_vlan_update(priv, is_double);
-
 del_vlan_error:
 	pm_runtime_put(priv->device);
 
-- 
cgit v1.2.3


From e38200e361cbe331806dc454c76c11c7cd95e1b9 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:26 +0000
Subject: net: stmmac: Improve double VLAN handling

The double VLAN bits (EDVLP, ESVL, DOVLTC) are handled inconsistently
between the two vlan_update_hash() implementations:

- dwxgmac2_update_vlan_hash() explicitly clears the double VLAN bits when
is_double is false, meaning that adding a 802.1Q VLAN will disable
double VLAN mode:

  $ ip link add link eth0 name eth0.200 type vlan id 200 protocol 802.1ad
  $ ip link add link eth0 name eth0.100 type vlan id 100
  # Double VLAN bits no longer set

- vlan_update_hash() sets these bits and only clears them when the last
VLAN has been removed, so double VLAN mode remains enabled even after all
802.1AD VLANs are removed.

Address both issues by tracking the number of active 802.1AD VLANs in
priv->num_double_vlans. Pass this count to stmmac_vlan_update() so both
implementations correctly set the double VLAN bits when any 802.1AD
VLAN is active, and clear them only when none remain.

Also update vlan_update_hash() to explicitly clear the double VLAN bits
when is_double is false, matching the dwxgmac2 behavior.

Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-3-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      |  1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 16 ++++++++++++----
 drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c |  8 ++++++++
 3 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 51c96a738151..33667a26708c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -323,6 +323,7 @@ struct stmmac_priv {
 	void __iomem *ptpaddr;
 	void __iomem *estaddr;
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	unsigned int num_double_vlans;
 	int sfty_irq;
 	int sfty_ce_irq;
 	int sfty_ue_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b6a127316ab5..01d181c2c68e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6775,6 +6775,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int num_double_vlans;
 	bool is_double = false;
 	int ret;
 
@@ -6786,7 +6787,8 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 		is_double = true;
 
 	set_bit(vid, priv->active_vlans);
-	ret = stmmac_vlan_update(priv, is_double);
+	num_double_vlans = priv->num_double_vlans + is_double;
+	ret = stmmac_vlan_update(priv, num_double_vlans);
 	if (ret) {
 		clear_bit(vid, priv->active_vlans);
 		goto err_pm_put;
@@ -6796,11 +6798,13 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 		ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
 		if (ret) {
 			clear_bit(vid, priv->active_vlans);
-			stmmac_vlan_update(priv, is_double);
+			stmmac_vlan_update(priv, priv->num_double_vlans);
 			goto err_pm_put;
 		}
 	}
 
+	priv->num_double_vlans = num_double_vlans;
+
 err_pm_put:
 	pm_runtime_put(priv->device);
 
@@ -6813,6 +6817,7 @@ err_pm_put:
 static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int num_double_vlans;
 	bool is_double = false;
 	int ret;
 
@@ -6824,7 +6829,8 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		is_double = true;
 
 	clear_bit(vid, priv->active_vlans);
-	ret = stmmac_vlan_update(priv, is_double);
+	num_double_vlans = priv->num_double_vlans - is_double;
+	ret = stmmac_vlan_update(priv, num_double_vlans);
 	if (ret) {
 		set_bit(vid, priv->active_vlans);
 		goto del_vlan_error;
@@ -6834,11 +6840,13 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi
 		ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid);
 		if (ret) {
 			set_bit(vid, priv->active_vlans);
-			stmmac_vlan_update(priv, is_double);
+			stmmac_vlan_update(priv, priv->num_double_vlans);
 			goto del_vlan_error;
 		}
 	}
 
+	priv->num_double_vlans = num_double_vlans;
+
 del_vlan_error:
 	pm_runtime_put(priv->device);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index b18404dd5a8b..de1a70e1c86e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -183,6 +183,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
 			value |= VLAN_EDVLP;
 			value |= VLAN_ESVL;
 			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
 		}
 
 		writel(value, ioaddr + VLAN_TAG);
@@ -193,6 +197,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
 			value |= VLAN_EDVLP;
 			value |= VLAN_ESVL;
 			value |= VLAN_DOVLTC;
+		} else {
+			value &= ~VLAN_EDVLP;
+			value &= ~VLAN_ESVL;
+			value &= ~VLAN_DOVLTC;
 		}
 
 		writel(value | perfect_match, ioaddr + VLAN_TAG);
-- 
cgit v1.2.3


From bd7ad51253a76fb35886d01cfe9a37f0e4ed6709 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:27 +0000
Subject: net: stmmac: Fix VLAN HW state restore

When the network interface is opened or resumed, a DMA reset is performed,
which resets all hardware state, including VLAN state. Currently, only
the resume path is restoring the VLAN state via
stmmac_restore_hw_vlan_rx_fltr(), but that is incomplete: the VLAN hash
table and the VLAN_TAG control bits are not restored.

Therefore, add stmmac_vlan_restore(), which restores the full VLAN
state by updating both the HW filter entries and the hash table, and
call it from both the open and resume paths.

The VLAN restore is moved outside of phylink_rx_clk_stop_block/unblock
in the resume path because receive clock stop is already disabled when
stmmac supports VLAN.

Also, remove the hash readback code in vlan_restore_hw_rx_fltr() that
attempts to restore VTHM by reading VLAN_HASH_TABLE, as it always reads
zero after DMA reset, making it dead code.

Fixes: 3cd1cfcba26e ("net: stmmac: Implement VLAN Hash Filtering in XGMAC")
Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-4-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 24 +++++++++++++++++++++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c | 10 ----------
 2 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 01d181c2c68e..6d4ce35e990f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -156,6 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue);
 static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue);
 static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 					  u32 rxmode, u32 chan);
+static int stmmac_vlan_restore(struct stmmac_priv *priv);
 
 #ifdef CONFIG_DEBUG_FS
 static const struct net_device_ops stmmac_netdev_ops;
@@ -4107,6 +4108,8 @@ static int __stmmac_open(struct net_device *dev,
 
 	phylink_start(priv->phylink);
 
+	stmmac_vlan_restore(priv);
+
 	ret = stmmac_request_irq(dev);
 	if (ret)
 		goto irq_error;
@@ -6853,6 +6856,23 @@ del_vlan_error:
 	return ret;
 }
 
+static int stmmac_vlan_restore(struct stmmac_priv *priv)
+{
+	int ret;
+
+	if (!(priv->dev->features & NETIF_F_VLAN_FEATURES))
+		return 0;
+
+	if (priv->hw->num_vlan)
+		stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw);
+
+	ret = stmmac_vlan_update(priv, priv->num_double_vlans);
+	if (ret)
+		netdev_err(priv->dev, "Failed to restore VLANs\n");
+
+	return ret;
+}
+
 static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -8277,10 +8297,10 @@ int stmmac_resume(struct device *dev)
 	stmmac_init_coalesce(priv);
 	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_rx_mode(ndev);
-
-	stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw);
 	phylink_rx_clk_stop_unblock(priv->phylink);
 
+	stmmac_vlan_restore(priv);
+
 	stmmac_enable_all_queues(priv);
 	stmmac_enable_all_dma_irq(priv);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index de1a70e1c86e..fcc34867405e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -139,9 +139,6 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 				    struct mac_device_info *hw)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-	u32 hash;
 	u32 val;
 	int i;
 
@@ -158,13 +155,6 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 			vlan_write_filter(dev, hw, i, val);
 		}
 	}
-
-	hash = readl(ioaddr + VLAN_HASH_TABLE);
-	if (hash & VLAN_VLHT) {
-		value = readl(ioaddr + VLAN_TAG);
-		value |= VLAN_VTHM;
-		writel(value, ioaddr + VLAN_TAG);
-	}
 }
 
 static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
-- 
cgit v1.2.3


From 2cd70e3968f505996d5fefdf7ca684f0f4575734 Mon Sep 17 00:00:00 2001
From: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Date: Tue, 3 Mar 2026 14:58:28 +0000
Subject: net: stmmac: Defer VLAN HW configuration when interface is down

VLAN register accesses on the MAC side require the PHY RX clock to be
active. When the network interface is down, the PHY is suspended and
the RX clock is unavailable, causing VLAN operations to fail with
timeouts.

The VLAN core automatically removes VID 0 after the interface goes down
and re-adds it when it comes back up, so these timeouts happen during
normal interface down/up:

    # ip link set end1 down
    renesas-gbeth 15c40000.ethernet end1: Timeout accessing MAC_VLAN_Tag_Filter
    renesas-gbeth 15c40000.ethernet end1: failed to kill vid 0081/0

Adding VLANs while the interface is down also fails:

    # ip link add link end1 name end1.10 type vlan id 10
    renesas-gbeth 15c40000.ethernet end1: Timeout accessing MAC_VLAN_Tag_Filter
    RTNETLINK answers: Device or resource busy

To fix this, check if the interface is up before accessing VLAN registers.
The software state is always kept up to date regardless of interface state.

When the interface is brought up, stmmac_vlan_restore() is called
to write the VLAN state to hardware.

Fixes: ed64639bc1e0 ("net: stmmac: Add support for VLAN Rx filtering")
Signed-off-by: Ovidiu Panait <ovidiu.panait.rb@renesas.com>
Link: https://patch.msgid.link/20260303145828.7845-5-ovidiu.panait.rb@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  3 ++
 drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c | 42 +++++++++++++----------
 2 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6d4ce35e990f..6827c99bde8c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6769,6 +6769,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 		hash = 0;
 	}
 
+	if (!netif_running(priv->dev))
+		return 0;
+
 	return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
index fcc34867405e..e24efe3bfedb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c
@@ -76,7 +76,9 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev,
 		}
 
 		hw->vlan_filter[0] = vid;
-		vlan_write_single(dev, vid);
+
+		if (netif_running(dev))
+			vlan_write_single(dev, vid);
 
 		return 0;
 	}
@@ -97,12 +99,15 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev,
 		return -EPERM;
 	}
 
-	ret = vlan_write_filter(dev, hw, index, val);
+	if (netif_running(dev)) {
+		ret = vlan_write_filter(dev, hw, index, val);
+		if (ret)
+			return ret;
+	}
 
-	if (!ret)
-		hw->vlan_filter[index] = val;
+	hw->vlan_filter[index] = val;
 
-	return ret;
+	return 0;
 }
 
 static int vlan_del_hw_rx_fltr(struct net_device *dev,
@@ -115,7 +120,9 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 	if (hw->num_vlan == 1) {
 		if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) {
 			hw->vlan_filter[0] = 0;
-			vlan_write_single(dev, 0);
+
+			if (netif_running(dev))
+				vlan_write_single(dev, 0);
 		}
 		return 0;
 	}
@@ -124,22 +131,23 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev,
 	for (i = 0; i < hw->num_vlan; i++) {
 		if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) &&
 		    ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) {
-			ret = vlan_write_filter(dev, hw, i, 0);
 
-			if (!ret)
-				hw->vlan_filter[i] = 0;
-			else
-				return ret;
+			if (netif_running(dev)) {
+				ret = vlan_write_filter(dev, hw, i, 0);
+				if (ret)
+					return ret;
+			}
+
+			hw->vlan_filter[i] = 0;
 		}
 	}
 
-	return ret;
+	return 0;
 }
 
 static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 				    struct mac_device_info *hw)
 {
-	u32 val;
 	int i;
 
 	/* Single Rx VLAN Filter */
@@ -149,12 +157,8 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev,
 	}
 
 	/* Extended Rx VLAN Filter Enable */
-	for (i = 0; i < hw->num_vlan; i++) {
-		if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) {
-			val = hw->vlan_filter[i];
-			vlan_write_filter(dev, hw, i, val);
-		}
-	}
+	for (i = 0; i < hw->num_vlan; i++)
+		vlan_write_filter(dev, hw, i, hw->vlan_filter[i]);
 }
 
 static void vlan_update_hash(struct mac_device_info *hw, u32 hash,
-- 
cgit v1.2.3


From 281cb17787d4284a7790b9cbd80fded826ca7739 Mon Sep 17 00:00:00 2001
From: hongao <hongao@uniontech.com>
Date: Wed, 4 Mar 2026 19:29:14 +0800
Subject: xfs: Remove redundant NULL check after __GFP_NOFAIL

kzalloc() is called with __GFP_NOFAIL, so a NULL return is not expected.
Drop the redundant !map check in xfs_dabuf_map().
Also switch the nirecs-sized allocation to kcalloc().

Signed-off-by: hongao <hongao@uniontech.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_da_btree.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 766631f0562e..09d4c17b3e7b 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2716,12 +2716,8 @@ xfs_dabuf_map(
 	 * larger one that needs to be free by the caller.
 	 */
 	if (nirecs > 1) {
-		map = kzalloc(nirecs * sizeof(struct xfs_buf_map),
-				GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
-		if (!map) {
-			error = -ENOMEM;
-			goto out_free_irecs;
-		}
+		map = kcalloc(nirecs, sizeof(struct xfs_buf_map),
+			      GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
 		*mapp = map;
 	}
 
-- 
cgit v1.2.3


From c242e92c9da456d361d1d4482fb6e93ee95bd8cf Mon Sep 17 00:00:00 2001
From: Kamal Heib <kheib@redhat.com>
Date: Mon, 2 Mar 2026 23:36:45 -0500
Subject: RDMA/bng_re: Fix silent failure in HWRM version query

If the firmware version query fails, the driver currently ignores the
error and continues initializing. This leaves the device in a bad state.

Fix this by making bng_re_query_hwrm_version() return the error code and
update the driver to check for this error and stop the setup process
safely if it happens.

Fixes: 745065770c2d ("RDMA/bng_re: Register and get the resources from bnge driver")
Signed-off-by: Kamal Heib <kheib@redhat.com>
Link: https://patch.msgid.link/20260303043645.425724-1-kheib@redhat.com
Reviewed-by: Siva Reddy Kallam <siva.kallam@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bng_re/bng_dev.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c
index d34b5f88cd40..71a7ca2196ad 100644
--- a/drivers/infiniband/hw/bng_re/bng_dev.c
+++ b/drivers/infiniband/hw/bng_re/bng_dev.c
@@ -210,7 +210,7 @@ static int bng_re_stats_ctx_alloc(struct bng_re_dev *rdev)
 	return rc;
 }
 
-static void bng_re_query_hwrm_version(struct bng_re_dev *rdev)
+static int bng_re_query_hwrm_version(struct bng_re_dev *rdev)
 {
 	struct bnge_auxr_dev *aux_dev = rdev->aux_dev;
 	struct hwrm_ver_get_output ver_get_resp = {};
@@ -230,7 +230,7 @@ static void bng_re_query_hwrm_version(struct bng_re_dev *rdev)
 	if (rc) {
 		ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x",
 			  rc);
-		return;
+		return rc;
 	}
 
 	cctx = rdev->chip_ctx;
@@ -244,6 +244,8 @@ static void bng_re_query_hwrm_version(struct bng_re_dev *rdev)
 
 	if (!cctx->hwrm_cmd_max_timeout)
 		cctx->hwrm_cmd_max_timeout = BNG_ROCE_FW_MAX_TIMEOUT;
+
+	return 0;
 }
 
 static void bng_re_dev_uninit(struct bng_re_dev *rdev)
@@ -306,13 +308,15 @@ static int bng_re_dev_init(struct bng_re_dev *rdev)
 		goto msix_ctx_fail;
 	}
 
-	bng_re_query_hwrm_version(rdev);
+	rc = bng_re_query_hwrm_version(rdev);
+	if (rc)
+		goto destroy_chip_ctx;
 
 	rc = bng_re_alloc_fw_channel(&rdev->bng_res, &rdev->rcfw);
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 			  "Failed to allocate RCFW Channel: %#x\n", rc);
-		goto alloc_fw_chl_fail;
+		goto destroy_chip_ctx;
 	}
 
 	/* Allocate nq record memory */
@@ -391,7 +395,7 @@ free_rcfw:
 	kfree(rdev->nqr);
 nq_alloc_fail:
 	bng_re_free_rcfw_channel(&rdev->rcfw);
-alloc_fw_chl_fail:
+destroy_chip_ctx:
 	bng_re_destroy_chip_ctx(rdev);
 msix_ctx_fail:
 	bnge_unregister_dev(rdev->aux_dev);
-- 
cgit v1.2.3


From ce8ee8583ed83122405eabaa8fb351be4d9dc65c Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 5 Mar 2026 11:15:50 +0800
Subject: block: use trylock to avoid lockdep circular dependency in sysfs

Use trylock instead of blocking lock acquisition for update_nr_hwq_lock
in queue_requests_store() and elv_iosched_store() to avoid circular lock
dependency with kernfs active reference during concurrent disk deletion:

  update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
  kn->active -> update_nr_hwq_lock (via sysfs write path)

Return -EBUSY when the lock is not immediately available.

Reported-and-tested-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs-em-4acsHabMdT=jJhXkCzjnprD-aQH1OgrZo4nTnmMw@mail.gmail.com/
Fixes: 626ff4f8ebcb ("blk-mq: convert to serialize updating nr_requests with update_nr_hwq_lock")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-sysfs.c |  8 +++++++-
 block/elevator.c  | 12 +++++++++++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f3b1968c80ce..55a1bbfef7d4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -78,8 +78,14 @@ queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 	/*
 	 * Serialize updating nr_requests with concurrent queue_requests_store()
 	 * and switching elevator.
+	 *
+	 * Use trylock to avoid circular lock dependency with kernfs active
+	 * reference during concurrent disk deletion:
+	 *   update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
+	 *   kn->active -> update_nr_hwq_lock (via this sysfs write path)
 	 */
-	down_write(&set->update_nr_hwq_lock);
+	if (!down_write_trylock(&set->update_nr_hwq_lock))
+		return -EBUSY;
 
 	if (nr == q->nr_requests)
 		goto unlock;
diff --git a/block/elevator.c b/block/elevator.c
index ebe2a1fcf011..3bcd37c2aa34 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -807,7 +807,16 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	elv_iosched_load_module(ctx.name);
 	ctx.type = elevator_find_get(ctx.name);
 
-	down_read(&set->update_nr_hwq_lock);
+	/*
+	 * Use trylock to avoid circular lock dependency with kernfs active
+	 * reference during concurrent disk deletion:
+	 *   update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
+	 *   kn->active -> update_nr_hwq_lock (via this sysfs write path)
+	 */
+	if (!down_read_trylock(&set->update_nr_hwq_lock)) {
+		ret = -EBUSY;
+		goto out;
+	}
 	if (!blk_queue_no_elv_switch(q)) {
 		ret = elevator_change(q, &ctx);
 		if (!ret)
@@ -817,6 +826,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	}
 	up_read(&set->update_nr_hwq_lock);
 
+out:
 	if (ctx.type)
 		elevator_put(ctx.type);
 	return ret;
-- 
cgit v1.2.3


From b824c3e16c1904bf80df489e293d1e3cbf98896d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 2 Mar 2026 17:26:31 +0100
Subject: net: Provide a PREEMPT_RT specific check for netdev_queue::_xmit_lock

After acquiring netdev_queue::_xmit_lock the number of the CPU owning
the lock is recorded in netdev_queue::xmit_lock_owner. This works as
long as the BH context is not preemptible.

On PREEMPT_RT the softirq context is preemptible and without the
softirq-lock it is possible to have multiple user in __dev_queue_xmit()
submitting a skb on the same CPU. This is fine in general but this means
also that the current CPU is recorded as netdev_queue::xmit_lock_owner.
This in turn leads to the recursion alert and the skb is dropped.

Instead checking the for CPU number, that owns the lock, PREEMPT_RT can
check if the lockowner matches the current task.

Add netif_tx_owned() which returns true if the current context owns the
lock by comparing the provided CPU number with the recorded number. This
resembles the current check by negating the condition (the current check
returns true if the lock is not owned).
On PREEMPT_RT use rt_mutex_owner() to return the lock owner and compare
the current task against it.
Use the new helper in __dev_queue_xmit() and netif_local_xmit_active()
which provides a similar check.
Update comments regarding pairing READ_ONCE().

Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/all/20260216134333.412332-1-spasswolf@web.de
Fixes: 3253cb49cbad4 ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20260302162631.uGUyIqDT@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 27 ++++++++++++++++++++++-----
 net/core/dev.c            |  5 +----
 net/core/netpoll.c        |  2 +-
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d4e6e00bb90a..67e25f6d15a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
@@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
@@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 	bool ok = spin_trylock(&txq->_xmit_lock);
 
 	if (likely(ok)) {
-		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		/* Pairs with READ_ONCE() in netif_tx_owned() */
 		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 	}
 	return ok;
@@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	/* Pairs with READ_ONCE() in netif_tx_owned() */
 	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
@@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev)
 	local_bh_enable();
 }
 
+#ifndef CONFIG_PREEMPT_RT
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	/* Other cpus might concurrently change txq->xmit_lock_owner
+	 * to -1 or to their cpu id, but not to our id.
+	 */
+	return READ_ONCE(txq->xmit_lock_owner) == cpu;
+}
+
+#else
+static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu)
+{
+	return rt_mutex_owner(&txq->_xmit_lock.lock) == current;
+}
+
+#endif
+
 static inline void netif_addr_lock(struct net_device *dev)
 {
 	unsigned char nest_level = 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index 20610a192ec7..14a83f2035b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4818,10 +4818,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	if (dev->flags & IFF_UP) {
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
-		/* Other cpus might concurrently change txq->xmit_lock_owner
-		 * to -1 or to their cpu id, but not to our id.
-		 */
-		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
+		if (!netif_tx_owned(txq, cpu)) {
 			bool is_list = false;
 
 			if (dev_xmit_recursion())
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a8558a52884f..cd74beffd209 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev)
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
 
-		if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id())
+		if (netif_tx_owned(txq, smp_processor_id()))
 			return 1;
 	}
 
-- 
cgit v1.2.3


From def602e498a4f951da95c95b1b8ce8ae68aa733a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 2 Mar 2026 23:12:37 +0100
Subject: netfilter: nf_tables: unconditionally bump set->nelems before
 insertion

In case that the set is full, a new element gets published then removed
without waiting for the RCU grace period, while RCU reader can be
walking over it already.

To address this issue, add the element transaction even if set is full,
but toggle the set_full flag to report -ENFILE so the abort path safely
unwinds the set to its previous state.

As for element updates, decrement set->nelems to restore it.

A simpler fix is to call synchronize_rcu() in the error path.
However, with a large batch adding elements to already maxed-out set,
this could cause noticeable slowdown of such batches.

Fixes: 35d0ac9070ef ("netfilter: nf_tables: fix set->nelems counting with no NLM_F_EXCL")
Reported-by: Inseo An <y0un9sa@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fd7f7e4e2a43..df67932d3e09 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7170,6 +7170,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_data_desc desc;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
+	bool set_full = false;
 	u64 expiration;
 	u64 timeout;
 	int err, i;
@@ -7461,10 +7462,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (err < 0)
 		goto err_elem_free;
 
+	if (!(flags & NFT_SET_ELEM_CATCHALL)) {
+		unsigned int max = nft_set_maxsize(set), nelems;
+
+		nelems = atomic_inc_return(&set->nelems);
+		if (nelems > max)
+			set_full = true;
+	}
+
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
 	if (trans == NULL) {
 		err = -ENOMEM;
-		goto err_elem_free;
+		goto err_set_size;
 	}
 
 	ext->genmask = nft_genmask_cur(ctx->net);
@@ -7516,7 +7525,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 
 						ue->priv = elem_priv;
 						nft_trans_commit_list_add_elem(ctx->net, trans);
-						goto err_elem_free;
+						goto err_set_size;
 					}
 				}
 			}
@@ -7534,23 +7543,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err_element_clash;
 	}
 
-	if (!(flags & NFT_SET_ELEM_CATCHALL)) {
-		unsigned int max = nft_set_maxsize(set);
-
-		if (!atomic_add_unless(&set->nelems, 1, max)) {
-			err = -ENFILE;
-			goto err_set_full;
-		}
-	}
-
 	nft_trans_container_elem(trans)->elems[0].priv = elem.priv;
 	nft_trans_commit_list_add_elem(ctx->net, trans);
-	return 0;
 
-err_set_full:
-	nft_setelem_remove(ctx->net, set, elem.priv);
+	return set_full ? -ENFILE : 0;
+
 err_element_clash:
 	kfree(trans);
+err_set_size:
+	if (!(flags & NFT_SET_ELEM_CATCHALL))
+		atomic_dec(&set->nelems);
 err_elem_free:
 	nf_tables_set_elem_destroy(ctx, set, elem.priv);
 err_parse_data:
-- 
cgit v1.2.3


From fb7fb4016300ac622c964069e286dc83166a5d52 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 2 Mar 2026 23:28:15 +0100
Subject: netfilter: nf_tables: clone set on flush only

Syzbot with fault injection triggered a failing memory allocation with
GFP_KERNEL which results in a WARN splat:

iter.err
WARNING: net/netfilter/nf_tables_api.c:845 at nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845, CPU#0: syz.0.17/5992
Modules linked in:
CPU: 0 UID: 0 PID: 5992 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
RIP: 0010:nft_map_deactivate+0x34e/0x3c0 net/netfilter/nf_tables_api.c:845
Code: 8b 05 86 5a 4e 09 48 3b 84 24 a0 00 00 00 75 62 48 8d 65 d8 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc e8 63 6d fa f7 90 <0f> 0b 90 43
+80 7c 35 00 00 0f 85 23 fe ff ff e9 26 fe ff ff 89 d9
RSP: 0018:ffffc900045af780 EFLAGS: 00010293
RAX: ffffffff89ca45bd RBX: 00000000fffffff4 RCX: ffff888028111e40
RDX: 0000000000000000 RSI: 00000000fffffff4 RDI: 0000000000000000
RBP: ffffc900045af870 R08: 0000000000400dc0 R09: 00000000ffffffff
R10: dffffc0000000000 R11: fffffbfff1d141db R12: ffffc900045af7e0
R13: 1ffff920008b5f24 R14: dffffc0000000000 R15: ffffc900045af920
FS:  000055557a6a5500(0000) GS:ffff888125496000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fb5ea271fc0 CR3: 000000003269e000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 __nft_release_table+0xceb/0x11f0 net/netfilter/nf_tables_api.c:12115
 nft_rcv_nl_event+0xc25/0xdb0 net/netfilter/nf_tables_api.c:12187
 notifier_call_chain+0x19d/0x3a0 kernel/notifier.c:85
 blocking_notifier_call_chain+0x6a/0x90 kernel/notifier.c:380
 netlink_release+0x123b/0x1ad0 net/netlink/af_netlink.c:761
 __sock_release net/socket.c:662 [inline]
 sock_close+0xc3/0x240 net/socket.c:1455

Restrict set clone to the flush set command in the preparation phase.
Add NFT_ITER_UPDATE_CLONE and use it for this purpose, update the rbtree
and pipapo backends to only clone the set when this iteration type is
used.

As for the existing NFT_ITER_UPDATE type, update the pipapo backend to
use the existing set clone if available, otherwise use the existing set
representation. After this update, there is no need to clone a set that
is being deleted, this includes bound anonymous set.

An alternative approach to NFT_ITER_UPDATE_CLONE is to add a .clone
interface and call it from the flush set path.

Reported-by: syzbot+4924a0edc148e8b4b342@syzkaller.appspotmail.com
Fixes: 3f1d886cc7c3 ("netfilter: nft_set_pipapo: move cloning of match info to insert/removal path")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 10 +++++++++-
 net/netfilter/nft_set_hash.c      |  1 +
 net/netfilter/nft_set_pipapo.c    | 11 +++++++++--
 net/netfilter/nft_set_rbtree.c    |  8 +++++---
 5 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 426534a711b0..ea6f29ad7888 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -320,11 +320,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
  * @NFT_ITER_UNSPEC: unspecified, to catch errors
  * @NFT_ITER_READ: read-only iteration over set elements
  * @NFT_ITER_UPDATE: iteration under mutex to update set element state
+ * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element
  */
 enum nft_iter_type {
 	NFT_ITER_UNSPEC,
 	NFT_ITER_READ,
 	NFT_ITER_UPDATE,
+	NFT_ITER_UPDATE_CLONE,
 };
 
 struct nft_set;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index df67932d3e09..058f7004cb2b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 	}
 }
 
+/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation
+ * phase, the set clone might already exist from a previous command, or it might
+ * be a set that is going away and does not require a clone. The netns and
+ * netlink release paths also need to work on the live set.
+ */
 static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set)
 {
 	struct nft_set_iter iter = {
@@ -7903,9 +7908,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx,
 
 static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask)
 {
+	/* The set backend might need to clone the set, do it now from the
+	 * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type.
+	 */
 	struct nft_set_iter iter = {
 		.genmask	= genmask,
-		.type		= NFT_ITER_UPDATE,
+		.type		= NFT_ITER_UPDATE_CLONE,
 		.fn		= nft_setelem_flush,
 	};
 
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 739b992bde59..b0e571c8e3f3 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 {
 	switch (iter->type) {
 	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		/* only relevant for netlink dumps which use READ type */
 		WARN_ON_ONCE(iter->skip != 0);
 
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 7ef4b44471d3..c091898df710 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -2144,13 +2144,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 	const struct nft_pipapo_match *m;
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
+	case NFT_ITER_UPDATE_CLONE:
 		m = pipapo_maybe_clone(set);
 		if (!m) {
 			iter->err = -ENOMEM;
 			return;
 		}
-
+		nft_pipapo_do_walk(ctx, set, m, iter);
+		break;
+	case NFT_ITER_UPDATE:
+		if (priv->clone)
+			m = priv->clone;
+		else
+			m = rcu_dereference_protected(priv->match,
+						      nft_pipapo_transaction_mutex_held(set));
 		nft_pipapo_do_walk(ctx, set, m, iter);
 		break;
 	case NFT_ITER_READ:
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 3f02e4478216..ee3d4f5b9ff7 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -861,13 +861,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_rbtree *priv = nft_set_priv(set);
 
 	switch (iter->type) {
-	case NFT_ITER_UPDATE:
-		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
-
+	case NFT_ITER_UPDATE_CLONE:
 		if (nft_array_may_resize(set) < 0) {
 			iter->err = -ENOMEM;
 			break;
 		}
+		fallthrough;
+	case NFT_ITER_UPDATE:
+		lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex);
+
 		nft_rbtree_do_walk(ctx, set, iter);
 		break;
 	case NFT_ITER_READ:
-- 
cgit v1.2.3


From 9df95785d3d8302f7c066050117b04cd3c2048c2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 3 Mar 2026 16:31:32 +0100
Subject: netfilter: nft_set_pipapo: split gc into unlink and reclaim phase

Yiming Qian reports Use-after-free in the pipapo set type:
  Under a large number of expired elements, commit-time GC can run for a very
  long time in a non-preemptible context, triggering soft lockup warnings and
  RCU stall reports (local denial of service).

We must split GC in an unlink and a reclaim phase.

We cannot queue elements for freeing until pointers have been swapped.
Expired elements are still exposed to both the packet path and userspace
dumpers via the live copy of the data structure.

call_rcu() does not protect us: dump operations or element lookups starting
after call_rcu has fired can still observe the free'd element, unless the
commit phase has made enough progress to swap the clone and live pointers
before any new reader has picked up the old version.

This a similar approach as done recently for the rbtree backend in commit
35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").

Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  5 ++++
 net/netfilter/nf_tables_api.c     |  5 ----
 net/netfilter/nft_set_pipapo.c    | 51 +++++++++++++++++++++++++++++++++------
 net/netfilter/nft_set_pipapo.h    |  2 ++
 4 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index ea6f29ad7888..e2d2bfc1f989 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1863,6 +1863,11 @@ struct nft_trans_gc {
 	struct rcu_head		rcu;
 };
 
+static inline int nft_trans_gc_space(const struct nft_trans_gc *trans)
+{
+	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
+}
+
 static inline void nft_ctx_update(struct nft_ctx *ctx,
 				  const struct nft_trans *trans)
 {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 058f7004cb2b..1862bd7fe804 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -10493,11 +10493,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans)
 	schedule_work(&trans_gc_work);
 }
 
-static int nft_trans_gc_space(struct nft_trans_gc *trans)
-{
-	return NFT_TRANS_GC_BATCHCOUNT - trans->count;
-}
-
 struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc,
 					      unsigned int gc_seq, gfp_t gfp)
 {
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index c091898df710..a34632ae6048 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1680,11 +1680,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set,
 }
 
 /**
- * pipapo_gc() - Drop expired entries from set, destroy start and end elements
+ * pipapo_gc_scan() - Drop expired entries from set and link them to gc list
  * @set:	nftables API set representation
  * @m:		Matching data
  */
-static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
+static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct net *net = read_pnet(&set->net);
@@ -1697,6 +1697,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 	if (!gc)
 		return;
 
+	list_add(&gc->list, &priv->gc_head);
+
 	while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) {
 		union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS];
 		const struct nft_pipapo_field *f;
@@ -1724,9 +1726,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		 * NFT_SET_ELEM_DEAD_BIT.
 		 */
 		if (__nft_set_elem_expired(&e->ext, tstamp)) {
-			gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
-			if (!gc)
-				return;
+			if (!nft_trans_gc_space(gc)) {
+				gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
+				if (!gc)
+					return;
+
+				list_add(&gc->list, &priv->gc_head);
+			}
 
 			nft_pipapo_gc_deactivate(net, set, e);
 			pipapo_drop(m, rulemap);
@@ -1740,10 +1746,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 		}
 	}
 
-	gc = nft_trans_gc_catchall_sync(gc);
+	priv->last_gc = jiffies;
+}
+
+/**
+ * pipapo_gc_queue() - Free expired elements
+ * @set:	nftables API set representation
+ */
+static void pipapo_gc_queue(struct nft_set *set)
+{
+	struct nft_pipapo *priv = nft_set_priv(set);
+	struct nft_trans_gc *gc, *next;
+
+	/* always do a catchall cycle: */
+	gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL);
 	if (gc) {
+		gc = nft_trans_gc_catchall_sync(gc);
+		if (gc)
+			nft_trans_gc_queue_sync_done(gc);
+	}
+
+	/* always purge queued gc elements. */
+	list_for_each_entry_safe(gc, next, &priv->gc_head, list) {
+		list_del(&gc->list);
 		nft_trans_gc_queue_sync_done(gc);
-		priv->last_gc = jiffies;
 	}
 }
 
@@ -1797,6 +1823,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu)
  *
  * We also need to create a new working copy for subsequent insertions and
  * deletions.
+ *
+ * After the live copy has been replaced by the clone, we can safely queue
+ * expired elements that have been collected by pipapo_gc_scan() for
+ * memory reclaim.
  */
 static void nft_pipapo_commit(struct nft_set *set)
 {
@@ -1807,7 +1837,7 @@ static void nft_pipapo_commit(struct nft_set *set)
 		return;
 
 	if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set)))
-		pipapo_gc(set, priv->clone);
+		pipapo_gc_scan(set, priv->clone);
 
 	old = rcu_replace_pointer(priv->match, priv->clone,
 				  nft_pipapo_transaction_mutex_held(set));
@@ -1815,6 +1845,8 @@ static void nft_pipapo_commit(struct nft_set *set)
 
 	if (old)
 		call_rcu(&old->rcu, pipapo_reclaim_match);
+
+	pipapo_gc_queue(set);
 }
 
 static void nft_pipapo_abort(const struct nft_set *set)
@@ -2279,6 +2311,7 @@ static int nft_pipapo_init(const struct nft_set *set,
 		f->mt = NULL;
 	}
 
+	INIT_LIST_HEAD(&priv->gc_head);
 	rcu_assign_pointer(priv->match, m);
 
 	return 0;
@@ -2328,6 +2361,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx,
 	struct nft_pipapo *priv = nft_set_priv(set);
 	struct nft_pipapo_match *m;
 
+	WARN_ON_ONCE(!list_empty(&priv->gc_head));
+
 	m = rcu_dereference_protected(priv->match, true);
 
 	if (priv->clone) {
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index eaab422aa56a..9aee9a9eaeb7 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -156,12 +156,14 @@ struct nft_pipapo_match {
  * @clone:	Copy where pending insertions and deletions are kept
  * @width:	Total bytes to be matched for one packet, including padding
  * @last_gc:	Timestamp of last garbage collection run, jiffies
+ * @gc_head:	list of nft_trans_gc to queue up for mem reclaim
  */
 struct nft_pipapo {
 	struct nft_pipapo_match __rcu *match;
 	struct nft_pipapo_match *clone;
 	int width;
 	unsigned long last_gc;
+	struct list_head gc_head;
 };
 
 struct nft_pipapo_elem;
-- 
cgit v1.2.3


From 3d543d9515928e4754a741c338dbcdf68ac47e39 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 12:18:10 +0100
Subject: ALSA: us122l: drop redundant interface references

Driver core holds a reference to the USB interface and its parent USB
device while the interface is bound to a driver and there is no need to
take additional references unless the structures are needed after
disconnect.

Similarly, USB core holds a reference to all interfaces in the active
configuration so there is no need for a driver to take a reference to a
sibling interface only to release it at disconnect either.

Drop the redundant references to reduce cargo culting, make it easier to
spot drivers where extra references are needed, and reduce the risk of
memory leaks when drivers fail to release them.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260305111810.18688-1-johan@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/us122l.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index 011ea96e9779..f00b53346abd 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -520,8 +520,6 @@ static int us122l_usb_probe(struct usb_interface *intf,
 		return err;
 	}
 
-	usb_get_intf(usb_ifnum_to_if(device, 0));
-	usb_get_dev(device);
 	*cardp = card;
 	return 0;
 }
@@ -542,11 +540,9 @@ static int snd_us122l_probe(struct usb_interface *intf,
 	if (intf->cur_altsetting->desc.bInterfaceNumber != 1)
 		return 0;
 
-	err = us122l_usb_probe(usb_get_intf(intf), id, &card);
-	if (err < 0) {
-		usb_put_intf(intf);
+	err = us122l_usb_probe(intf, id, &card);
+	if (err < 0)
 		return err;
-	}
 
 	usb_set_intfdata(intf, card);
 	return 0;
@@ -574,10 +570,6 @@ static void snd_us122l_disconnect(struct usb_interface *intf)
 		snd_usbmidi_disconnect(p);
 	}
 
-	usb_put_intf(usb_ifnum_to_if(us122l->dev, 0));
-	usb_put_intf(usb_ifnum_to_if(us122l->dev, 1));
-	usb_put_dev(us122l->dev);
-
 	snd_card_free_when_closed(card);
 }
 
-- 
cgit v1.2.3


From 0abc73c8a40fd64ac1739c90bb4f42c418d27a5e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 3 Mar 2026 18:56:39 +0100
Subject: net: ethernet: mtk_eth_soc: Reset prog ptr to old_prog in case of
 error in mtk_xdp_setup()

Reset eBPF program pointer to old_prog and do not decrease its ref-count
if mtk_open routine in mtk_xdp_setup() fails.

Fixes: 7c26c20da5d42 ("net: ethernet: mtk_eth_soc: add basic XDP support")
Suggested-by: Paolo Valerio <pvalerio@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260303-mtk-xdp-prog-ptr-fix-v2-1-97b6dbbe240f@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index e5e2ffa9c542..ddc321a02fda 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -3748,12 +3748,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 		mtk_stop(dev);
 
 	old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held());
+
+	if (netif_running(dev) && need_update) {
+		int err;
+
+		err = mtk_open(dev);
+		if (err) {
+			rcu_assign_pointer(eth->prog, old_prog);
+
+			return err;
+		}
+	}
+
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (netif_running(dev) && need_update)
-		return mtk_open(dev);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From f26b098d937488e8f5c617d465760a10bfcc7f13 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Thu, 5 Mar 2026 10:31:17 +0100
Subject: ftrace: Add MAINTAINERS entries for all ftrace headers

There is currently no entry for ftrace_irq.h and ftrace_regs.h. Add a
generic entry for all *ftrace* headers to include them and prevent
overlooking future ftrace headers.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://patch.msgid.link/20260305093117.853700-1-jmarchan@redhat.com
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 61bf550fd37c..b8d1ad952827 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10484,7 +10484,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
 F:	Documentation/trace/ftrace*
 F:	arch/*/*/*/*ftrace*
 F:	arch/*/*/*ftrace*
-F:	include/*/ftrace.h
+F:	include/*/*ftrace*
 F:	kernel/trace/fgraph.c
 F:	kernel/trace/ftrace*
 F:	samples/ftrace
-- 
cgit v1.2.3


From ac6769c8f948dff33265c50e524aebf9aa6f1be0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 28 Feb 2026 16:45:59 +0000
Subject: KVM: arm64: Eagerly init vgic dist/redist on vgic creation

If vgic_allocate_private_irqs_locked() fails for any odd reason,
we exit kvm_vgic_create() early, leaving dist->rd_regions uninitialised.

kvm_vgic_dist_destroy() then comes along and walks into the weeds
trying to free the RDs. Got to love this stuff.

Solve it by moving all the static initialisation early, and make
sure that if we fail halfway, we're in a reasonable shape to
perform the rest of the teardown. While at it, reset the vgic model
on failure, just in case...

Reported-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com
Tested-by: syzbot+f6a46b038fc243ac0175@syzkaller.appspotmail.com
Fixes: b3aa9283c0c50 ("KVM: arm64: vgic: Hoist SGI/PPI alloc from vgic_init() to kvm_create_vgic()")
Link: https://lore.kernel.org/r/69a2d58c.050a0220.3a55be.003b.GAE@google.com
Link: https://patch.msgid.link/20260228164559.936268-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
---
 arch/arm64/kvm/vgic/vgic-init.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 9b3091ad868c..e9b8b5fc480c 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -143,6 +143,21 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	kvm->arch.vgic.in_kernel = true;
 	kvm->arch.vgic.vgic_model = type;
 	kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST;
+	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
+
+	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
+	pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
+
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2) {
+		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+	} else {
+		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
+		aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
+		pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3);
+	}
+
+	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
+	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		ret = vgic_allocate_private_irqs_locked(vcpu, type);
@@ -157,25 +172,10 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 			vgic_cpu->private_irqs = NULL;
 		}
 
+		kvm->arch.vgic.vgic_model = 0;
 		goto out_unlock;
 	}
 
-	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
-
-	aa64pfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC;
-	pfr1 = kvm_read_vm_id_reg(kvm, SYS_ID_PFR1_EL1) & ~ID_PFR1_EL1_GIC;
-
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2) {
-		kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-	} else {
-		INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
-		aa64pfr0 |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, GIC, IMP);
-		pfr1 |= SYS_FIELD_PREP_ENUM(ID_PFR1_EL1, GIC, GICv3);
-	}
-
-	kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, aa64pfr0);
-	kvm_set_vm_id_reg(kvm, SYS_ID_PFR1_EL1, pfr1);
-
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V3)
 		kvm->arch.vgic.nassgicap = system_supports_direct_sgis();
 
-- 
cgit v1.2.3


From 8531d5a83d8eb8affb5c0249b466c28d94192603 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 5 Mar 2026 13:27:51 +0000
Subject: KVM: arm64: pkvm: Fallback to level-3 mapping on host stage-2 fault

If, for any odd reason, we cannot converge to mapping size that is
completely contained in a memblock region, we fail to install a S2
mapping and go back to the faulting instruction. Rince, repeat.

This happens when faulting in regions that are smaller than a page
or that do not have PAGE_SIZE-aligned boundaries (as witnessed on
an O6 board that refuses to boot in protected mode).

In this situation, fallback to using a PAGE_SIZE mapping anyway --
it isn't like we can go any lower.

Fixes: e728e705802fe ("KVM: arm64: Adjust range correctly during host stage-2 faults")
Link: https://lore.kernel.org/r/86wlzr77cn.wl-maz@kernel.org
Cc: stable@vger.kernel.org
Cc: Quentin Perret <qperret@google.com>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://patch.msgid.link/20260305132751.2928138-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 38f66a56a766..d815265bd374 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -518,7 +518,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		granule = kvm_granule_size(level);
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
-		if (!range_included(&cur, range))
+		if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL)
 			continue;
 		*range = cur;
 		return 0;
-- 
cgit v1.2.3


From 6be2681514261324c8ee8a1c6f76cefdf700220f Mon Sep 17 00:00:00 2001
From: Sun Jian <sun.jian.kdev@gmail.com>
Date: Wed, 25 Feb 2026 19:14:50 +0800
Subject: selftests/harness: order TEST_F and XFAIL_ADD constructors

TEST_F() allocates and registers its struct __test_metadata via mmap()
inside its constructor, and only then assigns the
_##fixture_##test##_object pointer.

XFAIL_ADD() runs in a constructor too and reads
_##fixture_##test##_object to initialize xfail->test. If XFAIL_ADD runs
first, xfail->test can be NULL and the expected failure will be reported
as FAIL.

Use constructor priorities to ensure TEST_F registration runs before
XFAIL_ADD, without adding extra state or runtime lookups.

Fixes: 2709473c9386 ("selftests: kselftest_harness: support using xfail")
Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Link: https://patch.msgid.link/20260225111451.347923-1-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/kselftest_harness.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 16a119a4656c..4afaef01c22e 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)
 		memset(s, c, n);
 }
 
+#define KSELFTEST_PRIO_TEST_F  20000
+#define KSELFTEST_PRIO_XFAIL   20001
+
 #define TEST_TIMEOUT_DEFAULT 30
 
 /* Utilities exposed to the test definitions */
@@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)
 			fixture_name##_teardown(_metadata, self, variant); \
 	} \
 	static struct __test_metadata *_##fixture_name##_##test_name##_object; \
-	static void __attribute__((constructor)) \
+	static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \
 			_register_##fixture_name##_##test_name(void) \
 	{ \
 		struct __test_metadata *object = mmap(NULL, sizeof(*object), \
@@ -880,7 +883,7 @@ struct __test_xfail {
 		.fixture = &_##fixture_name##_fixture_object, \
 		.variant = &_##fixture_name##_##variant_name##_object, \
 	}; \
-	static void __attribute__((constructor)) \
+	static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \
 		_register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \
 	{ \
 		_##fixture_name##_##variant_name##_##test_name##_xfail.test = \
-- 
cgit v1.2.3


From c952291593e54415a7bb74c4a7187a7c7c7e8651 Mon Sep 17 00:00:00 2001
From: Sun Jian <sun.jian.kdev@gmail.com>
Date: Wed, 25 Feb 2026 19:14:51 +0800
Subject: selftests: net: tun: don't abort XFAIL cases

The tun UDP tunnel GSO fixture contains XFAIL-marked variants intended to
exercise failure paths (e.g. EMSGSIZE / "Message too long").
Using ASSERT_EQ() in these tests aborts the subtest, which prevents the
harness from classifying them as XFAIL and can make the overall net: tun
test fail.

Switch the relevant ASSERT_EQ() checks to EXPECT_EQ() so the subtests
continue running and the failures are correctly reported and accounted
as XFAIL where applicable.

Signed-off-by: Sun Jian <sun.jian.kdev@gmail.com>
Link: https://patch.msgid.link/20260225111451.347923-2-sun.jian.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tun.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
index 8a5cd5cb5472..cf106a49b55e 100644
--- a/tools/testing/selftests/net/tun.c
+++ b/tools/testing/selftests/net/tun.c
@@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet)
 	ASSERT_EQ(ret, off);
 
 	ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss);
-	ASSERT_EQ(ret, variant->data_size);
-	ASSERT_EQ(r_num_mss, variant->r_num_mss);
+	EXPECT_EQ(ret, variant->data_size);
+	EXPECT_EQ(r_num_mss, variant->r_num_mss);
 }
 
 TEST_F(tun_vnet_udptnl, recv_gso_packet)
@@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet)
 	int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4;
 
 	ret = send_gso_packet_into_tunnel(self, variant);
-	ASSERT_EQ(ret, variant->data_size);
+	EXPECT_EQ(ret, variant->data_size);
 
 	memset(&vnet_hdr, 0, sizeof(vnet_hdr));
 	ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr);
-	ASSERT_EQ(ret, variant->data_size);
+	EXPECT_EQ(ret, variant->data_size);
 
 	if (!variant->no_gso) {
-		ASSERT_EQ(vh->gso_size, variant->gso_size);
+		EXPECT_EQ(vh->gso_size, variant->gso_size);
 		gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ?
 				    (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) :
 				    (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6);
-		ASSERT_EQ(vh->gso_type, gso_type);
+		EXPECT_EQ(vh->gso_type, gso_type);
 	}
 }
 
-- 
cgit v1.2.3


From f9b5bf12eb65e1e708a883a1e24712e81ed2f340 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:01 -0800
Subject: MAINTAINERS: remove Johan Hedberg from Bluetooth subsystem

We have not seen emails or tags from Johan in over 5 years,
and there is no recent mailing list activity.
Marcel Holtmann hasn't provided any tags in the Bluetooth
subsystem in over 5 years, but he is active on the Bluetooth
mailing list, providing informal review.
Luiz Augusto von Dentz is very active, handling essentially
all commits and reviews (12% coverage, but Luiz is the sole
active committer).

Subsystem BLUETOOTH SUBSYSTEM
  Changes 50 / 411 (12%)
  Last activity: 2026-02-23
  Marcel Holtmann <marcel@holtmann.org>:
  Johan Hedberg <johan.hedberg@gmail.com>:
  Luiz Augusto von Dentz <luiz.dentz@gmail.com>:
    Author 138d7eca445e 2026-02-23 00:00:00 164
    Committer 138d7eca445e 2026-02-23 00:00:00 361
    Tags 138d7eca445e 2026-02-23 00:00:00 362
  Top reviewers:
    [15]: pmenzel@molgen.mpg.de
    [8]: keescook@chromium.org
    [5]: willemb@google.com
    [4]: horms@kernel.org
    [3]: kuniyu@amazon.com
    [3]: luiz.von.dentz@intel.com
  INACTIVE MAINTAINER Johan Hedberg <johan.hedberg@gmail.com>

Acked-by: Marcel Holtmann <marcel@holtmann.org>
Link: https://patch.msgid.link/20260303215339.2333548-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index bee85351120e..4eb755b0a0d1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4615,7 +4615,6 @@ F:	drivers/bluetooth/
 
 BLUETOOTH SUBSYSTEM
 M:	Marcel Holtmann <marcel@holtmann.org>
-M:	Johan Hedberg <johan.hedberg@gmail.com>
 M:	Luiz Augusto von Dentz <luiz.dentz@gmail.com>
 L:	linux-bluetooth@vger.kernel.org
 S:	Supported
-- 
cgit v1.2.3


From 80f8a19fe7cf5b1b5d541c7aaa37aa9d7653bda5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:02 -0800
Subject: MAINTAINERS: remove Manish Chopra from QLogic QL4xxx (now orphan)

We have not seen tags from Manish for the QL4xxx driver in over 5 years,
and there is no mailing list activity since Oct 2023. There has been
no maintainer activity in this subsystem at all.

Since there is no other maintainer for this driver it becomes an Orphan.

Subsystem QLOGIC QL4xxx ETHERNET DRIVER
  Changes 40 / 74 (54%)
  (No activity)
  Top reviewers:
    [30]: horms@kernel.org
    [2]: jiri@nvidia.com
    [2]: shannon.nelson@amd.com
    [1]: saeedm@nvidia.com
    [1]: aleksandr.loktionov@intel.com
    [1]: kory.maincent@bootlin.com
  INACTIVE MAINTAINER Manish Chopra <manishc@marvell.com>

Link: https://patch.msgid.link/20260303215339.2333548-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4eb755b0a0d1..a83af9a89141 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21451,9 +21451,8 @@ S:	Supported
 F:	drivers/scsi/qedi/
 
 QLOGIC QL4xxx ETHERNET DRIVER
-M:	Manish Chopra <manishc@marvell.com>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/net/ethernet/qlogic/qed/
 F:	drivers/net/ethernet/qlogic/qede/
 F:	include/linux/qed/
-- 
cgit v1.2.3


From e07f796a86b2f0fda976268a08c321579022fcbc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:03 -0800
Subject: MAINTAINERS: remove Jerin Jacob from Marvell OcteonTX2

We have not seen tags from Jerin for OcteonTX2 in over 5 years.
Recent lore activity is in DPDK (non-kernel), not Linux.
Sunil, Linu, Geetha, hariprasad, and Subbaraya are active,
though the review coverage isn't great (38%).

Subsystem MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
  Changes 53 / 138 (38%)
  Last activity: 2026-02-18
  Sunil Goutham <sgoutham@marvell.com>:
    Author fc1b2901e0fe 2024-03-08 00:00:00 1
    Tags 70f8986ecef1 2025-06-16 00:00:00 9
  Linu Cherian <lcherian@marvell.com>:
    Author a861e5809f3e 2025-10-30 00:00:00 7
    Tags a861e5809f3e 2025-10-30 00:00:00 7
  Geetha sowjanya <gakula@marvell.com>:
    Author 70e9a5760abf 2026-01-29 00:00:00 16
    Tags 70e9a5760abf 2026-01-29 00:00:00 20
  Jerin Jacob <jerinj@marvell.com>:
  hariprasad <hkelam@marvell.com>:
    Author 45be47bf5d7d 2026-02-18 00:00:00 22
    Tags 45be47bf5d7d 2026-02-18 00:00:00 25
  Subbaraya Sundeep <sbhatta@marvell.com>:
    Author 47a1208776d7 2025-10-30 00:00:00 20
    Tags 47a1208776d7 2025-10-30 00:00:00 30
  Top reviewers:
    [36]: horms@kernel.org
    [4]: jacob.e.keller@intel.com
    [4]: kalesh-anakkur.purayil@broadcom.com
    [3]: vadim.fedorenko@linux.dev
    [2]: shaojijie@huawei.com
    [2]: jiri@nvidia.com
  INACTIVE MAINTAINER Jerin Jacob <jerinj@marvell.com>

Link: https://patch.msgid.link/20260303215339.2333548-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a83af9a89141..de0f5a38b525 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15469,7 +15469,6 @@ MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER
 M:	Sunil Goutham <sgoutham@marvell.com>
 M:	Linu Cherian <lcherian@marvell.com>
 M:	Geetha sowjanya <gakula@marvell.com>
-M:	Jerin Jacob <jerinj@marvell.com>
 M:	hariprasad <hkelam@marvell.com>
 M:	Subbaraya Sundeep <sbhatta@marvell.com>
 L:	netdev@vger.kernel.org
-- 
cgit v1.2.3


From 77f72ef58fb849cbe39fd69a20f9ae5076cd442b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:05 -0800
Subject: MAINTAINERS: remove Sean Wang from MediaTek Ethernet and switch

We have not seen tags from Sean in over 5 years,
with only one mailing list post since 2024.
Felix and Lorenzo are active for the Ethernet driver,
and Chester, Daniel and DENG Qingfang are active for
the switch driver.

Subsystem MEDIATEK ETHERNET DRIVER
  Changes 55 / 113 (48%)
  Last activity: 2025-10-12
  Felix Fietkau <nbd@nbd.name>:
    Author d4736737110f 2025-09-02 00:00:00 3
    Tags d4736737110f 2025-09-02 00:00:00 4
  Sean Wang <sean.wang@mediatek.com>:
  Lorenzo Bianconi <lorenzo@kernel.org>:
    Author 96326447d466 2025-08-13 00:00:00 35
    Tags 3abc0e55ea1f 2025-10-12 00:00:00 40
  Top reviewers:
    [26]: horms@kernel.org
    [5]: andrew@lunn.ch
    [4]: jacob.e.keller@intel.com
    [3]: shannon.nelson@amd.com
    [3]: michal.swiatkowski@linux.intel.com
  INACTIVE MAINTAINER Sean Wang <sean.wang@mediatek.com>

Subsystem MEDIATEK SWITCH DRIVER
  Changes 26 / 70 (37%)
  Last activity: 2025-12-01
  Chester A. Unal <chester.a.unal@arinc9.com>:
    Tags 585943b7ad30 2025-12-01 00:00:00 7
  Daniel Golle <daniel@makrotopia.org>:
    Author 497041d76301 2025-04-23 00:00:00 2
    Tags 3b87e60d2131 2025-12-01 00:00:00 14
  DENG Qingfang <dqfext@gmail.com>:
  Sean Wang <sean.wang@mediatek.com>:
  Top reviewers:
    [4]: andrew@lunn.ch
    [4]: florian.fainelli@broadcom.com
    [4]: arinc.unal@arinc9.com
    [2]: olteanv@gmail.com
  INACTIVE MAINTAINER Sean Wang <sean.wang@mediatek.com>

Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20260303215339.2333548-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index de0f5a38b525..706fb325bc67 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16157,7 +16157,6 @@ F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@nbd.name>
-M:	Sean Wang <sean.wang@mediatek.com>
 M:	Lorenzo Bianconi <lorenzo@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -16351,7 +16350,6 @@ MEDIATEK SWITCH DRIVER
 M:	Chester A. Unal <chester.a.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
 M:	DENG Qingfang <dqfext@gmail.com>
-M:	Sean Wang <sean.wang@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530-mdio.c
-- 
cgit v1.2.3


From 593cdf14523bfb837b947012cdc6545a53ea67b5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:06 -0800
Subject: MAINTAINERS: remove DENG Qingfang from MediaTek switch

We have not seen tags from DENG Qingfang for the MediaTek
switch driver in over 5 years. He is active upstream with
PPP/PPPoE patches in net-next. Chester and Daniel are active.

Subsystem MEDIATEK SWITCH DRIVER
  Changes 26 / 70 (37%)
  Last activity: 2025-12-01
  Chester A. Unal <chester.a.unal@arinc9.com>:
    Tags 585943b7ad30 2025-12-01 00:00:00 7
  Daniel Golle <daniel@makrotopia.org>:
    Author 497041d76301 2025-04-23 00:00:00 2
    Tags 3b87e60d2131 2025-12-01 00:00:00 14
  DENG Qingfang <dqfext@gmail.com>:
  Sean Wang <sean.wang@mediatek.com>:
  Top reviewers:
    [4]: andrew@lunn.ch
    [4]: florian.fainelli@broadcom.com
    [4]: arinc.unal@arinc9.com
    [2]: olteanv@gmail.com
  INACTIVE MAINTAINER DENG Qingfang <dqfext@gmail.com>

Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20260303215339.2333548-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 706fb325bc67..49bf6c8da74c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16349,7 +16349,6 @@ F:	include/soc/mediatek/smi.h
 MEDIATEK SWITCH DRIVER
 M:	Chester A. Unal <chester.a.unal@arinc9.com>
 M:	Daniel Golle <daniel@makrotopia.org>
-M:	DENG Qingfang <dqfext@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530-mdio.c
-- 
cgit v1.2.3


From 34f49454b25cd2e532f137174ef59b778f1a09f5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:07 -0800
Subject: MAINTAINERS: replace Clark Wang with Frank Li for Freescale FEC

We have not seen tags from Clark for FEC in over 5 years.
He has some limited recent activity on the mailing list in other
NXP subsystems (stmmac, phy). Wei Fang and Shenwei Wang are active,
with decent review coverage (61%).

Frank Li has been reviewing code actively more recenty, let's
make it official.

Subsystem FREESCALE IMX / MXC FEC DRIVER
  Changes 57 / 92 (61%)
  Last activity: 2026-02-10
  Wei Fang <wei.fang@nxp.com>:
    Author 25eb3058eb70 2026-02-10 00:00:00 33
    Tags 25eb3058eb70 2026-02-10 00:00:00 61
  Shenwei Wang <shenwei.wang@nxp.com>:
    Author d466c16026e9 2025-09-14 00:00:00 6
    Tags d466c16026e9 2025-09-14 00:00:00 6
  Clark Wang <xiaoning.wang@nxp.com>:
  Top reviewers:
    [23]: Frank.Li@nxp.com
    [17]: andrew@lunn.ch
    [4]: csokas.bence@prolan.hu
    [3]: horms@kernel.org
    [2]: maxime.chevallier@bootlin.com
  INACTIVE MAINTAINER Clark Wang <xiaoning.wang@nxp.com>

Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260303215339.2333548-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 49bf6c8da74c..b21c87332d14 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10167,8 +10167,8 @@ F:	drivers/i2c/busses/i2c-cpm.c
 
 FREESCALE IMX / MXC FEC DRIVER
 M:	Wei Fang <wei.fang@nxp.com>
+R:	Frank Li <frank.li@nxp.com>
 R:	Shenwei Wang <shenwei.wang@nxp.com>
-R:	Clark Wang <xiaoning.wang@nxp.com>
 L:	imx@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
cgit v1.2.3


From 60da2d2752ac4513fc3a91a0558dfd8176d2313f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:08 -0800
Subject: MAINTAINERS: remove Jonathan Lemon from OpenCompute PTP

We have not seen emails or tags from Jonathan in over 5 years,
and there is no recent mailing list activity.
Vadim Fedorenko is active.

Subsystem OPENCOMPUTE PTP CLOCK DRIVER
  Changes 49 / 130 (37%)
  Last activity: 2025-11-25
  Jonathan Lemon <jonathan.lemon@gmail.com>:
  Vadim Fedorenko <vadim.fedorenko@linux.dev>:
    Author d3ca2ef0c915 2025-09-19 00:00:00 5
    Tags 648282e2d1e5 2025-11-25 00:00:00 20
  Top reviewers:
    [7]: horms@kernel.org
    [4]: jiri@nvidia.com
    [3]: richardcochran@gmail.com
    [2]: aleksandr.loktionov@intel.com
  INACTIVE MAINTAINER Jonathan Lemon <jonathan.lemon@gmail.com>

Add Jonathan to CREDITS as the initial author of ptp_ocp.

Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20260303215339.2333548-9-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index d74c8b2b7ed3..fb9b4dc193a0 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2415,6 +2415,10 @@ S: Am Muehlenweg 38
 S: D53424 Remagen
 S: Germany
 
+N: Jonathan Lemon
+E: jonathan.lemon@gmail.com
+D: OpenCompute PTP clock driver (ptp_ocp)
+
 N: Colin Leroy
 E: colin@colino.net
 W: http://www.geekounet.org/
diff --git a/MAINTAINERS b/MAINTAINERS
index b21c87332d14..d63fe814b750 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19803,7 +19803,6 @@ F:	arch/*/boot/dts/
 F:	include/dt-bindings/
 
 OPENCOMPUTE PTP CLOCK DRIVER
-M:	Jonathan Lemon <jonathan.lemon@gmail.com>
 M:	Vadim Fedorenko <vadim.fedorenko@linux.dev>
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
cgit v1.2.3


From 9ede3e910f088fb3ffec0ed821f0b03951000d23 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:09 -0800
Subject: MAINTAINERS: replace Taras Chornyi with Elad Nachman for Marvell
 Prestera

We have not seen emails or tags from Taras in over 5 years,
and there is no recent mailing list activity.
Elad Nachman has been providing reviews in the last couple
of years and is the top reviewer for this subsystem.

Subsystem MARVELL PRESTERA ETHERNET SWITCH DRIVER
  Changes 39 / 157 (24%)
  (No activity)
  Top reviewers:
    [8]: enachman@marvell.com
    [6]: horms@kernel.org
    [4]: idosch@nvidia.com
    [3]: andrew@lunn.ch
    [3]: jacob.e.keller@intel.com
    [3]: jiri@nvidia.com
  INACTIVE MAINTAINER Taras Chornyi <taras.chornyi@plvision.eu>

Link: https://patch.msgid.link/20260303215339.2333548-10-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d63fe814b750..497822aac6aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15483,7 +15483,7 @@ S:	Supported
 F:	drivers/perf/marvell_pem_pmu.c
 
 MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M:	Taras Chornyi <taras.chornyi@plvision.eu>
+M:	Elad Nachman <enachman@marvell.com>
 S:	Supported
 W:	https://github.com/Marvell-switching/switchdev-prestera
 F:	drivers/net/ethernet/marvell/prestera/
-- 
cgit v1.2.3


From 4d37e68c46d15beb4af782b19d7f1b382316776c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:10 -0800
Subject: MAINTAINERS: remove Claudiu Manoil and Alexandre Belloni from Ocelot
 switch

We have not seen tags from Claudiu for the Ocelot switch driver
in over 5 years. He is active upstream in other NXP subsystems
(ENETC, gianfar), with 46 emails on lore since 2024.
We have not seen tags from Alexandre for the Ocelot switch driver
in over 5 years. He is very active upstream in other subsystems
(RTC, I3C, Atmel/Microchip SoC), with over 1,200 emails on lore
since 2024.
Vladimir Oltean is active.

Subsystem OCELOT ETHERNET SWITCH DRIVER
  Changes 180 / 494 (36%)
  Last activity: 2026-02-12
  Vladimir Oltean <vladimir.oltean@nxp.com>:
    Author c22ba07c827f 2026-02-10 00:00:00 33
    Tags 026f6513c588 2026-02-12 00:00:00 39
  Claudiu Manoil <claudiu.manoil@nxp.com>:
  Alexandre Belloni <alexandre.belloni@bootlin.com>:
  Top reviewers:
    [49]: f.fainelli@gmail.com
    [19]: horms@kernel.org
    [10]: richardcochran@gmail.com
    [9]: jacob.e.keller@intel.com
    [8]: colin.foster@in-advantage.com
  INACTIVE MAINTAINER Claudiu Manoil <claudiu.manoil@nxp.com>

Acked-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://patch.msgid.link/20260303215339.2333548-11-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 497822aac6aa..d050d756beec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19216,8 +19216,6 @@ F:	tools/objtool/
 
 OCELOT ETHERNET SWITCH DRIVER
 M:	Vladimir Oltean <vladimir.oltean@nxp.com>
-M:	Claudiu Manoil <claudiu.manoil@nxp.com>
-M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
 M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Supported
-- 
cgit v1.2.3


From ed6579002548f3d9c00380e2aeaa8305d3ed8fc5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 3 Mar 2026 13:53:11 -0800
Subject: MAINTAINERS: remove Thomas Falcon from IBM ibmvnic

We have not seen emails or tags from Thomas's IBM address
(tlfalcon@linux.ibm.com) in over 5 years. Looks like Thomas
is active in perf tooling at Intel (thomas.falcon@intel.com).

Subsystem IBM Power SRIOV Virtual NIC Device Driver
  Changes 49 / 134 (36%)
  Last activity: 2025-08-26
  Haren Myneni <haren@linux.ibm.com>:
    Tags 3c14917953a5 2025-08-26 00:00:00 2
  Rick Lindsley <ricklind@linux.ibm.com>:
  Nick Child <nnac123@linux.ibm.com>:
    Author d93a6caab5d7 2025-03-25 00:00:00 14
    Tags d93a6caab5d7 2025-03-25 00:00:00 16
  Thomas Falcon <tlfalcon@linux.ibm.com>:
  Top reviewers:
    [22]: drt@linux.ibm.com
    [13]: horms@kernel.org
    [9]: ricklind@linux.vnet.ibm.com
    [3]: davemarq@linux.ibm.com
  INACTIVE MAINTAINER Thomas Falcon <tlfalcon@linux.ibm.com>

Move Thomas to CREDITS as the initial author of ibmvnic.

Acked-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://patch.msgid.link/20260303215339.2333548-12-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 1 -
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index fb9b4dc193a0..9091bac3d2da 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1242,6 +1242,10 @@ N: Veaceslav Falico
 E: vfalico@gmail.com
 D: Co-maintainer and co-author of the network bonding driver.
 
+N: Thomas Falcon
+E: tlfalcon@linux.ibm.com
+D: Initial author of the IBM ibmvnic network driver
+
 N: János Farkas
 E: chexum@shadow.banki.hu
 D: romfs, various (mostly networking) fixes
diff --git a/MAINTAINERS b/MAINTAINERS
index d050d756beec..3fcb17815e00 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12212,7 +12212,6 @@ IBM Power SRIOV Virtual NIC Device Driver
 M:	Haren Myneni <haren@linux.ibm.com>
 M:	Rick Lindsley <ricklind@linux.ibm.com>
 R:	Nick Child <nnac123@linux.ibm.com>
-R:	Thomas Falcon <tlfalcon@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/ibm/ibmvnic.*
-- 
cgit v1.2.3


From 4c2264ecdf39ddbdb62e37b156015aacf05d0dcb Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:13 +0800
Subject: KVM: arm64: nv: Check S2 limits based on implemented PA size

check_base_s2_limits() checks the validity of SL0 and inputsize against
ia_size (inputsize again!) but the pseudocode from DDI0487 G.a
AArch64.TranslationTableWalk() says that we should check against the
implemented PA size.

We would otherwise fail to walk S2 with a valid configuration. E.g.,
granule size = 4KB, inputsize = 40 bits, initial lookup level = 0 (no
concatenation) on a system with 48 bits PA range supported is allowed by
architecture.

Fix it by obtaining PA size by kvm_get_pa_bits(). Note that
kvm_get_pa_bits() returns the fixed limit now and should eventually reflect
the per VM PARange (one day!). Given that the configured PARange should not
be greater that kvm_ipa_limit, it at least fixes the problem described
above.

While at it, inject a level 0 translation fault to guest if
check_base_s2_limits() fails, as per the pseudocode.

Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic")
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-2-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 12c9f6e8dfda..9da28814b646 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -152,31 +152,31 @@ static int get_ia_size(struct s2_walk_info *wi)
 	return 64 - wi->t0sz;
 }
 
-static int check_base_s2_limits(struct s2_walk_info *wi,
+static int check_base_s2_limits(struct kvm_vcpu *vcpu, struct s2_walk_info *wi,
 				int level, int input_size, int stride)
 {
-	int start_size, ia_size;
+	int start_size, pa_max;
 
-	ia_size = get_ia_size(wi);
+	pa_max = kvm_get_pa_bits(vcpu->kvm);
 
 	/* Check translation limits */
 	switch (BIT(wi->pgshift)) {
 	case SZ_64K:
-		if (level == 0 || (level == 1 && ia_size <= 42))
+		if (level == 0 || (level == 1 && pa_max <= 42))
 			return -EFAULT;
 		break;
 	case SZ_16K:
-		if (level == 0 || (level == 1 && ia_size <= 40))
+		if (level == 0 || (level == 1 && pa_max <= 40))
 			return -EFAULT;
 		break;
 	case SZ_4K:
-		if (level < 0 || (level == 0 && ia_size <= 42))
+		if (level < 0 || (level == 0 && pa_max <= 42))
 			return -EFAULT;
 		break;
 	}
 
 	/* Check input size limits */
-	if (input_size > ia_size)
+	if (input_size > pa_max)
 		return -EFAULT;
 
 	/* Check number of entries in starting level table */
@@ -269,9 +269,11 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 	if (input_size > 48 || input_size < 25)
 		return -EFAULT;
 
-	ret = check_base_s2_limits(wi, level, input_size, stride);
-	if (WARN_ON(ret))
+	ret = check_base_s2_limits(vcpu, wi, level, input_size, stride);
+	if (WARN_ON(ret)) {
+		out->esr = compute_fsc(0, ESR_ELx_FSC_FAULT);
 		return ret;
+	}
 
 	base_lower_bound = 3 + input_size - ((3 - level) * stride +
 			   wi->pgshift);
-- 
cgit v1.2.3


From 99a339377f3c1bdf6edd5614d36893ab1806f9e6 Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:14 +0800
Subject: KVM: arm64: nv: Report addrsz fault at level 0 with a bad VTTBR.BADDR

As per R_BFHQH,

" When an Address size fault is generated, the reported fault code
  indicates one of the following:

  If the fault was generated due to the TTBR_ELx used in the translation
  having nonzero address bits above the OA size, then a fault at level 0. "

Fix the reported Address size fault level as being 0 if the base address is
wrongly programmed by L1.

Fixes: 61e30b9eef7f ("KVM: arm64: nv: Implement nested Stage-2 page table walk logic")
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-3-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9da28814b646..91e4f3cb580a 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -280,7 +280,8 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 	base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound);
 
 	if (check_output_size(wi, base_addr)) {
-		out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ);
+		/* R_BFHQH */
+		out->esr = compute_fsc(0, ESR_ELx_FSC_ADDRSZ);
 		return 1;
 	}
 
-- 
cgit v1.2.3


From eb54fa1025f8b520f0e83a807d76e35e4587c5ff Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Thu, 26 Feb 2026 01:35:15 +0800
Subject: KVM: arm64: nv: Inject a SEA if failed to read the descriptor

Failure to read the descriptor (because it is outside of a memslot) should
result in a SEA being injected in the guest.

Suggested-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/86ms1m9lp3.wl-maz@kernel.org
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260225173515.20490-4-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 91e4f3cb580a..2c43097248b2 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -296,8 +296,10 @@ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa,
 
 		paddr = base_addr | index;
 		ret = read_guest_s2_desc(vcpu, paddr, &desc, wi);
-		if (ret < 0)
+		if (ret < 0) {
+			out->esr = ESR_ELx_FSC_SEA_TTW(level);
 			return ret;
+		}
 
 		new_desc = desc;
 
-- 
cgit v1.2.3


From b92b0075ee1870f78f59ab1f7da7dbfdd718ad7a Mon Sep 17 00:00:00 2001
From: Pedro Falcato <pfalcato@suse.de>
Date: Thu, 5 Mar 2026 14:53:12 +0000
Subject: ata: libata-core: Add BRIDGE_OK quirk for QEMU drives

Currently, whenever you boot with a QEMU drive over an AHCI interface,
you get:
[    1.632121] ata1.00: applying bridge limits

This happens due to the kernel not believing the given drive is SATA,
since word 93 of IDENTIFY (ATA_ID_HW_CONFIG) is non-zero. The result is
a pretty severe limit in max_hw_sectors_kb, which limits our IO sizes.

QEMU has set word 93 erroneously for SATA drives but does not, in any
way, emulate any of these real hardware details. There is no PATA
drive and no SATA cable.

As such, add a BRIDGE_OK quirk for QEMU HARDDISK. Special care is taken
to limit this quirk to "2.5+", to allow for fixed future versions.

This results in the max_hw_sectors being limited solely by the
controller interface's limits. Which, for AHCI controllers, takes it
from 128KB to 32767KB.

Cc: stable@vger.kernel.org
Signed-off-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 76b012f544ea..6c4e567b6582 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4232,6 +4232,7 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	/* Devices that do not need bridging limits applied */
 	{ "MTRON MSP-SATA*",		NULL,	ATA_QUIRK_BRIDGE_OK },
 	{ "BUFFALO HD-QSU2/R5",		NULL,	ATA_QUIRK_BRIDGE_OK },
+	{ "QEMU HARDDISK",		"2.5+",	ATA_QUIRK_BRIDGE_OK },
 
 	/* Devices which aren't very happy with higher link speeds */
 	{ "WD My Book",			NULL,	ATA_QUIRK_1_5_GBPS },
-- 
cgit v1.2.3


From e5e890630533bdc15b26a34bb8e7ef539bdf1322 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Wed, 4 Mar 2026 13:03:56 +0100
Subject: net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. Then, if neigh_suppress is enabled and an ICMPv6
Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will
dereference ipv6_stub->nd_tbl which is NULL, passing it to
neigh_lookup(). This causes a kernel NULL pointer dereference.

 BUG: kernel NULL pointer dereference, address: 0000000000000268
 Oops: 0000 [#1] PREEMPT SMP NOPTI
 [...]
 RIP: 0010:neigh_lookup+0x16/0xe0
 [...]
 Call Trace:
  <IRQ>
  ? neigh_lookup+0x16/0xe0
  br_do_suppress_nd+0x160/0x290 [bridge]
  br_handle_frame_finish+0x500/0x620 [bridge]
  br_handle_frame+0x353/0x440 [bridge]
  __netif_receive_skb_core.constprop.0+0x298/0x1110
  __netif_receive_skb_one_core+0x3d/0xa0
  process_backlog+0xa0/0x140
  __napi_poll+0x2c/0x170
  net_rx_action+0x2c4/0x3a0
  handle_softirqs+0xd0/0x270
  do_softirq+0x3f/0x60

Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in
the callers. This is in essence disabling NS/NA suppression when IPv6 is
disabled.

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Reported-by: Guruprasad C P <gurucp2005@gmail.com>
Closes: https://lore.kernel.org/netdev/CAHXs0ORzd62QOG-Fttqa2Cx_A_VFp=utE2H2VTX5nqfgs7LDxQ@mail.gmail.com/
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260304120357.9778-1-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_device.c | 2 +-
 net/bridge/br_input.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index ee01122f466f..f7502e62dd35 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	     eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) &&
 	    br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {
 		br_do_proxy_suppress_arp(skb, br, vid, NULL);
-	} else if (IS_ENABLED(CONFIG_IPV6) &&
+	} else if (ipv6_mod_enabled() &&
 		   skb->protocol == htons(ETH_P_IPV6) &&
 		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 1405f1061a54..2cbae0f9ae1f 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	    (skb->protocol == htons(ETH_P_ARP) ||
 	     skb->protocol == htons(ETH_P_RARP))) {
 		br_do_proxy_suppress_arp(skb, br, vid, p);
-	} else if (IS_ENABLED(CONFIG_IPV6) &&
+	} else if (ipv6_mod_enabled() &&
 		   skb->protocol == htons(ETH_P_IPV6) &&
 		   br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) &&
 		   pskb_may_pull(skb, sizeof(struct ipv6hdr) +
-- 
cgit v1.2.3


From 168ff39e4758897d2eee4756977d036d52884c7e Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Wed, 4 Mar 2026 13:03:57 +0100
Subject: net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. If an IPv6 packet is injected into the interface,
route_shortcircuit() is called and a NULL pointer dereference happens on
neigh_lookup().

 BUG: kernel NULL pointer dereference, address: 0000000000000380
 Oops: Oops: 0000 [#1] SMP NOPTI
 [...]
 RIP: 0010:neigh_lookup+0x20/0x270
 [...]
 Call Trace:
  <TASK>
  vxlan_xmit+0x638/0x1ef0 [vxlan]
  dev_hard_start_xmit+0x9e/0x2e0
  __dev_queue_xmit+0xbee/0x14e0
  packet_sendmsg+0x116f/0x1930
  __sys_sendto+0x1f5/0x200
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x12f/0x1590
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fix this by adding an early check on route_shortcircuit() when protocol
is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because
VXLAN can be built-in even when IPv6 is built as a module.

Fixes: e15a00aafa4b ("vxlan: add ipv6 route short circuit support")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Link: https://patch.msgid.link/20260304120357.9778-2-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 05558b6afecd..17c941aac32d 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2130,6 +2130,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	{
 		struct ipv6hdr *pip6;
 
+		/* check if nd_tbl is not initiliazed due to
+		 * ipv6.disable=1 set during boot
+		 */
+		if (!ipv6_stub->nd_tbl)
+			return false;
 		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 			return false;
 		pip6 = ipv6_hdr(skb);
-- 
cgit v1.2.3


From 21ec92774d1536f71bdc90b0e3d052eff99cf093 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 4 Mar 2026 19:38:13 +0800
Subject: net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop

When a standalone IPv6 nexthop object is created with a loopback device
(e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies
it as a reject route. This is because nexthop objects have no destination
prefix (fc_dst=::), causing fib6_is_reject() to match any loopback
nexthop. The reject path skips fib_nh_common_init(), leaving
nhc_pcpu_rth_output unallocated. If an IPv4 route later references this
nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and
panics.

Simplify the check in fib6_nh_init() to only match explicit reject
routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback
promotion heuristic in fib6_is_reject() is handled separately by
ip6_route_info_create_nh(). After this change, the three cases behave
as follows:

1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"):
   RTF_REJECT is set, enters reject path, skips fib_nh_common_init().
   No behavior change.

2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"):
   RTF_REJECT is not set, takes normal path, fib_nh_common_init() is
   called. ip6_route_info_create_nh() still promotes it to reject
   afterward. nhc_pcpu_rth_output is allocated but unused, which is
   harmless.

3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"):
   RTF_REJECT is not set, takes normal path, fib_nh_common_init() is
   called. nhc_pcpu_rth_output is properly allocated, fixing the crash
   when IPv4 routes reference this nexthop.

Suggested-by: Ido Schimmel <idosch@nvidia.com>
Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects")
Reported-by: syzbot+334190e097a98a1b81bb@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/698f8482.a70a0220.2c38d7.00ca.GAE@google.com/T/
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260304113817.294966-2-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7db0c837196c..08cd86f49bf9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3583,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker;
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
-	int addr_type;
 	int err;
 
 	fib6_nh->fib_nh_family = AF_INET6;
@@ -3625,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 
 	fib6_nh->fib_nh_weight = 1;
 
-	/* We cannot add true routes via loopback here,
-	 * they would result in kernel looping; promote them to reject routes
+	/* Reset the nexthop device to the loopback device in case of reject
+	 * routes.
 	 */
-	addr_type = ipv6_addr_type(&cfg->fc_dst);
-	if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) {
+	if (cfg->fc_flags & RTF_REJECT) {
 		/* hold loopback dev/idev if we haven't done so. */
 		if (dev != net->loopback_dev) {
 			if (dev) {
-- 
cgit v1.2.3


From 46c1ef0cfcea50aaf0b52316fdab94bf4b45795b Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 4 Mar 2026 19:38:14 +0800
Subject: selftests: net: add test for IPv4 route with loopback IPv6 nexthop

Add a regression test for a kernel panic that occurs when an IPv4 route
references an IPv6 nexthop object created on the loopback device.

The test creates an IPv6 nexthop on lo, binds an IPv4 route to it, then
triggers a route lookup via ping to verify the kernel does not crash.

  ./fib_nexthops.sh
  Tests passed: 249
  Tests failed:   0

Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260304113817.294966-3-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_nexthops.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 21026b667667..6eb7f95e70e1 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal()
 
 	run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1"
 	log_test $? 2 "IPv4 route with invalid IPv6 gateway"
+
+	# Test IPv4 route with loopback IPv6 nexthop
+	# Regression test: loopback IPv6 nexthop was misclassified as reject
+	# route, skipping nhc_pcpu_rth_output allocation, causing panic when
+	# an IPv4 route references it and triggers __mkroute_output().
+	run_cmd "$IP -6 nexthop add id 20 dev lo"
+	run_cmd "$IP ro add 172.20.20.0/24 nhid 20"
+	run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1"
+	log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)"
+	run_cmd "$IP ro del 172.20.20.0/24"
+	run_cmd "$IP nexthop del id 20"
 }
 
 ipv4_fcnal_runtime()
-- 
cgit v1.2.3


From e2cedd400c3ec0302ffca2490e8751772906ac23 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Wed, 4 Mar 2026 09:06:02 -0500
Subject: net/sched: act_ife: Fix metalist update behavior

Whenever an ife action replace changes the metalist, instead of
replacing the old data on the metalist, the current ife code is appending
the new metadata. Aside from being innapropriate behavior, this may lead
to an unbounded addition of metadata to the metalist which might cause an
out of bounds error when running the encode op:

[  138.423369][    C1] ==================================================================
[  138.424317][    C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.424906][    C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255
[  138.425778][    C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full)
[  138.425795][    C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  138.425800][    C1] Call Trace:
[  138.425804][    C1]  <IRQ>
[  138.425808][    C1]  dump_stack_lvl (lib/dump_stack.c:122)
[  138.425828][    C1]  print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
[  138.425839][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425844][    C1]  ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1))
[  138.425853][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425859][    C1]  kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597)
[  138.425868][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425878][    C1]  kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1))
[  138.425884][    C1]  __asan_memset (mm/kasan/shadow.c:84 (discriminator 2))
[  138.425889][    C1]  ife_tlv_meta_encode (net/ife/ife.c:168)
[  138.425893][    C1]  ? ife_tlv_meta_encode (net/ife/ife.c:171)
[  138.425898][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425903][    C1]  ife_encode_meta_u16 (net/sched/act_ife.c:57)
[  138.425910][    C1]  ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114)
[  138.425916][    C1]  ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3))
[  138.425921][    C1]  ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45)
[  138.425927][    C1]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  138.425931][    C1]  tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879)

To solve this issue, fix the replace behavior by adding the metalist to
the ife rcu data structure.

Fixes: aa9fd9a325d51 ("sched: act: ife: update parameters via rcu handling")
Reported-by: Ruitong Liu <cnitlrt@gmail.com>
Tested-by: Ruitong Liu <cnitlrt@gmail.com>
Co-developed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260304140603.76500-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tc_act/tc_ife.h |  4 +-
 net/sched/act_ife.c         | 93 +++++++++++++++++++++------------------------
 2 files changed, 45 insertions(+), 52 deletions(-)

diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index c7f24a2da1ca..24d4d5a62b3c 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -13,15 +13,13 @@ struct tcf_ife_params {
 	u8 eth_src[ETH_ALEN];
 	u16 eth_type;
 	u16 flags;
-
+	struct list_head metalist;
 	struct rcu_head rcu;
 };
 
 struct tcf_ife_info {
 	struct tc_action common;
 	struct tcf_ife_params __rcu *params;
-	/* list of metaids allowed */
-	struct list_head metalist;
 };
 #define to_ife(a) ((struct tcf_ife_info *)a)
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 79df81d12894..d5e8a91bb4eb 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held)
 /* called when adding new meta information
 */
 static int __add_metainfo(const struct tcf_meta_ops *ops,
-			  struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			  int len, bool atomic, bool exists)
+			  struct tcf_ife_params *p, u32 metaid, void *metaval,
+			  int len, bool atomic)
 {
 	struct tcf_meta_info *mi = NULL;
 	int ret = 0;
@@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops,
 		}
 	}
 
-	if (exists)
-		spin_lock_bh(&ife->tcf_lock);
-	list_add_tail(&mi->metalist, &ife->metalist);
-	if (exists)
-		spin_unlock_bh(&ife->tcf_lock);
+	list_add_tail(&mi->metalist, &p->metalist);
 
 	return ret;
 }
 
 static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops,
-				    struct tcf_ife_info *ife, u32 metaid,
-				    bool exists)
+				    struct tcf_ife_params *p, u32 metaid)
 {
 	int ret;
 
 	if (!try_module_get(ops->owner))
 		return -ENOENT;
-	ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists);
+	ret = __add_metainfo(ops, p, metaid, NULL, 0, true);
 	if (ret)
 		module_put(ops->owner);
 	return ret;
 }
 
-static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval,
-			int len, bool exists)
+static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval,
+			int len)
 {
 	const struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret;
 
 	if (!ops)
 		return -ENOENT;
-	ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists);
+	ret = __add_metainfo(ops, p, metaid, metaval, len, false);
 	if (ret)
 		/*put back what find_ife_oplist took */
 		module_put(ops->owner);
 	return ret;
 }
 
-static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
+static int use_all_metadata(struct tcf_ife_params *p)
 {
 	struct tcf_meta_ops *o;
 	int rc = 0;
@@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 
 	read_lock(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
-		rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists);
+		rc = add_metainfo_and_get_ops(o, p, o->metaid);
 		if (rc == 0)
 			installed += 1;
 	}
@@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists)
 		return -EINVAL;
 }
 
-static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
+static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p)
 {
 	struct tcf_meta_info *e;
 	struct nlattr *nest;
@@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
 	int total_encoded = 0;
 
 	/*can only happen on decode */
-	if (list_empty(&ife->metalist))
+	if (list_empty(&p->metalist))
 		return 0;
 
 	nest = nla_nest_start_noflag(skb, TCA_IFE_METALST);
 	if (!nest)
 		goto out_nlmsg_trim;
 
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry(e, &p->metalist, metalist) {
 		if (!e->ops->get(skb, e))
 			total_encoded += 1;
 	}
@@ -403,13 +398,11 @@ out_nlmsg_trim:
 	return -1;
 }
 
-/* under ife->tcf_lock */
-static void _tcf_ife_cleanup(struct tc_action *a)
+static void __tcf_ife_cleanup(struct tcf_ife_params *p)
 {
-	struct tcf_ife_info *ife = to_ife(a);
 	struct tcf_meta_info *e, *n;
 
-	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
+	list_for_each_entry_safe(e, n, &p->metalist, metalist) {
 		list_del(&e->metalist);
 		if (e->metaval) {
 			if (e->ops->release)
@@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a)
 	}
 }
 
+static void tcf_ife_cleanup_params(struct rcu_head *head)
+{
+	struct tcf_ife_params *p = container_of(head, struct tcf_ife_params,
+						rcu);
+
+	__tcf_ife_cleanup(p);
+	kfree(p);
+}
+
 static void tcf_ife_cleanup(struct tc_action *a)
 {
 	struct tcf_ife_info *ife = to_ife(a);
 	struct tcf_ife_params *p;
 
-	spin_lock_bh(&ife->tcf_lock);
-	_tcf_ife_cleanup(a);
-	spin_unlock_bh(&ife->tcf_lock);
-
 	p = rcu_dereference_protected(ife->params, 1);
 	if (p)
-		kfree_rcu(p, rcu);
+		call_rcu(&p->rcu, tcf_ife_cleanup_params);
 }
 
 static int load_metalist(struct nlattr **tb, bool rtnl_held)
@@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held)
 	return 0;
 }
 
-static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
-			     bool exists, bool rtnl_held)
+static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb)
 {
 	int len = 0;
 	int rc = 0;
@@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = add_metainfo(ife, i, val, len, exists);
+			rc = add_metainfo(p, i, val, len);
 			if (rc)
 				return rc;
 		}
@@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	p = kzalloc_obj(*p);
 	if (!p)
 		return -ENOMEM;
+	INIT_LIST_HEAD(&p->metalist);
 
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
@@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	ife = to_ife(*a);
-	if (ret == ACT_P_CREATED)
-		INIT_LIST_HEAD(&ife->metalist);
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
@@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (tb[TCA_IFE_METALST]) {
-		err = populate_metalist(ife, tb2, exists,
-					!(flags & TCA_ACT_FLAGS_NO_RTNL));
+		err = populate_metalist(p, tb2);
 		if (err)
 			goto metadata_parse_err;
 	} else {
@@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		 * as we can. You better have at least one else we are
 		 * going to bail out
 		 */
-		err = use_all_metadata(ife, exists);
+		err = use_all_metadata(p);
 		if (err)
 			goto metadata_parse_err;
 	}
@@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 	if (p)
-		kfree_rcu(p, rcu);
+		call_rcu(&p->rcu, tcf_ife_cleanup_params);
 
 	return ret;
 metadata_parse_err:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 release_idr:
+	__tcf_ife_cleanup(p);
 	kfree(p);
 	tcf_idr_release(*a, bind);
 	return err;
@@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type))
 		goto nla_put_failure;
 
-	if (dump_metalist(skb, ife)) {
+	if (dump_metalist(skb, p)) {
 		/*ignore failure to dump metalist */
 		pr_info("Failed to dump metalist\n");
 	}
@@ -693,13 +689,13 @@ nla_put_failure:
 	return -1;
 }
 
-static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife,
+static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p,
 			      u16 metaid, u16 mlen, void *mdata)
 {
 	struct tcf_meta_info *e;
 
 	/* XXX: use hash to speed up */
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (metaid == e->metaid) {
 			if (e->ops) {
 				/* We check for decode presence already */
@@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 {
 	struct tcf_ife_info *ife = to_ife(a);
 	int action = ife->tcf_action;
+	struct tcf_ife_params *p;
 	u8 *ifehdr_end;
 	u8 *tlv_data;
 	u16 metalen;
 
+	p = rcu_dereference_bh(ife->params);
+
 	bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb);
 	tcf_lastuse_update(&ife->tcf_tm);
 
@@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 			return TC_ACT_SHOT;
 		}
 
-		if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) {
+		if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) {
 			/* abuse overlimits to count when we receive metadata
 			 * but dont have an ops for it
 			 */
@@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a,
 /*XXX: check if we can do this at install time instead of current
  * send data path
 **/
-static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife)
+static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p)
 {
-	struct tcf_meta_info *e, *n;
+	struct tcf_meta_info *e;
 	int tot_run_sz = 0, run_sz = 0;
 
-	list_for_each_entry_safe(e, n, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (e->ops->check_presence) {
 			run_sz = e->ops->check_presence(skb, e);
 			tot_run_sz += run_sz;
@@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
 	   OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
 	   where ORIGDATA = original ethernet header ...
 	 */
-	u16 metalen = ife_get_sz(skb, ife);
+	u16 metalen = ife_get_sz(skb, p);
 	int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
 	unsigned int skboff = 0;
 	int new_len = skb->len + hdrm;
@@ -833,25 +832,21 @@ drop:
 	if (!ife_meta)
 		goto drop;
 
-	spin_lock(&ife->tcf_lock);
-
 	/* XXX: we dont have a clever way of telling encode to
 	 * not repeat some of the computations that are done by
 	 * ops->presence_check...
 	 */
-	list_for_each_entry(e, &ife->metalist, metalist) {
+	list_for_each_entry_rcu(e, &p->metalist, metalist) {
 		if (e->ops->encode) {
 			err = e->ops->encode(skb, (void *)(ife_meta + skboff),
 					     e);
 		}
 		if (err < 0) {
 			/* too corrupt to keep around if overwritten */
-			spin_unlock(&ife->tcf_lock);
 			goto drop;
 		}
 		skboff += err;
 	}
-	spin_unlock(&ife->tcf_lock);
 	oethh = (struct ethhdr *)skb->data;
 
 	if (!is_zero_ether_addr(p->eth_src))
-- 
cgit v1.2.3


From 5d1271ff4c131cd4a601dabdfdcdc1fe1252493f Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Wed, 4 Mar 2026 09:06:03 -0500
Subject: selftests/tc-testing: Add tests exercising act_ife metalist replace
 behaviour

Add 2 test cases to exercise fix in act_ife's internal metalist
behaviour.

- Update decode ife action into encode with tcindex metadata
- Update decode ife action into encode with multiple metadata

Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260304140603.76500-2-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/tc-testing/tc-tests/actions/ife.json | 99 ++++++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index f587a32e44c4..808aef4afe22 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -1279,5 +1279,104 @@
         "teardown": [
             "$TC actions flush action ife"
         ]
+    },
+    {
+        "id": "f2a0",
+        "name": "Update decode ife action with encode metadata",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife decode index 10"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j actions get action ife index 10",
+        "matchJSON": [
+            {
+                "total acts": 0
+            },
+            {
+                "actions": [
+                    {
+                        "order": 1,
+                        "kind": "ife",
+                        "mode": "encode",
+                        "control_action": {
+                            "type": "pipe"
+                        },
+                        "type": "0xed3e",
+                        "tcindex": 1,
+                        "index": 10,
+                        "ref": 1,
+                        "bind": 0,
+                        "not_in_hw": true
+                    }
+                ]
+            }
+        ],
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
+    },
+    {
+        "id": "d352",
+        "name": "Update decode ife action into encode with multiple metadata",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife decode index 10"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -j actions get action ife index 10",
+        "matchJSON": [
+            {
+                "total acts": 0
+            },
+            {
+                "actions": [
+                    {
+                        "order": 1,
+                        "kind": "ife",
+                        "mode": "encode",
+                        "control_action": {
+                            "type": "pipe"
+                        },
+                        "type": "0xed3e",
+                        "tcindex": 1,
+                        "mark": 22,
+                        "index": 10,
+                        "ref": 1,
+                        "bind": 0,
+                        "not_in_hw": true
+                    }
+                ]
+            }
+        ],
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 88b6b7f7b216108a09887b074395fa7b751880b1 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:42 +0100
Subject: xdp: use modulo operation to calculate XDP frag tailroom

The current formula for calculating XDP tailroom in mbuf packets works only
if each frag has its own page (if rxq->frag_size is PAGE_SIZE), this
defeats the purpose of the parameter overall and without any indication
leads to negative calculated tailroom on at least half of frags, if shared
pages are used.

There are not many drivers that set rxq->frag_size. Among them:
* i40e and enetc always split page uniformly between frags, use shared
  pages
* ice uses page_pool frags via libeth, those are power-of-2 and uniformly
  distributed across page
* idpf has variable frag_size with XDP on, so current API is not applicable
* mlx5, mtk and mvneta use PAGE_SIZE or 0 as frag_size for page_pool

As for AF_XDP ZC, only ice, i40e and idpf declare frag_size for it. Modulo
operation yields good results for aligned chunks, they are all power-of-2,
between 2K and PAGE_SIZE. Formula without modulo fails when chunk_size is
2K. Buffers in unaligned mode are not distributed uniformly, so modulo
operation would not work.

To accommodate unaligned buffers, we could define frag_size as
data + tailroom, and hence do not subtract offset when calculating
tailroom, but this would necessitate more changes in the drivers.

Define rxq->frag_size as an even portion of a page that fully belongs to a
single frag. When calculating tailroom, locate the data start within such
portion by performing a modulo operation on page offset.

Fixes: bf25146a5595 ("bpf: add frags support to the bpf_xdp_adjust_tail() API")
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-2-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 0d5d5a17acb2..d6fafb3633b0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4155,7 +4155,8 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
 		return -EOPNOTSUPP;
 
-	tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag);
+	tailroom = rxq->frag_size - skb_frag_size(frag) -
+		   skb_frag_off(frag) % rxq->frag_size;
 	if (unlikely(offset > tailroom))
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 16394d80539937d348dd3b9ea32415c54e67a81b Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:43 +0100
Subject: xsk: introduce helper to determine rxq->frag_size

rxq->frag_size is basically a step between consecutive strictly aligned
frames. In ZC mode, chunk size fits exactly, but if chunks are unaligned,
there is no safe way to determine accessible space to grow tailroom.

Report frag_size to be zero, if chunks are unaligned, chunk_size otherwise.

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-3-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index aefc368449d5..6b9ebae2dc95 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool);
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
@@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 	return 0;
 }
 
+static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
+{
+	return 0;
+}
+
 static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
-- 
cgit v1.2.3


From 02852b47c706772af795d3e28fca99fc9b923b2c Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:44 +0100
Subject: ice: fix rxq info registering in mbuf packets

XDP RxQ info contains frag_size, which depends on the MTU. This makes the
old way of registering RxQ info before calculating new buffer sizes
invalid. Currently, it leads to frag_size being outdated, making it
sometimes impossible to grow tailroom in a mbuf packet. E.g. fragments are
actually 3K+, but frag size is still as if MTU was 1500.

Always register new XDP RxQ info after reconfiguring memory pools.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-4-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c    | 26 +++++++-------------------
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  1 +
 drivers/net/ethernet/intel/ice/ice_txrx.c    |  4 +++-
 drivers/net/ethernet/intel/ice/ice_xsk.c     |  3 +++
 4 files changed, 14 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index d85b0a4baa37..165ef8afa8b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -666,23 +666,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 
 	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
 	    ring->vsi->type == ICE_VSI_LB) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-						 ring->q_index,
-						 ring->q_vector->napi.napi_id,
-						 ring->rx_buf_len);
-			if (err)
-				return err;
-		}
-
 		ice_rx_xsk_pool(ring);
 		err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool);
 		if (err)
 			return err;
 
 		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg(&ring->xdp_rxq);
-
 			rx_buf_len =
 				xsk_pool_get_rx_frame_size(ring->xsk_pool);
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
@@ -705,14 +694,13 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			if (err)
 				return err;
 
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-				err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-							 ring->q_index,
-							 ring->q_vector->napi.napi_id,
-							 ring->rx_buf_len);
-				if (err)
-					goto err_destroy_fq;
-			}
+			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+						 ring->q_index,
+						 ring->q_vector->napi.napi_id,
+						 ring->rx_buf_len);
+			if (err)
+				goto err_destroy_fq;
+
 			xdp_rxq_info_attach_page_pool(&ring->xdp_rxq,
 						      ring->pp);
 		}
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index b9be10b58856..301947d53ede 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3342,6 +3342,7 @@ process_rx:
 		rx_rings[i].cached_phctime = pf->ptp.cached_phc_time;
 		rx_rings[i].desc = NULL;
 		rx_rings[i].xdp_buf = NULL;
+		rx_rings[i].xdp_rxq = (struct xdp_rxq_info){ };
 
 		/* this is to allow wr32 to have something to write to
 		 * during early allocation of Rx buffers
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index a5bbce68f76c..a2cd4cf37734 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -560,7 +560,9 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 			i = 0;
 	}
 
-	if (rx_ring->vsi->type == ICE_VSI_PF &&
+	if ((rx_ring->vsi->type == ICE_VSI_PF ||
+	     rx_ring->vsi->type == ICE_VSI_SF ||
+	     rx_ring->vsi->type == ICE_VSI_LB) &&
 	    xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) {
 		xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq);
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index c673094663a3..0643017541c3 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -899,6 +899,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	u16 ntc = rx_ring->next_to_clean;
 	u16 ntu = rx_ring->next_to_use;
 
+	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+
 	while (ntc != ntu) {
 		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
-- 
cgit v1.2.3


From e142dc4ef0f451b7ef99d09aaa84e9389af629d7 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:45 +0100
Subject: ice: change XDP RxQ frag_size from DMA write length to xdp.frame_sz

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buff size instead
of DMA write size. Different assumptions in ice driver configuration lead
to negative tailroom.

This allows to trigger kernel panic, when using
XDP_ADJUST_TAIL_GROW_MULTI_BUFF xskxceiver test and changing packet size to
6912 and the requested offset to a huge value, e.g.
XSK_UMEM__MAX_FRAME_SIZE * 100.

Due to other quirks of the ZC configuration in ice, panic is not observed
in ZC mode, but tailroom growing still fails when it should not.

Use fill queue buffer truesize instead of DMA write size in XDP RxQ info.
Fix ZC mode too by using the new helper.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-5-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 165ef8afa8b0..1667f686ff75 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -661,7 +661,6 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 {
 	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	u32 num_bufs = ICE_DESC_UNUSED(ring);
-	u32 rx_buf_len;
 	int err;
 
 	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF ||
@@ -672,12 +671,12 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return err;
 
 		if (ring->xsk_pool) {
-			rx_buf_len =
-				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			u32 frag_size =
+				xsk_pool_get_rx_frag_step(ring->xsk_pool);
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
 						 ring->q_vector->napi.napi_id,
-						 rx_buf_len);
+						 frag_size);
 			if (err)
 				return err;
 			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -697,7 +696,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
 						 ring->q_vector->napi.napi_id,
-						 ring->rx_buf_len);
+						 ring->truesize);
 			if (err)
 				goto err_destroy_fq;
 
-- 
cgit v1.2.3


From 8f497dc8a61429cc004720aa8e713743355d80cf Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:46 +0100
Subject: i40e: fix registering XDP RxQ info

Current way of handling XDP RxQ info in i40e has a problem, where frag_size
is not updated when xsk_buff_pool is detached or when MTU is changed, this
leads to growing tail always failing for multi-buffer packets.

Couple XDP RxQ info registering with buffer allocations and unregistering
with cleaning the ring.

Fixes: a045d2f2d03d ("i40e: set xdp_rxq_info::frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-6-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 34 ++++++++++++++++-------------
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  5 +++--
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7b9e147d7365..781ec5aa814b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3583,18 +3583,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	if (ring->vsi->type != I40E_VSI_MAIN)
 		goto skip;
 
-	if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
-		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->queue_index,
-					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
-		if (err)
-			return err;
-	}
-
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
-		xdp_rxq_info_unreg(&ring->xdp_rxq);
 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
@@ -3606,17 +3596,23 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 						 MEM_TYPE_XSK_BUFF_POOL,
 						 NULL);
 		if (err)
-			return err;
+			goto unreg_xdp;
 		dev_info(&vsi->back->pdev->dev,
 			 "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 			 ring->queue_index);
 
 	} else {
+		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->queue_index,
+					 ring->q_vector->napi.napi_id,
+					 ring->rx_buf_len);
+		if (err)
+			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						 MEM_TYPE_PAGE_SHARED,
 						 NULL);
 		if (err)
-			return err;
+			goto unreg_xdp;
 	}
 
 skip:
@@ -3654,7 +3650,8 @@ skip:
 		dev_info(&vsi->back->pdev->dev,
 			 "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
 			 ring->queue_index, pf_q, err);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto unreg_xdp;
 	}
 
 	/* set the context in the HMC */
@@ -3663,7 +3660,8 @@ skip:
 		dev_info(&vsi->back->pdev->dev,
 			 "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n",
 			 ring->queue_index, pf_q, err);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto unreg_xdp;
 	}
 
 	/* configure Rx buffer alignment */
@@ -3671,7 +3669,8 @@ skip:
 		if (I40E_2K_TOO_SMALL_WITH_PADDING) {
 			dev_info(&vsi->back->pdev->dev,
 				 "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto unreg_xdp;
 		}
 		clear_ring_build_skb_enabled(ring);
 	} else {
@@ -3701,6 +3700,11 @@ skip:
 	}
 
 	return 0;
+unreg_xdp:
+	if (ring->vsi->type == I40E_VSI_MAIN)
+		xdp_rxq_info_unreg(&ring->xdp_rxq);
+
+	return err;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 34db7d8866b0..894f2d06d39d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1470,6 +1470,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 	if (!rx_ring->rx_bi)
 		return;
 
+	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
+		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+
 	if (rx_ring->xsk_pool) {
 		i40e_xsk_clean_rx_ring(rx_ring);
 		goto skip_free;
@@ -1527,8 +1530,6 @@ skip_free:
 void i40e_free_rx_resources(struct i40e_ring *rx_ring)
 {
 	i40e_clean_rx_ring(rx_ring);
-	if (rx_ring->vsi->type == I40E_VSI_MAIN)
-		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	rx_ring->xdp_prog = NULL;
 	kfree(rx_ring->rx_bi);
 	rx_ring->rx_bi = NULL;
-- 
cgit v1.2.3


From c69d22c6c46a1d792ba8af3d8d6356fdc0e6f538 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:47 +0100
Subject: i40e: use xdp.frame_sz as XDP RxQ info frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead
of DMA write size. Different assumptions in i40e driver configuration lead
to negative tailroom.

Set frag_size to the same value as frame_sz in shared pages mode, use new
helper to set frag_size when AF_XDP ZC is active.

Fixes: a045d2f2d03d ("i40e: set xdp_rxq_info::frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-7-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 781ec5aa814b..926d001b2150 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3569,6 +3569,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	u16 pf_q = vsi->base_queue + ring->queue_index;
 	struct i40e_hw *hw = &vsi->back->hw;
 	struct i40e_hmc_obj_rxq rx_ctx;
+	u32 xdp_frame_sz;
 	int err = 0;
 	bool ok;
 
@@ -3578,6 +3579,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	memset(&rx_ctx, 0, sizeof(rx_ctx));
 
 	ring->rx_buf_len = vsi->rx_buf_len;
+	xdp_frame_sz = i40e_rx_pg_size(ring) / 2;
 
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
 	if (ring->vsi->type != I40E_VSI_MAIN)
@@ -3585,11 +3587,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 
 	ring->xsk_pool = i40e_xsk_pool(ring);
 	if (ring->xsk_pool) {
+		xdp_frame_sz = xsk_pool_get_rx_frag_step(ring->xsk_pool);
 		ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3605,7 +3608,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->queue_index,
 					 ring->q_vector->napi.napi_id,
-					 ring->rx_buf_len);
+					 xdp_frame_sz);
 		if (err)
 			return err;
 		err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3616,7 +3619,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	}
 
 skip:
-	xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+	xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
 				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
-- 
cgit v1.2.3


From 75d9228982f23d68066ca0b7d87014c3eb8ddc85 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:48 +0100
Subject: libeth, idpf: use truesize as XDP RxQ info frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead
of DMA write size. Different assumptions in idpf driver configuration lead
to negative tailroom.

To make it worse, buffer sizes are not actually uniform in idpf when
splitq is enabled, as there are several buffer queues, so rxq->rx_buf_size
is meaningless in this case.

Use truesize of the first bufq in AF_XDP ZC, as there is only one. Disable
growing tail for regular splitq.

Fixes: ac8a861f632e ("idpf: prepare structures to support XDP")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-8-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/xdp.c   | 6 +++++-
 drivers/net/ethernet/intel/idpf/xsk.c   | 1 +
 drivers/net/ethernet/intel/libeth/xsk.c | 1 +
 include/net/libeth/xsk.h                | 3 +++
 4 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c
index 6ac9c6624c2a..cbccd4546768 100644
--- a/drivers/net/ethernet/intel/idpf/xdp.c
+++ b/drivers/net/ethernet/intel/idpf/xdp.c
@@ -47,12 +47,16 @@ static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg)
 {
 	const struct idpf_vport *vport = rxq->q_vector->vport;
 	const struct idpf_q_vec_rsrc *rsrc;
+	u32 frag_size = 0;
 	bool split;
 	int err;
 
+	if (idpf_queue_has(XSK, rxq))
+		frag_size = rxq->bufq_sets[0].bufq.truesize;
+
 	err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx,
 				 rxq->q_vector->napi.napi_id,
-				 rxq->rx_buf_size);
+				 frag_size);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c
index 676cbd80774d..d95d3efdfd36 100644
--- a/drivers/net/ethernet/intel/idpf/xsk.c
+++ b/drivers/net/ethernet/intel/idpf/xsk.c
@@ -403,6 +403,7 @@ int idpf_xskfq_init(struct idpf_buf_queue *bufq)
 	bufq->pending = fq.pending;
 	bufq->thresh = fq.thresh;
 	bufq->rx_buf_size = fq.buf_len;
+	bufq->truesize = fq.truesize;
 
 	if (!idpf_xskfq_refill(bufq))
 		netdev_err(bufq->pool->netdev,
diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c
index 846e902e31b6..4882951d5c9c 100644
--- a/drivers/net/ethernet/intel/libeth/xsk.c
+++ b/drivers/net/ethernet/intel/libeth/xsk.c
@@ -167,6 +167,7 @@ int libeth_xskfq_create(struct libeth_xskfq *fq)
 	fq->pending = fq->count;
 	fq->thresh = libeth_xdp_queue_threshold(fq->count);
 	fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool);
+	fq->truesize = xsk_pool_get_rx_frag_step(fq->pool);
 
 	return 0;
 }
diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index 481a7b28e6f2..82b5d21aae87 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp,
  * @pending: current number of XSkFQEs to refill
  * @thresh: threshold below which the queue is refilled
  * @buf_len: HW-writeable length per each buffer
+ * @truesize: step between consecutive buffers, 0 if none exists
  * @nid: ID of the closest NUMA node with memory
  */
 struct libeth_xskfq {
@@ -614,6 +615,8 @@ struct libeth_xskfq {
 	u32			thresh;
 
 	u32			buf_len;
+	u32			truesize;
+
 	int			nid;
 };
 
-- 
cgit v1.2.3


From f8e18abf183dbd636a8725532c7f5aa58957de84 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:49 +0100
Subject: net: enetc: use truesize as XDP RxQ info frag_size

The only user of frag_size field in XDP RxQ info is
bpf_xdp_frags_increase_tail(). It clearly expects truesize instead of DMA
write size. Different assumptions in enetc driver configuration lead to
negative tailroom.

Set frag_size to the same value as frame_sz.

Fixes: 2768b2e2f7d2 ("net: enetc: register XDP RX queues with frag_size")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-9-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 70768392912c..a146ceaf2ed6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3467,7 +3467,7 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	priv->rx_ring[i] = bdr;
 
 	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
-				 ENETC_RXB_DMA_SIZE_XDP);
+				 ENETC_RXB_TRUESIZE);
 	if (err)
 		goto free_vector;
 
-- 
cgit v1.2.3


From 8821e857759be9db3cde337ad328b71fe5c8a55f Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Thu, 5 Mar 2026 12:12:50 +0100
Subject: xdp: produce a warning when calculated tailroom is negative
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many ethernet drivers report xdp Rx queue frag size as being the same as
DMA write size. However, the only user of this field, namely
bpf_xdp_frags_increase_tail(), clearly expects a truesize.

Such difference leads to unspecific memory corruption issues under certain
circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when
running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses
all DMA-writable space in 2 buffers. This would be fine, if only
rxq->frag_size was properly set to 4K, but value of 3K results in a
negative tailroom, because there is a non-zero page offset.

We are supposed to return -EINVAL and be done with it in such case, but due
to tailroom being stored as an unsigned int, it is reported to be somewhere
near UINT_MAX, resulting in a tail being grown, even if the requested
offset is too much (it is around 2K in the abovementioned test). This later
leads to all kinds of unspecific calltraces.

[ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6
[ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4
[ 7340.338179]  in libc.so.6[61c9d,7f4161aaf000+160000]
[ 7340.339230]  in xskxceiver[42b5,400000+69000]
[ 7340.340300]  likely on CPU 6 (core 0, socket 6)
[ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe
[ 7340.340888]  likely on CPU 3 (core 0, socket 3)
[ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7
[ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI
[ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy)
[ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014
[ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80
[ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89
[ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202
[ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010
[ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff
[ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0
[ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0
[ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500
[ 7340.418229] FS:  0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000
[ 7340.419489] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0
[ 7340.421237] PKRU: 55555554
[ 7340.421623] Call Trace:
[ 7340.421987]  <TASK>
[ 7340.422309]  ? softleaf_from_pte+0x77/0xa0
[ 7340.422855]  swap_pte_batch+0xa7/0x290
[ 7340.423363]  zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270
[ 7340.424102]  zap_pte_range+0x281/0x580
[ 7340.424607]  zap_pmd_range.isra.0+0xc9/0x240
[ 7340.425177]  unmap_page_range+0x24d/0x420
[ 7340.425714]  unmap_vmas+0xa1/0x180
[ 7340.426185]  exit_mmap+0xe1/0x3b0
[ 7340.426644]  __mmput+0x41/0x150
[ 7340.427098]  exit_mm+0xb1/0x110
[ 7340.427539]  do_exit+0x1b2/0x460
[ 7340.427992]  do_group_exit+0x2d/0xc0
[ 7340.428477]  get_signal+0x79d/0x7e0
[ 7340.428957]  arch_do_signal_or_restart+0x34/0x100
[ 7340.429571]  exit_to_user_mode_loop+0x8e/0x4c0
[ 7340.430159]  do_syscall_64+0x188/0x6b0
[ 7340.430672]  ? __do_sys_clone3+0xd9/0x120
[ 7340.431212]  ? switch_fpu_return+0x4e/0xd0
[ 7340.431761]  ? arch_exit_to_user_mode_prepare.isra.0+0xa1/0xc0
[ 7340.432498]  ? do_syscall_64+0xbb/0x6b0
[ 7340.433015]  ? __handle_mm_fault+0x445/0x690
[ 7340.433582]  ? count_memcg_events+0xd6/0x210
[ 7340.434151]  ? handle_mm_fault+0x212/0x340
[ 7340.434697]  ? do_user_addr_fault+0x2b4/0x7b0
[ 7340.435271]  ? clear_bhb_loop+0x30/0x80
[ 7340.435788]  ? clear_bhb_loop+0x30/0x80
[ 7340.436299]  ? clear_bhb_loop+0x30/0x80
[ 7340.436812]  ? clear_bhb_loop+0x30/0x80
[ 7340.437323]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[ 7340.437973] RIP: 0033:0x7f4161b14169
[ 7340.438468] Code: Unable to access opcode bytes at 0x7f4161b1413f.
[ 7340.439242] RSP: 002b:00007ffc6ebfa770 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca
[ 7340.440173] RAX: fffffffffffffe00 RBX: 00000000000005a1 RCX: 00007f4161b14169
[ 7340.441061] RDX: 00000000000005a1 RSI: 0000000000000109 RDI: 00007f415bfff990
[ 7340.441943] RBP: 00007ffc6ebfa7a0 R08: 0000000000000000 R09: 00000000ffffffff
[ 7340.442824] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[ 7340.443707] R13: 0000000000000000 R14: 00007f415bfff990 R15: 00007f415bfff6c0
[ 7340.444586]  </TASK>
[ 7340.444922] Modules linked in: rfkill intel_rapl_msr intel_rapl_common intel_uncore_frequency_common skx_edac_common nfit libnvdimm kvm_intel vfat fat kvm snd_pcm irqbypass rapl iTCO_wdt snd_timer intel_pmc_bxt iTCO_vendor_support snd ixgbevf virtio_net soundcore i2c_i801 pcspkr libeth_xdp net_failover i2c_smbus lpc_ich failover libeth virtio_balloon joydev 9p fuse loop zram lz4hc_compress lz4_compress 9pnet_virtio 9pnet netfs ghash_clmulni_intel serio_raw qemu_fw_cfg
[ 7340.449650] ---[ end trace 0000000000000000 ]---

The issue can be fixed in all in-tree drivers, but we cannot just trust OOT
drivers to not do this. Therefore, make tailroom a signed int and produce a
warning when it is negative to prevent such mistakes in the future.

Fixes: bf25146a5595 ("bpf: add frags support to the bpf_xdp_adjust_tail() API")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20260305111253.2317394-10-larysa.zaremba@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index d6fafb3633b0..a77d23fe2359 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4150,13 +4150,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 	skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1];
 	struct xdp_rxq_info *rxq = xdp->rxq;
-	unsigned int tailroom;
+	int tailroom;
 
 	if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
 		return -EOPNOTSUPP;
 
 	tailroom = rxq->frag_size - skb_frag_size(frag) -
 		   skb_frag_off(frag) % rxq->frag_size;
+	WARN_ON_ONCE(tailroom < 0);
 	if (unlikely(offset > tailroom))
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 0927780c90ce551869fb692279d66387a4b66af5 Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Thu, 5 Mar 2026 14:18:56 +0800
Subject: sched_ext: Use READ_ONCE() for lock-free reads of module param
 variables

bypass_lb_cpu() reads scx_bypass_lb_intv_us and scx_slice_bypass_us
without holding any lock, in timer callback context where module
parameter writes via sysfs can happen concurrently:

    min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV;
                   ^^^^^^^^^^^^^^^^^^^^
                   plain read -- KCSAN data race

    if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us))
                                           ^^^^^^^^^^^^^^^^^
                                           plain read -- KCSAN data race

scx_bypass_lb_intv_us already uses READ_ONCE() in scx_bypass_lb_timerfn()
and scx_bypass() for its other lock-free read sites, leaving
bypass_lb_cpu() inconsistent. scx_slice_bypass_us has the same
lock-free access pattern in the same function.

Fix both plain reads by using READ_ONCE() to complete the concurrent
access annotation and make the code KCSAN-clean.

Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index c56de568ed94..10866bfb88bf 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3908,8 +3908,8 @@ static u32 bypass_lb_cpu(struct scx_sched *sch, struct rq *rq,
 	 * consider offloading iff the total queued duration is over the
 	 * threshold.
 	 */
-	min_delta_us = scx_bypass_lb_intv_us / SCX_BYPASS_LB_MIN_DELTA_DIV;
-	if (delta < DIV_ROUND_UP(min_delta_us, scx_slice_bypass_us))
+	min_delta_us = READ_ONCE(scx_bypass_lb_intv_us) / SCX_BYPASS_LB_MIN_DELTA_DIV;
+	if (delta < DIV_ROUND_UP(min_delta_us, READ_ONCE(scx_slice_bypass_us)))
 		return 0;
 
 	raw_spin_rq_lock_irq(rq);
-- 
cgit v1.2.3


From 70f54f61a3d52af13b72248a63e98eddf4c990ac Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Thu, 5 Mar 2026 07:29:00 +0100
Subject: sched_ext: Document task ownership state machine

The task ownership state machine in sched_ext is quite hard to follow
from the code alone. The interaction of ownership states, memory
ordering rules and cross-CPU "lock dancing" makes the overall model
subtle.

Extend the documentation next to scx_ops_state to provide a more
structured and self-contained description of the state transitions and
their synchronization rules.

The new reference should make the code easier to reason about and
maintain and can help future contributors understand the overall
task-ownership workflow.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_internal.h | 114 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 98 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 11ebb744d893..00b450597f3e 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1035,26 +1035,108 @@ static const char *scx_enable_state_str[] = {
 };
 
 /*
- * sched_ext_entity->ops_state
+ * Task Ownership State Machine (sched_ext_entity->ops_state)
  *
- * Used to track the task ownership between the SCX core and the BPF scheduler.
- * State transitions look as follows:
+ * The sched_ext core uses this state machine to track task ownership
+ * between the SCX core and the BPF scheduler. This allows the BPF
+ * scheduler to dispatch tasks without strict ordering requirements, while
+ * the SCX core safely rejects invalid dispatches.
  *
- * NONE -> QUEUEING -> QUEUED -> DISPATCHING
- *   ^              |                 |
- *   |              v                 v
- *   \-------------------------------/
+ * State Transitions
  *
- * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call
- * sites for explanations on the conditions being waited upon and why they are
- * safe. Transitions out of them into NONE or QUEUED must store_release and the
- * waiters should load_acquire.
+ *       .------------> NONE (owned by SCX core)
+ *       |               |           ^
+ *       |       enqueue |           | direct dispatch
+ *       |               v           |
+ *       |           QUEUEING -------'
+ *       |               |
+ *       |       enqueue |
+ *       |     completes |
+ *       |               v
+ *       |            QUEUED (owned by BPF scheduler)
+ *       |               |
+ *       |      dispatch |
+ *       |               |
+ *       |               v
+ *       |          DISPATCHING
+ *       |               |
+ *       |      dispatch |
+ *       |     completes |
+ *       `---------------'
  *
- * Tracking scx_ops_state enables sched_ext core to reliably determine whether
- * any given task can be dispatched by the BPF scheduler at all times and thus
- * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler
- * to try to dispatch any task anytime regardless of its state as the SCX core
- * can safely reject invalid dispatches.
+ * State Descriptions
+ *
+ * - %SCX_OPSS_NONE:
+ *     Task is owned by the SCX core. It's either on a run queue, running,
+ *     or being manipulated by the core scheduler. The BPF scheduler has no
+ *     claim on this task.
+ *
+ * - %SCX_OPSS_QUEUEING:
+ *     Transitional state while transferring a task from the SCX core to
+ *     the BPF scheduler. The task's rq lock is held during this state.
+ *     Since QUEUEING is both entered and exited under the rq lock, dequeue
+ *     can never observe this state (it would be a BUG). When finishing a
+ *     dispatch, if the task is still in %SCX_OPSS_QUEUEING the completion
+ *     path busy-waits for it to leave this state (via wait_ops_state())
+ *     before retrying.
+ *
+ * - %SCX_OPSS_QUEUED:
+ *     Task is owned by the BPF scheduler. It's on a DSQ (dispatch queue)
+ *     and the BPF scheduler is responsible for dispatching it. A QSEQ
+ *     (queue sequence number) is embedded in this state to detect
+ *     dispatch/dequeue races: if a task is dequeued and re-enqueued, the
+ *     QSEQ changes and any in-flight dispatch operations targeting the old
+ *     QSEQ are safely ignored.
+ *
+ * - %SCX_OPSS_DISPATCHING:
+ *     Transitional state while transferring a task from the BPF scheduler
+ *     back to the SCX core. This state indicates the BPF scheduler has
+ *     selected the task for execution. When dequeue needs to take the task
+ *     off a DSQ and it is still in %SCX_OPSS_DISPATCHING, the dequeue path
+ *     busy-waits for it to leave this state (via wait_ops_state()) before
+ *     proceeding. Exits to %SCX_OPSS_NONE when dispatch completes.
+ *
+ * Memory Ordering
+ *
+ * Transitions out of %SCX_OPSS_QUEUEING and %SCX_OPSS_DISPATCHING into
+ * %SCX_OPSS_NONE or %SCX_OPSS_QUEUED must use atomic_long_set_release()
+ * and waiters must use atomic_long_read_acquire(). This ensures proper
+ * synchronization between concurrent operations.
+ *
+ * Cross-CPU Task Migration
+ *
+ * When moving a task in the %SCX_OPSS_DISPATCHING state, we can't simply
+ * grab the target CPU's rq lock because a concurrent dequeue might be
+ * waiting on %SCX_OPSS_DISPATCHING while holding the source rq lock
+ * (deadlock).
+ *
+ * The sched_ext core uses a "lock dancing" protocol coordinated by
+ * p->scx.holding_cpu. When moving a task to a different rq:
+ *
+ *   1. Verify task can be moved (CPU affinity, migration_disabled, etc.)
+ *   2. Set p->scx.holding_cpu to the current CPU
+ *   3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
+ *      is set, so clearing DISPATCHING first prevents the circular wait
+ *      (safe to lock the rq we need)
+ *   4. Unlock the current CPU's rq
+ *   5. Lock src_rq (where the task currently lives)
+ *   6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
+ *      race (dequeue clears holding_cpu to -1 when it takes the task), in
+ *      this case migration is aborted
+ *   7. If src_rq == dst_rq: clear holding_cpu and enqueue directly
+ *      into dst_rq's local DSQ (no lock swap needed)
+ *   8. Otherwise: call move_remote_task_to_local_dsq(), which releases
+ *      src_rq, locks dst_rq, and performs the deactivate/activate
+ *      migration cycle (dst_rq is held on return)
+ *   9. Unlock dst_rq and re-lock the current CPU's rq to restore
+ *      the lock state expected by the caller
+ *
+ * If any verification fails, abort the migration.
+ *
+ * This state tracking allows the BPF scheduler to try to dispatch any task
+ * at any time regardless of its state. The SCX core can safely
+ * reject/ignore invalid dispatches, simplifying the BPF scheduler
+ * implementation.
  */
 enum scx_ops_state {
 	SCX_OPSS_NONE,		/* owned by the SCX core */
-- 
cgit v1.2.3


From e07fc9e2da91f6d9eeafa2961be9dc09d65ed633 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Wed, 4 Mar 2026 16:22:21 +0000
Subject: KVM: arm64: Fix page leak in user_mem_abort() on atomic fault

When a guest performs an atomic/exclusive operation on memory lacking
the required attributes, user_mem_abort() injects a data abort and
returns early. However, it fails to release the reference to the
host page acquired via __kvm_faultin_pfn().

A malicious guest could repeatedly trigger this fault, leaking host
page references and eventually causing host memory exhaustion (OOM).

Fix this by consolidating the early error returns to a new out_put_page
label that correctly calls kvm_release_page_unused().

Fixes: 2937aeec9dc5 ("KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory")
Signed-off-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Yuan Yao <yaoyuan@linux.alibaba.com>
Link: https://patch.msgid.link/20260304162222.836152-2-tabba@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/mmu.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ec2eee857208..e1d6a4f591a9 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1837,10 +1837,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && s2_force_noncacheable)
 		ret = -ENOEXEC;
 
-	if (ret) {
-		kvm_release_page_unused(page);
-		return ret;
-	}
+	if (ret)
+		goto out_put_page;
 
 	/*
 	 * Guest performs atomic/exclusive operations on memory with unsupported
@@ -1850,7 +1848,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 */
 	if (esr_fsc_is_excl_atomic_fault(kvm_vcpu_get_esr(vcpu))) {
 		kvm_inject_dabt_excl_atomic(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
+		ret = 1;
+		goto out_put_page;
 	}
 
 	if (nested)
@@ -1936,6 +1935,10 @@ out_unlock:
 		mark_page_dirty_in_slot(kvm, memslot, gfn);
 
 	return ret != -EAGAIN ? ret : 0;
+
+out_put_page:
+	kvm_release_page_unused(page);
+	return ret;
 }
 
 /* Resolve the access fault by making the page young again. */
-- 
cgit v1.2.3


From e31a374a99f5026df6ebff2a1c49492276e776fd Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 4 Mar 2026 19:15:48 +0100
Subject: fbdev: au1100fb: Fix build on MIPS64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix an error reported by the kernel test robot:
 au1100fb.c: error: implicit declaration of function 'KSEG1ADDR'; did you mean 'CKSEG1ADDR'?

arch/mips/include/asm/addrspace.h defines KSEG1ADDR only for 32 bit
configurations. So provide its compile-test stub also for 64bit mips builds.

Fixes: 6f366e86481a ("fbdev: au1100fb: Make driver compilable on non-mips platforms")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603042127.PT6LuKqi-lkp@intel.com/
Signed-off-by: Helge Deller <deller@gmx.de>
Acked-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
---
 drivers/video/fbdev/au1100fb.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 1a04154bc535..c54cfcd832bb 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -380,8 +380,12 @@ static struct au1100fb_panel known_lcd_panels[] =
 #define panel_is_color(panel) (panel->control_base & LCD_CONTROL_PC)
 #define panel_swap_rgb(panel) (panel->control_base & LCD_CONTROL_CCO)
 
-#if defined(CONFIG_COMPILE_TEST) && !defined(CONFIG_MIPS)
-/* This is only defined to be able to compile this driver on non-mips platforms */
+#if defined(CONFIG_COMPILE_TEST) && (!defined(CONFIG_MIPS) || defined(CONFIG_64BIT))
+/*
+ * KSEG1ADDR() is defined in arch/mips/include/asm/addrspace.h
+ * for 32 bit configurations. Provide a stub for compile testing
+ * on other platforms.
+ */
 #define KSEG1ADDR(x) (x)
 #endif
 
-- 
cgit v1.2.3


From 35c3f72a2d55dbf52f28f4ecae51c76be1acf545 Mon Sep 17 00:00:00 2001
From: Tzung-Bi Shih <tzungbi@kernel.org>
Date: Fri, 6 Feb 2026 03:30:33 +0000
Subject: remoteproc: mediatek: Unprepare SCP clock during system suspend

Prior to commit d935187cfb27 ("remoteproc: mediatek: Break lock
dependency to prepare_lock"), `scp->clk` was prepared and enabled only
when it needs to communicate with the SCP.  The commit d935187cfb27
moved the prepare operation to remoteproc's prepare(), keeping the clock
prepared as long as the SCP is running.

The power consumption due to the prolonged clock preparation can be
negligible when the system is running, as SCP is designed to be a very
power efficient processor.

However, the clock remains prepared even when the system enters system
suspend.  This prevents the underlying clock controller (and potentially
the parent PLLs) from shutting down, which increases power consumption
and may block the system from entering deep sleep states.

Add suspend and resume callbacks.  Unprepare the clock in suspend() if
it was active and re-prepare it in resume() to ensure the clock is
properly disabled during system suspend, while maintaining the "always
prepared" semantics while the system is active.  The driver doesn't
implement .attach() callback, hence it only checks for RPROC_RUNNING.

Fixes: d935187cfb27 ("remoteproc: mediatek: Break lock dependency to prepare_lock")
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://lore.kernel.org/r/20260206033034.3031781-1-tzungbi@kernel.org
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/mtk_scp.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
index 4651311aeb07..bb6f6a16d895 100644
--- a/drivers/remoteproc/mtk_scp.c
+++ b/drivers/remoteproc/mtk_scp.c
@@ -1592,12 +1592,51 @@ static const struct of_device_id mtk_scp_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_scp_of_match);
 
+static int __maybe_unused scp_suspend(struct device *dev)
+{
+	struct mtk_scp *scp = dev_get_drvdata(dev);
+	struct rproc *rproc = scp->rproc;
+
+	/*
+	 * Only unprepare if the SCP is running and holding the clock.
+	 *
+	 * Note: `scp_ops` doesn't implement .attach() callback, hence
+	 * `rproc->state` can never be RPROC_ATTACHED.  Otherwise, it
+	 * should also be checked here.
+	 */
+	if (rproc->state == RPROC_RUNNING)
+		clk_unprepare(scp->clk);
+	return 0;
+}
+
+static int __maybe_unused scp_resume(struct device *dev)
+{
+	struct mtk_scp *scp = dev_get_drvdata(dev);
+	struct rproc *rproc = scp->rproc;
+
+	/*
+	 * Only prepare if the SCP was running and holding the clock.
+	 *
+	 * Note: `scp_ops` doesn't implement .attach() callback, hence
+	 * `rproc->state` can never be RPROC_ATTACHED.  Otherwise, it
+	 * should also be checked here.
+	 */
+	if (rproc->state == RPROC_RUNNING)
+		return clk_prepare(scp->clk);
+	return 0;
+}
+
+static const struct dev_pm_ops scp_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(scp_suspend, scp_resume)
+};
+
 static struct platform_driver mtk_scp_driver = {
 	.probe = scp_probe,
 	.remove = scp_remove,
 	.driver = {
 		.name = "mtk-scp",
 		.of_match_table = mtk_scp_of_match,
+		.pm = &scp_pm_ops,
 	},
 };
 
-- 
cgit v1.2.3


From 97e4567d39941248579da34b7fbb568e6659511e Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Sun, 8 Feb 2026 19:30:35 +0800
Subject: remoteproc: imx_rproc: Fix unreachable platform prepare_ops

Smatch reports unreachable code in imx_rproc_prepare(), where an early
return inside the reserved-memory parsing loop prevents platform
prepare_ops from being executed.

When of_reserved_mem_region_to_resource() fails, imx_rproc_prepare()
returns immediately, so the platform-specific prepare callback is never
called. As a result, prepare_ops such as imx_rproc_sm_lmm_prepare() on
i.MX95 have no chance to run.

This is problematic when Linux controls the M7 Logical Machine and is
responsible for preparing resources such as TCM. Without running the
platform prepare callback, loading the M7 ELF into TCM may fail if the
bootloader did not power up and initialize TCM.

Fix this by breaking out of the reserved-memory loop instead of
returning, allowing the platform prepare_ops to be executed as intended.

Fixes: edd2a9956055 ("remoteproc: imx_rproc: Introduce prepare ops for imx_rproc_dcfg")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-remoteproc/aYYXAa2Fj36XG4yQ@p14s/T/#t
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://lore.kernel.org/r/20260208-imx-rproc-fix-v1-1-ad74555eb9a4@nxp.com
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
---
 drivers/remoteproc/imx_rproc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
index f5f916d67905..8c8ddbf995a4 100644
--- a/drivers/remoteproc/imx_rproc.c
+++ b/drivers/remoteproc/imx_rproc.c
@@ -617,7 +617,7 @@ static int imx_rproc_prepare(struct rproc *rproc)
 
 		err = of_reserved_mem_region_to_resource(np, i++, &res);
 		if (err)
-			return 0;
+			break;
 
 		/*
 		 * Ignore the first memory region which will be used vdev buffer.
-- 
cgit v1.2.3


From f42f9091be9e5ff57567a3945cfcdd498f475348 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:37 -0800
Subject: workqueue: Use POOL_BH instead of WQ_BH when checking pool flags

pr_cont_worker_id() checks pool->flags against WQ_BH, which is a
workqueue-level flag (defined in workqueue.h). Pool flags use a
separate namespace with POOL_* constants (defined in workqueue.c).
The correct constant is POOL_BH. Both WQ_BH and POOL_BH are defined
as (1 << 0) so this has no behavioral impact, but it is semantically
wrong and inconsistent with every other pool-level BH check in the
file.

Fixes: 4cb1ef64609f ("workqueue: Implement BH workqueues to eventually replace tasklets")
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aeaec79bc09c..1e5b6cb0fbda 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6274,7 +6274,7 @@ static void pr_cont_worker_id(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	if (pool->flags & WQ_BH)
+	if (pool->flags & POOL_BH)
 		pr_cont("bh%s",
 			pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : "");
 	else
-- 
cgit v1.2.3


From 6037160e52d72028da68546fd270a7dcac130d85 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:38 -0800
Subject: workqueue: Rename pool->watchdog_ts to pool->last_progress_ts

The watchdog_ts name doesn't convey what the timestamp actually tracks.
This field tracks the last time a workqueue got progress.

Rename it to last_progress_ts to make it clear that it records when the
pool last made forward progress (started processing new work items).

No functional change.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1e5b6cb0fbda..687d5c55c617 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -190,7 +190,7 @@ struct worker_pool {
 	int			id;		/* I: pool ID */
 	unsigned int		flags;		/* L: flags */
 
-	unsigned long		watchdog_ts;	/* L: watchdog timestamp */
+	unsigned long		last_progress_ts;	/* L: last forward progress timestamp */
 	bool			cpu_stall;	/* WD: stalled cpu bound pool */
 
 	/*
@@ -1697,7 +1697,7 @@ static void __pwq_activate_work(struct pool_workqueue *pwq,
 	WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE));
 	trace_workqueue_activate_work(work);
 	if (list_empty(&pwq->pool->worklist))
-		pwq->pool->watchdog_ts = jiffies;
+		pwq->pool->last_progress_ts = jiffies;
 	move_linked_works(work, &pwq->pool->worklist, NULL);
 	__clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb);
 }
@@ -2348,7 +2348,7 @@ retry:
 	 */
 	if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) {
 		if (list_empty(&pool->worklist))
-			pool->watchdog_ts = jiffies;
+			pool->last_progress_ts = jiffies;
 
 		trace_workqueue_activate_work(work);
 		insert_work(pwq, work, &pool->worklist, work_flags);
@@ -3352,7 +3352,7 @@ static void process_scheduled_works(struct worker *worker)
 	while ((work = list_first_entry_or_null(&worker->scheduled,
 						struct work_struct, entry))) {
 		if (first) {
-			worker->pool->watchdog_ts = jiffies;
+			worker->pool->last_progress_ts = jiffies;
 			first = false;
 		}
 		process_one_work(worker, work);
@@ -4850,7 +4850,7 @@ static int init_worker_pool(struct worker_pool *pool)
 	pool->cpu = -1;
 	pool->node = NUMA_NO_NODE;
 	pool->flags |= POOL_DISASSOCIATED;
-	pool->watchdog_ts = jiffies;
+	pool->last_progress_ts = jiffies;
 	INIT_LIST_HEAD(&pool->worklist);
 	INIT_LIST_HEAD(&pool->idle_list);
 	hash_init(pool->busy_hash);
@@ -6462,7 +6462,7 @@ static void show_one_worker_pool(struct worker_pool *pool)
 
 	/* How long the first pending work is waiting for a worker. */
 	if (!list_empty(&pool->worklist))
-		hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000;
+		hung = jiffies_to_msecs(jiffies - pool->last_progress_ts) / 1000;
 
 	/*
 	 * Defer printing to avoid deadlocks in console drivers that
@@ -7691,7 +7691,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
 		else
 			touched = READ_ONCE(wq_watchdog_touched);
-		pool_ts = READ_ONCE(pool->watchdog_ts);
+		pool_ts = READ_ONCE(pool->last_progress_ts);
 
 		if (time_after(pool_ts, touched))
 			ts = pool_ts;
-- 
cgit v1.2.3


From e8e14ac7cfe437b896838e7f7d07c573965b4e4e Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:39 -0800
Subject: workqueue: Show in-flight work item duration in stall diagnostics

When diagnosing workqueue stalls, knowing how long each in-flight work
item has been executing is valuable. Add a current_start timestamp
(jiffies) to struct worker, set it when a work item begins execution in
process_one_work(), and print the elapsed wall-clock time in show_pwq().

Unlike current_at (which tracks CPU runtime and resets on wakeup for
CPU-intensive detection), current_start is never reset because the
diagnostic cares about total wall-clock time including sleeps.

Before: in-flight: 165:stall_work_fn [wq_stall]
After:  in-flight: 165:stall_work_fn [wq_stall] for 100s

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c          | 3 +++
 kernel/workqueue_internal.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 687d5c55c617..56d8af13843f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3204,6 +3204,7 @@ __acquires(&pool->lock)
 	worker->current_pwq = pwq;
 	if (worker->task)
 		worker->current_at = worker->task->se.sum_exec_runtime;
+	worker->current_start = jiffies;
 	work_data = *work_data_bits(work);
 	worker->current_color = get_work_color(work_data);
 
@@ -6359,6 +6360,8 @@ static void show_pwq(struct pool_workqueue *pwq)
 			pr_cont(" %s", comma ? "," : "");
 			pr_cont_worker_id(worker);
 			pr_cont(":%ps", worker->current_func);
+			pr_cont(" for %us",
+				jiffies_to_msecs(jiffies - worker->current_start) / 1000);
 			list_for_each_entry(work, &worker->scheduled, entry)
 				pr_cont_work(false, work, &pcws);
 			pr_cont_work_flush(comma, (work_func_t)-1L, &pcws);
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index f6275944ada7..8def1ddc5a1b 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -32,6 +32,7 @@ struct worker {
 	work_func_t		current_func;	/* K: function */
 	struct pool_workqueue	*current_pwq;	/* K: pwq */
 	u64			current_at;	/* K: runtime at start or last wakeup */
+	unsigned long		current_start;	/* K: start time of current work item */
 	unsigned int		current_color;	/* K: color */
 
 	int			sleeping;	/* S: is worker sleeping? */
-- 
cgit v1.2.3


From 8823eaef45da7f156a1396f40d53b985c511edef Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:40 -0800
Subject: workqueue: Show all busy workers in stall diagnostics
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

show_cpu_pool_hog() only prints workers whose task is currently running
on the CPU (task_is_running()).  This misses workers that are busy
processing a work item but are sleeping or blocked — for example, a
worker that clears PF_WQ_WORKER and enters wait_event_idle().  Such a
worker still occupies a pool slot and prevents progress, yet produces
an empty backtrace section in the watchdog output.

This is happening on real arm64 systems, where
toggle_allocation_gate() IPIs every single CPU in the machine (which
lacks NMI), causing workqueue stalls that show empty backtraces because
toggle_allocation_gate() is sleeping in wait_event_idle().

Remove the task_is_running() filter so every in-flight worker in the
pool's busy_hash is dumped.  The busy_hash is protected by pool->lock,
which is already held.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 56d8af13843f..09b9ad78d566 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7583,9 +7583,9 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds
 
 /*
  * Show workers that might prevent the processing of pending work items.
- * The only candidates are CPU-bound workers in the running state.
- * Pending work items should be handled by another idle worker
- * in all other situations.
+ * A busy worker that is not running on the CPU (e.g. sleeping in
+ * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as
+ * effectively as a CPU-bound one, so dump every in-flight worker.
  */
 static void show_cpu_pool_hog(struct worker_pool *pool)
 {
@@ -7596,19 +7596,17 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 	raw_spin_lock_irqsave(&pool->lock, irq_flags);
 
 	hash_for_each(pool->busy_hash, bkt, worker, hentry) {
-		if (task_is_running(worker->task)) {
-			/*
-			 * Defer printing to avoid deadlocks in console
-			 * drivers that queue work while holding locks
-			 * also taken in their write paths.
-			 */
-			printk_deferred_enter();
+		/*
+		 * Defer printing to avoid deadlocks in console
+		 * drivers that queue work while holding locks
+		 * also taken in their write paths.
+		 */
+		printk_deferred_enter();
 
-			pr_info("pool %d:\n", pool->id);
-			sched_show_task(worker->task);
+		pr_info("pool %d:\n", pool->id);
+		sched_show_task(worker->task);
 
-			printk_deferred_exit();
-		}
+		printk_deferred_exit();
 	}
 
 	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
@@ -7619,7 +7617,7 @@ static void show_cpu_pools_hogs(void)
 	struct worker_pool *pool;
 	int pi;
 
-	pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n");
+	pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n");
 
 	rcu_read_lock();
 
-- 
cgit v1.2.3


From 9e83d5104a70d8545bad61a77e166190d9447e1d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 5 Mar 2026 08:15:41 -0800
Subject: workqueue: Add stall detector sample module

Add a sample module under samples/workqueue/stall_detector/ that
reproduces a workqueue stall caused by PF_WQ_WORKER misuse.  The
module queues two work items on the same per-CPU pool, then clears
PF_WQ_WORKER and sleeps in wait_event_idle(), hiding from the
concurrency manager and stalling the second work item indefinitely.

This is useful for testing the workqueue watchdog stall diagnostics.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 samples/workqueue/stall_detector/Makefile   |  1 +
 samples/workqueue/stall_detector/wq_stall.c | 98 +++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)
 create mode 100644 samples/workqueue/stall_detector/Makefile
 create mode 100644 samples/workqueue/stall_detector/wq_stall.c

diff --git a/samples/workqueue/stall_detector/Makefile b/samples/workqueue/stall_detector/Makefile
new file mode 100644
index 000000000000..8849e85e95bb
--- /dev/null
+++ b/samples/workqueue/stall_detector/Makefile
@@ -0,0 +1 @@
+obj-m += wq_stall.o
diff --git a/samples/workqueue/stall_detector/wq_stall.c b/samples/workqueue/stall_detector/wq_stall.c
new file mode 100644
index 000000000000..6f4a497b1881
--- /dev/null
+++ b/samples/workqueue/stall_detector/wq_stall.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * wq_stall - Test module for the workqueue stall detector.
+ *
+ * Deliberately creates a workqueue stall so the watchdog fires and
+ * prints diagnostic output.  Useful for verifying that the stall
+ * detector correctly identifies stuck workers and produces useful
+ * backtraces.
+ *
+ * The stall is triggered by clearing PF_WQ_WORKER before sleeping,
+ * which hides the worker from the concurrency manager.  A second
+ * work item queued on the same pool then sits in the worklist with
+ * no worker available to process it.
+ *
+ * After ~30s the workqueue watchdog fires:
+ *   BUG: workqueue lockup - pool cpus=N ...
+ *
+ * Build:
+ *	make -C <kernel tree> M=samples/workqueue/stall_detector modules
+ *
+ * Copyright (c) 2026 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2026 Breno Leitao <leitao@debian.org>
+ */
+
+#include <linux/module.h>
+#include <linux/workqueue.h>
+#include <linux/wait.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+
+static DECLARE_WAIT_QUEUE_HEAD(stall_wq_head);
+static atomic_t wake_condition = ATOMIC_INIT(0);
+static struct work_struct stall_work1;
+static struct work_struct stall_work2;
+
+static void stall_work2_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: second work item finally ran\n");
+}
+
+static void stall_work1_fn(struct work_struct *work)
+{
+	pr_info("wq_stall: first work item running on cpu %d\n",
+		raw_smp_processor_id());
+
+	/*
+	 * Queue second item while we're still counted as running
+	 * (pool->nr_running > 0).  Since schedule_work() on a per-CPU
+	 * workqueue targets raw_smp_processor_id(), item 2 lands on the
+	 * same pool.  __queue_work -> kick_pool -> need_more_worker()
+	 * sees nr_running > 0 and does NOT wake a new worker.
+	 */
+	schedule_work(&stall_work2);
+
+	/*
+	 * Hide from the workqueue concurrency manager.  Without
+	 * PF_WQ_WORKER, schedule() won't call wq_worker_sleeping(),
+	 * so nr_running is never decremented and no replacement
+	 * worker is created.  Item 2 stays stuck in pool->worklist.
+	 */
+	current->flags &= ~PF_WQ_WORKER;
+
+	pr_info("wq_stall: entering wait_event_idle (PF_WQ_WORKER cleared)\n");
+	pr_info("wq_stall: expect 'BUG: workqueue lockup' in ~30-60s\n");
+	wait_event_idle(stall_wq_head, atomic_read(&wake_condition) != 0);
+
+	/* Restore so process_one_work() cleanup works correctly */
+	current->flags |= PF_WQ_WORKER;
+	pr_info("wq_stall: woke up, PF_WQ_WORKER restored\n");
+}
+
+static int __init wq_stall_init(void)
+{
+	pr_info("wq_stall: loading\n");
+
+	INIT_WORK(&stall_work1, stall_work1_fn);
+	INIT_WORK(&stall_work2, stall_work2_fn);
+	schedule_work(&stall_work1);
+
+	return 0;
+}
+
+static void __exit wq_stall_exit(void)
+{
+	pr_info("wq_stall: unloading\n");
+	atomic_set(&wake_condition, 1);
+	wake_up(&stall_wq_head);
+	flush_work(&stall_work1);
+	flush_work(&stall_work2);
+	pr_info("wq_stall: all work flushed, module unloaded\n");
+}
+
+module_init(wq_stall_init);
+module_exit(wq_stall_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Reproduce workqueue stall caused by PF_WQ_WORKER misuse");
+MODULE_AUTHOR("Breno Leitao <leitao@debian.org>");
-- 
cgit v1.2.3


From 9f2c7349b2810c671badfc1adc804f711a83e420 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 5 Mar 2026 09:18:52 -0800
Subject: MAINTAINERS: Orphan Altera PCIe controller driver

Email to Joyce Ooi <joyce.ooi@intel.com> now bounces.  Remove the address
and mark the Altera PCIe controller driver as an orphan for now.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260305171852.3114177-1-dave.hansen@linux.intel.com
---
 MAINTAINERS | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..02768d27802c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20122,9 +20122,8 @@ F:	Documentation/devicetree/bindings/pci/marvell,armada-3700-pcie.yaml
 F:	drivers/pci/controller/pci-aardvark.c
 
 PCI DRIVER FOR ALTERA PCIE IP
-M:	Joyce Ooi <joyce.ooi@intel.com>
 L:	linux-pci@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	Documentation/devicetree/bindings/pci/altr,pcie-root-port.yaml
 F:	drivers/pci/controller/pcie-altera.c
 
@@ -20369,9 +20368,8 @@ S:	Supported
 F:	Documentation/PCI/pci-error-recovery.rst
 
 PCI MSI DRIVER FOR ALTERA MSI IP
-M:	Joyce Ooi <joyce.ooi@intel.com>
 L:	linux-pci@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	Documentation/devicetree/bindings/interrupt-controller/altr,msi-controller.yaml
 F:	drivers/pci/controller/pcie-altera-msi.c
 
-- 
cgit v1.2.3


From 1e972ec76e10cf9cdacf1db2fbf69f7216903a86 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 4 Mar 2026 17:22:20 -0300
Subject: tools arch x86: Sync msr-index.h to pick
 MSR_{OMR_[0-3],CORE_PERF_GLOBAL_STATUS_SET}

To pick up the changes in:

  4e955c08d6dc76fb ("perf/x86/intel: Support the 4 new OMR MSRs introduced in DMR and NVL")
  736a2dcfdae72483 ("x86/CPU/AMD: Simplify the spectral chicken fix")
  56bb2736975068cc ("KVM: x86/pmu: Load/put mediated PMU context when entering/exiting guest")

Addressing this tools/perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

That makes the beautification scripts to pick some new entries:

  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before.txt
  $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
  $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after.txt
  $ diff -u before.txt after.txt
  --- before.txt	2026-03-04 17:21:39.165956041 -0300
  +++ after.txt	2026-03-04 17:21:52.479191640 -0300
  @@ -130,6 +130,11 @@
   	[0x0000038e] = "CORE_PERF_GLOBAL_STATUS",
   	[0x0000038f] = "CORE_PERF_GLOBAL_CTRL",
   	[0x00000390] = "CORE_PERF_GLOBAL_OVF_CTRL",
  +	[0x00000391] = "CORE_PERF_GLOBAL_STATUS_SET",
  +	[0x000003e0] = "OMR_0",
  +	[0x000003e1] = "OMR_1",
  +	[0x000003e2] = "OMR_2",
  +	[0x000003e3] = "OMR_3",
   	[0x000003f1] = "IA32_PEBS_ENABLE",
   	[0x000003f2] = "PEBS_DATA_CFG",
   	[0x000003f4] = "IA32_PEBS_BASE",
  $

Now one can use those strings in 'perf trace' to do filtering, e.g.:

  # perf trace -e msr:*_msr/max-stack=32/ --filter="msr==CORE_PERF_GLOBAL_STATUS_SET"

Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/msr-index.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 43adc38d31d5..da5275d8eda6 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -263,6 +263,11 @@
 #define MSR_SNOOP_RSP_0			0x00001328
 #define MSR_SNOOP_RSP_1			0x00001329
 
+#define MSR_OMR_0			0x000003e0
+#define MSR_OMR_1			0x000003e1
+#define MSR_OMR_2			0x000003e2
+#define MSR_OMR_3			0x000003e3
+
 #define MSR_LBR_SELECT			0x000001c8
 #define MSR_LBR_TOS			0x000001c9
 
@@ -1219,6 +1224,7 @@
 #define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+#define MSR_CORE_PERF_GLOBAL_STATUS_SET	0x00000391
 
 #define MSR_PERF_METRICS		0x00000329
 
-- 
cgit v1.2.3


From b3ce769203a99d6f3c6d6269ec09232a8c5da422 Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Wed, 4 Mar 2026 11:06:12 -0800
Subject: perf disasm: Fix off-by-one bug in outside check

If a branch target points to one past the end of a function, the branch
should be treated as a branch to another function.

This can happen e.g. with a tail call to a function that is laid out
immediately after the caller.

Fixes: 751b1783da784299 ("perf annotate: Mark jumps to outher functions with the call arrow")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Peter Collingbourne <pcc@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://linux-review.googlesource.com/id/Ide471112e82d68177e0faf08ca411d9fcf0a7bdf
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/disasm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index ddcc488f2e5f..9e0420e14be1 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -384,7 +384,7 @@ static int jump__parse(const struct arch *arch, struct ins_operands *ops, struct
 	start = map__unmap_ip(map, sym->start);
 	end = map__unmap_ip(map, sym->end);
 
-	ops->target.outside = target.addr < start || target.addr > end;
+	ops->target.outside = target.addr < start || target.addr >= end;
 
 	/*
 	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
-- 
cgit v1.2.3


From c9d77f0a0c78eacdf6bbac07c494205a2c3053b4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 5 Mar 2026 17:16:07 -0300
Subject: tools headers: Update the syscall tables and unistd.h, to support the
 new 'rseq_slice_yield' syscall

Picking up the changes from these csets:

  2153b2e8917b73e9 ("sparc: Add architecture support for clone3")
  99d2592023e5d0a3 ("rseq: Implement sys_rseq_slice_yield()")
  4ac286c4a8d904c8 ("s390/syscalls: Switch to generic system call table generation")

This makes 'perf trace' support it, now its possible, for instance, to
do:

  # perf trace -e rseq_slice_yield --max-stack=16

Here is an example with the 'sendmmsg' syscall:

  root@x1:~# perf trace -e sendmmsg --max-stack 16 --max-events=1
       0.000 ( 0.062 ms): dbus-broker/1012 sendmmsg(fd: 150, mmsg: 0x7ffef57cca50, vlen: 1, flags: DONTWAIT|NOSIGNAL) = 1
                                         syscall_exit_to_user_mode_prepare ([kernel.kallsyms])
                                         syscall_exit_to_user_mode_prepare ([kernel.kallsyms])
                                         syscall_exit_to_user_mode ([kernel.kallsyms])
                                         do_syscall_64 ([kernel.kallsyms])
                                         entry_SYSCALL_64 ([kernel.kallsyms])
                                         [0x117ce7] (/usr/lib64/libc.so.6 (deleted))
  root@x1:~#

To do a system wide tracing of the new 'rseq_slice_yield' syscall with a
backtrace of at most 16 entries.

This addresses these perf tools build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
    diff -u tools/scripts/syscall.tbl scripts/syscall.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
    diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl
    diff -u tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl
    diff -u tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl

Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ludwig Rydberg <ludwig.rydberg@gaisler.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/unistd.h            |   5 +-
 tools/perf/arch/arm/entry/syscalls/syscall.tbl     |   1 +
 .../perf/arch/mips/entry/syscalls/syscall_n64.tbl  |   1 +
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |   1 +
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    | 859 ++++++++++-----------
 tools/perf/arch/sh/entry/syscalls/syscall.tbl      |   1 +
 tools/perf/arch/sparc/entry/syscalls/syscall.tbl   |   3 +-
 tools/perf/arch/x86/entry/syscalls/syscall_32.tbl  |   1 +
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |   1 +
 tools/perf/arch/xtensa/entry/syscalls/syscall.tbl  |   1 +
 tools/scripts/syscall.tbl                          |   1 +
 11 files changed, 406 insertions(+), 469 deletions(-)

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 942370b3f5d2..a627acc8fb5f 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -860,8 +860,11 @@ __SYSCALL(__NR_file_setattr, sys_file_setattr)
 #define __NR_listns 470
 __SYSCALL(__NR_listns, sys_listns)
 
+#define __NR_rseq_slice_yield 471
+__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield)
+
 #undef __NR_syscalls
-#define __NR_syscalls 471
+#define __NR_syscalls 472
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index fd09afae72a2..94351e22bfcf 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -485,3 +485,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 9b92bddf06b5..630aab9e5425 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -385,3 +385,4 @@
 468	n64	file_getattr			sys_file_getattr
 469	n64	file_setattr			sys_file_setattr
 470	n64	listns				sys_listns
+471	n64	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index ec4458cdb97b..4fcc7c58a105 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -561,3 +561,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	nospu	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 5863787ab036..09a7ef04d979 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -3,473 +3,398 @@
 # System call table for s390
 #
 # Format:
+# <nr> <abi> <syscall> <entry>
 #
-# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
-#
-# where <abi> can be common, 64, or 32
+# <abi> is always common.
 
-1    common	exit			sys_exit			sys_exit
-2    common	fork			sys_fork			sys_fork
-3    common	read			sys_read			compat_sys_s390_read
-4    common	write			sys_write			compat_sys_s390_write
-5    common	open			sys_open			compat_sys_open
-6    common	close			sys_close			sys_close
-7    common	restart_syscall		sys_restart_syscall		sys_restart_syscall
-8    common	creat			sys_creat			sys_creat
-9    common	link			sys_link			sys_link
-10   common	unlink			sys_unlink			sys_unlink
-11   common	execve			sys_execve			compat_sys_execve
-12   common	chdir			sys_chdir			sys_chdir
-13   32		time			-				sys_time32
-14   common	mknod			sys_mknod			sys_mknod
-15   common	chmod			sys_chmod			sys_chmod
-16   32		lchown			-				sys_lchown16
-19   common	lseek			sys_lseek			compat_sys_lseek
-20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			sys_mount
-22   common	umount			sys_oldumount			sys_oldumount
-23   32		setuid			-				sys_setuid16
-24   32		getuid			-				sys_getuid16
-25   32		stime			-				sys_stime32
-26   common	ptrace			sys_ptrace			compat_sys_ptrace
-27   common	alarm			sys_alarm			sys_alarm
-29   common	pause			sys_pause			sys_pause
-30   common	utime			sys_utime			sys_utime32
-33   common	access			sys_access			sys_access
-34   common	nice			sys_nice			sys_nice
-36   common	sync			sys_sync			sys_sync
-37   common	kill			sys_kill			sys_kill
-38   common	rename			sys_rename			sys_rename
-39   common	mkdir			sys_mkdir			sys_mkdir
-40   common	rmdir			sys_rmdir			sys_rmdir
-41   common	dup			sys_dup				sys_dup
-42   common	pipe			sys_pipe			sys_pipe
-43   common	times			sys_times			compat_sys_times
-45   common	brk			sys_brk				sys_brk
-46   32		setgid			-				sys_setgid16
-47   32		getgid			-				sys_getgid16
-48   common	signal			sys_signal			sys_signal
-49   32		geteuid			-				sys_geteuid16
-50   32		getegid			-				sys_getegid16
-51   common	acct			sys_acct			sys_acct
-52   common	umount2			sys_umount			sys_umount
-54   common	ioctl			sys_ioctl			compat_sys_ioctl
-55   common	fcntl			sys_fcntl			compat_sys_fcntl
-57   common	setpgid			sys_setpgid			sys_setpgid
-60   common	umask			sys_umask			sys_umask
-61   common	chroot			sys_chroot			sys_chroot
-62   common	ustat			sys_ustat			compat_sys_ustat
-63   common	dup2			sys_dup2			sys_dup2
-64   common	getppid			sys_getppid			sys_getppid
-65   common	getpgrp			sys_getpgrp			sys_getpgrp
-66   common	setsid			sys_setsid			sys_setsid
-67   common	sigaction		sys_sigaction			compat_sys_sigaction
-70   32		setreuid		-				sys_setreuid16
-71   32		setregid		-				sys_setregid16
-72   common	sigsuspend		sys_sigsuspend			sys_sigsuspend
-73   common	sigpending		sys_sigpending			compat_sys_sigpending
-74   common	sethostname		sys_sethostname			sys_sethostname
-75   common	setrlimit		sys_setrlimit			compat_sys_setrlimit
-76   32		getrlimit		-				compat_sys_old_getrlimit
-77   common	getrusage		sys_getrusage			compat_sys_getrusage
-78   common	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
-79   common	settimeofday		sys_settimeofday		compat_sys_settimeofday
-80   32		getgroups		-				sys_getgroups16
-81   32		setgroups		-				sys_setgroups16
-83   common	symlink			sys_symlink			sys_symlink
-85   common	readlink		sys_readlink			sys_readlink
-86   common	uselib			sys_uselib			sys_uselib
-87   common	swapon			sys_swapon			sys_swapon
-88   common	reboot			sys_reboot			sys_reboot
-89   common	readdir			-				compat_sys_old_readdir
-90   common	mmap			sys_old_mmap			compat_sys_s390_old_mmap
-91   common	munmap			sys_munmap			sys_munmap
-92   common	truncate		sys_truncate			compat_sys_truncate
-93   common	ftruncate		sys_ftruncate			compat_sys_ftruncate
-94   common	fchmod			sys_fchmod			sys_fchmod
-95   32		fchown			-				sys_fchown16
-96   common	getpriority		sys_getpriority			sys_getpriority
-97   common	setpriority		sys_setpriority			sys_setpriority
-99   common	statfs			sys_statfs			compat_sys_statfs
-100  common	fstatfs			sys_fstatfs			compat_sys_fstatfs
-101  32		ioperm			-				-
-102  common	socketcall		sys_socketcall			compat_sys_socketcall
-103  common	syslog			sys_syslog			sys_syslog
-104  common	setitimer		sys_setitimer			compat_sys_setitimer
-105  common	getitimer		sys_getitimer			compat_sys_getitimer
-106  common	stat			sys_newstat			compat_sys_newstat
-107  common	lstat			sys_newlstat			compat_sys_newlstat
-108  common	fstat			sys_newfstat			compat_sys_newfstat
-110  common	lookup_dcookie		-				-
-111  common	vhangup			sys_vhangup			sys_vhangup
-112  common	idle			-				-
-114  common	wait4			sys_wait4			compat_sys_wait4
-115  common	swapoff			sys_swapoff			sys_swapoff
-116  common	sysinfo			sys_sysinfo			compat_sys_sysinfo
-117  common	ipc			sys_s390_ipc			compat_sys_s390_ipc
-118  common	fsync			sys_fsync			sys_fsync
-119  common	sigreturn		sys_sigreturn			compat_sys_sigreturn
-120  common	clone			sys_clone			sys_clone
-121  common	setdomainname		sys_setdomainname		sys_setdomainname
-122  common	uname			sys_newuname			sys_newuname
-124  common	adjtimex		sys_adjtimex			sys_adjtimex_time32
-125  common	mprotect		sys_mprotect			sys_mprotect
-126  common	sigprocmask		sys_sigprocmask			compat_sys_sigprocmask
-127  common	create_module		-				-
-128  common	init_module		sys_init_module			sys_init_module
-129  common	delete_module		sys_delete_module		sys_delete_module
-130  common	get_kernel_syms		-				-
-131  common	quotactl		sys_quotactl			sys_quotactl
-132  common	getpgid			sys_getpgid			sys_getpgid
-133  common	fchdir			sys_fchdir			sys_fchdir
-134  common	bdflush			sys_ni_syscall			sys_ni_syscall
-135  common	sysfs			sys_sysfs			sys_sysfs
-136  common	personality		sys_s390_personality		sys_s390_personality
-137  common	afs_syscall		-				-
-138  32		setfsuid		-				sys_setfsuid16
-139  32		setfsgid		-				sys_setfsgid16
-140  32		_llseek			-				sys_llseek
-141  common	getdents		sys_getdents			compat_sys_getdents
-142  32		_newselect		-				compat_sys_select
-142  64		select			sys_select			-
-143  common	flock			sys_flock			sys_flock
-144  common	msync			sys_msync			sys_msync
-145  common	readv			sys_readv			sys_readv
-146  common	writev			sys_writev			sys_writev
-147  common	getsid			sys_getsid			sys_getsid
-148  common	fdatasync		sys_fdatasync			sys_fdatasync
-149  common	_sysctl			-				-
-150  common	mlock			sys_mlock			sys_mlock
-151  common	munlock			sys_munlock			sys_munlock
-152  common	mlockall		sys_mlockall			sys_mlockall
-153  common	munlockall		sys_munlockall			sys_munlockall
-154  common	sched_setparam		sys_sched_setparam		sys_sched_setparam
-155  common	sched_getparam		sys_sched_getparam		sys_sched_getparam
-156  common	sched_setscheduler	sys_sched_setscheduler		sys_sched_setscheduler
-157  common	sched_getscheduler	sys_sched_getscheduler		sys_sched_getscheduler
-158  common	sched_yield		sys_sched_yield			sys_sched_yield
-159  common	sched_get_priority_max	sys_sched_get_priority_max	sys_sched_get_priority_max
-160  common	sched_get_priority_min	sys_sched_get_priority_min	sys_sched_get_priority_min
-161  common	sched_rr_get_interval	sys_sched_rr_get_interval	sys_sched_rr_get_interval_time32
-162  common	nanosleep		sys_nanosleep			sys_nanosleep_time32
-163  common	mremap			sys_mremap			sys_mremap
-164  32		setresuid		-				sys_setresuid16
-165  32		getresuid		-				sys_getresuid16
-167  common	query_module		-				-
-168  common	poll			sys_poll			sys_poll
-169  common	nfsservctl		-				-
-170  32		setresgid		-				sys_setresgid16
-171  32		getresgid		-				sys_getresgid16
-172  common	prctl			sys_prctl			sys_prctl
-173  common	rt_sigreturn		sys_rt_sigreturn		compat_sys_rt_sigreturn
-174  common	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
-175  common	rt_sigprocmask		sys_rt_sigprocmask		compat_sys_rt_sigprocmask
-176  common	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
-177  common	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time32
-178  common	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
-179  common	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
-180  common	pread64			sys_pread64			compat_sys_s390_pread64
-181  common	pwrite64		sys_pwrite64			compat_sys_s390_pwrite64
-182  32		chown			-				sys_chown16
-183  common	getcwd			sys_getcwd			sys_getcwd
-184  common	capget			sys_capget			sys_capget
-185  common	capset			sys_capset			sys_capset
-186  common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
-187  common	sendfile		sys_sendfile64			compat_sys_sendfile
-188  common	getpmsg			-				-
-189  common	putpmsg			-				-
-190  common	vfork			sys_vfork			sys_vfork
-191  32		ugetrlimit		-				compat_sys_getrlimit
-191  64		getrlimit		sys_getrlimit			-
-192  32		mmap2			-				compat_sys_s390_mmap2
-193  32		truncate64		-				compat_sys_s390_truncate64
-194  32		ftruncate64		-				compat_sys_s390_ftruncate64
-195  32		stat64			-				compat_sys_s390_stat64
-196  32		lstat64			-				compat_sys_s390_lstat64
-197  32		fstat64			-				compat_sys_s390_fstat64
-198  32		lchown32		-				sys_lchown
-198  64		lchown			sys_lchown			-
-199  32		getuid32		-				sys_getuid
-199  64		getuid			sys_getuid			-
-200  32		getgid32		-				sys_getgid
-200  64		getgid			sys_getgid			-
-201  32		geteuid32		-				sys_geteuid
-201  64		geteuid			sys_geteuid			-
-202  32		getegid32		-				sys_getegid
-202  64		getegid			sys_getegid			-
-203  32		setreuid32		-				sys_setreuid
-203  64		setreuid		sys_setreuid			-
-204  32		setregid32		-				sys_setregid
-204  64		setregid		sys_setregid			-
-205  32		getgroups32		-				sys_getgroups
-205  64		getgroups		sys_getgroups			-
-206  32		setgroups32		-				sys_setgroups
-206  64		setgroups		sys_setgroups			-
-207  32		fchown32		-				sys_fchown
-207  64		fchown			sys_fchown			-
-208  32		setresuid32		-				sys_setresuid
-208  64		setresuid		sys_setresuid			-
-209  32		getresuid32		-				sys_getresuid
-209  64		getresuid		sys_getresuid			-
-210  32		setresgid32		-				sys_setresgid
-210  64		setresgid		sys_setresgid			-
-211  32		getresgid32		-				sys_getresgid
-211  64		getresgid		sys_getresgid			-
-212  32		chown32			-				sys_chown
-212  64		chown			sys_chown			-
-213  32		setuid32		-				sys_setuid
-213  64		setuid			sys_setuid			-
-214  32		setgid32		-				sys_setgid
-214  64		setgid			sys_setgid			-
-215  32		setfsuid32		-				sys_setfsuid
-215  64		setfsuid		sys_setfsuid			-
-216  32		setfsgid32		-				sys_setfsgid
-216  64		setfsgid		sys_setfsgid			-
-217  common	pivot_root		sys_pivot_root			sys_pivot_root
-218  common	mincore			sys_mincore			sys_mincore
-219  common	madvise			sys_madvise			sys_madvise
-220  common	getdents64		sys_getdents64			sys_getdents64
-221  32		fcntl64			-				compat_sys_fcntl64
-222  common	readahead		sys_readahead			compat_sys_s390_readahead
-223  32		sendfile64		-				compat_sys_sendfile64
-224  common	setxattr		sys_setxattr			sys_setxattr
-225  common	lsetxattr		sys_lsetxattr			sys_lsetxattr
-226  common	fsetxattr		sys_fsetxattr			sys_fsetxattr
-227  common	getxattr		sys_getxattr			sys_getxattr
-228  common	lgetxattr		sys_lgetxattr			sys_lgetxattr
-229  common	fgetxattr		sys_fgetxattr			sys_fgetxattr
-230  common	listxattr		sys_listxattr			sys_listxattr
-231  common	llistxattr		sys_llistxattr			sys_llistxattr
-232  common	flistxattr		sys_flistxattr			sys_flistxattr
-233  common	removexattr		sys_removexattr			sys_removexattr
-234  common	lremovexattr		sys_lremovexattr		sys_lremovexattr
-235  common	fremovexattr		sys_fremovexattr		sys_fremovexattr
-236  common	gettid			sys_gettid			sys_gettid
-237  common	tkill			sys_tkill			sys_tkill
-238  common	futex			sys_futex			sys_futex_time32
-239  common	sched_setaffinity	sys_sched_setaffinity		compat_sys_sched_setaffinity
-240  common	sched_getaffinity	sys_sched_getaffinity		compat_sys_sched_getaffinity
-241  common	tgkill			sys_tgkill			sys_tgkill
-243  common	io_setup		sys_io_setup			compat_sys_io_setup
-244  common	io_destroy		sys_io_destroy			sys_io_destroy
-245  common	io_getevents		sys_io_getevents		sys_io_getevents_time32
-246  common	io_submit		sys_io_submit			compat_sys_io_submit
-247  common	io_cancel		sys_io_cancel			sys_io_cancel
-248  common	exit_group		sys_exit_group			sys_exit_group
-249  common	epoll_create		sys_epoll_create		sys_epoll_create
-250  common	epoll_ctl		sys_epoll_ctl			sys_epoll_ctl
-251  common	epoll_wait		sys_epoll_wait			sys_epoll_wait
-252  common	set_tid_address		sys_set_tid_address		sys_set_tid_address
-253  common	fadvise64		sys_fadvise64_64		compat_sys_s390_fadvise64
-254  common	timer_create		sys_timer_create		compat_sys_timer_create
-255  common	timer_settime		sys_timer_settime		sys_timer_settime32
-256  common	timer_gettime		sys_timer_gettime		sys_timer_gettime32
-257  common	timer_getoverrun	sys_timer_getoverrun		sys_timer_getoverrun
-258  common	timer_delete		sys_timer_delete		sys_timer_delete
-259  common	clock_settime		sys_clock_settime		sys_clock_settime32
-260  common	clock_gettime		sys_clock_gettime		sys_clock_gettime32
-261  common	clock_getres		sys_clock_getres		sys_clock_getres_time32
-262  common	clock_nanosleep		sys_clock_nanosleep		sys_clock_nanosleep_time32
-264  32		fadvise64_64		-				compat_sys_s390_fadvise64_64
-265  common	statfs64		sys_statfs64			compat_sys_statfs64
-266  common	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
-267  common	remap_file_pages	sys_remap_file_pages		sys_remap_file_pages
-268  common	mbind			sys_mbind			sys_mbind
-269  common	get_mempolicy		sys_get_mempolicy		sys_get_mempolicy
-270  common	set_mempolicy		sys_set_mempolicy		sys_set_mempolicy
-271  common	mq_open			sys_mq_open			compat_sys_mq_open
-272  common	mq_unlink		sys_mq_unlink			sys_mq_unlink
-273  common	mq_timedsend		sys_mq_timedsend		sys_mq_timedsend_time32
-274  common	mq_timedreceive		sys_mq_timedreceive		sys_mq_timedreceive_time32
-275  common	mq_notify		sys_mq_notify			compat_sys_mq_notify
-276  common	mq_getsetattr		sys_mq_getsetattr		compat_sys_mq_getsetattr
-277  common	kexec_load		sys_kexec_load			compat_sys_kexec_load
-278  common	add_key			sys_add_key			sys_add_key
-279  common	request_key		sys_request_key			sys_request_key
-280  common	keyctl			sys_keyctl			compat_sys_keyctl
-281  common	waitid			sys_waitid			compat_sys_waitid
-282  common	ioprio_set		sys_ioprio_set			sys_ioprio_set
-283  common	ioprio_get		sys_ioprio_get			sys_ioprio_get
-284  common	inotify_init		sys_inotify_init		sys_inotify_init
-285  common	inotify_add_watch	sys_inotify_add_watch		sys_inotify_add_watch
-286  common	inotify_rm_watch	sys_inotify_rm_watch		sys_inotify_rm_watch
-287  common	migrate_pages		sys_migrate_pages		sys_migrate_pages
-288  common	openat			sys_openat			compat_sys_openat
-289  common	mkdirat			sys_mkdirat			sys_mkdirat
-290  common	mknodat			sys_mknodat			sys_mknodat
-291  common	fchownat		sys_fchownat			sys_fchownat
-292  common	futimesat		sys_futimesat			sys_futimesat_time32
-293  32		fstatat64		-				compat_sys_s390_fstatat64
-293  64		newfstatat		sys_newfstatat			-
-294  common	unlinkat		sys_unlinkat			sys_unlinkat
-295  common	renameat		sys_renameat			sys_renameat
-296  common	linkat			sys_linkat			sys_linkat
-297  common	symlinkat		sys_symlinkat			sys_symlinkat
-298  common	readlinkat		sys_readlinkat			sys_readlinkat
-299  common	fchmodat		sys_fchmodat			sys_fchmodat
-300  common	faccessat		sys_faccessat			sys_faccessat
-301  common	pselect6		sys_pselect6			compat_sys_pselect6_time32
-302  common	ppoll			sys_ppoll			compat_sys_ppoll_time32
-303  common	unshare			sys_unshare			sys_unshare
-304  common	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
-305  common	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
-306  common	splice			sys_splice			sys_splice
-307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
-308  common	tee			sys_tee				sys_tee
-309  common	vmsplice		sys_vmsplice			sys_vmsplice
-310  common	move_pages		sys_move_pages			sys_move_pages
-311  common	getcpu			sys_getcpu			sys_getcpu
-312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
-313  common	utimes			sys_utimes			sys_utimes_time32
-314  common	fallocate		sys_fallocate			compat_sys_s390_fallocate
-315  common	utimensat		sys_utimensat			sys_utimensat_time32
-316  common	signalfd		sys_signalfd			compat_sys_signalfd
-317  common	timerfd			-				-
-318  common	eventfd			sys_eventfd			sys_eventfd
-319  common	timerfd_create		sys_timerfd_create		sys_timerfd_create
-320  common	timerfd_settime		sys_timerfd_settime		sys_timerfd_settime32
-321  common	timerfd_gettime		sys_timerfd_gettime		sys_timerfd_gettime32
-322  common	signalfd4		sys_signalfd4			compat_sys_signalfd4
-323  common	eventfd2		sys_eventfd2			sys_eventfd2
-324  common	inotify_init1		sys_inotify_init1		sys_inotify_init1
-325  common	pipe2			sys_pipe2			sys_pipe2
-326  common	dup3			sys_dup3			sys_dup3
-327  common	epoll_create1		sys_epoll_create1		sys_epoll_create1
-328  common	preadv			sys_preadv			compat_sys_preadv
-329  common	pwritev			sys_pwritev			compat_sys_pwritev
-330  common	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
-331  common	perf_event_open		sys_perf_event_open		sys_perf_event_open
-332  common	fanotify_init		sys_fanotify_init		sys_fanotify_init
-333  common	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
-334  common	prlimit64		sys_prlimit64			sys_prlimit64
-335  common	name_to_handle_at	sys_name_to_handle_at		sys_name_to_handle_at
-336  common	open_by_handle_at	sys_open_by_handle_at		compat_sys_open_by_handle_at
-337  common	clock_adjtime		sys_clock_adjtime		sys_clock_adjtime32
-338  common	syncfs			sys_syncfs			sys_syncfs
-339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
-342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
-343  common	kcmp			sys_kcmp			sys_kcmp
-344  common	finit_module		sys_finit_module		sys_finit_module
-345  common	sched_setattr		sys_sched_setattr		sys_sched_setattr
-346  common	sched_getattr		sys_sched_getattr		sys_sched_getattr
-347  common	renameat2		sys_renameat2			sys_renameat2
-348  common	seccomp			sys_seccomp			sys_seccomp
-349  common	getrandom		sys_getrandom			sys_getrandom
-350  common	memfd_create		sys_memfd_create		sys_memfd_create
-351  common	bpf			sys_bpf				sys_bpf
-352  common	s390_pci_mmio_write	sys_s390_pci_mmio_write		sys_s390_pci_mmio_write
-353  common	s390_pci_mmio_read	sys_s390_pci_mmio_read		sys_s390_pci_mmio_read
-354  common	execveat		sys_execveat			compat_sys_execveat
-355  common	userfaultfd		sys_userfaultfd			sys_userfaultfd
-356  common	membarrier		sys_membarrier			sys_membarrier
-357  common	recvmmsg		sys_recvmmsg			compat_sys_recvmmsg_time32
-358  common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
-359  common	socket			sys_socket			sys_socket
-360  common	socketpair		sys_socketpair			sys_socketpair
-361  common	bind			sys_bind			sys_bind
-362  common	connect			sys_connect			sys_connect
-363  common	listen			sys_listen			sys_listen
-364  common	accept4			sys_accept4			sys_accept4
-365  common	getsockopt		sys_getsockopt			sys_getsockopt
-366  common	setsockopt		sys_setsockopt			sys_setsockopt
-367  common	getsockname		sys_getsockname			sys_getsockname
-368  common	getpeername		sys_getpeername			sys_getpeername
-369  common	sendto			sys_sendto			sys_sendto
-370  common	sendmsg			sys_sendmsg			compat_sys_sendmsg
-371  common	recvfrom		sys_recvfrom			compat_sys_recvfrom
-372  common	recvmsg			sys_recvmsg			compat_sys_recvmsg
-373  common	shutdown		sys_shutdown			sys_shutdown
-374  common	mlock2			sys_mlock2			sys_mlock2
-375  common	copy_file_range		sys_copy_file_range		sys_copy_file_range
-376  common	preadv2			sys_preadv2			compat_sys_preadv2
-377  common	pwritev2		sys_pwritev2			compat_sys_pwritev2
-378  common	s390_guarded_storage	sys_s390_guarded_storage	sys_s390_guarded_storage
-379  common	statx			sys_statx			sys_statx
-380  common	s390_sthyi		sys_s390_sthyi			sys_s390_sthyi
-381  common	kexec_file_load		sys_kexec_file_load		sys_kexec_file_load
-382  common	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
-383  common	rseq			sys_rseq			sys_rseq
-384  common	pkey_mprotect		sys_pkey_mprotect		sys_pkey_mprotect
-385  common	pkey_alloc		sys_pkey_alloc			sys_pkey_alloc
-386  common	pkey_free		sys_pkey_free			sys_pkey_free
+1	common	exit				sys_exit
+2	common	fork				sys_fork
+3	common	read				sys_read
+4	common	write				sys_write
+5	common	open				sys_open
+6	common	close				sys_close
+7	common	restart_syscall			sys_restart_syscall
+8	common	creat				sys_creat
+9	common	link				sys_link
+10	common	unlink				sys_unlink
+11	common	execve				sys_execve
+12	common	chdir				sys_chdir
+14	common	mknod				sys_mknod
+15	common	chmod				sys_chmod
+19	common	lseek				sys_lseek
+20	common	getpid				sys_getpid
+21	common	mount				sys_mount
+22	common	umount				sys_oldumount
+26	common	ptrace				sys_ptrace
+27	common	alarm				sys_alarm
+29	common	pause				sys_pause
+30	common	utime				sys_utime
+33	common	access				sys_access
+34	common	nice				sys_nice
+36	common	sync				sys_sync
+37	common	kill				sys_kill
+38	common	rename				sys_rename
+39	common	mkdir				sys_mkdir
+40	common	rmdir				sys_rmdir
+41	common	dup				sys_dup
+42	common	pipe				sys_pipe
+43	common	times				sys_times
+45	common	brk				sys_brk
+48	common	signal				sys_signal
+51	common	acct				sys_acct
+52	common	umount2				sys_umount
+54	common	ioctl				sys_ioctl
+55	common	fcntl				sys_fcntl
+57	common	setpgid				sys_setpgid
+60	common	umask				sys_umask
+61	common	chroot				sys_chroot
+62	common	ustat				sys_ustat
+63	common	dup2				sys_dup2
+64	common	getppid				sys_getppid
+65	common	getpgrp				sys_getpgrp
+66	common	setsid				sys_setsid
+67	common	sigaction			sys_sigaction
+72	common	sigsuspend			sys_sigsuspend
+73	common	sigpending			sys_sigpending
+74	common	sethostname			sys_sethostname
+75	common	setrlimit			sys_setrlimit
+77	common	getrusage			sys_getrusage
+78	common	gettimeofday			sys_gettimeofday
+79	common	settimeofday			sys_settimeofday
+83	common	symlink				sys_symlink
+85	common	readlink			sys_readlink
+86	common	uselib				sys_uselib
+87	common	swapon				sys_swapon
+88	common	reboot				sys_reboot
+89	common	readdir				sys_ni_syscall
+90	common	mmap				sys_old_mmap
+91	common	munmap				sys_munmap
+92	common	truncate			sys_truncate
+93	common	ftruncate			sys_ftruncate
+94	common	fchmod				sys_fchmod
+96	common	getpriority			sys_getpriority
+97	common	setpriority			sys_setpriority
+99	common	statfs				sys_statfs
+100	common	fstatfs				sys_fstatfs
+102	common	socketcall			sys_socketcall
+103	common	syslog				sys_syslog
+104	common	setitimer			sys_setitimer
+105	common	getitimer			sys_getitimer
+106	common	stat				sys_newstat
+107	common	lstat				sys_newlstat
+108	common	fstat				sys_newfstat
+110	common	lookup_dcookie			sys_ni_syscall
+111	common	vhangup				sys_vhangup
+112	common	idle				sys_ni_syscall
+114	common	wait4				sys_wait4
+115	common	swapoff				sys_swapoff
+116	common	sysinfo				sys_sysinfo
+117	common	ipc				sys_s390_ipc
+118	common	fsync				sys_fsync
+119	common	sigreturn			sys_sigreturn
+120	common	clone				sys_clone
+121	common	setdomainname			sys_setdomainname
+122	common	uname				sys_newuname
+124	common	adjtimex			sys_adjtimex
+125	common	mprotect			sys_mprotect
+126	common	sigprocmask			sys_sigprocmask
+127	common	create_module			sys_ni_syscall
+128	common	init_module			sys_init_module
+129	common	delete_module			sys_delete_module
+130	common	get_kernel_syms			sys_ni_syscall
+131	common	quotactl			sys_quotactl
+132	common	getpgid				sys_getpgid
+133	common	fchdir				sys_fchdir
+134	common	bdflush				sys_ni_syscall
+135	common	sysfs				sys_sysfs
+136	common	personality			sys_s390_personality
+137	common	afs_syscall			sys_ni_syscall
+141	common	getdents			sys_getdents
+142	common	select				sys_select
+143	common	flock				sys_flock
+144	common	msync				sys_msync
+145	common	readv				sys_readv
+146	common	writev				sys_writev
+147	common	getsid				sys_getsid
+148	common	fdatasync			sys_fdatasync
+149	common	_sysctl				sys_ni_syscall
+150	common	mlock				sys_mlock
+151	common	munlock				sys_munlock
+152	common	mlockall			sys_mlockall
+153	common	munlockall			sys_munlockall
+154	common	sched_setparam			sys_sched_setparam
+155	common	sched_getparam			sys_sched_getparam
+156	common	sched_setscheduler		sys_sched_setscheduler
+157	common	sched_getscheduler		sys_sched_getscheduler
+158	common	sched_yield			sys_sched_yield
+159	common	sched_get_priority_max		sys_sched_get_priority_max
+160	common	sched_get_priority_min		sys_sched_get_priority_min
+161	common	sched_rr_get_interval		sys_sched_rr_get_interval
+162	common	nanosleep			sys_nanosleep
+163	common	mremap				sys_mremap
+167	common	query_module			sys_ni_syscall
+168	common	poll				sys_poll
+169	common	nfsservctl			sys_ni_syscall
+172	common	prctl				sys_prctl
+173	common	rt_sigreturn			sys_rt_sigreturn
+174	common	rt_sigaction			sys_rt_sigaction
+175	common	rt_sigprocmask			sys_rt_sigprocmask
+176	common	rt_sigpending			sys_rt_sigpending
+177	common	rt_sigtimedwait			sys_rt_sigtimedwait
+178	common	rt_sigqueueinfo			sys_rt_sigqueueinfo
+179	common	rt_sigsuspend			sys_rt_sigsuspend
+180	common	pread64				sys_pread64
+181	common	pwrite64			sys_pwrite64
+183	common	getcwd				sys_getcwd
+184	common	capget				sys_capget
+185	common	capset				sys_capset
+186	common	sigaltstack			sys_sigaltstack
+187	common	sendfile			sys_sendfile64
+188	common	getpmsg				sys_ni_syscall
+189	common	putpmsg				sys_ni_syscall
+190	common	vfork				sys_vfork
+191	common	getrlimit			sys_getrlimit
+198	common	lchown				sys_lchown
+199	common	getuid				sys_getuid
+200	common	getgid				sys_getgid
+201	common	geteuid				sys_geteuid
+202	common	getegid				sys_getegid
+203	common	setreuid			sys_setreuid
+204	common	setregid			sys_setregid
+205	common	getgroups			sys_getgroups
+206	common	setgroups			sys_setgroups
+207	common	fchown				sys_fchown
+208	common	setresuid			sys_setresuid
+209	common	getresuid			sys_getresuid
+210	common	setresgid			sys_setresgid
+211	common	getresgid			sys_getresgid
+212	common	chown				sys_chown
+213	common	setuid				sys_setuid
+214	common	setgid				sys_setgid
+215	common	setfsuid			sys_setfsuid
+216	common	setfsgid			sys_setfsgid
+217	common	pivot_root			sys_pivot_root
+218	common	mincore				sys_mincore
+219	common	madvise				sys_madvise
+220	common	getdents64			sys_getdents64
+222	common	readahead			sys_readahead
+224	common	setxattr			sys_setxattr
+225	common	lsetxattr			sys_lsetxattr
+226	common	fsetxattr			sys_fsetxattr
+227	common	getxattr			sys_getxattr
+228	common	lgetxattr			sys_lgetxattr
+229	common	fgetxattr			sys_fgetxattr
+230	common	listxattr			sys_listxattr
+231	common	llistxattr			sys_llistxattr
+232	common	flistxattr			sys_flistxattr
+233	common	removexattr			sys_removexattr
+234	common	lremovexattr			sys_lremovexattr
+235	common	fremovexattr			sys_fremovexattr
+236	common	gettid				sys_gettid
+237	common	tkill				sys_tkill
+238	common	futex				sys_futex
+239	common	sched_setaffinity		sys_sched_setaffinity
+240	common	sched_getaffinity		sys_sched_getaffinity
+241	common	tgkill				sys_tgkill
+243	common	io_setup			sys_io_setup
+244	common	io_destroy			sys_io_destroy
+245	common	io_getevents			sys_io_getevents
+246	common	io_submit			sys_io_submit
+247	common	io_cancel			sys_io_cancel
+248	common	exit_group			sys_exit_group
+249	common	epoll_create			sys_epoll_create
+250	common	epoll_ctl			sys_epoll_ctl
+251	common	epoll_wait			sys_epoll_wait
+252	common	set_tid_address			sys_set_tid_address
+253	common	fadvise64			sys_fadvise64_64
+254	common	timer_create			sys_timer_create
+255	common	timer_settime			sys_timer_settime
+256	common	timer_gettime			sys_timer_gettime
+257	common	timer_getoverrun		sys_timer_getoverrun
+258	common	timer_delete			sys_timer_delete
+259	common	clock_settime			sys_clock_settime
+260	common	clock_gettime			sys_clock_gettime
+261	common	clock_getres			sys_clock_getres
+262	common	clock_nanosleep			sys_clock_nanosleep
+265	common	statfs64			sys_statfs64
+266	common	fstatfs64			sys_fstatfs64
+267	common	remap_file_pages		sys_remap_file_pages
+268	common	mbind				sys_mbind
+269	common	get_mempolicy			sys_get_mempolicy
+270	common	set_mempolicy			sys_set_mempolicy
+271	common	mq_open				sys_mq_open
+272	common	mq_unlink			sys_mq_unlink
+273	common	mq_timedsend			sys_mq_timedsend
+274	common	mq_timedreceive			sys_mq_timedreceive
+275	common	mq_notify			sys_mq_notify
+276	common	mq_getsetattr			sys_mq_getsetattr
+277	common	kexec_load			sys_kexec_load
+278	common	add_key				sys_add_key
+279	common	request_key			sys_request_key
+280	common	keyctl				sys_keyctl
+281	common	waitid				sys_waitid
+282	common	ioprio_set			sys_ioprio_set
+283	common	ioprio_get			sys_ioprio_get
+284	common	inotify_init			sys_inotify_init
+285	common	inotify_add_watch		sys_inotify_add_watch
+286	common	inotify_rm_watch		sys_inotify_rm_watch
+287	common	migrate_pages			sys_migrate_pages
+288	common	openat				sys_openat
+289	common	mkdirat				sys_mkdirat
+290	common	mknodat				sys_mknodat
+291	common	fchownat			sys_fchownat
+292	common	futimesat			sys_futimesat
+293	common	newfstatat			sys_newfstatat
+294	common	unlinkat			sys_unlinkat
+295	common	renameat			sys_renameat
+296	common	linkat				sys_linkat
+297	common	symlinkat			sys_symlinkat
+298	common	readlinkat			sys_readlinkat
+299	common	fchmodat			sys_fchmodat
+300	common	faccessat			sys_faccessat
+301	common	pselect6			sys_pselect6
+302	common	ppoll				sys_ppoll
+303	common	unshare				sys_unshare
+304	common	set_robust_list			sys_set_robust_list
+305	common	get_robust_list			sys_get_robust_list
+306	common	splice				sys_splice
+307	common	sync_file_range			sys_sync_file_range
+308	common	tee				sys_tee
+309	common	vmsplice			sys_vmsplice
+310	common	move_pages			sys_move_pages
+311	common	getcpu				sys_getcpu
+312	common	epoll_pwait			sys_epoll_pwait
+313	common	utimes				sys_utimes
+314	common	fallocate			sys_fallocate
+315	common	utimensat			sys_utimensat
+316	common	signalfd			sys_signalfd
+317	common	timerfd				sys_ni_syscall
+318	common	eventfd				sys_eventfd
+319	common	timerfd_create			sys_timerfd_create
+320	common	timerfd_settime			sys_timerfd_settime
+321	common	timerfd_gettime			sys_timerfd_gettime
+322	common	signalfd4			sys_signalfd4
+323	common	eventfd2			sys_eventfd2
+324	common	inotify_init1			sys_inotify_init1
+325	common	pipe2				sys_pipe2
+326	common	dup3				sys_dup3
+327	common	epoll_create1			sys_epoll_create1
+328	common	preadv				sys_preadv
+329	common	pwritev				sys_pwritev
+330	common	rt_tgsigqueueinfo		sys_rt_tgsigqueueinfo
+331	common	perf_event_open			sys_perf_event_open
+332	common	fanotify_init			sys_fanotify_init
+333	common	fanotify_mark			sys_fanotify_mark
+334	common	prlimit64			sys_prlimit64
+335	common	name_to_handle_at		sys_name_to_handle_at
+336	common	open_by_handle_at		sys_open_by_handle_at
+337	common	clock_adjtime			sys_clock_adjtime
+338	common	syncfs				sys_syncfs
+339	common	setns				sys_setns
+340	common	process_vm_readv		sys_process_vm_readv
+341	common	process_vm_writev		sys_process_vm_writev
+342	common	s390_runtime_instr		sys_s390_runtime_instr
+343	common	kcmp				sys_kcmp
+344	common	finit_module			sys_finit_module
+345	common	sched_setattr			sys_sched_setattr
+346	common	sched_getattr			sys_sched_getattr
+347	common	renameat2			sys_renameat2
+348	common	seccomp				sys_seccomp
+349	common	getrandom			sys_getrandom
+350	common	memfd_create			sys_memfd_create
+351	common	bpf				sys_bpf
+352	common	s390_pci_mmio_write		sys_s390_pci_mmio_write
+353	common	s390_pci_mmio_read		sys_s390_pci_mmio_read
+354	common	execveat			sys_execveat
+355	common	userfaultfd			sys_userfaultfd
+356	common	membarrier			sys_membarrier
+357	common	recvmmsg			sys_recvmmsg
+358	common	sendmmsg			sys_sendmmsg
+359	common	socket				sys_socket
+360	common	socketpair			sys_socketpair
+361	common	bind				sys_bind
+362	common	connect				sys_connect
+363	common	listen				sys_listen
+364	common	accept4				sys_accept4
+365	common	getsockopt			sys_getsockopt
+366	common	setsockopt			sys_setsockopt
+367	common	getsockname			sys_getsockname
+368	common	getpeername			sys_getpeername
+369	common	sendto				sys_sendto
+370	common	sendmsg				sys_sendmsg
+371	common	recvfrom			sys_recvfrom
+372	common	recvmsg				sys_recvmsg
+373	common	shutdown			sys_shutdown
+374	common	mlock2				sys_mlock2
+375	common	copy_file_range			sys_copy_file_range
+376	common	preadv2				sys_preadv2
+377	common	pwritev2			sys_pwritev2
+378	common	s390_guarded_storage		sys_s390_guarded_storage
+379	common	statx				sys_statx
+380	common	s390_sthyi			sys_s390_sthyi
+381	common	kexec_file_load			sys_kexec_file_load
+382	common	io_pgetevents			sys_io_pgetevents
+383	common	rseq				sys_rseq
+384	common	pkey_mprotect			sys_pkey_mprotect
+385	common	pkey_alloc			sys_pkey_alloc
+386	common	pkey_free			sys_pkey_free
 # room for arch specific syscalls
-392	64	semtimedop		sys_semtimedop			-
-393  common	semget			sys_semget			sys_semget
-394  common	semctl			sys_semctl			compat_sys_semctl
-395  common	shmget			sys_shmget			sys_shmget
-396  common	shmctl			sys_shmctl			compat_sys_shmctl
-397  common	shmat			sys_shmat			compat_sys_shmat
-398  common	shmdt			sys_shmdt 			sys_shmdt
-399  common	msgget			sys_msgget			sys_msgget
-400  common	msgsnd			sys_msgsnd			compat_sys_msgsnd
-401  common	msgrcv			sys_msgrcv			compat_sys_msgrcv
-402  common	msgctl			sys_msgctl			compat_sys_msgctl
-403	32	clock_gettime64		-				sys_clock_gettime
-404	32	clock_settime64		-				sys_clock_settime
-405	32	clock_adjtime64		-				sys_clock_adjtime
-406	32	clock_getres_time64	-				sys_clock_getres
-407	32	clock_nanosleep_time64	-				sys_clock_nanosleep
-408	32	timer_gettime64		-				sys_timer_gettime
-409	32	timer_settime64		-				sys_timer_settime
-410	32	timerfd_gettime64	-				sys_timerfd_gettime
-411	32	timerfd_settime64	-				sys_timerfd_settime
-412	32	utimensat_time64	-				sys_utimensat
-413	32	pselect6_time64		-				compat_sys_pselect6_time64
-414	32	ppoll_time64		-				compat_sys_ppoll_time64
-416	32	io_pgetevents_time64	-				compat_sys_io_pgetevents_time64
-417	32	recvmmsg_time64		-				compat_sys_recvmmsg_time64
-418	32	mq_timedsend_time64	-				sys_mq_timedsend
-419	32	mq_timedreceive_time64	-				sys_mq_timedreceive
-420	32	semtimedop_time64	-				sys_semtimedop
-421	32	rt_sigtimedwait_time64	-				compat_sys_rt_sigtimedwait_time64
-422	32	futex_time64		-				sys_futex
-423	32	sched_rr_get_interval_time64	-			sys_sched_rr_get_interval
-424  common	pidfd_send_signal	sys_pidfd_send_signal		sys_pidfd_send_signal
-425  common	io_uring_setup		sys_io_uring_setup              sys_io_uring_setup
-426  common	io_uring_enter		sys_io_uring_enter              sys_io_uring_enter
-427  common	io_uring_register	sys_io_uring_register           sys_io_uring_register
-428  common	open_tree		sys_open_tree			sys_open_tree
-429  common	move_mount		sys_move_mount			sys_move_mount
-430  common	fsopen			sys_fsopen			sys_fsopen
-431  common	fsconfig		sys_fsconfig			sys_fsconfig
-432  common	fsmount			sys_fsmount			sys_fsmount
-433  common	fspick			sys_fspick			sys_fspick
-434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
-435  common	clone3			sys_clone3			sys_clone3
-436  common	close_range		sys_close_range			sys_close_range
-437  common	openat2			sys_openat2			sys_openat2
-438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
-439  common	faccessat2		sys_faccessat2			sys_faccessat2
-440  common	process_madvise		sys_process_madvise		sys_process_madvise
-441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
-442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
-443  common	quotactl_fd		sys_quotactl_fd			sys_quotactl_fd
-444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
-445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
-446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
-447  common	memfd_secret		sys_memfd_secret		sys_memfd_secret
-448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
-449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
-450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
-451  common	cachestat		sys_cachestat			sys_cachestat
-452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
-453  common	map_shadow_stack	sys_map_shadow_stack		sys_map_shadow_stack
-454  common	futex_wake		sys_futex_wake			sys_futex_wake
-455  common	futex_wait		sys_futex_wait			sys_futex_wait
-456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
-457  common	statmount		sys_statmount			sys_statmount
-458  common	listmount		sys_listmount			sys_listmount
-459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
-460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
-461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
-462  common	mseal			sys_mseal			sys_mseal
-463  common	setxattrat		sys_setxattrat			sys_setxattrat
-464  common	getxattrat		sys_getxattrat			sys_getxattrat
-465  common	listxattrat		sys_listxattrat			sys_listxattrat
-466  common	removexattrat		sys_removexattrat		sys_removexattrat
-467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
-468  common	file_getattr		sys_file_getattr		sys_file_getattr
-469  common	file_setattr		sys_file_setattr		sys_file_setattr
-470  common	listns			sys_listns			sys_listns
+392	common	semtimedop			sys_semtimedop
+393	common	semget				sys_semget
+394	common	semctl				sys_semctl
+395	common	shmget				sys_shmget
+396	common	shmctl				sys_shmctl
+397	common	shmat				sys_shmat
+398	common	shmdt				sys_shmdt
+399	common	msgget				sys_msgget
+400	common	msgsnd				sys_msgsnd
+401	common	msgrcv				sys_msgrcv
+402	common	msgctl				sys_msgctl
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
+428	common	open_tree			sys_open_tree
+429	common	move_mount			sys_move_mount
+430	common	fsopen				sys_fsopen
+431	common	fsconfig			sys_fsconfig
+432	common	fsmount				sys_fsmount
+433	common	fspick				sys_fspick
+434	common	pidfd_open			sys_pidfd_open
+435	common	clone3				sys_clone3
+436	common	close_range			sys_close_range
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2
+442	common	mount_setattr			sys_mount_setattr
+443	common	quotactl_fd			sys_quotactl_fd
+444	common	landlock_create_ruleset		sys_landlock_create_ruleset
+445	common	landlock_add_rule		sys_landlock_add_rule
+446	common	landlock_restrict_self		sys_landlock_restrict_self
+447	common	memfd_secret			sys_memfd_secret
+448	common	process_mrelease		sys_process_mrelease
+449	common	futex_waitv			sys_futex_waitv
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	common	cachestat			sys_cachestat
+452	common	fchmodat2			sys_fchmodat2
+453	common	map_shadow_stack		sys_map_shadow_stack
+454	common	futex_wake			sys_futex_wake
+455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
+459	common	lsm_get_self_attr		sys_lsm_get_self_attr
+460	common	lsm_set_self_attr		sys_lsm_set_self_attr
+461	common	lsm_list_modules		sys_lsm_list_modules
+462	common	mseal				sys_mseal
+463	common	setxattrat			sys_setxattrat
+464	common	getxattrat			sys_getxattrat
+465	common	listxattrat			sys_listxattrat
+466	common	removexattrat			sys_removexattrat
+467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
+470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index 969c11325ade..70b315cbe710 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -474,3 +474,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 39aa26b6a50b..7e71bf7fcd14 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -480,7 +480,7 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	common	clone3				__sys_clone3
 436	common	close_range			sys_close_range
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
@@ -516,3 +516,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index e979a3eac7a3..f832ebd2d79b 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -476,3 +476,4 @@
 468	i386	file_getattr		sys_file_getattr
 469	i386	file_setattr		sys_file_setattr
 470	i386	listns			sys_listns
+471	i386	rseq_slice_yield	sys_rseq_slice_yield
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 8a4ac4841be6..524155d655da 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,6 +395,7 @@
 468	common	file_getattr		sys_file_getattr
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
+471	common	rseq_slice_yield	sys_rseq_slice_yield
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index 438a3b170402..a9bca4e484de 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index e74868be513c..7a42b32b6577 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -411,3 +411,4 @@
 468	common	file_getattr			sys_file_getattr
 469	common	file_setattr			sys_file_setattr
 470	common	listns				sys_listns
+471	common	rseq_slice_yield		sys_rseq_slice_yield
-- 
cgit v1.2.3


From 0693907ffaca001036009bc82dc334fb8e11540f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 5 Mar 2026 17:28:44 -0300
Subject: tools headers UAPI: Update tools' copy of linux/coresight-pmu.h

To get the comment changes in this commit:

  171efc70097a9f5f ("x86/ibs: Fix typo in dc_l2tlb_miss comment")

This silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/amd/ibs.h arch/x86/include/asm/amd/ibs.h

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/amd/ibs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h
index cbce54fec7b9..41e8abd72c8b 100644
--- a/tools/arch/x86/include/asm/amd/ibs.h
+++ b/tools/arch/x86/include/asm/amd/ibs.h
@@ -110,7 +110,7 @@ union ibs_op_data3 {
 		__u64	ld_op:1,			/* 0: load op */
 			st_op:1,			/* 1: store op */
 			dc_l1tlb_miss:1,		/* 2: data cache L1TLB miss */
-			dc_l2tlb_miss:1,		/* 3: data cache L2TLB hit in 2M page */
+			dc_l2tlb_miss:1,		/* 3: data cache L2TLB miss in 2M page */
 			dc_l1tlb_hit_2m:1,		/* 4: data cache L1TLB hit in 2M page */
 			dc_l1tlb_hit_1g:1,		/* 5: data cache L1TLB hit in 1G page */
 			dc_l2tlb_hit_2m:1,		/* 6: data cache L2TLB hit in 2M page */
-- 
cgit v1.2.3


From f2fa6cc736ef518628f6a9d1155f9ec24e0af4e7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 4 Mar 2026 16:01:19 -0800
Subject: rcutorture: Update due to x86 not supporting none/voluntary
 preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such rcutorture scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/bfe89f6c-3b63-40c6-aa6d-5f523e3e9a31@paulmck-laptop
---
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-N  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-T  | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/SRCU-U  | 4 ++--
 tools/testing/selftests/rcutorture/configs/rcu/TASKS02 | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TINY01  | 4 ++--
 tools/testing/selftests/rcutorture/configs/rcu/TINY02  | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TRACE01 | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE04  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE05  | 4 +++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE06  | 5 ++++-
 tools/testing/selftests/rcutorture/configs/rcu/TREE10  | 1 +
 tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL | 4 +++-
 12 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 07f5e0a70ae7..f943cdfb0a74 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -2,7 +2,9 @@ CONFIG_RCU_TRACE=n
 CONFIG_SMP=y
 CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
index c70cf0405f24..06e4d1030279 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
index bc9eeabaa1b1..71da6e3e9488 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
@@ -7,4 +8,3 @@ CONFIG_PREEMPT_DYNAMIC=n
 CONFIG_RCU_TRACE=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
index 2f9fcffff5ae..dd2bd4e08da4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 0953c52fcfd7..2be53bf60d65 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
@@ -11,4 +12,3 @@ CONFIG_RCU_TRACE=n
 #CHECK#CONFIG_RCU_STALL_COMMON=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
-CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index 30439f6fc20e..be8860342ef7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 18efab346381..8fb124c28f28 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -1,7 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=5
 CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 67caf4276bb0..ac857d5bcb22 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -1,10 +1,12 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_LAZY=y
 CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
 #CHECK#CONFIG_TREE_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 9f48c73709ec..61d15b1b54d1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -1,6 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TREE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index db27651de04b..0e090bb68a0f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -1,9 +1,12 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 #CHECK#CONFIG_TREE_RCU=y
+#CHECK#CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 420632b030dc..b2ce37861e71 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -6,6 +6,7 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
 #CHECK#CONFIG_TREE_RCU=y
+CONFIG_PREEMPT_RCU=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
index 5d546efa68e8..696fba9968c6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL
@@ -1,6 +1,8 @@
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_DYNAMIC=n
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
-- 
cgit v1.2.3


From 59af2d5652e998fea64335de6145afb3c1e0c958 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:01 -0800
Subject: rcuscale: Update due to x86 not supporting none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such rcuscale scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-2-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/rcuscale/TINY    | 3 ++-
 tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
index 0fa2dc086e10..c1a7d38823fb 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
index 0059592c7408..f3f1368b8386 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
-- 
cgit v1.2.3


From 3c6ddb58f670baa584b22eef761aade77bd81b16 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:02 -0800
Subject: refscale: Update due to x86 not supporting none/voluntary preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such refscale scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-3-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT | 3 ++-
 tools/testing/selftests/rcutorture/configs/refscale/TINY      | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
index 67f9d2998afd..1f215e17cbae 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/TINY b/tools/testing/selftests/rcutorture/configs/refscale/TINY
index 759343980b80..9a11b578ff34 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/TINY
+++ b/tools/testing/selftests/rcutorture/configs/refscale/TINY
@@ -1,5 +1,6 @@
 CONFIG_SMP=n
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
-- 
cgit v1.2.3


From 78c2ce0fd6ddb6c87aaa56b0d49c70e17df21e6d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 3 Mar 2026 15:59:03 -0800
Subject: scftorture: Update due to x86 not supporting none/voluntary
 preemption

As of v7.0-rc1, architectures that support preemption, including x86 and
arm64, no longer support CONFIG_PREEMPT_NONE or CONFIG_PREEMPT_VOLUNTARY.
Attempting to build kernels with these two Kconfig options results in
.config errors.  This commit therefore switches such scftorture scenarios
to CONFIG_PREEMPT_LAZY.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Link: https://patch.msgid.link/20260303235903.1967409-4-paulmck@kernel.org
---
 tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
index 6133f54ce2a7..f9621e2770a4 100644
--- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
@@ -1,5 +1,6 @@
 CONFIG_SMP=y
-CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_LAZY=y
+CONFIG_PREEMPT_NONE=n
 CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=n
 CONFIG_PREEMPT_DYNAMIC=n
-- 
cgit v1.2.3


From 7e459c41264fdd87b096ede8da796a302d569722 Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Date: Thu, 5 Mar 2026 23:51:16 +0530
Subject: drm/msm/a8xx: Fix ubwc config related to swizzling

To disable l2/l3 swizzling in A8x, set the respective bits in both
GRAS_NC_MODE_CNTL and RB_CCU_NC_MODE_CNTL registers. This is required
for Glymur where it is recommended to keep l2/l3 swizzling disabled.

Fixes: 288a93200892 ("drm/msm/adreno: Introduce A8x GPU Support")
Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Message-ID: <20260305-a8xx-ubwc-fix-v1-1-d99b6da4c5a9@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a8xx_gpu.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
index 5a320f5bde41..b1887e0cf698 100644
--- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
@@ -310,11 +310,21 @@ static void a8xx_set_ubwc_config(struct msm_gpu *gpu)
 	hbb = cfg->highest_bank_bit - 13;
 	hbb_hi = hbb >> 2;
 	hbb_lo = hbb & 3;
-	a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5);
-	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5);
+
+	a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL,
+			hbb << 5 |
+			level3_swizzling_dis << 4 |
+			level2_swizzling_dis << 3);
+
+	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL,
+			hbb << 5 |
+			level3_swizzling_dis << 4 |
+			level2_swizzling_dis << 3);
 
 	a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL,
 			yuvnotcomptofc << 6 |
+			level3_swizzling_dis << 5 |
+			level2_swizzling_dis << 4 |
 			hbb_hi << 3 |
 			hbb_lo << 1);
 
-- 
cgit v1.2.3


From 4ce71cea574658f5c5c7412b1a3cc54efe4f9b50 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Thu, 5 Mar 2026 18:17:07 +0800
Subject: drm/msm/dpu: Correct the SA8775P intr_underrun/intr_underrun index

The intr_underrun and intr_vsync indices have been swapped, just simply
corrects them.

Cc: stable@vger.kernel.org
Fixes: b139c80d181c ("drm/msm/dpu: Add SA8775P support")
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Yongxing Mou <yongxing.mou@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/709209/
Link: https://lore.kernel.org/r/20260305-mdss_catalog-v5-2-06678ac39ac7@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
index 0f7b4a224e4c..42cf3bd5a12a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h
@@ -366,8 +366,8 @@ static const struct dpu_intf_cfg sa8775p_intf[] = {
 		.type = INTF_NONE,
 		.controller_id = MSM_DP_CONTROLLER_0,	/* pair with intf_0 for DP MST */
 		.prog_fetch_lines_worst_case = 24,
-		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
-		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+		.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
 	}, {
 		.name = "intf_7", .id = INTF_7,
 		.base = 0x3b000, .len = 0x280,
-- 
cgit v1.2.3


From 7403e87c138475a74e5176176778f391d847f42d Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@oss.qualcomm.com>
Date: Tue, 3 Mar 2026 11:03:11 +0200
Subject: dt-bindings: display: msm: Fix reg ranges and clocks on Glymur

The Glymur platform has four DisplayPort controllers. The hardware
supports four streams (MST) per controller. However, on Glymur the first
three controllers only have two streams wired to the display subsystem,
while the fourth controller operates in single-stream mode.

Add a dedicated clause for the Glymur compatible to require the register
ranges for all four stream blocks, while allowing either one pixel clock
(for the single-stream controller) or two pixel clocks (for the remaining
controllers).

Update the Glymur MDSS schema example by adding the missing p2, p3,
mst2link and mst3link register blocks. Without these, the bindings
validation fails. Also replace the made-up register addresses with the
actual addresses from the first controller to match the SoC devicetree
description.

Cc: stable@vger.kernel.org # v6.19
Fixes: 8f63bf908213 ("dt-bindings: display: msm: Document the Glymur DiplayPort controller")
Fixes: 1aee577bbc60 ("dt-bindings: display: msm: Document the Glymur Mobile Display SubSystem")
Signed-off-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/708518/
Link: https://lore.kernel.org/r/20260303-glymur-fix-dp-bindings-reg-clocks-v4-1-1ebd9c7c2cee@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 .../bindings/display/msm/dp-controller.yaml         | 21 ++++++++++++++++++++-
 .../bindings/display/msm/qcom,glymur-mdss.yaml      | 16 ++++++++++------
 2 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
index ebda78db87a6..02ddfaab5f56 100644
--- a/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dp-controller.yaml
@@ -253,7 +253,6 @@ allOf:
             enum:
               # these platforms support 2 streams MST on some interfaces,
               # others are SST only
-              - qcom,glymur-dp
               - qcom,sc8280xp-dp
               - qcom,x1e80100-dp
     then:
@@ -310,6 +309,26 @@ allOf:
           minItems: 6
           maxItems: 8
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              # these platforms support 2 streams MST on some interfaces,
+              # others are SST only, but all controllers have 4 ports
+              - qcom,glymur-dp
+    then:
+      properties:
+        reg:
+          minItems: 9
+          maxItems: 9
+        clocks:
+          minItems: 5
+          maxItems: 6
+        clocks-names:
+          minItems: 5
+          maxItems: 6
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
index 2329ed96e6cb..64dde43373ac 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,glymur-mdss.yaml
@@ -176,13 +176,17 @@ examples:
                 };
             };
 
-            displayport-controller@ae90000 {
+            displayport-controller@af54000 {
                 compatible = "qcom,glymur-dp";
-                reg = <0xae90000 0x200>,
-                      <0xae90200 0x200>,
-                      <0xae90400 0x600>,
-                      <0xae91000 0x400>,
-                      <0xae91400 0x400>;
+                reg = <0xaf54000 0x200>,
+                      <0xaf54200 0x200>,
+                      <0xaf55000 0xc00>,
+                      <0xaf56000 0x400>,
+                      <0xaf57000 0x400>,
+                      <0xaf58000 0x400>,
+                      <0xaf59000 0x400>,
+                      <0xaf5a000 0x600>,
+                      <0xaf5b000 0x600>;
 
                 interrupt-parent = <&mdss>;
                 interrupts = <12>;
-- 
cgit v1.2.3


From fd941c787cbb402e8ebd84336f2a0026d5d0724d Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Thu, 26 Feb 2026 20:29:57 +0800
Subject: drm/msm/dsi/phy: fix hardware revision

The hardware revision for TSMC 3nm-based Qualcomm SOCs should be 7.2,
this can be confirmed from REG_DSI_7nm_PHY_CMN_REVISION_ID0, the value
is 0x27, which means hardware revision is 7.2

No functional change.

Fixes: 1337d7ebfb6d ("drm/msm/dsi/phy: Add support for SM8750")
Suggested-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707414/
Link: https://lore.kernel.org/r/20260226122958.22555-2-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 8cb0db3a9880..01182442dfd6 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -51,8 +51,8 @@
 #define DSI_PHY_7NM_QUIRK_V4_3		BIT(3)
 /* Hardware is V5.2 */
 #define DSI_PHY_7NM_QUIRK_V5_2		BIT(4)
-/* Hardware is V7.0 */
-#define DSI_PHY_7NM_QUIRK_V7_0		BIT(5)
+/* Hardware is V7.2 */
+#define DSI_PHY_7NM_QUIRK_V7_2		BIT(5)
 
 struct dsi_pll_config {
 	bool enable_ssc;
@@ -143,7 +143,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config
 
 	if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_PRE_V4_1) {
 		config->pll_clock_inverters = 0x28;
-	} else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	} else if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (pll_freq < 163000000ULL)
 			config->pll_clock_inverters = 0xa0;
 		else if (pll_freq < 175000000ULL)
@@ -284,7 +284,7 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll)
 	}
 
 	if ((pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (pll->vco_current_rate < 1557000000ULL)
 			vco_config_1 = 0x08;
 		else
@@ -699,7 +699,7 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 	case MSM_DSI_PHY_MASTER:
 		pll_7nm->slave = pll_7nm_list[(pll_7nm->phy->id + 1) % DSI_MAX];
 		/* v7.0: Enable ATB_EN0 and alternate clock output to external phy */
-		if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)
+		if (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)
 			writel(0x07, base + REG_DSI_7nm_PHY_CMN_CTRL_5);
 		break;
 	case MSM_DSI_PHY_SLAVE:
@@ -987,7 +987,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	/* Request for REFGEN READY */
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) ||
 	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		writel(0x1, phy->base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10);
 		udelay(500);
 	}
@@ -1021,7 +1021,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 		lane_ctrl0 = 0x1f;
 	}
 
-	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		if (phy->cphy_mode) {
 			/* TODO: different for second phy */
 			vreg_ctrl_0 = 0x57;
@@ -1097,7 +1097,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 
 	/* program CMN_CTRL_4 for minor_ver 2 chipsets*/
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0) ||
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2) ||
 	    (readl(base + REG_DSI_7nm_PHY_CMN_REVISION_ID0) & (0xf0)) == 0x20)
 		writel(0x04, base + REG_DSI_7nm_PHY_CMN_CTRL_4);
 
@@ -1213,7 +1213,7 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 	/* Turn off REFGEN Vote */
 	if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_3) ||
 	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2) ||
-	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_0)) {
+	    (phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V7_2)) {
 		writel(0x0, base + REG_DSI_7nm_PHY_CMN_GLBL_DIGTOP_SPARE10);
 		wmb();
 		/* Delay to ensure HW removes vote before PHY shut down */
@@ -1502,7 +1502,7 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_8750_cfgs = {
 #endif
 	.io_start = { 0xae95000, 0xae97000 },
 	.num_dsi_phy = 2,
-	.quirks = DSI_PHY_7NM_QUIRK_V7_0,
+	.quirks = DSI_PHY_7NM_QUIRK_V7_2,
 };
 
 const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = {
@@ -1525,5 +1525,5 @@ const struct msm_dsi_phy_cfg dsi_phy_3nm_kaanapali_cfgs = {
 #endif
 	.io_start = { 0x9ac1000, 0x9ac4000 },
 	.num_dsi_phy = 2,
-	.quirks = DSI_PHY_7NM_QUIRK_V7_0,
+	.quirks = DSI_PHY_7NM_QUIRK_V7_2,
 };
-- 
cgit v1.2.3


From 4355b13d46f696d687f42b982efed7570e03e532 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Wed, 25 Feb 2026 18:34:20 +0100
Subject: dt-bindings: display/msm: qcom,sm8750-mdss: Fix model typo

Fix obvious model typo (SM8650->SM8750) in the description.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Fixes: 6b93840116df ("dt-bindings: display/msm: qcom,sm8750-mdss: Add SM8750")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/707192/
Link: https://lore.kernel.org/r/20260225173419.125565-2-krzysztof.kozlowski@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
index d55fda9a523e..a38c2261ef1a 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8750-mdss.yaml
@@ -10,7 +10,7 @@ maintainers:
   - Krzysztof Kozlowski <krzk@kernel.org>
 
 description:
-  SM8650 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like
+  SM8750 MSM Mobile Display Subsystem(MDSS), which encapsulates sub-blocks like
   DPU display controller, DSI and DP interfaces etc.
 
 $ref: /schemas/display/msm/mdss-common.yaml#
-- 
cgit v1.2.3


From e174dd14bf0beac811a5201e370ab26ce8c67f23 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Tue, 24 Feb 2026 15:29:56 +0800
Subject: rust: kbuild: emit dep-info into $(depfile) directly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 295d8398c67e ("kbuild: specify output names separately for
each emission type from rustc"), the preferred pattern is to ask rustc to
emit dependency information into $(depfile) directly, and after commit
2185242faddd ("kbuild: remove sed commands after rustc rules"), the
post-processing to remove comments is no longer necessary as fixdep can
handle comments directly. Thus, emit dep-info into $(depfile) directly and
remove the mv and sed invocation.

This fixes the issue where a non-ignored .d file is emitted during
compilation and removed shortly afterwards.

[ Like Gary mentioned in Zulip, this likely happened due to rebasing
  the builds part of the old `syn` work I had. - Miguel ]

Reported-by: Onur Özkan <work@onurozkan.dev>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/syn.20artifact.20being.20tracked.20by.20git/with/575467879
Fixes: 7dbe46c0b11d ("rust: kbuild: add proc macro library support")
Signed-off-by: Gary Guo <gary@garyguo.net>
Tested-by: Onur Özkan <work@onurozkan.dev>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260224072957.214979-1-gary@garyguo.net
[ Reworded for a couple of typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/Makefile | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/rust/Makefile b/rust/Makefile
index 629b3bdd2b20..1500993d7ecc 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -526,11 +526,9 @@ quiet_cmd_rustc_procmacrolibrary = $(RUSTC_OR_CLIPPY_QUIET) PL $@
       cmd_rustc_procmacrolibrary = \
 	$(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \
 		$(filter-out $(skip_flags),$(rust_common_flags) $(rustc_target_flags)) \
-		--emit=dep-info,link --crate-type rlib -O \
+		--emit=dep-info=$(depfile) --emit=link=$@ --crate-type rlib -O \
 		--out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \
-		--crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<; \
-	mv $(objtree)/$(obj)/$(patsubst lib%.rlib,%,$(notdir $@)).d $(depfile); \
-	sed -i '/^\#/d' $(depfile)
+		--crate-name $(patsubst lib%.rlib,%,$(notdir $@)) $<
 
 $(obj)/libproc_macro2.rlib: private skip_clippy = 1
 $(obj)/libproc_macro2.rlib: private rustc_target_flags = $(proc_macro2-flags)
-- 
cgit v1.2.3


From dda135077ecc9f15c407f094dcfe7800376be867 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Thu, 26 Feb 2026 15:21:11 +0000
Subject: rust: build: remap path to avoid absolute path

When building with an out directory (O=), absolute paths can end up in the
file name in `#[track_caller]` or the panic message. This is not desirable
as this leaks the exact path being used to build the kernel and means that
the same location can appear in two forms (relative or absolute).

This is reported by Asahi [1] and is being workaround in [2] previously to
force everything to be absolute path. Using absolute path for everything
solves the inconsistency, however it does not address the reproducibility
issue. So, fix this by remap all absolute paths to srctree to relative path
instead.

This is previously attempted in commit dbdffaf50ff9 ("kbuild, rust: use
-fremap-path-prefix to make paths relative") but that was reverted as
remapping debug info causes some tool (e.g. objdump) to be unable to find
sources. Therefore, use `--remap-path-scope` to only remap macros but leave
debuginfo untouched. `--remap-path-scope` is only stable in Rust 1.95, so
use `rustc-option` to detect its presence. This feature has been available
as  `-Zremap-path-scope` for all versions that we support; however due to
bugs in the Rust compiler, it does not work reliably until 1.94. I opted to
not enable it for 1.94 as it's just a single version that we missed.

This change can be validated by building a kernel with O=, strip debug info
on vmlinux, and then check if the absolute path exists in `strings
vmlinux`, e.g. `strings vmlinux |grep \/home`.

Reported-by: Janne Grunau <j@jannau.net>
Reported-by: Asahi Lina <lina+kernel@asahilina.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/288089-General/topic/Per-call-site.20data.20and.20lock.20class.20keys/near/572466559 [1]
Link: https://github.com/AsahiLinux/linux/commit/54ab88878869036c9d6620101bfe17a81e88c2f9 [2]
Signed-off-by: Gary Guo <gary@garyguo.net>
Acked-by: Nicolas Schier <nsc@kernel.org> # kbuild
Link: https://patch.msgid.link/20260226152112.3222886-1-gary@kernel.org
[ Reworded for few typos. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile      | 3 +++
 rust/Makefile | 5 +++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 2446085983f7..73a39592f112 100644
--- a/Makefile
+++ b/Makefile
@@ -1113,6 +1113,9 @@ KBUILD_CFLAGS += -fno-builtin-wcslen
 # change __FILE__ to the relative path to the source directory
 ifdef building_out_of_srctree
 KBUILD_CPPFLAGS += -fmacro-prefix-map=$(srcroot)/=
+ifeq ($(call rustc-option-yn, --remap-path-scope=macro),y)
+KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/= --remap-path-scope=macro
+endif
 endif
 
 # include additional Makefiles when needed
diff --git a/rust/Makefile b/rust/Makefile
index 1500993d7ecc..9801af2e1e02 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -148,7 +148,8 @@ doctests_modifiers_workaround := $(rustdoc_modifiers_workaround)$(if $(call rust
 quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $<
       cmd_rustdoc = \
 	OBJTREE=$(abspath $(objtree)) \
-	$(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=%,$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \
+	$(RUSTDOC) $(filter-out $(skip_flags) --remap-path-prefix=% --remap-path-scope=%, \
+			$(if $(rustdoc_host),$(rust_common_flags),$(rust_flags))) \
 		$(rustc_target_flags) -L$(objtree)/$(obj) \
 		-Zunstable-options --generate-link-to-definition \
 		--output $(rustdoc_output) \
@@ -334,7 +335,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $<
 	rm -rf $(objtree)/$(obj)/test/doctests/kernel; \
 	mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \
 	OBJTREE=$(abspath $(objtree)) \
-	$(RUSTDOC) --test $(filter-out --remap-path-prefix=%,$(rust_flags)) \
+	$(RUSTDOC) --test $(filter-out --remap-path-prefix=% --remap-path-scope=%,$(rust_flags)) \
 		-L$(objtree)/$(obj) --extern ffi --extern pin_init \
 		--extern kernel --extern build_error --extern macros \
 		--extern bindings --extern uapi \
-- 
cgit v1.2.3


From a075082a15e7f5c4889d0cbb51a4041c332cb00c Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Mon, 2 Mar 2026 15:04:14 +0100
Subject: rust: pin-init: internal: init: remove
 `#[disable_initialized_field_access]`

Gary noticed [1] that the initializer macros as well as the `[Pin]Init`
traits cannot support unaligned fields, since they use operations that
require aligned pointers. This means that any code using structs with
unaligned fields in pin-init is unsound.

By default, the `init!` macro generates references to initialized fields,
which makes the compiler check that those fields are aligned.  However,
we added the `#[disable_initialized_field_access]` attribute to avoid
this behavior in commit ceca298c53f9 ("rust: pin-init: internal: init:
add escape hatch for referencing initialized fields"). Thus remove the
`#[disable_initialized_field_access]` attribute from `init!`, which is
the only safe way to create an initializer handling unaligned fields.

If support for in-place initializing structs with unaligned fields is
required in the future, we could figure out a solution. This is tracked
in [2].

Reported-by: Gary Guo <gary@garyguo.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1]
Link: https://github.com/Rust-for-Linux/pin-init/issues/112 [2]
Fixes: ceca298c53f9 ("rust: pin-init: internal: init: add escape hatch for referencing initialized fields")
Signed-off-by: Benno Lossin <lossin@kernel.org>
Acked-by: Janne Grunau <j@jannau.net>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://patch.msgid.link/20260302140424.4097655-1-lossin@kernel.org
[ Adjusted tags and reworded as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 39 ++++++++------------------------------
 1 file changed, 8 insertions(+), 31 deletions(-)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index 42936f915a07..da53adc44ecf 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -62,7 +62,6 @@ impl InitializerKind {
 
 enum InitializerAttribute {
     DefaultError(DefaultErrorAttribute),
-    DisableInitializedFieldAccess,
 }
 
 struct DefaultErrorAttribute {
@@ -86,6 +85,7 @@ pub(crate) fn expand(
     let error = error.map_or_else(
         || {
             if let Some(default_error) = attrs.iter().fold(None, |acc, attr| {
+                #[expect(irrefutable_let_patterns)]
                 if let InitializerAttribute::DefaultError(DefaultErrorAttribute { ty }) = attr {
                     Some(ty.clone())
                 } else {
@@ -145,15 +145,7 @@ pub(crate) fn expand(
     };
     // `mixed_site` ensures that the data is not accessible to the user-controlled code.
     let data = Ident::new("__data", Span::mixed_site());
-    let init_fields = init_fields(
-        &fields,
-        pinned,
-        !attrs
-            .iter()
-            .any(|attr| matches!(attr, InitializerAttribute::DisableInitializedFieldAccess)),
-        &data,
-        &slot,
-    );
+    let init_fields = init_fields(&fields, pinned, &data, &slot);
     let field_check = make_field_check(&fields, init_kind, &path);
     Ok(quote! {{
         // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return
@@ -236,7 +228,6 @@ fn get_init_kind(rest: Option<(Token![..], Expr)>, dcx: &mut DiagCtxt) -> InitKi
 fn init_fields(
     fields: &Punctuated<InitializerField, Token![,]>,
     pinned: bool,
-    generate_initialized_accessors: bool,
     data: &Ident,
     slot: &Ident,
 ) -> TokenStream {
@@ -272,13 +263,6 @@ fn init_fields(
                         unsafe { &mut (*#slot).#ident }
                     }
                 };
-                let accessor = generate_initialized_accessors.then(|| {
-                    quote! {
-                        #(#cfgs)*
-                        #[allow(unused_variables)]
-                        let #ident = #accessor;
-                    }
-                });
                 quote! {
                     #(#attrs)*
                     {
@@ -286,7 +270,9 @@ fn init_fields(
                         // SAFETY: TODO
                         unsafe { #write(::core::ptr::addr_of_mut!((*#slot).#ident), #value_ident) };
                     }
-                    #accessor
+                    #(#cfgs)*
+                    #[allow(unused_variables)]
+                    let #ident = #accessor;
                 }
             }
             InitializerKind::Init { ident, value, .. } => {
@@ -326,20 +312,15 @@ fn init_fields(
                         },
                     )
                 };
-                let accessor = generate_initialized_accessors.then(|| {
-                    quote! {
-                        #(#cfgs)*
-                        #[allow(unused_variables)]
-                        let #ident = #accessor;
-                    }
-                });
                 quote! {
                     #(#attrs)*
                     {
                         let #init = #value;
                         #value_init
                     }
-                    #accessor
+                    #(#cfgs)*
+                    #[allow(unused_variables)]
+                    let #ident = #accessor;
                 }
             }
             InitializerKind::Code { block: value, .. } => quote! {
@@ -466,10 +447,6 @@ impl Parse for Initializer {
                 if a.path().is_ident("default_error") {
                     a.parse_args::<DefaultErrorAttribute>()
                         .map(InitializerAttribute::DefaultError)
-                } else if a.path().is_ident("disable_initialized_field_access") {
-                    a.meta
-                        .require_path_only()
-                        .map(|_| InitializerAttribute::DisableInitializedFieldAccess)
                 } else {
                     Err(syn::Error::new_spanned(a, "unknown initializer attribute"))
                 }
-- 
cgit v1.2.3


From 580cc37b1de4fcd9997c48d7080e744533f09f36 Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Mon, 2 Mar 2026 15:04:15 +0100
Subject: rust: pin-init: internal: init: document load-bearing fact of field
 accessors

The functions `[Pin]Init::__[pinned_]init` and `ptr::write` called from
the `init!` macro require the passed pointer to be aligned. This fact is
ensured by the creation of field accessors to previously initialized
fields.

Since we missed this very important fact from the beginning [1],
document it in the code.

Link: https://rust-for-linux.zulipchat.com/#narrow/channel/561532-pin-init/topic/initialized.20field.20accessor.20detection/with/576210658 [1]
Fixes: 90e53c5e70a6 ("rust: add pin-init API core")
Cc: <stable@vger.kernel.org> # 6.6.y, 6.12.y: 42415d163e5d: rust: pin-init: add references to previously initialized fields
Cc: <stable@vger.kernel.org> # 6.6.y, 6.12.y, 6.18.y, 6.19.y
Signed-off-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260302140424.4097655-2-lossin@kernel.org
[ Updated Cc: stable@ tags as discussed. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index da53adc44ecf..738f62c8105c 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -251,6 +251,10 @@ fn init_fields(
                 });
                 // Again span for better diagnostics
                 let write = quote_spanned!(ident.span()=> ::core::ptr::write);
+                // NOTE: the field accessor ensures that the initialized field is properly aligned.
+                // Unaligned fields will cause the compiler to emit E0793. We do not support
+                // unaligned fields since `Init::__init` requires an aligned pointer; the call to
+                // `ptr::write` below has the same requirement.
                 let accessor = if pinned {
                     let project_ident = format_ident!("__project_{ident}");
                     quote! {
@@ -278,6 +282,10 @@ fn init_fields(
             InitializerKind::Init { ident, value, .. } => {
                 // Again span for better diagnostics
                 let init = format_ident!("init", span = value.span());
+                // NOTE: the field accessor ensures that the initialized field is properly aligned.
+                // Unaligned fields will cause the compiler to emit E0793. We do not support
+                // unaligned fields since `Init::__init` requires an aligned pointer; the call to
+                // `ptr::write` below has the same requirement.
                 let (value_init, accessor) = if pinned {
                     let project_ident = format_ident!("__project_{ident}");
                     (
-- 
cgit v1.2.3


From f76a93241d71fbba8425e3967097b498c29264ed Mon Sep 17 00:00:00 2001
From: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Date: Tue, 3 Mar 2026 17:25:12 -0300
Subject: net: dsa: realtek: rtl8365mb: remove ifOutDiscards from rx_packets

rx_packets should report the number of frames successfully received:
unicast + multicast + broadcast. Subtracting ifOutDiscards (a TX
counter) is incorrect and can undercount RX packets. RX drops are
already reported via rx_dropped (e.g. etherStatsDropEvents), so
there is no need to adjust rx_packets.

This patch removes the subtraction of ifOutDiscards from rx_packets
in rtl8365mb_stats_update().

Link: https://lore.kernel.org/netdev/878777925.105015.1763423928520@mail.yahoo.com/
Fixes: 4af2950c50c8 ("net: dsa: realtek-smi: add rtl8365mb subdriver for RTL8365MB-VC")
Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Linus Walleij <linusw@kernel.org>
Link: https://patch.msgid.link/20260303-realtek_namiltd_fix2-v1-1-bfa433d3401e@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8365mb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index f938a3f701cc..31fa94dac627 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -1480,8 +1480,7 @@ static void rtl8365mb_stats_update(struct realtek_priv *priv, int port)
 
 	stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifInMulticastPkts] +
-			    cnt[RTL8365MB_MIB_ifInBroadcastPkts] -
-			    cnt[RTL8365MB_MIB_ifOutDiscards];
+			    cnt[RTL8365MB_MIB_ifInBroadcastPkts];
 
 	stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] +
 			    cnt[RTL8365MB_MIB_ifOutMulticastPkts] +
-- 
cgit v1.2.3


From 048efe129a297256d3c2088cf8d79515ff5ec864 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Thu, 5 Mar 2026 21:57:06 -0300
Subject: smb: client: fix oops due to uninitialised var in smb2_unlink()

If SMB2_open_init() or SMB2_close_init() fails (e.g. reconnect), the
iovs set @rqst will be left uninitialised, hence calling
SMB2_open_free(), SMB2_close_free() or smb2_set_related() on them will
oops.

Fix this by initialising @close_iov and @open_iov before setting them
in @rqst.

Reported-by: Thiago Becker <tbecker@redhat.com>
Fixes: 1cf9f2a6a544 ("smb: client: handle unlink(2) of files open by different clients")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 1c4663ed7e69..5280c5c869ad 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1216,6 +1216,7 @@ again:
 	memset(resp_buftype, 0, sizeof(resp_buftype));
 	memset(rsp_iov, 0, sizeof(rsp_iov));
 
+	memset(open_iov, 0, sizeof(open_iov));
 	rqst[0].rq_iov = open_iov;
 	rqst[0].rq_nvec = ARRAY_SIZE(open_iov);
 
@@ -1240,14 +1241,15 @@ again:
 	creq = rqst[0].rq_iov[0].iov_base;
 	creq->ShareAccess = FILE_SHARE_DELETE_LE;
 
+	memset(&close_iov, 0, sizeof(close_iov));
 	rqst[1].rq_iov = &close_iov;
 	rqst[1].rq_nvec = 1;
 
 	rc = SMB2_close_init(tcon, server, &rqst[1],
 			     COMPOUND_FID, COMPOUND_FID, false);
-	smb2_set_related(&rqst[1]);
 	if (rc)
 		goto err_free;
+	smb2_set_related(&rqst[1]);
 
 	if (retries) {
 		/* Back-off before retry */
-- 
cgit v1.2.3


From 8565617a8599dd17b96b7bf7e1eb19809ac6ae5e Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Fri, 16 Jan 2026 10:57:31 +0100
Subject: KVM: riscv: Fix Spectre-v1 in APLIC interrupt handling

Guests can control IRQ indices via MMIO. Sanitize them with
array_index_nospec() to prevent speculative out-of-bounds access
to the aplic->irqs[] array.

Similar to arm64 commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible
spectre-v1 in vgic_get_irq()") and x86 commit 8c86405f606c ("KVM: x86:
Protect ioapic_read_indirect() from Spectre-v1/L1TF attacks").

Fixes: 74967aa208e2 ("RISC-V: KVM: Add in-kernel emulation of AIA APLIC")
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260116095731.24555-1-lukas.gerlach@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_aplic.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c
index d1e50bf5c351..3464f3351df7 100644
--- a/arch/riscv/kvm/aia_aplic.c
+++ b/arch/riscv/kvm/aia_aplic.c
@@ -10,6 +10,7 @@
 #include <linux/irqchip/riscv-aplic.h>
 #include <linux/kvm_host.h>
 #include <linux/math.h>
+#include <linux/nospec.h>
 #include <linux/spinlock.h>
 #include <linux/swab.h>
 #include <kvm/iodev.h>
@@ -45,7 +46,7 @@ static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return 0;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = irqd->sourcecfg;
@@ -61,7 +62,7 @@ static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	if (val & APLIC_SOURCECFG_D)
 		val = 0;
@@ -81,7 +82,7 @@ static u32 aplic_read_target(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return 0;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = irqd->target;
@@ -97,7 +98,7 @@ static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	val &= APLIC_TARGET_EIID_MASK |
 	       (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) |
@@ -116,7 +117,7 @@ static bool aplic_read_pending(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false;
@@ -132,7 +133,7 @@ static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -170,7 +171,7 @@ static bool aplic_read_enabled(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false;
@@ -186,7 +187,7 @@ static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 	if (enabled)
@@ -205,7 +206,7 @@ static bool aplic_read_input(struct aplic *aplic, u32 irq)
 
 	if (!irq || aplic->nr_irqs <= irq)
 		return false;
-	irqd = &aplic->irqs[irq];
+	irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -254,7 +255,7 @@ static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last)
 	for (irq = first; irq <= last; irq++) {
 		if (!irq || aplic->nr_irqs <= irq)
 			continue;
-		irqd = &aplic->irqs[irq];
+		irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)];
 
 		raw_spin_lock_irqsave(&irqd->lock, flags);
 
@@ -283,7 +284,7 @@ int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level)
 
 	if (!aplic || !source || (aplic->nr_irqs <= source))
 		return -ENODEV;
-	irqd = &aplic->irqs[source];
+	irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)];
 	ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false;
 
 	raw_spin_lock_irqsave(&irqd->lock, flags);
-- 
cgit v1.2.3


From dec9ed9944349643874d482238ca2437d4f47b61 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Mon, 2 Feb 2026 04:00:59 +0000
Subject: RISC-V: KVM: Fix use-after-free in kvm_riscv_gstage_get_leaf()

While fuzzing KVM on RISC-V, a use-after-free was observed in
kvm_riscv_gstage_get_leaf(),  where ptep_get() dereferences a
freed gstage page table page during gfn unmap.

The crash manifests as:
  use-after-free in ptep_get include/linux/pgtable.h:340 [inline]
  use-after-free in kvm_riscv_gstage_get_leaf arch/riscv/kvm/gstage.c:89
  Call Trace:
    ptep_get include/linux/pgtable.h:340 [inline]
    kvm_riscv_gstage_get_leaf+0x2ea/0x358 arch/riscv/kvm/gstage.c:89
    kvm_riscv_gstage_unmap_range+0xf0/0x308 arch/riscv/kvm/gstage.c:265
    kvm_unmap_gfn_range+0x168/0x1fc arch/riscv/kvm/mmu.c:256
    kvm_mmu_unmap_gfn_range virt/kvm/kvm_main.c:724 [inline]
  page last free pid 808 tgid 808 stack trace:
    kvm_riscv_mmu_free_pgd+0x1b6/0x26a arch/riscv/kvm/mmu.c:457
    kvm_arch_flush_shadow_all+0x1a/0x24 arch/riscv/kvm/mmu.c:134
    kvm_flush_shadow_all virt/kvm/kvm_main.c:344 [inline]

The UAF is caused by gstage page table walks running concurrently with
gstage pgd teardown. In particular, kvm_unmap_gfn_range() can traverse
gstage page tables while kvm_arch_flush_shadow_all() frees the pgd,
leading to use-after-free of page table pages.

Fix the issue by serializing gstage unmap and pgd teardown with
kvm->mmu_lock. Holding mmu_lock ensures that gstage page tables
remain valid for the duration of unmap operations and prevents
concurrent frees.

This matches existing RISC-V KVM usage of mmu_lock to protect gstage
map/unmap operations, e.g. kvm_riscv_mmu_iounmap.

Fixes: dd82e35638d67f ("RISC-V: KVM: Factor-out g-stage page table management")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260202040059.1801167-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/mmu.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 0b75eb2a1820..87c8f41482c5 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -245,6 +245,7 @@ out:
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	struct kvm_gstage gstage;
+	bool mmu_locked;
 
 	if (!kvm->arch.pgd)
 		return false;
@@ -253,9 +254,12 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	gstage.flags = 0;
 	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
 	gstage.pgd = kvm->arch.pgd;
+	mmu_locked = spin_trylock(&kvm->mmu_lock);
 	kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT,
 				     (range->end - range->start) << PAGE_SHIFT,
 				     range->may_block);
+	if (mmu_locked)
+		spin_unlock(&kvm->mmu_lock);
 	return false;
 }
 
-- 
cgit v1.2.3


From c28eb189e481f5dac993d1907710716a9b561890 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Thu, 26 Feb 2026 08:51:19 +0000
Subject: RISC-V: KVM: Fix null pointer dereference in
 kvm_riscv_vcpu_aia_rmw_topei()

kvm_riscv_vcpu_aia_rmw_topei() assumes that the per-vCPU IMSIC state has
been initialized once AIA is reported as available and initialized at
the VM level. This assumption does not always hold.

Under fuzzed ioctl sequences, a guest may access the IMSIC TOPEI CSR
before the vCPU IMSIC state is set up. In this case,
vcpu->arch.aia_context.imsic_state is still NULL, and the TOPEI RMW path
dereferences it unconditionally, leading to a host kernel crash.

The crash manifests as:
  Unable to handle kernel paging request at virtual address
  dfffffff0000000e
  ...
  kvm_riscv_vcpu_aia_imsic_rmw arch/riscv/kvm/aia_imsic.c:909
  kvm_riscv_vcpu_aia_rmw_topei arch/riscv/kvm/aia.c:231
  csr_insn arch/riscv/kvm/vcpu_insn.c:208
  system_opcode_insn arch/riscv/kvm/vcpu_insn.c:281
  kvm_riscv_vcpu_virtual_insn arch/riscv/kvm/vcpu_insn.c:355
  kvm_riscv_vcpu_exit arch/riscv/kvm/vcpu_exit.c:230
  kvm_arch_vcpu_ioctl_run arch/riscv/kvm/vcpu.c:1008
  ...

Fix this by explicitly checking whether the vCPU IMSIC state has been
initialized before handling TOPEI CSR accesses. If not, forward the CSR
emulation to user space.

Fixes: db8b7e97d6137 ("RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260226085119.643295-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_imsic.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 06752fa24798..8786f52cf65a 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -908,6 +908,10 @@ int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel,
 	int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC;
 	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
 
+	/* If IMSIC vCPU state not initialized then forward to user space */
+	if (!imsic)
+		return KVM_INSN_EXIT_TO_USER_SPACE;
+
 	if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) {
 		/* Read pending and enabled interrupt with highest priority */
 		topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix,
-- 
cgit v1.2.3


From 5c1bb07871119eae6434c640e5e645a74d54a222 Mon Sep 17 00:00:00 2001
From: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Date: Fri, 27 Feb 2026 13:46:16 +0000
Subject: RISC-V: KVM: fix off-by-one array access in SBI PMU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The indexed array only has RISCV_KVM_MAX_COUNTERS elements.
The out-of-bound access could have been performed by a guest,
but it could only access another guest accessible data.

Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf")
Signed-off-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260227134617.23378-1-radim.krcmar@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index 4d8d5e9aa53d..aec6b293968b 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -520,7 +520,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx,
 {
 	struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu);
 
-	if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) {
+	if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) {
 		retdata->err_val = SBI_ERR_INVALID_PARAM;
 		return 0;
 	}
-- 
cgit v1.2.3


From 721ead7757125d66ec9b4ad98939a13d25e0b473 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Mon, 2 Mar 2026 13:27:03 +0000
Subject: RISC-V: KVM: Fix use-after-free in kvm_riscv_aia_aplic_has_attr()

Fuzzer reports a KASAN use-after-free bug triggered by a race
between KVM_HAS_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls on
the AIA device. The root cause is that aia_has_attr() invokes
kvm_riscv_aia_aplic_has_attr() without holding dev->kvm->lock, while
a concurrent aia_set_attr() may call aia_init() under that lock. When
aia_init() fails after kvm_riscv_aia_aplic_init() has succeeded, it
calls kvm_riscv_aia_aplic_cleanup() in its fail_cleanup_imsics path,
which frees both aplic_state and aplic_state->irqs. The concurrent
has_attr path can then dereference the freed aplic->irqs in
aplic_read_pending():
	irqd = &aplic->irqs[irq];   /* UAF here */

KASAN report:
 BUG: KASAN: slab-use-after-free in aplic_read_pending
             arch/riscv/kvm/aia_aplic.c:119 [inline]
 BUG: KASAN: slab-use-after-free in aplic_read_pending_word
             arch/riscv/kvm/aia_aplic.c:351 [inline]
 BUG: KASAN: slab-use-after-free in aplic_mmio_read_offset
             arch/riscv/kvm/aia_aplic.c:406
 Read of size 8 at addr ff600000ba965d58 by task 9498
 Call Trace:
  aplic_read_pending arch/riscv/kvm/aia_aplic.c:119 [inline]
  aplic_read_pending_word arch/riscv/kvm/aia_aplic.c:351 [inline]
  aplic_mmio_read_offset arch/riscv/kvm/aia_aplic.c:406
  kvm_riscv_aia_aplic_has_attr arch/riscv/kvm/aia_aplic.c:566
  aia_has_attr arch/riscv/kvm/aia_device.c:469
 allocated by task 9473:
  kvm_riscv_aia_aplic_init arch/riscv/kvm/aia_aplic.c:583
  aia_init arch/riscv/kvm/aia_device.c:248 [inline]
  aia_set_attr arch/riscv/kvm/aia_device.c:334
 freed by task 9473:
  kvm_riscv_aia_aplic_cleanup arch/riscv/kvm/aia_aplic.c:644
  aia_init arch/riscv/kvm/aia_device.c:292 [inline]
  aia_set_attr arch/riscv/kvm/aia_device.c:334

Fix this race by acquiring dev->kvm->lock in aia_has_attr() before
calling kvm_riscv_aia_aplic_has_attr(), consistent with the locking
pattern used in aia_get_attr() and aia_set_attr().

Fixes: 289a007b98b06d ("RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip")
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260302132703.1721415-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index b195a93add1c..fb901947aefe 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -437,7 +437,7 @@ static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 
 static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 {
-	int nr_vcpus;
+	int nr_vcpus, r = -ENXIO;
 
 	switch (attr->group) {
 	case KVM_DEV_RISCV_AIA_GRP_CONFIG:
@@ -466,12 +466,15 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		}
 		break;
 	case KVM_DEV_RISCV_AIA_GRP_APLIC:
-		return kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr);
+		mutex_lock(&dev->kvm->lock);
+		r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr);
+		mutex_unlock(&dev->kvm->lock);
+		break;
 	case KVM_DEV_RISCV_AIA_GRP_IMSIC:
 		return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
 	}
 
-	return -ENXIO;
+	return r;
 }
 
 struct kvm_device_ops kvm_riscv_aia_device_ops = {
-- 
cgit v1.2.3


From 7120a9d9e0232ad3c661a100973c57328f462b80 Mon Sep 17 00:00:00 2001
From: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Date: Wed, 4 Mar 2026 08:08:04 +0000
Subject: RISC-V: KVM: Fix potential UAF in kvm_riscv_aia_imsic_has_attr()

The KVM_DEV_RISCV_AIA_GRP_APLIC branch of aia_has_attr() was identified
to have a race condition with concurrent KVM_SET_DEVICE_ATTR ioctls,
leading to a use-after-free bug.

Upon analyzing the code, it was discovered that the
KVM_DEV_RISCV_AIA_GRP_IMSIC branch of aia_has_attr() suffers from the same
lack of synchronization. It invokes kvm_riscv_aia_imsic_has_attr() without
holding dev->kvm->lock.

While aia_has_attr() is running, a concurrent aia_set_attr() could call
aia_init() under the dev->kvm->lock. If aia_init() fails, it may trigger
kvm_riscv_vcpu_aia_imsic_cleanup(), which frees imsic_state. Without proper
locking, kvm_riscv_aia_imsic_has_attr() could attempt to access imsic_state
while it is being deallocated.

Although this specific path has not yet been reported by a fuzzer, it
is logically identical to the APLIC issue. Fix this by acquiring the
dev->kvm->lock before calling kvm_riscv_aia_imsic_has_attr(), ensuring
consistency with the locking pattern used for other AIA attribute groups.

Fixes: 5463091a51cf ("RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip")
Signed-off-by: Jiakai Xu <xujiakai2025@iscas.ac.cn>
Signed-off-by: Jiakai Xu <jiakaiPeanut@gmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260304080804.2281721-1-xujiakai2025@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index fb901947aefe..9a45c85239fe 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -471,7 +471,10 @@ static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		mutex_unlock(&dev->kvm->lock);
 		break;
 	case KVM_DEV_RISCV_AIA_GRP_IMSIC:
-		return kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
+		mutex_lock(&dev->kvm->lock);
+		r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr);
+		mutex_unlock(&dev->kvm->lock);
+		break;
 	}
 
 	return r;
-- 
cgit v1.2.3


From b342166cbcf96a8c846db96529e75dc2d2420d58 Mon Sep 17 00:00:00 2001
From: Wang Yechao <wang.yechao255@zte.com.cn>
Date: Thu, 26 Feb 2026 19:12:31 +0800
Subject: RISC-V: KVM: Skip THP support check during dirty logging

When dirty logging is enabled, guest stage mappings are forced to
PAGE_SIZE granularity. Changing the mapping page size at this point
is incorrect.

Fixes: ed7ae7a34bea ("RISC-V: KVM: Transparent huge page support")
Signed-off-by: Wang Yechao <wang.yechao255@zte.com.cn>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20260226191231140_X1Juus7s2kgVlc0ZyW_K@zte.com.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index 87c8f41482c5..088d33ba90ed 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -539,7 +539,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		goto out_unlock;
 
 	/* Check if we are backed by a THP and thus use block mapping if possible */
-	if (vma_pagesize == PAGE_SIZE)
+	if (!logging && (vma_pagesize == PAGE_SIZE))
 		vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa);
 
 	if (writable) {
-- 
cgit v1.2.3


From f9e26fc325411a34555ad07ddf0a19ff72ea06d4 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:41 +0100
Subject: KVM: riscv: Fix Spectre-v1 in ONE_REG register access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled register indices from the ONE_REG ioctl are used to
index into arrays of register values. Sanitize them with
array_index_nospec() to prevent speculative out-of-bounds access.

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-1-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index e7ab6cb00646..a4c8703a96a9 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 #include <linux/kvm_host.h>
 #include <asm/cacheflush.h>
@@ -127,6 +128,7 @@ static int kvm_riscv_vcpu_isa_check_host(unsigned long kvm_ext, unsigned long *g
 	    kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr))
 		return -ENOENT;
 
+	kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr));
 	*guest_ext = kvm_isa_ext_arr[kvm_ext];
 	switch (*guest_ext) {
 	case RISCV_ISA_EXT_SMNPM:
@@ -443,13 +445,16 @@ static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    KVM_REG_RISCV_CORE);
+	unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long);
 	unsigned long reg_val;
 
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
 		reg_val = cntx->sepc;
 	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
@@ -476,13 +481,16 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
 	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
 					    KVM_REG_SIZE_MASK |
 					    KVM_REG_RISCV_CORE);
+	unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long);
 	unsigned long reg_val;
 
 	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
 		return -EINVAL;
-	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
@@ -507,10 +515,13 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu,
 					  unsigned long *out_val)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		kvm_riscv_vcpu_flush_interrupts(vcpu);
 		*out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
@@ -526,10 +537,13 @@ static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu,
 					  unsigned long reg_val)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
 		reg_val &= VSIP_VALID_MASK;
 		reg_val <<= VSIP_TO_HVIP_SHIFT;
@@ -548,11 +562,14 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu,
 						   unsigned long reg_val)
 {
 	struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
+		sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) /
-		sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -EINVAL;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	((unsigned long *)csr)[reg_num] = reg_val;
 	return 0;
 }
@@ -562,11 +579,14 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu,
 					    unsigned long *out_val)
 {
 	struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
+		sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_smstateen_csr) /
-		sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -EINVAL;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	*out_val = ((unsigned long *)csr)[reg_num];
 	return 0;
 }
-- 
cgit v1.2.3


From ec87a82ca8740891bce9e93e79ea2cd6c2d70ac8 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:42 +0100
Subject: KVM: riscv: Fix Spectre-v1 in AIA CSR access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled indices are used to access AIA CSR registers.
Sanitize them with array_index_nospec() to prevent speculative
out-of-bounds access.

Similar to x86 commit 8c86405f606c ("KVM: x86: Protect
ioapic_read_indirect() from Spectre-v1/L1TF attacks") and arm64
commit 41b87599c743 ("KVM: arm/arm64: vgic: fix possible spectre-v1
in vgic_get_irq()").

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-2-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index cac3c2b51d72..38de97d2f5b8 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -13,6 +13,7 @@
 #include <linux/irqchip/riscv-imsic.h>
 #include <linux/irqdomain.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
 #include <asm/cpufeature.h>
@@ -182,10 +183,13 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
 			       unsigned long *out_val)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	*out_val = 0;
 	if (kvm_riscv_aia_available())
 		*out_val = ((unsigned long *)csr)[reg_num];
@@ -198,10 +202,13 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 			       unsigned long val)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
+	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
-	if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long))
+	if (reg_num >= regs_max)
 		return -ENOENT;
 
+	reg_num = array_index_nospec(reg_num, regs_max);
+
 	if (kvm_riscv_aia_available()) {
 		((unsigned long *)csr)[reg_num] = val;
 
-- 
cgit v1.2.3


From 8f0c15c4b14f27dd9bd35971adb9c908241f2f63 Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:43 +0100
Subject: KVM: riscv: Fix Spectre-v1 in floating-point register access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User-controlled indices are used to index into floating-point registers.
Sanitize them with array_index_nospec() to prevent speculative
out-of-bounds access.

Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-3-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_fp.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c
index 030904d82b58..bd5a9e7e7165 100644
--- a/arch/riscv/kvm/vcpu_fp.c
+++ b/arch/riscv/kvm/vcpu_fp.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 #include <asm/cpufeature.h>
 
@@ -93,9 +94,11 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
 			reg_val = &cntx->fp.f.fcsr;
 		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
-			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) {
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.f.f));
 			reg_val = &cntx->fp.f.f[reg_num];
-		else
+		} else
 			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
@@ -107,6 +110,8 @@ int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu,
 			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
 			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 				return -EINVAL;
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.d.f));
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
 			return -ENOENT;
@@ -138,9 +143,11 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 		if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr))
 			reg_val = &cntx->fp.f.fcsr;
 		else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) &&
-			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31]))
+			  reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) {
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.f.f));
 			reg_val = &cntx->fp.f.f[reg_num];
-		else
+		} else
 			return -ENOENT;
 	} else if ((rtype == KVM_REG_RISCV_FP_D) &&
 		   riscv_isa_extension_available(vcpu->arch.isa, d)) {
@@ -152,6 +159,8 @@ int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu,
 			   reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) {
 			if (KVM_REG_SIZE(reg->id) != sizeof(u64))
 				return -EINVAL;
+			reg_num = array_index_nospec(reg_num,
+					ARRAY_SIZE(cntx->fp.d.f));
 			reg_val = &cntx->fp.d.f[reg_num];
 		} else
 			return -ENOENT;
-- 
cgit v1.2.3


From 2dda6a9e09ee4f3c30ea72ba949a6ea781205e3a Mon Sep 17 00:00:00 2001
From: Lukas Gerlach <lukas.gerlach@cispa.de>
Date: Tue, 3 Mar 2026 15:19:44 +0100
Subject: KVM: riscv: Fix Spectre-v1 in PMU counter access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Guest-controlled counter indices received via SBI ecalls are used to
index into the PMC array. Sanitize them with array_index_nospec()
to prevent speculative out-of-bounds access.

Similar to x86 commit 13c5183a4e64 ("KVM: x86: Protect MSR-based
index computations in pmu.h from Spectre-v1/L1TF attacks").

Fixes: 8f0153ecd3bf ("RISC-V: KVM: Add skeleton support for perf")
Reviewed-by: Radim Krčmář <radim.krcmar@oss.qualcomm.com>
Signed-off-by: Lukas Gerlach <lukas.gerlach@cispa.de>
Link: https://lore.kernel.org/r/20260303-kvm-riscv-spectre-v1-v2-4-192caab8e0dc@cispa.de
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_pmu.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index aec6b293968b..e873430e596b 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/nospec.h>
 #include <linux/perf/riscv_pmu.h>
 #include <asm/csr.h>
 #include <asm/kvm_vcpu_sbi.h>
@@ -87,7 +88,8 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 
 static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code)
 {
-	return hw_event_perf_map[sbi_event_code];
+	return hw_event_perf_map[array_index_nospec(sbi_event_code,
+						    SBI_PMU_HW_GENERAL_MAX)];
 }
 
 static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code)
@@ -218,6 +220,7 @@ static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return -EINVAL;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[cidx];
 
 	if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW)
@@ -244,6 +247,7 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return -EINVAL;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[cidx];
 
 	if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) {
@@ -525,6 +529,7 @@ int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx,
 		return 0;
 	}
 
+	cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS);
 	retdata->out_val = kvpmu->pmc[cidx].cinfo.value;
 
 	return 0;
@@ -559,7 +564,8 @@ int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 	}
 	/* Start the counters that have been configured and requested by the guest */
 	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
-		pmc_index = i + ctr_base;
+		pmc_index = array_index_nospec(i + ctr_base,
+					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
 			continue;
 		/* The guest started the counter again. Reset the overflow status */
@@ -630,7 +636,8 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 
 	/* Stop the counters that have been configured and requested by the guest */
 	for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) {
-		pmc_index = i + ctr_base;
+		pmc_index = array_index_nospec(i + ctr_base,
+					       RISCV_KVM_MAX_COUNTERS);
 		if (!test_bit(pmc_index, kvpmu->pmc_in_use))
 			continue;
 		pmc = &kvpmu->pmc[pmc_index];
@@ -761,6 +768,7 @@ int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_ba
 		}
 	}
 
+	ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS);
 	pmc = &kvpmu->pmc[ctr_idx];
 	pmc->idx = ctr_idx;
 
-- 
cgit v1.2.3


From 45700a743af3b7402cb7238860a25c62f0498ab4 Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:47 +0530
Subject: RISC-V: KVM: Fix error code returned for Smstateen ONE_REG

Return -ENOENT for Smstateen ONE_REG when:
1) Smstateen is not enabled for a VCPU
2) ONE_REG id is out of range

This will make Smstateen ONE_REG error codes consistent
with other ONE_REG interfaces of KVM RISC-V.

Fixes: c04913f2b54e ("RISCV: KVM: Add sstateen0 to ONE_REG")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-2-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_onereg.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index a4c8703a96a9..45ecc0082e90 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -565,8 +565,10 @@ static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu,
 	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
 		sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN))
+		return -ENOENT;
 	if (reg_num >= regs_max)
-		return -EINVAL;
+		return -ENOENT;
 
 	reg_num = array_index_nospec(reg_num, regs_max);
 
@@ -582,8 +584,10 @@ static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu,
 	unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) /
 		sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN))
+		return -ENOENT;
 	if (reg_num >= regs_max)
-		return -EINVAL;
+		return -ENOENT;
 
 	reg_num = array_index_nospec(reg_num, regs_max);
 
@@ -615,10 +619,7 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, &reg_val);
 		break;
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
-		rc = -EINVAL;
-		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
-			rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num,
-							      &reg_val);
+		rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, &reg_val);
 		break;
 	default:
 		rc = -ENOENT;
@@ -660,10 +661,7 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 		rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val);
 		break;
 	case KVM_REG_RISCV_CSR_SMSTATEEN:
-		rc = -EINVAL;
-		if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN))
-			rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num,
-							      reg_val);
+		rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val);
 		break;
 	default:
 		rc = -ENOENT;
-- 
cgit v1.2.3


From 24433b2b5c74a9fee7baa3a97a1947446868901d Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:48 +0530
Subject: RISC-V: KVM: Fix error code returned for Ssaia ONE_REG

Return -ENOENT for Ssaia ONE_REG when Ssaia is not enabled
for a VCPU.

This will make Ssaia ONE_REG error codes consistent with
other ONE_REG interfaces of KVM RISC-V.

Fixes: 2a88f38cd58d ("RISC-V: KVM: return ENOENT in *_one_reg() when reg is unknown")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-3-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 38de97d2f5b8..5ec503288555 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -185,6 +185,8 @@ int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
+		return -ENOENT;
 	if (reg_num >= regs_max)
 		return -ENOENT;
 
@@ -204,6 +206,8 @@ int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
 	unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long);
 
+	if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA))
+		return -ENOENT;
 	if (reg_num >= regs_max)
 		return -ENOENT;
 
-- 
cgit v1.2.3


From c61ec3e8cc5d46fa269434a9ec16ca36d362e0dd Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@oss.qualcomm.com>
Date: Tue, 20 Jan 2026 13:29:49 +0530
Subject: RISC-V: KVM: Check host Ssaia extension when creating AIA irqchip

The KVM user-space may create KVM AIA irqchip before checking
VCPU Ssaia extension availability so KVM AIA irqchip must fail
when host does not have Ssaia extension.

Fixes: 89d01306e34d ("RISC-V: KVM: Implement device interface for AIA irqchip")
Signed-off-by: Anup Patel <anup.patel@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260120080013.2153519-4-anup.patel@oss.qualcomm.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_device.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 9a45c85239fe..49c71d3cdb00 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -11,6 +11,7 @@
 #include <linux/irqchip/riscv-imsic.h>
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
+#include <linux/cpufeature.h>
 
 static int aia_create(struct kvm_device *dev, u32 type)
 {
@@ -22,6 +23,9 @@ static int aia_create(struct kvm_device *dev, u32 type)
 	if (irqchip_in_kernel(kvm))
 		return -EEXIST;
 
+	if (!riscv_isa_extension_available(NULL, SSAIA))
+		return -ENODEV;
+
 	ret = -EBUSY;
 	if (kvm_trylock_all_vcpus(kvm))
 		return ret;
-- 
cgit v1.2.3


From 54fcd2f95f8d216183965a370ec69e1aab14f5da Mon Sep 17 00:00:00 2001
From: Carlos Maiolino <cem@kernel.org>
Date: Wed, 4 Mar 2026 19:54:27 +0100
Subject: xfs: fix returned valued from xfs_defer_can_append

xfs_defer_can_append returns a bool, it shouldn't be returning
a NULL.

Found by code inspection.

Fixes: 4dffb2cbb483 ("xfs: allow pausing of pending deferred work items")
Cc: <stable@vger.kernel.org> # v6.8
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Acked-by: Souptick Joarder <souptick.joarder@hpe.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_defer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 472c261163ed..c6909716b041 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -809,7 +809,7 @@ xfs_defer_can_append(
 
 	/* Paused items cannot absorb more work */
 	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
-		return NULL;
+		return false;
 
 	/* Already full? */
 	if (ops->max_items && dfp->dfp_count >= ops->max_items)
-- 
cgit v1.2.3


From ee0e6e69a772d601e152e5368a1da25d656122a8 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 5 Mar 2026 18:48:05 -0800
Subject: ata: libata-eh: Fix detection of deferred qc timeouts

If the ata_qc_for_each_raw() loop finishes without finding a matching SCSI
command for any QC, the variable qc will hold a pointer to the last element
examined, which has the tag i == ATA_MAX_QUEUE - 1. This qc can match the
port deferred QC (ap->deferred_qc).

If that happens, the condition qc == ap->deferred_qc evaluates to true
despite the loop not breaking with a match on the SCSI command for this QC.
In that case, the error handler mistakenly intercepts a command that has
not been issued yet and that has not timed out, and thus erroneously
returning a timeout error.

Fix the problem by checking for i < ATA_MAX_QUEUE in addition to
qc == ap->deferred_qc.

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Assisted-by: Gemini:gemini-3.1-pro
Fixes: eddb98ad9364 ("ata: libata-eh: correctly handle deferred qc timeouts")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
[cassel: modified commit log as suggested by Damien]
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-eh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 563432400f72..23be85418b3b 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -647,7 +647,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 				break;
 		}
 
-		if (qc == ap->deferred_qc) {
+		if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) {
 			/*
 			 * This is a deferred command that timed out while
 			 * waiting for the command queue to drain. Since the qc
-- 
cgit v1.2.3


From bd9121a5e9fa03fcf32afa5f3d238e942ae6045e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 3 Mar 2026 12:37:39 +0100
Subject: wifi: mac80211_hwsim: fully initialise PMSR capabilities

Since the recent additions to PMSR capabilities, it's no longer
sufficient to call parse_pmsr_capa() here since the capabilities
that were added aren't represented/filled by it. Always init the
data to zero to avoid using uninitialized memory.

Fixes: 86c6b6e4d187 ("wifi: nl80211/cfg80211: add new FTM capabilities")
Reported-by: syzbot+c686c6b197d10ff3a749@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/69a67aa3.a70a0220.b118c.000a.GAE@google.com/
Link: https://patch.msgid.link/20260303113739.176403-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index e89173f91637..f6b890dea7e0 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -6489,7 +6489,7 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
 	if (info->attrs[HWSIM_ATTR_PMSR_SUPPORT]) {
 		struct cfg80211_pmsr_capabilities *pmsr_capa;
 
-		pmsr_capa = kmalloc_obj(*pmsr_capa);
+		pmsr_capa = kzalloc_obj(*pmsr_capa);
 		if (!pmsr_capa) {
 			ret = -ENOMEM;
 			goto out_free;
-- 
cgit v1.2.3


From 708bbb45537780a8d3721ca1e0cf1932c1d1bf5f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 3 Mar 2026 15:03:39 +0100
Subject: wifi: mac80211: remove keys after disabling beaconing

We shouldn't remove keys before disable beaconing, at least when
beacon protection is used, since that would remove keys that are
still used for beacon transmission at the same time. Stop before
removing keys so there's no race.

Fixes: af2d14b01c32 ("mac80211: Beacon protection using the new BIGTK (STA)")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20260303150339.574e7887b3ab.I50d708f5aa22584506a91d0da7f8a73ba39fceac@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b92b4a5c2636..b85375ceb575 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1904,12 +1904,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	__sta_info_flush(sdata, true, link_id, NULL);
 
-	ieee80211_remove_link_keys(link, &keys);
-	if (!list_empty(&keys)) {
-		synchronize_net();
-		ieee80211_free_key_list(local, &keys);
-	}
-
 	ieee80211_stop_mbssid(sdata);
 	RCU_INIT_POINTER(link_conf->tx_bss_conf, NULL);
 
@@ -1921,6 +1915,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 	ieee80211_link_info_change_notify(sdata, link,
 					  BSS_CHANGED_BEACON_ENABLED);
 
+	ieee80211_remove_link_keys(link, &keys);
+	if (!list_empty(&keys)) {
+		synchronize_net();
+		ieee80211_free_key_list(local, &keys);
+	}
+
 	if (sdata->wdev.links[link_id].cac_started) {
 		chandef = link_conf->chanreq.oper;
 		wiphy_hrtimer_work_cancel(wiphy, &link->dfs_cac_timer_work);
-- 
cgit v1.2.3


From ac6f24cc9c0a9aefa55ec9696dcafa971d4d760b Mon Sep 17 00:00:00 2001
From: Nicolas Cavallari <nicolas.cavallari@green-communications.fr>
Date: Tue, 3 Mar 2026 17:06:39 +0100
Subject: wifi: mac80211: use jiffies_delta_to_msecs() for sta_info inactive
 times

Inactive times of around 0xffffffff milliseconds have been observed on
an ath9k device on ARM.  This is likely due to a memory ordering race in
the jiffies_to_msecs(jiffies - last_active()) calculation causing an
overflow when the observed jiffies is below ieee80211_sta_last_active().

Use jiffies_delta_to_msecs() instead to avoid this problem.

Fixes: 7bbdd2d98797 ("mac80211: implement station stats retrieval")
Signed-off-by: Nicolas Cavallari <nicolas.cavallari@green-communications.fr>
Link: https://patch.msgid.link/20260303161701.31808-1-nicolas.cavallari@green-communications.fr
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 6dc22f1593be..dd51a578fbc5 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2782,7 +2782,9 @@ static void sta_set_link_sinfo(struct sta_info *sta,
 	}
 
 	link_sinfo->inactive_time =
-		jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta, link_id));
+		jiffies_delta_to_msecs(jiffies -
+				       ieee80211_sta_last_active(sta,
+								 link_id));
 
 	if (!(link_sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) |
 				    BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) {
@@ -3015,7 +3017,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 	sinfo->connected_time = ktime_get_seconds() - sta->last_connected;
 	sinfo->assoc_at = sta->assoc_at;
 	sinfo->inactive_time =
-		jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta, -1));
+		jiffies_delta_to_msecs(jiffies -
+				       ieee80211_sta_last_active(sta, -1));
 
 	if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) |
 			       BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) {
-- 
cgit v1.2.3


From 672e5229e1ecfc2a3509b53adcb914d8b024a853 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 5 Mar 2026 17:08:12 +0000
Subject: mac80211: fix crash in ieee80211_chan_bw_change for AP_VLAN stations

ieee80211_chan_bw_change() iterates all stations and accesses
link->reserved.oper via sta->sdata->link[link_id]. For stations on
AP_VLAN interfaces (e.g. 4addr WDS clients), sta->sdata points to
the VLAN sdata, whose link never participates in chanctx reservations.
This leaves link->reserved.oper zero-initialized with chan == NULL,
causing a NULL pointer dereference in __ieee80211_sta_cap_rx_bw()
when accessing chandef->chan->band during CSA.

Resolve the VLAN sdata to its parent AP sdata using get_bss_sdata()
before accessing link data.

Cc: stable@vger.kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://patch.msgid.link/20260305170812.2904208-1-nbd@nbd.name
[also change sta->sdata in ARRAY_SIZE even if it doesn't matter]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/chan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 4447cf03c41b..05f45e66999b 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -561,14 +561,16 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local,
 	rcu_read_lock();
 	list_for_each_entry_rcu(sta, &local->sta_list,
 				list) {
-		struct ieee80211_sub_if_data *sdata = sta->sdata;
+		struct ieee80211_sub_if_data *sdata;
 		enum ieee80211_sta_rx_bandwidth new_sta_bw;
 		unsigned int link_id;
 
 		if (!ieee80211_sdata_running(sta->sdata))
 			continue;
 
-		for (link_id = 0; link_id < ARRAY_SIZE(sta->sdata->link); link_id++) {
+		sdata = get_bss_sdata(sta->sdata);
+
+		for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) {
 			struct ieee80211_link_data *link =
 				rcu_dereference(sdata->link[link_id]);
 			struct ieee80211_bss_conf *link_conf;
-- 
cgit v1.2.3


From b94ae8e0d5fe1bdbbfdc3854ff6ce98f6876a828 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 6 Mar 2026 07:24:02 +0000
Subject: wifi: mac80211: Fix static_branch_dec() underflow for aql_disable.

syzbot reported static_branch_dec() underflow in aql_enable_write(). [0]

The problem is that aql_enable_write() does not serialise concurrent
write()s to the debugfs.

aql_enable_write() checks static_key_false(&aql_disable.key) and
later calls static_branch_inc() or static_branch_dec(), but the
state may change between the two calls.

aql_disable does not need to track inc/dec.

Let's use static_branch_enable() and static_branch_disable().

[0]:
val == 0
WARNING: kernel/jump_label.c:311 at __static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311, CPU#0: syz.1.3155/20288
Modules linked in:
CPU: 0 UID: 0 PID: 20288 Comm: syz.1.3155 Tainted: G     U       L      syzkaller #0 PREEMPT(full)
Tainted: [U]=USER, [L]=SOFTLOCKUP
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/24/2026
RIP: 0010:__static_key_slow_dec_cpuslocked.part.0+0x107/0x120 kernel/jump_label.c:311
Code: f2 c9 ff 5b 5d c3 cc cc cc cc e8 54 f2 c9 ff 48 89 df e8 ac f9 ff ff eb ad e8 45 f2 c9 ff 90 0f 0b 90 eb a2 e8 3a f2 c9 ff 90 <0f> 0b 90 eb 97 48 89 df e8 5c 4b 33 00 e9 36 ff ff ff 0f 1f 80 00
RSP: 0018:ffffc9000b9f7c10 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffffffff9b3e5d40 RCX: ffffffff823c57b4
RDX: ffff8880285a0000 RSI: ffffffff823c5846 RDI: ffff8880285a0000
RBP: 0000000000000000 R08: 0000000000000005 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000000a
R13: 1ffff9200173ef88 R14: 0000000000000001 R15: ffffc9000b9f7e98
FS:  00007f530dd726c0(0000) GS:ffff8881245e3000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000200000001140 CR3: 000000007cc4a000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 __static_key_slow_dec_cpuslocked kernel/jump_label.c:297 [inline]
 __static_key_slow_dec kernel/jump_label.c:321 [inline]
 static_key_slow_dec+0x7c/0xc0 kernel/jump_label.c:336
 aql_enable_write+0x2b2/0x310 net/mac80211/debugfs.c:343
 short_proxy_write+0x133/0x1a0 fs/debugfs/file.c:383
 vfs_write+0x2aa/0x1070 fs/read_write.c:684
 ksys_pwrite64 fs/read_write.c:793 [inline]
 __do_sys_pwrite64 fs/read_write.c:801 [inline]
 __se_sys_pwrite64 fs/read_write.c:798 [inline]
 __x64_sys_pwrite64+0x1eb/0x250 fs/read_write.c:798
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xc9/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f530cf9aeb9
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f530dd72028 EFLAGS: 00000246 ORIG_RAX: 0000000000000012
RAX: ffffffffffffffda RBX: 00007f530d215fa0 RCX: 00007f530cf9aeb9
RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000010
RBP: 00007f530d008c1f R08: 0000000000000000 R09: 0000000000000000
R10: 4200000000000005 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f530d216038 R14: 00007f530d215fa0 R15: 00007ffde89fb978
 </TASK>

Fixes: e908435e402a ("mac80211: introduce aql_enable node in debugfs")
Reported-by: syzbot+feb9ce36a95341bb47a4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69a8979e.a70a0220.b118c.0025.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260306072405.3649474-1-kuniyu@google.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/debugfs.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index d02f07368c51..687a66cd4943 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -320,7 +320,6 @@ static ssize_t aql_enable_read(struct file *file, char __user *user_buf,
 static ssize_t aql_enable_write(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
-	bool aql_disabled = static_key_false(&aql_disable.key);
 	char buf[3];
 	size_t len;
 
@@ -335,15 +334,12 @@ static ssize_t aql_enable_write(struct file *file, const char __user *user_buf,
 	if (len > 0 && buf[len - 1] == '\n')
 		buf[len - 1] = 0;
 
-	if (buf[0] == '0' && buf[1] == '\0') {
-		if (!aql_disabled)
-			static_branch_inc(&aql_disable);
-	} else if (buf[0] == '1' && buf[1] == '\0') {
-		if (aql_disabled)
-			static_branch_dec(&aql_disable);
-	} else {
+	if (buf[0] == '0' && buf[1] == '\0')
+		static_branch_enable(&aql_disable);
+	else if (buf[0] == '1' && buf[1] == '\0')
+		static_branch_disable(&aql_disable);
+	else
 		return -EINVAL;
-	}
 
 	return count;
 }
-- 
cgit v1.2.3


From 8e732934fb81282be41602550e7e07baf265e972 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 3 Mar 2026 23:36:10 +0100
Subject: parisc: Increase initial mapping to 64 MB with KALLSYMS

The 32MB initial kernel mapping can become too small when CONFIG_KALLSYMS
is used. Increase the mapping to 64 MB in this case.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/include/asm/pgtable.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 2c139a4dbf4b..17afe7a59edf 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -85,7 +85,7 @@ extern void __update_cache(pte_t pte);
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#if defined(CONFIG_64BIT)
+#if defined(CONFIG_64BIT) || defined(CONFIG_KALLSYMS)
 #define KERNEL_INITIAL_ORDER	26	/* 1<<26 = 64MB */
 #else
 #define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */
-- 
cgit v1.2.3


From 17c144f1104bfc29a3ce3f7d0931a1bfb7a3558c Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 3 Mar 2026 23:36:11 +0100
Subject: parisc: Check kernel mapping earlier at bootup

The check if the initial mapping is sufficient needs to happen much
earlier during bootup. Move this test directly to the start_parisc()
function and use native PDC iodc functions to print the warning, because
panic() and printk() are not functional yet.

This fixes boot when enabling various KALLSYSMS options which need
much more space.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/kernel/setup.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index ace483b6f19a..d3e17a7a8901 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -120,14 +120,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	printk(KERN_CONT ".\n");
 
-	/*
-	 * Check if initial kernel page mappings are sufficient.
-	 * panic early if not, else we may access kernel functions
-	 * and variables which can't be reached.
-	 */
-	if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
-		panic("KERNEL_INITIAL_ORDER too small!");
-
 #ifdef CONFIG_64BIT
 	if(parisc_narrow_firmware) {
 		printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n");
@@ -279,6 +271,18 @@ void __init start_parisc(void)
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
 
+	/*
+	 * Check if initial kernel page mapping is sufficient.
+	 * Print warning if not, because we may access kernel functions and
+	 * variables which can't be reached yet through the initial mappings.
+	 * Note that the panic() and printk() functions are not functional
+	 * yet, so we need to use direct iodc() firmware calls instead.
+	 */
+	const char warn1[] = "CRITICAL: Kernel may crash because "
+			     "KERNEL_INITIAL_ORDER is too small.\n";
+	if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE)
+		pdc_iodc_print(warn1, sizeof(warn1) - 1);
+
 	/* check QEMU/SeaBIOS marker in PAGE0 */
 	running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
 
-- 
cgit v1.2.3


From 8475d8fe21ec9c7eb2faca555fbc5b68cf0d2597 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 4 Mar 2026 22:24:18 +0100
Subject: parisc: Fix initial page table creation for boot

The KERNEL_INITIAL_ORDER value defines the initial size (usually 32 or
64 MB) of the page table during bootup. Up until now the whole area was
initialized with PTE entries, but there was no check if we filled too
many entries.  Change the code to fill up with so many entries that the
"_end" symbol can be reached by the kernel, but not more entries than
actually fit into the initial PTE tables.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> # v6.0+
---
 arch/parisc/kernel/head.S | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index 96e0264ac961..9188c8d87437 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -56,6 +56,7 @@ ENTRY(parisc_kernel_start)
 
 	.import __bss_start,data
 	.import __bss_stop,data
+	.import __end,data
 
 	load32		PA(__bss_start),%r3
 	load32		PA(__bss_stop),%r4
@@ -149,7 +150,11 @@ $cpu_ok:
 	 * everything ... it will get remapped correctly later */
 	ldo		0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */
 	load32		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
-	load32		PA(pg0),%r1
+	load32		PA(_end),%r1
+	SHRREG		%r1,PAGE_SHIFT,%r1  /* %r1 is PFN count for _end symbol */
+	cmpb,<<,n	%r11,%r1,1f
+	copy		%r1,%r11	/* %r1 PFN count smaller than %r11 */
+1:	load32		PA(pg0),%r1
 
 $pgt_fill_loop:
 	STREGM          %r3,ASM_PTE_ENTRY_SIZE(%r1)
-- 
cgit v1.2.3


From 244acf1976b889b80b234982a70e9550c6f0bab7 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Wed, 4 Mar 2026 16:22:22 +0000
Subject: KVM: arm64: Fix vma_shift staleness on nested hwpoison path

When user_mem_abort() handles a nested stage-2 fault, it truncates
vma_pagesize to respect the guest's mapping size. However, the local
variable vma_shift is never updated to match this new size.

If the underlying host page turns out to be hardware poisoned,
kvm_send_hwpoison_signal() is called with the original, larger
vma_shift instead of the actual mapping size. This signals incorrect
poison boundaries to userspace and breaks hugepage memory poison
containment for nested VMs.

Update vma_shift to match the truncated vma_pagesize when operating
on behalf of a nested hypervisor.

Fixes: fd276e71d1e7 ("KVM: arm64: nv: Handle shadow stage 2 page faults")
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://patch.msgid.link/20260304162222.836152-3-tabba@google.com
[maz: simplified vma_shift assignment from the original patch]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/mmu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index e1d6a4f591a9..17d64a1e11e5 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1751,6 +1751,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 		force_pte = (max_map_size == PAGE_SIZE);
 		vma_pagesize = min_t(long, vma_pagesize, max_map_size);
+		vma_shift = __ffs(vma_pagesize);
 	}
 
 	/*
-- 
cgit v1.2.3


From 3599c714c08c324f0fcfa392bfb857c92c575400 Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Fri, 6 Mar 2026 15:44:22 +0800
Subject: KVM: arm64: Remove the redundant ISB in __kvm_at_s1e2()

We already have an ISB in __kvm_at() to make the address translation result
visible to subsequent reads of PAR_EL1. Remove the redundant one right
after it.

Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260306074422.47694-1-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/at.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 6588ea251ed7..c5c5644b1878 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1504,8 +1504,6 @@ int __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 			fail = true;
 		}
 
-		isb();
-
 		if (!fail)
 			par = read_sysreg_par();
 
-- 
cgit v1.2.3


From 25966fc097691e5c925ad080f64a2f19c5fd940a Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Thu, 5 Mar 2026 14:31:46 -0500
Subject: ublk: fix NULL pointer dereference in ublk_ctrl_set_size()

ublk_ctrl_set_size() unconditionally dereferences ub->ub_disk via
set_capacity_and_notify() without checking if it is NULL.

ub->ub_disk is NULL before UBLK_CMD_START_DEV completes (it is only
assigned in ublk_ctrl_start_dev()) and after UBLK_CMD_STOP_DEV runs
(ublk_detach_disk() sets it to NULL). Since the UBLK_CMD_UPDATE_SIZE
handler performs no state validation, a user can trigger a NULL pointer
dereference by sending UPDATE_SIZE to a device that has been added but
not yet started, or one that has been stopped.

Fix this by checking ub->ub_disk under ub->mutex before dereferencing
it, and returning -ENODEV if the disk is not available.

Fixes: 98b995660bff ("ublk: Add UBLK_U_CMD_UPDATE_SIZE")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c13cda58a7c6..03edabdf8977 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -5003,15 +5003,22 @@ static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header)
 	return 0;
 }
 
-static void ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header)
+static int ublk_ctrl_set_size(struct ublk_device *ub, const struct ublksrv_ctrl_cmd *header)
 {
 	struct ublk_param_basic *p = &ub->params.basic;
 	u64 new_size = header->data[0];
+	int ret = 0;
 
 	mutex_lock(&ub->mutex);
+	if (!ub->ub_disk) {
+		ret = -ENODEV;
+		goto out;
+	}
 	p->dev_sectors = new_size;
 	set_capacity_and_notify(ub->ub_disk, p->dev_sectors);
+out:
 	mutex_unlock(&ub->mutex);
+	return ret;
 }
 
 struct count_busy {
@@ -5331,8 +5338,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
 		ret = ublk_ctrl_end_recovery(ub, &header);
 		break;
 	case UBLK_CMD_UPDATE_SIZE:
-		ublk_ctrl_set_size(ub, &header);
-		ret = 0;
+		ret = ublk_ctrl_set_size(ub, &header);
 		break;
 	case UBLK_CMD_QUIESCE_DEV:
 		ret = ublk_ctrl_quiesce_dev(ub, &header);
-- 
cgit v1.2.3


From 97c5550b763171dbef61e6239cab372b9f9cd4a2 Mon Sep 17 00:00:00 2001
From: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Date: Thu, 5 Mar 2026 15:26:29 -0800
Subject: arm64: contpte: fix set_access_flags() no-op check for SMMU/ATS
 faults

contpte_ptep_set_access_flags() compared the gathered ptep_get() value
against the requested entry to detect no-ops. ptep_get() ORs AF/dirty
from all sub-PTEs in the CONT block, so a dirty sibling can make the
target appear already-dirty. When the gathered value matches entry, the
function returns 0 even though the target sub-PTE still has PTE_RDONLY
set in hardware.

For a CPU with FEAT_HAFDBS this gathered view is fine, since hardware may
set AF/dirty on any sub-PTE and CPU TLB behavior is effectively gathered
across the CONT range. But page-table walkers that evaluate each
descriptor individually (e.g. a CPU without DBM support, or an SMMU
without HTTU, or with HA/HD disabled in CD.TCR) can keep faulting on the
unchanged target sub-PTE, causing an infinite fault loop.

Gathering can therefore cause false no-ops when only a sibling has been
updated:
 - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared)
 - read faults:  target still lacks PTE_AF

Fix by checking each sub-PTE against the requested AF/dirty/write state
(the same bits consumed by __ptep_set_access_flags()), using raw
per-PTE values rather than the gathered ptep_get() view, before
returning no-op. Keep using the raw target PTE for the write-bit unfold
decision.

Per Arm ARM (DDI 0487) D8.7.1 ("The Contiguous bit"), any sub-PTE in a CONT
range may become the effective cached translation and software must
maintain consistent attributes across the range.

Fixes: 4602e5757bcc ("arm64/mm: wire up PTE_CONT for user mappings")
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Acked-by: Balbir Singh <balbirs@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/contpte.c | 53 +++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 49 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index b929a455103f..1519d090d5ea 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -599,6 +599,27 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
 
+static bool contpte_all_subptes_match_access_flags(pte_t *ptep, pte_t entry)
+{
+	pte_t *cont_ptep = contpte_align_down(ptep);
+	/*
+	 * PFNs differ per sub-PTE. Match only bits consumed by
+	 * __ptep_set_access_flags(): AF, DIRTY and write permission.
+	 */
+	const pteval_t cmp_mask = PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
+	pteval_t entry_cmp = pte_val(entry) & cmp_mask;
+	int i;
+
+	for (i = 0; i < CONT_PTES; i++) {
+		pteval_t pte_cmp = pte_val(__ptep_get(cont_ptep + i)) & cmp_mask;
+
+		if (pte_cmp != entry_cmp)
+			return false;
+	}
+
+	return true;
+}
+
 int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep,
 					pte_t entry, int dirty)
@@ -608,13 +629,37 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 	int i;
 
 	/*
-	 * Gather the access/dirty bits for the contiguous range. If nothing has
-	 * changed, its a noop.
+	 * Check whether all sub-PTEs in the CONT block already match the
+	 * requested access flags/write permission, using raw per-PTE values
+	 * rather than the gathered ptep_get() view.
+	 *
+	 * __ptep_set_access_flags() can update AF, dirty and write
+	 * permission, but only to make the mapping more permissive.
+	 *
+	 * ptep_get() gathers AF/dirty state across the whole CONT block,
+	 * which is correct for a CPU with FEAT_HAFDBS. But page-table
+	 * walkers that evaluate each descriptor individually (e.g. a CPU
+	 * without DBM support, or an SMMU without HTTU, or with HA/HD
+	 * disabled in CD.TCR) can keep faulting on the target sub-PTE if
+	 * only a sibling has been updated. Gathering can therefore cause
+	 * false no-ops when only a sibling has been updated:
+	 *  - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared)
+	 *  - read faults:  target still lacks PTE_AF
+	 *
+	 * Per Arm ARM (DDI 0487) D8.7.1, any sub-PTE in a CONT range may
+	 * become the effective cached translation, so all entries must have
+	 * consistent attributes. Check the full CONT block before returning
+	 * no-op, and when any sub-PTE mismatches, proceed to update the whole
+	 * range.
 	 */
-	orig_pte = pte_mknoncont(ptep_get(ptep));
-	if (pte_val(orig_pte) == pte_val(entry))
+	if (contpte_all_subptes_match_access_flags(ptep, entry))
 		return 0;
 
+	/*
+	 * Use raw target pte (not gathered) for write-bit unfold decision.
+	 */
+	orig_pte = pte_mknoncont(__ptep_get(ptep));
+
 	/*
 	 * We can fix up access/dirty bits without having to unfold the contig
 	 * range. But if the write bit is changing, we must unfold.
-- 
cgit v1.2.3


From f303406efd0b6b8740ce5c47e852097bbcf54879 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Tue, 3 Mar 2026 18:52:06 +0100
Subject: KVM: s390: Fix a deadlock

In some scenarios, a deadlock can happen, involving _do_shadow_pte().

Convert all usages of pgste_get_lock() to pgste_get_trylock() in
_do_shadow_pte() and return -EAGAIN. All callers can already deal with
-EAGAIN being returned.

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Tested-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Christoph Schlameuss <schlameuss@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4630b2a067ea..a9da9390867d 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1434,7 +1434,8 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 	if (rc)
 		return rc;
 
-	pgste = pgste_get_lock(ptep_h);
+	if (!pgste_get_trylock(ptep_h, &pgste))
+		return -EAGAIN;
 	newpte = _pte(f->pfn, f->writable, !p, 0);
 	newpte.s.d |= ptep->s.d;
 	newpte.s.sd |= ptep->s.sd;
@@ -1444,7 +1445,8 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 	pgste_set_unlock(ptep_h, pgste);
 
 	newpte = _pte(f->pfn, 0, !p, 0);
-	pgste = pgste_get_lock(ptep);
+	if (!pgste_get_trylock(ptep, &pgste))
+		return -EAGAIN;
 	pgste = __dat_ptep_xchg(ptep, pgste, newpte, gpa_to_gfn(raddr), sg->asce, uses_skeys(sg));
 	pgste_set_unlock(ptep, pgste);
 
-- 
cgit v1.2.3


From 6dccbc9f3e1d38565dff7730d2b7d1e8b16c9b09 Mon Sep 17 00:00:00 2001
From: Peddolla Harshavardhan Reddy <peddolla.reddy@oss.qualcomm.com>
Date: Thu, 5 Mar 2026 21:36:59 +0530
Subject: wifi: cfg80211: cancel pmsr_free_wk in cfg80211_pmsr_wdev_down

When the nl80211 socket that originated a PMSR request is
closed, cfg80211_release_pmsr() sets the request's nl_portid
to zero and schedules pmsr_free_wk to process the abort
asynchronously. If the interface is concurrently torn down
before that work runs, cfg80211_pmsr_wdev_down() calls
cfg80211_pmsr_process_abort() directly. However, the already-
scheduled pmsr_free_wk work item remains pending and may run
after the interface has been removed from the driver. This
could cause the driver's abort_pmsr callback to operate on a
torn-down interface, leading to undefined behavior and
potential crashes.

Cancel pmsr_free_wk synchronously in cfg80211_pmsr_wdev_down()
before calling cfg80211_pmsr_process_abort(). This ensures any
pending or in-progress work is drained before interface teardown
proceeds, preventing the work from invoking the driver abort
callback after the interface is gone.

Fixes: 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator API")
Signed-off-by: Peddolla Harshavardhan Reddy <peddolla.reddy@oss.qualcomm.com>
Link: https://patch.msgid.link/20260305160712.1263829-3-peddolla.reddy@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/pmsr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 44bd88c9ea66..50e8e19aa366 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -664,6 +664,7 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev)
 	}
 	spin_unlock_bh(&wdev->pmsr_lock);
 
+	cancel_work_sync(&wdev->pmsr_free_wk);
 	if (found)
 		cfg80211_pmsr_process_abort(wdev);
 
-- 
cgit v1.2.3


From d87c828daa7ead9763416f75cc416496969cf1dc Mon Sep 17 00:00:00 2001
From: Yifan Wu <wuyifan50@huawei.com>
Date: Thu, 5 Mar 2026 09:36:37 +0800
Subject: selftest/arm64: Fix sve2p1_sigill() to hwcap test

The FEAT_SVE2p1 is indicated by ID_AA64ZFR0_EL1.SVEver. However,
the BFADD requires the FEAT_SVE_B16B16, which is indicated by
ID_AA64ZFR0_EL1.B16B16. This could cause the test to incorrectly
fail on a CPU that supports FEAT_SVE2.1 but not FEAT_SVE_B16B16.

LD1Q Gather load quadwords which is decoded from SVE encodings and
implied by FEAT_SVE2p1.

Fixes: c5195b027d29 ("kselftest/arm64: Add SVE 2.1 to hwcap test")
Signed-off-by: Yifan Wu <wuyifan50@huawei.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 tools/testing/selftests/arm64/abi/hwcap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9d2df1f3e6bb..c2661a312fc9 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -475,8 +475,8 @@ static void sve2_sigill(void)
 
 static void sve2p1_sigill(void)
 {
-	/* BFADD Z0.H, Z0.H, Z0.H */
-	asm volatile(".inst 0x65000000" : : : "z0");
+	/* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */
+	asm volatile(".inst 0xC400A000" : : : "z0");
 }
 
 static void sve2p2_sigill(void)
-- 
cgit v1.2.3


From bb70589b67039e491dd60cf71272884e926a0f95 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 23 Jan 2026 22:59:54 +0000
Subject: arm64: dts: renesas: rzt2h-n2h-evk: Add ramp delay for SD0 card
 regulator

Add a ramp delay of 60 uV/us to the vqmmc_sdhi0 voltage regulator to
fix UHS-I SD card detection failures.

Measurements on CN78 pin 4 showed the actual voltage ramp time to be
21.86ms when switching between 3.3V and 1.8V. A 25ms ramp delay has
been configured to provide adequate margin. The calculation is based
on the voltage delta of 1.5V (3.3V - 1.8V):
  1500000 uV / 60 uV/us = 25000 us (25ms)

Prior to this patch, UHS-I cards failed to initialize with:

    mmc0: error -110 whilst initialising SD card

After this patch, UHS-I cards are properly detected on SD0:

    mmc0: new UHS-I speed SDR104 SDXC card at address aaaa
    mmcblk0: mmc0:aaaa SR64G 59.5 GiB

Fixes: d065453e5ee09 ("arm64: dts: renesas: rzt2h-rzn2h-evk: Enable SD card slot")
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260123225957.1007089-2-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi
index 510399febf29..f87c2492f414 100644
--- a/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzt2h-n2h-evk-common.dtsi
@@ -53,6 +53,7 @@
 		regulator-max-microvolt = <3300000>;
 		gpios-states = <0>;
 		states = <3300000 0>, <1800000 1>;
+		regulator-ramp-delay = <60>;
 	};
 #endif
 
-- 
cgit v1.2.3


From 5c03465ecf6a56b7b261df9594f0e10612f53a50 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 23 Jan 2026 22:59:57 +0000
Subject: arm64: dts: renesas: rzv2-evk-cn15-sd: Add ramp delay for SD0
 regulator

Set an appropriate ramp delay for the SD0 I/O voltage regulator in the
CN15 SD overlay to make UHS-I voltage switching reliable during card
initialization.

This issue was observed on the RZ/V2H EVK, while the same UHS-I cards
worked on the RZ/V2N EVK without problems. Adding the ramp delay makes
the behavior consistent and avoids SD init timeouts.

Before this change SD0 could fail with:

    mmc0: error -110 whilst initialising SD card

With the delay in place UHS-I cards enumerate correctly:

    mmc0: new UHS-I speed SDR104 SDXC card at address aaaa
    mmcblk0: mmc0:aaaa SR64G 59.5 GiB
     mmcblk0: p1

Fixes: 3d6c2bc7629c8 ("arm64: dts: renesas: Add CN15 eMMC and SD overlays for RZ/V2H and RZ/V2N EVKs")
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260123225957.1007089-5-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso
index 0af1e0a6c7f4..fc53c1aae3b5 100644
--- a/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso
+++ b/arch/arm64/boot/dts/renesas/rzv2-evk-cn15-sd.dtso
@@ -25,6 +25,7 @@
 		regulator-max-microvolt = <3300000>;
 		gpios-states = <0>;
 		states = <3300000 0>, <1800000 1>;
+		regulator-ramp-delay = <60>;
 	};
 };
 
-- 
cgit v1.2.3


From a3f34651de4287138c0da19ba321ad72622b4af3 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Tue, 3 Feb 2026 12:42:46 +0000
Subject: arm64: dts: renesas: r9a09g057: Remove wdt{0,2,3} nodes

The HW user manual for the Renesas RZ/V2H(P) SoC (a.k.a r9a09g057)
states that only WDT1 is supposed to be accessed by the CA55 cores.
WDT0 is supposed to be used by the CM33 core, WDT2 is supposed
to be used by the CR8 core 0, and WDT3 is supposed to be used
by the CR8 core 1.

Remove wdt{0,2,3} from the SoC specific device tree to make it
compliant with the specification from the HW manual.

This change is harmless as there are currently no users of the
wdt{0,2,3} device tree nodes, only the wdt1 node is actually used.

Fixes: 095105496e7d ("arm64: dts: renesas: r9a09g057: Add WDT0-WDT3 nodes")
Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260203124247.7320-3-fabrizio.castro.jz@renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r9a09g057.dtsi | 30 ------------------------------
 1 file changed, 30 deletions(-)

diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
index 80cba9fcfe7b..504c28386622 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
@@ -581,16 +581,6 @@
 			status = "disabled";
 		};
 
-		wdt0: watchdog@11c00400 {
-			compatible = "renesas,r9a09g057-wdt";
-			reg = <0 0x11c00400 0 0x400>;
-			clocks = <&cpg CPG_MOD 0x4b>, <&cpg CPG_MOD 0x4c>;
-			clock-names = "pclk", "oscclk";
-			resets = <&cpg 0x75>;
-			power-domains = <&cpg>;
-			status = "disabled";
-		};
-
 		wdt1: watchdog@14400000 {
 			compatible = "renesas,r9a09g057-wdt";
 			reg = <0 0x14400000 0 0x400>;
@@ -601,26 +591,6 @@
 			status = "disabled";
 		};
 
-		wdt2: watchdog@13000000 {
-			compatible = "renesas,r9a09g057-wdt";
-			reg = <0 0x13000000 0 0x400>;
-			clocks = <&cpg CPG_MOD 0x4f>, <&cpg CPG_MOD 0x50>;
-			clock-names = "pclk", "oscclk";
-			resets = <&cpg 0x77>;
-			power-domains = <&cpg>;
-			status = "disabled";
-		};
-
-		wdt3: watchdog@13000400 {
-			compatible = "renesas,r9a09g057-wdt";
-			reg = <0 0x13000400 0 0x400>;
-			clocks = <&cpg CPG_MOD 0x51>, <&cpg CPG_MOD 0x52>;
-			clock-names = "pclk", "oscclk";
-			resets = <&cpg 0x78>;
-			power-domains = <&cpg>;
-			status = "disabled";
-		};
-
 		rtc: rtc@11c00800 {
 			compatible = "renesas,r9a09g057-rtca3", "renesas,rz-rtca3";
 			reg = <0 0x11c00800 0 0x400>;
-- 
cgit v1.2.3


From b12985ceca18bcf67f176883175d544daad5e00e Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 13 Feb 2026 13:17:41 +0000
Subject: arm64: dts: renesas: r9a09g077: Fix CPG register region sizes

The CPG register regions were incorrectly sized.  Update them to match
the actual hardware specification:
  - First region (0x80280000): 0x1000 -> 0x10000 (64kiB)
  - Second region (0x81280000): 0x9000 -> 0x10000 (64kiB)

Fixes: d17b34744f5e4 ("arm64: dts: renesas: Add initial support for the Renesas RZ/T2H SoC")
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260213131742.3606334-2-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r9a09g077.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi
index 14d7fb6f8952..9d0b4d8d3d5b 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g077.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g077.dtsi
@@ -974,8 +974,8 @@
 
 		cpg: clock-controller@80280000 {
 			compatible = "renesas,r9a09g077-cpg-mssr";
-			reg = <0 0x80280000 0 0x1000>,
-			      <0 0x81280000 0 0x9000>;
+			reg = <0 0x80280000 0 0x10000>,
+			      <0 0x81280000 0 0x10000>;
 			clocks = <&extal_clk>;
 			clock-names = "extal";
 			#clock-cells = <2>;
-- 
cgit v1.2.3


From f459672cf3ffd3c062973838951418271aa2ceef Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Fri, 13 Feb 2026 13:17:42 +0000
Subject: arm64: dts: renesas: r9a09g087: Fix CPG register region sizes

The CPG register regions were incorrectly sized.  Update them to match
the actual hardware specification:
  - First region (0x80280000): 0x1000 -> 0x10000 (64kiB)
  - Second region (0x81280000): 0x9000 -> 0x10000 (64kiB)

Fixes: 4b3d31f0b81fe ("arm64: dts: renesas: Add initial SoC DTSI for the RZ/N2H SoC")
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260213131742.3606334-3-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r9a09g087.dtsi | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi
index 4a1339561332..d407c48f9966 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g087.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g087.dtsi
@@ -977,8 +977,8 @@
 
 		cpg: clock-controller@80280000 {
 			compatible = "renesas,r9a09g087-cpg-mssr";
-			reg = <0 0x80280000 0 0x1000>,
-			      <0 0x81280000 0 0x9000>;
+			reg = <0 0x80280000 0 0x10000>,
+			      <0 0x81280000 0 0x10000>;
 			clocks = <&extal_clk>;
 			clock-names = "extal";
 			#clock-cells = <2>;
-- 
cgit v1.2.3


From 6dcbb6f070cccabc6a13d640a5a84de581fdd761 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Mon, 2 Mar 2026 15:57:03 +0200
Subject: arm64: dts: renesas: rzg3s-smarc-som: Set bypass for Versa3 PLL2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The default settings for the Versa3 device on the Renesas RZ/G3S SMARC
SoM board have PLL2 disabled. PLL2 was later enabled together with audio
support, as it is required to support both 44.1 kHz and 48 kHz audio.

With PLL2 enabled, it was observed that Linux occasionally either hangs
during boot (the last log message being related to the I2C probe) or
randomly crashes. This was mainly reproducible on cold boots. During
debugging, it was also noticed that the Unicode replacement character (�)
sometimes appears on the serial console. Further investigation traced this
to the configuration applied through the Versa3 register at offset 0x1c,
which controls PLL enablement.

The appearance of the Unicode replacement character suggested an issue
with the SoC reference clock. The RZ/G3S reference clock is provided by
the Versa3 clock generator (REF output).

After checking with the Renesas Versa3 hardware team, it was found that
this is related to the PLL2 lock bit being set through the
renesas,settings DT property.

The PLL lock bit must be set to avoid unstable clock output from the PLL.
However, due to the Versa3 hardware design, when a PLL lock bit is set,
all outputs (including the REF clock) are temporarily disabled until the
configured PLLs become stable.

As an alternative, the bypass bit can be used. This does not interrupt the
PLL2 output or any other Versa3 outputs, but it may result in temporary
instability on PLL2 output while the configuration is applied. Since PLL2
feeds only the audio path and audio is not used during early boot, this is
acceptable and does not affect system boot.

Drop the PLL2 lock bit and set the bypass bit instead.

This has been tested with more than 1000 cold boots.

Fixes: a94253232b04 ("arm64: dts: renesas: rzg3s-smarc-som: Add versa3 clock generator node")
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260302135703.162601-1-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
index 982f17aafbc5..b45acfe6288a 100644
--- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi
@@ -162,7 +162,7 @@
 				       <100000000>;
 		renesas,settings = [
 		  80 00 11 19 4c 42 dc 2f 06 7d 20 1a 5f 1e f2 27
-		  00 40 00 00 00 00 00 00 06 0c 19 02 3f f0 90 86
+		  00 40 00 00 00 00 00 00 06 0c 19 02 3b f0 90 86
 		  a0 80 30 30 9c
 		];
 	};
-- 
cgit v1.2.3


From 85c2601e2c2feb60980c7ca23de28c49472f61f1 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 4 Mar 2026 17:29:01 +0100
Subject: arm64: dts: renesas: r8a78000: Fix out-of-range SPI interrupt numbers

SPI interrupts are in the range 0-987.  Extended SPI interrupts should
use GIC_ESPI, instead of abusing GIC_SPI with a manual offset of 4064.

Fixes: 63500d12cf76d003 ("arm64: dts: renesas: Add R8A78000 SoC support")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/1f9dd274720ea1b66617a5dd84f76c3efc829dc8.1772641415.git.geert+renesas@glider.be
---
 arch/arm64/boot/dts/renesas/r8a78000.dtsi | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/boot/dts/renesas/r8a78000.dtsi b/arch/arm64/boot/dts/renesas/r8a78000.dtsi
index 4c97298fa763..3e1c98903cea 100644
--- a/arch/arm64/boot/dts/renesas/r8a78000.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a78000.dtsi
@@ -698,7 +698,7 @@
 			compatible = "renesas,scif-r8a78000",
 				     "renesas,rcar-gen5-scif", "renesas,scif";
 			reg = <0 0xc0700000 0 0x40>;
-			interrupts = <GIC_SPI 4074 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 10 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -708,7 +708,7 @@
 			compatible = "renesas,scif-r8a78000",
 				     "renesas,rcar-gen5-scif", "renesas,scif";
 			reg = <0 0xc0704000 0 0x40>;
-			interrupts = <GIC_SPI 4075 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 11 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -718,7 +718,7 @@
 			compatible = "renesas,scif-r8a78000",
 				     "renesas,rcar-gen5-scif", "renesas,scif";
 			reg = <0 0xc0708000 0 0x40>;
-			interrupts = <GIC_SPI 4076 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 12 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -728,7 +728,7 @@
 			compatible = "renesas,scif-r8a78000",
 				     "renesas,rcar-gen5-scif", "renesas,scif";
 			reg = <0 0xc070c000 0 0x40>;
-			interrupts = <GIC_SPI 4077 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 13 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -738,7 +738,7 @@
 			compatible = "renesas,hscif-r8a78000",
 				     "renesas,rcar-gen5-hscif", "renesas,hscif";
 			reg = <0 0xc0710000 0 0x60>;
-			interrupts = <GIC_SPI 4078 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 14 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -748,7 +748,7 @@
 			compatible = "renesas,hscif-r8a78000",
 				     "renesas,rcar-gen5-hscif", "renesas,hscif";
 			reg = <0 0xc0714000 0 0x60>;
-			interrupts = <GIC_SPI 4079 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 15 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -758,7 +758,7 @@
 			compatible = "renesas,hscif-r8a78000",
 				     "renesas,rcar-gen5-hscif", "renesas,hscif";
 			reg = <0 0xc0718000 0 0x60>;
-			interrupts = <GIC_SPI 4080 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 16 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
@@ -768,7 +768,7 @@
 			compatible = "renesas,hscif-r8a78000",
 				     "renesas,rcar-gen5-hscif", "renesas,hscif";
 			reg = <0 0xc071c000 0 0x60>;
-			interrupts = <GIC_SPI 4081 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_ESPI 17 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&dummy_clk_sgasyncd4>, <&dummy_clk_sgasyncd4>, <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
 			status = "disabled";
-- 
cgit v1.2.3


From e825c79ef914bd55cf7c2476ddcfb2738eb689c3 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 27 Jan 2026 00:35:47 +0800
Subject: pinctrl: renesas: rzt2h: Fix device node leak in
 rzt2h_gpio_register()

When calling of_parse_phandle_with_fixed_args(), the caller is
responsible for calling of_node_put() to release the device node
reference.

In rzt2h_gpio_register(), the driver fails to call of_node_put() to
release the reference in of_args.np, which causes a memory leak.

Add the missing of_node_put() call to fix the leak.

Fixes: 34d4d093077a ("pinctrl: renesas: Add support for RZ/T2H")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260127-rzt2h-v1-1-86472e7421b8@gmail.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzt2h.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzt2h.c b/drivers/pinctrl/renesas/pinctrl-rzt2h.c
index 9949108a35bb..5e0586d45cb7 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzt2h.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzt2h.c
@@ -833,6 +833,7 @@ static int rzt2h_gpio_register(struct rzt2h_pinctrl *pctrl)
 	if (ret)
 		return dev_err_probe(dev, ret, "Unable to parse gpio-ranges\n");
 
+	of_node_put(of_args.np);
 	if (of_args.args[0] != 0 || of_args.args[1] != 0 ||
 	    of_args.args[2] != pctrl->data->n_port_pins)
 		return dev_err_probe(dev, -EINVAL,
-- 
cgit v1.2.3


From ebe7561e9b9203611cea72a764bc321ff308f737 Mon Sep 17 00:00:00 2001
From: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Date: Thu, 5 Feb 2026 12:39:30 +0200
Subject: pinctrl: renesas: rzt2h: Fix invalid wait context

The rzt2h_gpio_get_direction() function is called from
gpiod_get_direction(), which ends up being used within the __setup_irq()
call stack when requesting an interrupt.

__setup_irq() holds a raw_spinlock_t with IRQs disabled, which creates
an atomic context. spinlock_t cannot be used within atomic context
when PREEMPT_RT is enabled, since it may become a sleeping lock.

An "[ BUG: Invalid wait context ]" splat is observed when running with
CONFIG_PROVE_LOCKING enabled, describing exactly the aforementioned call
stack.

__setup_irq() needs to hold a raw_spinlock_t with IRQs disabled to
serialize access against a concurrent hard interrupt.

Switch to raw_spinlock_t to fix this.

Fixes: 829dde3369a9 ("pinctrl: renesas: rzt2h: Add GPIO IRQ chip to handle interrupts")
Signed-off-by: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260205103930.666051-1-cosmin-gabriel.tanislav.xa@renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rzt2h.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rzt2h.c b/drivers/pinctrl/renesas/pinctrl-rzt2h.c
index 5e0586d45cb7..5927744c7a96 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzt2h.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzt2h.c
@@ -85,7 +85,7 @@ struct rzt2h_pinctrl {
 	struct gpio_chip		gpio_chip;
 	struct pinctrl_gpio_range	gpio_range;
 	DECLARE_BITMAP(used_irqs, RZT2H_INTERRUPTS_NUM);
-	spinlock_t			lock; /* lock read/write registers */
+	raw_spinlock_t			lock; /* lock read/write registers */
 	struct mutex			mutex; /* serialize adding groups and functions */
 	bool				safety_port_enabled;
 	atomic_t			wakeup_path;
@@ -145,7 +145,7 @@ static void rzt2h_pinctrl_set_pfc_mode(struct rzt2h_pinctrl *pctrl,
 	u64 reg64;
 	u16 reg16;
 
-	guard(spinlock_irqsave)(&pctrl->lock);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
 
 	/* Set pin to 'Non-use (Hi-Z input protection)'  */
 	reg16 = rzt2h_pinctrl_readw(pctrl, port, PM(port));
@@ -474,7 +474,7 @@ static int rzt2h_gpio_request(struct gpio_chip *chip, unsigned int offset)
 	if (ret)
 		return ret;
 
-	guard(spinlock_irqsave)(&pctrl->lock);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
 
 	/* Select GPIO mode in PMC Register */
 	rzt2h_pinctrl_set_gpio_en(pctrl, port, bit, true);
@@ -487,7 +487,7 @@ static void rzt2h_gpio_set_direction(struct rzt2h_pinctrl *pctrl, u32 port,
 {
 	u16 reg;
 
-	guard(spinlock_irqsave)(&pctrl->lock);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
 
 	reg = rzt2h_pinctrl_readw(pctrl, port, PM(port));
 	reg &= ~PM_PIN_MASK(bit);
@@ -509,7 +509,7 @@ static int rzt2h_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
 	if (ret)
 		return ret;
 
-	guard(spinlock_irqsave)(&pctrl->lock);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
 
 	if (rzt2h_pinctrl_readb(pctrl, port, PMC(port)) & BIT(bit)) {
 		/*
@@ -547,7 +547,7 @@ static int rzt2h_gpio_set(struct gpio_chip *chip, unsigned int offset,
 	u8 bit = RZT2H_PIN_ID_TO_PIN(offset);
 	u8 reg;
 
-	guard(spinlock_irqsave)(&pctrl->lock);
+	guard(raw_spinlock_irqsave)(&pctrl->lock);
 
 	reg = rzt2h_pinctrl_readb(pctrl, port, P(port));
 	if (value)
@@ -965,7 +965,7 @@ static int rzt2h_pinctrl_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	spin_lock_init(&pctrl->lock);
+	raw_spin_lock_init(&pctrl->lock);
 	mutex_init(&pctrl->mutex);
 	platform_set_drvdata(pdev, pctrl);
 
-- 
cgit v1.2.3


From 93d0fcdddc9e7be9d4f42acbe57bc90dbb0fe75d Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 5 Mar 2026 12:40:56 -0800
Subject: cxl/acpi: Fix CXL_ACPI and CXL_PMEM Kconfig tristate mismatch

Commit e7e222ad73d9 ("cxl: Move devm_cxl_add_nvdimm_bridge() to
cxl_pmem.ko") moves devm_cxl_add_nvdimm_bridge() into the cxl_pmem file,
which has independent config compile options for built-in or module. The
call from cxl_acpi_probe() is guarded by IS_ENABLED(CONFIG_CXL_PMEM),
which evaluates to true for both =y and =m.

When CONFIG_CXL_PMEM=m, a built-in cxl_acpi attempts to reference a
symbol exported by a module, which fails to link. CXL_PMEM cannot simply
be promoted to =y in this configuration because it depends on LIBNVDIMM,
which may itself be =m.

Add a Kconfig dependency to prevent CXL_ACPI from being built-in when
CXL_PMEM is a module. This contrains CXL_ACPI to =m when CXL_PMEM=m,
while still allowing CXL_ACPI to be freely configured when CXL_PMEM is
either built-in or disabled.

[ dj: Fix up commit reference formatting. ]

Fixes: e7e222ad73d9 ("cxl: Move devm_cxl_add_nvdimm_bridge() to cxl_pmem.ko")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260305204057.1516948-1-kbusch@meta.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig
index 4589bf11d3fe..80aeb0d556bd 100644
--- a/drivers/cxl/Kconfig
+++ b/drivers/cxl/Kconfig
@@ -59,6 +59,7 @@ config CXL_ACPI
 	tristate "CXL ACPI: Platform Support"
 	depends on ACPI
 	depends on ACPI_NUMA
+	depends on CXL_PMEM || !CXL_PMEM
 	default CXL_BUS
 	select ACPI_TABLE_LIB
 	select ACPI_HMAT
-- 
cgit v1.2.3


From f9fb44b0ecefc1f218db56661ed66d4e8d67317d Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:09 -0800
Subject: objtool/klp: Fix detection of corrupt static branch/call entries

Patching a function which references a static key living in a kernel
module is unsupported due to ordering issues inherent to late module
patching:

  1) Load a livepatch module which has a __jump_table entry which needs
     a klp reloc to reference static key K which lives in module M.

  2) The __jump_table klp reloc does *not* get resolved because module M
     is not yet loaded.

  3) jump_label_add_module() corrupts memory (or causes a panic) when
     dereferencing the uninitialized pointer to key K.

validate_special_section_klp_reloc() intends to prevent that from ever
happening by catching it at build time.  However, it incorrectly assumes
the special section entry's reloc symbol references have already been
converted from section symbols to object symbols, causing the validation
to miss corruption in extracted static branch/call table entries.

Make sure the references have been properly converted before doing the
validation.

Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files")
Reported-by: Song Liu <song@kernel.org>
Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/124ad747b751df0df1725eff89de8332e3fb26d6.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index 9f1f4011eb9c..d94632e80955 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1364,6 +1364,9 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		const char *sym_modname;
 		struct export *export;
 
+		if (convert_reloc_sym(e->patched, reloc))
+			continue;
+
 		/* Static branch/call keys are always STT_OBJECT */
 		if (reloc->sym->type != STT_OBJECT) {
 
-- 
cgit v1.2.3


From e476bb277cf91b7ac3ea803ec78a4f0791bddec3 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:10 -0800
Subject: objtool/klp: Disable unsupported pr_debug() usage

Instead of erroring out on unsupported pr_debug() (e.g., when patching a
module), issue a warning and make it inert, similar to how unsupported
tracepoints are currently handled.

Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/3a7db3a5b7d4abf9b2534803a74e2e7231322738.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index d94632e80955..9ff65b01882b 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1334,18 +1334,18 @@ static bool should_keep_special_sym(struct elf *elf, struct symbol *sym)
  * be applied after static branch/call init, resulting in code corruption.
  *
  * Validate a special section entry to avoid that.  Note that an inert
- * tracepoint is harmless enough, in that case just skip the entry and print a
- * warning.  Otherwise, return an error.
+ * tracepoint or pr_debug() is harmless enough, in that case just skip the
+ * entry and print a warning.  Otherwise, return an error.
  *
- * This is only a temporary limitation which will be fixed when livepatch adds
- * support for submodules: fully self-contained modules which are embedded in
- * the top-level livepatch module's data and which can be loaded on demand when
- * their corresponding to-be-patched module gets loaded.  Then klp relocs can
- * be retired.
+ * TODO: This is only a temporary limitation which will be fixed when livepatch
+ * adds support for submodules: fully self-contained modules which are embedded
+ * in the top-level livepatch module's data and which can be loaded on demand
+ * when their corresponding to-be-patched module gets loaded.  Then klp relocs
+ * can be retired.
  *
  * Return:
  *   -1: error: validation failed
- *    1: warning: tracepoint skipped
+ *    1: warning: disabled tracepoint or pr_debug()
  *    0: success
  */
 static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym)
@@ -1403,6 +1403,13 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 				continue;
 			}
 
+			if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) {
+				WARN("%s: disabling unsupported pr_debug()",
+				     code_sym->name);
+				ret = 1;
+				continue;
+			}
+
 			ERROR("%s+0x%lx: unsupported static branch key %s.  Use static_key_enabled() instead",
 			      code_sym->name, code_offset, reloc->sym->name);
 			return -1;
-- 
cgit v1.2.3


From 11c2adcd1fa2a9380a507db1e57c8542bfc81827 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Feb 2026 13:50:11 -0800
Subject: objtool/klp: Avoid NULL pointer dereference when printing code symbol
 name

Fix a hypothetical NULL pointer defereference of the 'code_sym'
variable.  In theory this should never happen.

Reviewed-and-tested-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/64116517bc93851a98fe366ea0a4d807f4c70aab.1770759954.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index 9ff65b01882b..a3198a63c2f0 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -1352,7 +1352,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 {
 	bool static_branch = !strcmp(sym->sec->name, "__jump_table");
 	bool static_call   = !strcmp(sym->sec->name, ".static_call_sites");
-	struct symbol *code_sym = NULL;
+	const char *code_sym = NULL;
 	unsigned long code_offset = 0;
 	struct reloc *reloc;
 	int ret = 0;
@@ -1372,7 +1372,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 
 			/* Save code location which can be printed below */
 			if (reloc->sym->type == STT_FUNC && !code_sym) {
-				code_sym = reloc->sym;
+				code_sym = reloc->sym->name;
 				code_offset = reloc_addend(reloc);
 			}
 
@@ -1395,23 +1395,26 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		if (!strcmp(sym_modname, "vmlinux"))
 			continue;
 
+		if (!code_sym)
+			code_sym = "<unknown>";
+
 		if (static_branch) {
 			if (strstarts(reloc->sym->name, "__tracepoint_")) {
 				WARN("%s: disabling unsupported tracepoint %s",
-				     code_sym->name, reloc->sym->name + 13);
+				     code_sym, reloc->sym->name + 13);
 				ret = 1;
 				continue;
 			}
 
 			if (strstr(reloc->sym->name, "__UNIQUE_ID_ddebug_")) {
 				WARN("%s: disabling unsupported pr_debug()",
-				     code_sym->name);
+				     code_sym);
 				ret = 1;
 				continue;
 			}
 
 			ERROR("%s+0x%lx: unsupported static branch key %s.  Use static_key_enabled() instead",
-			      code_sym->name, code_offset, reloc->sym->name);
+			      code_sym, code_offset, reloc->sym->name);
 			return -1;
 		}
 
@@ -1422,7 +1425,7 @@ static int validate_special_section_klp_reloc(struct elfs *e, struct symbol *sym
 		}
 
 		ERROR("%s()+0x%lx: unsupported static call key %s.  Use KLP_STATIC_CALL() instead",
-		      code_sym->name, code_offset, reloc->sym->name);
+		      code_sym, code_offset, reloc->sym->name);
 		return -1;
 	}
 
-- 
cgit v1.2.3


From 32234049107d012703d50547e815f198f147968b Mon Sep 17 00:00:00 2001
From: HONG Yifan <elsk@google.com>
Date: Tue, 3 Mar 2026 01:03:39 +0000
Subject: objtool: Use HOSTCFLAGS for HAVE_XXHASH test

Previously, HAVE_XXHASH is tested by invoking HOSTCC without HOSTCFLAGS.

Consider the following scenario:

- The host machine has libxxhash installed
- We build the kernel with HOSTCFLAGS containing a --sysroot that does
  not have xxhash.h (for hermetic builds)

In this case, HAVE_XXHASH is set to y, but when it builds objtool with
HOSTCFLAGS, because the --sysroot does not contain xxhash.h, the
following error is raised:

<...>/common/tools/objtool/include/objtool/checksum_types.h:12:10: fatal error: 'xxhash.h' file not found
   12 | #include <xxhash.h>
      |          ^~~~~~~~~~

To resolve the error, we test HAVE_XXHASH by invoking HOSTCC with
HOSTCFLAGS.

Signed-off-by: HONG Yifan <elsk@google.com>
Reviewed-by: Carlos Llamas <cmllamas@google.com>
Link: https://patch.msgid.link/20260303010340.306164-1-elsk@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 6964175abdfd..b8b8529f8ea9 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -13,7 +13,7 @@ endif
 
 ifeq ($(ARCH_HAS_KLP),y)
 	HAVE_XXHASH = $(shell printf "$(pound)include <xxhash.h>\nXXH3_state_t *state;int main() {}" | \
-		      $(HOSTCC) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n)
+		      $(HOSTCC) $(HOSTCFLAGS) -xc - -o /dev/null -lxxhash 2> /dev/null && echo y || echo n)
 	ifeq ($(HAVE_XXHASH),y)
 		BUILD_KLP	 := y
 		LIBXXHASH_CFLAGS := $(shell $(HOSTPKG_CONFIG) libxxhash --cflags 2>/dev/null) \
-- 
cgit v1.2.3


From 356e4b2f5b80f757965f3f4d0219c81fca91b6f2 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Wed, 4 Mar 2026 19:31:20 -0800
Subject: objtool: Fix data alignment in elf_add_data()

Any data added to a section needs to be aligned in accordance with the
section's sh_addralign value.  Particularly strings added to a .str1.8
section.  Otherwise you may get some funky strings.

Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files")
Link: https://patch.msgid.link/d962fc0ca24fa0825cca8dad71932dccdd9312a9.1772681234.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 2c02c7b49265..3da90686350d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -1375,7 +1375,7 @@ void *elf_add_data(struct elf *elf, struct section *sec, const void *data, size_
 		memcpy(sec->data->d_buf, data, size);
 
 	sec->data->d_size = size;
-	sec->data->d_align = 1;
+	sec->data->d_align = sec->sh.sh_addralign;
 
 	offset = ALIGN(sec->sh.sh_size, sec->sh.sh_addralign);
 	sec->sh.sh_size = offset + size;
-- 
cgit v1.2.3


From 1fd1dc41724319406b0aff221a352a400b0ddfc5 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Wed, 4 Mar 2026 19:31:21 -0800
Subject: objtool: Fix ERROR_INSN() error message

Confusingly, ERROR_INSN() shows "warning:" instead of "error:".  Fix that.

Link: https://patch.msgid.link/c4fe793bb3d23fac2c636b2511059af1158410e2.1772681234.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/include/objtool/warn.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h
index 2b27b54096b8..fa8b7d292e83 100644
--- a/tools/objtool/include/objtool/warn.h
+++ b/tools/objtool/include/objtool/warn.h
@@ -107,7 +107,7 @@ static inline char *offstr(struct section *sec, unsigned long offset)
 #define ERROR_ELF(format, ...) __WARN_ELF(ERROR_STR, format, ##__VA_ARGS__)
 #define ERROR_GLIBC(format, ...) __WARN_GLIBC(ERROR_STR, format, ##__VA_ARGS__)
 #define ERROR_FUNC(sec, offset, format, ...) __WARN_FUNC(ERROR_STR, sec, offset, format, ##__VA_ARGS__)
-#define ERROR_INSN(insn, format, ...) WARN_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__)
+#define ERROR_INSN(insn, format, ...) ERROR_FUNC(insn->sec, insn->offset, format, ##__VA_ARGS__)
 
 extern bool debug;
 extern int indent;
-- 
cgit v1.2.3


From 7fe44c4388146bdbb3c5932d81a26d9fa0fd3ec9 Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Fri, 6 Mar 2026 10:49:18 +0000
Subject: bpf: drop kthread_exit from noreturn_deny

kthread_exit became a macro to do_exit in commit 28aaa9c39945
("kthread: consolidate kthread exit paths to prevent use-after-free"),
so there is no kthread_exit function BTF ID to resolve. Remove it from
noreturn_deny to avoid resolve_btfids unresolved symbol warnings.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/bpf/verifier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 401d6c4960ec..8db79e593156 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25261,7 +25261,6 @@ BTF_ID(func, __x64_sys_exit_group)
 BTF_ID(func, do_exit)
 BTF_ID(func, do_group_exit)
 BTF_ID(func, kthread_complete_and_exit)
-BTF_ID(func, kthread_exit)
 BTF_ID(func, make_task_dead)
 BTF_SET_END(noreturn_deny)
 
-- 
cgit v1.2.3


From a4e8473b775160f3ce978f621cf8dea2c7250433 Mon Sep 17 00:00:00 2001
From: Yeoreum Yun <yeoreum.yun@arm.com>
Date: Wed, 4 Mar 2026 12:09:53 +0000
Subject: firmware: arm_ffa: Remove vm_id argument in ffa_rxtx_unmap()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to the FF-A specification (DEN0077, v1.1, §13.7), when
FFA_RXTX_UNMAP is invoked from any instance other than non-secure
physical, the w1 register must be zero (MBZ). If a non-zero value is
supplied in this context, the SPMC must return FFA_INVALID_PARAMETER.

The Arm FF-A driver operates exclusively as a guest or non-secure
physical instance where the partition ID is always zero and is not
invoked from a hypervisor context where w1 carries a VM ID. In this
execution model, the partition ID observed by the driver is always zero,
and passing a VM ID is unnecessary and potentially invalid.

Remove the vm_id parameter from ffa_rxtx_unmap() and ensure that the
SMC call is issued with w1 implicitly zeroed, as required by the
specification. This prevents invalid parameter errors and aligns the
implementation with the defined FF-A ABI behavior.

Fixes: 3bbfe9871005 ("firmware: arm_ffa: Add initial Arm FFA driver support")
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Message-Id: <20260304120953.847671-1-yeoreum.yun@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@kernel.org>
---
 drivers/firmware/arm_ffa/driver.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 12a625387d6e..f2f94d4d533e 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -205,12 +205,12 @@ static int ffa_rxtx_map(phys_addr_t tx_buf, phys_addr_t rx_buf, u32 pg_cnt)
 	return 0;
 }
 
-static int ffa_rxtx_unmap(u16 vm_id)
+static int ffa_rxtx_unmap(void)
 {
 	ffa_value_t ret;
 
 	invoke_ffa_fn((ffa_value_t){
-		      .a0 = FFA_RXTX_UNMAP, .a1 = PACK_TARGET_INFO(vm_id, 0),
+		      .a0 = FFA_RXTX_UNMAP,
 		      }, &ret);
 
 	if (ret.a0 == FFA_ERROR)
@@ -2097,7 +2097,7 @@ static int __init ffa_init(void)
 
 	pr_err("failed to setup partitions\n");
 	ffa_notifications_cleanup();
-	ffa_rxtx_unmap(drv_info->vm_id);
+	ffa_rxtx_unmap();
 free_pages:
 	if (drv_info->tx_buffer)
 		free_pages_exact(drv_info->tx_buffer, rxtx_bufsz);
@@ -2112,7 +2112,7 @@ static void __exit ffa_exit(void)
 {
 	ffa_notifications_cleanup();
 	ffa_partitions_cleanup();
-	ffa_rxtx_unmap(drv_info->vm_id);
+	ffa_rxtx_unmap();
 	free_pages_exact(drv_info->tx_buffer, drv_info->rxtx_bufsz);
 	free_pages_exact(drv_info->rx_buffer, drv_info->rxtx_bufsz);
 	kfree(drv_info);
-- 
cgit v1.2.3


From 8ce8d0524c136f60a1bddb0951db2999342d7217 Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Fri, 6 Mar 2026 10:30:51 +0000
Subject: sched_ext: Documentation: Mention scheduling class precedence

Mention the scheduling class precedence of fair and sched_ext to
clear up how sched_ext partial mode works.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/scheduler/sched-ext.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index 9e2882d937b4..100d45963781 100644
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -58,7 +58,8 @@ in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and
 However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is
 set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled
 by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and
-``SCHED_IDLE`` policies are scheduled by the fair-class scheduler.
+``SCHED_IDLE`` policies are scheduled by the fair-class scheduler which has
+higher sched_class precedence than ``SCHED_EXT``.
 
 Terminating the sched_ext scheduler program, triggering `SysRq-S`, or
 detection of any internal error including stalled runnable tasks aborts the
-- 
cgit v1.2.3


From 98c790b100764102d877e9339471b8c4c9233f2c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 6 Mar 2026 02:46:42 -0800
Subject: workqueue: Rename show_cpu_pool{s,}_hog{s,}() to reflect broadened
 scope
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

show_cpu_pool_hog() and show_cpu_pools_hogs() no longer only dump CPU
hogs — since commit 8823eaef45da ("workqueue: Show all busy workers in
stall diagnostics"), they dump every in-flight worker in the pool's
busy_hash.

Rename them to show_cpu_pool_busy_workers() and
show_cpu_pools_busy_workers() to accurately describe what they do.

Also fix the pr_info() message to say "stalled worker pools" instead of
"stalled CPU-bound worker pools", since sleeping/blocked workers are now
included.

No functional change.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 09b9ad78d566..b77119d71641 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7587,7 +7587,7 @@ MODULE_PARM_DESC(panic_on_stall_time, "Panic if stall exceeds this many seconds
  * wait_event_idle() with PF_WQ_WORKER cleared) can stall the pool just as
  * effectively as a CPU-bound one, so dump every in-flight worker.
  */
-static void show_cpu_pool_hog(struct worker_pool *pool)
+static void show_cpu_pool_busy_workers(struct worker_pool *pool)
 {
 	struct worker *worker;
 	unsigned long irq_flags;
@@ -7612,18 +7612,18 @@ static void show_cpu_pool_hog(struct worker_pool *pool)
 	raw_spin_unlock_irqrestore(&pool->lock, irq_flags);
 }
 
-static void show_cpu_pools_hogs(void)
+static void show_cpu_pools_busy_workers(void)
 {
 	struct worker_pool *pool;
 	int pi;
 
-	pr_info("Showing backtraces of busy workers in stalled CPU-bound worker pools:\n");
+	pr_info("Showing backtraces of busy workers in stalled worker pools:\n");
 
 	rcu_read_lock();
 
 	for_each_pool(pool, pi) {
 		if (pool->cpu_stall)
-			show_cpu_pool_hog(pool);
+			show_cpu_pool_busy_workers(pool);
 
 	}
 
@@ -7720,7 +7720,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		show_all_workqueues();
 
 	if (cpu_pool_stall)
-		show_cpu_pools_hogs();
+		show_cpu_pools_busy_workers();
 
 	if (lockup_detected)
 		panic_on_wq_watchdog(max_stall_time);
-- 
cgit v1.2.3


From 1dde502587657045b267f179d7a1ecc7b8a1a265 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Fri, 6 Mar 2026 04:50:55 +0000
Subject: sched_ext: Use READ_ONCE() for scx_slice_bypass_us in scx_bypass()

Commit 0927780c90ce ("sched_ext: Use READ_ONCE() for lock-free reads
of module param variables") annotated the plain reads of
scx_slice_bypass_us and scx_bypass_lb_intv_us in bypass_lb_cpu(), but
missed a third site in scx_bypass():

  WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC);

scx_slice_bypass_us is a module parameter writable via sysfs in
process context through set_slice_us() -> param_set_uint_minmax(),
which performs a plain store without holding bypass_lock. scx_bypass()
reads the variable under bypass_lock, but since the writer does not
take that lock, the two accesses are concurrent.

WRITE_ONCE() only applies volatile semantics to the store of
scx_slice_dfl -- the val expression containing scx_slice_bypass_us is
evaluated as a plain read, providing no protection against concurrent
writes.

Wrap the read with READ_ONCE() to complete the annotation started by
commit 0927780c90ce and make the access KCSAN-clean, consistent with
the existing READ_ONCE(scx_slice_bypass_us) in bypass_lb_cpu().

Signed-off-by: David Carlier <devnexen@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 10866bfb88bf..f323df7be180 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4137,7 +4137,7 @@ static void scx_bypass(bool bypass)
 		WARN_ON_ONCE(scx_bypass_depth <= 0);
 		if (scx_bypass_depth != 1)
 			goto unlock;
-		WRITE_ONCE(scx_slice_dfl, scx_slice_bypass_us * NSEC_PER_USEC);
+		WRITE_ONCE(scx_slice_dfl, READ_ONCE(scx_slice_bypass_us) * NSEC_PER_USEC);
 		bypass_timestamp = ktime_get_ns();
 		if (sch)
 			scx_add_event(sch, SCX_EV_BYPASS_ACTIVATE, 1);
-- 
cgit v1.2.3


From ca174c705db52db3cc842e754fd25a5f50eb702d Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 5 Mar 2026 14:53:29 -0500
Subject: cgroup/cpuset: Call rebuild_sched_domains() directly in hotplug

Besides deferring the call to housekeeping_update(), commit 6df415aa46ec
("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug
to workqueue") also defers the rebuild_sched_domains() call to
the workqueue. So a new offline CPU may still be in a sched domain
or new online CPU not showing up in the sched domains for a short
transition period. That could be a problem in some corner cases and
can be the cause of a reported test failure[1]. Fix it by calling
rebuild_sched_domains_cpuslocked() directly in hotplug as before. If
isolated partition invalidation or recreation is being done, the
housekeeping_update() call to update the housekeeping cpumasks will
still be deferred to a workqueue.

In commit 3bfe47967191 ("cgroup/cpuset: Move
housekeeping_update()/rebuild_sched_domains() together"),
housekeeping_update() is called before rebuild_sched_domains() because
it needs to access the HK_TYPE_DOMAIN housekeeping cpumask. That is now
changed to use the static HK_TYPE_DOMAIN_BOOT cpumask as HK_TYPE_DOMAIN
cpumask is now changeable at run time.  As a result, we can move the
rebuild_sched_domains() call before housekeeping_update() with
the slight advantage that it will be done in the same cpus_read_lock
critical section without the possibility of interference by a concurrent
cpu hot add/remove operation.

As it doesn't make sense to acquire cpuset_mutex/cpuset_top_mutex after
calling housekeeping_update() and immediately release them again, move
the cpuset_full_unlock() operation inside update_hk_sched_domains()
and rename it to cpuset_update_sd_hk_unlock() to signify that it will
release the full set of locks.

[1] https://lore.kernel.org/lkml/1a89aceb-48db-4edd-a730-b445e41221fe@nvidia.com

Fixes: 6df415aa46ec ("cgroup/cpuset: Defer housekeeping_update() calls from CPU hotplug to workqueue")
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Chen Ridong <chenridong@huaweicloud.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 59 ++++++++++++++++++++++++++------------------------
 1 file changed, 31 insertions(+), 28 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index e200de7c60b6..d21868455341 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -879,7 +879,7 @@ generate_doms:
 	/*
 	 * Cgroup v2 doesn't support domain attributes, just set all of them
 	 * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a
-	 * subset of HK_TYPE_DOMAIN housekeeping CPUs.
+	 * subset of HK_TYPE_DOMAIN_BOOT housekeeping CPUs.
 	 */
 	for (i = 0; i < ndoms; i++) {
 		/*
@@ -888,7 +888,7 @@ generate_doms:
 		 */
 		if (!csa || csa[i] == &top_cpuset)
 			cpumask_and(doms[i], top_cpuset.effective_cpus,
-				    housekeeping_cpumask(HK_TYPE_DOMAIN));
+				    housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT));
 		else
 			cpumask_copy(doms[i], csa[i]->effective_cpus);
 		if (dattr)
@@ -1329,17 +1329,22 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus)
 }
 
 /*
- * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains
+ * cpuset_update_sd_hk_unlock - Rebuild sched domains, update HK & unlock
  *
- * Update housekeeping cpumasks and rebuild sched domains if necessary.
- * This should be called at the end of cpuset or hotplug actions.
+ * Update housekeeping cpumasks and rebuild sched domains if necessary and
+ * then do a cpuset_full_unlock().
+ * This should be called at the end of cpuset operation.
  */
-static void update_hk_sched_domains(void)
+static void cpuset_update_sd_hk_unlock(void)
+	__releases(&cpuset_mutex)
+	__releases(&cpuset_top_mutex)
 {
+	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
+	if (force_sd_rebuild)
+		rebuild_sched_domains_locked();
+
 	if (update_housekeeping) {
-		/* Updating HK cpumasks implies rebuild sched domains */
 		update_housekeeping = false;
-		force_sd_rebuild = true;
 		cpumask_copy(isolated_hk_cpus, isolated_cpus);
 
 		/*
@@ -1350,22 +1355,19 @@ static void update_hk_sched_domains(void)
 		mutex_unlock(&cpuset_mutex);
 		cpus_read_unlock();
 		WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus));
-		cpus_read_lock();
-		mutex_lock(&cpuset_mutex);
+		mutex_unlock(&cpuset_top_mutex);
+	} else {
+		cpuset_full_unlock();
 	}
-	/* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */
-	if (force_sd_rebuild)
-		rebuild_sched_domains_locked();
 }
 
 /*
- * Work function to invoke update_hk_sched_domains()
+ * Work function to invoke cpuset_update_sd_hk_unlock()
  */
 static void hk_sd_workfn(struct work_struct *work)
 {
 	cpuset_full_lock();
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 }
 
 /**
@@ -3230,8 +3232,7 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 
 	free_cpuset(trialcs);
 out_unlock:
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 	if (of_cft(of)->private == FILE_MEMLIST)
 		schedule_flush_migrate_mm();
 	return retval ?: nbytes;
@@ -3338,8 +3339,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	cpuset_full_lock();
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 	return retval ?: nbytes;
 }
 
@@ -3513,8 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css)
 	/* Reset valid partition back to member */
 	if (is_partition_valid(cs))
 		update_prstate(cs, PRS_MEMBER);
-	update_hk_sched_domains();
-	cpuset_full_unlock();
+	cpuset_update_sd_hk_unlock();
 }
 
 static void cpuset_css_free(struct cgroup_subsys_state *css)
@@ -3923,11 +3922,13 @@ static void cpuset_handle_hotplug(void)
 		rcu_read_unlock();
 	}
 
-
 	/*
-	 * Queue a work to call housekeeping_update() & rebuild_sched_domains()
-	 * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping
-	 * cpumask can correctly reflect what is in isolated_cpus.
+	 * rebuild_sched_domains() will always be called directly if needed
+	 * to make sure that newly added or removed CPU will be reflected in
+	 * the sched domains. However, if isolated partition invalidation
+	 * or recreation is being done (update_housekeeping set), a work item
+	 * will be queued to call housekeeping_update() to update the
+	 * corresponding housekeeping cpumasks after some slight delay.
 	 *
 	 * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that
 	 * is still pending. Before the pending bit is cleared, the work data
@@ -3936,8 +3937,10 @@ static void cpuset_handle_hotplug(void)
 	 * previously queued work. Since hk_sd_workfn() doesn't use the work
 	 * item at all, this is not a problem.
 	 */
-	if (update_housekeeping || force_sd_rebuild)
-		queue_work(system_unbound_wq, &hk_sd_work);
+	if (force_sd_rebuild)
+		rebuild_sched_domains_cpuslocked();
+	if (update_housekeeping)
+		queue_work(system_dfl_wq, &hk_sd_work);
 
 	free_tmpmasks(ptmp);
 }
-- 
cgit v1.2.3


From 0b2758f48f22b173963f39e553d0ecd05f3b4433 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 6 Mar 2026 09:10:36 -0800
Subject: Require (reasonably) normal mappings for MADV_DOFORK

This came up as a result of the tracing fix pull request, and commit
e39bb9e02b68 ("tracing: Fix WARN_ON in tracing_buffers_mmap_close") in
particular.

The use of MADV_DOFORK confused the ring buffer mapping reference
counting just because it was unexpected, since the mapping was
originally done with VM_DONTCOPY.

The tracing code may well be the only case of this (and fixed it all by
just using the mmap open callback to unconfuse itself), but it's just
strange that we allow MADV_DOFORK on special mappings where the kernel
has set the "don't copy this" bit.

The code already disallowed it for VM_IO mappings (going back to the
original commit f822566165dd: "madvise MADV_DONTFORK/MADV_DOFORK"), so
just extend it to any of the VM_SPECIAL cases (which includes
VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP in addition to VM_IO).

We could also allow MADV_DOFORK only on mappings that had been marked
DONTFORK by the user.  But that would require us to track that
(presumably with another VM_xyz bit), so let's just do this trivial and
straightforward modifications.

If anybody notices, Lorenzo will be boarding Flying Pig Airlines.

Suggested-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Link: https://lore.kernel.org/all/a8907468-d7e9-4727-af28-66d905093230@kernel.org/
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/madvise.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index c0370d9b4e23..dbb69400786d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1389,7 +1389,7 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior)
 		new_flags |= VM_DONTCOPY;
 		break;
 	case MADV_DOFORK:
-		if (new_flags & VM_IO)
+		if (new_flags & VM_SPECIAL)
 			return -EINVAL;
 		new_flags &= ~VM_DONTCOPY;
 		break;
-- 
cgit v1.2.3


From 457965c13f0837a289c9164b842d0860133f6274 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 5 Mar 2026 11:33:39 -0800
Subject: tracing: Add NULL pointer check to trigger_data_free()

If trigger_data_alloc() fails and returns NULL, event_hist_trigger_parse()
jumps to the out_free error path. While kfree() safely handles a NULL
pointer, trigger_data_free() does not. This causes a NULL pointer
dereference in trigger_data_free() when evaluating
data->cmd_ops->set_filter.

Fix the problem by adding a NULL pointer check to trigger_data_free().

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Cc: Miaoqian Lin <linmq006@gmail.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://patch.msgid.link/20260305193339.2810953-1-linux@roeck-us.net
Fixes: 0550069cc25f ("tracing: Properly process error handling in event_hist_trigger_parse()")
Assisted-by: Gemini:gemini-3.1-pro
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_trigger.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index fecbd679d432..d5230b759a2d 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -50,6 +50,9 @@ static int trigger_kthread_fn(void *ignore)
 
 void trigger_data_free(struct event_trigger_data *data)
 {
+	if (!data)
+		return;
+
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 
-- 
cgit v1.2.3


From e4eb11b34d6c84f398d8f08d7cb4d6c38e739dd2 Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Sat, 7 Mar 2026 00:32:38 +0800
Subject: drm/msm/dsi: fix pclk rate calculation for bonded dsi

Recently, we round up new_hdisplay once at most, for bonded dsi, we
may need twice, since they are independent links, we should round up
each half separately. This also aligns with the hdisplay we program
later in dsi_timing_setup()

Example:
	full_hdisplay = 1904, dsc_bpp = 8, bpc = 8
	new_full_hdisplay = DIV_ROUND_UP(1904 * 8, 8 * 3) = 635

if we use half display
	new_half_hdisplay = DIV_ROUND_UP(952 * 8, 8 * 3) = 318
	new_full_display = 636

Fixes: 7c9e4a554d4a ("drm/msm/dsi: Reduce pclk rate for compression")
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/709716/
Link: https://lore.kernel.org/r/20260306163255.215456-1-mitltlatltl@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index e8e83ee61eb0..db6da99375a1 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -584,13 +584,30 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
  *  FIXME: Reconsider this if/when CMD mode handling is rewritten to use
  *  transfer time and data overhead as a starting point of the calculations.
  */
-static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode,
-		const struct drm_dsc_config *dsc)
+static unsigned long
+dsi_adjust_pclk_for_compression(const struct drm_display_mode *mode,
+				const struct drm_dsc_config *dsc,
+				bool is_bonded_dsi)
 {
-	int new_hdisplay = DIV_ROUND_UP(mode->hdisplay * drm_dsc_get_bpp_int(dsc),
-			dsc->bits_per_component * 3);
+	int hdisplay, new_hdisplay, new_htotal;
 
-	int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
+	/*
+	 * For bonded DSI, split hdisplay across two links and round up each
+	 * half separately, passing the full hdisplay would only round up once.
+	 * This also aligns with the hdisplay we program later in
+	 * dsi_timing_setup()
+	 */
+	hdisplay = mode->hdisplay;
+	if (is_bonded_dsi)
+		hdisplay /= 2;
+
+	new_hdisplay = DIV_ROUND_UP(hdisplay * drm_dsc_get_bpp_int(dsc),
+				    dsc->bits_per_component * 3);
+
+	if (is_bonded_dsi)
+		new_hdisplay *= 2;
+
+	new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
 
 	return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal);
 }
@@ -603,7 +620,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
 	pclk_rate = mode->clock * 1000u;
 
 	if (dsc)
-		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc);
+		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc, is_bonded_dsi);
 
 	/*
 	 * For bonded DSI mode, the current DRM mode has the complete width of the
-- 
cgit v1.2.3


From 0e16181704e37330069c24cea143f15b7b298da3 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 5 Mar 2026 09:28:05 -0800
Subject: MAINTAINERS: Remove bouncing T7XX reviewer

This reviewer's email no longer works. Remove it from MAINTAINERS.

Cc: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Cc: Liu Haijun <haijun.liu@mediatek.com>
Cc: Ricardo Martinez <ricardo.martinez@linux.intel.com>
Cc: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Link: https://patch.msgid.link/20260305172806.3118806-1-dave.hansen@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b277d5bf3d1..4f8e772808c7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16358,7 +16358,6 @@ F:	net/dsa/tag_mtk.c
 
 MEDIATEK T7XX 5G WWAN MODEM DRIVER
 M:	Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
-R:	Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com>
 R:	Liu Haijun <haijun.liu@mediatek.com>
 R:	Ricardo Martinez <ricardo.martinez@linux.intel.com>
 L:	netdev@vger.kernel.org
-- 
cgit v1.2.3


From 3b1679e086bb869ca02722f6bd29b3573a6a0e7e Mon Sep 17 00:00:00 2001
From: Andrei-Alexandru Tachici <andrei-alexandru.tachici@oss.qualcomm.com>
Date: Mon, 2 Mar 2026 11:27:34 +0100
Subject: tracing: Fix enabling multiple events on the kernel command line and
 bootconfig

Multiple events can be enabled on the kernel command line via a comma
separator. But if the are specified one at a time, then only the last
event is enabled. This is because the event names are saved in a temporary
buffer, and each call by the init cmdline code will reset that buffer.

This also affects names in the boot config file, as it may call the
callback multiple times with an example of:

  kernel.trace_event = ":mod:rproc_qcom_common", ":mod:qrtr", ":mod:qcom_aoss"

Change the cmdline callback function to append a comma and the next value
if the temporary buffer already has content.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260302-trace-events-allow-multiple-modules-v1-1-ce4436e37fb8@oss.qualcomm.com
Signed-off-by: Andrei-Alexandru Tachici <andrei-alexandru.tachici@oss.qualcomm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b7343fdfd7b0..249d1cba72c0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -4493,7 +4493,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 
 static __init int setup_trace_event(char *str)
 {
-	strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	if (bootup_event_buf[0] != '\0')
+		strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE);
+
+	strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE);
+
 	trace_set_ring_buffer_expanded(NULL);
 	disable_tracing_selftest("running event tracing");
 
-- 
cgit v1.2.3


From cb47c882c31334aadc13ace80781728ed22a05ee Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Tue, 3 Mar 2026 21:10:11 -0500
Subject: drm/amd/pm: add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu
 v13

add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v13.0.0/13.0.7

Fixes: cfffd980bf21 ("drm/amd/pm: add zero RPM OD setting support for SMU13")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 576a10797b607ee9e4068218daf367b481564120)
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 3 ++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index b32c053950c9..a8d63d4d1f6e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2222,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index f08cfa510a8a..5500a0f12f0e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2224,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
-- 
cgit v1.2.3


From 9d4837a26149355ffe3a1f80de80531eafdd3353 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Tue, 3 Mar 2026 21:14:10 -0500
Subject: drm/amd/pm: add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu
 v14

add missing od setting PP_OD_FEATURE_ZERO_FAN_BIT for smu v14.0.2/14.0.3

Fixes: 9710b84e2a6a ("drm/amd/pm: add overdrive support on smu v14.0.2/3")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5018
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1b5cf07d80bb16d1593579ccdb23f08ea4262c14)
---
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 9994d4369da8..73762d9b5969 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
-- 
cgit v1.2.3


From 062ea905fff7756b2e87143ffccaece5cdb44267 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 4 Mar 2026 14:07:40 -0600
Subject: drm/amd: Fix NULL pointer dereference in device cleanup

When GPU initialization fails due to an unsupported HW block
IP blocks may have a NULL version pointer. During cleanup in
amdgpu_device_fini_hw, the code calls amdgpu_device_set_pg_state and
amdgpu_device_set_cg_state which iterate over all IP blocks and access
adev->ip_blocks[i].version without NULL checks, leading to a kernel
NULL pointer dereference.

Add NULL checks for adev->ip_blocks[i].version in both
amdgpu_device_set_cg_state and amdgpu_device_set_pg_state to prevent
dereferencing NULL pointers during GPU teardown when initialization has
failed.

Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b7ac77468cda92eecae560b05f62f997a12fe2f2)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3e19b51a2763..10b10bac8b18 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3247,6 +3247,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip CG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3286,6 +3288,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev,
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip PG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
-- 
cgit v1.2.3


From 52289ce48ef1f8a81cd39df1574098356e3c9d4c Mon Sep 17 00:00:00 2001
From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Date: Thu, 5 Mar 2026 13:16:36 +0200
Subject: drm/amdgpu: Fix kernel-doc comments for some LUT properties

The following members of struct amdgpu_mode_info do not have valid
references in the related kernel-doc sections:

 - plane_shaper_lut_property
 - plane_shaper_lut_size_property,
 - plane_lut3d_size_property

Correct all affected comment blocks.

Fixes: f545d82479b4 ("drm/amd/display: add plane shaper LUT and TF driver-specific properties")
Fixes: 671994e3bf33 ("drm/amd/display: add plane 3D LUT driver-specific properties")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ec5708d6e547f7efe2f009073bfa98dbc4c5c2ac)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index dc8d2f52c7d6..e244c12ceb23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -368,15 +368,15 @@ struct amdgpu_mode_info {
 
 	struct drm_property *plane_ctm_property;
 	/**
-	 * @shaper_lut_property: Plane property to set pre-blending shaper LUT
-	 * that converts color content before 3D LUT. If
-	 * plane_shaper_tf_property != Identity TF, AMD color module will
+	 * @plane_shaper_lut_property: Plane property to set pre-blending
+	 * shaper LUT that converts color content before 3D LUT.
+	 * If plane_shaper_tf_property != Identity TF, AMD color module will
 	 * combine the user LUT values with pre-defined TF into the LUT
 	 * parameters to be programmed.
 	 */
 	struct drm_property *plane_shaper_lut_property;
 	/**
-	 * @shaper_lut_size_property: Plane property for the size of
+	 * @plane_shaper_lut_size_property: Plane property for the size of
 	 * pre-blending shaper LUT as supported by the driver (read-only).
 	 */
 	struct drm_property *plane_shaper_lut_size_property;
@@ -400,10 +400,10 @@ struct amdgpu_mode_info {
 	 */
 	struct drm_property *plane_lut3d_property;
 	/**
-	 * @plane_degamma_lut_size_property: Plane property to define the max
-	 * size of 3D LUT as supported by the driver (read-only). The max size
-	 * is the max size of one dimension and, therefore, the max number of
-	 * entries for 3D LUT array is the 3D LUT size cubed;
+	 * @plane_lut3d_size_property: Plane property to define the max size
+	 * of 3D LUT as supported by the driver (read-only). The max size is
+	 * the max size of one dimension and, therefore, the max number of
+	 * entries for 3D LUT array is the 3D LUT size cubed.
 	 */
 	struct drm_property *plane_lut3d_size_property;
 	/**
-- 
cgit v1.2.3


From a6571045cf06c4aa749b4801382ae96650e2f0e1 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Wed, 4 Mar 2026 18:45:45 -0500
Subject: drm/amdgpu: fix gpu idle power consumption issue for gfx v12

Older versions of the MES firmware may cause abnormal GPU power consumption.
When performing inference tasks on the GPU (e.g., with Ollama using ROCm),
the GPU may show abnormal power consumption in idle state and incorrect GPU load information.
This issue has been fixed in firmware version 0x8b and newer.

Closes: https://github.com/ROCm/ROCm/issues/5706
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4e22a5fe6ea6e0b057e7f246df4ac3ff8bfbc46a)
---
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 5bfa5d1d0b36..023c7345ea54 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	int i;
 	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt;
+	uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ?
+		(mes->sched_version & AMDGPU_MES_VERSION_MASK) :
+		(mes->kiq_version & AMDGPU_MES_VERSION_MASK);
 
 	memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt));
 
@@ -785,7 +788,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	 * handling support, other queue will not use the oversubscribe timer.
 	 * handling  mode - 0: disabled; 1: basic version; 2: basic+ version
 	 */
-	mes_set_hw_res_pkt.oversubscription_timer = 50;
+	mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50;
 	mes_set_hw_res_pkt.unmapped_doorbell_handling = 1;
 
 	if (amdgpu_mes_log_enable) {
-- 
cgit v1.2.3


From 72ecb1dae72775fa9fea0159d8445d620a0a2295 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 5 Mar 2026 09:06:11 -0600
Subject: drm/amd: Fix a few more NULL pointer dereference in device cleanup

I found a few more paths that cleanup fails due to a NULL version pointer
on unsupported hardware.

Add NULL checks as applicable.

Fixes: 39fc2bc4da00 ("drm/amdgpu: Protect GPU register accesses in powergated state in some paths")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f5a05f8414fc10f307eb965f303580c7778f8dd2)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 10b10bac8b18..761ee5ebb4f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3497,6 +3497,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (!adev->ip_blocks[i].version->funcs->early_fini)
 			continue;
 
@@ -3574,6 +3576,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
 
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_ucode_free_bo(adev);
 			amdgpu_free_static_csa(&adev->virt.csa_obj);
@@ -3600,6 +3604,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->funcs->late_fini)
 			adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]);
 		adev->ip_blocks[i].status.late_initialized = false;
-- 
cgit v1.2.3


From 2a0596d516870951ce0e8edf510e48c87cb80761 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sat, 7 Mar 2026 02:21:01 +0800
Subject: sched_ext: Documentation: Update sched-ext.rst

- Remove CONFIG_PAHOLE_HAS_BTF_TAG from required config list
- Document ext_idle.c as the built-in idle CPU selection policy
- Add descriptions for example schedulers in tools/sched_ext/

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/scheduler/sched-ext.rst | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index 100d45963781..d74c2c2b9ef3 100644
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -43,7 +43,6 @@ options should be enabled to use sched_ext:
     CONFIG_DEBUG_INFO_BTF=y
     CONFIG_BPF_JIT_ALWAYS_ON=y
     CONFIG_BPF_JIT_DEFAULT_ON=y
-    CONFIG_PAHOLE_HAS_BTF_TAG=y
 
 sched_ext is used only when the BPF scheduler is loaded and running.
 
@@ -346,6 +345,8 @@ Where to Look
   The functions prefixed with ``scx_bpf_`` can be called from the BPF
   scheduler.
 
+* ``kernel/sched/ext_idle.c`` contains the built-in idle CPU selection policy.
+
 * ``tools/sched_ext/`` hosts example BPF scheduler implementations.
 
   * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a
@@ -354,13 +355,35 @@ Where to Look
   * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five
     levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``.
 
+  * ``scx_central[.bpf].c``: A central FIFO scheduler where all scheduling
+    decisions are made on one CPU, demonstrating ``LOCAL_ON`` dispatching,
+    tickless operation, and kthread preemption.
+
+  * ``scx_cpu0[.bpf].c``: A scheduler that queues all tasks to a shared DSQ
+    and only dispatches them on CPU0 in FIFO order. Useful for testing bypass
+    behavior.
+
+  * ``scx_flatcg[.bpf].c``: A flattened cgroup hierarchy scheduler
+    implementing hierarchical weight-based cgroup CPU control by compounding
+    each cgroup's share at every level into a single flat scheduling layer.
+
+  * ``scx_pair[.bpf].c``: A core-scheduling example that always makes
+    sibling CPU pairs execute tasks from the same CPU cgroup.
+
+  * ``scx_sdt[.bpf].c``: A variation of ``scx_simple`` demonstrating BPF
+    arena memory management for per-task data.
+
+  * ``scx_userland[.bpf].c``: A minimal scheduler demonstrating user space
+    scheduling. Tasks with CPU affinity are direct-dispatched in FIFO order;
+    all others are scheduled in user space by a simple vruntime scheduler.
+
 ABI Instability
 ===============
 
 The APIs provided by sched_ext to BPF schedulers programs have no stability
 guarantees. This includes the ops table callbacks and constants defined in
 ``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in
-``kernel/sched/ext.c``.
+``kernel/sched/ext.c`` and ``kernel/sched/ext_idle.c``.
 
 While we will attempt to provide a relatively stable API surface when
 possible, they are subject to change without warning between kernel
-- 
cgit v1.2.3


From a72f73c4dd9b209c53cf8b03b6e97fcefad4262c Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 6 Mar 2026 20:22:35 +0100
Subject: cgroup: Don't expose dead tasks in cgroup

Once a task exits it has its state set to TASK_DEAD and then it is
removed from the cgroup it belonged to. The last step happens on the task
gets out of its last schedule() invocation and is delayed on PREEMPT_RT
due to locking constraints.

As a result it is possible to receive a pid via waitpid() of a task
which is still listed in cgroup.procs for the cgroup it belonged
to. This is something that systemd does not expect and as a result it
waits for its exit until a time out occurs.
This can also be reproduced on !PREEMPT_RT kernel with a significant
delay in do_exit() after exit_notify().

Hide the task from the output which have PF_EXITING set which is done
before the parent is notified. Keeping zombies with live threads
shouldn't break anything (suggested by Tejun).

Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/all/20260219164648.3014-1-spasswolf@web.de/
Tested-by: Bert Karwatzki <spasswolf@web.de>
Fixes: 9311e6c29b34 ("cgroup: Fix sleeping from invalid context warning on PREEMPT_RT")
Cc: stable@vger.kernel.org # v6.19+
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cgroup.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index be1d71dda317..01fc2a93f3ef 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -5109,6 +5109,12 @@ repeat:
 		return;
 
 	task = list_entry(it->task_pos, struct task_struct, cg_list);
+	/*
+	 * Hide tasks that are exiting but not yet removed. Keep zombie
+	 * leaders with live threads visible.
+	 */
+	if ((task->flags & PF_EXITING) && !atomic_read(&task->signal->live))
+		goto repeat;
 
 	if (it->flags & CSS_TASK_ITER_PROCS) {
 		/* if PROCS, skip over tasks which aren't group leaders */
-- 
cgit v1.2.3


From 224a0d284c3caf1951302d1744a714784febed71 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 11:45:49 +0100
Subject: net: mctp: fix device leak on probe failure

Driver core holds a reference to the USB interface and its parent USB
device while the interface is bound to a driver and there is no need to
take additional references unless the structures are needed after
disconnect.

This driver takes a reference to the USB device during probe but does
not to release it on probe failures.

Drop the redundant device reference to fix the leak, reduce cargo
culting, make it easier to spot drivers where an extra reference is
needed, and reduce the risk of further memory leaks.

Fixes: 0791c0327a6e ("net: mctp: Add MCTP USB transport driver")
Cc: stable@vger.kernel.org	# 6.15
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://patch.msgid.link/20260305104549.16110-1-johan@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mctp/mctp-usb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c
index ef860cfc629f..3b5dff144177 100644
--- a/drivers/net/mctp/mctp-usb.c
+++ b/drivers/net/mctp/mctp-usb.c
@@ -329,7 +329,7 @@ static int mctp_usb_probe(struct usb_interface *intf,
 	SET_NETDEV_DEV(netdev, &intf->dev);
 	dev = netdev_priv(netdev);
 	dev->netdev = netdev;
-	dev->usbdev = usb_get_dev(interface_to_usbdev(intf));
+	dev->usbdev = interface_to_usbdev(intf);
 	dev->intf = intf;
 	usb_set_intfdata(intf, dev);
 
@@ -365,7 +365,6 @@ static void mctp_usb_disconnect(struct usb_interface *intf)
 	mctp_unregister_netdev(dev->netdev);
 	usb_free_urb(dev->tx_urb);
 	usb_free_urb(dev->rx_urb);
-	usb_put_dev(dev->usbdev);
 	free_netdev(dev->netdev);
 }
 
-- 
cgit v1.2.3


From 45fc134bcfadde456639c1b1e206e6918d69a553 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Mar 2026 15:13:53 +0800
Subject: bonding: do not set usable_slaves for broadcast mode

After commit e0caeb24f538 ("net: bonding: update the slave array for broadcast mode"),
broadcast mode will also set all_slaves and usable_slaves during
bond_enslave(). But if we also set updelay, during enslave, the
slave init state will be BOND_LINK_BACK. And later
bond_update_slave_arr() will alloc usable_slaves but add nothing.
This will cause bond_miimon_inspect() to have ignore_updelay
always true. So the updelay will be always ignored. e.g.

[    6.498368] bond0: (slave veth2): link status definitely down, disabling slave
[    7.536371] bond0: (slave veth2): link status up, enabling it in 0 ms
[    7.536402] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex

To fix it, we can either always call bond_update_slave_arr() on every
place when link changes. Or, let's just not set usable_slaves for
broadcast mode.

Fixes: e0caeb24f538 ("net: bonding: update the slave array for broadcast mode")
Reported-by: Liang Li <liali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-1-f72eb2e454d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 14ed91391fcc..93a32a368d31 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5069,13 +5069,18 @@ static void bond_set_slave_arr(struct bonding *bond,
 {
 	struct bond_up_slave *usable, *all;
 
-	usable = rtnl_dereference(bond->usable_slaves);
-	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
-	kfree_rcu(usable, rcu);
-
 	all = rtnl_dereference(bond->all_slaves);
 	rcu_assign_pointer(bond->all_slaves, all_slaves);
 	kfree_rcu(all, rcu);
+
+	if (BOND_MODE(bond) == BOND_MODE_BROADCAST) {
+		kfree_rcu(usable_slaves, rcu);
+		return;
+	}
+
+	usable = rtnl_dereference(bond->usable_slaves);
+	rcu_assign_pointer(bond->usable_slaves, usable_slaves);
+	kfree_rcu(usable, rcu);
 }
 
 static void bond_reset_slave_arr(struct bonding *bond)
-- 
cgit v1.2.3


From 3348be7978f450ede0c308a4e8416ac716cf1015 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Mar 2026 15:13:54 +0800
Subject: bonding: handle BOND_LINK_FAIL, BOND_LINK_BACK as valid link states

Before the fixed commit, we check slave->new_link during commit
state, which values are only BOND_LINK_{NOCHANGE, UP, DOWN}. After
the commit, we start using slave->link_new_state, which state also could
be BOND_LINK_{FAIL, BACK}.

For example, when we set updelay/downdelay, after a failover,
the slave->link_new_state could be set to BOND_LINK_{FAIL, BACK} in
bond_miimon_inspect(). And later in bond_miimon_commit(), it will treat
it as invalid and print an error, which would cause confusion for users.

[  106.440254] bond0: (slave veth2): link status down for interface, disabling it in 200 ms
[  106.440265] bond0: (slave veth2): invalid new link 1 on slave
[  106.648276] bond0: (slave veth2): link status definitely down, disabling slave
[  107.480271] bond0: (slave veth2): link status up, enabling it in 200 ms
[  107.480288] bond0: (slave veth2): invalid new link 3 on slave
[  107.688302] bond0: (slave veth2): link status definitely up, 10000 Mbps full duplex

Let's handle BOND_LINK_{FAIL, BACK} as valid link states.

Fixes: 1899bb325149 ("bonding: fix state transition issue in link monitoring")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260304-b4-bond_updelay-v1-2-f72eb2e454d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 93a32a368d31..444519078da3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2801,8 +2801,14 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			continue;
 
+		case BOND_LINK_FAIL:
+		case BOND_LINK_BACK:
+			slave_dbg(bond->dev, slave->dev, "link_new_state %d on slave\n",
+				  slave->link_new_state);
+			continue;
+
 		default:
-			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
+			slave_err(bond->dev, slave->dev, "invalid link_new_state %d on slave\n",
 				  slave->link_new_state);
 			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
-- 
cgit v1.2.3


From 55f854dd5bdd8e19b936a00ef1f8d776ac32c7b0 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 4 Mar 2026 14:43:38 +0100
Subject: qmi_wwan: allow max_mtu above hard_mtu to control rx_urb_size

Commit c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu")
capped net->max_mtu to the device's hard_mtu in usbnet_probe(). While
this correctly prevents oversized packets on standard USB network
devices, it breaks the qmi_wwan driver.

qmi_wwan relies on userspace (e.g. ModemManager) setting a large MTU on
the wwan0 interface to configure rx_urb_size via usbnet_change_mtu().
QMI modems negotiate USB transfer sizes of 16,383 or 32,767 bytes, and
the USB receive buffers must be sized accordingly. With max_mtu capped
to hard_mtu (~1500 bytes), userspace can no longer raise the MTU, the
receive buffers remain small, and download speeds drop from >300 Mbps
to ~0.8 Mbps.

Introduce a FLAG_NOMAXMTU driver flag that allows individual usbnet
drivers to opt out of the max_mtu cap. Set this flag in qmi_wwan's
driver_info structures to restore the previous behavior for QMI devices,
while keeping the safety fix in place for all other usbnet drivers.

Fixes: c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/lkml/CAPh3n803k8JcBPV5qEzUB-oKzWkAs-D5CU7z=Vd_nLRCr5ZqQg@mail.gmail.com/
Reported-by: Koen Vandeputte <koen.vandeputte@citymesh.com>
Tested-by: Daniele Palmas <dnlplm@gmail.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Link: https://patch.msgid.link/20260304134338.1785002-1-lvivier@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 4 ++--
 drivers/net/usb/usbnet.c   | 7 ++++---
 include/linux/usb/usbnet.h | 1 +
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 3a4985b582cb..05acac10cd2b 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -928,7 +928,7 @@ err:
 
 static const struct driver_info	qmi_wwan_info = {
 	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
+	.flags		= FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP,
 	.bind		= qmi_wwan_bind,
 	.unbind		= qmi_wwan_unbind,
 	.manage_power	= qmi_wwan_manage_power,
@@ -937,7 +937,7 @@ static const struct driver_info	qmi_wwan_info = {
 
 static const struct driver_info	qmi_wwan_info_quirk_dtr = {
 	.description	= "WWAN/QMI device",
-	.flags		= FLAG_WWAN | FLAG_SEND_ZLP,
+	.flags		= FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP,
 	.bind		= qmi_wwan_bind,
 	.unbind		= qmi_wwan_unbind,
 	.manage_power	= qmi_wwan_manage_power,
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ed86ba87ca4e..b72ba0803392 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1829,11 +1829,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod)
 		if ((dev->driver_info->flags & FLAG_NOARP) != 0)
 			net->flags |= IFF_NOARP;
 
-		if (net->max_mtu > (dev->hard_mtu - net->hard_header_len))
+		if ((dev->driver_info->flags & FLAG_NOMAXMTU) == 0 &&
+		    net->max_mtu > (dev->hard_mtu - net->hard_header_len))
 			net->max_mtu = dev->hard_mtu - net->hard_header_len;
 
-		if (net->mtu > net->max_mtu)
-			net->mtu = net->max_mtu;
+		if (net->mtu > (dev->hard_mtu - net->hard_header_len))
+			net->mtu = dev->hard_mtu - net->hard_header_len;
 
 	} else if (!info->in || !info->out)
 		status = usbnet_get_endpoints(dev, udev);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index b0e84896e6ac..bbf799ccf3b3 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -132,6 +132,7 @@ struct driver_info {
 #define FLAG_MULTI_PACKET	0x2000
 #define FLAG_RX_ASSEMBLE	0x4000	/* rx packets may span >1 frames */
 #define FLAG_NOARP		0x8000	/* device can't do ARP */
+#define FLAG_NOMAXMTU		0x10000	/* allow max_mtu above hard_mtu */
 
 	/* init device ... can sleep, or cause probe() failure */
 	int	(*bind)(struct usbnet *, struct usb_interface *);
-- 
cgit v1.2.3


From aed763abf0e905b4b8d747d1ba9e172961572f57 Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Thu, 5 Mar 2026 10:10:19 +0200
Subject: net/mlx5: Fix deadlock between devlink lock and esw->wq

esw->work_queue executes esw_functions_changed_event_handler ->
esw_vfs_changed_event_handler and acquires the devlink lock.

.eswitch_mode_set (acquires devlink lock in devlink_nl_pre_doit) ->
mlx5_devlink_eswitch_mode_set -> mlx5_eswitch_disable_locked ->
mlx5_eswitch_event_handler_unregister -> flush_workqueue deadlocks
when esw_vfs_changed_event_handler executes.

Fix that by no longer flushing the work to avoid the deadlock, and using
a generation counter to keep track of work relevance. This avoids an old
handler manipulating an esw that has undergone one or more mode changes:
- the counter is incremented in mlx5_eswitch_event_handler_unregister.
- the counter is read and passed to the ephemeral mlx5_host_work struct.
- the work handler takes the devlink lock and bails out if the current
  generation is different than the one it was scheduled to operate on.
- mlx5_eswitch_cleanup does the final draining before destroying the wq.

No longer flushing the workqueue has the side effect of maybe no longer
cancelling pending vport_change_handler work items, but that's ok since
those are disabled elsewhere:
- mlx5_eswitch_disable_locked disables the vport eq notifier.
- mlx5_esw_vport_disable disarms the HW EQ notification and marks
  vport->enabled under state_lock to false to prevent pending vport
  handler from doing anything.
- mlx5_eswitch_cleanup destroys the workqueue and makes sure all events
  are disabled/finished.

Fixes: f1bc646c9a06 ("net/mlx5: Use devl_ API in mlx5_esw_offloads_devlink_port_register")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305081019.1811100-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c      |  7 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h      |  2 ++
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 18 +++++++++++++-----
 3 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d3af87a94a18..123c96716a54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1072,10 +1072,11 @@ static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw)
 
 static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw)
 {
-	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS &&
+	    mlx5_eswitch_is_funcs_handler(esw->dev)) {
 		mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
-
-	flush_workqueue(esw->work_queue);
+		atomic_inc(&esw->esw_funcs.generation);
+	}
 }
 
 static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6841caef02d1..c2563bee74df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -335,10 +335,12 @@ struct esw_mc_addr { /* SRIOV only */
 struct mlx5_host_work {
 	struct work_struct	work;
 	struct mlx5_eswitch	*esw;
+	int			work_gen;
 };
 
 struct mlx5_esw_functions {
 	struct mlx5_nb		nb;
+	atomic_t		generation;
 	bool			host_funcs_disabled;
 	u16			num_vfs;
 	u16			num_ec_vfs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1366f6e489bd..8c5e48d001be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3582,22 +3582,28 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 }
 
 static void
-esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
+esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen,
+			      const u32 *out)
 {
 	struct devlink *devlink;
 	bool host_pf_disabled;
 	u16 new_num_vfs;
 
+	devlink = priv_to_devlink(esw->dev);
+	devl_lock(devlink);
+
+	/* Stale work from one or more mode changes ago. Bail out. */
+	if (work_gen != atomic_read(&esw->esw_funcs.generation))
+		goto unlock;
+
 	new_num_vfs = MLX5_GET(query_esw_functions_out, out,
 			       host_params_context.host_num_of_vfs);
 	host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
 				    host_params_context.host_pf_disabled);
 
 	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
-		return;
+		goto unlock;
 
-	devlink = priv_to_devlink(esw->dev);
-	devl_lock(devlink);
 	/* Number of VFs can only change from "0 to x" or "x to 0". */
 	if (esw->esw_funcs.num_vfs > 0) {
 		mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
@@ -3612,6 +3618,7 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
 		}
 	}
 	esw->esw_funcs.num_vfs = new_num_vfs;
+unlock:
 	devl_unlock(devlink);
 }
 
@@ -3628,7 +3635,7 @@ static void esw_functions_changed_event_handler(struct work_struct *work)
 	if (IS_ERR(out))
 		goto out;
 
-	esw_vfs_changed_event_handler(esw, out);
+	esw_vfs_changed_event_handler(esw, host_work->work_gen, out);
 	kvfree(out);
 out:
 	kfree(host_work);
@@ -3648,6 +3655,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type
 	esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);
 
 	host_work->esw = esw;
+	host_work->work_gen = atomic_read(&esw_funcs->generation);
 
 	INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
 	queue_work(esw->work_queue, &host_work->work);
-- 
cgit v1.2.3


From 24b2795f9683e092dc22a68f487e7aaaf2ddafea Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:30 +0200
Subject: net/mlx5: Fix crash when moving to switchdev mode

When moving to switchdev mode when the device doesn't support IPsec,
we try to clean up the IPsec resources anyway which causes the crash
below, fix that by correctly checking for IPsec support before trying
to clean up its resources.

[27642.515799] WARNING: arch/x86/mm/fault.c:1276 at
do_user_addr_fault+0x18a/0x680, CPU#4: devlink/6490
[27642.517159] Modules linked in: xt_conntrack xt_MASQUERADE
ip6table_nat ip6table_filter ip6_tables iptable_nat nf_nat xt_addrtype
rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl nfnetlink
zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi
scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core
ib_core
[27642.521358] CPU: 4 UID: 0 PID: 6490 Comm: devlink Not tainted
6.19.0-rc5_for_upstream_min_debug_2026_01_14_16_47 #1 NONE
[27642.522923] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
[27642.524528] RIP: 0010:do_user_addr_fault+0x18a/0x680
[27642.525362] Code: ff 0f 84 75 03 00 00 48 89 ee 4c 89 e7 e8 5e b9 22
00 49 89 c0 48 85 c0 0f 84 a8 02 00 00 f7 c3 60 80 00 00 74 22 31 c9 eb
   ae <0f> 0b 48 83 c4 10 48 89 ea 48 89 de 4c 89 f7 5b 5d 41 5c 41 5d
41
[27642.528166] RSP: 0018:ffff88810770f6b8 EFLAGS: 00010046
[27642.529038] RAX: 0000000000000000 RBX: 0000000000000002 RCX:
ffff88810b980f00
[27642.530158] RDX: 00000000000000a0 RSI: 0000000000000002 RDI:
ffff88810770f728
[27642.531270] RBP: 00000000000000a0 R08: 0000000000000000 R09:
0000000000000000
[27642.532383] R10: 0000000000000000 R11: 0000000000000000 R12:
ffff888103f3c4c0
[27642.533499] R13: 0000000000000000 R14: ffff88810770f728 R15:
0000000000000000
[27642.534614] FS:  00007f197c741740(0000) GS:ffff88856a94c000(0000)
knlGS:0000000000000000
[27642.535915] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[27642.536858] CR2: 00000000000000a0 CR3: 000000011334c003 CR4:
0000000000172eb0
[27642.537982] Call Trace:
[27642.538466]  <TASK>
[27642.538907]  exc_page_fault+0x76/0x140
[27642.539583]  asm_exc_page_fault+0x22/0x30
[27642.540282] RIP: 0010:_raw_spin_lock_irqsave+0x10/0x30
[27642.541134] Code: 07 85 c0 75 11 ba ff 00 00 00 f0 0f b1 17 75 06 b8
01 00 00 00 c3 31 c0 c3 90 0f 1f 44 00 00 53 9c 5b fa 31 c0 ba 01 00 00
   00 <f0> 0f b1 17 75 05 48 89 d8 5b c3 89 c6 e8 7e 02 00 00 48 89 d8
      5b
[27642.543936] RSP: 0018:ffff88810770f7d8 EFLAGS: 00010046
[27642.544803] RAX: 0000000000000000 RBX: 0000000000000202 RCX:
ffff888113ad96d8
[27642.545916] RDX: 0000000000000001 RSI: ffff88810770f818 RDI:
00000000000000a0
[27642.547027] RBP: 0000000000000098 R08: 0000000000000400 R09:
ffff88810b980f00
[27642.548140] R10: 0000000000000001 R11: ffff888101845a80 R12:
00000000000000a8
[27642.549263] R13: ffffffffa02a9060 R14: 00000000000000a0 R15:
ffff8881130d8a40
[27642.550379]  complete_all+0x20/0x90
[27642.551010]  mlx5e_ipsec_disable_events+0xb6/0xf0 [mlx5_core]
[27642.552022]  mlx5e_nic_disable+0x12d/0x220 [mlx5_core]
[27642.552929]  mlx5e_detach_netdev+0x66/0xf0 [mlx5_core]
[27642.553822]  mlx5e_netdev_change_profile+0x5b/0x120 [mlx5_core]
[27642.554821]  mlx5e_vport_rep_load+0x419/0x590 [mlx5_core]
[27642.555757]  ? xa_load+0x53/0x90
[27642.556361]  __esw_offloads_load_rep+0x54/0x70 [mlx5_core]
[27642.557328]  mlx5_esw_offloads_rep_load+0x45/0xd0 [mlx5_core]
[27642.558320]  esw_offloads_enable+0xb4b/0xc90 [mlx5_core]
[27642.559247]  mlx5_eswitch_enable_locked+0x34e/0x4f0 [mlx5_core]
[27642.560257]  ? mlx5_rescan_drivers_locked+0x222/0x2d0 [mlx5_core]
[27642.561284]  mlx5_devlink_eswitch_mode_set+0x5ac/0x9c0 [mlx5_core]
[27642.562334]  ? devlink_rate_set_ops_supported+0x21/0x3a0
[27642.563220]  devlink_nl_eswitch_set_doit+0x67/0xe0
[27642.564026]  genl_family_rcv_msg_doit+0xe0/0x130
[27642.564816]  genl_rcv_msg+0x183/0x290
[27642.565466]  ? __devlink_nl_pre_doit.isra.0+0x160/0x160
[27642.566329]  ? devlink_nl_eswitch_get_doit+0x290/0x290
[27642.567181]  ? devlink_nl_pre_doit_parent_dev_optional+0x20/0x20
[27642.568147]  ? genl_family_rcv_msg_dumpit+0xf0/0xf0
[27642.568966]  netlink_rcv_skb+0x4b/0xf0
[27642.569629]  genl_rcv+0x24/0x40
[27642.570215]  netlink_unicast+0x255/0x380
[27642.570901]  ? __alloc_skb+0xfa/0x1e0
[27642.571560]  netlink_sendmsg+0x1f3/0x420
[27642.572249]  __sock_sendmsg+0x38/0x60
[27642.572911]  __sys_sendto+0x119/0x180
[27642.573561]  ? __sys_recvmsg+0x5c/0xb0
[27642.574227]  __x64_sys_sendto+0x20/0x30
[27642.574904]  do_syscall_64+0x55/0xc10
[27642.575554]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[27642.576391] RIP: 0033:0x7f197c85e807
[27642.577050] Code: c7 c0 ff ff ff ff eb be 66 2e 0f 1f 84 00 00 00 00
00 90 f3 0f 1e fa 80 3d 45 08 0d 00 00 41 89 ca 74 10 b8 2c 00 00 00 0f
   05 <48> 3d 00 f0 ff ff 77 69 c3 55 48 89 e5 53 48 83 ec 38 44 89 4d
      d0
[27642.579846] RSP: 002b:00007ffebd4e2248 EFLAGS: 00000202 ORIG_RAX:
000000000000002c
[27642.581082] RAX: ffffffffffffffda RBX: 000055cfcd9cd2a0 RCX:
00007f197c85e807
[27642.582200] RDX: 0000000000000038 RSI: 000055cfcd9cd490 RDI:
0000000000000003
[27642.583320] RBP: 00007ffebd4e2290 R08: 00007f197c942200 R09:
000000000000000c
[27642.584437] R10: 0000000000000000 R11: 0000000000000202 R12:
0000000000000000
[27642.585555] R13: 000055cfcd9cd490 R14: 00007ffebd4e45d1 R15:
000055cfcd9cd2a0
[27642.586671]  </TASK>
[27642.587121] ---[ end trace 0000000000000000 ]---
[27642.587910] BUG: kernel NULL pointer dereference, address:
00000000000000a0

Fixes: 664f76be38a1 ("net/mlx5: Fix IPsec cleanup over MPV device")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 197a1c6930c0..329608c59313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -2912,7 +2912,7 @@ void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv)
 		goto out;
 
 	peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp);
-	if (peer_priv)
+	if (peer_priv && peer_priv->ipsec)
 		complete_all(&peer_priv->ipsec->comp);
 
 	mlx5_devcom_for_each_peer_end(priv->devcom);
-- 
cgit v1.2.3


From 76324e4041c0efb4808702b05426d7a0a7d8df5b Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:31 +0200
Subject: net/mlx5: Fix peer miss rules host disabled checks

The check on mlx5_esw_host_functions_enabled(esw->dev) for adding VF
peer miss rules is incorrect. These rules match traffic from peer's VFs,
so the local device's host function status is irrelevant. Remove this
check to ensure peer VF traffic is properly handled regardless of local
host configuration.

Also fix the PF peer miss rule deletion to be symmetric with the add
path, so only attempt to delete the rule if it was actually created.

Fixes: 520369ef43a8 ("net/mlx5: Support disabling host PFs")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 27 ++++++++++------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8c5e48d001be..7a9ee36b8dca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1241,21 +1241,17 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 		flows[peer_vport->index] = flow;
 	}
 
-	if (mlx5_esw_host_functions_enabled(esw->dev)) {
-		mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
-					   mlx5_core_max_vfs(peer_dev)) {
-			esw_set_peer_miss_rule_source_port(esw, peer_esw,
-							   spec,
-							   peer_vport->vport);
-
-			flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
-						   spec, &flow_act, &dest, 1);
-			if (IS_ERR(flow)) {
-				err = PTR_ERR(flow);
-				goto add_vf_flow_err;
-			}
-			flows[peer_vport->index] = flow;
+	mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport,
+				   mlx5_core_max_vfs(peer_dev)) {
+		esw_set_peer_miss_rule_source_port(esw, peer_esw, spec,
+						   peer_vport->vport);
+		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_vf_flow_err;
 		}
+		flows[peer_vport->index] = flow;
 	}
 
 	if (mlx5_core_ec_sriov_enabled(peer_dev)) {
@@ -1347,7 +1343,8 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
 
-	if (mlx5_core_is_ecpf_esw_manager(peer_dev)) {
+	if (mlx5_core_is_ecpf_esw_manager(peer_dev) &&
+	    mlx5_esw_host_functions_enabled(peer_dev)) {
 		peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF);
 		mlx5_del_flow_rules(flows[peer_vport->index]);
 	}
-- 
cgit v1.2.3


From 1633111d69053512d099658d4a05fc736fab36b0 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:32 +0200
Subject: net/mlx5e: Fix DMA FIFO desync on error CQE SQ recovery

In case of a TX error CQE, a recovery flow is triggered,
mlx5e_reset_txqsq_cc_pc() resets dma_fifo_cc to 0 but not dma_fifo_pc,
desyncing the DMA FIFO producer and consumer.

After recovery, the producer pushes new DMA entries at the old
dma_fifo_pc, while the consumer reads from position 0.
This causes us to unmap stale DMA addresses from before the recovery.

The DMA FIFO is a purely software construct with no HW counterpart.
At the point of reset, all WQEs have been flushed so dma_fifo_cc is
already equal to dma_fifo_pc. There is no need to reset either counter,
similar to how skb_fifo pc/cc are untouched.

Remove the 'dma_fifo_cc = 0' reset.

This fixes the following WARNING:
    WARNING: CPU: 0 PID: 0 at drivers/iommu/dma-iommu.c:1240 iommu_dma_unmap_page+0x79/0x90
    Modules linked in: mlx5_vdpa vringh vdpa bonding mlx5_ib mlx5_vfio_pci ipip mlx5_fwctl tunnel4 mlx5_core ib_ipoib geneve ip6_gre ip_gre gre nf_tables ip6_tunnel rdma_ucm ib_uverbs ib_umad vfio_pci vfio_pci_core act_mirred act_skbedit act_vlan vhost_net vhost tap ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress vhost_iotlb iptable_raw tunnel6 vfio_iommu_type1 vfio openvswitch nsh rpcsec_gss_krb5 auth_rpcgss oid_registry xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter overlay zram zsmalloc rpcrdma ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm ib_core fuse [last unloaded: nf_tables]
    CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.13.0-rc5_for_upstream_min_debug_2024_12_30_21_33 #1
    Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
    RIP: 0010:iommu_dma_unmap_page+0x79/0x90
    Code: 2b 4d 3b 21 72 26 4d 3b 61 08 73 20 49 89 d8 44 89 f9 5b 4c 89 f2 4c 89 e6 48 89 ef 5d 41 5c 41 5d 41 5e 41 5f e9 c7 ae 9e ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 66 2e 0f 1f 84 00 00 00 00
    Call Trace:
     <IRQ>
     ? __warn+0x7d/0x110
     ? iommu_dma_unmap_page+0x79/0x90
     ? report_bug+0x16d/0x180
     ? handle_bug+0x4f/0x90
     ? exc_invalid_op+0x14/0x70
     ? asm_exc_invalid_op+0x16/0x20
     ? iommu_dma_unmap_page+0x79/0x90
     ? iommu_dma_unmap_page+0x2e/0x90
     dma_unmap_page_attrs+0x10d/0x1b0
     mlx5e_tx_wi_dma_unmap+0xbe/0x120 [mlx5_core]
     mlx5e_poll_tx_cq+0x16d/0x690 [mlx5_core]
     mlx5e_napi_poll+0x8b/0xac0 [mlx5_core]
     __napi_poll+0x24/0x190
     net_rx_action+0x32a/0x3b0
     ? mlx5_eq_comp_int+0x7e/0x270 [mlx5_core]
     ? notifier_call_chain+0x35/0xa0
     handle_softirqs+0xc9/0x270
     irq_exit_rcu+0x71/0xd0
     common_interrupt+0x7f/0xa0
     </IRQ>
     <TASK>
     asm_common_interrupt+0x22/0x40

Fixes: db75373c91b0 ("net/mlx5e: Recover Send Queue (SQ) from error state")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 60ba840e00fa..afdeb1b3d425 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -47,7 +47,6 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
 		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
 		  sq->sqn, sq->cc, sq->pc);
 	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
 	sq->pc = 0;
 }
 
-- 
cgit v1.2.3


From db25c42c2e1f9c0d136420fff5e5700f7e771a6f Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:33 +0200
Subject: net/mlx5e: RX, Fix XDP multi-buf frag counting for striding RQ

XDP multi-buf programs can modify the layout of the XDP buffer when the
program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The
referenced commit in the fixes tag corrected the assumption in the mlx5
driver that the XDP buffer layout doesn't change during a program
execution. However, this fix introduced another issue: the dropped
fragments still need to be counted on the driver side to avoid page
fragment reference counting issues.

The issue was discovered by the drivers/net/xdp.py selftest,
more specifically the test_xdp_native_tx_mb:
- The mlx5 driver allocates a page_pool page and initializes it with
  a frag counter of 64 (pp_ref_count=64) and the internal frag counter
  to 0.
- The test sends one packet with no payload.
- On RX (mlx5e_skb_from_cqe_mpwrq_nonlinear()), mlx5 configures the XDP
  buffer with the packet data starting in the first fragment which is the
  page mentioned above.
- The XDP program runs and calls bpf_xdp_pull_data() which moves the
  header into the linear part of the XDP buffer. As the packet doesn't
  contain more data, the program drops the tail fragment since it no
  longer contains any payload (pp_ref_count=63).
- mlx5 device skips counting this fragment. Internal frag counter
  remains 0.
- mlx5 releases all 64 fragments of the page but page pp_ref_count is
  63 => negative reference counting error.

Resulting splat during the test:

  WARNING: CPU: 0 PID: 188225 at ./include/net/page_pool/helpers.h:297 mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core]
  Modules linked in: [...]
  CPU: 0 UID: 0 PID: 188225 Comm: ip Not tainted 6.18.0-rc7_for_upstream_min_debug_2025_12_08_11_44 #1 NONE
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
  RIP: 0010:mlx5e_page_release_fragmented.isra.0+0xbd/0xe0 [mlx5_core]
  [...]
  Call Trace:
   <TASK>
   mlx5e_free_rx_mpwqe+0x20a/0x250 [mlx5_core]
   mlx5e_dealloc_rx_mpwqe+0x37/0xb0 [mlx5_core]
   mlx5e_free_rx_descs+0x11a/0x170 [mlx5_core]
   mlx5e_close_rq+0x78/0xa0 [mlx5_core]
   mlx5e_close_queues+0x46/0x2a0 [mlx5_core]
   mlx5e_close_channel+0x24/0x90 [mlx5_core]
   mlx5e_close_channels+0x5d/0xf0 [mlx5_core]
   mlx5e_safe_switch_params+0x2ec/0x380 [mlx5_core]
   mlx5e_change_mtu+0x11d/0x490 [mlx5_core]
   mlx5e_change_nic_mtu+0x19/0x30 [mlx5_core]
   netif_set_mtu_ext+0xfc/0x240
   do_setlink.isra.0+0x226/0x1100
   rtnl_newlink+0x7a9/0xba0
   rtnetlink_rcv_msg+0x220/0x3c0
   netlink_rcv_skb+0x4b/0xf0
   netlink_unicast+0x255/0x380
   netlink_sendmsg+0x1f3/0x420
   __sock_sendmsg+0x38/0x60
   ____sys_sendmsg+0x1e8/0x240
   ___sys_sendmsg+0x7c/0xb0
   [...]
   __sys_sendmsg+0x5f/0xb0
   do_syscall_64+0x55/0xc70

The problem applies for XDP_PASS as well which is handled in a different
code path in the driver.

This patch fixes the issue by doing page frag counting on all the
original XDP buffer fragments for all relevant XDP actions (XDP_TX ,
XDP_REDIRECT and XDP_PASS). This is basically reverting to the original
counting before the commit in the fixes tag.

As frag_page is still pointing to the original tail, the nr_frags
parameter to xdp_update_skb_frags_info() needs to be calculated
in a different way to reflect the new nr_frags.

Fixes: 87bcef158ac1 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for striding RQ")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Cc: Amery Hung <ameryhung@gmail.com>
Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260305142634.1813208-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index efcfcddab376..40e53a612989 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1957,14 +1957,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 
 	if (prog) {
 		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u8 new_nr_frags;
 		u32 len;
 
 		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 				struct mlx5e_frag_page *pfp;
 
-				frag_page -= old_nr_frags - sinfo->nr_frags;
-
 				for (pfp = head_page; pfp < frag_page; pfp++)
 					pfp->frags++;
 
@@ -1975,13 +1974,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
-		nr_frags_free = old_nr_frags - sinfo->nr_frags;
-		if (unlikely(nr_frags_free)) {
-			frag_page -= nr_frags_free;
+		new_nr_frags = sinfo->nr_frags;
+		nr_frags_free = old_nr_frags - new_nr_frags;
+		if (unlikely(nr_frags_free))
 			truesize -= (nr_frags_free - 1) * PAGE_SIZE +
 				ALIGN(pg_consumed_bytes,
 				      BIT(rq->mpwqe.log_stride_sz));
-		}
 
 		len = mxbuf->xdp.data_end - mxbuf->xdp.data;
 
@@ -2003,7 +2001,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 			struct mlx5e_frag_page *pagep;
 
 			/* sinfo->nr_frags is reset by build_skb, calculate again. */
-			xdp_update_skb_frags_info(skb, frag_page - head_page,
+			xdp_update_skb_frags_info(skb, new_nr_frags,
 						  sinfo->xdp_frags_size,
 						  truesize,
 						  xdp_buff_get_skb_flags(&mxbuf->xdp));
-- 
cgit v1.2.3


From a6413e6f6c9d9bb9833324cb3753582f7bc0f2fa Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 5 Mar 2026 16:26:34 +0200
Subject: net/mlx5e: RX, Fix XDP multi-buf frag counting for legacy RQ

XDP multi-buf programs can modify the layout of the XDP buffer when the
program calls bpf_xdp_pull_data() or bpf_xdp_adjust_tail(). The
referenced commit in the fixes tag corrected the assumption in the mlx5
driver that the XDP buffer layout doesn't change during a program
execution. However, this fix introduced another issue: the dropped
fragments still need to be counted on the driver side to avoid page
fragment reference counting issues.

Such issue can be observed with the
test_xdp_native_adjst_tail_shrnk_data selftest when using a payload of
3600 and shrinking by 256 bytes (an upcoming selftest patch): the last
fragment gets released by the XDP code but doesn't get tracked by the
driver. This results in a negative pp_ref_count during page release and
the following splat:

  WARNING: include/net/page_pool/helpers.h:297 at mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core], CPU#12: ip/3137
  Modules linked in: [...]
  CPU: 12 UID: 0 PID: 3137 Comm: ip Not tainted 6.19.0-rc3+ #12 NONE
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
  RIP: 0010:mlx5e_page_release_fragmented.isra.0+0x4a/0x50 [mlx5_core]
  [...]
  Call Trace:
   <TASK>
   mlx5e_dealloc_rx_wqe+0xcb/0x1a0 [mlx5_core]
   mlx5e_free_rx_descs+0x7f/0x110 [mlx5_core]
   mlx5e_close_rq+0x50/0x60 [mlx5_core]
   mlx5e_close_queues+0x36/0x2c0 [mlx5_core]
   mlx5e_close_channel+0x1c/0x50 [mlx5_core]
   mlx5e_close_channels+0x45/0x80 [mlx5_core]
   mlx5e_safe_switch_params+0x1a5/0x230 [mlx5_core]
   mlx5e_change_mtu+0xf3/0x2f0 [mlx5_core]
   netif_set_mtu_ext+0xf1/0x230
   do_setlink.isra.0+0x219/0x1180
   rtnl_newlink+0x79f/0xb60
   rtnetlink_rcv_msg+0x213/0x3a0
   netlink_rcv_skb+0x48/0xf0
   netlink_unicast+0x24a/0x350
   netlink_sendmsg+0x1ee/0x410
   __sock_sendmsg+0x38/0x60
   ____sys_sendmsg+0x232/0x280
   ___sys_sendmsg+0x78/0xb0
   __sys_sendmsg+0x5f/0xb0
   [...]
   do_syscall_64+0x57/0xc50

This patch fixes the issue by doing page frag counting on all the
original XDP buffer fragments for all relevant XDP actions (XDP_TX ,
XDP_REDIRECT and XDP_PASS). This is basically reverting to the original
counting before the commit in the fixes tag.

As frag_page is still pointing to the original tail, the nr_frags
parameter to xdp_update_skb_frags_info() needs to be calculated
in a different way to reflect the new nr_frags.

Fixes: afd5ba577c10 ("net/mlx5e: RX, Fix generating skb from non-linear xdp_buff for legacy RQ")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Link: https://patch.msgid.link/20260305142634.1813208-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 40e53a612989..268e20884757 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1589,6 +1589,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	struct skb_shared_info *sinfo;
 	u32 frag_consumed_bytes;
 	struct bpf_prog *prog;
+	u8 nr_frags_free = 0;
 	struct sk_buff *skb;
 	dma_addr_t addr;
 	u32 truesize;
@@ -1631,15 +1632,13 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog) {
-		u8 nr_frags_free, old_nr_frags = sinfo->nr_frags;
+		u8 old_nr_frags = sinfo->nr_frags;
 
 		if (mlx5e_xdp_handle(rq, prog, mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT,
 						 rq->flags)) {
 				struct mlx5e_wqe_frag_info *pwi;
 
-				wi -= old_nr_frags - sinfo->nr_frags;
-
 				for (pwi = head_wi; pwi < wi; pwi++)
 					pwi->frag_page->frags++;
 			}
@@ -1647,10 +1646,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		}
 
 		nr_frags_free = old_nr_frags - sinfo->nr_frags;
-		if (unlikely(nr_frags_free)) {
-			wi -= nr_frags_free;
+		if (unlikely(nr_frags_free))
 			truesize -= nr_frags_free * frag_info->frag_stride;
-		}
 	}
 
 	skb = mlx5e_build_linear_skb(
@@ -1666,7 +1663,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	if (xdp_buff_has_frags(&mxbuf->xdp)) {
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
-		xdp_update_skb_frags_info(skb, wi - head_wi - 1,
+		xdp_update_skb_frags_info(skb, wi - head_wi - nr_frags_free - 1,
 					  sinfo->xdp_frags_size, truesize,
 					  xdp_buff_get_skb_flags(&mxbuf->xdp));
 
-- 
cgit v1.2.3


From 5c3398a54266541610c8d0a7082e654e9ff3e259 Mon Sep 17 00:00:00 2001
From: Jian Zhang <zhangjian.3032@bytedance.com>
Date: Thu, 5 Mar 2026 14:06:55 +0800
Subject: net: ncsi: fix skb leak in error paths

Early return paths in NCSI RX and AEN handlers fail to release
the received skb, resulting in a memory leak.

Specifically, ncsi_aen_handler() returns on invalid AEN packets
without consuming the skb. Similarly, ncsi_rcv_rsp() exits early
when failing to resolve the NCSI device, response handler, or
request, leaving the skb unfreed.

CC: stable@vger.kernel.org
Fixes: 7a82ecf4cfb8 ("net/ncsi: NCSI AEN packet handler")
Fixes: 138635cc27c9 ("net/ncsi: NCSI response packet handler")
Signed-off-by: Jian Zhang <zhangjian.3032@bytedance.com>
Link: https://patch.msgid.link/20260305060656.3357250-1-zhangjian.3032@bytedance.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ncsi/ncsi-aen.c |  3 ++-
 net/ncsi/ncsi-rsp.c | 16 ++++++++++++----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 62fb1031763d..040a31557201 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -224,7 +224,8 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb)
 	if (!nah) {
 		netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n",
 			    h->type);
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out;
 	}
 
 	ret = ncsi_validate_aen_pkt(h, nah->payload);
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 271ec6c3929e..fbd84bc8026a 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -1176,8 +1176,10 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	/* Find the NCSI device */
 	nd = ncsi_find_dev(orig_dev);
 	ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL;
-	if (!ndp)
-		return -ENODEV;
+	if (!ndp) {
+		ret = -ENODEV;
+		goto err_free_skb;
+	}
 
 	/* Check if it is AEN packet */
 	hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb);
@@ -1199,7 +1201,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	if (!nrh) {
 		netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n",
 			   hdr->type);
-		return -ENOENT;
+		ret = -ENOENT;
+		goto err_free_skb;
 	}
 
 	/* Associate with the request */
@@ -1207,7 +1210,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	nr = &ndp->requests[hdr->id];
 	if (!nr->used) {
 		spin_unlock_irqrestore(&ndp->lock, flags);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_free_skb;
 	}
 
 	nr->rsp = skb;
@@ -1261,4 +1265,8 @@ out_netlink:
 out:
 	ncsi_free_request(nr);
 	return ret;
+
+err_free_skb:
+	kfree_skb(skb);
+	return ret;
 }
-- 
cgit v1.2.3


From 0cc0c2e661af418bbf7074179ea5cfffc0a5c466 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 4 Mar 2026 12:42:18 +0800
Subject: net/sched: teql: fix NULL pointer dereference in iptunnel_xmit on
 TEQL slave xmit

teql_master_xmit() calls netdev_start_xmit(skb, slave) to transmit
through slave devices, but does not update skb->dev to the slave device
beforehand.

When a gretap tunnel is a TEQL slave, the transmit path reaches
iptunnel_xmit() which saves dev = skb->dev (still pointing to teql0
master) and later calls iptunnel_xmit_stats(dev, pkt_len). This
function does:

    get_cpu_ptr(dev->tstats)

Since teql_master_setup() does not set dev->pcpu_stat_type to
NETDEV_PCPU_STAT_TSTATS, the core network stack never allocates tstats
for teql0, so dev->tstats is NULL. get_cpu_ptr(NULL) computes
NULL + __per_cpu_offset[cpu], resulting in a page fault.

 BUG: unable to handle page fault for address: ffff8880e6659018
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 68bc067 P4D 68bc067 PUD 0
 Oops: Oops: 0002 [#1] SMP KASAN PTI
 RIP: 0010:iptunnel_xmit (./include/net/ip_tunnels.h:664 net/ipv4/ip_tunnel_core.c:89)
 Call Trace:
  <TASK>
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  __gre_xmit (net/ipv4/ip_gre.c:478)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  teql_master_xmit (net/sched/sch_teql.c:319)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  neigh_direct_output (net/core/neighbour.c:1660)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  __ip_finish_output.part.0 (net/ipv4/ip_output.c:315)
  ip_mc_output (net/ipv4/ip_output.c:369)
  ip_send_skb (net/ipv4/ip_output.c:1508)
  udp_send_skb (net/ipv4/udp.c:1195)
  udp_sendmsg (net/ipv4/udp.c:1485)
  inet_sendmsg (net/ipv4/af_inet.c:859)
  __sys_sendto (net/socket.c:2206)

Fix this by setting skb->dev = slave before calling
netdev_start_xmit(), so that tunnel xmit functions see the correct
slave device with properly allocated tstats.

Fixes: 039f50629b7f ("ip_tunnel: Move stats update to iptunnel_xmit()")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260304044216.3517851-3-bestswngs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_teql.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 6e4bdaa876ed..783300d8b019 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -315,6 +315,7 @@ restart:
 			if (__netif_tx_trylock(slave_txq)) {
 				unsigned int length = qdisc_pkt_len(skb);
 
+				skb->dev = slave;
 				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
 				    netdev_start_xmit(skb, slave, slave_txq, false) ==
 				    NETDEV_TX_OK) {
-- 
cgit v1.2.3


From 976703cae7375898b445fc40d14faf849e916a4b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 5 Mar 2026 00:08:59 +0200
Subject: net: dsa: sja1105: reorder sja1105_reload_cbs() and
 phylink_replay_link_end()

Move phylink_replay_link_end() as the last locked operation under
sja1105_static_config_reload(). The purpose is to be able to goto
this step from the error path of intermediate steps (we must call
phylink_replay_link_end()).

sja1105_reload_cbs() notably does not depend on port states or link
speeds. See commit 954ad9bf13c4 ("net: dsa: sja1105: fix bandwidth
discrepancy between tc-cbs software and offload") which has discussed
this issue specifically.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260304220900.3865120-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 94d17b06da40..bf720d96bad8 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2339,13 +2339,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 			goto out;
 	}
 
+	rc = sja1105_reload_cbs(priv);
+
 	dsa_switch_for_each_available_port(dp, ds)
 		if (dp->pl)
 			phylink_replay_link_end(dp->pl);
-
-	rc = sja1105_reload_cbs(priv);
-	if (rc < 0)
-		goto out;
 out:
 	mutex_unlock(&priv->mgmt_lock);
 	mutex_unlock(&priv->fdb_lock);
-- 
cgit v1.2.3


From ce2da643f00af3111f1fffe2adea8506592ef6e5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 5 Mar 2026 00:09:00 +0200
Subject: net: dsa: sja1105: ensure phylink_replay_link_end() will not be
 missed

Most errors that can occur in sja1105_static_config_reload() are fatal
(example: fail to communicate with hardware), but not all are.

For example, sja1105_static_config_upload() -> kcalloc() may fail, and
if that happens, we have called phylink_replay_link_begin() but never
phylink_replay_link_end().

Under that circumstance, all port phylink instances are left in a state
where the resolver is stopped with the PHYLINK_DISABLE_REPLAY bit set.
We have effectively disabled link management with no way to recover from
this condition.

Avoid that situation by ensuring phylink_replay_link_begin() is always
paired with phylink_replay_link_end(), regardless of whether we faced
any errors during switch reset, configuration reload and general state
reload.

Fixes: 0b2edc531e0b ("net: dsa: sja1105: let phylink help with the replay of link callbacks")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20260304220900.3865120-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index bf720d96bad8..c72c2bfdcffb 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2341,10 +2341,11 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
 
 	rc = sja1105_reload_cbs(priv);
 
+out:
 	dsa_switch_for_each_available_port(dp, ds)
 		if (dp->pl)
 			phylink_replay_link_end(dp->pl);
-out:
+
 	mutex_unlock(&priv->mgmt_lock);
 	mutex_unlock(&priv->fdb_lock);
 
-- 
cgit v1.2.3


From 4245a79003adf30e67f8e9060915bd05cb31d142 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 5 Mar 2026 12:31:01 +0000
Subject: rxrpc, afs: Fix missing error pointer check after
 rxrpc_kernel_lookup_peer()

rxrpc_kernel_lookup_peer() can also return error pointers in addition to
NULL, so just checking for NULL is not sufficient.

Fix this by:

 (1) Changing rxrpc_kernel_lookup_peer() to return -ENOMEM rather than NULL
     on allocation failure.

 (2) Making the callers in afs use IS_ERR() and PTR_ERR() to pass on the
     error code returned.

Fixes: 72904d7b9bfb ("rxrpc, afs: Allow afs to pin rxrpc_peer objects")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/368272.1772713861@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/addr_list.c   | 8 ++++----
 net/rxrpc/af_rxrpc.c | 8 +++++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index a936f9ea5610..63bf096b721a 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -298,8 +298,8 @@ int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist,
 	srx.transport.sin.sin_addr.s_addr = xdr;
 
 	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
-	if (!peer)
-		return -ENOMEM;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
 
 	for (i = 0; i < alist->nr_ipv4; i++) {
 		if (peer == alist->addrs[i].peer) {
@@ -342,8 +342,8 @@ int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
 	memcpy(&srx.transport.sin6.sin6_addr, xdr, 16);
 
 	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
-	if (!peer)
-		return -ENOMEM;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
 
 	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
 		if (peer == alist->addrs[i].peer) {
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0c2c68c4b07e..0f90272ac254 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -267,12 +267,13 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * Lookup or create a remote transport endpoint record for the specified
  * address.
  *
- * Return: The peer record found with a reference, %NULL if no record is found
- * or a negative error code if the address is invalid or unsupported.
+ * Return: The peer record found with a reference or a negative error code if
+ * the address is invalid or unsupported.
  */
 struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
 					    struct sockaddr_rxrpc *srx, gfp_t gfp)
 {
+	struct rxrpc_peer *peer;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	int ret;
 
@@ -280,7 +281,8 @@ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	return rxrpc_lookup_peer(rx->local, srx, gfp);
+	peer = rxrpc_lookup_peer(rx->local, srx, gfp);
+	return peer ?: ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(rxrpc_kernel_lookup_peer);
 
-- 
cgit v1.2.3


From fbc7aef517d8765e4c425d2792409bb9bf2e1f13 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:24 -0800
Subject: bpf: Fix u32/s32 bounds when ranges cross min/max boundary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Same as in __reg64_deduce_bounds(), refine s32/u32 ranges
in __reg32_deduce_bounds() in the following situations:

- s32 range crosses U32_MAX/0 boundary, positive part of the s32 range
  overlaps with u32 range:

  0                                                   U32_MAX
  |  [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]              |
  |----------------------------|----------------------------|
  |xxxxx s32 range xxxxxxxxx]                       [xxxxxxx|
  0                     S32_MAX S32_MIN                    -1

- s32 range crosses U32_MAX/0 boundary, negative part of the s32 range
  overlaps with u32 range:

  0                                                   U32_MAX
  |              [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]  |
  |----------------------------|----------------------------|
  |xxxxxxxxx]                       [xxxxxxxxxxxx s32 range |
  0                     S32_MAX S32_MIN                    -1

- No refinement if ranges overlap in two intervals.

This helps for e.g. consider the following program:

   call %[bpf_get_prandom_u32];
   w0 &= 0xffffffff;
   if w0 < 0x3 goto 1f;    // on fall-through u32 range [3..U32_MAX]
   if w0 s> 0x1 goto 1f;   // on fall-through s32 range [S32_MIN..1]
   if w0 s< 0x0 goto 1f;   // range can be narrowed to  [S32_MIN..-1]
   r10 = 0;
1: ...;

The reg_bounds.c selftest is updated to incorporate identical logic,
refinement based on non-overflowing range halves:

  ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪
  ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1]))

Reported-by: Andrea Righi <arighi@nvidia.com>
Reported-by: Emil Tsalapatis <emil@etsalapatis.com>
Closes: https://lore.kernel.org/bpf/aakqucg4vcujVwif@gpd4/T/
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-1-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                              | 24 +++++++++
 .../testing/selftests/bpf/prog_tests/reg_bounds.c  | 62 ++++++++++++++++++++--
 2 files changed, 82 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 401d6c4960ec..f960b382fdb3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2511,6 +2511,30 @@ static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
 	if ((u32)reg->s32_min_value <= (u32)reg->s32_max_value) {
 		reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value);
 		reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value);
+	} else {
+		if (reg->u32_max_value < (u32)reg->s32_min_value) {
+			/* See __reg64_deduce_bounds() for detailed explanation.
+			 * Refine ranges in the following situation:
+			 *
+			 * 0                                                   U32_MAX
+			 * |  [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]              |
+			 * |----------------------------|----------------------------|
+			 * |xxxxx s32 range xxxxxxxxx]                       [xxxxxxx|
+			 * 0                     S32_MAX S32_MIN                    -1
+			 */
+			reg->s32_min_value = (s32)reg->u32_min_value;
+			reg->u32_max_value = min_t(u32, reg->u32_max_value, reg->s32_max_value);
+		} else if ((u32)reg->s32_max_value < reg->u32_min_value) {
+			/*
+			 * 0                                                   U32_MAX
+			 * |              [xxxxxxxxxxxxxx u32 range xxxxxxxxxxxxxx]  |
+			 * |----------------------------|----------------------------|
+			 * |xxxxxxxxx]                       [xxxxxxxxxxxx s32 range |
+			 * 0                     S32_MAX S32_MIN                    -1
+			 */
+			reg->s32_max_value = (s32)reg->u32_max_value;
+			reg->u32_min_value = max_t(u32, reg->u32_min_value, reg->s32_min_value);
+		}
 	}
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 0322f817d07b..04938d0d431b 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -422,15 +422,69 @@ static bool is_valid_range(enum num_t t, struct range x)
 	}
 }
 
-static struct range range_improve(enum num_t t, struct range old, struct range new)
+static struct range range_intersection(enum num_t t, struct range old, struct range new)
 {
 	return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b));
 }
 
+/*
+ * Result is precise when 'x' and 'y' overlap or form a continuous range,
+ * result is an over-approximation if 'x' and 'y' do not overlap.
+ */
+static struct range range_union(enum num_t t, struct range x, struct range y)
+{
+	if (!is_valid_range(t, x))
+		return y;
+	if (!is_valid_range(t, y))
+		return x;
+	return range(t, min_t(t, x.a, y.a), max_t(t, x.b, y.b));
+}
+
+/*
+ * This function attempts to improve x range intersecting it with y.
+ * range_cast(... to_t ...) looses precision for ranges that pass to_t
+ * min/max boundaries. To avoid such precision loses this function
+ * splits both x and y into halves corresponding to non-overflowing
+ * sub-ranges: [0, smin] and [smax, -1].
+ * Final result is computed as follows:
+ *
+ *   ((x ∩ [0, smax]) ∩ (y ∩ [0, smax])) ∪
+ *   ((x ∩ [smin,-1]) ∩ (y ∩ [smin,-1]))
+ *
+ * Precision might still be lost if final union is not a continuous range.
+ */
+static struct range range_refine_in_halves(enum num_t x_t, struct range x,
+					   enum num_t y_t, struct range y)
+{
+	struct range x_pos, x_neg, y_pos, y_neg, r_pos, r_neg;
+	u64 smax, smin, neg_one;
+
+	if (t_is_32(x_t)) {
+		smax = (u64)(u32)S32_MAX;
+		smin = (u64)(u32)S32_MIN;
+		neg_one = (u64)(u32)(s32)(-1);
+	} else {
+		smax = (u64)S64_MAX;
+		smin = (u64)S64_MIN;
+		neg_one = U64_MAX;
+	}
+	x_pos = range_intersection(x_t, x, range(x_t, 0, smax));
+	x_neg = range_intersection(x_t, x, range(x_t, smin, neg_one));
+	y_pos = range_intersection(y_t, y, range(x_t, 0, smax));
+	y_neg = range_intersection(y_t, y, range(y_t, smin, neg_one));
+	r_pos = range_intersection(x_t, x_pos, range_cast(y_t, x_t, y_pos));
+	r_neg = range_intersection(x_t, x_neg, range_cast(y_t, x_t, y_neg));
+	return range_union(x_t, r_pos, r_neg);
+
+}
+
 static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y)
 {
 	struct range y_cast;
 
+	if (t_is_32(x_t) == t_is_32(y_t))
+		x = range_refine_in_halves(x_t, x, y_t, y);
+
 	y_cast = range_cast(y_t, x_t, y);
 
 	/* If we know that
@@ -444,7 +498,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 	 */
 	if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX  && y_cast.b <= S32_MAX &&
 	    (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX)
-		return range_improve(x_t, x, y_cast);
+		return range_intersection(x_t, x, y_cast);
 
 	/* the case when new range knowledge, *y*, is a 32-bit subregister
 	 * range, while previous range knowledge, *x*, is a full register
@@ -462,7 +516,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 		x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b));
 		if (!is_valid_range(x_t, x_swap))
 			return x;
-		return range_improve(x_t, x, x_swap);
+		return range_intersection(x_t, x, x_swap);
 	}
 
 	if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
@@ -480,7 +534,7 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 	}
 
 	/* otherwise, plain range cast and intersection works */
-	return range_improve(x_t, x, y_cast);
+	return range_intersection(x_t, x, y_cast);
 }
 
 /* =======================
-- 
cgit v1.2.3


From f81fdfd16771e266753146bd83f6dd23515ebee9 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:25 -0800
Subject: selftests/bpf: test refining u32/s32 bounds when ranges cross min/max
 boundary

Two test cases for signed/unsigned 32-bit bounds refinement
when s32 range crosses the sign boundary:
- s32 range [S32_MIN..1] overlapping with u32 range [3..U32_MAX],
  s32 range tail before sign boundary overlaps with u32 range.
- s32 range [-3..5] overlapping with u32 range [0..S32_MIN+3],
  s32 range head after the sign boundary overlaps with u32 range.

This covers both branches added in the __reg32_deduce_bounds().

Also, crossing_32_bit_signed_boundary_2() no longer triggers invariant
violations.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Reviewed-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-2-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/progs/verifier_bounds.c  | 39 +++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 97065a26cf70..e526315c718a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -1148,7 +1148,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
 __success __retval(0)
-__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
+__flag(BPF_F_TEST_REG_INVARIANTS)
 __naked void crossing_32_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -2000,4 +2000,41 @@ __naked void bounds_refinement_multiple_overlaps(void *ctx)
 	: __clobber_all);
 }
 
+SEC("socket")
+__success
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void signed_unsigned_intersection32_case1(void *ctx)
+{
+	asm volatile("									\
+	call %[bpf_get_prandom_u32];							\
+	w0 &= 0xffffffff;								\
+	if w0 < 0x3 goto 1f;		/* on fall-through u32 range [3..U32_MAX]  */	\
+	if w0 s> 0x1 goto 1f;		/* on fall-through s32 range [S32_MIN..1]  */	\
+	if w0 s< 0x0 goto 1f;		/* range can be narrowed to  [S32_MIN..-1] */	\
+	r10 = 0;			/* thus predicting the jump. */			\
+1:	exit;										\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void signed_unsigned_intersection32_case2(void *ctx)
+{
+	asm volatile("									\
+	call %[bpf_get_prandom_u32];							\
+	w0 &= 0xffffffff;								\
+	if w0 > 0x80000003 goto 1f;	/* on fall-through u32 range [0..S32_MIN+3] */	\
+	if w0 s< -3 goto 1f;		/* on fall-through s32 range [-3..S32_MAX] */	\
+	if w0 s> 5 goto 1f;		/* on fall-through s32 range [-3..5] */		\
+	if w0 <= 5 goto 1f;		/* range can be narrowed to  [0..5] */		\
+	r10 = 0;			/* thus predicting the jump */			\
+1:	exit;										\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From d87c9305a8841b312b14ca0c360a563ef60b2a5b Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:54:26 -0800
Subject: Revert "selftests/bpf: Update reg_bound range refinement logic"

This reverts commit da653de268d32a80e135c9eb960a8147c186f1bc.
Removed logic is now covered by range_refine_in_halves()
which handles both 32-bit and 64-bit refinements.

Suggested-by: Paul Chaignon <paul.chaignon@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-bpf-32-bit-range-overflow-v3-3-f7f67e060a6b@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/reg_bounds.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index 04938d0d431b..cb8dd2f63296 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -519,20 +519,6 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t,
 		return range_intersection(x_t, x, x_swap);
 	}
 
-	if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
-		if (x_t == S64 && x.a > x.b) {
-			if (x.b < y.a && x.a <= y.b)
-				return range(x_t, x.a, y.b);
-			if (x.a > y.b && x.b >= y.a)
-				return range(x_t, y.a, x.b);
-		} else if (x_t == U64 && y.a > y.b) {
-			if (y.b < x.a && y.a <= x.b)
-				return range(x_t, y.a, x.b);
-			if (y.a > x.b && y.b >= x.a)
-				return range(x_t, x.a, y.b);
-		}
-	}
-
 	/* otherwise, plain range cast and intersection works */
 	return range_intersection(x_t, x, y_cast);
 }
-- 
cgit v1.2.3


From 3aa1417803c1833cbd5bacb7e6a6489a196f2519 Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Thu, 5 Mar 2026 14:39:38 +0800
Subject: net: spacemit: Fix error handling in emac_alloc_rx_desc_buffers()

Even if we get a dma_mapping_error() while mapping an RX buffer, we
should still update rx_ring->head to ensure that the buffers we were
able to allocate and map are used. Fix this by breaking out to the
existing code after the loop, analogous to the existing handling for skb
allocation failure.

Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC")
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-1-e4e434d65055@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/spacemit/k1_emac.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c
index 338a2637b1da..5a5cb61be08c 100644
--- a/drivers/net/ethernet/spacemit/k1_emac.c
+++ b/drivers/net/ethernet/spacemit/k1_emac.c
@@ -565,7 +565,9 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv)
 						  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&priv->pdev->dev, rx_buf->dma_addr)) {
 			dev_err_ratelimited(&ndev->dev, "Mapping skb failed\n");
-			goto err_free_skb;
+			dev_kfree_skb_any(skb);
+			rx_buf->skb = NULL;
+			break;
 		}
 
 		rx_desc_addr = &((struct emac_desc *)rx_ring->desc_addr)[i];
@@ -590,10 +592,6 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv)
 
 	rx_ring->head = i;
 	return;
-
-err_free_skb:
-	dev_kfree_skb_any(skb);
-	rx_buf->skb = NULL;
 }
 
 /* Returns number of packets received */
-- 
cgit v1.2.3


From 86292155bea578ebab0ca3b65d4d87ecd8a0e9ea Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Thu, 5 Mar 2026 14:39:39 +0800
Subject: net: spacemit: Fix error handling in emac_tx_mem_map()

The DMA mappings were leaked on mapping error. Free them with the
existing emac_free_tx_buf() function.

Fixes: bfec6d7f2001 ("net: spacemit: Add K1 Ethernet MAC")
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://patch.msgid.link/20260305-k1-ethernet-more-fixes-v2-2-e4e434d65055@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/spacemit/k1_emac.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c
index 5a5cb61be08c..15d43e4a748b 100644
--- a/drivers/net/ethernet/spacemit/k1_emac.c
+++ b/drivers/net/ethernet/spacemit/k1_emac.c
@@ -733,7 +733,7 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb)
 	struct emac_desc tx_desc, *tx_desc_addr;
 	struct device *dev = &priv->pdev->dev;
 	struct emac_tx_desc_buffer *tx_buf;
-	u32 head, old_head, frag_num, f;
+	u32 head, old_head, frag_num, f, i;
 	bool buf_idx;
 
 	frag_num = skb_shinfo(skb)->nr_frags;
@@ -801,6 +801,15 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb)
 
 err_free_skb:
 	dev_dstats_tx_dropped(priv->ndev);
+
+	i = old_head;
+	while (i != head) {
+		emac_free_tx_buf(priv, i);
+
+		if (++i == tx_ring->total_cnt)
+			i = 0;
+	}
+
 	dev_kfree_skb_any(skb);
 }
 
-- 
cgit v1.2.3


From d008ba8be8984760e36d7dcd4adbd5a41a645708 Mon Sep 17 00:00:00 2001
From: Calvin Owens <calvin@wbinvd.org>
Date: Fri, 6 Mar 2026 19:19:25 -0800
Subject: tracing: Fix trace_buf_size= cmdline parameter with sizes >= 2G

Some of the sizing logic through tracer_alloc_buffers() uses int
internally, causing unexpected behavior if the user passes a value that
does not fit in an int (on my x86 machine, the result is uselessly tiny
buffers).

Fix by plumbing the parameter's real type (unsigned long) through to the
ring buffer allocation functions, which already use unsigned long.

It has always been possible to create larger ring buffers via the sysfs
interface: this only affects the cmdline parameter.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/bff42a4288aada08bdf74da3f5b67a2c28b761f8.1772852067.git.calvin@wbinvd.org
Fixes: 73c5162aa362 ("tracing: keep ring buffer to minimum size till used")
Signed-off-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1e7c032a72d2..ebd996f8710e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9350,7 +9350,7 @@ static void setup_trace_scratch(struct trace_array *tr,
 }
 
 static int
-allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size)
+allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size)
 {
 	enum ring_buffer_flags rb_flags;
 	struct trace_scratch *tscratch;
@@ -9405,7 +9405,7 @@ static void free_trace_buffer(struct array_buffer *buf)
 	}
 }
 
-static int allocate_trace_buffers(struct trace_array *tr, int size)
+static int allocate_trace_buffers(struct trace_array *tr, unsigned long size)
 {
 	int ret;
 
@@ -10769,7 +10769,7 @@ __init static void enable_instances(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	int ring_buf_size;
+	unsigned long ring_buf_size;
 	int ret = -ENOMEM;
 
 
-- 
cgit v1.2.3


From 2658a1720a1944fbaeda937000ad2b3c3dfaf1bb Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:02:47 -0800
Subject: bpf: collect only live registers in linked regs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix an inconsistency between func_states_equal() and
collect_linked_regs():
- regsafe() uses check_ids() to verify that cached and current states
  have identical register id mapping.
- func_states_equal() calls regsafe() only for registers computed as
  live by compute_live_registers().
- clean_live_states() is supposed to remove dead registers from cached
  states, but it can skip states belonging to an iterator-based loop.
- collect_linked_regs() collects all registers sharing the same id,
  ignoring the marks computed by compute_live_registers().
  Linked registers are stored in the state's jump history.
- backtrack_insn() marks all linked registers for an instruction
  as precise whenever one of the linked registers is precise.

The above might lead to a scenario:
- There is an instruction I with register rY known to be dead at I.
- Instruction I is reached via two paths: first A, then B.
- On path A:
  - There is an id link between registers rX and rY.
  - Checkpoint C is created at I.
  - Linked register set {rX, rY} is saved to the jump history.
  - rX is marked as precise at I, causing both rX and rY
    to be marked precise at C.
- On path B:
  - There is no id link between registers rX and rY,
    otherwise register states are sub-states of those in C.
  - Because rY is dead at I, check_ids() returns true.
  - Current state is considered equal to checkpoint C,
    propagate_precision() propagates spurious precision
    mark for register rY along the path B.
  - Depending on a program, this might hit verifier_bug()
    in the backtrack_insn(), e.g. if rY ∈  [r1..r5]
    and backtrack_insn() spots a function call.

The reproducer program is in the next patch.
This was hit by sched_ext scx_lavd scheduler code.

Changes in tests:
- verifier_scalar_ids.c selftests need modification to preserve
  some registers as live for __msg() checks.
- exceptions_assert.c adjusted to match changes in the verifier log,
  R0 is dead after conditional instruction and thus does not get
  range.
- precise.c adjusted to match changes in the verifier log, register r9
  is dead after comparison and it's range is not important for test.

Reported-by: Emil Tsalapatis <emil@etsalapatis.com>
Fixes: 0fb3cf6110a5 ("bpf: use register liveness information for func_states_equal")
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-linked-regs-and-propagate-precision-v1-1-18e859be570d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                              | 13 +++--
 .../selftests/bpf/progs/exceptions_assert.c        | 34 ++++++-------
 .../selftests/bpf/progs/verifier_scalar_ids.c      | 56 ++++++++++++++++------
 tools/testing/selftests/bpf/verifier/precise.c     |  8 ++--
 4 files changed, 73 insertions(+), 38 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f960b382fdb3..836ceb128d19 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17359,17 +17359,24 @@ static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_st
  * in verifier state, save R in linked_regs if R->id == id.
  * If there are too many Rs sharing same id, reset id for leftover Rs.
  */
-static void collect_linked_regs(struct bpf_verifier_state *vstate, u32 id,
+static void collect_linked_regs(struct bpf_verifier_env *env,
+				struct bpf_verifier_state *vstate,
+				u32 id,
 				struct linked_regs *linked_regs)
 {
+	struct bpf_insn_aux_data *aux = env->insn_aux_data;
 	struct bpf_func_state *func;
 	struct bpf_reg_state *reg;
+	u16 live_regs;
 	int i, j;
 
 	id = id & ~BPF_ADD_CONST;
 	for (i = vstate->curframe; i >= 0; i--) {
+		live_regs = aux[frame_insn_idx(vstate, i)].live_regs_before;
 		func = vstate->frame[i];
 		for (j = 0; j < BPF_REG_FP; j++) {
+			if (!(live_regs & BIT(j)))
+				continue;
 			reg = &func->regs[j];
 			__collect_linked_regs(linked_regs, reg, id, i, j, true);
 		}
@@ -17584,9 +17591,9 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	 * if parent state is created.
 	 */
 	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id)
-		collect_linked_regs(this_branch, src_reg->id, &linked_regs);
+		collect_linked_regs(env, this_branch, src_reg->id, &linked_regs);
 	if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
-		collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
+		collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs);
 	if (linked_regs.cnt > 1) {
 		err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
 		if (err)
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index a01c2736890f..858af5988a38 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -18,43 +18,43 @@
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0=0xffffffff80000000")
+__msg("R{{.}}=0xffffffff80000000")
 check_assert(s64, ==, eq_int_min, INT_MIN);
-__msg(": R0=0x7fffffff")
+__msg("R{{.}}=0x7fffffff")
 check_assert(s64, ==, eq_int_max, INT_MAX);
-__msg(": R0=0")
+__msg("R{{.}}=0")
 check_assert(s64, ==, eq_zero, 0);
-__msg(": R0=0x8000000000000000 R1=0x8000000000000000")
+__msg("R{{.}}=0x8000000000000000")
 check_assert(s64, ==, eq_llong_min, LLONG_MIN);
-__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff")
+__msg("R{{.}}=0x7fffffffffffffff")
 check_assert(s64, ==, eq_llong_max, LLONG_MAX);
 
-__msg(": R0=scalar(id=1,smax=0x7ffffffe)")
+__msg("R{{.}}=scalar(id=1,smax=0x7ffffffe)")
 check_assert(s64, <, lt_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
 check_assert(s64, <, lt_zero, 0);
-__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff")
+__msg("R{{.}}=scalar(id=1,smax=0xffffffff7fffffff")
 check_assert(s64, <, lt_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smax=0x7fffffff)")
+__msg("R{{.}}=scalar(id=1,smax=0x7fffffff)")
 check_assert(s64, <=, le_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smax=0)")
+__msg("R{{.}}=scalar(id=1,smax=0)")
 check_assert(s64, <=, le_zero, 0);
-__msg(": R0=scalar(id=1,smax=0xffffffff80000000")
+__msg("R{{.}}=scalar(id=1,smax=0xffffffff80000000")
 check_assert(s64, <=, le_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >, gt_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >, gt_zero, 0);
-__msg(": R0=scalar(id=1,smin=0xffffffff80000001")
+__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000001")
 check_assert(s64, >, gt_neg, INT_MIN);
 
-__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >=, ge_pos, INT_MAX);
-__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+__msg("R{{.}}=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
 check_assert(s64, >=, ge_zero, 0);
-__msg(": R0=scalar(id=1,smin=0xffffffff80000000")
+__msg("R{{.}}=scalar(id=1,smin=0xffffffff80000000")
 check_assert(s64, >=, ge_neg, INT_MIN);
 
 SEC("?tc")
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
index 3072fee9a448..58c7704d61cd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -40,6 +40,9 @@ __naked void linked_regs_bpf_k(void)
 	 */
 	"r3 = r10;"
 	"r3 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -73,6 +76,9 @@ __naked void linked_regs_bpf_x_src(void)
 	 */
 	"r4 = r10;"
 	"r4 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -106,6 +112,10 @@ __naked void linked_regs_bpf_x_dst(void)
 	 */
 	"r4 = r10;"
 	"r4 += r3;"
+	/* Mark r1 and r2 as alive. */
+	"r0 = r0;"
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -143,6 +153,9 @@ __naked void linked_regs_broken_link(void)
 	 */
 	"r3 = r10;"
 	"r3 += r0;"
+	/* Mark r1 and r2 as alive. */
+	"r1 = r1;"
+	"r2 = r2;"
 	"r0 = 0;"
 	"exit;"
 	:
@@ -156,16 +169,16 @@ __naked void linked_regs_broken_link(void)
  */
 SEC("socket")
 __success __log_level(2)
-__msg("12: (0f) r2 += r1")
+__msg("17: (0f) r2 += r1")
 /* Current state */
-__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ")
-__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10")
+__msg("frame2: last_idx 17 first_idx 14 subseq_idx -1 ")
+__msg("frame2: regs=r1 stack= before 16: (bf) r2 = r10")
 __msg("frame2: parent state regs=r1 stack=")
 __msg("frame1: parent state regs= stack=")
 __msg("frame0: parent state regs= stack=")
 /* Parent state */
-__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ")
-__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0")
+__msg("frame2: last_idx 13 first_idx 13 subseq_idx 14 ")
+__msg("frame2: regs=r1 stack= before 13: (25) if r1 > 0x7 goto pc+0")
 __msg("frame2: parent state regs=r1 stack=")
 /* frame1.r{6,7} are marked because mark_precise_scalar_ids()
  * looks for all registers with frame2.r1.id in the current state
@@ -173,20 +186,20 @@ __msg("frame2: parent state regs=r1 stack=")
 __msg("frame1: parent state regs=r6,r7 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10")
-__msg("frame2: regs=r1 stack= before 8: (85) call pc+1")
+__msg("frame2: last_idx 9 first_idx 9 subseq_idx 13")
+__msg("frame2: regs=r1 stack= before 9: (85) call pc+3")
 /* frame1.r1 is marked because of backtracking of call instruction */
 __msg("frame1: parent state regs=r1,r6,r7 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8")
-__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1")
-__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1")
+__msg("frame1: last_idx 8 first_idx 7 subseq_idx 9")
+__msg("frame1: regs=r1,r6,r7 stack= before 8: (bf) r7 = r1")
+__msg("frame1: regs=r1,r6 stack= before 7: (bf) r6 = r1")
 __msg("frame1: parent state regs=r1 stack=")
 __msg("frame0: parent state regs=r6 stack=")
 /* Parent state */
-__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6")
-__msg("frame1: regs=r1 stack= before 4: (85) call pc+1")
+__msg("frame1: last_idx 4 first_idx 4 subseq_idx 7")
+__msg("frame1: regs=r1 stack= before 4: (85) call pc+2")
 __msg("frame0: parent state regs=r1,r6 stack=")
 /* Parent state */
 __msg("frame0: last_idx 3 first_idx 1 subseq_idx 4")
@@ -204,6 +217,7 @@ __naked void precision_many_frames(void)
 	"r1 = r0;"
 	"r6 = r0;"
 	"call precision_many_frames__foo;"
+	"r6 = r6;" /* mark r6 as live */
 	"exit;"
 	:
 	: __imm(bpf_ktime_get_ns)
@@ -220,6 +234,8 @@ void precision_many_frames__foo(void)
 	"r6 = r1;"
 	"r7 = r1;"
 	"call precision_many_frames__bar;"
+	"r6 = r6;" /* mark r6 as live */
+	"r7 = r7;" /* mark r7 as live */
 	"exit"
 	::: __clobber_all);
 }
@@ -229,6 +245,8 @@ void precision_many_frames__bar(void)
 {
 	asm volatile (
 	"if r1 > 7 goto +0;"
+	"r6 = 0;" /* mark r6 as live */
+	"r7 = 0;" /* mark r7 as live */
 	/* force r1 to be precise, this eventually marks:
 	 * - bar frame r1
 	 * - foo frame r{1,6,7}
@@ -340,6 +358,8 @@ __naked void precision_two_ids(void)
 	"r3 += r7;"
 	/* force r9 to be precise, this also marks r8 */
 	"r3 += r9;"
+	"r6 = r6;" /* mark r6 as live */
+	"r8 = r8;" /* mark r8 as live */
 	"exit;"
 	:
 	: __imm(bpf_ktime_get_ns)
@@ -353,7 +373,7 @@ __flag(BPF_F_TEST_STATE_FREQ)
  * collect_linked_regs() can't tie more than 6 registers for a single insn.
  */
 __msg("8: (25) if r0 > 0x7 goto pc+0         ; R0=scalar(id=1")
-__msg("9: (bf) r6 = r6                       ; R6=scalar(id=2")
+__msg("14: (bf) r6 = r6                      ; R6=scalar(id=2")
 /* check that r{0-5} are marked precise after 'if' */
 __msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
 __msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
@@ -372,6 +392,12 @@ __naked void linked_regs_too_many_regs(void)
 	"r6 = r0;"
 	/* propagate range for r{0-6} */
 	"if r0 > 7 goto +0;"
+	/* keep r{1-5} live */
+	"r1 = r1;"
+	"r2 = r2;"
+	"r3 = r3;"
+	"r4 = r4;"
+	"r5 = r5;"
 	/* make r6 appear in the log */
 	"r6 = r6;"
 	/* force r0 to be precise,
@@ -517,7 +543,7 @@ __naked void check_ids_in_regsafe_2(void)
 	"*(u64*)(r10 - 8) = r1;"
 	/* r9 = pointer to stack */
 	"r9 = r10;"
-	"r9 += -8;"
+	"r9 += -16;"
 	/* r8 = ktime_get_ns() */
 	"call %[bpf_ktime_get_ns];"
 	"r8 = r0;"
@@ -538,6 +564,8 @@ __naked void check_ids_in_regsafe_2(void)
 	"if r7 > 4 goto l2_%=;"
 	/* Access memory at r9[r6] */
 	"r9 += r6;"
+	"r9 += r7;"
+	"r9 += r8;"
 	"r0 = *(u8*)(r9 + 0);"
 "l2_%=:"
 	"r0 = 0;"
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 061d98f6e9bb..a9242103dc47 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -44,9 +44,9 @@
 	mark_precise: frame0: regs=r2 stack= before 23\
 	mark_precise: frame0: regs=r2 stack= before 22\
 	mark_precise: frame0: regs=r2 stack= before 20\
-	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 10\
-	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r2 stack= before 19\
 	mark_precise: frame0: regs=r9 stack= before 18\
 	mark_precise: frame0: regs=r8,r9 stack= before 17\
 	mark_precise: frame0: regs=r0,r9 stack= before 15\
@@ -107,9 +107,9 @@
 	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 20 first_idx 20\
 	mark_precise: frame0: regs=r2 stack= before 20\
-	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: parent state regs=r2 stack=:\
 	mark_precise: frame0: last_idx 19 first_idx 17\
-	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r2 stack= before 19\
 	mark_precise: frame0: regs=r9 stack= before 18\
 	mark_precise: frame0: regs=r8,r9 stack= before 17\
 	mark_precise: frame0: parent state regs= stack=:",
-- 
cgit v1.2.3


From 223ffb6a3d0582522455e83ccf7ad2d3a753e039 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 6 Mar 2026 16:02:48 -0800
Subject: selftests/bpf: add reproducer for spurious precision propagation
 through calls

Add a test for the scenario described in the previous commit:
an iterator loop with two paths where one ties r2/r7 via
shared scalar id and skips a call, while the other goes
through the call. Precision marks from the linked registers
get spuriously propagated to the call path via
propagate_precision(), hitting "backtracking call unexpected
regs" in backtrack_insn().

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260306-linked-regs-and-propagate-precision-v1-2-18e859be570d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/verifier_linked_scalars.c  | 64 ++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
index 2ef346c827c2..7bf7dbfd237d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
@@ -363,4 +363,68 @@ void alu32_negative_offset(void)
 	__sink(path[0]);
 }
 
+void dummy_calls(void)
+{
+	bpf_iter_num_new(0, 0, 0);
+	bpf_iter_num_next(0);
+	bpf_iter_num_destroy(0);
+}
+
+SEC("socket")
+__success
+__flag(BPF_F_TEST_STATE_FREQ)
+int spurious_precision_marks(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile(
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 4f;"
+		"r7 = *(u32 *)(r0 + 0);"
+		"r8 = *(u32 *)(r0 + 0);"
+		/* This jump can't be predicted and does not change r7 or r8 state. */
+		"if r7 > r8 goto 2f;"
+		/* Branch explored first ties r2 and r7 as having the same id. */
+		"r2 = r7;"
+		"goto 3f;"
+	"2:"
+		/* Branch explored second does not tie r2 and r7 but has a function call. */
+		"call %[bpf_get_prandom_u32];"
+	"3:"
+		/*
+		 * A checkpoint.
+		 * When first branch is explored, this would inject linked registers
+		 * r2 and r7 into the jump history.
+		 * When second branch is explored, this would be a cache hit point,
+		 * triggering propagate_precision().
+		 */
+		"if r7 <= 42 goto +0;"
+		/*
+		 * Mark r7 as precise using an if condition that is always true.
+		 * When reached via the second branch, this triggered a bug in the backtrack_insn()
+		 * because r2 (tied to r7) was propagated as precise to a call.
+		 */
+		"if r7 <= 0xffffFFFF goto +0;"
+		"goto 1b;"
+	"4:"
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_common, "r7", "r8"
+	);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 73cdf24e81e4eba52a40a6b10c6cf285d0ac23fd Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:24 +0530
Subject: powerpc64: make clang cross-build friendly

ARCH_USING_PATCHABLE_FUNCTION_ENTRY depends on toolchain support for
-fpatchable-function-entry option. The current script that checks
for this support only handles GCC. Rename the script and extend it
to detect support for -fpatchable-function-entry with Clang as well,
allowing clean cross-compilation with Clang toolchains.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-2-hbathini@linux.ibm.com
---
 arch/powerpc/Kconfig                               |  4 ++--
 .../tools/check-fpatchable-function-entry.sh       | 25 ++++++++++++++++++++++
 .../tools/gcc-check-fpatchable-function-entry.sh   | 25 ----------------------
 3 files changed, 27 insertions(+), 27 deletions(-)
 create mode 100755 arch/powerpc/tools/check-fpatchable-function-entry.sh
 delete mode 100755 arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ad7a2fe63a2a..10240cb80904 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -573,8 +573,8 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
 	depends on FUNCTION_TRACER && (PPC32 || PPC64_ELF_ABI_V2)
 	depends on $(cc-option,-fpatchable-function-entry=2)
 	def_bool y if PPC32
-	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
-	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) $(CLANG_FLAGS) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
+	def_bool $(success,$(srctree)/arch/powerpc/tools/check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
 
 config PPC_FTRACE_OUT_OF_LINE
 	def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY
diff --git a/arch/powerpc/tools/check-fpatchable-function-entry.sh b/arch/powerpc/tools/check-fpatchable-function-entry.sh
new file mode 100755
index 000000000000..baed467a016b
--- /dev/null
+++ b/arch/powerpc/tools/check-fpatchable-function-entry.sh
@@ -0,0 +1,25 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# To debug, uncomment the following line
+# set -x
+
+# Output from -fpatchable-function-entry can only vary on ppc64 elfv2, so this
+# should not be invoked for other targets. Therefore we can pass in -m64 and
+# -mabi explicitly, to take care of toolchains defaulting to other targets.
+
+# Test whether the compile option -fpatchable-function-entry exists and
+# generates appropriate code
+echo "int func() { return 0; }" | \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+    grep -q "__patchable_function_entries"
+
+# Test whether nops are generated after the local entry point
+echo "int x; int func() { return x; }" | \
+    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
+    awk 'BEGIN { RS = ";" } /\.localentry.*nop.*\n[[:space:]]*nop/ { print $0 }' | \
+    grep -q "func:"
+
+exit 0
diff --git a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh b/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
deleted file mode 100755
index baed467a016b..000000000000
--- a/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-set -e
-
-# To debug, uncomment the following line
-# set -x
-
-# Output from -fpatchable-function-entry can only vary on ppc64 elfv2, so this
-# should not be invoked for other targets. Therefore we can pass in -m64 and
-# -mabi explicitly, to take care of toolchains defaulting to other targets.
-
-# Test whether the compile option -fpatchable-function-entry exists and
-# generates appropriate code
-echo "int func() { return 0; }" | \
-    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
-    grep -q "__patchable_function_entries"
-
-# Test whether nops are generated after the local entry point
-echo "int x; int func() { return x; }" | \
-    $* -m64 -mabi=elfv2 -S -x c -O2 -fpatchable-function-entry=2 - -o - 2> /dev/null | \
-    awk 'BEGIN { RS = ";" } /\.localentry.*nop.*\n[[:space:]]*nop/ { print $0 }' | \
-    grep -q "func:"
-
-exit 0
-- 
cgit v1.2.3


From 875612a7745013a43c67493cb0583ee3f7476344 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:25 +0530
Subject: powerpc64/ftrace: fix OOL stub count with clang

The total number of out-of-line (OOL) stubs required for function
tracing is determined using the following command:

    $(OBJDUMP) -r -j __patchable_function_entries vmlinux.o

While this works correctly with GNU objdump, llvm-objdump does not
list the expected relocation records for this section. Fix this by
using the -d option and counting R_PPC64_ADDR64 relocation entries.
This works as desired with both objdump and llvm-objdump.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-3-hbathini@linux.ibm.com
---
 arch/powerpc/tools/ftrace-gen-ool-stubs.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
index bac186bdf64a..9218d43aeb54 100755
--- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
+++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
@@ -15,9 +15,9 @@ if [ -z "$is_64bit" ]; then
 	RELOCATION=R_PPC_ADDR32
 fi
 
-num_ool_stubs_total=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+num_ool_stubs_total=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" |
 		      grep -c "$RELOCATION")
-num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries "$vmlinux_o" |
+num_ool_stubs_inittext=$($objdump -r -j __patchable_function_entries -d "$vmlinux_o" |
 			 grep -e ".init.text" -e ".text.startup" | grep -c "$RELOCATION")
 num_ool_stubs_text=$((num_ool_stubs_total - num_ool_stubs_inittext))
 
-- 
cgit v1.2.3


From db54c28702f7270e74dce36c84cb0db4cec96389 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 27 Jan 2026 14:19:26 +0530
Subject: powerpc64/ftrace: workaround clang recording GEP in
 __patchable_function_entries

Support for -fpatchable-function-entry on ppc64le was added in Clang
with [1]. However, when no prefix NOPs are specified - as is the case
with CONFIG_PPC_FTRACE_OUT_OF_LINE - the first NOP is emitted at LEP,
but Clang records the Global Entry Point (GEP) unlike GCC which does
record the Local Entry Point (LEP). Issue [2] has been raised to align
Clang's behavior with GCC. As a temporary workaround to ensure ftrace
initialization works as expected with Clang, derive the LEP using
ppc_function_entry() for kernel symbols and by looking for the below
module GEP sequence for module addresses, until [2] is resolved:

	ld	r2, -8(r12)
	add	r2, r2, r12

[1] https://github.com/llvm/llvm-project/pull/151569
[2] https://github.com/llvm/llvm-project/issues/163706

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260127084926.34497-4-hbathini@linux.ibm.com
---
 arch/powerpc/kernel/trace/ftrace.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 841d077e2825..1b2f293e7dcb 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -37,11 +37,29 @@ unsigned long ftrace_call_adjust(unsigned long addr)
 	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
 		return 0;
 
-	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
-	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
-		addr += MCOUNT_INSN_SIZE;
-		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) {
+		if (!IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 			addr += MCOUNT_INSN_SIZE;
+			if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+				addr += MCOUNT_INSN_SIZE;
+		} else if (IS_ENABLED(CONFIG_CC_IS_CLANG) && IS_ENABLED(CONFIG_PPC64)) {
+			/*
+			 * addr points to global entry point though the NOP was emitted at local
+			 * entry point due to https://github.com/llvm/llvm-project/issues/163706
+			 * Handle that here with ppc_function_entry() for kernel symbols while
+			 * adjusting module addresses in the else case, by looking for the below
+			 * module global entry point sequence:
+			 *	ld    r2, -8(r12)
+			 *	add   r2, r2, r12
+			 */
+			if (is_kernel_text(addr) || is_kernel_inittext(addr))
+				addr = ppc_function_entry((void *)addr);
+			else if ((ppc_inst_val(ppc_inst_read((u32 *)addr)) ==
+				  PPC_RAW_LD(_R2, _R12, -8)) &&
+				 (ppc_inst_val(ppc_inst_read((u32 *)(addr+4))) ==
+				  PPC_RAW_ADD(_R2, _R2, _R12)))
+				addr += 8;
+		}
 	}
 
 	return addr;
-- 
cgit v1.2.3


From 521bd39d9d28ce54cbfec7f9b89c94ad4fdb8350 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:25 +0530
Subject: powerpc64/bpf: do not increment tailcall count when prog is NULL

Do not increment tailcall count, if tailcall did not succeed due to
missing BPF program.

Fixes: ce0761419fae ("powerpc/bpf: Implement support for tail calls")
Cc: stable@vger.kernel.org
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-2-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp64.c | 39 +++++++++++++++++++++------------------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index b1a3945ccc9f..44ce8a8783f9 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -522,9 +522,30 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 
 	/*
 	 * tail_call_info++; <- Actual value of tcc here
+	 * Writeback this updated value only if tailcall succeeds.
 	 */
 	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1));
 
+	/* prog = array->ptrs[index]; */
+	EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_2), b2p_index, 8));
+	EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2), b2p_bpf_array));
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			offsetof(struct bpf_array, ptrs)));
+
+	/*
+	 * if (prog == NULL)
+	 *   goto out;
+	 */
+	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), 0));
+	PPC_BCC_SHORT(COND_EQ, out);
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			offsetof(struct bpf_prog, bpf_func)));
+	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			  FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size));
+	EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_2)));
+
 	/*
 	 * Before writing updated tail_call_info, distinguish if current frame
 	 * is storing a reference to tail_call_info or actual tcc value in
@@ -539,24 +560,6 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	/* Writeback updated value to tail_call_info */
 	EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0));
 
-	/* prog = array->ptrs[index]; */
-	EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8));
-	EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), b2p_bpf_array));
-	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_array, ptrs)));
-
-	/*
-	 * if (prog == NULL)
-	 *   goto out;
-	 */
-	EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), 0));
-	PPC_BCC_SHORT(COND_EQ, out);
-
-	/* goto *(prog->bpf_func + prologue_size); */
-	EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_prog, bpf_func)));
-	EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1),
-			FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size));
-	EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1)));
-
 	/* tear down stack, restore NVRs, ... */
 	bpf_jit_emit_common_epilogue(image, ctx);
 
-- 
cgit v1.2.3


From 157820264ac3dadfafffad63184b883eb28f9ae0 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:26 +0530
Subject: powerpc64/bpf: fix the address returned by bpf_get_func_ip

bpf_get_func_ip() helper function returns the address of the traced
function. It relies on the IP address stored at ctx - 16 by the bpf
trampoline. On 64-bit powerpc, this address is recovered from LR
accounting for OOL trampoline. But the address stored here was off
by 4-bytes. Ensure the address is the actual start of the traced
function.

Reported-by: Abhishek Dubey <adubey@linux.ibm.com>
Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.org
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-3-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 52162e4a7f84..95f208229b09 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -785,9 +785,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 *       retval_off             [ return value      ]
 	 *                              [ reg argN          ]
 	 *                              [ ...               ]
-	 *       regs_off               [ reg_arg1          ] prog ctx context
-	 *       nregs_off              [ args count        ]
-	 *       ip_off                 [ traced function   ]
+	 *       regs_off               [ reg_arg1          ] prog_ctx
+	 *       nregs_off              [ args count        ] ((u64 *)prog_ctx)[-1]
+	 *       ip_off                 [ traced function   ] ((u64 *)prog_ctx)[-2]
 	 *                              [ ...               ]
 	 *       run_ctx_off            [ bpf_tramp_run_ctx ]
 	 *                              [ reg argN          ]
@@ -895,7 +895,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
 
-	/* Save our return address */
+	/* Save our LR/return address */
 	EMIT(PPC_RAW_MFLR(_R3));
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
@@ -903,24 +903,34 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
 
 	/*
-	 * Save ip address of the traced function.
-	 * We could recover this from LR, but we will need to address for OOL trampoline,
-	 * and optional GEP area.
+	 * Derive IP address of the traced function.
+	 * In case of CONFIG_PPC_FTRACE_OUT_OF_LINE or BPF program, LR points to the instruction
+	 * after the 'bl' instruction in the OOL stub. Refer to ftrace_init_ool_stub() and
+	 * bpf_arch_text_poke() for OOL stub of kernel functions and bpf programs respectively.
+	 * Relevant stub sequence:
+	 *
+	 *               bl <tramp>
+	 *   LR (R3) =>  mtlr r0
+	 *               b <func_addr+4>
+	 *
+	 * Recover kernel function/bpf program address from the unconditional
+	 * branch instruction at the end of OOL stub.
 	 */
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) {
 		EMIT(PPC_RAW_LWZ(_R4, _R3, 4));
 		EMIT(PPC_RAW_SLWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_SRAWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_ADD(_R3, _R3, _R4));
-		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 	}
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
 
-	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		/* Fake our LR for unwind */
+		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+	}
 
 	/* Save function arg count -- see bpf_get_func_arg_cnt() */
 	EMIT(PPC_RAW_LI(_R3, nr_regs));
-- 
cgit v1.2.3


From 3727d6ec13665c1d99bf6dedb107104368ba42b4 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:27 +0530
Subject: powerpc64/bpf: use consistent tailcall offset in trampoline

Ideally, the offset used to load the tail call info field and to find
the pass by reference address for tail call field should be the same.
But while setting up the tail call info in the trampoline, this was
not followed. This can be misleading and can lead to unpredictable
results if and when bpf_has_stack_frame() ends up returning true
for trampoline frame. Since commit 15513beeb673 ("powerpc64/bpf:
Moving tail_call_cnt to bottom of frame") and commit 2ed2d8f6fb38
("powerpc64/bpf: Support tailcalls with subprogs") ensured tail call
field is at the bottom of the stack frame for BPF programs as well as
BPF trampoline, avoid relying on bpf_jit_stack_tailcallinfo_offset()
and bpf_has_stack_frame() for trampoline frame and always calculate
tail call field offset with reference to older frame.

Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs")
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-4-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit.h        |  5 -----
 arch/powerpc/net/bpf_jit_comp.c   | 12 +++++-------
 arch/powerpc/net/bpf_jit_comp64.c |  5 ++++-
 3 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 82bbf63f0e57..7354e1d72f79 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -81,9 +81,6 @@
 
 #ifdef CONFIG_PPC64
 
-/* for gpr non volatile registers BPG_REG_6 to 10 */
-#define BPF_PPC_STACK_SAVE	(6 * 8)
-
 /* If dummy pass (!image), account for maximum possible instructions */
 #define PPC_LI64(d, i)		do {					      \
 	if (!image)							      \
@@ -219,8 +216,6 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
 			  struct codegen_context *ctx, int insn_idx,
 			  int jmp_off, int dst_reg, u32 code);
-
-int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx);
 #endif
 
 #endif
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 95f208229b09..a4aa1e4c9f1c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -642,15 +642,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 						int bpf_dummy_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/* See Generated stack layout */
-		int tailcallinfo_offset = BPF_PPC_TAILCALL;
-
 		/*
 		 * func_frame_offset =                                   ...(1)
 		 *      bpf_dummy_frame_size + trampoline_frame_size
 		 */
 		EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset));
-		EMIT(PPC_RAW_LD(_R3, _R4, -tailcallinfo_offset));
+		/* Refer to trampoline's Generated stack layout */
+		EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL));
 
 		/*
 		 * Setting the tail_call_info in trampoline's frame
@@ -658,7 +656,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 */
 		EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
-		EMIT(PPC_RAW_ADDI(_R3, _R4, bpf_jit_stack_tailcallinfo_offset(ctx)));
+		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
 		/*
 		 * From ...(1) above:
 		 * trampoline_frame_bottom =                            ...(2)
@@ -666,14 +664,14 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		 *
 		 * Using ...(2) derived above:
 		 * trampoline_tail_call_info_offset =                  ...(3)
-		 *      trampoline_frame_bottom - tailcallinfo_offset
+		 *      trampoline_frame_bottom - BPF_PPC_TAILCALL
 		 *
 		 * From ...(3):
 		 * Use trampoline_tail_call_info_offset to write reference of main's
 		 * tail_call_info in trampoline frame.
 		 */
 		EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size)
-								- tailcallinfo_offset));
+								- BPF_PPC_TAILCALL));
 	} else {
 		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
 		EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 44ce8a8783f9..7655be76f537 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -42,6 +42,9 @@
  * exception boundary.
  */
 
+/* BPF non-volatile registers save area size */
+#define BPF_PPC_STACK_SAVE	(6 * 8)
+
 /* for bpf JIT code internal usage */
 #define BPF_PPC_STACK_LOCALS	24
 /*
@@ -148,7 +151,7 @@ static int bpf_jit_stack_local(struct codegen_context *ctx)
 	}
 }
 
-int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx)
+static int bpf_jit_stack_tailcallinfo_offset(struct codegen_context *ctx)
 {
 	return bpf_jit_stack_local(ctx) + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE;
 }
-- 
cgit v1.2.3


From 2d347d10f8e20e28a9eab52edf55079ae1ec0aae Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:28 +0530
Subject: powerpc64/bpf: remove BPF redzone protection in trampoline stack

Since bpf2bpf tailcall support is enabled for 64-bit powerpc with
kernel commit 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with
subprogs"), 'tailcalls/tailcall_bpf2bpf_hierarchy_fexit' BPF selftest
is triggering "corrupted stack end detected inside scheduler" with the
config option CONFIG_SCHED_STACK_END_CHECK enabled. While reviewing
the stack layout for BPF trampoline, observed that the dummy frame is
trying to protect the redzone of BPF program. This is because tail
call info and NVRs save area are in redzone at the time of tailcall
as the current BPF program stack frame is teared down before the
tailcall. But saving this redzone in the dummy frame of trampoline
is unnecessary because of the follow reasons:

  1) Firstly, trampoline can be attached to BPF entry/main program
     or subprog. But prologue part of the BPF entry/main program,
     where the trampoline attachpoint is, is skipped during tailcall.
     So, protecting the redzone does not arise when the trampoline is
     not even triggered in this scenario.
  2) In case of subprog, the caller's stackframe is already setup
     and the subprog's stackframe is yet to be setup. So, nothing
     on the redzone to be protected.

Also, using dummy frame in BPF trampoline, wastes critically scarce
kernel stack space, especially in tailcall sequence, for marginal
benefit in stack unwinding. So, drop setting up the dummy frame.
Instead, save return address in bpf trampoline frame and use it as
appropriate. Pruning this unnecessary stack usage mitigates the
likelihood of stack overflow in scenarios where bpf2bpf tailcalls
and fexit programs are mixed.

Reported-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
Fixes: 2ed2d8f6fb38 ("powerpc64/bpf: Support tailcalls with subprogs")
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-5-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c | 89 +++++++++++++++--------------------------
 1 file changed, 33 insertions(+), 56 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index a4aa1e4c9f1c..85457bcb2040 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -638,15 +638,10 @@ static int invoke_bpf_mod_ret(u32 *image, u32 *ro_image, struct codegen_context
  * for the traced function (BPF subprog/callee) to fetch it.
  */
 static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_context *ctx,
-						int func_frame_offset,
-						int bpf_dummy_frame_size, int r4_off)
+						int bpf_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC64)) {
-		/*
-		 * func_frame_offset =                                   ...(1)
-		 *      bpf_dummy_frame_size + trampoline_frame_size
-		 */
-		EMIT(PPC_RAW_LD(_R4, _R1, func_frame_offset));
+		EMIT(PPC_RAW_LD(_R4, _R1, bpf_frame_size));
 		/* Refer to trampoline's Generated stack layout */
 		EMIT(PPC_RAW_LD(_R3, _R4, -BPF_PPC_TAILCALL));
 
@@ -657,21 +652,13 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 		EMIT(PPC_RAW_CMPLWI(_R3, MAX_TAIL_CALL_CNT));
 		PPC_BCC_CONST_SHORT(COND_GT, 8);
 		EMIT(PPC_RAW_ADDI(_R3, _R4, -BPF_PPC_TAILCALL));
+
 		/*
-		 * From ...(1) above:
-		 * trampoline_frame_bottom =                            ...(2)
-		 *      func_frame_offset - bpf_dummy_frame_size
-		 *
-		 * Using ...(2) derived above:
-		 * trampoline_tail_call_info_offset =                  ...(3)
-		 *      trampoline_frame_bottom - BPF_PPC_TAILCALL
-		 *
-		 * From ...(3):
-		 * Use trampoline_tail_call_info_offset to write reference of main's
-		 * tail_call_info in trampoline frame.
+		 * Trampoline's tail_call_info is at the same offset, as that of
+		 * any bpf program, with reference to previous frame. Update the
+		 * address of main's tail_call_info in trampoline frame.
 		 */
-		EMIT(PPC_RAW_STL(_R3, _R1, (func_frame_offset - bpf_dummy_frame_size)
-								- BPF_PPC_TAILCALL));
+		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size - BPF_PPC_TAILCALL));
 	} else {
 		/* See bpf_jit_stack_offsetof() and BPF_PPC_TC */
 		EMIT(PPC_RAW_LL(_R4, _R1, r4_off));
@@ -679,7 +666,7 @@ static void bpf_trampoline_setup_tail_call_info(u32 *image, struct codegen_conte
 }
 
 static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_context *ctx,
-						 int func_frame_offset, int r4_off)
+						 int bpf_frame_size, int r4_off)
 {
 	if (IS_ENABLED(CONFIG_PPC32)) {
 		/*
@@ -690,12 +677,12 @@ static void bpf_trampoline_restore_tail_call_cnt(u32 *image, struct codegen_cont
 	}
 }
 
-static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx, int func_frame_offset,
-				     int nr_regs, int regs_off)
+static void bpf_trampoline_save_args(u32 *image, struct codegen_context *ctx,
+				     int bpf_frame_size, int nr_regs, int regs_off)
 {
 	int param_save_area_offset;
 
-	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset = bpf_frame_size;
 	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
 
 	for (int i = 0; i < nr_regs; i++) {
@@ -718,11 +705,11 @@ static void bpf_trampoline_restore_args_regs(u32 *image, struct codegen_context
 
 /* Used when we call into the traced function. Replicate parameter save area */
 static void bpf_trampoline_restore_args_stack(u32 *image, struct codegen_context *ctx,
-					      int func_frame_offset, int nr_regs, int regs_off)
+					      int bpf_frame_size, int nr_regs, int regs_off)
 {
 	int param_save_area_offset;
 
-	param_save_area_offset = func_frame_offset; /* the two frames we alloted */
+	param_save_area_offset = bpf_frame_size;
 	param_save_area_offset += STACK_FRAME_MIN_SIZE; /* param save area is past frame header */
 
 	for (int i = 8; i < nr_regs; i++) {
@@ -739,10 +726,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 					 void *func_addr)
 {
 	int regs_off, nregs_off, ip_off, run_ctx_off, retval_off, nvr_off, alt_lr_off, r4_off = 0;
-	int i, ret, nr_regs, bpf_frame_size = 0, bpf_dummy_frame_size = 0, func_frame_offset;
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+	int i, ret, nr_regs, retaddr_off, bpf_frame_size = 0;
 	struct codegen_context codegen_ctx, *ctx;
 	u32 *image = (u32 *)rw_image;
 	ppc_inst_t branch_insn;
@@ -768,16 +755,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 * Generated stack layout:
 	 *
 	 * func prev back chain         [ back chain        ]
-	 *                              [                   ]
-	 * bpf prog redzone/tailcallcnt [ ...               ] 64 bytes (64-bit powerpc)
-	 *                              [                   ] --
-	 * LR save area                 [ r0 save (64-bit)  ]   | header
-	 *                              [ r0 save (32-bit)  ]   |
-	 * dummy frame for unwind       [ back chain 1      ] --
 	 *                              [ tail_call_info    ] optional - 64-bit powerpc
 	 *                              [ padding           ] align stack frame
 	 *       r4_off                 [ r4 (tailcallcnt)  ] optional - 32-bit powerpc
 	 *       alt_lr_off             [ real lr (ool stub)] optional - actual lr
+	 *       retaddr_off            [ return address    ]
 	 *                              [ r26               ]
 	 *       nvr_off                [ r25               ] nvr save area
 	 *       retval_off             [ return value      ]
@@ -841,6 +823,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	nvr_off = bpf_frame_size;
 	bpf_frame_size += 2 * SZL;
 
+	/* Save area for return address */
+	retaddr_off = bpf_frame_size;
+	bpf_frame_size += SZL;
+
 	/* Optional save area for actual LR in case of ool ftrace */
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		alt_lr_off = bpf_frame_size;
@@ -867,16 +853,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	/* Padding to align stack frame, if any */
 	bpf_frame_size = round_up(bpf_frame_size, SZL * 2);
 
-	/* Dummy frame size for proper unwind - includes 64-bytes red zone for 64-bit powerpc */
-	bpf_dummy_frame_size = STACK_FRAME_MIN_SIZE + 64;
-
-	/* Offset to the traced function's stack frame */
-	func_frame_offset = bpf_dummy_frame_size + bpf_frame_size;
-
-	/* Create dummy frame for unwind, store original return value */
+	/*  Store original return value */
 	EMIT(PPC_RAW_STL(_R0, _R1, PPC_LR_STKOFF));
-	/* Protect red zone where tail call count goes */
-	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_dummy_frame_size));
 
 	/* Create our stack frame */
 	EMIT(PPC_RAW_STLU(_R1, _R1, -bpf_frame_size));
@@ -891,14 +869,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	if (IS_ENABLED(CONFIG_PPC32) && nr_regs < 2)
 		EMIT(PPC_RAW_STL(_R4, _R1, r4_off));
 
-	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
+	bpf_trampoline_save_args(image, ctx, bpf_frame_size, nr_regs, regs_off);
 
 	/* Save our LR/return address */
 	EMIT(PPC_RAW_MFLR(_R3));
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
 	else
-		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off));
 
 	/*
 	 * Derive IP address of the traced function.
@@ -925,9 +903,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
 
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
-		/* Fake our LR for unwind */
+		/* Fake our LR for BPF_TRAMP_F_CALL_ORIG case */
 		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
-		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_STL(_R3, _R1, retaddr_off));
 	}
 
 	/* Save function arg count -- see bpf_get_func_arg_cnt() */
@@ -966,20 +944,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	/* Call the traced function */
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/*
-		 * The address in LR save area points to the correct point in the original function
+		 * retaddr on trampoline stack points to the correct point in the original function
 		 * with both PPC_FTRACE_OUT_OF_LINE as well as with traditional ftrace instruction
 		 * sequence
 		 */
-		EMIT(PPC_RAW_LL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+		EMIT(PPC_RAW_LL(_R3, _R1, retaddr_off));
 		EMIT(PPC_RAW_MTCTR(_R3));
 
 		/* Replicate tail_call_cnt before calling the original BPF prog */
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
-			bpf_trampoline_setup_tail_call_info(image, ctx, func_frame_offset,
-								bpf_dummy_frame_size, r4_off);
+			bpf_trampoline_setup_tail_call_info(image, ctx, bpf_frame_size, r4_off);
 
 		/* Restore args */
-		bpf_trampoline_restore_args_stack(image, ctx, func_frame_offset, nr_regs, regs_off);
+		bpf_trampoline_restore_args_stack(image, ctx, bpf_frame_size, nr_regs, regs_off);
 
 		/* Restore TOC for 64-bit */
 		if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
@@ -993,7 +970,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 		/* Restore updated tail_call_cnt */
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
-			bpf_trampoline_restore_tail_call_cnt(image, ctx, func_frame_offset, r4_off);
+			bpf_trampoline_restore_tail_call_cnt(image, ctx, bpf_frame_size, r4_off);
 
 		/* Reserve space to patch branch instruction to skip fexit progs */
 		if (ro_image) /* image is NULL for dummy pass */
@@ -1045,7 +1022,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		EMIT(PPC_RAW_LD(_R2, _R1, 24));
 	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* Skip the traced function and return to parent */
-		EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+		EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 		EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 		EMIT(PPC_RAW_MTLR(_R0));
 		EMIT(PPC_RAW_BLR());
@@ -1053,13 +1030,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 			EMIT(PPC_RAW_LL(_R0, _R1, alt_lr_off));
 			EMIT(PPC_RAW_MTLR(_R0));
-			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 			EMIT(PPC_RAW_BLR());
 		} else {
-			EMIT(PPC_RAW_LL(_R0, _R1, bpf_frame_size + PPC_LR_STKOFF));
+			EMIT(PPC_RAW_LL(_R0, _R1, retaddr_off));
 			EMIT(PPC_RAW_MTCTR(_R0));
-			EMIT(PPC_RAW_ADDI(_R1, _R1, func_frame_offset));
+			EMIT(PPC_RAW_ADDI(_R1, _R1, bpf_frame_size));
 			EMIT(PPC_RAW_LL(_R0, _R1, PPC_LR_STKOFF));
 			EMIT(PPC_RAW_MTLR(_R0));
 			EMIT(PPC_RAW_BCTR());
-- 
cgit v1.2.3


From 51b8de4b3d27ec12128fa2405e526c527a77ae65 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:29 +0530
Subject: powerpc64/bpf: fix handling of BPF stack in exception callback

Exception callback reuses the stack frame of exception boundary. When
exception boundary and exception callback programs have different BPF
stack depth, the current stack unwind in exception callback will fail.
Adjust the stack frame size of exception callback, in its prologue,
if its BPF stack depth is different from that of exception boundary.

Reported-by: bot+bpf-ci@kernel.org
Closes: https://lore.kernel.org/bpf/2a310e86a59eb4c44c3ac9e5647814469d9c955580c9c0f1b3d9ca4a44717a34@mail.kernel.org/
Fixes: 11d45eee9f42 ("powerpc64/bpf: Additional NVR handling for bpf_throw")
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-6-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp64.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 7655be76f537..04e76440d1ad 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -32,14 +32,15 @@
  *
  *		[	prev sp		] <-------------
  *		[    tail_call_info	] 8		|
- *		[   nv gpr save area	] 6*8 + (12*8)	|
+ *		[   nv gpr save area	] (6 * 8)	|
+ *		[ addl. nv gpr save area] (12 * 8)	| <--- exception boundary/callback program
  *		[    local_tmp_var	] 24		|
  * fp (r31) -->	[   ebpf stack space	] upto 512	|
  *		[     frame header	] 32/112	|
  * sp (r1) --->	[    stack pointer	] --------------
  *
- * Additional (12*8) in 'nv gpr save area' only in case of
- * exception boundary.
+ * Additional (12 * 8) in 'nv gpr save area' only in case of
+ * exception boundary/callback.
  */
 
 /* BPF non-volatile registers save area size */
@@ -51,7 +52,7 @@
  * for additional non volatile registers(r14-r25) to be saved
  * at exception boundary
  */
-#define BPF_PPC_EXC_STACK_SAVE (12*8)
+#define BPF_PPC_EXC_STACK_SAVE (12 * 8)
 
 /* stack frame excluding BPF stack, ensure this is quadword aligned */
 #define BPF_PPC_STACKFRAME	(STACK_FRAME_MIN_SIZE + \
@@ -128,12 +129,13 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
  *		[	  ...       	] 		|
  * sp (r1) --->	[    stack pointer	] --------------
  *		[    tail_call_info	] 8
- *		[   nv gpr save area	] 6*8 + (12*8)
+ *		[   nv gpr save area	] (6 * 8)
+ *		[ addl. nv gpr save area] (12 * 8) <--- exception boundary/callback program
  *		[    local_tmp_var	] 24
  *		[   unused red zone	] 224
  *
- * Additional (12*8) in 'nv gpr save area' only in case of
- * exception boundary.
+ * Additional (12 * 8) in 'nv gpr save area' only in case of
+ * exception boundary/callback.
  */
 static int bpf_jit_stack_local(struct codegen_context *ctx)
 {
@@ -240,10 +242,6 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 
 	if (bpf_has_stack_frame(ctx) && !ctx->exception_cb) {
 		/*
-		 * exception_cb uses boundary frame after stack walk.
-		 * It can simply use redzone, this optimization reduces
-		 * stack walk loop by one level.
-		 *
 		 * We need a stack frame, but we don't necessarily need to
 		 * save/restore LR unless we call other functions
 		 */
@@ -287,6 +285,22 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
 		 * program(main prog) as third arg
 		 */
 		EMIT(PPC_RAW_MR(_R1, _R5));
+		/*
+		 * Exception callback reuses the stack frame of exception boundary.
+		 * But BPF stack depth of exception callback and exception boundary
+		 * don't have to be same. If BPF stack depth is different, adjust the
+		 * stack frame size considering BPF stack depth of exception callback.
+		 * The non-volatile register save area remains unchanged. These non-
+		 * volatile registers are restored in exception callback's epilogue.
+		 */
+		EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R5, 0));
+		EMIT(PPC_RAW_SUB(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_1), _R1));
+		EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_2), bpf_to_ppc(TMP_REG_2),
+			-BPF_PPC_EXC_STACKFRAME));
+		EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_2), ctx->stack_size));
+		PPC_BCC_CONST_SHORT(COND_EQ, 12);
+		EMIT(PPC_RAW_MR(_R1, bpf_to_ppc(TMP_REG_1)));
+		EMIT(PPC_RAW_STDU(_R1, _R1, -(BPF_PPC_EXC_STACKFRAME + ctx->stack_size)));
 	}
 
 	/*
-- 
cgit v1.2.3


From 01b6ac72729610ae732ca2a66e3a642e23f6cd60 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.ibm.com>
Date: Tue, 3 Mar 2026 23:40:30 +0530
Subject: powerpc64/bpf: fix kfunc call support

Commit 61688a82e047 ("powerpc/bpf: enable kfunc call") inadvertently
enabled kfunc call support for 32-bit powerpc but that support will
not be possible until ABI mismatch between 32-bit powerpc and eBPF is
handled in 32-bit powerpc JIT code. Till then, advertise support only
for 64-bit powerpc. Also, in powerpc ABI, caller needs to extend the
arguments properly based on signedness. The JIT code is responsible
for handling this explicitly for kfunc calls as verifier can't handle
this for each architecture-specific ABI needs. But this was not taken
care of while kfunc call support was enabled for powerpc. Fix it by
handling this with bpf_jit_find_kfunc_model() and using zero_extend()
& sign_extend() helper functions.

Fixes: 61688a82e047 ("powerpc/bpf: enable kfunc call")
Cc: stable@vger.kernel.org
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-7-hbathini@linux.ibm.com
---
 arch/powerpc/net/bpf_jit_comp.c   |   2 +-
 arch/powerpc/net/bpf_jit_comp64.c | 101 +++++++++++++++++++++++++++++++++++---
 2 files changed, 94 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 85457bcb2040..a62a9a92b7b5 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -450,7 +450,7 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 
 bool bpf_jit_supports_kfunc_call(void)
 {
-	return true;
+	return IS_ENABLED(CONFIG_PPC64);
 }
 
 bool bpf_jit_supports_arena(void)
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 04e76440d1ad..c5e26d231cd5 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -499,6 +499,83 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *
 	return 0;
 }
 
+static int zero_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size)
+{
+	switch (size) {
+	case 1:
+		 /* zero-extend 8 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 56));
+		return 0;
+	case 2:
+		 /* zero-extend 16 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 48));
+		return 0;
+	case 4:
+		 /* zero-extend 32 bits into 64 bits */
+		EMIT(PPC_RAW_RLDICL(dst_reg, src_reg, 0, 32));
+		fallthrough;
+	case 8:
+		/* Nothing to do */
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+static int sign_extend(u32 *image, struct codegen_context *ctx, u32 src_reg, u32 dst_reg, u32 size)
+{
+	switch (size) {
+	case 1:
+		 /* sign-extend 8 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
+		return 0;
+	case 2:
+		 /* sign-extend 16 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
+		return 0;
+	case 4:
+		 /* sign-extend 32 bits into 64 bits */
+		EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
+		fallthrough;
+	case 8:
+		/* Nothing to do */
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+/*
+ * Handle powerpc ABI expectations from caller:
+ *   - Unsigned arguments are zero-extended.
+ *   - Signed arguments are sign-extended.
+ */
+static int prepare_for_kfunc_call(const struct bpf_prog *fp, u32 *image,
+				  struct codegen_context *ctx,
+				  const struct bpf_insn *insn)
+{
+	const struct btf_func_model *m = bpf_jit_find_kfunc_model(fp, insn);
+	int i;
+
+	if (!m)
+		return -1;
+
+	for (i = 0; i < m->nr_args; i++) {
+		/* Note that BPF ABI only allows up to 5 args for kfuncs */
+		u32 reg = bpf_to_ppc(BPF_REG_1 + i), size = m->arg_size[i];
+
+		if (!(m->arg_flags[i] & BTF_FMODEL_SIGNED_ARG)) {
+			if (zero_extend(image, ctx, reg, reg, size))
+				return -1;
+		} else {
+			if (sign_extend(image, ctx, reg, reg, size))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
 static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out)
 {
 	/*
@@ -1143,14 +1220,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 				/* special mov32 for zext */
 				EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31));
 				break;
-			} else if (off == 8) {
-				EMIT(PPC_RAW_EXTSB(dst_reg, src_reg));
-			} else if (off == 16) {
-				EMIT(PPC_RAW_EXTSH(dst_reg, src_reg));
-			} else if (off == 32) {
-				EMIT(PPC_RAW_EXTSW(dst_reg, src_reg));
-			} else if (dst_reg != src_reg)
-				EMIT(PPC_RAW_MR(dst_reg, src_reg));
+			}
+			if (off == 0) {
+				/* MOV */
+				if (dst_reg != src_reg)
+					EMIT(PPC_RAW_MR(dst_reg, src_reg));
+			} else {
+				/* MOVSX: dst = (s8,s16,s32)src (off = 8,16,32) */
+				if (sign_extend(image, ctx, src_reg, dst_reg, off / 8))
+					return -1;
+			}
 			goto bpf_alu32_trunc;
 		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
 		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
@@ -1618,6 +1697,12 @@ emit_clear:
 			if (ret < 0)
 				return ret;
 
+			/* Take care of powerpc ABI requirements before kfunc call */
+			if (insn[i].src_reg == BPF_PSEUDO_KFUNC_CALL) {
+				if (prepare_for_kfunc_call(fp, image, ctx, &insn[i]))
+					return -1;
+			}
+
 			ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 			if (ret)
 				return ret;
-- 
cgit v1.2.3


From 202d23eeccd4b12047869538d6fb91d1e42c4ddd Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 17:04:08 +0100
Subject: dt-bindings: powerpc: Add Freescale/NXP MPC83xx SoCs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new binding for MPC83xx platforms, describing the board compatible
strings used in currently existing device trees.

Note that the SoC bus is called immr@... in many existing devicetrees,
but this contradicts the simple-bus binding.

Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-ppcyaml-soc-v5-1-2982d5a857bc@posteo.net
---
 .../bindings/powerpc/fsl/fsl,mpc83xx.yaml          | 93 ++++++++++++++++++++++
 1 file changed, 93 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml

diff --git a/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml
new file mode 100644
index 000000000000..9e37d155c582
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/fsl/fsl,mpc83xx.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/powerpc/fsl/fsl,mpc83xx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale PowerQUICC II Pro (MPC83xx) platforms
+
+maintainers:
+  - J. Neuschäfer <j.ne@posteo.net>
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+      - description: MPC83xx Reference Design Boards
+        items:
+          - enum:
+              - fsl,mpc8308rdb
+              - fsl,mpc8315erdb
+              - fsl,mpc8360rdk
+              - fsl,mpc8377rdb
+              - fsl,mpc8377wlan
+              - fsl,mpc8378rdb
+              - fsl,mpc8379rdb
+
+      - description: MPC8313E Reference Design Board
+        items:
+          - const: MPC8313ERDB
+          - const: MPC831xRDB
+          - const: MPC83xxRDB
+
+      - description: MPC8323E Reference Design Board
+        items:
+          - const: MPC8323ERDB
+          - const: MPC832xRDB
+          - const: MPC83xxRDB
+
+      - description: MPC8349E-mITX(-GP) Reference Design Platform
+        items:
+          - enum:
+              - MPC8349EMITX
+              - MPC8349EMITXGP
+          - const: MPC834xMITX
+          - const: MPC83xxMITX
+
+      - description: Keymile KMETER1 board
+        const: keymile,KMETER1
+
+      - description: MPC8308 P1M board
+        const: denx,mpc8308_p1m
+
+patternProperties:
+  "^soc@.*$":
+    type: object
+    properties:
+      compatible:
+        oneOf:
+          - items:
+              - enum:
+                  - fsl,mpc8315-immr
+                  - fsl,mpc8308-immr
+              - const: simple-bus
+          - items:
+              - const: fsl,mpc8360-immr
+              - const: fsl,immr
+              - const: fsl,soc
+              - const: simple-bus
+          - const: simple-bus
+
+additionalProperties: true
+
+examples:
+  - |
+    / {
+        compatible = "fsl,mpc8315erdb";
+        model = "MPC8315E-RDB";
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        soc@e0000000 {
+            compatible = "fsl,mpc8315-immr", "simple-bus";
+            reg = <0xe0000000 0x00000200>;
+            #address-cells = <1>;
+            #size-cells = <1>;
+            device_type = "soc";
+            ranges = <0 0xe0000000 0x00100000>;
+            bus-frequency = <0>;
+        };
+    };
+
+...
-- 
cgit v1.2.3


From 691417ffe7821721e0a28bd25ad8c0dc0d4ae4ad Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:31:42 +0100
Subject: powerpc: 83xx: km83xx: Fix keymile vendor prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When kmeter.c was refactored into km83xx.c in 2011, the "keymile" vendor
prefix was changed to upper-case "Keymile". The devicetree at
arch/powerpc/boot/dts/kmeter1.dts never underwent the same change,
suggesting that this was simply a mistake.

Fixes: 93e2b95c81042d ("powerpc/83xx: rename and update kmeter1")
Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Reviewed-by: Heiko Schocher <hs@nabladev.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-keymile-v1-1-463a11e71702@posteo.net
---
 arch/powerpc/platforms/83xx/km83xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 2b5d187d9b62..9ef8fb39dd1b 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -155,8 +155,8 @@ machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices);
 
 /* list of the supported boards */
 static char *board[] __initdata = {
-	"Keymile,KMETER1",
-	"Keymile,kmpbec8321",
+	"keymile,KMETER1",
+	"keymile,kmpbec8321",
 	NULL
 };
 
-- 
cgit v1.2.3


From 38ce944d47b717cac6b5f2bae9dd247f87f21ac7 Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:51 +0100
Subject: powerpc: dts: mpc8313erdb: Use IRQ_TYPE_* macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This increases readability, because "0x8" isn't very descriptive.

mpc8313erdb.dtb remains identical after this patch.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-1-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8313erdb.dts | 59 ++++++++++++++++++++---------------
 1 file changed, 34 insertions(+), 25 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 09508b4c8c73..137217d377e9 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -6,6 +6,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	model = "MPC8313ERDB";
@@ -48,7 +49,7 @@
 		#size-cells = <1>;
 		compatible = "fsl,mpc8313-elbc", "fsl,elbc", "simple-bus";
 		reg = <0xe0005000 0x1000>;
-		interrupts = <77 0x8>;
+		interrupts = <77 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
 
 		// CS0 and CS1 are swapped when
@@ -118,7 +119,7 @@
 				cell-index = <0>;
 				compatible = "fsl-i2c";
 				reg = <0x3000 0x100>;
-				interrupts = <14 0x8>;
+				interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-parent = <&ipic>;
 				dfsrr;
 				rtc@68 {
@@ -131,7 +132,7 @@
 				compatible = "fsl,sec2.2", "fsl,sec2.1",
 				             "fsl,sec2.0";
 				reg = <0x30000 0x10000>;
-				interrupts = <11 0x8>;
+				interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 				interrupt-parent = <&ipic>;
 				fsl,num-channels = <1>;
 				fsl,channel-fifo-len = <24>;
@@ -146,7 +147,7 @@
 			cell-index = <1>;
 			compatible = "fsl-i2c";
 			reg = <0x3100 0x100>;
-			interrupts = <15 0x8>;
+			interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			dfsrr;
 		};
@@ -155,7 +156,7 @@
 			cell-index = <0>;
 			compatible = "fsl,spi";
 			reg = <0x7000 0x1000>;
-			interrupts = <16 0x8>;
+			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			mode = "cpu";
 		};
@@ -167,7 +168,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupt-parent = <&ipic>;
-			interrupts = <38 0x8>;
+			interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
 			phy_type = "utmi_wide";
 			sleep = <&pmc 0x00300000>;
 		};
@@ -175,7 +176,8 @@
 		ptp_clock@24E00 {
 			compatible = "fsl,etsec-ptp";
 			reg = <0x24E00 0xB0>;
-			interrupts = <12 0x8 13 0x8>;
+			interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
+				     <13 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = < &ipic >;
 			fsl,tclk-period = <10>;
 			fsl,tmr-prsc    = <100>;
@@ -197,7 +199,9 @@
 			compatible = "gianfar";
 			reg = <0x24000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <37 0x8 36 0x8 35 0x8>;
+			interrupts = <37 IRQ_TYPE_LEVEL_LOW>,
+				     <36 IRQ_TYPE_LEVEL_LOW>,
+				     <35 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = < &tbi0 >;
 			/* Vitesse 7385 isn't on the MDIO bus */
@@ -211,7 +215,7 @@
 				reg = <0x520 0x20>;
 				phy4: ethernet-phy@4 {
 					interrupt-parent = <&ipic>;
-					interrupts = <20 0x8>;
+					interrupts = <20 IRQ_TYPE_LEVEL_LOW>;
 					reg = <0x4>;
 				};
 				tbi0: tbi-phy@11 {
@@ -231,7 +235,9 @@
 			reg = <0x25000 0x1000>;
 			ranges = <0x0 0x25000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <34 0x8 33 0x8 32 0x8>;
+			interrupts = <34 IRQ_TYPE_LEVEL_LOW>,
+				     <33 IRQ_TYPE_LEVEL_LOW>,
+				     <32 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = < &tbi1 >;
 			phy-handle = < &phy4 >;
@@ -259,7 +265,7 @@
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4500 0x100>;
 			clock-frequency = <0>;
-			interrupts = <9 0x8>;
+			interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -269,15 +275,12 @@
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4600 0x100>;
 			clock-frequency = <0>;
-			interrupts = <10 0x8>;
+			interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		/* IPIC
-		 * interrupts cell = <intr #, sense>
-		 * sense values match linux IORESOURCE_IRQ_* defines:
-		 * sense == 8: Level, low assertion
-		 * sense == 2: Edge, high-to-low change
+		 * interrupts cell = <intr #, type>
 		 */
 		ipic: pic@700 {
 			interrupt-controller;
@@ -290,7 +293,7 @@
 		pmc: power@b00 {
 			compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
 			reg = <0xb00 0x100 0xa00 0x100>;
-			interrupts = <80 8>;
+			interrupts = <80 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 
@@ -306,14 +309,20 @@
 		gtm1: timer@500 {
 			compatible = "fsl,mpc8313-gtm", "fsl,gtm";
 			reg = <0x500 0x100>;
-			interrupts = <90 8 78 8 84 8 72 8>;
+			interrupts = <90 IRQ_TYPE_LEVEL_LOW>,
+				     <78 IRQ_TYPE_LEVEL_LOW>,
+				     <84 IRQ_TYPE_LEVEL_LOW>,
+				     <72 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		timer@600 {
 			compatible = "fsl,mpc8313-gtm", "fsl,gtm";
 			reg = <0x600 0x100>;
-			interrupts = <91 8 79 8 85 8 73 8>;
+			interrupts = <91 IRQ_TYPE_LEVEL_LOW>,
+				     <79 IRQ_TYPE_LEVEL_LOW>,
+				     <85 IRQ_TYPE_LEVEL_LOW>,
+				     <73 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 	};
@@ -341,7 +350,7 @@
 					 0x7800 0x0 0x0 0x3 &ipic 17 0x8
 					 0x7800 0x0 0x0 0x4 &ipic 18 0x8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <66 0x8>;
+			interrupts = <66 IRQ_TYPE_LEVEL_LOW>;
 			bus-range = <0x0 0x0>;
 			ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000
 				  0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000
@@ -363,14 +372,14 @@
 			reg = <0xe00082a8 4>;
 			ranges = <0 0xe0008100 0x1a8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <71 8>;
+			interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 
 			dma-channel@0 {
 				compatible = "fsl,mpc8313-dma-channel",
 				             "fsl,elo-dma-channel";
 				reg = <0 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <0>;
 			};
 
@@ -379,7 +388,7 @@
 				             "fsl,elo-dma-channel";
 				reg = <0x80 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <1>;
 			};
 
@@ -388,7 +397,7 @@
 				             "fsl,elo-dma-channel";
 				reg = <0x100 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <2>;
 			};
 
@@ -397,7 +406,7 @@
 				             "fsl,elo-dma-channel";
 				reg = <0x180 0x28>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 				cell-index = <3>;
 			};
 		};
-- 
cgit v1.2.3


From 4f439747811977d05a87da65c1ae11246d4f4dee Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:52 +0100
Subject: powerpc: dts: mpc8315erdb: Use IRQ_TYPE_* macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This increases readability, because "0x8" isn't very descriptive.

mpc8315erdb.dtb remains identical after this patch.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-2-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 111 ++++++++++++++++++----------------
 1 file changed, 59 insertions(+), 52 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index a8f68d6e50b0..1957b6687b29 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -50,7 +50,7 @@
 		#size-cells = <1>;
 		compatible = "fsl,mpc8315-elbc", "fsl,elbc", "simple-bus";
 		reg = <0xe0005000 0x1000>;
-		interrupts = <77 0x8>;
+		interrupts = <77 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
 
 		// CS0 and CS1 are swapped when
@@ -112,7 +112,7 @@
 			cell-index = <0>;
 			compatible = "fsl-i2c";
 			reg = <0x3000 0x100>;
-			interrupts = <14 0x8>;
+			interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
@@ -133,7 +133,7 @@
 			cell-index = <0>;
 			compatible = "fsl,spi";
 			reg = <0x7000 0x1000>;
-			interrupts = <16 0x8>;
+			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			mode = "cpu";
 		};
@@ -145,35 +145,35 @@
 			reg = <0x82a8 4>;
 			ranges = <0 0x8100 0x1a8>;
 			interrupt-parent = <&ipic>;
-			interrupts = <71 8>;
+			interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			cell-index = <0>;
 			dma-channel@0 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0 0x80>;
 				cell-index = <0>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@80 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x80 0x80>;
 				cell-index = <1>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@100 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x100 0x80>;
 				cell-index = <2>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 			dma-channel@180 {
 				compatible = "fsl,mpc8315-dma-channel", "fsl,elo-dma-channel";
 				reg = <0x180 0x28>;
 				cell-index = <3>;
 				interrupt-parent = <&ipic>;
-				interrupts = <71 8>;
+				interrupts = <71 IRQ_TYPE_LEVEL_LOW>;
 			};
 		};
 
@@ -183,7 +183,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupt-parent = <&ipic>;
-			interrupts = <38 0x8>;
+			interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
 			phy_type = "utmi";
 		};
 
@@ -197,7 +197,9 @@
 			reg = <0x24000 0x1000>;
 			ranges = <0x0 0x24000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <32 0x8 33 0x8 34 0x8>;
+			interrupts = <32 IRQ_TYPE_LEVEL_LOW>,
+				     <33 IRQ_TYPE_LEVEL_LOW>,
+				     <34 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = <&tbi0>;
 			phy-handle = < &phy0 >;
@@ -238,7 +240,9 @@
 			reg = <0x25000 0x1000>;
 			ranges = <0x0 0x25000 0x1000>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <35 0x8 36 0x8 37 0x8>;
+			interrupts = <35 IRQ_TYPE_LEVEL_LOW>,
+				     <36 IRQ_TYPE_LEVEL_LOW>,
+				     <37 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			tbi-handle = <&tbi1>;
 			phy-handle = < &phy1 >;
@@ -263,7 +267,7 @@
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4500 0x100>;
 			clock-frequency = <133333333>;
-			interrupts = <9 0x8>;
+			interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -273,7 +277,7 @@
 			compatible = "fsl,ns16550", "ns16550";
 			reg = <0x4600 0x100>;
 			clock-frequency = <133333333>;
-			interrupts = <10 0x8>;
+			interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -282,7 +286,7 @@
 				     "fsl,sec2.4", "fsl,sec2.2", "fsl,sec2.1",
 				     "fsl,sec2.0";
 			reg = <0x30000 0x10000>;
-			interrupts = <11 0x8>;
+			interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,num-channels = <4>;
 			fsl,channel-fifo-len = <24>;
@@ -294,7 +298,7 @@
 			compatible = "fsl,mpc8315-sata", "fsl,pq-sata";
 			reg = <0x18000 0x1000>;
 			cell-index = <1>;
-			interrupts = <44 0x8>;
+			interrupts = <44 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
@@ -302,14 +306,17 @@
 			compatible = "fsl,mpc8315-sata", "fsl,pq-sata";
 			reg = <0x19000 0x1000>;
 			cell-index = <2>;
-			interrupts = <45 0x8>;
+			interrupts = <45 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 		};
 
 		gtm1: timer@500 {
 			compatible = "fsl,mpc8315-gtm", "fsl,gtm";
 			reg = <0x500 0x100>;
-			interrupts = <90 8 78 8 84 8 72 8>;
+			interrupts = <90 IRQ_TYPE_LEVEL_LOW>,
+				     <78 IRQ_TYPE_LEVEL_LOW>,
+				     <84 IRQ_TYPE_LEVEL_LOW>,
+				     <72 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			clock-frequency = <133333333>;
 		};
@@ -317,16 +324,16 @@
 		timer@600 {
 			compatible = "fsl,mpc8315-gtm", "fsl,gtm";
 			reg = <0x600 0x100>;
-			interrupts = <91 8 79 8 85 8 73 8>;
+			interrupts = <91 IRQ_TYPE_LEVEL_LOW>,
+				     <79 IRQ_TYPE_LEVEL_LOW>,
+				     <85 IRQ_TYPE_LEVEL_LOW>,
+				     <73 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			clock-frequency = <133333333>;
 		};
 
 		/* IPIC
-		 * interrupts cell = <intr #, sense>
-		 * sense values match linux IORESOURCE_IRQ_* defines:
-		 * sense == 8: Level, low assertion
-		 * sense == 2: Edge, high-to-low change
+		 * interrupts cell = <intr #, type>
 		 */
 		ipic: interrupt-controller@700 {
 			interrupt-controller;
@@ -340,14 +347,14 @@
 			compatible = "fsl,ipic-msi";
 			reg = <0x7c0 0x40>;
 			msi-available-ranges = <0 0x100>;
-			interrupts = <0x43 0x8
-				      0x4  0x8
-				      0x51 0x8
-				      0x52 0x8
-				      0x56 0x8
-				      0x57 0x8
-				      0x58 0x8
-				      0x59 0x8>;
+			interrupts = <0x43 IRQ_TYPE_LEVEL_LOW
+				      0x4  IRQ_TYPE_LEVEL_LOW
+				      0x51 IRQ_TYPE_LEVEL_LOW
+				      0x52 IRQ_TYPE_LEVEL_LOW
+				      0x56 IRQ_TYPE_LEVEL_LOW
+				      0x57 IRQ_TYPE_LEVEL_LOW
+				      0x58 IRQ_TYPE_LEVEL_LOW
+				      0x59 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = < &ipic >;
 		};
 
@@ -355,7 +362,7 @@
 			compatible = "fsl,mpc8315-pmc", "fsl,mpc8313-pmc",
 				     "fsl,mpc8349-pmc";
 			reg = <0xb00 0x100 0xa00 0x100>;
-			interrupts = <80 8>;
+			interrupts = <80 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 		};
@@ -374,24 +381,24 @@
 		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
 		interrupt-map = <
 				/* IDSEL 0x0E -mini PCI */
-				 0x7000 0x0 0x0 0x1 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x2 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x3 &ipic 18 0x8
-				 0x7000 0x0 0x0 0x4 &ipic 18 0x8
+				 0x7000 0x0 0x0 0x1 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x2 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x3 &ipic 18 IRQ_TYPE_LEVEL_LOW
+				 0x7000 0x0 0x0 0x4 &ipic 18 IRQ_TYPE_LEVEL_LOW
 
 				/* IDSEL 0x0F -mini PCI */
-				 0x7800 0x0 0x0 0x1 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x2 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x3 &ipic 17 0x8
-				 0x7800 0x0 0x0 0x4 &ipic 17 0x8
+				 0x7800 0x0 0x0 0x1 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x3 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x7800 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW
 
 				/* IDSEL 0x10 - PCI slot */
-				 0x8000 0x0 0x0 0x1 &ipic 48 0x8
-				 0x8000 0x0 0x0 0x2 &ipic 17 0x8
-				 0x8000 0x0 0x0 0x3 &ipic 48 0x8
-				 0x8000 0x0 0x0 0x4 &ipic 17 0x8>;
+				 0x8000 0x0 0x0 0x1 &ipic 48 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x2 &ipic 17 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x3 &ipic 48 IRQ_TYPE_LEVEL_LOW
+				 0x8000 0x0 0x0 0x4 &ipic 17 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-parent = <&ipic>;
-		interrupts = <66 0x8>;
+		interrupts = <66 IRQ_TYPE_LEVEL_LOW>;
 		bus-range = <0x0 0x0>;
 		ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000
 			  0x42000000 0 0x80000000 0x80000000 0 0x10000000
@@ -417,10 +424,10 @@
 		          0x01000000 0 0x00000000 0xb1000000 0 0x00800000>;
 		bus-range = <0 255>;
 		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <0 0 0 1 &ipic 1 8
-				 0 0 0 2 &ipic 1 8
-				 0 0 0 3 &ipic 1 8
-				 0 0 0 4 &ipic 1 8>;
+		interrupt-map = <0 0 0 1 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 2 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 3 &ipic 1 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 4 &ipic 1 IRQ_TYPE_LEVEL_LOW>;
 		clock-frequency = <0>;
 
 		pcie@0 {
@@ -448,10 +455,10 @@
 			  0x01000000 0 0x00000000 0xd1000000 0 0x00800000>;
 		bus-range = <0 255>;
 		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <0 0 0 1 &ipic 2 8
-				 0 0 0 2 &ipic 2 8
-				 0 0 0 3 &ipic 2 8
-				 0 0 0 4 &ipic 2 8>;
+		interrupt-map = <0 0 0 1 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 2 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 3 &ipic 2 IRQ_TYPE_LEVEL_LOW
+				 0 0 0 4 &ipic 2 IRQ_TYPE_LEVEL_LOW>;
 		clock-frequency = <0>;
 
 		pcie@0 {
-- 
cgit v1.2.3


From 31618e0e21c4633c365b26e6d45cae2084f4245b Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:53 +0100
Subject: powerpc: dts: mpc8315erdb: Rename LED nodes to comply with schema
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The leds-gpio.yaml schema requires that GPIO LED nodes contain "led",
and preferably start with "led-"

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-3-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 1957b6687b29..f4938a7292b9 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -478,12 +478,12 @@
 	leds {
 		compatible = "gpio-leds";
 
-		pwr {
+		led-pwr {
 			gpios = <&mcu_pio 0 0>;
 			default-state = "on";
 		};
 
-		hdd {
+		led-hdd {
 			gpios = <&mcu_pio 1 0>;
 			linux,default-trigger = "disk-activity";
 		};
-- 
cgit v1.2.3


From fde54f1a4dc7bfd83908380c0b4b6a830a0f9e01 Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:54 +0100
Subject: powerpc: dts: mpc8315erdb: Add missing #cells properties to SPI bus
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These properties are required by the spi-controller binding.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-4-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index f4938a7292b9..0b087180e181 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -135,6 +135,8 @@
 			reg = <0x7000 0x1000>;
 			interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-parent = <&ipic>;
+			#address-cells = <1>;
+			#size-cells = <0>;
 			mode = "cpu";
 		};
 
-- 
cgit v1.2.3


From 6373a2b5c878e920341d7bda84ac1126f72e6a68 Mon Sep 17 00:00:00 2001
From: "J. Neuschäfer" <j.ne@posteo.net>
Date: Tue, 3 Mar 2026 16:50:55 +0100
Subject: powerpc: dts: mpc83xx: Add unit addresses to /memory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes dtschema warnings such as the following:

  arch/powerpc/boot/dts/mpc8315erdb.dtb: /: memory: False schema
  does not allow {'device_type': ['memory'], 'reg': [[0, 134217728]]}

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303-mpc83xx-cleanup-v2-5-187d3a13effa@posteo.net
---
 arch/powerpc/boot/dts/asp834x-redboot.dts | 2 +-
 arch/powerpc/boot/dts/mpc8308_p1m.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8308rdb.dts      | 2 +-
 arch/powerpc/boot/dts/mpc8313erdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8315erdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc832x_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8349emitx.dts    | 2 +-
 arch/powerpc/boot/dts/mpc8349emitxgp.dts  | 2 +-
 arch/powerpc/boot/dts/mpc8377_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8377_wlan.dts    | 2 +-
 arch/powerpc/boot/dts/mpc8378_rdb.dts     | 2 +-
 arch/powerpc/boot/dts/mpc8379_rdb.dts     | 2 +-
 12 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts
index 33ddb17d1876..c541bd367983 100644
--- a/arch/powerpc/boot/dts/asp834x-redboot.dts
+++ b/arch/powerpc/boot/dts/asp834x-redboot.dts
@@ -37,7 +37,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x8000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts
index 2638555afcc4..41f917f97dab 100644
--- a/arch/powerpc/boot/dts/mpc8308_p1m.dts
+++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts
@@ -37,7 +37,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts
index af2ed8380a86..39ed26fba410 100644
--- a/arch/powerpc/boot/dts/mpc8308rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8308rdb.dts
@@ -38,7 +38,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts
index 137217d377e9..c9fe4dabc80a 100644
--- a/arch/powerpc/boot/dts/mpc8313erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8313erdb.dts
@@ -39,7 +39,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 0b087180e181..7ba1159f8803 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -40,7 +40,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x08000000>;	// 128MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index ba7caaf98fd5..06f134490d95 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -38,7 +38,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x04000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index 13f17232ba83..12d33cb55b72 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -39,7 +39,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index eae0afd5abbc..2998a233a790 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -37,7 +37,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;
 	};
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index f137ccb8cfde..fb311a7eb9f2 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -39,7 +39,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8377_wlan.dts b/arch/powerpc/boot/dts/mpc8377_wlan.dts
index ce254dd74dd0..f736a15cceff 100644
--- a/arch/powerpc/boot/dts/mpc8377_wlan.dts
+++ b/arch/powerpc/boot/dts/mpc8377_wlan.dts
@@ -40,7 +40,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x20000000>;	// 512MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index 19e5473d4161..32c49622b404 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -39,7 +39,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index 61519acca228..07deb89c5a9b 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -37,7 +37,7 @@
 		};
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x00000000 0x10000000>;	// 256MB at 0
 	};
-- 
cgit v1.2.3


From 35e4f2a17eb40288f9bcdb09549fa04a63a96279 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 2 Mar 2026 01:39:48 +0100
Subject: powerpc/pseries: Correct MSI allocation tracking

The per-device MSI allocation calculation in pseries_irq_domain_alloc()
is clearly wrong. It can still happen to work when nr_irqs is 1.

Correct it.

Fixes: c0215e2d72de ("powerpc/pseries: Fix MSI-X allocation failure when quota is exceeded")
Cc: stable@vger.kernel.org
Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
[maddy: Fixed Nilay's reviewed-by tag]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260302003948.1452016-1-namcao@linutronix.de
---
 arch/powerpc/platforms/pseries/msi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 64ffc6476ad6..8285b9a29fbf 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -605,7 +605,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 					      &pseries_msi_irq_chip, pseries_dev);
 	}
 
-	pseries_dev->msi_used++;
+	pseries_dev->msi_used += nr_irqs;
 	return 0;
 
 out:
-- 
cgit v1.2.3


From e2fa075d5ce1963e7cb7b0ac708ba567e5af66db Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 5 Mar 2026 11:21:52 -0800
Subject: iio: adc: ti-ads7950: normalize return value of gpio_get

The GPIO get callback is expected to return 0 or 1 (or a negative error
code). Ensure that the value returned by ti_ads7950_get() for output
pins is normalized to the [0, 1] range.

Fixes: 86ef402d805d ("gpiolib: sanitize the return value of gpio_chip::get()")
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads7950.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c
index bbe1ce577789..b8cc39fc39fb 100644
--- a/drivers/iio/adc/ti-ads7950.c
+++ b/drivers/iio/adc/ti-ads7950.c
@@ -433,7 +433,7 @@ static int ti_ads7950_get(struct gpio_chip *chip, unsigned int offset)
 
 	/* If set as output, return the output */
 	if (st->gpio_cmd_settings_bitmask & BIT(offset)) {
-		ret = st->cmd_settings_bitmask & BIT(offset);
+		ret = (st->cmd_settings_bitmask & BIT(offset)) ? 1 : 0;
 		goto out;
 	}
 
-- 
cgit v1.2.3


From d20bbae6e5d408a8a7c2a4344d76dd1ac557a149 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 5 Mar 2026 11:21:53 -0800
Subject: iio: adc: ti-ads7950: do not clobber gpio state in ti_ads7950_get()

GPIO state was inadvertently overwritten by the result of spi_sync(),
resulting in ti_ads7950_get() only returning 0 as GPIO state (or error).

Fix this by introducing a separate variable to hold the state.

Fixes: c97dce792dc8 ("iio: adc: ti-ads7950: add GPIO support")
Reported-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads7950.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c
index b8cc39fc39fb..cdc624889559 100644
--- a/drivers/iio/adc/ti-ads7950.c
+++ b/drivers/iio/adc/ti-ads7950.c
@@ -427,13 +427,15 @@ static int ti_ads7950_set(struct gpio_chip *chip, unsigned int offset,
 static int ti_ads7950_get(struct gpio_chip *chip, unsigned int offset)
 {
 	struct ti_ads7950_state *st = gpiochip_get_data(chip);
+	bool state;
 	int ret;
 
 	mutex_lock(&st->slock);
 
 	/* If set as output, return the output */
 	if (st->gpio_cmd_settings_bitmask & BIT(offset)) {
-		ret = (st->cmd_settings_bitmask & BIT(offset)) ? 1 : 0;
+		state = st->cmd_settings_bitmask & BIT(offset);
+		ret = 0;
 		goto out;
 	}
 
@@ -444,7 +446,7 @@ static int ti_ads7950_get(struct gpio_chip *chip, unsigned int offset)
 	if (ret)
 		goto out;
 
-	ret = ((st->single_rx >> 12) & BIT(offset)) ? 1 : 0;
+	state = (st->single_rx >> 12) & BIT(offset);
 
 	/* Revert back to original settings */
 	st->cmd_settings_bitmask &= ~TI_ADS7950_CR_GPIO_DATA;
@@ -456,7 +458,7 @@ static int ti_ads7950_get(struct gpio_chip *chip, unsigned int offset)
 out:
 	mutex_unlock(&st->slock);
 
-	return ret;
+	return ret ?: state;
 }
 
 static int ti_ads7950_get_direction(struct gpio_chip *chip,
-- 
cgit v1.2.3


From 6f658d19a5a29a602c372e8cfe8d4a623367d211 Mon Sep 17 00:00:00 2001
From: Chunyang Chen <chenchunyang0908@gmail.com>
Date: Thu, 5 Mar 2026 20:43:02 +0800
Subject: iio: adc: ti-ads1018: fix type overflow for data rate

The variable 'drate' is currently defined as u8. However, the data rate
values in ads1018 can reach up to 3300 Hz, which exceeds the maximum
value of 255 that a u8 can hold.

Change the type of 'drate' to u32 to match the data_rate_mode_to_hz
array definition and ensure the data rate is handled correctly.

Fixes: bf0bba486b5b ("iio: adc: Add ti-ads1018 driver")
Signed-off-by: Chunyang Chen <chenchunyang0908@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Reviewed-by: Kurt Borja <kuurtb@gmail.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads1018.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ti-ads1018.c b/drivers/iio/adc/ti-ads1018.c
index 6246b3cab71f..0780abd0d0db 100644
--- a/drivers/iio/adc/ti-ads1018.c
+++ b/drivers/iio/adc/ti-ads1018.c
@@ -249,7 +249,7 @@ static int ads1018_single_shot(struct ads1018 *ads1018,
 			       struct iio_chan_spec const *chan, u16 *cnv)
 {
 	u8 max_drate_mode = ads1018->chip_info->num_data_rate_mode_to_hz - 1;
-	u8 drate = ads1018->chip_info->data_rate_mode_to_hz[max_drate_mode];
+	u32 drate = ads1018->chip_info->data_rate_mode_to_hz[max_drate_mode];
 	u8 pga_mode = ads1018->chan_data[chan->scan_index].pga_mode;
 	struct spi_transfer xfer[2] = {
 		{
-- 
cgit v1.2.3


From 2f168094177f8553a36046afce139001801ca917 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 3 Mar 2026 21:47:33 +0800
Subject: iio: adc: ti-ads1119: Reinit completion before
 wait_for_completion_timeout()

The completion is not reinit before wait_for_completion_timeout(),
so wait_for_completion_timeout() will return immediately after
the first successful completion.

Fixes: a9306887eba4 ("iio: adc: ti-ads1119: Add driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-ads1119.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c
index 7f771c7023b8..79be71b4de96 100644
--- a/drivers/iio/adc/ti-ads1119.c
+++ b/drivers/iio/adc/ti-ads1119.c
@@ -280,6 +280,9 @@ static int ads1119_single_conversion(struct ads1119_state *st,
 	if (ret)
 		goto pdown;
 
+	if (st->client->irq)
+		reinit_completion(&st->completion);
+
 	ret = i2c_smbus_write_byte(st->client, ADS1119_CMD_START_SYNC);
 	if (ret)
 		goto pdown;
-- 
cgit v1.2.3


From 7cf2f6ed8e7a3bf481ef70b6b4a2edb8abfa5c57 Mon Sep 17 00:00:00 2001
From: Billy Tsai <billy_tsai@aspeedtech.com>
Date: Tue, 3 Mar 2026 10:38:26 +0800
Subject: iio: adc: aspeed: clear reference voltage bits before configuring
 vref

Ensures the reference voltage bits are cleared in the ADC engine
control register before configuring the voltage reference. This
avoids potential misconfigurations caused by residual bits.

Fixes: 1b5ceb55fec2 ("iio: adc: aspeed: Support ast2600 adc.")
Signed-off-by: Billy Tsai <billy_tsai@aspeedtech.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/aspeed_adc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iio/adc/aspeed_adc.c b/drivers/iio/adc/aspeed_adc.c
index 4be44c524b4d..83a9885b9ae4 100644
--- a/drivers/iio/adc/aspeed_adc.c
+++ b/drivers/iio/adc/aspeed_adc.c
@@ -415,6 +415,7 @@ static int aspeed_adc_vref_config(struct iio_dev *indio_dev)
 	}
 	adc_engine_control_reg_val =
 		readl(data->base + ASPEED_REG_ENGINE_CONTROL);
+	adc_engine_control_reg_val &= ~ASPEED_ADC_REF_VOLTAGE;
 
 	ret = devm_regulator_get_enable_read_voltage(data->dev, "vref");
 	if (ret < 0 && ret != -ENODEV)
-- 
cgit v1.2.3


From ea7e2e43d768102e2601dbbda42041c78d7a99f9 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 27 Feb 2026 14:20:46 +0200
Subject: iio: imu: adis16550: fix swapped gyro/accel filter functions

The low-pass filter handlers for IIO_ANGL_VEL and IIO_ACCEL call each
other's filter functions in both read_raw and write_raw. Swap them so
each channel type uses its correct filter accessor.

Fixes: bac4368fab62 ("iio: imu: adis16550: add adis16550 support")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Acked-by: Robert Budai <robert.budai@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis16550.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c
index 28f0dbd0226c..1f2af506f4bd 100644
--- a/drivers/iio/imu/adis16550.c
+++ b/drivers/iio/imu/adis16550.c
@@ -643,12 +643,12 @@ static int adis16550_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
 		switch (chan->type) {
 		case IIO_ANGL_VEL:
-			ret = adis16550_get_accl_filter_freq(st, val);
+			ret = adis16550_get_gyro_filter_freq(st, val);
 			if (ret)
 				return ret;
 			return IIO_VAL_INT;
 		case IIO_ACCEL:
-			ret = adis16550_get_gyro_filter_freq(st, val);
+			ret = adis16550_get_accl_filter_freq(st, val);
 			if (ret)
 				return ret;
 			return IIO_VAL_INT;
@@ -681,9 +681,9 @@ static int adis16550_write_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
 		switch (chan->type) {
 		case IIO_ANGL_VEL:
-			return adis16550_set_accl_filter_freq(st, val);
-		case IIO_ACCEL:
 			return adis16550_set_gyro_filter_freq(st, val);
+		case IIO_ACCEL:
+			return adis16550_set_accl_filter_freq(st, val);
 		default:
 			return -EINVAL;
 		}
-- 
cgit v1.2.3


From 57ccf5ccdc56954f2a91a7f66684fd31c566bde5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 7 Mar 2026 04:53:32 -1000
Subject: sched_ext: Fix enqueue_task_scx() truncation of upper enqueue flags

enqueue_task_scx() takes int enq_flags from the sched_class interface.
SCX enqueue flags starting at bit 32 (SCX_ENQ_PREEMPT and above) are
silently truncated when passed through activate_task(). extra_enq_flags
was added as a workaround - storing high bits in rq->scx.extra_enq_flags
and OR-ing them back in enqueue_task_scx(). However, the OR target is
still the int parameter, so the high bits are lost anyway.

The current impact is limited as the only affected flag is SCX_ENQ_PREEMPT
which is informational to the BPF scheduler - its loss means the scheduler
doesn't know about preemption but doesn't cause incorrect behavior.

Fix by renaming the int parameter to core_enq_flags and introducing a
u64 enq_flags local that merges both sources. All downstream functions
already take u64 enq_flags.

Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index f323df7be180..174e3650d7fe 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1470,16 +1470,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
 }
 
-static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
+static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags)
 {
 	struct scx_sched *sch = scx_root;
 	int sticky_cpu = p->scx.sticky_cpu;
+	u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags;
 
 	if (enq_flags & ENQUEUE_WAKEUP)
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
 
-	enq_flags |= rq->scx.extra_enq_flags;
-
 	if (sticky_cpu >= 0)
 		p->scx.sticky_cpu = -1;
 
-- 
cgit v1.2.3


From 4ce7ada40c008fa21b7e52ab9d04e8746e2e9325 Mon Sep 17 00:00:00 2001
From: Junxiao Bi <junxiao.bi@oracle.com>
Date: Wed, 4 Mar 2026 08:46:03 -0800
Subject: scsi: core: Fix error handling for scsi_alloc_sdev()

After scsi_sysfs_device_initialize() was called, error paths must call
__scsi_remove_device().

Fixes: 1ac22c8eae81 ("scsi: core: Fix refcount leak for tagset_refcnt")
Cc: stable@vger.kernel.org
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260304164603.51528-1-junxiao.bi@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_scan.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 2cfcf1f5d6a4..7b11bc7de0e3 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -360,12 +360,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * default device queue depth to figure out sbitmap shift
 	 * since we use this queue depth most of times.
 	 */
-	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
-		kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
-		put_device(&starget->dev);
-		kfree(sdev);
-		goto out;
-	}
+	if (scsi_realloc_sdev_budget_map(sdev, depth))
+		goto out_device_destroy;
 
 	scsi_change_queue_depth(sdev, depth);
 
-- 
cgit v1.2.3


From b0bd84c39289ef6a6c3827dd52c875659291970a Mon Sep 17 00:00:00 2001
From: Wang Shuaiwei <wangshuaiwei1@xiaomi.com>
Date: Sat, 7 Mar 2026 11:51:28 +0800
Subject: scsi: ufs: core: Fix SError in ufshcd_rtc_work() during UFS suspend

In __ufshcd_wl_suspend(), cancel_delayed_work_sync() is called to cancel
the UFS RTC work, but it is placed after ufshcd_vops_suspend(hba, pm_op,
POST_CHANGE). This creates a race condition where ufshcd_rtc_work() can
still be running while ufshcd_vops_suspend() is executing. When
UFSHCD_CAP_CLK_GATING is not supported, the condition
!hba->clk_gating.active_reqs is always true, causing ufshcd_update_rtc()
to be executed. Since ufshcd_vops_suspend() typically performs clock
gating operations, executing ufshcd_update_rtc() at that moment triggers
an SError. The kernel panic trace is as follows:

Kernel panic - not syncing: Asynchronous SError Interrupt
Call trace:
 dump_backtrace+0xec/0x128
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0xa0
 dump_stack+0x18/0x24
 panic+0x148/0x374
 nmi_panic+0x3c/0x8c
 arm64_serror_panic+0x64/0x8c
 do_serror+0xc4/0xc8
 el1h_64_error_handler+0x34/0x4c
 el1h_64_error+0x68/0x6c
 el1_interrupt+0x20/0x58
 el1h_64_irq_handler+0x18/0x24
 el1h_64_irq+0x68/0x6c
 ktime_get+0xc4/0x12c
 ufshcd_mcq_sq_stop+0x4c/0xec
 ufshcd_mcq_sq_cleanup+0x64/0x1dc
 ufshcd_clear_cmd+0x38/0x134
 ufshcd_issue_dev_cmd+0x298/0x4d0
 ufshcd_exec_dev_cmd+0x1a4/0x1c4
 ufshcd_query_attr+0xbc/0x19c
 ufshcd_rtc_work+0x10c/0x1c8
 process_scheduled_works+0x1c4/0x45c
 worker_thread+0x32c/0x3e8
 kthread+0x120/0x1d8
 ret_from_fork+0x10/0x20

Fix this by moving cancel_delayed_work_sync() before the call to
ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE), ensuring the UFS RTC work is
fully completed or cancelled at that point.

Cc: Bean Huo <beanhuo@iokpp.de>
Fixes: 6bf999e0eb41 ("scsi: ufs: core: Add UFS RTC support")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Wang Shuaiwei <wangshuaiwei1@xiaomi.com>
Link: https://patch.msgid.link/20260307035128.3419687-1-wangshuaiwei1@xiaomi.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 899e663fea6e..9ceb6d6d479d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10066,6 +10066,7 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	}
 
 	flush_work(&hba->eeh_work);
+	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 
 	ret = ufshcd_vops_suspend(hba, pm_op, PRE_CHANGE);
 	if (ret)
@@ -10120,7 +10121,6 @@ vops_suspend:
 	if (ret)
 		goto set_link_active;
 
-	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 	goto out;
 
 set_link_active:
-- 
cgit v1.2.3


From c0b7da13a04bd70ef6070bfb9ea85f582294560a Mon Sep 17 00:00:00 2001
From: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Date: Tue, 10 Feb 2026 11:08:22 +0100
Subject: scsi: qla2xxx: Completely fix fcport double free

In qla24xx_els_dcmd_iocb() sp->free is set to qla2x00_els_dcmd_sp_free().
When an error happens, this function is called by qla2x00_sp_release(),
when kref_put() releases the first and the last reference.

qla2x00_els_dcmd_sp_free() frees fcport by calling qla2x00_free_fcport().
Doing it one more time after kref_put() is a bad idea.

Fixes: 82f522ae0d97 ("scsi: qla2xxx: Fix double free of fcport")
Fixes: 4895009c4bb7 ("scsi: qla2xxx: Prevent command send on chip reset")
Signed-off-by: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Signed-off-by: Farhat Abbas <fabbas@cloudlinux.com>
Link: https://patch.msgid.link/aYsDln9NFQQsPDgg@vova-pc
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 9038f6723444..dbe3cd4e274c 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2751,7 +2751,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	if (!elsio->u.els_logo.els_logo_pyld) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
-		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2776,7 +2775,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	if (rval != QLA_SUCCESS) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
-		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 
-- 
cgit v1.2.3


From 8ddc0c26916574395447ebf4cff684314f6873a9 Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Thu, 5 Mar 2026 14:40:39 +0800
Subject: scsi: hisi_sas: Fix NULL pointer exception during user_scan()

user_scan() invokes updated sas_user_scan() for channel 0, and if
successful, iteratively scans remaining channels (1 to shost->max_channel)
via scsi_scan_host_selected() in commit 37c4e72b0651 ("scsi: Fix
sas_user_scan() to handle wildcard and multi-channel scans"). However,
hisi_sas supports only one channel, and the current value of max_channel is
1. sas_user_scan() for channel 1 will trigger the following NULL pointer
exception:

[  441.554662] Unable to handle kernel NULL pointer dereference at virtual address 00000000000008b0
[  441.554699] Mem abort info:
[  441.554710]   ESR = 0x0000000096000004
[  441.554718]   EC = 0x25: DABT (current EL), IL = 32 bits
[  441.554723]   SET = 0, FnV = 0
[  441.554726]   EA = 0, S1PTW = 0
[  441.554730]   FSC = 0x04: level 0 translation fault
[  441.554735] Data abort info:
[  441.554737]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[  441.554742]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[  441.554747]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[  441.554752] user pgtable: 4k pages, 48-bit VAs, pgdp=00000828377a6000
[  441.554757] [00000000000008b0] pgd=0000000000000000, p4d=0000000000000000
[  441.554769] Internal error: Oops: 0000000096000004 [#1]  SMP
[  441.629589] Modules linked in: arm_spe_pmu arm_smmuv3_pmu tpm_tis_spi hisi_uncore_sllc_pmu hisi_uncore_pa_pmu hisi_uncore_l3c_pmu hisi_uncore_hha_pmu hisi_uncore_ddrc_pmu hisi_uncore_cpa_pmu hns3_pmu hisi_ptt hisi_pcie_pmu tpm_tis_core spidev spi_hisi_sfc_v3xx hisi_uncore_pmu spi_dw_mmio fuse hclge hclge_common hisi_sec2 hisi_hpre hisi_zip hisi_qm hns3 hisi_sas_v3_hw sm3_ce sbsa_gwdt hnae3 hisi_sas_main uacce hisi_dma i2c_hisi dm_mirror dm_region_hash dm_log dm_mod
[  441.670819] CPU: 46 UID: 0 PID: 6994 Comm: bash Kdump: loaded Not tainted 7.0.0-rc2+ #84 PREEMPT
[  441.691327] pstate: 81400009 (Nzcv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[  441.698277] pc : sas_find_dev_by_rphy+0x44/0x118
[  441.702896] lr : sas_find_dev_by_rphy+0x3c/0x118
[  441.707502] sp : ffff80009abbba40
[  441.710805] x29: ffff80009abbba40 x28: ffff082819a40008 x27: ffff082810c37c08
[  441.717930] x26: ffff082810c37c28 x25: ffff082819a40290 x24: ffff082810c37c00
[  441.725054] x23: 0000000000000000 x22: 0000000000000001 x21: ffff082819a40000
[  441.732179] x20: ffff082819a40290 x19: 0000000000000000 x18: 0000000000000020
[  441.739304] x17: 0000000000000000 x16: ffffb5dad6bda690 x15: 00000000ffffffff
[  441.746428] x14: ffff082814c3b26c x13: 00000000ffffffff x12: ffff082814c3b26a
[  441.753553] x11: 00000000000000c0 x10: 000000000000003a x9 : ffffb5dad5ea94f4
[  441.760678] x8 : 000000000000003a x7 : ffff80009abbbab0 x6 : 0000000000000030
[  441.767802] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
[  441.774926] x2 : ffff08280f35a300 x1 : ffffb5dad7127180 x0 : 0000000000000000
[  441.782053] Call trace:
[  441.784488]  sas_find_dev_by_rphy+0x44/0x118 (P)
[  441.789095]  sas_target_alloc+0x24/0xb0
[  441.792920]  scsi_alloc_target+0x290/0x330
[  441.797010]  __scsi_scan_target+0x88/0x258
[  441.801096]  scsi_scan_channel+0x74/0xb8
[  441.805008]  scsi_scan_host_selected+0x170/0x188
[  441.809615]  sas_user_scan+0xfc/0x148
[  441.813267]  store_scan+0x10c/0x180
[  441.816743]  dev_attr_store+0x20/0x40
[  441.820398]  sysfs_kf_write+0x84/0xa8
[  441.824054]  kernfs_fop_write_iter+0x130/0x1c8
[  441.828487]  vfs_write+0x2c0/0x370
[  441.831880]  ksys_write+0x74/0x118
[  441.835271]  __arm64_sys_write+0x24/0x38
[  441.839182]  invoke_syscall+0x50/0x120
[  441.842919]  el0_svc_common.constprop.0+0xc8/0xf0
[  441.847611]  do_el0_svc+0x24/0x38
[  441.850913]  el0_svc+0x38/0x158
[  441.854043]  el0t_64_sync_handler+0xa0/0xe8
[  441.858214]  el0t_64_sync+0x1ac/0x1b0
[  441.861865] Code: aa1303e0 97ff70a8 34ffff80 d10a4273 (f9445a75)
[  441.867946] ---[ end trace 0000000000000000 ]---

Therefore, set max_channel to 0.

Fixes: e21fe3a52692 ("scsi: hisi_sas: add initialisation for v3 pci-based controller")
Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Link: https://patch.msgid.link/20260305064039.4096775-1-liyihang9@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 2 +-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 30a9c6612651..c2b082f1252c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2578,7 +2578,7 @@ int hisi_sas_probe(struct platform_device *pdev,
 	shost->transportt = hisi_sas_stt;
 	shost->max_id = HISI_SAS_MAX_DEVICES;
 	shost->max_lun = ~0;
-	shost->max_channel = 1;
+	shost->max_channel = 0;
 	shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN;
 	if (hisi_hba->hw->slot_index_alloc) {
 		shost->can_queue = HISI_SAS_MAX_COMMANDS;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 2f9e01717ef3..f69efc6494b8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4993,7 +4993,7 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	shost->transportt = hisi_sas_stt;
 	shost->max_id = HISI_SAS_MAX_DEVICES;
 	shost->max_lun = ~0;
-	shost->max_channel = 1;
+	shost->max_channel = 0;
 	shost->max_cmd_len = HISI_SAS_MAX_CDB_LEN;
 	shost->can_queue = HISI_SAS_UNRESERVED_IPTT;
 	shost->cmd_per_lun = HISI_SAS_UNRESERVED_IPTT;
-- 
cgit v1.2.3


From b0dcdcb9ae757c8a8ba2fb24d34f8d147bae707b Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Wed, 4 Mar 2026 17:47:30 -0800
Subject: resolve_btfids: Fix linker flags detection

The "|| echo -lzstd" default makes zstd an unconditional link
dependency of resolve_btfids. On systems where libzstd-dev is not
installed and pkg-config fails, the linker fails:

  ld: cannot find -lzstd: No such file or directory

libzstd is a transitive dependency of libelf, so the -lzstd flag is
strictly necessary only for static builds [1].

Remove ZSTD_LIBS variable, and instead set LIBELF_LIBS depending on
whether the build is static or not. Use $(HOSTPKG_CONFIG) as primary
source of the flags list.

Also add a default value for HOSTPKG_CONFIG in case it's not built via
the toplevel Makefile. Pass it from selftests/bpf too.

[1] https://lore.kernel.org/bpf/4ff82800-2daa-4b9f-95a9-6f512859ee70@linux.dev/

Reported-by: BPF CI Bot (Claude Opus 4.6) <bot+bpf-ci@kernel.org>
Reported-by: Vitaly Chikunov <vt@altlinux.org>
Closes: https://lore.kernel.org/bpf/aaWqMcK-2AQw5dx8@altlinux.org/
Fixes: 4021848a903e ("selftests/bpf: Pass through build flags to bpftool and resolve_btfids")
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Reviewed-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/20260305014730.3123382-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/resolve_btfids/Makefile    | 9 +++++++--
 tools/testing/selftests/bpf/Makefile | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index ef083602b73a..7672208f65e4 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -23,6 +23,7 @@ RM      ?= rm
 HOSTCC  ?= gcc
 HOSTLD  ?= ld
 HOSTAR  ?= ar
+HOSTPKG_CONFIG ?= pkg-config
 CROSS_COMPILE =
 
 OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
@@ -63,10 +64,14 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU
 		    $(abspath $@) install_headers
 
 LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null)
+
+ifneq ($(filter -static,$(EXTRA_LDFLAGS)),)
+LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs --static 2>/dev/null || echo -lelf -lzstd)
+else
 LIBELF_LIBS  := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+endif
 
 ZLIB_LIBS  := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz)
-ZSTD_LIBS  := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd)
 
 HOSTCFLAGS_resolve_btfids += -g \
           -I$(srctree)/tools/include \
@@ -76,7 +81,7 @@ HOSTCFLAGS_resolve_btfids += -g \
           $(LIBELF_FLAGS) \
           -Wall -Werror
 
-LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS)
+LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS)
 
 export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 72a9ba41f95e..d5acbeba0383 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -409,6 +409,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
 		EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \
+		HOSTPKG_CONFIG=$(PKG_CONFIG) \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-- 
cgit v1.2.3


From 879c001afbac3df94160334fe5117c0c83b2cf48 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Wed, 21 Jan 2026 21:08:19 +0800
Subject: firmware: arm_scpi: Fix device_node reference leak in probe path

A device_node reference obtained from the device tree is not released
on all error paths in the arm_scpi probe path. Specifically, a node
returned by of_parse_phandle() could be leaked when the probe failed
after the node was acquired. The probe function returns early and
the shmem reference is not released.

Use __free(device_node) scope-based cleanup to automatically release
the reference when the variable goes out of scope.

Fixes: ed7ecb883901 ("firmware: arm_scpi: Add compatibility checks for shmem node")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Message-Id: <20260121-arm_scpi_2-v2-1-702d7fa84acb@gmail.com>
Signed-off-by: Sudeep Holla <sudeep.holla@kernel.org>
---
 drivers/firmware/arm_scpi.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c
index 00e74449ce09..2acad5fa5a28 100644
--- a/drivers/firmware/arm_scpi.c
+++ b/drivers/firmware/arm_scpi.c
@@ -18,6 +18,7 @@
 
 #include <linux/bitmap.h>
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/export.h>
@@ -940,13 +941,13 @@ static int scpi_probe(struct platform_device *pdev)
 		int idx = scpi_drvinfo->num_chans;
 		struct scpi_chan *pchan = scpi_drvinfo->channels + idx;
 		struct mbox_client *cl = &pchan->cl;
-		struct device_node *shmem = of_parse_phandle(np, "shmem", idx);
+		struct device_node *shmem __free(device_node) =
+			of_parse_phandle(np, "shmem", idx);
 
 		if (!of_match_node(shmem_of_match, shmem))
 			return -ENXIO;
 
 		ret = of_address_to_resource(shmem, 0, &res);
-		of_node_put(shmem);
 		if (ret) {
 			dev_err(dev, "failed to get SCPI payload mem resource\n");
 			return ret;
-- 
cgit v1.2.3


From 555317d6100164748f7d09f80142739bd29f0cda Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 5 Mar 2026 13:10:11 +0000
Subject: firmware: arm_scmi: Fix NULL dereference on notify error path

Since commit b5daf93b809d1 ("firmware: arm_scmi: Avoid notifier
registration for unsupported events") the call chains leading to the helper
__scmi_event_handler_get_ops expect an ERR_PTR to be returned on failure to
get an handler for the requested event key, while the current helper can
still return a NULL when no handler could be found or created.

Fix by forcing an ERR_PTR return value when the handler reference is NULL.

Fixes: b5daf93b809d1 ("firmware: arm_scmi: Avoid notifier registration for unsupported events")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Message-Id: <20260305131011.541444-1-cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@kernel.org>
---
 drivers/firmware/arm_scmi/notify.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/notify.c b/drivers/firmware/arm_scmi/notify.c
index 9168794adae4..40ec184eedae 100644
--- a/drivers/firmware/arm_scmi/notify.c
+++ b/drivers/firmware/arm_scmi/notify.c
@@ -1066,7 +1066,7 @@ static int scmi_register_event_handler(struct scmi_notify_instance *ni,
  * since at creation time we usually want to have all setup and ready before
  * events really start flowing.
  *
- * Return: A properly refcounted handler on Success, NULL on Failure
+ * Return: A properly refcounted handler on Success, ERR_PTR on Failure
  */
 static inline struct scmi_event_handler *
 __scmi_event_handler_get_ops(struct scmi_notify_instance *ni,
@@ -1113,7 +1113,7 @@ __scmi_event_handler_get_ops(struct scmi_notify_instance *ni,
 	}
 	mutex_unlock(&ni->pending_mtx);
 
-	return hndl;
+	return hndl ?: ERR_PTR(-ENODEV);
 }
 
 static struct scmi_event_handler *
-- 
cgit v1.2.3


From 75aa996ea63f8656b668f8d9acb2c7a77c055e7f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 6 Mar 2026 12:19:19 +0100
Subject: s390: Revert "s390/irq/idle: Remove psw bits early"

This reverts commit d8b5cf9c63143fae54a734c41e3bb55cf3f365c7.

Mikhail Zaslonko reported that linux-next doesn't boot anymore [2]. Reason
for this is recent change [2] was supposed to slightly optimize the irq
entry/exit path by removing some psw bits early in case of an idle exit.

This however is incorrect since irqentry_exit() requires the correct old
psw state at irq entry. Otherwise the embedded regs_irqs_disabled() will
not provide the correct result.

With linux-next and HRTIMER_REARM_DEFERRED this leads to the observed boot
problems, however the commit is broken in any case.

Revert the commit which introduced this.

Thanks to Peter Zijlstra for pointing out that this is a bug in the s390
entry code.

Fixes: d8b5cf9c6314 ("s390/irq/idle: Remove psw bits early") [1]
Reported-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Closes: https://lore.kernel.org/r/af549a19-db99-4b16-8511-bf315177a13e@linux.ibm.com/ [2]
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Tested-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20260306111919.362559-1-hca@linux.ibm.com
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/irq.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 7fdf960191d3..d10a17e6531d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -147,10 +147,8 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle) {
+	if (from_idle)
 		update_timer_idle();
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
-	}
 
 	irq_enter_rcu();
 
@@ -176,6 +174,9 @@ void noinstr do_io_irq(struct pt_regs *regs)
 
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 void noinstr do_ext_irq(struct pt_regs *regs)
@@ -185,10 +186,8 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	bool from_idle;
 
 	from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT);
-	if (from_idle) {
+	if (from_idle)
 		update_timer_idle();
-		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
-	}
 
 	irq_enter_rcu();
 
@@ -210,6 +209,9 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
+
+	if (from_idle)
+		regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT);
 }
 
 static void show_msi_interrupt(struct seq_file *p, int irq)
-- 
cgit v1.2.3


From 598bbefa8032cc58b564a81d1ad68bd815c8dc0f Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@linux.ibm.com>
Date: Fri, 27 Feb 2026 14:30:51 +0100
Subject: s390/zcrypt: Enable AUTOSEL_DOM for CCA serialnr sysfs attribute

The serialnr sysfs attribute for CCA cards when queried always
used the default domain for sending the request down to the card.
If for any reason exactly this default domain is disabled then
the attribute code fails to retrieve the CCA info and the sysfs
entry shows an empty string. Works as designed but the serial
number is a card attribute and thus it does not matter which
domain is used for the query. So if there are other domains on
this card available, these could be used.

So extend the code to use AUTOSEL_DOM for the domain value to
address any online domain within the card for querying the cca
info and thus show the serialnr as long as there is one domain
usable regardless of the default domain setting.

Fixes: 8f291ebf3270 ("s390/zcrypt: enable card/domain autoselect on ep11 cprbs")
Suggested-by: Ingo Franzki <ifranzki@linux.ibm.com>
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Reviewed-by: Ingo Franzki <ifranzki@linux.ibm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 drivers/s390/crypto/zcrypt_ccamisc.c | 12 +++++++-----
 drivers/s390/crypto/zcrypt_cex4.c    |  3 +--
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 573bad1d6d86..37a157a1d969 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -1639,11 +1639,13 @@ int cca_get_info(u16 cardnr, u16 domain, struct cca_info *ci, u32 xflags)
 
 	memset(ci, 0, sizeof(*ci));
 
-	/* get first info from zcrypt device driver about this apqn */
-	rc = zcrypt_device_status_ext(cardnr, domain, &devstat);
-	if (rc)
-		return rc;
-	ci->hwtype = devstat.hwtype;
+	/* if specific domain given, fetch status and hw info for this apqn */
+	if (domain != AUTOSEL_DOM) {
+		rc = zcrypt_device_status_ext(cardnr, domain, &devstat);
+		if (rc)
+			return rc;
+		ci->hwtype = devstat.hwtype;
+	}
 
 	/*
 	 * Prep memory for rule array and var array use.
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index e9a984903bff..e7b0ed26a9ec 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -85,8 +85,7 @@ static ssize_t cca_serialnr_show(struct device *dev,
 
 	memset(&ci, 0, sizeof(ci));
 
-	if (ap_domain_index >= 0)
-		cca_get_info(ac->id, ap_domain_index, &ci, 0);
+	cca_get_info(ac->id, AUTOSEL_DOM, &ci, 0);
 
 	return sysfs_emit(buf, "%s\n", ci.serial);
 }
-- 
cgit v1.2.3


From 6da5e537f5afe091658e846da1949d7e557d2ade Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 7 Mar 2026 19:11:51 +0000
Subject: KVM: arm64: vgic: Pick EOIcount deactivations from AP-list tail

Valentine reports that their guests fail to boot correctly, losing
interrupts, and indicates that the wrong interrupt gets deactivated.

What happens here is that if the maintenance interrupt is slow enough
to kick us out of the guest, extra interrupts can be activated from
the LRs. We then exit and proceed to handle EOIcount deactivations,
picking active interrupts from the AP list. But we start from the
top of the list, potentially deactivating interrupts that were in
the LRs, while EOIcount only denotes deactivation of interrupts that
are not present in an LR.

Solve this by tracking the last interrupt that made it in the LRs,
and start the EOIcount deactivation walk *after* that interrupt.
Since this only makes sense while the vcpu is loaded, stash this
in the per-CPU host state.

Huge thanks to Valentine for doing all the detective work and
providing an initial patch.

Fixes: 3cfd59f81e0f3 ("KVM: arm64: GICv3: Handle LR overflow when EOImode==0")
Fixes: 281c6c06e2a7b ("KVM: arm64: GICv2: Handle LR overflow when EOImode==0")
Reported-by: Valentine Burley <valentine.burley@collabora.com>
Tested-by: Valentine Burley <valentine.burley@collabora.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20260307115955.369455-1-valentine.burley@collabora.com
Link: https://patch.msgid.link/20260307191151.3781182-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/include/asm/kvm_host.h |  3 +++
 arch/arm64/kvm/vgic/vgic-v2.c     |  4 ++--
 arch/arm64/kvm/vgic/vgic-v3.c     | 12 ++++++------
 arch/arm64/kvm/vgic/vgic.c        |  6 ++++++
 4 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2ca264b3db5f..70cb9cfd760a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -784,6 +784,9 @@ struct kvm_host_data {
 	/* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
 	unsigned int debug_brps;
 	unsigned int debug_wrps;
+
+	/* Last vgic_irq part of the AP list recorded in an LR */
+	struct vgic_irq *last_lr_irq;
 };
 
 struct kvm_host_psci_config {
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index 585491fbda80..cafa3cb32bda 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -115,7 +115,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2;
 	u32 eoicount = FIELD_GET(GICH_HCR_EOICOUNT, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
@@ -123,7 +123,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 		vgic_v2_fold_lr(vcpu, cpuif->vgic_lr[lr]);
 
 	/* See the GICv3 equivalent for the EOIcount handling rationale */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u32 lr;
 
 		if (!eoicount) {
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 386ddf69a9c5..6a355eca1934 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -148,7 +148,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3;
 	u32 eoicount = FIELD_GET(ICH_HCR_EL2_EOIcount, cpuif->vgic_hcr);
-	struct vgic_irq *irq;
+	struct vgic_irq *irq = *host_data_ptr(last_lr_irq);
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
@@ -158,12 +158,12 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	/*
 	 * EOIMode=0: use EOIcount to emulate deactivation. We are
 	 * guaranteed to deactivate in reverse order of the activation, so
-	 * just pick one active interrupt after the other in the ap_list,
-	 * and replay the deactivation as if the CPU was doing it. We also
-	 * rely on priority drop to have taken place, and the list to be
-	 * sorted by priority.
+	 * just pick one active interrupt after the other in the tail part
+	 * of the ap_list, past the LRs, and replay the deactivation as if
+	 * the CPU was doing it. We also rely on priority drop to have taken
+	 * place, and the list to be sorted by priority.
 	 */
-	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+	list_for_each_entry_continue(irq, &vgic_cpu->ap_list_head, ap_list) {
 		u64 lr;
 
 		/*
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 430aa98888fd..e22b79cfff96 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -814,6 +814,9 @@ retry:
 
 static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
 {
+	if (!*host_data_ptr(last_lr_irq))
+		return;
+
 	if (kvm_vgic_global_state.type == VGIC_V2)
 		vgic_v2_fold_lr_state(vcpu);
 	else
@@ -960,10 +963,13 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 	if (irqs_outside_lrs(&als))
 		vgic_sort_ap_list(vcpu);
 
+	*host_data_ptr(last_lr_irq) = NULL;
+
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		scoped_guard(raw_spinlock,  &irq->irq_lock) {
 			if (likely(vgic_target_oracle(irq) == vcpu)) {
 				vgic_populate_lr(vcpu, irq, count++);
+				*host_data_ptr(last_lr_irq) = irq;
 			}
 		}
 
-- 
cgit v1.2.3


From 08da98f18f4f99aa16838397b76086d2d1d364b3 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:34 +0000
Subject: rust: ptr: add `KnownSize` trait to support DST size info extraction

Add a `KnownSize` trait which is used obtain a size from a raw pointer's
metadata. This makes it possible to obtain size information on a raw slice
pointer. This is similar to Rust `core::mem::size_of_val_raw` which is not
yet stable.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://patch.msgid.link/20260302164239.284084-2-gary@kernel.org
[ Fix wording in doc-comment. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/lib.rs |  1 +
 rust/kernel/ptr.rs | 27 ++++++++++++++++++++++++++-
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 3da92f18f4ee..510cc7fe4961 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -20,6 +20,7 @@
 #![feature(generic_nonzero)]
 #![feature(inline_const)]
 #![feature(pointer_is_aligned)]
+#![feature(slice_ptr_len)]
 //
 // Stable since Rust 1.80.0.
 #![feature(slice_flatten)]
diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs
index 5b6a382637fe..e91de5f0d78f 100644
--- a/rust/kernel/ptr.rs
+++ b/rust/kernel/ptr.rs
@@ -2,7 +2,10 @@
 
 //! Types and functions to work with pointers and addresses.
 
-use core::mem::align_of;
+use core::mem::{
+    align_of,
+    size_of, //
+};
 use core::num::NonZero;
 
 /// Type representing an alignment, which is always a power of two.
@@ -225,3 +228,25 @@ macro_rules! impl_alignable_uint {
 }
 
 impl_alignable_uint!(u8, u16, u32, u64, usize);
+
+/// Trait to represent compile-time known size information.
+///
+/// This is a generalization of [`size_of`] that works for dynamically sized types.
+pub trait KnownSize {
+    /// Get the size of an object of this type in bytes, with the metadata of the given pointer.
+    fn size(p: *const Self) -> usize;
+}
+
+impl<T> KnownSize for T {
+    #[inline(always)]
+    fn size(_: *const Self) -> usize {
+        size_of::<T>()
+    }
+}
+
+impl<T> KnownSize for [T] {
+    #[inline(always)]
+    fn size(p: *const Self) -> usize {
+        p.len() * size_of::<T>()
+    }
+}
-- 
cgit v1.2.3


From f41941aab3acd33f13d65a2ae496329bc8ae4de0 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:35 +0000
Subject: rust: ptr: add projection infrastructure

Add a generic infrastructure for performing field and index projections on
raw pointers. This will form the basis of performing I/O projections.

Pointers manipulations are intentionally using the safe wrapping variants
instead of the unsafe variants, as the latter requires pointers to be
inside an allocation which is not necessarily true for I/O pointers.

This projection macro protects against rogue `Deref` implementation, which
can causes the projected pointer to be outside the bounds of starting
pointer. This is extremely unlikely and Rust has a lint to catch this, but
is unsoundness regardless. The protection works by inducing type inference
ambiguity when `Deref` is implemented.

This projection macro also stops projecting into unaligned fields (i.e.
fields of `#[repr(packed)]` structs), as misaligned pointers require
special handling. This is implemented by attempting to create reference to
projected field inside a `if false` block. Despite being unreachable, Rust
still checks that they're not unaligned fields.

The projection macro supports both fallible and infallible index
projections. These are described in detail inside the documentation.

Signed-off-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://patch.msgid.link/20260302164239.284084-3-gary@kernel.org
[ * Add intro-doc links where possible,
  * Fix typos and slightly improve wording, e.g. "as documentation
    describes" -> "as the documentation of [`Self::proj`] describes",
  * Add an empty line between regular and safety comments, before
    examples, and between logically independent comments,
  * Capitalize various safety comments.

    - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/lib.rs            |   3 +
 rust/kernel/ptr.rs            |   3 +
 rust/kernel/ptr/projection.rs | 305 ++++++++++++++++++++++++++++++++++++++++++
 scripts/Makefile.build        |   4 +-
 4 files changed, 314 insertions(+), 1 deletion(-)
 create mode 100644 rust/kernel/ptr/projection.rs

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 510cc7fe4961..d93292d47420 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -38,6 +38,9 @@
 #![feature(const_ptr_write)]
 #![feature(const_refs_to_cell)]
 //
+// Stable since Rust 1.84.0.
+#![feature(strict_provenance)]
+//
 // Expected to become stable.
 #![feature(arbitrary_self_types)]
 //
diff --git a/rust/kernel/ptr.rs b/rust/kernel/ptr.rs
index e91de5f0d78f..bdc2d79ff669 100644
--- a/rust/kernel/ptr.rs
+++ b/rust/kernel/ptr.rs
@@ -2,6 +2,9 @@
 
 //! Types and functions to work with pointers and addresses.
 
+pub mod projection;
+pub use crate::project_pointer as project;
+
 use core::mem::{
     align_of,
     size_of, //
diff --git a/rust/kernel/ptr/projection.rs b/rust/kernel/ptr/projection.rs
new file mode 100644
index 000000000000..140ea8e21617
--- /dev/null
+++ b/rust/kernel/ptr/projection.rs
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Infrastructure for handling projections.
+
+use core::{
+    mem::MaybeUninit,
+    ops::Deref, //
+};
+
+use crate::prelude::*;
+
+/// Error raised when a projection is attempted on an array or slice out of bounds.
+pub struct OutOfBound;
+
+impl From<OutOfBound> for Error {
+    #[inline(always)]
+    fn from(_: OutOfBound) -> Self {
+        ERANGE
+    }
+}
+
+/// A helper trait to perform index projection.
+///
+/// This is similar to [`core::slice::SliceIndex`], but operates on raw pointers safely and
+/// fallibly.
+///
+/// # Safety
+///
+/// The implementation of `index` and `get` (if [`Some`] is returned) must ensure that, if provided
+/// input pointer `slice` and returned pointer `output`, then:
+/// - `output` has the same provenance as `slice`;
+/// - `output.byte_offset_from(slice)` is between 0 to
+///   `KnownSize::size(slice) - KnownSize::size(output)`.
+///
+/// This means that if the input pointer is valid, then pointer returned by `get` or `index` is
+/// also valid.
+#[diagnostic::on_unimplemented(message = "`{Self}` cannot be used to index `{T}`")]
+#[doc(hidden)]
+pub unsafe trait ProjectIndex<T: ?Sized>: Sized {
+    type Output: ?Sized;
+
+    /// Returns an index-projected pointer, if in bounds.
+    fn get(self, slice: *mut T) -> Option<*mut Self::Output>;
+
+    /// Returns an index-projected pointer; fail the build if it cannot be proved to be in bounds.
+    #[inline(always)]
+    fn index(self, slice: *mut T) -> *mut Self::Output {
+        Self::get(self, slice).unwrap_or_else(|| build_error!())
+    }
+}
+
+// Forward array impl to slice impl.
+//
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T, I, const N: usize> ProjectIndex<[T; N]> for I
+where
+    I: ProjectIndex<[T]>,
+{
+    type Output = <I as ProjectIndex<[T]>>::Output;
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T; N]) -> Option<*mut Self::Output> {
+        <I as ProjectIndex<[T]>>::get(self, slice)
+    }
+
+    #[inline(always)]
+    fn index(self, slice: *mut [T; N]) -> *mut Self::Output {
+        <I as ProjectIndex<[T]>>::index(self, slice)
+    }
+}
+
+// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to
+// not exceed the required bound.
+unsafe impl<T> ProjectIndex<[T]> for usize {
+    type Output = T;
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut T> {
+        if self >= slice.len() {
+            None
+        } else {
+            Some(slice.cast::<T>().wrapping_add(self))
+        }
+    }
+}
+
+// SAFETY: `get`-returned pointer has the same provenance as `slice` and the offset is checked to
+// not exceed the required bound.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::Range<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        let new_len = self.end.checked_sub(self.start)?;
+        if self.end > slice.len() {
+            return None;
+        }
+        Some(core::ptr::slice_from_raw_parts_mut(
+            slice.cast::<T>().wrapping_add(self.start),
+            new_len,
+        ))
+    }
+}
+
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeTo<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        (0..self.end).get(slice)
+    }
+}
+
+// SAFETY: Safety requirement guaranteed by the forwarded impl.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFrom<usize> {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        (self.start..slice.len()).get(slice)
+    }
+}
+
+// SAFETY: `get` returned the pointer as is, so it always has the same provenance and offset of 0.
+unsafe impl<T> ProjectIndex<[T]> for core::ops::RangeFull {
+    type Output = [T];
+
+    #[inline(always)]
+    fn get(self, slice: *mut [T]) -> Option<*mut [T]> {
+        Some(slice)
+    }
+}
+
+/// A helper trait to perform field projection.
+///
+/// This trait has a `DEREF` generic parameter so it can be implemented twice for types that
+/// implement [`Deref`]. This will cause an ambiguity error and thus block [`Deref`] types being
+/// used as base of projection, as they can inject unsoundness. Users therefore must not specify
+/// `DEREF` and should always leave it to be inferred.
+///
+/// # Safety
+///
+/// `proj` may only invoke `f` with a valid allocation, as the documentation of [`Self::proj`]
+/// describes.
+#[doc(hidden)]
+pub unsafe trait ProjectField<const DEREF: bool> {
+    /// Project a pointer to a type to a pointer of a field.
+    ///
+    /// `f` may only be invoked with a valid allocation so it can safely obtain raw pointers to
+    /// fields using `&raw mut`.
+    ///
+    /// This is needed because `base` might not point to a valid allocation, while `&raw mut`
+    /// requires pointers to be in bounds of a valid allocation.
+    ///
+    /// # Safety
+    ///
+    /// `f` must return a pointer in bounds of the provided pointer.
+    unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F;
+}
+
+// NOTE: in theory, this API should work for `T: ?Sized` and `F: ?Sized`, too. However, we cannot
+// currently support that as we need to obtain a valid allocation that `&raw const` can operate on.
+//
+// SAFETY: `proj` invokes `f` with valid allocation.
+unsafe impl<T> ProjectField<false> for T {
+    #[inline(always)]
+    unsafe fn proj<F>(base: *mut Self, f: impl FnOnce(*mut Self) -> *mut F) -> *mut F {
+        // Create a valid allocation to start projection, as `base` is not necessarily so. The
+        // memory is never actually used so it will be optimized out, so it should work even for
+        // very large `T` (`memoffset` crate also relies on this). To be extra certain, we also
+        // annotate `f` closure with `#[inline(always)]` in the macro.
+        let mut place = MaybeUninit::uninit();
+        let place_base = place.as_mut_ptr();
+        let field = f(place_base);
+        // SAFETY: `field` is in bounds from `base` per safety requirement.
+        let offset = unsafe { field.byte_offset_from(place_base) };
+        // Use `wrapping_byte_offset` as `base` does not need to be of valid allocation.
+        base.wrapping_byte_offset(offset).cast()
+    }
+}
+
+// SAFETY: Vacuously satisfied.
+unsafe impl<T: Deref> ProjectField<true> for T {
+    #[inline(always)]
+    unsafe fn proj<F>(_: *mut Self, _: impl FnOnce(*mut Self) -> *mut F) -> *mut F {
+        build_error!("this function is a guard against `Deref` impl and is never invoked");
+    }
+}
+
+/// Create a projection from a raw pointer.
+///
+/// The projected pointer is within the memory region marked by the input pointer. There is no
+/// requirement that the input raw pointer needs to be valid, so this macro may be used for
+/// projecting pointers outside normal address space, e.g. I/O pointers. However, if the input
+/// pointer is valid, the projected pointer is also valid.
+///
+/// Supported projections include field projections and index projections.
+/// It is not allowed to project into types that implement custom [`Deref`] or
+/// [`Index`](core::ops::Index).
+///
+/// The macro has basic syntax of `kernel::ptr::project!(ptr, projection)`, where `ptr` is an
+/// expression that evaluates to a raw pointer which serves as the base of projection. `projection`
+/// can be a projection expression of form `.field` (normally identifier, or numeral in case of
+/// tuple structs) or of form `[index]`.
+///
+/// If a mutable pointer is needed, the macro input can be prefixed with the `mut` keyword, i.e.
+/// `kernel::ptr::project!(mut ptr, projection)`. By default, a const pointer is created.
+///
+/// `ptr::project!` macro can perform both fallible indexing and build-time checked indexing.
+/// `[index]` form performs build-time bounds checking; if compiler fails to prove `[index]` is in
+/// bounds, compilation will fail. `[index]?` can be used to perform runtime bounds checking;
+/// `OutOfBound` error is raised via `?` if the index is out of bounds.
+///
+/// # Examples
+///
+/// Field projections are performed with `.field_name`:
+///
+/// ```
+/// struct MyStruct { field: u32, }
+/// let ptr: *const MyStruct = core::ptr::dangling();
+/// let field_ptr: *const u32 = kernel::ptr::project!(ptr, .field);
+///
+/// struct MyTupleStruct(u32, u32);
+///
+/// fn proj(ptr: *const MyTupleStruct) {
+///     let field_ptr: *const u32 = kernel::ptr::project!(ptr, .1);
+/// }
+/// ```
+///
+/// Index projections are performed with `[index]`:
+///
+/// ```
+/// fn proj(ptr: *const [u8; 32]) -> Result {
+///     let field_ptr: *const u8 = kernel::ptr::project!(ptr, [1]);
+///     // The following invocation, if uncommented, would fail the build.
+///     //
+///     // kernel::ptr::project!(ptr, [128]);
+///
+///     // This will raise an `OutOfBound` error (which is convertible to `ERANGE`).
+///     kernel::ptr::project!(ptr, [128]?);
+///     Ok(())
+/// }
+/// ```
+///
+/// If you need to match on the error instead of propagate, put the invocation inside a closure:
+///
+/// ```
+/// let ptr: *const [u8; 32] = core::ptr::dangling();
+/// let field_ptr: Result<*const u8> = (|| -> Result<_> {
+///     Ok(kernel::ptr::project!(ptr, [128]?))
+/// })();
+/// assert!(field_ptr.is_err());
+/// ```
+///
+/// For mutable pointers, put `mut` as the first token in macro invocation.
+///
+/// ```
+/// let ptr: *mut [(u8, u16); 32] = core::ptr::dangling_mut();
+/// let field_ptr: *mut u16 = kernel::ptr::project!(mut ptr, [1].1);
+/// ```
+#[macro_export]
+macro_rules! project_pointer {
+    (@gen $ptr:ident, ) => {};
+    // Field projection. `$field` needs to be `tt` to support tuple index like `.0`.
+    (@gen $ptr:ident, .$field:tt $($rest:tt)*) => {
+        // SAFETY: The provided closure always returns an in-bounds pointer.
+        let $ptr = unsafe {
+            $crate::ptr::projection::ProjectField::proj($ptr, #[inline(always)] |ptr| {
+                // Check unaligned field. Not all users (e.g. DMA) can handle unaligned
+                // projections.
+                if false {
+                    let _ = &(*ptr).$field;
+                }
+                // SAFETY: `$field` is in bounds, and no implicit `Deref` is possible (if the
+                // type implements `Deref`, Rust cannot infer the generic parameter `DEREF`).
+                &raw mut (*ptr).$field
+            })
+        };
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    // Fallible index projection.
+    (@gen $ptr:ident, [$index:expr]? $($rest:tt)*) => {
+        let $ptr = $crate::ptr::projection::ProjectIndex::get($index, $ptr)
+            .ok_or($crate::ptr::projection::OutOfBound)?;
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    // Build-time checked index projection.
+    (@gen $ptr:ident, [$index:expr] $($rest:tt)*) => {
+        let $ptr = $crate::ptr::projection::ProjectIndex::index($index, $ptr);
+        $crate::ptr::project!(@gen $ptr, $($rest)*)
+    };
+    (mut $ptr:expr, $($proj:tt)*) => {{
+        let ptr: *mut _ = $ptr;
+        $crate::ptr::project!(@gen ptr, $($proj)*);
+        ptr
+    }};
+    ($ptr:expr, $($proj:tt)*) => {{
+        let ptr = <*const _>::cast_mut($ptr);
+        // We currently always project using mutable pointer, as it is not decided whether `&raw
+        // const` allows the resulting pointer to be mutated (see documentation of `addr_of!`).
+        $crate::ptr::project!(@gen ptr, $($proj)*);
+        ptr.cast_const()
+    }};
+}
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 32e209bc7985..3652b85be545 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -310,16 +310,18 @@ $(obj)/%.lst: $(obj)/%.c FORCE
 
 # The features in this list are the ones allowed for non-`rust/` code.
 #
+#   - Stable since Rust 1.79.0: `feature(slice_ptr_len)`.
 #   - Stable since Rust 1.81.0: `feature(lint_reasons)`.
 #   - Stable since Rust 1.82.0: `feature(asm_const)`,
 #     `feature(offset_of_nested)`, `feature(raw_ref_op)`.
+#   - Stable since Rust 1.84.0: `feature(strict_provenance)`.
 #   - Stable since Rust 1.87.0: `feature(asm_goto)`.
 #   - Expected to become stable: `feature(arbitrary_self_types)`.
 #   - To be determined: `feature(used_with_arg)`.
 #
 # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on
 # the unstable features in use.
-rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg
+rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,slice_ptr_len,strict_provenance,used_with_arg
 
 # `--out-dir` is required to avoid temporaries being created by `rustc` in the
 # current working directory, which may be not accessible in the out-of-tree
-- 
cgit v1.2.3


From 4da879a0d3fd170a70994b73baa554c6913918b5 Mon Sep 17 00:00:00 2001
From: Gary Guo <gary@garyguo.net>
Date: Mon, 2 Mar 2026 16:42:36 +0000
Subject: rust: dma: use pointer projection infra for `dma_{read,write}` macro

Current `dma_read!`, `dma_write!` macros also use a custom
`addr_of!()`-based implementation for projecting pointers, which has
soundness issue as it relies on absence of `Deref` implementation on types.
It also has a soundness issue where it does not protect against unaligned
fields (when `#[repr(packed)]` is used) so it can generate misaligned
accesses.

This commit migrates them to use the general pointer projection
infrastructure, which handles these cases correctly.

As part of migration, the macro is updated to have an improved surface
syntax. The current macro have

    dma_read!(a.b.c[d].e.f)

to mean `a.b.c` is a DMA coherent allocation and it should project into it
with `[d].e.f` and do a read, which is confusing as it makes the indexing
operator integral to the macro (so it will break if you have an array of
`CoherentAllocation`, for example).

This also is problematic as we would like to generalize
`CoherentAllocation` from just slices to arbitrary types.

Make the macro expects `dma_read!(path.to.dma, .path.inside.dma)` as the
canonical syntax. The index operator is no longer special and is just one
type of projection (in additional to field projection). Similarly, make
`dma_write!(path.to.dma, .path.inside.dma, value)` become the canonical
syntax for writing.

Another issue of the current macro is that it is always fallible. This
makes sense with existing design of `CoherentAllocation`, but once we
support fixed size arrays with `CoherentAllocation`, it is desirable to
have the ability to perform infallible indexing as well, e.g. doing a `[0]`
index of `[Foo; 2]` is okay and can be checked at build-time, so forcing
falliblity is non-ideal. To capture this, the macro is changed to use
`[idx]` as infallible projection and `[idx]?` as fallible index projection
(those syntax are part of the general projection infra). A benefit of this
is that while individual indexing operation may fail, the overall
read/write operation is not fallible.

Fixes: ad2907b4e308 ("rust: add dma coherent allocator abstraction")
Reviewed-by: Benno Lossin <lossin@kernel.org>
Signed-off-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260302164239.284084-4-gary@kernel.org
[ Capitalize safety comments; slightly improve wording in doc-comments.
  - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp.rs      |  14 ++---
 drivers/gpu/nova-core/gsp/boot.rs |   2 +-
 drivers/gpu/nova-core/gsp/cmdq.rs |  10 +++-
 rust/kernel/dma.rs                | 114 +++++++++++++++++---------------------
 samples/rust/rust_dma.rs          |  30 +++++-----
 5 files changed, 81 insertions(+), 89 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 174feaca0a6b..25cd48514c77 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -143,14 +143,14 @@ impl Gsp {
                     // _kgspInitLibosLoggingStructures (allocates memory for buffers)
                     // kgspSetupLibosInitArgs_IMPL (creates pLibosInitArgs[] array)
                     dma_write!(
-                        libos[0] = LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0)
-                    )?;
+                        libos, [0]?, LibosMemoryRegionInitArgument::new("LOGINIT", &loginit.0)
+                    );
                     dma_write!(
-                        libos[1] = LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0)
-                    )?;
-                    dma_write!(libos[2] = LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0))?;
-                    dma_write!(rmargs[0].inner = fw::GspArgumentsCached::new(cmdq))?;
-                    dma_write!(libos[3] = LibosMemoryRegionInitArgument::new("RMARGS", rmargs))?;
+                        libos, [1]?, LibosMemoryRegionInitArgument::new("LOGINTR", &logintr.0)
+                    );
+                    dma_write!(libos, [2]?, LibosMemoryRegionInitArgument::new("LOGRM", &logrm.0));
+                    dma_write!(rmargs, [0]?.inner, fw::GspArgumentsCached::new(cmdq));
+                    dma_write!(libos, [3]?, LibosMemoryRegionInitArgument::new("RMARGS", rmargs));
                 },
             }))
         })
diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs
index be427fe26a58..94833f7996e8 100644
--- a/drivers/gpu/nova-core/gsp/boot.rs
+++ b/drivers/gpu/nova-core/gsp/boot.rs
@@ -157,7 +157,7 @@ impl super::Gsp {
 
         let wpr_meta =
             CoherentAllocation::<GspFwWprMeta>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(wpr_meta[0] = GspFwWprMeta::new(&gsp_fw, &fb_layout))?;
+        dma_write!(wpr_meta, [0]?, GspFwWprMeta::new(&gsp_fw, &fb_layout));
 
         self.cmdq
             .send_command(bar, commands::SetSystemInfo::new(pdev))?;
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 46819a82a51a..ae54708c38eb 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -201,9 +201,13 @@ impl DmaGspMem {
 
         let gsp_mem =
             CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(gsp_mem[0].ptes = PteArray::new(gsp_mem.dma_handle())?)?;
-        dma_write!(gsp_mem[0].cpuq.tx = MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES))?;
-        dma_write!(gsp_mem[0].cpuq.rx = MsgqRxHeader::new())?;
+        dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?);
+        dma_write!(
+            gsp_mem,
+            [0]?.cpuq.tx,
+            MsgqTxHeader::new(MSGQ_SIZE, RX_HDR_OFF, MSGQ_NUM_PAGES)
+        );
+        dma_write!(gsp_mem, [0]?.cpuq.rx, MsgqRxHeader::new());
 
         Ok(Self(gsp_mem))
     }
diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs
index 909d56fd5118..a396f8435739 100644
--- a/rust/kernel/dma.rs
+++ b/rust/kernel/dma.rs
@@ -461,6 +461,19 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> {
         self.count * core::mem::size_of::<T>()
     }
 
+    /// Returns the raw pointer to the allocated region in the CPU's virtual address space.
+    #[inline]
+    pub fn as_ptr(&self) -> *const [T] {
+        core::ptr::slice_from_raw_parts(self.cpu_addr.as_ptr(), self.count)
+    }
+
+    /// Returns the raw pointer to the allocated region in the CPU's virtual address space as
+    /// a mutable pointer.
+    #[inline]
+    pub fn as_mut_ptr(&self) -> *mut [T] {
+        core::ptr::slice_from_raw_parts_mut(self.cpu_addr.as_ptr(), self.count)
+    }
+
     /// Returns the base address to the allocated region in the CPU's virtual address space.
     pub fn start_ptr(&self) -> *const T {
         self.cpu_addr.as_ptr()
@@ -581,23 +594,6 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> {
         Ok(())
     }
 
-    /// Returns a pointer to an element from the region with bounds checking. `offset` is in
-    /// units of `T`, not the number of bytes.
-    ///
-    /// Public but hidden since it should only be used from [`dma_read`] and [`dma_write`] macros.
-    #[doc(hidden)]
-    pub fn item_from_index(&self, offset: usize) -> Result<*mut T> {
-        if offset >= self.count {
-            return Err(EINVAL);
-        }
-        // SAFETY:
-        // - The pointer is valid due to type invariant on `CoherentAllocation`
-        // and we've just checked that the range and index is within bounds.
-        // - `offset` can't overflow since it is smaller than `self.count` and we've checked
-        // that `self.count` won't overflow early in the constructor.
-        Ok(unsafe { self.cpu_addr.as_ptr().add(offset) })
-    }
-
     /// Reads the value of `field` and ensures that its type is [`FromBytes`].
     ///
     /// # Safety
@@ -670,6 +666,9 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {}
 
 /// Reads a field of an item from an allocated region of structs.
 ///
+/// The syntax is of the form `kernel::dma_read!(dma, proj)` where `dma` is an expression evaluating
+/// to a [`CoherentAllocation`] and `proj` is a [projection specification](kernel::ptr::project!).
+///
 /// # Examples
 ///
 /// ```
@@ -684,36 +683,29 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {}
 /// unsafe impl kernel::transmute::AsBytes for MyStruct{};
 ///
 /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result {
-/// let whole = kernel::dma_read!(alloc[2]);
-/// let field = kernel::dma_read!(alloc[1].field);
+/// let whole = kernel::dma_read!(alloc, [2]?);
+/// let field = kernel::dma_read!(alloc, [1]?.field);
 /// # Ok::<(), Error>(()) }
 /// ```
 #[macro_export]
 macro_rules! dma_read {
-    ($dma:expr, $idx: expr, $($field:tt)*) => {{
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be
-            // dereferenced. The compiler also further validates the expression on whether `field`
-            // is a member of `item` when expanded by the macro.
-            unsafe {
-                let ptr_field = ::core::ptr::addr_of!((*item) $($field)*);
-                ::core::result::Result::Ok(
-                    $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field)
-                )
-            }
-        })()
+    ($dma:expr, $($proj:tt)*) => {{
+        let dma = &$dma;
+        let ptr = $crate::ptr::project!(
+            $crate::dma::CoherentAllocation::as_ptr(dma), $($proj)*
+        );
+        // SAFETY: The pointer created by the projection is within the DMA region.
+        unsafe { $crate::dma::CoherentAllocation::field_read(dma, ptr) }
     }};
-    ($dma:ident [ $idx:expr ] $($field:tt)* ) => {
-        $crate::dma_read!($dma, $idx, $($field)*)
-    };
-    ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {
-        $crate::dma_read!($($dma).*, $idx, $($field)*)
-    };
 }
 
 /// Writes to a field of an item from an allocated region of structs.
 ///
+/// The syntax is of the form `kernel::dma_write!(dma, proj, val)` where `dma` is an expression
+/// evaluating to a [`CoherentAllocation`], `proj` is a
+/// [projection specification](kernel::ptr::project!), and `val` is the value to be written to the
+/// projected location.
+///
 /// # Examples
 ///
 /// ```
@@ -728,37 +720,31 @@ macro_rules! dma_read {
 /// unsafe impl kernel::transmute::AsBytes for MyStruct{};
 ///
 /// # fn test(alloc: &kernel::dma::CoherentAllocation<MyStruct>) -> Result {
-/// kernel::dma_write!(alloc[2].member = 0xf);
-/// kernel::dma_write!(alloc[1] = MyStruct { member: 0xf });
+/// kernel::dma_write!(alloc, [2]?.member, 0xf);
+/// kernel::dma_write!(alloc, [1]?, MyStruct { member: 0xf });
 /// # Ok::<(), Error>(()) }
 /// ```
 #[macro_export]
 macro_rules! dma_write {
-    ($dma:ident [ $idx:expr ] $($field:tt)*) => {{
-        $crate::dma_write!($dma, $idx, $($field)*)
-    }};
-    ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {{
-        $crate::dma_write!($($dma).*, $idx, $($field)*)
+    (@parse [$dma:expr] [$($proj:tt)*] [, $val:expr]) => {{
+        let dma = &$dma;
+        let ptr = $crate::ptr::project!(
+            mut $crate::dma::CoherentAllocation::as_mut_ptr(dma), $($proj)*
+        );
+        let val = $val;
+        // SAFETY: The pointer created by the projection is within the DMA region.
+        unsafe { $crate::dma::CoherentAllocation::field_write(dma, ptr, val) }
     }};
-    ($dma:expr, $idx: expr, = $val:expr) => {
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid item.
-            unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) }
-            ::core::result::Result::Ok(())
-        })()
+    (@parse [$dma:expr] [$($proj:tt)*] [.$field:tt $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* .$field] [$($rest)*])
+    };
+    (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr]? $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* [$index]?] [$($rest)*])
+    };
+    (@parse [$dma:expr] [$($proj:tt)*] [[$index:expr] $($rest:tt)*]) => {
+        $crate::dma_write!(@parse [$dma] [$($proj)* [$index]] [$($rest)*])
     };
-    ($dma:expr, $idx: expr, $(.$field:ident)* = $val:expr) => {
-        (|| -> ::core::result::Result<_, $crate::error::Error> {
-            let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?;
-            // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be
-            // dereferenced. The compiler also further validates the expression on whether `field`
-            // is a member of `item` when expanded by the macro.
-            unsafe {
-                let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*);
-                $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val)
-            }
-            ::core::result::Result::Ok(())
-        })()
+    ($dma:expr, $($rest:tt)*) => {
+        $crate::dma_write!(@parse [$dma] [] [$($rest)*])
     };
 }
diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs
index 9c45851c876e..ce39b5545097 100644
--- a/samples/rust/rust_dma.rs
+++ b/samples/rust/rust_dma.rs
@@ -68,7 +68,7 @@ impl pci::Driver for DmaSampleDriver {
                 CoherentAllocation::alloc_coherent(pdev.as_ref(), TEST_VALUES.len(), GFP_KERNEL)?;
 
             for (i, value) in TEST_VALUES.into_iter().enumerate() {
-                kernel::dma_write!(ca[i] = MyStruct::new(value.0, value.1))?;
+                kernel::dma_write!(ca, [i]?, MyStruct::new(value.0, value.1));
             }
 
             let size = 4 * page::PAGE_SIZE;
@@ -85,24 +85,26 @@ impl pci::Driver for DmaSampleDriver {
     }
 }
 
+impl DmaSampleDriver {
+    fn check_dma(&self) -> Result {
+        for (i, value) in TEST_VALUES.into_iter().enumerate() {
+            let val0 = kernel::dma_read!(self.ca, [i]?.h);
+            let val1 = kernel::dma_read!(self.ca, [i]?.b);
+
+            assert_eq!(val0, value.0);
+            assert_eq!(val1, value.1);
+        }
+
+        Ok(())
+    }
+}
+
 #[pinned_drop]
 impl PinnedDrop for DmaSampleDriver {
     fn drop(self: Pin<&mut Self>) {
         dev_info!(self.pdev, "Unload DMA test driver.\n");
 
-        for (i, value) in TEST_VALUES.into_iter().enumerate() {
-            let val0 = kernel::dma_read!(self.ca[i].h);
-            let val1 = kernel::dma_read!(self.ca[i].b);
-            assert!(val0.is_ok());
-            assert!(val1.is_ok());
-
-            if let Ok(val0) = val0 {
-                assert_eq!(val0, value.0);
-            }
-            if let Ok(val1) = val1 {
-                assert_eq!(val1, value.1);
-            }
-        }
+        assert!(self.check_dma().is_ok());
 
         for (i, entry) in self.sgt.iter().enumerate() {
             dev_info!(
-- 
cgit v1.2.3


From 1954c4f012206147c34acda8da04f827aa7d3ee3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2026 20:07:15 +0000
Subject: eventpoll: Convert epoll_put_uevent() to scoped user access

Saves two function calls, and one stac/clac pair.

stac/clac is rather expensive on older cpus like Zen 2.

A synthetic network stress test gives a ~1.5% increase of pps
on AMD Zen 2.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/eventpoll.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index ccb478eb174b..ea9ca0e4172a 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -82,11 +82,14 @@ static inline struct epoll_event __user *
 epoll_put_uevent(__poll_t revents, __u64 data,
 		 struct epoll_event __user *uevent)
 {
-	if (__put_user(revents, &uevent->events) ||
-	    __put_user(data, &uevent->data))
-		return NULL;
-
+	scoped_user_write_access_size(uevent, sizeof(*uevent), efault) {
+		unsafe_put_user(revents, &uevent->events, efault);
+		unsafe_put_user(data, &uevent->data, efault);
+	}
 	return uevent+1;
+
+efault:
+	return NULL;
 }
 #endif
 
-- 
cgit v1.2.3


From 4e701b47c3ba8f4eaf51d676732b11204bc75b35 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 20 Feb 2026 10:55:15 +0100
Subject: firmware: arm_scmi: Spelling s/mulit/multi/, s/currenly/currently/

Fix misspellings of "multi" and "currently".

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Message-Id: <6735401861e0c2f3e5e680533cd6f71c4d6fd5eb.1771581270.git.geert+renesas@glider.be>
Signed-off-by: Sudeep Holla <sudeep.holla@kernel.org>
---
 drivers/firmware/arm_scmi/protocols.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/protocols.h b/drivers/firmware/arm_scmi/protocols.h
index 4c75970326e6..f51245aca259 100644
--- a/drivers/firmware/arm_scmi/protocols.h
+++ b/drivers/firmware/arm_scmi/protocols.h
@@ -189,13 +189,13 @@ struct scmi_protocol_handle {
 
 /**
  * struct scmi_iterator_state  - Iterator current state descriptor
- * @desc_index: Starting index for the current mulit-part request.
+ * @desc_index: Starting index for the current multi-part request.
  * @num_returned: Number of returned items in the last multi-part reply.
  * @num_remaining: Number of remaining items in the multi-part message.
  * @max_resources: Maximum acceptable number of items, configured by the caller
  *		   depending on the underlying resources that it is querying.
  * @loop_idx: The iterator loop index in the current multi-part reply.
- * @rx_len: Size in bytes of the currenly processed message; it can be used by
+ * @rx_len: Size in bytes of the currently processed message; it can be used by
  *	    the user of the iterator to verify a reply size.
  * @priv: Optional pointer to some additional state-related private data setup
  *	  by the caller during the iterations.
-- 
cgit v1.2.3


From ef3b06742c8a201d0e83edc9a33a89a4fe3009f8 Mon Sep 17 00:00:00 2001
From: Yonatan Nachum <ynachum@amazon.com>
Date: Sun, 8 Mar 2026 16:53:50 +0000
Subject: RDMA/efa: Fix use of completion ctx after free

On admin queue completion handling, if the admin command completed with
error we print data from the completion context. The issue is that we
already freed the completion context in polling/interrupts handler which
means we print data from context in an unknown state (it might be
already used again).
Change the admin submission flow so alloc/dealloc of the context will be
symmetric and dealloc will be called after any potential use of the
context.

Fixes: 68fb9f3e312a ("RDMA/efa: Remove redundant NULL pointer check of CQE")
Reviewed-by: Daniel Kranzdorf <dkkranzd@amazon.com>
Reviewed-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Link: https://patch.msgid.link/20260308165350.18219-1-ynachum@amazon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/efa/efa_com.c | 87 +++++++++++++++++--------------------
 1 file changed, 39 insertions(+), 48 deletions(-)

diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c
index 229b0ad3b0cb..56caba612139 100644
--- a/drivers/infiniband/hw/efa/efa_com.c
+++ b/drivers/infiniband/hw/efa/efa_com.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /*
- * Copyright 2018-2025 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2026 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include <linux/log2.h>
@@ -310,23 +310,19 @@ static inline struct efa_comp_ctx *efa_com_get_comp_ctx_by_cmd_id(struct efa_com
 	return &aq->comp_ctx[ctx_id];
 }
 
-static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
-						       struct efa_admin_aq_entry *cmd,
-						       size_t cmd_size_in_bytes,
-						       struct efa_admin_acq_entry *comp,
-						       size_t comp_size_in_bytes)
+static void __efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
+				       struct efa_comp_ctx *comp_ctx,
+				       struct efa_admin_aq_entry *cmd,
+				       size_t cmd_size_in_bytes,
+				       struct efa_admin_acq_entry *comp,
+				       size_t comp_size_in_bytes)
 {
 	struct efa_admin_aq_entry *aqe;
-	struct efa_comp_ctx *comp_ctx;
 	u16 queue_size_mask;
 	u16 cmd_id;
 	u16 ctx_id;
 	u16 pi;
 
-	comp_ctx = efa_com_alloc_comp_ctx(aq);
-	if (!comp_ctx)
-		return ERR_PTR(-EINVAL);
-
 	queue_size_mask = aq->depth - 1;
 	pi = aq->sq.pc & queue_size_mask;
 	ctx_id = efa_com_get_comp_ctx_id(aq, comp_ctx);
@@ -360,8 +356,6 @@ static struct efa_comp_ctx *__efa_com_submit_admin_cmd(struct efa_com_admin_queu
 
 	/* barrier not needed in case of writel */
 	writel(aq->sq.pc, aq->sq.db_addr);
-
-	return comp_ctx;
 }
 
 static inline int efa_com_init_comp_ctxt(struct efa_com_admin_queue *aq)
@@ -394,28 +388,25 @@ static inline int efa_com_init_comp_ctxt(struct efa_com_admin_queue *aq)
 	return 0;
 }
 
-static struct efa_comp_ctx *efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
-						     struct efa_admin_aq_entry *cmd,
-						     size_t cmd_size_in_bytes,
-						     struct efa_admin_acq_entry *comp,
-						     size_t comp_size_in_bytes)
+static int efa_com_submit_admin_cmd(struct efa_com_admin_queue *aq,
+				    struct efa_comp_ctx *comp_ctx,
+				    struct efa_admin_aq_entry *cmd,
+				    size_t cmd_size_in_bytes,
+				    struct efa_admin_acq_entry *comp,
+				    size_t comp_size_in_bytes)
 {
-	struct efa_comp_ctx *comp_ctx;
-
 	spin_lock(&aq->sq.lock);
 	if (!test_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state)) {
 		ibdev_err_ratelimited(aq->efa_dev, "Admin queue is closed\n");
 		spin_unlock(&aq->sq.lock);
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
-	comp_ctx = __efa_com_submit_admin_cmd(aq, cmd, cmd_size_in_bytes, comp,
-					      comp_size_in_bytes);
+	__efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size_in_bytes, comp,
+				   comp_size_in_bytes);
 	spin_unlock(&aq->sq.lock);
-	if (IS_ERR(comp_ctx))
-		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
 
-	return comp_ctx;
+	return 0;
 }
 
 static int efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
@@ -512,7 +503,6 @@ static int efa_com_wait_and_process_admin_cq_polling(struct efa_comp_ctx *comp_c
 {
 	unsigned long timeout;
 	unsigned long flags;
-	int err;
 
 	timeout = jiffies + usecs_to_jiffies(aq->completion_timeout);
 
@@ -532,24 +522,20 @@ static int efa_com_wait_and_process_admin_cq_polling(struct efa_comp_ctx *comp_c
 			atomic64_inc(&aq->stats.no_completion);
 
 			clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
-			err = -ETIME;
-			goto out;
+			return -ETIME;
 		}
 
 		msleep(aq->poll_interval);
 	}
 
-	err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status);
-out:
-	efa_com_dealloc_comp_ctx(aq, comp_ctx);
-	return err;
+	return efa_com_comp_status_to_errno(
+		comp_ctx->user_cqe->acq_common_descriptor.status);
 }
 
 static int efa_com_wait_and_process_admin_cq_interrupts(struct efa_comp_ctx *comp_ctx,
 							struct efa_com_admin_queue *aq)
 {
 	unsigned long flags;
-	int err;
 
 	wait_for_completion_timeout(&comp_ctx->wait_event,
 				    usecs_to_jiffies(aq->completion_timeout));
@@ -585,14 +571,11 @@ static int efa_com_wait_and_process_admin_cq_interrupts(struct efa_comp_ctx *com
 				aq->cq.cc);
 
 		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
-		err = -ETIME;
-		goto out;
+		return -ETIME;
 	}
 
-	err = efa_com_comp_status_to_errno(comp_ctx->user_cqe->acq_common_descriptor.status);
-out:
-	efa_com_dealloc_comp_ctx(aq, comp_ctx);
-	return err;
+	return efa_com_comp_status_to_errno(
+		comp_ctx->user_cqe->acq_common_descriptor.status);
 }
 
 /*
@@ -642,30 +625,38 @@ int efa_com_cmd_exec(struct efa_com_admin_queue *aq,
 	ibdev_dbg(aq->efa_dev, "%s (opcode %d)\n",
 		  efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
 		  cmd->aq_common_descriptor.opcode);
-	comp_ctx = efa_com_submit_admin_cmd(aq, cmd, cmd_size, comp, comp_size);
-	if (IS_ERR(comp_ctx)) {
+
+	comp_ctx = efa_com_alloc_comp_ctx(aq);
+	if (!comp_ctx) {
+		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
+		return -EINVAL;
+	}
+
+	err = efa_com_submit_admin_cmd(aq, comp_ctx, cmd, cmd_size, comp, comp_size);
+	if (err) {
 		ibdev_err_ratelimited(
 			aq->efa_dev,
-			"Failed to submit command %s (opcode %u) err %pe\n",
+			"Failed to submit command %s (opcode %u) err %d\n",
 			efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
-			cmd->aq_common_descriptor.opcode, comp_ctx);
+			cmd->aq_common_descriptor.opcode, err);
 
+		efa_com_dealloc_comp_ctx(aq, comp_ctx);
 		up(&aq->avail_cmds);
 		atomic64_inc(&aq->stats.cmd_err);
-		return PTR_ERR(comp_ctx);
+		return err;
 	}
 
 	err = efa_com_wait_and_process_admin_cq(comp_ctx, aq);
 	if (err) {
 		ibdev_err_ratelimited(
 			aq->efa_dev,
-			"Failed to process command %s (opcode %u) comp_status %d err %d\n",
+			"Failed to process command %s (opcode %u) err %d\n",
 			efa_com_cmd_str(cmd->aq_common_descriptor.opcode),
-			cmd->aq_common_descriptor.opcode,
-			comp_ctx->user_cqe->acq_common_descriptor.status, err);
+			cmd->aq_common_descriptor.opcode, err);
 		atomic64_inc(&aq->stats.cmd_err);
 	}
 
+	efa_com_dealloc_comp_ctx(aq, comp_ctx);
 	up(&aq->avail_cmds);
 
 	return err;
-- 
cgit v1.2.3


From 1f318b96cc84d7c2ab792fcc0bfd42a7ca890681 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 8 Mar 2026 16:56:54 -0700
Subject: Linux 7.0-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 4b54a5c74332..2b15f0b4a0cb 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From d6db827b430bdcca3976cebca7bd69cca03cde2c Mon Sep 17 00:00:00 2001
From: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Date: Fri, 27 Feb 2026 20:15:34 +0530
Subject: ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and
 start

During ADSP stop and start, the kernel crashes due to the order in which
ASoC components are removed.

On ADSP stop, the q6apm-audio .remove callback unloads topology and removes
PCM runtimes during ASoC teardown. This deletes the RTDs that contain the
q6apm DAI components before their removal pass runs, leaving those
components still linked to the card and causing crashes on the next rebind.

Fix this by ensuring that all dependent (child) components are removed
first, and the q6apm component is removed last.

[   48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0
[   48.114763] Mem abort info:
[   48.117650]   ESR = 0x0000000096000004
[   48.121526]   EC = 0x25: DABT (current EL), IL = 32 bits
[   48.127010]   SET = 0, FnV = 0
[   48.130172]   EA = 0, S1PTW = 0
[   48.133415]   FSC = 0x04: level 0 translation fault
[   48.138446] Data abort info:
[   48.141422]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[   48.147079]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[   48.152354]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000
[   48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000
[   48.171530] Internal error: Oops: 0000000096000004 [#1]  SMP
[   48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core
[   48.177444]  coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6
[   48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT
[   48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT)
[   48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface]
[   48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   48.330825] pc : mutex_lock+0xc/0x54
[   48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core]
[   48.340794] sp : ffff800084ddb7b0
[   48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00
[   48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098
[   48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0
[   48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff
[   48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f
[   48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673
[   48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001
[   48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000
[   48.402854] x5 : 0000000000000000 x4 : 0000000000000028 x3 : ffff000ef397a698
[   48.410180] x2 : ffff00009a2aadc0 x1 : 0000000000000000 x0 : 00000000000000d0
[   48.417506] Call trace:
[   48.420025]  mutex_lock+0xc/0x54 (P)
[   48.423712]  snd_soc_dapm_shutdown+0x44/0xbc [snd_soc_core]
[   48.429447]  soc_cleanup_card_resources+0x30/0x2c0 [snd_soc_core]
[   48.435719]  snd_soc_bind_card+0x4dc/0xcc0 [snd_soc_core]
[   48.441278]  snd_soc_add_component+0x27c/0x2c8 [snd_soc_core]
[   48.447192]  snd_soc_register_component+0x9c/0xf4 [snd_soc_core]
[   48.453371]  devm_snd_soc_register_component+0x64/0xc4 [snd_soc_core]
[   48.459994]  apm_probe+0xb4/0x110 [snd_q6apm]
[   48.464479]  apr_device_probe+0x24/0x40 [apr]
[   48.468964]  really_probe+0xbc/0x298
[   48.472651]  __driver_probe_device+0x78/0x12c
[   48.477132]  driver_probe_device+0x40/0x160
[   48.481435]  __device_attach_driver+0xb8/0x134
[   48.486011]  bus_for_each_drv+0x80/0xdc
[   48.489964]  __device_attach+0xa8/0x1b0
[   48.493916]  device_initial_probe+0x50/0x54
[   48.498219]  bus_probe_device+0x38/0xa0
[   48.502170]  device_add+0x590/0x760
[   48.505761]  device_register+0x20/0x30
[   48.509623]  of_register_apr_devices+0x1d8/0x318 [apr]
[   48.514905]  apr_pd_status+0x2c/0x54 [apr]
[   48.519114]  pdr_notifier_work+0x8c/0xe0 [pdr_interface]
[   48.524570]  process_one_work+0x150/0x294
[   48.528692]  worker_thread+0x2d8/0x3d8
[   48.532551]  kthread+0x130/0x204
[   48.535874]  ret_from_fork+0x10/0x20
[   48.539559] Code: d65f03c0 d5384102 d503201f d2800001 (c8e17c02)
[   48.545823] ---[ end trace 0000000000000000 ]---

Fixes: 5477518b8a0e ("ASoC: qdsp6: audioreach: add q6apm support")
Cc: stable@vger.kernel.org
Signed-off-by: Ravi Hothi <ravi.hothi@oss.qualcomm.com>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Link: https://patch.msgid.link/20260227144534.278568-1-ravi.hothi@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6apm-dai.c        | 1 +
 sound/soc/qcom/qdsp6/q6apm-lpass-dais.c | 1 +
 sound/soc/qcom/qdsp6/q6apm.c            | 1 +
 3 files changed, 3 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c
index de3bdac3e791..168c166c960d 100644
--- a/sound/soc/qcom/qdsp6/q6apm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6apm-dai.c
@@ -838,6 +838,7 @@ static const struct snd_soc_component_driver q6apm_fe_dai_component = {
 	.ack		= q6apm_dai_ack,
 	.compress_ops	= &q6apm_dai_compress_ops,
 	.use_dai_pcm_id = true,
+	.remove_order   = SND_SOC_COMP_ORDER_EARLY,
 };
 
 static int q6apm_dai_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
index 528756f1332b..5be37eeea329 100644
--- a/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
+++ b/sound/soc/qcom/qdsp6/q6apm-lpass-dais.c
@@ -278,6 +278,7 @@ static const struct snd_soc_component_driver q6apm_lpass_dai_component = {
 	.of_xlate_dai_name = q6dsp_audio_ports_of_xlate_dai_name,
 	.be_pcm_base = AUDIOREACH_BE_PCM_BASE,
 	.use_dai_pcm_id = true,
+	.remove_order   = SND_SOC_COMP_ORDER_FIRST,
 };
 
 static int q6apm_lpass_dai_dev_probe(struct platform_device *pdev)
diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c
index 44841fde3856..970b08c89bb3 100644
--- a/sound/soc/qcom/qdsp6/q6apm.c
+++ b/sound/soc/qcom/qdsp6/q6apm.c
@@ -715,6 +715,7 @@ static const struct snd_soc_component_driver q6apm_audio_component = {
 	.name		= APM_AUDIO_DRV_NAME,
 	.probe		= q6apm_audio_probe,
 	.remove		= q6apm_audio_remove,
+	.remove_order   = SND_SOC_COMP_ORDER_LAST,
 };
 
 static int apm_probe(gpr_device_t *gdev)
-- 
cgit v1.2.3


From facfdef64d11c08e6f1e69d02a0b87cb74cee0f5 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 4 Mar 2026 14:12:50 +0000
Subject: firmware: cs_dsp: Fix fragmentation regression in firmware download

Use vmalloc() instead of kmalloc(..., GFP_DMA) to alloc the temporary
buffer for firmware download blobs. This avoids the problem that a
heavily fragmented system cannot allocate enough physically-contiguous
memory for a large blob.

The redundant alloc buffer mechanism was removed in commit 900baa6e7bb0
("firmware: cs_dsp: Remove redundant download buffer allocator").
While doing that I was overly focused on the possibility of the
underlying bus requiring DMA-safe memory. So I used GFP_DMA kmalloc()s.
I failed to notice that the code I was removing used vmalloc().
This creates a regression.

Way back in 2014 the problem of fragmentation with kmalloc()s was fixed
by commit cdcd7f728753 ("ASoC: wm_adsp: Use vmalloc to allocate firmware
download buffer").

Although we don't need physically-contiguous memory, we don't know if the
bus needs some particular alignment of the buffers. Since the change in
2014, the firmware download has always used whatever alignment vmalloc()
returns. To avoid introducing a new problem, the temporary buffer is still
used, to keep the same alignment of pointers passed to regmap_raw_write().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 900baa6e7bb0 ("firmware: cs_dsp: Remove redundant download buffer allocator")
Link: https://patch.msgid.link/20260304141250.1578597-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/cirrus/cs_dsp.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index b4f1c01e3b5b..5d8be0ac7c5e 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1610,11 +1610,17 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 			   region_name);
 
 		if (reg) {
+			/*
+			 * Although we expect the underlying bus does not require
+			 * physically-contiguous buffers, we pessimistically use
+			 * a temporary buffer instead of trusting that the
+			 * alignment of region->data is ok.
+			 */
 			region_len = le32_to_cpu(region->len);
 			if (region_len > buf_len) {
 				buf_len = round_up(region_len, PAGE_SIZE);
-				kfree(buf);
-				buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA);
+				vfree(buf);
+				buf = vmalloc(buf_len);
 				if (!buf) {
 					ret = -ENOMEM;
 					goto out_fw;
@@ -1643,7 +1649,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 
 	ret = 0;
 out_fw:
-	kfree(buf);
+	vfree(buf);
 
 	if (ret == -EOVERFLOW)
 		cs_dsp_err(dsp, "%s: file content overflows file data\n", file);
@@ -2331,11 +2337,17 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 		}
 
 		if (reg) {
+			/*
+			 * Although we expect the underlying bus does not require
+			 * physically-contiguous buffers, we pessimistically use
+			 * a temporary buffer instead of trusting that the
+			 * alignment of blk->data is ok.
+			 */
 			region_len = le32_to_cpu(blk->len);
 			if (region_len > buf_len) {
 				buf_len = round_up(region_len, PAGE_SIZE);
-				kfree(buf);
-				buf = kmalloc(buf_len, GFP_KERNEL | GFP_DMA);
+				vfree(buf);
+				buf = vmalloc(buf_len);
 				if (!buf) {
 					ret = -ENOMEM;
 					goto out_fw;
@@ -2366,7 +2378,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 
 	ret = 0;
 out_fw:
-	kfree(buf);
+	vfree(buf);
 
 	if (ret == -EOVERFLOW)
 		cs_dsp_err(dsp, "%s: file content overflows file data\n", file);
-- 
cgit v1.2.3


From c15e7c62feb3751cbdd458555819df1d70374890 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 26 Feb 2026 21:54:21 -0800
Subject: smb/server: Fix another refcount leak in smb2_open()

If ksmbd_override_fsids() fails, we jump to err_out2. At that point, fp is
NULL because it hasn't been assigned dh_info.fp yet, so ksmbd_fd_put(work,
fp) will not be called. However, dh_info.fp was already inserted into the
session file table by ksmbd_reopen_durable_fd(), so it will leak in the
session file table until the session is closed.

Move fp = dh_info.fp; ahead of the ksmbd_override_fsids() check to fix the
problem.

Found by an experimental AI code review agent at Google.

Fixes: c8efcc786146a ("ksmbd: add support for durable handles v1/v2")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 743c629fe7ec..48836b97951b 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -3012,13 +3012,14 @@ int smb2_open(struct ksmbd_work *work)
 				goto err_out2;
 			}
 
+			fp = dh_info.fp;
+
 			if (ksmbd_override_fsids(work)) {
 				rc = -ENOMEM;
 				ksmbd_put_durable_fd(dh_info.fp);
 				goto err_out2;
 			}
 
-			fp = dh_info.fp;
 			file_info = FILE_OPENED;
 
 			rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat);
-- 
cgit v1.2.3


From 40955015fae4908157ac6c959ea696d05e6e9b31 Mon Sep 17 00:00:00 2001
From: Ali Khaledi <ali.khaledi1989@gmail.com>
Date: Mon, 2 Mar 2026 10:15:48 +0900
Subject: ksmbd: fix use-after-free in proc_show_files due to early
 rcu_read_unlock

The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window. A concurrent opinfo_put() can free the opinfo between the
unlock and the subsequent access to opinfo->is_lease,
opinfo->o_lease->state, and opinfo->level.

Fix this by deferring rcu_read_unlock() until after all opinfo
field accesses are complete. The values needed (const_names, count,
level) are copied into local variables under the RCU read lock,
and the potentially-sleeping seq_printf calls happen after the
lock is released.

Found by AI-assisted code review (Claude Opus 4.6, Anthropic)
in collaboration with Ali Khaledi.

Cc: stable@vger.kernel.org
Fixes: b38f99c1217a ("ksmbd: add procfs interface for runtime monitoring and statistics")
Signed-off-by: Ali Khaledi <ali.khaledi1989@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/vfs_cache.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index ff4ea412d900..168f2dd7e200 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -87,11 +87,7 @@ static int proc_show_files(struct seq_file *m, void *v)
 
 		rcu_read_lock();
 		opinfo = rcu_dereference(fp->f_opinfo);
-		rcu_read_unlock();
-
-		if (!opinfo) {
-			seq_printf(m, " %-15s", " ");
-		} else {
+		if (opinfo) {
 			const struct ksmbd_const_name *const_names;
 			int count;
 			unsigned int level;
@@ -105,8 +101,12 @@ static int proc_show_files(struct seq_file *m, void *v)
 				count = ARRAY_SIZE(ksmbd_oplock_const_names);
 				level = opinfo->level;
 			}
+			rcu_read_unlock();
 			ksmbd_proc_show_const_name(m, " %-15s",
 						   const_names, count, level);
+		} else {
+			rcu_read_unlock();
+			seq_printf(m, " %-15s", " ");
 		}
 
 		seq_printf(m, " %#010x %#010x %s\n",
-- 
cgit v1.2.3


From 1dfd062caa165ec9d7ee0823087930f3ab8a6294 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 7 Mar 2026 11:32:31 +0900
Subject: ksmbd: fix use-after-free by using call_rcu() for oplock_info

ksmbd currently frees oplock_info immediately using kfree(), even
though it is accessed under RCU read-side critical sections in places
like opinfo_get() and proc_show_files().

Since there is no RCU grace period delay between nullifying the pointer
and freeing the memory, a reader can still access oplock_info
structure after it has been freed. This can leads to a use-after-free
especially in opinfo_get() where atomic_inc_not_zero() is called on
already freed memory.

Fix this by switching to deferred freeing using call_rcu().

Fixes: 18b4fac5ef17 ("ksmbd: fix use-after-free in smb_break_all_levII_oplock()")
Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 29 +++++++++++++++++++++--------
 fs/smb/server/oplock.h |  5 +++--
 2 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 09d9878db9cb..8c9aa17384f3 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -120,7 +120,7 @@ static void free_lease(struct oplock_info *opinfo)
 	kfree(lease);
 }
 
-static void free_opinfo(struct oplock_info *opinfo)
+static void __free_opinfo(struct oplock_info *opinfo)
 {
 	if (opinfo->is_lease)
 		free_lease(opinfo);
@@ -129,6 +129,18 @@ static void free_opinfo(struct oplock_info *opinfo)
 	kfree(opinfo);
 }
 
+static void free_opinfo_rcu(struct rcu_head *rcu)
+{
+	struct oplock_info *opinfo = container_of(rcu, struct oplock_info, rcu);
+
+	__free_opinfo(opinfo);
+}
+
+static void free_opinfo(struct oplock_info *opinfo)
+{
+	call_rcu(&opinfo->rcu, free_opinfo_rcu);
+}
+
 struct oplock_info *opinfo_get(struct ksmbd_file *fp)
 {
 	struct oplock_info *opinfo;
@@ -176,9 +188,9 @@ void opinfo_put(struct oplock_info *opinfo)
 	free_opinfo(opinfo);
 }
 
-static void opinfo_add(struct oplock_info *opinfo)
+static void opinfo_add(struct oplock_info *opinfo, struct ksmbd_file *fp)
 {
-	struct ksmbd_inode *ci = opinfo->o_fp->f_ci;
+	struct ksmbd_inode *ci = fp->f_ci;
 
 	down_write(&ci->m_lock);
 	list_add(&opinfo->op_entry, &ci->m_op_list);
@@ -1277,20 +1289,21 @@ set_lev:
 	set_oplock_level(opinfo, req_op_level, lctx);
 
 out:
-	rcu_assign_pointer(fp->f_opinfo, opinfo);
-	opinfo->o_fp = fp;
-
 	opinfo_count_inc(fp);
-	opinfo_add(opinfo);
+	opinfo_add(opinfo, fp);
+
 	if (opinfo->is_lease) {
 		err = add_lease_global_list(opinfo);
 		if (err)
 			goto err_out;
 	}
 
+	rcu_assign_pointer(fp->f_opinfo, opinfo);
+	opinfo->o_fp = fp;
+
 	return 0;
 err_out:
-	free_opinfo(opinfo);
+	__free_opinfo(opinfo);
 	return err;
 }
 
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 9a56eaadd0dd..921e3199e4df 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -69,8 +69,9 @@ struct oplock_info {
 	struct lease		*o_lease;
 	struct list_head        op_entry;
 	struct list_head        lease_entry;
-	wait_queue_head_t oplock_q; /* Other server threads */
-	wait_queue_head_t oplock_brk; /* oplock breaking wait */
+	wait_queue_head_t	oplock_q; /* Other server threads */
+	wait_queue_head_t	oplock_brk; /* oplock breaking wait */
+	struct rcu_head		rcu;
 };
 
 struct lease_break_info {
-- 
cgit v1.2.3


From eac3361e3d5dd8067b3258c69615888eb45e9f25 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Mon, 2 Mar 2026 12:55:02 +0900
Subject: ksmbd: fix use-after-free in smb_lazy_parent_lease_break_close()

opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is being
accessed after rcu_read_unlock() has been called. This creates a
race condition where the memory could be freed by a concurrent
writer between the unlock and the subsequent pointer dereferences
(opinfo->is_lease, etc.), leading to a use-after-free.

Fixes: 5fb282ba4fef ("ksmbd: fix possible null-deref in smb_lazy_parent_lease_break_close")
Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 8c9aa17384f3..393a4ae47cc1 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1135,10 +1135,12 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
 
 	rcu_read_lock();
 	opinfo = rcu_dereference(fp->f_opinfo);
-	rcu_read_unlock();
 
-	if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2)
+	if (!opinfo || !opinfo->is_lease || opinfo->o_lease->version != 2) {
+		rcu_read_unlock();
 		return;
+	}
+	rcu_read_unlock();
 
 	p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent);
 	if (!p_ci)
-- 
cgit v1.2.3


From 1e689a56173827669a35da7cb2a3c78ed5c53680 Mon Sep 17 00:00:00 2001
From: Marios Makassikis <mmakassikis@freebox.fr>
Date: Tue, 3 Mar 2026 11:14:32 +0100
Subject: smb: server: fix use-after-free in smb2_open()

The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window.

Cc: stable@vger.kernel.org
Signed-off-by: Marios Makassikis <mmakassikis@freebox.fr>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 48836b97951b..9f7ff7491e9a 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -3617,10 +3617,8 @@ int smb2_open(struct ksmbd_work *work)
 
 reconnected_fp:
 	rsp->StructureSize = cpu_to_le16(89);
-	rcu_read_lock();
-	opinfo = rcu_dereference(fp->f_opinfo);
+	opinfo = opinfo_get(fp);
 	rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0;
-	rcu_read_unlock();
 	rsp->Flags = 0;
 	rsp->CreateAction = cpu_to_le32(file_info);
 	rsp->CreationTime = cpu_to_le64(fp->create_time);
@@ -3661,6 +3659,7 @@ reconnected_fp:
 		next_ptr = &lease_ccontext->Next;
 		next_off = conn->vals->create_lease_size;
 	}
+	opinfo_put(opinfo);
 
 	if (maximal_access_ctxt) {
 		struct create_context *mxac_ccontext;
-- 
cgit v1.2.3


From 441336115df26b966575de56daf7107ed474faed Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 14:25:53 +0100
Subject: ksmbd: Don't log keys in SMB3 signing and encryption key generation

When KSMBD_DEBUG_AUTH logging is enabled, generate_smb3signingkey() and
generate_smb3encryptionkey() log the session, signing, encryption, and
decryption key bytes. Remove the logs to avoid exposing credentials.

Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/auth.c | 22 ++--------------------
 1 file changed, 2 insertions(+), 20 deletions(-)

diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c
index 5fe8c667c6b1..af5f40304331 100644
--- a/fs/smb/server/auth.c
+++ b/fs/smb/server/auth.c
@@ -589,12 +589,8 @@ static int generate_smb3signingkey(struct ksmbd_session *sess,
 	if (!(conn->dialect >= SMB30_PROT_ID && signing->binding))
 		memcpy(chann->smb3signingkey, key, SMB3_SIGN_KEY_SIZE);
 
-	ksmbd_debug(AUTH, "dumping generated AES signing keys\n");
+	ksmbd_debug(AUTH, "generated SMB3 signing key\n");
 	ksmbd_debug(AUTH, "Session Id    %llu\n", sess->id);
-	ksmbd_debug(AUTH, "Session Key   %*ph\n",
-		    SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key);
-	ksmbd_debug(AUTH, "Signing Key   %*ph\n",
-		    SMB3_SIGN_KEY_SIZE, key);
 	return 0;
 }
 
@@ -652,23 +648,9 @@ static void generate_smb3encryptionkey(struct ksmbd_conn *conn,
 		     ptwin->decryption.context,
 		     sess->smb3decryptionkey, SMB3_ENC_DEC_KEY_SIZE);
 
-	ksmbd_debug(AUTH, "dumping generated AES encryption keys\n");
+	ksmbd_debug(AUTH, "generated SMB3 encryption/decryption keys\n");
 	ksmbd_debug(AUTH, "Cipher type   %d\n", conn->cipher_type);
 	ksmbd_debug(AUTH, "Session Id    %llu\n", sess->id);
-	ksmbd_debug(AUTH, "Session Key   %*ph\n",
-		    SMB2_NTLMV2_SESSKEY_SIZE, sess->sess_key);
-	if (conn->cipher_type == SMB2_ENCRYPTION_AES256_CCM ||
-	    conn->cipher_type == SMB2_ENCRYPTION_AES256_GCM) {
-		ksmbd_debug(AUTH, "ServerIn Key  %*ph\n",
-			    SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3encryptionkey);
-		ksmbd_debug(AUTH, "ServerOut Key %*ph\n",
-			    SMB3_GCM256_CRYPTKEY_SIZE, sess->smb3decryptionkey);
-	} else {
-		ksmbd_debug(AUTH, "ServerIn Key  %*ph\n",
-			    SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3encryptionkey);
-		ksmbd_debug(AUTH, "ServerOut Key %*ph\n",
-			    SMB3_GCM128_CRYPTKEY_SIZE, sess->smb3decryptionkey);
-	}
 }
 
 void ksmbd_gen_smb30_encryptionkey(struct ksmbd_conn *conn,
-- 
cgit v1.2.3


From 3f63297ff61a994b99d710dcb6dbde41c4003233 Mon Sep 17 00:00:00 2001
From: LUO Haowen <luo-hw@foxmail.com>
Date: Wed, 4 Mar 2026 14:45:09 +0800
Subject: dmaengine: dw-edma: Fix multiple times setting of the CYCLE_STATE and
 CYCLE_BIT bits for HDMA.

Others have submitted this issue (https://lore.kernel.org/dmaengine/
20240722030405.3385-1-zhengdongxiong@gxmicro.cn/),
but it has not been fixed yet. Therefore, more supplementary information
is provided here.

As mentioned in the "PCS-CCS-CB-TCB" Producer-Consumer Synchronization of
"DesignWare Cores PCI Express Controller Databook, version 6.00a":

1. The Consumer CYCLE_STATE (CCS) bit in the register only needs to be
initialized once; the value will update automatically to be
~CYCLE_BIT (CB) in the next chunk.
2. The Consumer CYCLE_BIT bit in the register is loaded from the LL
element and tested against CCS. When CB = CCS, the data transfer is
executed. Otherwise not.

The current logic sets customer (HDMA) CS and CB bits to 1 in each chunk
while setting the producer (software) CB of odd chunks to 0 and even
chunks to 1 in the linked list. This is leading to a mismatch between
the producer CB and consumer CS bits.

This issue can be reproduced by setting the transmission data size to
exceed one chunk. By the way, in the EDMA using the same "PCS-CCS-CB-TCB"
mechanism, the CS bit is only initialized once and this issue was not
found. Refer to
drivers/dma/dw-edma/dw-edma-v0-core.c:dw_edma_v0_core_start.

So fix this issue by initializing the CYCLE_STATE and CYCLE_BIT bits
only once.

Fixes: e74c39573d35 ("dmaengine: dw-edma: Add support for native HDMA")
Signed-off-by: LUO Haowen <luo-hw@foxmail.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/tencent_CB11AA9F3920C1911AF7477A9BD8EFE0AD05@qq.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw-edma/dw-hdma-v0-core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index e3f8db4fe909..ce8f7254bab2 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -252,10 +252,10 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 			  lower_32_bits(chunk->ll_region.paddr));
 		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
 			  upper_32_bits(chunk->ll_region.paddr));
+		/* Set consumer cycle */
+		SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
+			HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
 	}
-	/* Set consumer cycle */
-	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
-		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
 
 	dw_hdma_v0_sync_ll_data(chunk);
 
-- 
cgit v1.2.3


From e0adbf74e2a0455a6bc9628726ba87bcd0b42bf8 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Tue, 14 Oct 2025 08:13:08 +0200
Subject: dmaengine: xilinx: xdma: Fix regmap init error handling

devm_regmap_init_mmio returns an ERR_PTR() upon error, not NULL.
Fix the error check and also fix the error message. Use the error code
from ERR_PTR() instead of the wrong value in ret.

Fixes: 17ce252266c7 ("dmaengine: xilinx: xdma: Add xilinx xdma driver")
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20251014061309.283468-1-alexander.stein@ew.tq-group.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xdma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index d02a4dac2291..782a55edc55b 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -1234,8 +1234,8 @@ static int xdma_probe(struct platform_device *pdev)
 
 	xdev->rmap = devm_regmap_init_mmio(&pdev->dev, reg_base,
 					   &xdma_regmap_config);
-	if (!xdev->rmap) {
-		xdma_err(xdev, "config regmap failed: %d", ret);
+	if (IS_ERR(xdev->rmap)) {
+		xdma_err(xdev, "config regmap failed: %pe", xdev->rmap);
 		goto failed;
 	}
 	INIT_LIST_HEAD(&xdev->dma_dev.channels);
-- 
cgit v1.2.3


From 56fbbe096a89ff4b52af78a21a4afd9d94bdcc80 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Thu, 5 Mar 2026 10:35:59 +0800
Subject: ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix headphone

The BIOS of this machine has set 0x19 to mic, which needs to be set
to headphone pin in order to work properly.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220814
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/b55f6ebe-7449-49f7-ae85-00d2ba1e7af0@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc662.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c
index 5073165d1f3c..3a943adf9087 100644
--- a/sound/hda/codecs/realtek/alc662.c
+++ b/sound/hda/codecs/realtek/alc662.c
@@ -313,6 +313,7 @@ enum {
 	ALC897_FIXUP_HEADSET_MIC_PIN2,
 	ALC897_FIXUP_UNIS_H3C_X500S,
 	ALC897_FIXUP_HEADSET_MIC_PIN3,
+	ALC897_FIXUP_H610M_HP_PIN,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -766,6 +767,13 @@ static const struct hda_fixup alc662_fixups[] = {
 			{ }
 		},
 	},
+	[ALC897_FIXUP_H610M_HP_PIN] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x0321403f }, /* HP out */
+			{ }
+		},
+	},
 };
 
 static const struct hda_quirk alc662_fixup_tbl[] = {
@@ -815,6 +823,7 @@ static const struct hda_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
 	SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2),
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
+	SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN),
 	SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS),
 	SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN),
-- 
cgit v1.2.3


From 9b1dbd69ba6f8f8c69bc7b77c2ce3b9c6ed05ba6 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Thu, 5 Mar 2026 14:35:07 -0500
Subject: ALSA: pcm: fix use-after-free on linked stream runtime in
 snd_pcm_drain()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the drain loop, the local variable 'runtime' is reassigned to a
linked stream's runtime (runtime = s->runtime at line 2157).  After
releasing the stream lock at line 2169, the code accesses
runtime->no_period_wakeup, runtime->rate, and runtime->buffer_size
(lines 2170-2178) — all referencing the linked stream's runtime without
any lock or refcount protecting its lifetime.

A concurrent close() on the linked stream's fd triggers
snd_pcm_release_substream() → snd_pcm_drop() → pcm_release_private()
→ snd_pcm_unlink() → snd_pcm_detach_substream() → kfree(runtime).
No synchronization prevents kfree(runtime) from completing while the
drain path dereferences the stale pointer.

Fix by caching the needed runtime fields (no_period_wakeup, rate,
buffer_size) into local variables while still holding the stream lock,
and using the cached values after the lock is released.

Fixes: f2b3614cefb6 ("ALSA: PCM - Don't check DMA time-out too shortly")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Link: https://patch.msgid.link/20260305193508.311096-1-mehulrao@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm_native.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 67cf6a0e17ba..5a64453da728 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -2144,6 +2144,10 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 	for (;;) {
 		long tout;
 		struct snd_pcm_runtime *to_check;
+		unsigned int drain_rate;
+		snd_pcm_uframes_t drain_bufsz;
+		bool drain_no_period_wakeup;
+
 		if (signal_pending(current)) {
 			result = -ERESTARTSYS;
 			break;
@@ -2163,16 +2167,25 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 		snd_pcm_group_unref(group, substream);
 		if (!to_check)
 			break; /* all drained */
+		/*
+		 * Cache the runtime fields needed after unlock.
+		 * A concurrent close() on the linked stream may free
+		 * its runtime via snd_pcm_detach_substream() once we
+		 * release the stream lock below.
+		 */
+		drain_no_period_wakeup = to_check->no_period_wakeup;
+		drain_rate = to_check->rate;
+		drain_bufsz = to_check->buffer_size;
 		init_waitqueue_entry(&wait, current);
 		set_current_state(TASK_INTERRUPTIBLE);
 		add_wait_queue(&to_check->sleep, &wait);
 		snd_pcm_stream_unlock_irq(substream);
-		if (runtime->no_period_wakeup)
+		if (drain_no_period_wakeup)
 			tout = MAX_SCHEDULE_TIMEOUT;
 		else {
 			tout = 100;
-			if (runtime->rate) {
-				long t = runtime->buffer_size * 1100 / runtime->rate;
+			if (drain_rate) {
+				long t = drain_bufsz * 1100 / drain_rate;
 				tout = max(t, tout);
 			}
 			tout = msecs_to_jiffies(tout);
-- 
cgit v1.2.3


From 0d3429f12133c2ca47aa82ddab2342bc360c47d3 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 6 Mar 2026 20:33:17 +0800
Subject: ALSA: hda/realtek: add quirk for ASUS UM6702RC

The sound card of this machine cannot adjust the volume, it can only
be 0 or 100%. The reason is that the DAC with pin 0x17 is connected
to 0x06. Testing found that connecting 0x02 can fix this problem.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220356
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260306123317.575346-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 4c49f1195e1b..dc4a10aaef60 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7273,6 +7273,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2),
+	HDA_CODEC_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC285_FIXUP_ASUS_I2C_SPEAKER2_TO_DAC1),
 	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
-- 
cgit v1.2.3


From 178dd118c0f07fd63a9ed74cfbd8c31ae50e33af Mon Sep 17 00:00:00 2001
From: Liucheng Lu <luliucheng100@outlook.com>
Date: Sat, 7 Mar 2026 11:27:27 +0800
Subject: ALSA: hda/realtek: add HP Laptop 14s-dr5xxx mute LED quirk

HP Laptop 14s-dr5xxx with ALC236 codec does not handle the toggling of
the mute LED.
This patch adds a quirk entry for subsystem ID 0x8a1f using
ALC236_FIXUP_HP_MUTE_LED_COEFBIT2 fixup, enabling correct mute LED
behavior.

Signed-off-by: Liucheng Lu <luliucheng100@outlook.com>
Link: https://patch.msgid.link/PAVPR03MB9774F3FCE9CCD181C585281AE37BA@PAVPR03MB9774.eurprd03.prod.outlook.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index dc4a10aaef60..4cfbb7922eeb 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6940,6 +6940,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x89da, "HP Spectre x360 14t-ea100", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
 	SND_PCI_QUIRK(0x103c, 0x89e7, "HP Elite x2 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8a1f, "HP Laptop 14s-dr5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a26, "HP Victus 16-d1xxx (MB 8A26)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
-- 
cgit v1.2.3


From 542127f6528ca7cc3cf61e1651d6ccb58495f953 Mon Sep 17 00:00:00 2001
From: Uzair Mughal <contact@uzair.is-a.dev>
Date: Sat, 7 Mar 2026 06:29:06 +0500
Subject: ALSA: hda/realtek: Add headset jack quirk for Thinkpad X390

The Lenovo ThinkPad X390 (ALC257 codec, subsystem ID 0x17aa2288)
does not report headset button press events. Headphone insertion is
detected (SW_HEADPHONE_INSERT), but pressing the inline microphone
button on a headset produces no input events.

Add a SND_PCI_QUIRK entry that maps this subsystem ID to
ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, which enables
headset jack button detection through alc_fixup_headset_jack()
and ThinkPad ACPI integration. This is the same fixup used by
similar ThinkPad models (P1 Gen 3, X1 Extreme Gen 3).

Signed-off-by: Uzair Mughal <contact@uzair.is-a.dev>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260307012906.20093-1-contact@uzair.is-a.dev
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 4cfbb7922eeb..ab4b22fcb72e 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7495,6 +7495,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2288, "Thinkpad X390", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
 	SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
-- 
cgit v1.2.3


From 67e467a11f62ff64ad219dc6aa5459e132c79d14 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Sat, 7 Mar 2026 14:30:41 +0530
Subject: netfs: Fix kernel BUG in netfs_limit_iter() for ITER_KVEC iterators

When a process crashes and the kernel writes a core dump to a 9P
filesystem, __kernel_write() creates an ITER_KVEC iterator. This
iterator reaches netfs_limit_iter() via netfs_unbuffered_write(), which
only handles ITER_FOLIOQ, ITER_BVEC and ITER_XARRAY iterator types,
hitting the BUG() for any other type.

Fix this by adding netfs_limit_kvec() following the same pattern as
netfs_limit_bvec(), since both kvec and bvec are simple segment arrays
with pointer and length fields. Dispatch it from netfs_limit_iter() when
the iterator type is ITER_KVEC.

Fixes: cae932d3aee5 ("netfs: Add func to calculate pagecount/size-limited span of an iterator")
Reported-by: syzbot+9c058f0d63475adc97fd@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=9c058f0d63475adc97fd
Tested-by: syzbot+9c058f0d63475adc97fd@syzkaller.appspotmail.com
Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
Link: https://patch.msgid.link/20260307090041.359870-1-kartikey406@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/iterator.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 72a435e5fc6d..154a14bb2d7f 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -142,6 +142,47 @@ static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
 	return min(span, max_size);
 }
 
+/*
+ * Select the span of a kvec iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  Returns the size of the span
+ * in bytes.
+ */
+static size_t netfs_limit_kvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct kvec *kvecs = iter->kvec;
+	unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_kvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nkv && skip) {
+		len = kvecs[ix].iov_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nkv) {
+		len = min3(n, kvecs[ix].iov_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
 /*
  * Select the span of an xarray iterator we're going to use.  Limit it by both
  * maximum size and maximum number of segments.  It is assumed that segments
@@ -245,6 +286,8 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
 	if (iov_iter_is_xarray(iter))
 		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_kvec(iter))
+		return netfs_limit_kvec(iter, start_offset, max_size, max_segs);
 	BUG();
 }
 EXPORT_SYMBOL(netfs_limit_iter);
-- 
cgit v1.2.3


From e9075e420a1eb3b52c60f3b95893a55e77419ce8 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Sat, 7 Mar 2026 10:09:47 +0530
Subject: netfs: Fix NULL pointer dereference in netfs_unbuffered_write() on
 retry

When a write subrequest is marked NETFS_SREQ_NEED_RETRY, the retry path
in netfs_unbuffered_write() unconditionally calls stream->prepare_write()
without checking if it is NULL.

Filesystems such as 9P do not set the prepare_write operation, so
stream->prepare_write remains NULL. When get_user_pages() fails with
-EFAULT and the subrequest is flagged for retry, this results in a NULL
pointer dereference at fs/netfs/direct_write.c:189.

Fix this by mirroring the pattern already used in write_retry.c: if
stream->prepare_write is NULL, skip renegotiation and directly reissue
the subrequest via netfs_reissue_write(), which handles iterator reset,
IN_PROGRESS flag, stats update and reissue internally.

Fixes: a0b4c7a49137 ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence")
Reported-by: syzbot+7227db0fbac9f348dba0@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7227db0fbac9f348dba0
Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
Link: https://patch.msgid.link/20260307043947.347092-1-kartikey406@gmail.com
Tested-by: syzbot+7227db0fbac9f348dba0@syzkaller.appspotmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/direct_write.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index dd1451bf7543..4d9760e36c11 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -186,10 +186,18 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq)
 		stream->sreq_max_segs	= INT_MAX;
 
 		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-		stream->prepare_write(subreq);
 
-		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-		netfs_stat(&netfs_n_wh_retry_write_subreq);
+		if (stream->prepare_write) {
+			stream->prepare_write(subreq);
+			__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+			netfs_stat(&netfs_n_wh_retry_write_subreq);
+		} else {
+			struct iov_iter source;
+
+			netfs_reset_iter(subreq);
+			source = subreq->io_iter;
+			netfs_reissue_write(stream, subreq, &source);
+		}
 	}
 
 	netfs_unbuffered_write_done(wreq);
-- 
cgit v1.2.3


From e1c9866173c5f8521f2d0768547a01508cb9ff27 Mon Sep 17 00:00:00 2001
From: Tuo Li <islituo@gmail.com>
Date: Tue, 6 Jan 2026 11:24:28 +0800
Subject: dmaengine: idxd: fix possible wrong descriptor completion in
 llist_abort_desc()

At the end of this function, d is the traversal cursor of flist, but the
code completes found instead. This can lead to issues such as NULL pointer
dereferences, double completion, or descriptor leaks.

Fix this by completing d instead of found in the final
list_for_each_entry_safe() loop.

Fixes: aa8d18becc0c ("dmaengine: idxd: add callback support for iaa crypto")
Signed-off-by: Tuo Li <islituo@gmail.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260106032428.162445-1-islituo@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/submit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index 6db1c5fcedc5..03217041b8b3 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -138,7 +138,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 	 */
 	list_for_each_entry_safe(d, t, &flist, list) {
 		list_del_init(&d->list);
-		idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, true,
+		idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true,
 				      NULL, NULL);
 	}
 }
-- 
cgit v1.2.3


From ce0123cbb4a40a2f1bbb815f292b26e96088639f Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Fri, 5 Sep 2025 23:15:30 +0200
Subject: ceph: fix i_nlink underrun during async unlink

During async unlink, we drop the `i_nlink` counter before we receive
the completion (that will eventually update the `i_nlink`) because "we
assume that the unlink will succeed".  That is not a bad idea, but it
races against deletions by other clients (or against the completion of
our own unlink) and can lead to an underrun which emits a WARNING like
this one:

 WARNING: CPU: 85 PID: 25093 at fs/inode.c:407 drop_nlink+0x50/0x68
 Modules linked in:
 CPU: 85 UID: 3221252029 PID: 25093 Comm: php-cgi8.1 Not tainted 6.14.11-cm4all1-ampere #655
 Hardware name: Supermicro ARS-110M-NR/R12SPD-A, BIOS 1.1b 10/17/2023
 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : drop_nlink+0x50/0x68
 lr : ceph_unlink+0x6c4/0x720
 sp : ffff80012173bc90
 x29: ffff80012173bc90 x28: ffff086d0a45aaf8 x27: ffff0871d0eb5680
 x26: ffff087f2a64a718 x25: 0000020000000180 x24: 0000000061c88647
 x23: 0000000000000002 x22: ffff07ff9236d800 x21: 0000000000001203
 x20: ffff07ff9237b000 x19: ffff088b8296afc0 x18: 00000000f3c93365
 x17: 0000000000070000 x16: ffff08faffcbdfe8 x15: ffff08faffcbdfec
 x14: 0000000000000000 x13: 45445f65645f3037 x12: 34385f6369706f74
 x11: 0000a2653104bb20 x10: ffffd85f26d73290 x9 : ffffd85f25664f94
 x8 : 00000000000000c0 x7 : 0000000000000000 x6 : 0000000000000002
 x5 : 0000000000000081 x4 : 0000000000000481 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff08727d3f91e8
 Call trace:
  drop_nlink+0x50/0x68 (P)
  vfs_unlink+0xb0/0x2e8
  do_unlinkat+0x204/0x288
  __arm64_sys_unlinkat+0x3c/0x80
  invoke_syscall.constprop.0+0x54/0xe8
  do_el0_svc+0xa4/0xc8
  el0_svc+0x18/0x58
  el0t_64_sync_handler+0x104/0x130
  el0t_64_sync+0x154/0x158

In ceph_unlink(), a call to ceph_mdsc_submit_request() submits the
CEPH_MDS_OP_UNLINK to the MDS, but does not wait for completion.

Meanwhile, between this call and the following drop_nlink() call, a
worker thread may process a CEPH_CAP_OP_IMPORT, CEPH_CAP_OP_GRANT or
just a CEPH_MSG_CLIENT_REPLY (the latter of which could be our own
completion).  These will lead to a set_nlink() call, updating the
`i_nlink` counter to the value received from the MDS.  If that new
`i_nlink` value happens to be zero, it is illegal to decrement it
further.  But that is exactly what ceph_unlink() will do then.

The WARNING can be reproduced this way:

1. Force async unlink; only the async code path is affected.  Having
   no real clue about Ceph internals, I was unable to find out why the
   MDS wouldn't give me the "Fxr" capabilities, so I patched
   get_caps_for_async_unlink() to always succeed.

   (Note that the WARNING dump above was found on an unpatched kernel,
   without this kludge - this is not a theoretical bug.)

2. Add a sleep call after ceph_mdsc_submit_request() so the unlink
   completion gets handled by a worker thread before drop_nlink() is
   called.  This guarantees that the `i_nlink` is already zero before
   drop_nlink() runs.

The solution is to skip the counter decrement when it is already zero,
but doing so without a lock is still racy (TOCTOU).  Since
ceph_fill_inode() and handle_cap_grant() both hold the
`ceph_inode_info.i_ceph_lock` spinlock while set_nlink() runs, this
seems like the proper lock to protect the `i_nlink` updates.

I found prior art in NFS and SMB (using `inode.i_lock`) and AFS (using
`afs_vnode.cb_lock`).  All three have the zero check as well.

Cc: stable@vger.kernel.org
Fixes: 2ccb45462aea ("ceph: perform asynchronous unlink if we have sufficient caps")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/dir.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 86d7aa594ea9..415db39a56d8 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1339,6 +1339,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	struct ceph_client *cl = fsc->client;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct inode *inode = d_inode(dentry);
+	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_request *req;
 	bool try_async = ceph_test_mount_opt(fsc, ASYNC_DIROPS);
 	struct dentry *dn;
@@ -1424,7 +1425,19 @@ retry:
 			 * We have enough caps, so we assume that the unlink
 			 * will succeed. Fix up the target inode and dcache.
 			 */
-			drop_nlink(inode);
+
+			/*
+			 * Protect the i_nlink update with i_ceph_lock
+			 * to precent racing against ceph_fill_inode()
+			 * handling our completion on a worker thread
+			 * and don't decrement if i_nlink has already
+			 * been updated to zero by this completion.
+			 */
+			spin_lock(&ci->i_ceph_lock);
+			if (inode->i_nlink > 0)
+				drop_nlink(inode);
+			spin_unlock(&ci->i_ceph_lock);
+
 			d_delete(dentry);
 		} else {
 			spin_lock(&fsc->async_unlink_conflict_lock);
-- 
cgit v1.2.3


From 43323a5934b660afae687e8e4e95ac328615a5c4 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Tue, 24 Feb 2026 14:10:29 +0100
Subject: ceph: add a bunch of missing ceph_path_info initializers

ceph_mdsc_build_path() must be called with a zero-initialized
ceph_path_info parameter, or else the following
ceph_mdsc_free_path_info() may crash.

Example crash (on Linux 6.18.12):

  virt_to_cache: Object is not a Slab page!
  WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6732 kmem_cache_free+0x316/0x400
  [...]
  Call Trace:
   [...]
   ceph_open+0x13d/0x3e0
   do_dentry_open+0x134/0x480
   vfs_open+0x2a/0xe0
   path_openat+0x9a3/0x1160
  [...]
  cache_from_obj: Wrong slab cache. names_cache but object is from ceph_inode_info
  WARNING: CPU: 184 PID: 2871736 at mm/slub.c:6746 kmem_cache_free+0x2dd/0x400
  [...]
  kernel BUG at mm/slub.c:634!
  Oops: invalid opcode: 0000 [#1] SMP NOPTI
  RIP: 0010:__slab_free+0x1a4/0x350

Some of the ceph_mdsc_build_path() callers had initializers, but
others had not, even though they were all added by commit 15f519e9f883
("ceph: fix race condition validating r_parent before applying state").
The ones without initializer are suspectible to random crashes.  (I can
imagine it could even be possible to exploit this bug to elevate
privileges.)

Unfortunately, these Ceph functions are undocumented and its semantics
can only be derived from the code.  I see that ceph_mdsc_build_path()
initializes the structure only on success, but not on error.

Calling ceph_mdsc_free_path_info() after a failed
ceph_mdsc_build_path() call does not even make sense, but that's what
all callers do, and for it to be safe, the structure must be
zero-initialized.  The least intrusive approach to fix this is
therefore to add initializers everywhere.

Cc: stable@vger.kernel.org
Fixes: 15f519e9f883 ("ceph: fix race condition validating r_parent before applying state")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/debugfs.c | 4 ++--
 fs/ceph/dir.c     | 2 +-
 fs/ceph/file.c    | 4 ++--
 fs/ceph/inode.c   | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f3fe786b4143..7dc307790240 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -79,7 +79,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		if (req->r_inode) {
 			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
 		} else if (req->r_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
@@ -98,7 +98,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 		}
 
 		if (req->r_old_dentry) {
-			struct ceph_path_info path_info;
+			struct ceph_path_info path_info = {0};
 			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 415db39a56d8..bac9cfb6b982 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1364,7 +1364,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 66bbf6d517a9..5e7c73a29aa3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -397,7 +397,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
@@ -807,7 +807,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!dn) {
 		try_async = false;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d76f9a79dc0c..d99e12d1100b 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2551,7 +2551,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		struct ceph_path_info path_info;
+		struct ceph_path_info path_info = {0};
 		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
-- 
cgit v1.2.3


From 040d159a45ded7f33201421a81df0aa2a86e5a0b Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Tue, 24 Feb 2026 14:26:57 +0100
Subject: ceph: fix memory leaks in ceph_mdsc_build_path()

Add __putname() calls to error code paths that did not free the "path"
pointer obtained by __getname().  If ownership of this pointer is not
passed to the caller via path_info.path, the function must free it
before returning.

Cc: stable@vger.kernel.org
Fixes: 3fd945a79e14 ("ceph: encode encrypted name in ceph_mdsc_build_path and dentry release")
Fixes: 550f7ca98ee0 ("ceph: give up on paths longer than PATH_MAX")
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 23b6d00643c9..b1746273f186 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2768,6 +2768,7 @@ retry:
 			if (ret < 0) {
 				dput(parent);
 				dput(cur);
+				__putname(path);
 				return ERR_PTR(ret);
 			}
 
@@ -2777,6 +2778,7 @@ retry:
 				if (len < 0) {
 					dput(parent);
 					dput(cur);
+					__putname(path);
 					return ERR_PTR(len);
 				}
 			}
@@ -2813,6 +2815,7 @@ retry:
 		 * cannot ever succeed.  Creating paths that long is
 		 * possible with Ceph, but Linux cannot use them.
 		 */
+		__putname(path);
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 
-- 
cgit v1.2.3


From 081a0b78ef30f5746cda3e92e28b4d4ae92901d1 Mon Sep 17 00:00:00 2001
From: Hristo Venev <hristo@venev.name>
Date: Wed, 25 Feb 2026 19:07:56 +0200
Subject: ceph: do not skip the first folio of the next object in writeback

When `ceph_process_folio_batch` encounters a folio past the end of the
current object, it should leave it in the batch so that it is picked up
in the next iteration.

Removing the folio from the batch means that it does not get written
back and remains dirty instead. This makes `fsync()` silently skip some
of the data, delays capability release, and breaks coherence with
`O_DIRECT`.

The link below contains instructions for reproducing the bug.

Cc: stable@vger.kernel.org
Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method")
Link: https://tracker.ceph.com/issues/75156
Signed-off-by: Hristo Venev <hristo@venev.name>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e87b3bb94ee8..2090fc78529c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1326,7 +1326,6 @@ void ceph_process_folio_batch(struct address_space *mapping,
 			continue;
 		} else if (rc == -E2BIG) {
 			folio_unlock(folio);
-			ceph_wbc->fbatch.folios[i] = NULL;
 			break;
 		}
 
-- 
cgit v1.2.3


From 73a505dc48144ec72e25874e2b2a72487b02d3bc Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Mon, 9 Mar 2026 10:39:49 +0100
Subject: thunderbolt: Fix property read in nhi_wake_supported()

device_property_read_foo() returns 0 on success and only then modifies
'val'. Currently, val is left uninitialized if the aforementioned
function returns non-zero, making nhi_wake_supported() return true
almost always (random != 0) if the property is not present in device
firmware.

Invert the check to make it make sense.

Fixes: 3cdb9446a117 ("thunderbolt: Add support for Intel Ice Lake")
Cc: stable@vger.kernel.org
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/nhi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index ccce020a2432..2bb2e79ca3cb 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -1020,7 +1020,7 @@ static bool nhi_wake_supported(struct pci_dev *pdev)
 	 * If power rails are sustainable for wakeup from S4 this
 	 * property is set by the BIOS.
 	 */
-	if (device_property_read_u8(&pdev->dev, "WAKE_SUPPORTED", &val))
+	if (!device_property_read_u8(&pdev->dev, "WAKE_SUPPORTED", &val))
 		return !!val;
 
 	return true;
-- 
cgit v1.2.3


From d800d0bb2009a73630a096d7c7a80a2e64c1e41e Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 25 Feb 2026 13:51:09 +0100
Subject: dt-bindings: i2c: dw: Update maintainer

Jarkko does now work for Intel anymore and since I'm currently
maintaining this driver, update my contact information here to make sure
patches get Cc'd to me as well.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> (internally)
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
index 914200188809..082fdc2e69ea 100644
--- a/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/snps,designware-i2c.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Synopsys DesignWare APB I2C Controller
 
 maintainers:
-  - Jarkko Nikula <jarkko.nikula@linux.intel.com>
+  - Mika Westerberg <mika.westerberg@linux.intel.com>
 
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#
-- 
cgit v1.2.3


From b20b437666e1cb26a7c499d1664e8f2a0ac67000 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Fri, 6 Mar 2026 01:24:32 +0800
Subject: spi: amlogic: spifc-a4: Fix DMA mapping error handling

Fix three bugs in aml_sfc_dma_buffer_setup() error paths:
1. Unnecessary goto: When the first DMA mapping (sfc->daddr) fails,
   nothing needs cleanup. Use direct return instead of goto.
2. Double-unmap bug: When info DMA mapping failed, the code would
   unmap sfc->daddr inline, then fall through to out_map_data which
   would unmap it again, causing a double-unmap.
3. Wrong unmap size: The out_map_info label used datalen instead of
   infolen when unmapping sfc->iaddr, which could lead to incorrect
   DMA sync behavior.

Fixes: 4670db6f32e9 ("spi: amlogic: add driver for Amlogic SPI Flash Controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260306-spifc-a4-v1-1-f22c9965f64a@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-amlogic-spifc-a4.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c
index 2aef528cfc1b..3956869cfec1 100644
--- a/drivers/spi/spi-amlogic-spifc-a4.c
+++ b/drivers/spi/spi-amlogic-spifc-a4.c
@@ -411,7 +411,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 	ret = dma_mapping_error(sfc->dev, sfc->daddr);
 	if (ret) {
 		dev_err(sfc->dev, "DMA mapping error\n");
-		goto out_map_data;
+		return ret;
 	}
 
 	cmd = CMD_DATA_ADDRL(sfc->daddr);
@@ -429,7 +429,6 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 		ret = dma_mapping_error(sfc->dev, sfc->iaddr);
 		if (ret) {
 			dev_err(sfc->dev, "DMA mapping error\n");
-			dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir);
 			goto out_map_data;
 		}
 
@@ -448,7 +447,7 @@ static int aml_sfc_dma_buffer_setup(struct aml_sfc *sfc, void *databuf,
 	return 0;
 
 out_map_info:
-	dma_unmap_single(sfc->dev, sfc->iaddr, datalen, dir);
+	dma_unmap_single(sfc->dev, sfc->iaddr, infolen, dir);
 out_map_data:
 	dma_unmap_single(sfc->dev, sfc->daddr, datalen, dir);
 
-- 
cgit v1.2.3


From ad0e9ac2d5f5ab7a773c2c07ecf06ee59db9259f Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 5 Mar 2026 20:22:38 +0800
Subject: spi: atcspi200: Fix double-free in atcspi_configure_dma()

The driver uses devm_dma_request_chan() which registers automatic cleanup
via devm_add_action_or_reset(). Calling dma_release_channel() manually on
the RX channel when TX channel request fails causes a double-free when
the devm cleanup runs.

Remove the unnecessary manual cleanup and simplify the error handling
since devm will properly release channels on probe failure or driver
detach.

Fixes: 34e3815ea459 ("spi: atcspi200: Add ATCSPI200 SPI controller driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260305-atcspi2000-v1-1-eafe08dcca60@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-atcspi200.c | 28 +++++++---------------------
 1 file changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c
index 60a37ff5c6f5..fef6954d27e1 100644
--- a/drivers/spi/spi-atcspi200.c
+++ b/drivers/spi/spi-atcspi200.c
@@ -497,31 +497,17 @@ static int atcspi_init_resources(struct platform_device *pdev,
 
 static int atcspi_configure_dma(struct atcspi_dev *spi)
 {
-	struct dma_chan *dma_chan;
-	int ret = 0;
+	spi->host->dma_rx = devm_dma_request_chan(spi->dev, "rx");
+	if (IS_ERR(spi->host->dma_rx))
+		return PTR_ERR(spi->host->dma_rx);
 
-	dma_chan = devm_dma_request_chan(spi->dev, "rx");
-	if (IS_ERR(dma_chan)) {
-		ret = PTR_ERR(dma_chan);
-		goto err_exit;
-	}
-	spi->host->dma_rx = dma_chan;
+	spi->host->dma_tx = devm_dma_request_chan(spi->dev, "tx");
+	if (IS_ERR(spi->host->dma_tx))
+		return PTR_ERR(spi->host->dma_tx);
 
-	dma_chan = devm_dma_request_chan(spi->dev, "tx");
-	if (IS_ERR(dma_chan)) {
-		ret = PTR_ERR(dma_chan);
-		goto free_rx;
-	}
-	spi->host->dma_tx = dma_chan;
 	init_completion(&spi->dma_completion);
 
-	return ret;
-
-free_rx:
-	dma_release_channel(spi->host->dma_rx);
-	spi->host->dma_rx = NULL;
-err_exit:
-	return ret;
+	return 0;
 }
 
 static int atcspi_enable_clk(struct atcspi_dev *spi)
-- 
cgit v1.2.3


From 155a3bedccaf57c69aa0b590ba3fb579debf3a4d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 8 Mar 2026 22:39:02 +0800
Subject: ublk: don't clear GD_SUPPRESS_PART_SCAN for unprivileged daemons

When UBLK_F_NO_AUTO_PART_SCAN is set, GD_SUPPRESS_PART_SCAN is cleared
unconditionally, including for unprivileged daemons. Keep it consistent
with the code block for setting GD_SUPPRESS_PART_SCAN by not clearing
it for unprivileged daemons.

In reality this isn't a problem because ioctl(BLKRRPART) requires
CAP_SYS_ADMIN, but it is more reliable to not clear the bit.

Cc: Alexander Atanasov <alex@zazolabs.com>
Fixes: 8443e2087e70 ("ublk: add UBLK_F_NO_AUTO_PART_SCAN feature flag")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 03edabdf8977..9f6e9109d310 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -4440,7 +4440,9 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub,
 
 	/* Skip partition scan if disabled by user */
 	if (ub->dev_info.flags & UBLK_F_NO_AUTO_PART_SCAN) {
-		clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
+		/* Not clear for unprivileged daemons, see comment above */
+		if (!ub->unprivileged_daemons)
+			clear_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
 	} else {
 		/* Schedule async partition scan for trusted daemons */
 		if (!ub->unprivileged_daemons)
-- 
cgit v1.2.3


From 0b352f83cabfefdaafa806d6471f0eca117dc7d5 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Wed, 4 Mar 2026 15:09:35 +0100
Subject: xfrm: iptfs: fix skb_put() panic on non-linear skb during reassembly

In iptfs_reassem_cont(), IP-TFS attempts to append data to the new inner
packet 'newskb' that is being reassembled. First a zero-copy approach is
tried if it succeeds then newskb becomes non-linear.

When a subsequent fragment in the same datagram does not meet the
fast-path conditions, a memory copy is performed. It calls skb_put() to
append the data and as newskb is non-linear it triggers
SKB_LINEAR_ASSERT check.

 Oops: invalid opcode: 0000 [#1] SMP NOPTI
 [...]
 RIP: 0010:skb_put+0x3c/0x40
 [...]
 Call Trace:
  <IRQ>
  iptfs_reassem_cont+0x1ab/0x5e0 [xfrm_iptfs]
  iptfs_input_ordered+0x2af/0x380 [xfrm_iptfs]
  iptfs_input+0x122/0x3e0 [xfrm_iptfs]
  xfrm_input+0x91e/0x1a50
  xfrm4_esp_rcv+0x3a/0x110
  ip_protocol_deliver_rcu+0x1d7/0x1f0
  ip_local_deliver_finish+0xbe/0x1e0
  __netif_receive_skb_core.constprop.0+0xb56/0x1120
  __netif_receive_skb_list_core+0x133/0x2b0
  netif_receive_skb_list_internal+0x1ff/0x3f0
  napi_complete_done+0x81/0x220
  virtnet_poll+0x9d6/0x116e [virtio_net]
  __napi_poll.constprop.0+0x2b/0x270
  net_rx_action+0x162/0x360
  handle_softirqs+0xdc/0x510
  __irq_exit_rcu+0xe7/0x110
  irq_exit_rcu+0xe/0x20
  common_interrupt+0x85/0xa0
  </IRQ>
  <TASK>

Fix this by checking if the skb is non-linear. If it is, linearize it by
calling skb_linearize(). As the initial allocation of newskb originally
reserved enough tailroom for the entire reassembled packet we do not
need to check if we have enough tailroom or extend it.

Fixes: 5f2b6a909574 ("xfrm: iptfs: add skb-fragment sharing code")
Reported-by: Hao Long <me@imlonghao.com>
Closes: https://lore.kernel.org/netdev/DGRCO9SL0T5U.JTINSHJQ9KPK@imlonghao.com/
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_iptfs.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 0747d1cfa333..2c87290fe06c 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -901,6 +901,12 @@ static u32 iptfs_reassem_cont(struct xfrm_iptfs_data *xtfs, u64 seq,
 	    iptfs_skb_can_add_frags(newskb, fragwalk, data, copylen)) {
 		iptfs_skb_add_frags(newskb, fragwalk, data, copylen);
 	} else {
+		if (skb_linearize(newskb)) {
+			XFRM_INC_STATS(xs_net(xtfs->x),
+				       LINUX_MIB_XFRMINBUFFERERROR);
+			goto abandon;
+		}
+
 		/* copy fragment data into newskb */
 		if (skb_copy_seq_read(st, data, skb_put(newskb, copylen),
 				      copylen)) {
-- 
cgit v1.2.3


From 1bc17c67194716f53037685b7059a22cc1a911b2 Mon Sep 17 00:00:00 2001
From: Sheetal <sheetal@nvidia.com>
Date: Tue, 3 Mar 2026 15:32:49 +0530
Subject: ASoC: tegra: Add support for Tegra238 soundcard

Tegra238 platforms use different clock rates for plla and
plla_out0 clocks. Add Tegra238 support in the Tegra
sound card driver to apply specific clock configurations.

Signed-off-by: Aditya Bavanari <abavanari@nvidia.com>
Signed-off-by: Sheetal <sheetal@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Link: https://patch.msgid.link/20260303100249.3214529-3-sheetal@nvidia.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra_audio_graph_card.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c
index 94b5ab77649b..ea10e6e8a9fe 100644
--- a/sound/soc/tegra/tegra_audio_graph_card.c
+++ b/sound/soc/tegra/tegra_audio_graph_card.c
@@ -231,6 +231,15 @@ static const struct tegra_audio_cdata tegra186_data = {
 	.plla_out0_rates[x11_RATE] = 45158400,
 };
 
+static const struct tegra_audio_cdata tegra238_data = {
+	/* PLLA */
+	.plla_rates[x8_RATE] = 1277952000,
+	.plla_rates[x11_RATE] = 1264435200,
+	/* PLLA_OUT0 */
+	.plla_out0_rates[x8_RATE] = 49152000,
+	.plla_out0_rates[x11_RATE] = 45158400,
+};
+
 static const struct tegra_audio_cdata tegra264_data = {
 	/* PLLA1 */
 	.plla_rates[x8_RATE] = 983040000,
@@ -245,6 +254,8 @@ static const struct of_device_id graph_of_tegra_match[] = {
 	  .data = &tegra210_data },
 	{ .compatible = "nvidia,tegra186-audio-graph-card",
 	  .data = &tegra186_data },
+	{ .compatible = "nvidia,tegra238-audio-graph-card",
+	  .data = &tegra238_data },
 	{ .compatible = "nvidia,tegra264-audio-graph-card",
 	  .data = &tegra264_data },
 	{},
-- 
cgit v1.2.3


From a8aec14230322ed8f1e8042b6d656c1631d41163 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Fri, 6 Mar 2026 12:33:05 -0600
Subject: nvdimm/bus: Fix potential use after free in asynchronous
 initialization

Dingisoul with KASAN reports a use after free if device_add() fails in
nd_async_device_register().

Commit b6eae0f61db2 ("libnvdimm: Hold reference on parent while
scheduling async init") correctly added a reference on the parent device
to be held until asynchronous initialization was complete.  However, if
device_add() results in an allocation failure the ref count of the
device drops to 0 prior to the parent pointer being accessed.  Thus
resulting in use after free.

The bug bot AI correctly identified the fix.  Save a reference to the
parent pointer to be used to drop the parent reference regardless of the
outcome of device_add().

Reported-by: Dingisoul <dingiso.kernel@gmail.com>
Closes: http://lore.kernel.org/8855544b-be9e-4153-aa55-0bc328b13733@gmail.com
Fixes: b6eae0f61db2 ("libnvdimm: Hold reference on parent while scheduling async init")
Cc: stable@vger.kernel.org
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://patch.msgid.link/20260306-fix-uaf-async-init-v1-1-a28fd7526723@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 drivers/nvdimm/bus.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index bd9621d3f73c..45b7d756e39a 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -486,14 +486,15 @@ EXPORT_SYMBOL_GPL(nd_synchronize);
 static void nd_async_device_register(void *d, async_cookie_t cookie)
 {
 	struct device *dev = d;
+	struct device *parent = dev->parent;
 
 	if (device_add(dev) != 0) {
 		dev_err(dev, "%s: failed\n", __func__);
 		put_device(dev);
 	}
 	put_device(dev);
-	if (dev->parent)
-		put_device(dev->parent);
+	if (parent)
+		put_device(parent);
 }
 
 static void nd_async_device_unregister(void *d, async_cookie_t cookie)
-- 
cgit v1.2.3


From 3306a589e598b50a5bbdfe837371670b507043c0 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Mon, 9 Mar 2026 15:34:41 +0100
Subject: io_uring/register: fix comment about task_no_new_privs

The actual code is right, but the comment is the wrong way around.

Fixes: ed82f35b926b ("io_uring: allow registration of per-task restrictions")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/register.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/io_uring/register.c b/io_uring/register.c
index 594b1f2ce875..a839b22fd392 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -202,7 +202,7 @@ static int io_register_restrictions_task(void __user *arg, unsigned int nr_args)
 		return -EPERM;
 	/*
 	 * Similar to seccomp, disallow setting a filter if task_no_new_privs
-	 * is true and we're not CAP_SYS_ADMIN.
+	 * is false and we're not CAP_SYS_ADMIN.
 	 */
 	if (!task_no_new_privs(current) &&
 	    !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
@@ -238,7 +238,7 @@ static int io_register_bpf_filter_task(void __user *arg, unsigned int nr_args)
 
 	/*
 	 * Similar to seccomp, disallow setting a filter if task_no_new_privs
-	 * is true and we're not CAP_SYS_ADMIN.
+	 * is false and we're not CAP_SYS_ADMIN.
 	 */
 	if (!task_no_new_privs(current) &&
 	    !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
-- 
cgit v1.2.3


From 7fdaa640c810cb42090a182c33f905bcc47a616a Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Fri, 6 Mar 2026 09:35:06 -0800
Subject: objtool: Handle Clang RSP musical chairs

For no apparent reason (possibly related to CONFIG_KMSAN), Clang can
randomly pass the value of RSP to other registers and then back again to
RSP.  Handle that accordingly.

Fixes the following warnings:

  drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: undefined stack state
  drivers/input/misc/uinput.o: warning: objtool: uinput_str_to_user+0x165: unknown CFA base reg -1

Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com
Link: https://patch.msgid.link/240e6a172cc73292499334a3724d02ccb3247fc7.1772818491.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/arch/x86/decode.c | 62 +++++++++++++++--------------------------
 tools/objtool/check.c           | 14 ++++++++++
 2 files changed, 37 insertions(+), 39 deletions(-)

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 73bfea220d1b..c5817829cdfa 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -395,52 +395,36 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 		if (!rex_w)
 			break;
 
-		if (modrm_reg == CFI_SP) {
-
-			if (mod_is_reg()) {
-				/* mov %rsp, reg */
-				ADD_OP(op) {
-					op->src.type = OP_SRC_REG;
-					op->src.reg = CFI_SP;
-					op->dest.type = OP_DEST_REG;
-					op->dest.reg = modrm_rm;
-				}
-				break;
-
-			} else {
-				/* skip RIP relative displacement */
-				if (is_RIP())
-					break;
-
-				/* skip nontrivial SIB */
-				if (have_SIB()) {
-					modrm_rm = sib_base;
-					if (sib_index != CFI_SP)
-						break;
-				}
-
-				/* mov %rsp, disp(%reg) */
-				ADD_OP(op) {
-					op->src.type = OP_SRC_REG;
-					op->src.reg = CFI_SP;
-					op->dest.type = OP_DEST_REG_INDIRECT;
-					op->dest.reg = modrm_rm;
-					op->dest.offset = ins.displacement.value;
-				}
-				break;
+		if (mod_is_reg()) {
+			/* mov reg, reg */
+			ADD_OP(op) {
+				op->src.type = OP_SRC_REG;
+				op->src.reg = modrm_reg;
+				op->dest.type = OP_DEST_REG;
+				op->dest.reg = modrm_rm;
 			}
-
 			break;
 		}
 
-		if (rm_is_reg(CFI_SP)) {
+		/* skip RIP relative displacement */
+		if (is_RIP())
+			break;
 
-			/* mov reg, %rsp */
+		/* skip nontrivial SIB */
+		if (have_SIB()) {
+			modrm_rm = sib_base;
+			if (sib_index != CFI_SP)
+				break;
+		}
+
+		/* mov %rsp, disp(%reg) */
+		if (modrm_reg == CFI_SP) {
 			ADD_OP(op) {
 				op->src.type = OP_SRC_REG;
-				op->src.reg = modrm_reg;
-				op->dest.type = OP_DEST_REG;
-				op->dest.reg = CFI_SP;
+				op->src.reg = CFI_SP;
+				op->dest.type = OP_DEST_REG_INDIRECT;
+				op->dest.reg = modrm_rm;
+				op->dest.offset = ins.displacement.value;
 			}
 			break;
 		}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index a30379e4ff97..786b2f2adbab 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3000,6 +3000,20 @@ static int update_cfi_state(struct instruction *insn,
 				cfi->stack_size += 8;
 			}
 
+			else if (cfi->vals[op->src.reg].base == CFI_CFA) {
+				/*
+				 * Clang RSP musical chairs:
+				 *
+				 *   mov %rsp, %rdx [handled above]
+				 *   ...
+				 *   mov %rdx, %rbx [handled here]
+				 *   ...
+				 *   mov %rbx, %rsp [handled above]
+				 */
+				cfi->vals[op->dest.reg].base = CFI_CFA;
+				cfi->vals[op->dest.reg].offset = cfi->vals[op->src.reg].offset;
+			}
+
 
 			break;
 
-- 
cgit v1.2.3


From 9a73f085dc91980ab7fcc5e9716f4449424b3b59 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Fri, 6 Mar 2026 10:28:14 -0800
Subject: objtool: Fix another stack overflow in validate_branch()

The insn state is getting saved on the stack twice for each recursive
iteration.  No need for that, once is enough.

Fixes the following reported stack overflow:

  drivers/scsi/qla2xxx/qla_dbg.o: error: SIGSEGV: objtool stack overflow!
  Segmentation fault

Fixes: 70589843b36f ("objtool: Add option to trace function validation")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/90956545-2066-46e3-b547-10c884582eb0@app.fastmail.com
Link: https://patch.msgid.link/8b97f62d083457f3b0a29a424275f7957dd3372f.1772821683.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/check.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 786b2f2adbab..91b3ff4803cf 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3748,7 +3748,7 @@ static void checksum_update_insn(struct objtool_file *file, struct symbol *func,
 static int validate_branch(struct objtool_file *file, struct symbol *func,
 			   struct instruction *insn, struct insn_state state);
 static int do_validate_branch(struct objtool_file *file, struct symbol *func,
-			      struct instruction *insn, struct insn_state state);
+			      struct instruction *insn, struct insn_state *state);
 
 static int validate_insn(struct objtool_file *file, struct symbol *func,
 			 struct instruction *insn, struct insn_state *statep,
@@ -4013,7 +4013,7 @@ static int validate_insn(struct objtool_file *file, struct symbol *func,
  * tools/objtool/Documentation/objtool.txt.
  */
 static int do_validate_branch(struct objtool_file *file, struct symbol *func,
-			      struct instruction *insn, struct insn_state state)
+			      struct instruction *insn, struct insn_state *state)
 {
 	struct instruction *next_insn, *prev_insn = NULL;
 	bool dead_end;
@@ -4044,7 +4044,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func,
 			return 1;
 		}
 
-		ret = validate_insn(file, func, insn, &state, prev_insn, next_insn,
+		ret = validate_insn(file, func, insn, state, prev_insn, next_insn,
 				    &dead_end);
 
 		if (!insn->trace) {
@@ -4055,7 +4055,7 @@ static int do_validate_branch(struct objtool_file *file, struct symbol *func,
 		}
 
 		if (!dead_end && !next_insn) {
-			if (state.cfi.cfa.base == CFI_UNDEFINED)
+			if (state->cfi.cfa.base == CFI_UNDEFINED)
 				return 0;
 			if (file->ignore_unreachables)
 				return 0;
@@ -4080,7 +4080,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 	int ret;
 
 	trace_depth_inc();
-	ret = do_validate_branch(file, func, insn, state);
+	ret = do_validate_branch(file, func, insn, &state);
 	trace_depth_dec();
 
 	return ret;
-- 
cgit v1.2.3


From 2fcfe5951eb2e8440fc5e1dd6ea977336ff83a1d Mon Sep 17 00:00:00 2001
From: zhidao su <suzhidao@xiaomi.com>
Date: Mon, 9 Mar 2026 10:46:12 +0800
Subject: sched_ext: Use WRITE_ONCE() for the write side of scx_enable helper
 pointer

scx_enable() uses double-checked locking to lazily initialize a static
kthread_worker pointer. The fast path reads helper locklessly:

    if (!READ_ONCE(helper)) {          // lockless read -- no helper_mutex

The write side initializes helper under helper_mutex, but previously
used a plain assignment:

        helper = kthread_run_worker(0, "scx_enable_helper");
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                 plain write -- KCSAN data race with READ_ONCE() above

Since READ_ONCE() on the fast path and the plain write on the
initialization path access the same variable without a common lock,
they constitute a data race. KCSAN requires that all sides of a
lock-free access use READ_ONCE()/WRITE_ONCE() consistently.

Use a temporary variable to stage the result of kthread_run_worker(),
and only WRITE_ONCE() into helper after confirming the pointer is
valid. This avoids a window where a concurrent caller on the fast path
could observe an ERR pointer via READ_ONCE(helper) before the error
check completes.

Fixes: b06ccbabe250 ("sched_ext: Fix starvation of scx_enable() under fair-class saturation")
Signed-off-by: zhidao su <suzhidao@xiaomi.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 174e3650d7fe..26a6ac2f8826 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5258,13 +5258,14 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	if (!READ_ONCE(helper)) {
 		mutex_lock(&helper_mutex);
 		if (!helper) {
-			helper = kthread_run_worker(0, "scx_enable_helper");
-			if (IS_ERR_OR_NULL(helper)) {
-				helper = NULL;
+			struct kthread_worker *w =
+				kthread_run_worker(0, "scx_enable_helper");
+			if (IS_ERR_OR_NULL(w)) {
 				mutex_unlock(&helper_mutex);
 				return -ENOMEM;
 			}
-			sched_set_fifo(helper->task);
+			sched_set_fifo(w->task);
+			WRITE_ONCE(helper, w);
 		}
 		mutex_unlock(&helper_mutex);
 	}
-- 
cgit v1.2.3


From 8b8f1d5e350acdf972b6b02e225d9e14c600f7ad Mon Sep 17 00:00:00 2001
From: Ryota Sakamoto <sakamo.ryota@gmail.com>
Date: Sun, 8 Mar 2026 18:06:20 +0900
Subject: kunit: Add documentation of --list_suites

Commit 60f3ada4174f ("kunit: Add --list_suites to show suites") introduced
the --list_suites option to kunit.py, but the update to the corresponding
run_wrapper documentation was omitted.

Add the missing description for --list_suites to keep the documentation in
sync with the tool's supported arguments.

Fixes: 60f3ada4174f ("kunit: Add --list_suites to show suites")
Signed-off-by: Ryota Sakamoto <sakamo.ryota@gmail.com>
Reviewed-by: David Gow <david@davidgow.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kunit/run_wrapper.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/dev-tools/kunit/run_wrapper.rst b/Documentation/dev-tools/kunit/run_wrapper.rst
index 3c0b585dcfff..770bb09a475a 100644
--- a/Documentation/dev-tools/kunit/run_wrapper.rst
+++ b/Documentation/dev-tools/kunit/run_wrapper.rst
@@ -336,6 +336,8 @@ command line arguments:
 - ``--list_tests_attr``: If set, lists all tests that will be run and all of their
   attributes.
 
+- ``--list_suites``: If set, lists all suites that will be run.
+
 Command-line completion
 ==============================
 
-- 
cgit v1.2.3


From 2f1763f62909ccb6386ac50350fa0abbf5bb16a9 Mon Sep 17 00:00:00 2001
From: Benoît Sevens <bsevens@google.com>
Date: Tue, 3 Mar 2026 13:58:28 +0000
Subject: HID: wacom: fix out-of-bounds read in wacom_intuos_bt_irq
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The wacom_intuos_bt_irq() function processes Bluetooth HID reports
without sufficient bounds checking. A maliciously crafted short report
can trigger an out-of-bounds read when copying data into the wacom
structure.

Specifically, report 0x03 requires at least 22 bytes to safely read
the processed data and battery status, while report 0x04 (which
falls through to 0x03) requires 32 bytes.

Add explicit length checks for these report IDs and log a warning if
a short report is received.

Signed-off-by: Benoît Sevens <bsevens@google.com>
Reviewed-by: Jason Gerecke <jason.gerecke@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_wac.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 9b2c710f8da1..da1f0ea85625 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -1208,10 +1208,20 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 
 	switch (data[0]) {
 	case 0x04:
+		if (len < 32) {
+			dev_warn(wacom->pen_input->dev.parent,
+				 "Report 0x04 too short: %zu bytes\n", len);
+			break;
+		}
 		wacom_intuos_bt_process_data(wacom, data + i);
 		i += 10;
 		fallthrough;
 	case 0x03:
+		if (i == 1 && len < 22) {
+			dev_warn(wacom->pen_input->dev.parent,
+				 "Report 0x03 too short: %zu bytes\n", len);
+			break;
+		}
 		wacom_intuos_bt_process_data(wacom, data + i);
 		i += 10;
 		wacom_intuos_bt_process_data(wacom, data + i);
-- 
cgit v1.2.3


From 111e2863372c322e836e0c896f6dd9cf4ee08c71 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 10 Mar 2026 02:01:34 +0800
Subject: spi: rockchip-sfc: Fix double-free in remove() callback

The driver uses devm_spi_register_controller() for registration, which
automatically unregisters the controller via devm cleanup when the
device is removed. The manual call to spi_unregister_controller() in
the remove() callback can lead to a double-free.

And to make sure controller is unregistered before DMA buffer is
unmapped, switch to use spi_register_controller() in probe().

Fixes: 8011709906d0 ("spi: rockchip-sfc: Support pm ops")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260310-sfc-v2-1-67fab04b097f@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-rockchip-sfc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-rockchip-sfc.c b/drivers/spi/spi-rockchip-sfc.c
index 2990bf85ee47..174995042f53 100644
--- a/drivers/spi/spi-rockchip-sfc.c
+++ b/drivers/spi/spi-rockchip-sfc.c
@@ -711,7 +711,7 @@ static int rockchip_sfc_probe(struct platform_device *pdev)
 		}
 	}
 
-	ret = devm_spi_register_controller(dev, host);
+	ret = spi_register_controller(host);
 	if (ret)
 		goto err_register;
 
-- 
cgit v1.2.3


From 785d4625d3e05bb0ac536ff4fd74d096cfe51714 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:20:14 -0600
Subject: io_uring/bpf_filter: use bpf_prog_run_pin_on_cpu() to prevent
 migration

Since the caller, __io_uring_run_bpf_filters(), doesn't prevent
migration, it should use the migration disabling variant for running
the BPF program.

Fixes: d42eb05e60fe ("io_uring: add support for BPF filtering for opcode restrictions")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/bpf_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/bpf_filter.c b/io_uring/bpf_filter.c
index 28a23e92ee81..9cc44764e0ac 100644
--- a/io_uring/bpf_filter.c
+++ b/io_uring/bpf_filter.c
@@ -85,7 +85,7 @@ int __io_uring_run_bpf_filters(struct io_bpf_filter __rcu **filters,
 	do {
 		if (filter == &dummy_filter)
 			return -EACCES;
-		ret = bpf_prog_run(filter->prog, &bpf_ctx);
+		ret = bpf_prog_run_pin_on_cpu(filter->prog, &bpf_ctx);
 		if (!ret)
 			return -EACCES;
 		filter = filter->next;
-- 
cgit v1.2.3


From a76e30c2479ce6ffa2aa6c8a8462897afc82bc90 Mon Sep 17 00:00:00 2001
From: Charles Mirabile <cmirabil@redhat.com>
Date: Sat, 7 Mar 2026 23:43:30 -0500
Subject: kbuild: Delete .builtin-dtbs.S when running make clean

The makefile tries to delete a file named ".builtin-dtb.S" but the file
created by scripts/Makefile.vmlinux is actually called ".builtin-dtbs.S".

Fixes: 654102df2ac2a ("kbuild: add generic support for built-in boot DTBs")
Cc: stable@vger.kernel.org
Signed-off-by: Charles Mirabile <cmirabil@redhat.com>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Link: https://patch.msgid.link/20260308044338.181403-1-cmirabil@redhat.com
[nathan: Small commit message adjustments]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 2b15f0b4a0cb..2317618fd074 100644
--- a/Makefile
+++ b/Makefile
@@ -1650,7 +1650,7 @@ CLEAN_FILES += vmlinux.symvers modules-only.symvers \
 	       modules.builtin.ranges vmlinux.o.map vmlinux.unstripped \
 	       compile_commands.json rust/test \
 	       rust-project.json .vmlinux.objs .vmlinux.export.c \
-               .builtin-dtbs-list .builtin-dtb.S
+               .builtin-dtbs-list .builtin-dtbs.S
 
 # Directories & files removed with 'make mrproper'
 MRPROPER_FILES += include/config include/generated          \
-- 
cgit v1.2.3


From 3b4a3a00de8770f3a60c1fa483921ce37415132d Mon Sep 17 00:00:00 2001
From: Weizhao Ouyang <o451686892@gmail.com>
Date: Mon, 9 Mar 2026 20:15:05 +0800
Subject: scripts: kconfig: merge_config.sh: fix unexpected operator warning

Fix a warning for:

$ ./scripts/kconfig/merge_config.sh .config extra.config
Using .config as base
Merging extra.config
./scripts/kconfig/merge_config.sh: 384: [: false: unexpected operator

The shellcheck report is also attached:

if [ "$STRICT" == "true" ] && [ "$STRICT_MODE_VIOLATED" == "true" ]; then
               ^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.
                                                        ^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.

Fixes: dfc97e1c5da5 ("scripts: kconfig: merge_config.sh: use awk in checks too")
Signed-off-by: Weizhao Ouyang <o451686892@gmail.com>
Reviewed-by: Mikko Rapeli <mikko.rapeli@linaro.org>
Link: https://patch.msgid.link/20260309121505.40454-1-o451686892@gmail.com
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/kconfig/merge_config.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index 735e1de450c6..073c6bec5245 100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -381,7 +381,7 @@ END {
 	STRICT_MODE_VIOLATED=true
 fi
 
-if [ "$STRICT" == "true" ] && [ "$STRICT_MODE_VIOLATED" == "true" ]; then
+if [ "$STRICT" = "true" ] && [ "$STRICT_MODE_VIOLATED" = "true" ]; then
 	echo "Requested and effective config differ"
 	exit 1
 fi
-- 
cgit v1.2.3


From 652a3017c485937cdb0706aa54f9dc74312c97a7 Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Fri, 6 Mar 2026 14:42:54 +0800
Subject: crypto: arm64/aes-neonbs - Move key expansion off the stack

aesbs_setkey() and aesbs_cbc_ctr_setkey() allocate struct crypto_aes_ctx
on the stack. On arm64, the kernel-mode NEON context is also stored on
the stack, causing the combined frame size to exceed 1024 bytes and
triggering -Wframe-larger-than= warnings.

Allocate struct crypto_aes_ctx on the heap instead and use
kfree_sensitive() to ensure the key material is zeroed on free.
Use a goto-based cleanup path to ensure kfree_sensitive() is always
called.

Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Fixes: 4fa617cc6851 ("arm64/fpsimd: Allocate kernel mode FP/SIMD buffers on the stack")
Link: https://lore.kernel.org/r/20260306064254.2079274-1-yphbchou0911@gmail.com
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 arch/arm64/crypto/aes-neonbs-glue.c | 37 +++++++++++++++++++++++--------------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index cb87c8fc66b3..00530b291010 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -76,19 +76,24 @@ static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			unsigned int key_len)
 {
 	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_aes_ctx rk;
+	struct crypto_aes_ctx *rk;
 	int err;
 
-	err = aes_expandkey(&rk, in_key, key_len);
+	rk = kmalloc(sizeof(*rk), GFP_KERNEL);
+	if (!rk)
+		return -ENOMEM;
+
+	err = aes_expandkey(rk, in_key, key_len);
 	if (err)
-		return err;
+		goto out;
 
 	ctx->rounds = 6 + key_len / 4;
 
 	scoped_ksimd()
-		aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
-
-	return 0;
+		aesbs_convert_key(ctx->rk, rk->key_enc, ctx->rounds);
+out:
+	kfree_sensitive(rk);
+	return err;
 }
 
 static int __ecb_crypt(struct skcipher_request *req,
@@ -133,22 +138,26 @@ static int aesbs_cbc_ctr_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
 	struct aesbs_cbc_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct crypto_aes_ctx rk;
+	struct crypto_aes_ctx *rk;
 	int err;
 
-	err = aes_expandkey(&rk, in_key, key_len);
+	rk = kmalloc(sizeof(*rk), GFP_KERNEL);
+	if (!rk)
+		return -ENOMEM;
+
+	err = aes_expandkey(rk, in_key, key_len);
 	if (err)
-		return err;
+		goto out;
 
 	ctx->key.rounds = 6 + key_len / 4;
 
-	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
+	memcpy(ctx->enc, rk->key_enc, sizeof(ctx->enc));
 
 	scoped_ksimd()
-		aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
-	memzero_explicit(&rk, sizeof(rk));
-
-	return 0;
+		aesbs_convert_key(ctx->key.rk, rk->key_enc, ctx->key.rounds);
+out:
+	kfree_sensitive(rk);
+	return err;
 }
 
 static int cbc_encrypt(struct skcipher_request *req)
-- 
cgit v1.2.3


From 3c99c9f0ed60582c1c9852b685d78d5d3a50de63 Mon Sep 17 00:00:00 2001
From: "matteo.cotifava" <cotifavamatteo@gmail.com>
Date: Mon, 9 Mar 2026 22:54:11 +0100
Subject: ASoC: soc-core: drop delayed_work_pending() check before flush

The delayed_work_pending() check before flush_delayed_work() in
soc_free_pcm_runtime() is unnecessary and racy. flush_delayed_work()
is safe to call unconditionally - it is a no-op when no work is
pending. Remove the check.

The original check was added by commit 9c9b65203492 ("ASoC: core:
only flush inited work during free") but delayed_work_pending()
followed by flush_delayed_work() has a time-of-check/time-of-use
window where work can become pending between the two calls.

Fixes: 9c9b65203492 ("ASoC: core: only flush inited work during free")
Signed-off-by: Matteo Cotifava <cotifavamatteo@gmail.com>
Link: https://patch.msgid.link/20260309215412.545628-2-cotifavamatteo@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d0fffef65daf..e5ac8ae1665d 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -462,8 +462,7 @@ static void soc_free_pcm_runtime(struct snd_soc_pcm_runtime *rtd)
 
 	list_del(&rtd->list);
 
-	if (delayed_work_pending(&rtd->delayed_work))
-		flush_delayed_work(&rtd->delayed_work);
+	flush_delayed_work(&rtd->delayed_work);
 	snd_soc_pcm_component_free(rtd);
 
 	/*
-- 
cgit v1.2.3


From 95bc5c225513fc3c4ce169563fb5e3929fbb938b Mon Sep 17 00:00:00 2001
From: "matteo.cotifava" <cotifavamatteo@gmail.com>
Date: Mon, 9 Mar 2026 22:54:12 +0100
Subject: ASoC: soc-core: flush delayed work before removing DAIs and widgets

When a sound card is unbound while a PCM stream is open, a
use-after-free can occur in snd_soc_dapm_stream_event(), called from
the close_delayed_work workqueue handler.

During unbind, snd_soc_unbind_card() flushes delayed work and then
calls soc_cleanup_card_resources(). Inside cleanup,
snd_card_disconnect_sync() releases all PCM file descriptors, and
the resulting PCM close path can call snd_soc_dapm_stream_stop()
which schedules new delayed work with a pmdown_time timer delay.
Since this happens after the flush in snd_soc_unbind_card(), the
new work is not caught. soc_remove_link_components() then frees
DAPM widgets before this work fires, leading to the use-after-free.

The existing flush in soc_free_pcm_runtime() also cannot help as it
runs after soc_remove_link_components() has already freed the widgets.

Add a flush in soc_cleanup_card_resources() after
snd_card_disconnect_sync() (after which no new PCM closes can
schedule further delayed work) and before soc_remove_link_dais()
and soc_remove_link_components() (which tear down the structures the
delayed work accesses).

Fixes: e894efef9ac7 ("ASoC: core: add support to card rebind")
Signed-off-by: Matteo Cotifava <cotifavamatteo@gmail.com>
Link: https://patch.msgid.link/20260309215412.545628-3-cotifavamatteo@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index e5ac8ae1665d..cf826c2a8b59 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2121,6 +2121,9 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card)
 	for_each_card_rtds(card, rtd)
 		if (rtd->initialized)
 			snd_soc_link_exit(rtd);
+	/* flush delayed work before removing DAIs and DAPM widgets */
+	snd_soc_flush_all_delayed_work(card);
+
 	/* remove and free each DAI */
 	soc_remove_link_dais(card);
 	soc_remove_link_components(card);
-- 
cgit v1.2.3


From 9063d7e2615f4a7ab321de6b520e23d370e58816 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 15 Jan 2026 15:30:50 +0100
Subject: apparmor: validate DFA start states are in bounds in unpack_pdb

Start states are read from untrusted data and used as indexes into the
DFA state tables. The aa_dfa_next() function call in unpack_pdb() will
access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds
the number of states in the DFA, this results in an out-of-bound read.

==================================================================
 BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360
 Read of size 4 at addr ffff88811956fb90 by task su/1097
 ...

Reject policies with out-of-bounds start states during unpacking
to prevent the issue.

Fixes: ad5ff3db53c6 ("AppArmor: Add ability to load extended policy")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 1769417a9962..ba5d40dbeb24 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -1010,7 +1010,17 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy,
 		if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
 			/* default start state for xmatch and file dfa */
 			pdb->start[AA_CLASS_FILE] = DFA_START;
-		}	/* setup class index */
+		}
+
+		size_t state_count = pdb->dfa->tables[YYTD_ID_BASE]->td_lolen;
+
+		if (pdb->start[0] >= state_count ||
+		    pdb->start[AA_CLASS_FILE] >= state_count) {
+			*info = "invalid dfa start state";
+			goto fail;
+		}
+
+		/* setup class index */
 		for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
 			pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
 						    i);
-- 
cgit v1.2.3


From e38c55d9f834e5b848bfed0f5c586aaf45acb825 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Tue, 20 Jan 2026 15:24:04 +0100
Subject: apparmor: fix memory leak in verify_header

The function sets `*ns = NULL` on every call, leaking the namespace
string allocated in previous iterations when multiple profiles are
unpacked. This also breaks namespace consistency checking since *ns
is always NULL when the comparison is made.

Remove the incorrect assignment.
The caller (aa_unpack) initializes *ns to NULL once before the loop,
which is sufficient.

Fixes: dd51c8485763 ("apparmor: provide base for multiple profiles to be replaced at once")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy_unpack.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index ba5d40dbeb24..5d90ea55de82 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -1419,7 +1419,6 @@ static int verify_header(struct aa_ext *e, int required, const char **ns)
 {
 	int error = -EPROTONOSUPPORT;
 	const char *name = NULL;
-	*ns = NULL;
 
 	/* get the interface version */
 	if (!aa_unpack_u32(e, &e->version, "version")) {
-- 
cgit v1.2.3


From ab09264660f9de5d05d1ef4e225aa447c63a8747 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Tue, 13 Jan 2026 09:09:43 +0100
Subject: apparmor: replace recursive profile removal with iterative approach

The profile removal code uses recursion when removing nested profiles,
which can lead to kernel stack exhaustion and system crashes.

Reproducer:
  $ pf='a'; for ((i=0; i<1024; i++)); do
      echo -e "profile $pf { \n }" | apparmor_parser -K -a;
      pf="$pf//x";
  done
  $ echo -n a > /sys/kernel/security/apparmor/.remove

Replace the recursive __aa_profile_list_release() approach with an
iterative approach in __remove_profile(). The function repeatedly
finds and removes leaf profiles until the entire subtree is removed,
maintaining the same removal semantic without recursion.

Fixes: c88d4c7b049e ("AppArmor: core policy routines")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy.c | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 9108d74c6b46..566821852592 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -191,19 +191,43 @@ static void __list_remove_profile(struct aa_profile *profile)
 }
 
 /**
- * __remove_profile - remove old profile, and children
- * @profile: profile to be replaced  (NOT NULL)
+ * __remove_profile - remove profile, and children
+ * @profile: profile to be removed  (NOT NULL)
  *
  * Requires: namespace list lock be held, or list not be shared
  */
 static void __remove_profile(struct aa_profile *profile)
 {
+	struct aa_profile *curr, *to_remove;
+
 	AA_BUG(!profile);
 	AA_BUG(!profile->ns);
 	AA_BUG(!mutex_is_locked(&profile->ns->lock));
 
 	/* release any children lists first */
-	__aa_profile_list_release(&profile->base.profiles);
+	if (!list_empty(&profile->base.profiles)) {
+		curr = list_first_entry(&profile->base.profiles, struct aa_profile, base.list);
+
+		while (curr != profile) {
+
+			while (!list_empty(&curr->base.profiles))
+				curr = list_first_entry(&curr->base.profiles,
+							struct aa_profile, base.list);
+
+			to_remove = curr;
+			if (!list_is_last(&to_remove->base.list,
+					  &aa_deref_parent(curr)->base.profiles))
+				curr = list_next_entry(to_remove, base.list);
+			else
+				curr = aa_deref_parent(curr);
+
+			/* released by free_profile */
+			aa_label_remove(&to_remove->label);
+			__aafs_profile_rmdir(to_remove);
+			__list_remove_profile(to_remove);
+		}
+	}
+
 	/* released by free_profile */
 	aa_label_remove(&profile->label);
 	__aafs_profile_rmdir(profile);
-- 
cgit v1.2.3


From 306039414932c80f8420695a24d4fe10c84ccfb2 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 3 Mar 2026 11:08:02 -0800
Subject: apparmor: fix: limit the number of levels of policy namespaces

Currently the number of policy namespaces is not bounded relying on
the user namespace limit. However policy namespaces aren't strictly
tied to user namespaces and it is possible to create them and nest
them arbitrarily deep which can be used to exhaust system resource.

Hard cap policy namespaces to the same depth as user namespaces.

Fixes: c88d4c7b049e8 ("AppArmor: core policy routines")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Ryan Lee <ryan.lee@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/include/policy_ns.h | 2 ++
 security/apparmor/policy_ns.c         | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/security/apparmor/include/policy_ns.h b/security/apparmor/include/policy_ns.h
index d646070fd966..cc6e84151812 100644
--- a/security/apparmor/include/policy_ns.h
+++ b/security/apparmor/include/policy_ns.h
@@ -18,6 +18,8 @@
 #include "label.h"
 #include "policy.h"
 
+/* Match max depth of user namespaces */
+#define MAX_NS_DEPTH 32
 
 /* struct aa_ns_acct - accounting of profiles in namespace
  * @max_size: maximum space allowed for all profiles in namespace
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
index 01b653a3609b..5a907a875d8f 100644
--- a/security/apparmor/policy_ns.c
+++ b/security/apparmor/policy_ns.c
@@ -223,6 +223,8 @@ static struct aa_ns *__aa_create_ns(struct aa_ns *parent, const char *name,
 	AA_BUG(!name);
 	AA_BUG(!mutex_is_locked(&parent->lock));
 
+	if (parent->level > MAX_NS_DEPTH)
+		return ERR_PTR(-ENOSPC);
 	ns = alloc_ns(parent->base.hname, name);
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
-- 
cgit v1.2.3


From 8756b68edae37ff546c02091989a4ceab3f20abd Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 29 Jan 2026 17:08:25 +0100
Subject: apparmor: fix side-effect bug in match_char() macro usage

The match_char() macro evaluates its character parameter multiple
times when traversing differential encoding chains. When invoked
with *str++, the string pointer advances on each iteration of the
inner do-while loop, causing the DFA to check different characters
at each iteration and therefore skip input characters.
This results in out-of-bounds reads when the pointer advances past
the input buffer boundary.

[   94.984676] ==================================================================
[   94.985301] BUG: KASAN: slab-out-of-bounds in aa_dfa_match+0x5ae/0x760
[   94.985655] Read of size 1 at addr ffff888100342000 by task file/976

[   94.986319] CPU: 7 UID: 1000 PID: 976 Comm: file Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy)
[   94.986322] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   94.986329] Call Trace:
[   94.986341]  <TASK>
[   94.986347]  dump_stack_lvl+0x5e/0x80
[   94.986374]  print_report+0xc8/0x270
[   94.986384]  ? aa_dfa_match+0x5ae/0x760
[   94.986388]  kasan_report+0x118/0x150
[   94.986401]  ? aa_dfa_match+0x5ae/0x760
[   94.986405]  aa_dfa_match+0x5ae/0x760
[   94.986408]  __aa_path_perm+0x131/0x400
[   94.986418]  aa_path_perm+0x219/0x2f0
[   94.986424]  apparmor_file_open+0x345/0x570
[   94.986431]  security_file_open+0x5c/0x140
[   94.986442]  do_dentry_open+0x2f6/0x1120
[   94.986450]  vfs_open+0x38/0x2b0
[   94.986453]  ? may_open+0x1e2/0x2b0
[   94.986466]  path_openat+0x231b/0x2b30
[   94.986469]  ? __x64_sys_openat+0xf8/0x130
[   94.986477]  do_file_open+0x19d/0x360
[   94.986487]  do_sys_openat2+0x98/0x100
[   94.986491]  __x64_sys_openat+0xf8/0x130
[   94.986499]  do_syscall_64+0x8e/0x660
[   94.986515]  ? count_memcg_events+0x15f/0x3c0
[   94.986526]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986540]  ? handle_mm_fault+0x1639/0x1ef0
[   94.986551]  ? vma_start_read+0xf0/0x320
[   94.986558]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986561]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986563]  ? fpregs_assert_state_consistent+0x50/0xe0
[   94.986572]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986574]  ? arch_exit_to_user_mode_prepare+0x9/0xb0
[   94.986587]  ? srso_alias_return_thunk+0x5/0xfbef5
[   94.986588]  ? irqentry_exit+0x3c/0x590
[   94.986595]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   94.986597] RIP: 0033:0x7fda4a79c3ea

Fix by extracting the character value before invoking match_char,
ensuring single evaluation per outer loop.

Fixes: 074c1cd798cb ("apparmor: dfa move character match into a macro")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/match.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 8fa0a1494acd..30c46b119869 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -463,13 +463,18 @@ aa_state_t aa_dfa_match_len(struct aa_dfa *dfa, aa_state_t start,
 	if (dfa->tables[YYTD_ID_EC]) {
 		/* Equivalence class table defined */
 		u8 *equiv = EQUIV_TABLE(dfa);
-		for (; len; len--)
-			match_char(state, def, base, next, check,
-				   equiv[(u8) *str++]);
+		for (; len; len--) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
 	} else {
 		/* default is direct to next state */
-		for (; len; len--)
-			match_char(state, def, base, next, check, (u8) *str++);
+		for (; len; len--) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
 	}
 
 	return state;
@@ -503,13 +508,18 @@ aa_state_t aa_dfa_match(struct aa_dfa *dfa, aa_state_t start, const char *str)
 		/* Equivalence class table defined */
 		u8 *equiv = EQUIV_TABLE(dfa);
 		/* default is direct to next state */
-		while (*str)
-			match_char(state, def, base, next, check,
-				   equiv[(u8) *str++]);
+		while (*str) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
 	} else {
 		/* default is direct to next state */
-		while (*str)
-			match_char(state, def, base, next, check, (u8) *str++);
+		while (*str) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
 	}
 
 	return state;
-- 
cgit v1.2.3


From d352873bbefa7eb39995239d0b44ccdf8aaa79a4 Mon Sep 17 00:00:00 2001
From: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Date: Thu, 29 Jan 2026 16:51:11 +0100
Subject: apparmor: fix missing bounds check on DEFAULT table in verify_dfa()

The verify_dfa() function only checks DEFAULT_TABLE bounds when the state
is not differentially encoded.

When the verification loop traverses the differential encoding chain,
it reads k = DEFAULT_TABLE[j] and uses k as an array index without
validation. A malformed DFA with DEFAULT_TABLE[j] >= state_count,
therefore, causes both out-of-bounds reads and writes.

[   57.179855] ==================================================================
[   57.180549] BUG: KASAN: slab-out-of-bounds in verify_dfa+0x59a/0x660
[   57.180904] Read of size 4 at addr ffff888100eadec4 by task su/993

[   57.181554] CPU: 1 UID: 0 PID: 993 Comm: su Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy)
[   57.181558] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   57.181563] Call Trace:
[   57.181572]  <TASK>
[   57.181577]  dump_stack_lvl+0x5e/0x80
[   57.181596]  print_report+0xc8/0x270
[   57.181605]  ? verify_dfa+0x59a/0x660
[   57.181608]  kasan_report+0x118/0x150
[   57.181620]  ? verify_dfa+0x59a/0x660
[   57.181623]  verify_dfa+0x59a/0x660
[   57.181627]  aa_dfa_unpack+0x1610/0x1740
[   57.181629]  ? __kmalloc_cache_noprof+0x1d0/0x470
[   57.181640]  unpack_pdb+0x86d/0x46b0
[   57.181647]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181653]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181656]  ? aa_unpack_nameX+0x1a8/0x300
[   57.181659]  aa_unpack+0x20b0/0x4c30
[   57.181662]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181664]  ? stack_depot_save_flags+0x33/0x700
[   57.181681]  ? kasan_save_track+0x4f/0x80
[   57.181683]  ? kasan_save_track+0x3e/0x80
[   57.181686]  ? __kasan_kmalloc+0x93/0xb0
[   57.181688]  ? __kvmalloc_node_noprof+0x44a/0x780
[   57.181693]  ? aa_simple_write_to_buffer+0x54/0x130
[   57.181697]  ? policy_update+0x154/0x330
[   57.181704]  aa_replace_profiles+0x15a/0x1dd0
[   57.181707]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181710]  ? __kvmalloc_node_noprof+0x44a/0x780
[   57.181712]  ? aa_loaddata_alloc+0x77/0x140
[   57.181715]  ? srso_alias_return_thunk+0x5/0xfbef5
[   57.181717]  ? _copy_from_user+0x2a/0x70
[   57.181730]  policy_update+0x17a/0x330
[   57.181733]  profile_replace+0x153/0x1a0
[   57.181735]  ? rw_verify_area+0x93/0x2d0
[   57.181740]  vfs_write+0x235/0xab0
[   57.181745]  ksys_write+0xb0/0x170
[   57.181748]  do_syscall_64+0x8e/0x660
[   57.181762]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   57.181765] RIP: 0033:0x7f6192792eb2

Remove the MATCH_FLAG_DIFF_ENCODE condition to validate all DEFAULT_TABLE
entries unconditionally.

Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: Massimiliano Pellizzer <massimiliano.pellizzer@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/match.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 30c46b119869..2aad2cbed565 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -160,9 +160,10 @@ static int verify_dfa(struct aa_dfa *dfa)
 	if (state_count == 0)
 		goto out;
 	for (i = 0; i < state_count; i++) {
-		if (!(BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE) &&
-		    (DEFAULT_TABLE(dfa)[i] >= state_count))
+		if (DEFAULT_TABLE(dfa)[i] >= state_count) {
+			pr_err("AppArmor DFA default state out of bounds");
 			goto out;
+		}
 		if (BASE_TABLE(dfa)[i] & MATCH_FLAGS_INVALID) {
 			pr_err("AppArmor DFA state with invalid match flags");
 			goto out;
-- 
cgit v1.2.3


From 5df0c44e8f5f619d3beb871207aded7c78414502 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Wed, 10 Sep 2025 06:22:17 -0700
Subject: apparmor: Fix double free of ns_name in aa_replace_profiles()

if ns_name is NULL after
1071         error = aa_unpack(udata, &lh, &ns_name);

and if ent->ns_name contains an ns_name in
1089                 } else if (ent->ns_name) {

then ns_name is assigned the ent->ns_name
1095                         ns_name = ent->ns_name;

however ent->ns_name is freed at
1262                 aa_load_ent_free(ent);

and then again when freeing ns_name at
1270         kfree(ns_name);

Fix this by NULLing out ent->ns_name after it is transferred to ns_name

Fixes: 145a0ef21c8e9 ("apparmor: fix blob compression when ns is forced on a policy load
")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/policy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 566821852592..4476515d97b1 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -1166,6 +1166,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 				goto fail;
 			}
 			ns_name = ent->ns_name;
+			ent->ns_name = NULL;
 		} else
 			count++;
 	}
-- 
cgit v1.2.3


From 6601e13e82841879406bf9f369032656f441a425 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Fri, 7 Nov 2025 08:36:04 -0800
Subject: apparmor: fix unprivileged local user can do privileged policy
 management

An unprivileged local user can load, replace, and remove profiles by
opening the apparmorfs interfaces, via a confused deputy attack, by
passing the opened fd to a privileged process, and getting the
privileged process to write to the interface.

This does require a privileged target that can be manipulated to do
the write for the unprivileged process, but once such access is
achieved full policy management is possible and all the possible
implications that implies: removing confinement, DoS of system or
target applications by denying all execution, by-passing the
unprivileged user namespace restriction, to exploiting kernel bugs for
a local privilege escalation.

The policy management interface can not have its permissions simply
changed from 0666 to 0600 because non-root processes need to be able
to load policy to different policy namespaces.

Instead ensure the task writing the interface has privileges that
are a subset of the task that opened the interface. This is already
done via policy for confined processes, but unconfined can delegate
access to the opened fd, by-passing the usual policy check.

Fixes: b7fd2c0340eac ("apparmor: add per policy ns .load, .replace, .remove interface files")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c     | 16 +++++++++-------
 security/apparmor/include/policy.h |  2 +-
 security/apparmor/policy.c         | 34 +++++++++++++++++++++++++++++++++-
 3 files changed, 43 insertions(+), 9 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 2f84bd23edb6..81e57666a56e 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -417,7 +417,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 }
 
 static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
-			     loff_t *pos, struct aa_ns *ns)
+			     loff_t *pos, struct aa_ns *ns,
+			     const struct cred *ocred)
 {
 	struct aa_loaddata *data;
 	struct aa_label *label;
@@ -428,7 +429,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	/* high level check about policy management - fine grained in
 	 * below after unpack
 	 */
-	error = aa_may_manage_policy(current_cred(), label, ns, mask);
+	error = aa_may_manage_policy(current_cred(), label, ns, ocred, mask);
 	if (error)
 		goto end_section;
 
@@ -449,7 +450,8 @@ static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
 			    loff_t *pos)
 {
 	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
-	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns);
+	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns,
+				  f->f_cred);
 
 	aa_put_ns(ns);
 
@@ -467,7 +469,7 @@ static ssize_t profile_replace(struct file *f, const char __user *buf,
 {
 	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY,
-				  buf, size, pos, ns);
+				  buf, size, pos, ns, f->f_cred);
 	aa_put_ns(ns);
 
 	return error;
@@ -492,7 +494,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	 * below after unpack
 	 */
 	error = aa_may_manage_policy(current_cred(), label, ns,
-				     AA_MAY_REMOVE_POLICY);
+				     f->f_cred, AA_MAY_REMOVE_POLICY);
 	if (error)
 		goto out;
 
@@ -1830,7 +1832,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir,
 	int error;
 
 	label = begin_current_label_crit_section();
-	error = aa_may_manage_policy(current_cred(), label, NULL,
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
 				     AA_MAY_LOAD_POLICY);
 	end_current_label_crit_section(label);
 	if (error)
@@ -1880,7 +1882,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry)
 	int error;
 
 	label = begin_current_label_crit_section();
-	error = aa_may_manage_policy(current_cred(), label, NULL,
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
 				     AA_MAY_LOAD_POLICY);
 	end_current_label_crit_section(label);
 	if (error)
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index 5115ebae2661..fda9e75b8879 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -443,7 +443,7 @@ bool aa_policy_admin_capable(const struct cred *subj_cred,
 			     struct aa_label *label, struct aa_ns *ns);
 int aa_may_manage_policy(const struct cred *subj_cred,
 			 struct aa_label *label, struct aa_ns *ns,
-			 u32 mask);
+			 const struct cred *ocred, u32 mask);
 bool aa_current_policy_view_capable(struct aa_ns *ns);
 bool aa_current_policy_admin_capable(struct aa_ns *ns);
 
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index 4476515d97b1..e2bebf14a4d0 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -942,17 +942,44 @@ bool aa_current_policy_admin_capable(struct aa_ns *ns)
 	return res;
 }
 
+static bool is_subset_of_obj_privilege(const struct cred *cred,
+				       struct aa_label *label,
+				       const struct cred *ocred)
+{
+	if (cred == ocred)
+		return true;
+
+	if (!aa_label_is_subset(label, cred_label(ocred)))
+		return false;
+	/* don't allow crossing userns for now */
+	if (cred->user_ns != ocred->user_ns)
+		return false;
+	if (!cap_issubset(cred->cap_inheritable, ocred->cap_inheritable))
+		return false;
+	if (!cap_issubset(cred->cap_permitted, ocred->cap_permitted))
+		return false;
+	if (!cap_issubset(cred->cap_effective, ocred->cap_effective))
+		return false;
+	if (!cap_issubset(cred->cap_bset, ocred->cap_bset))
+		return false;
+	if (!cap_issubset(cred->cap_ambient, ocred->cap_ambient))
+		return false;
+	return true;
+}
+
+
 /**
  * aa_may_manage_policy - can the current task manage policy
  * @subj_cred: subjects cred
  * @label: label to check if it can manage policy
  * @ns: namespace being managed by @label (may be NULL if @label's ns)
+ * @ocred: object cred if request is coming from an open object
  * @mask: contains the policy manipulation operation being done
  *
  * Returns: 0 if the task is allowed to manipulate policy else error
  */
 int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label,
-			 struct aa_ns *ns, u32 mask)
+			 struct aa_ns *ns, const struct cred *ocred, u32 mask)
 {
 	const char *op;
 
@@ -968,6 +995,11 @@ int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label,
 		return audit_policy(label, op, NULL, NULL, "policy_locked",
 				    -EACCES);
 
+	if (ocred && !is_subset_of_obj_privilege(subj_cred, label, ocred))
+		return audit_policy(label, op, NULL, NULL,
+				    "not privileged for target profile",
+				    -EACCES);
+
 	if (!aa_policy_admin_capable(subj_cred, label, ns))
 		return audit_policy(label, op, NULL, NULL, "not policy admin",
 				    -EACCES);
-- 
cgit v1.2.3


From 39440b137546a3aa383cfdabc605fb73811b6093 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Fri, 17 Oct 2025 01:53:00 -0700
Subject: apparmor: fix differential encoding verification

Differential encoding allows loops to be created if it is abused. To
prevent this the unpack should verify that a diff-encode chain
terminates.

Unfortunately the differential encode verification had two bugs.

1. it conflated states that had gone through check and already been
   marked, with states that were currently being checked and marked.
   This means that loops in the current chain being verified are treated
   as a chain that has already been verified.

2. the order bailout on already checked states compared current chain
   check iterators j,k instead of using the outer loop iterator i.
   Meaning a step backwards in states in the current chain verification
   was being mistaken for moving to an already verified state.

Move to a double mark scheme where already verified states get a
different mark, than the current chain being kept. This enables us
to also drop the backwards verification check that was the cause of
the second error as any already verified state is already marked.

Fixes: 031dcc8f4e84 ("apparmor: dfa add support for state differential encoding")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/include/match.h |  1 +
 security/apparmor/match.c         | 23 +++++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h
index 0dde8eda3d1a..7accb1c39849 100644
--- a/security/apparmor/include/match.h
+++ b/security/apparmor/include/match.h
@@ -185,6 +185,7 @@ static inline void aa_put_dfa(struct aa_dfa *dfa)
 #define MATCH_FLAG_DIFF_ENCODE 0x80000000
 #define MARK_DIFF_ENCODE 0x40000000
 #define MATCH_FLAG_OOB_TRANSITION 0x20000000
+#define MARK_DIFF_ENCODE_VERIFIED 0x10000000
 #define MATCH_FLAGS_MASK 0xff000000
 #define MATCH_FLAGS_VALID (MATCH_FLAG_DIFF_ENCODE | MATCH_FLAG_OOB_TRANSITION)
 #define MATCH_FLAGS_INVALID (MATCH_FLAGS_MASK & ~MATCH_FLAGS_VALID)
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
index 2aad2cbed565..e9fac67e5178 100644
--- a/security/apparmor/match.c
+++ b/security/apparmor/match.c
@@ -202,16 +202,31 @@ static int verify_dfa(struct aa_dfa *dfa)
 		size_t j, k;
 
 		for (j = i;
-		     (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) &&
-		     !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE);
+		     ((BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) &&
+		      !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE_VERIFIED));
 		     j = k) {
+			if (BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE)
+				/* loop in current chain */
+				goto out;
 			k = DEFAULT_TABLE(dfa)[j];
 			if (j == k)
+				/* self loop */
 				goto out;
-			if (k < j)
-				break;		/* already verified */
 			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE;
 		}
+		/* move mark to verified */
+		for (j = i;
+		     (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE);
+		     j = k) {
+			k = DEFAULT_TABLE(dfa)[j];
+			if (j < i)
+				/* jumps to state/chain that has been
+				 * verified
+				 */
+				break;
+			BASE_TABLE(dfa)[j] &= ~MARK_DIFF_ENCODE;
+			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE_VERIFIED;
+		}
 	}
 	error = 0;
 
-- 
cgit v1.2.3


From a0b7091c4de45a7325c8780e6934a894f92ac86b Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Tue, 24 Feb 2026 10:20:02 -0800
Subject: apparmor: fix race on rawdata dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a race condition that leads to a use-after-free situation:
because the rawdata inodes are not refcounted, an attacker can start
open()ing one of the rawdata files, and at the same time remove the
last reference to this rawdata (by removing the corresponding profile,
for example), which frees its struct aa_loaddata; as a result, when
seq_rawdata_open() is reached, i_private is a dangling pointer and
freed memory is accessed.

The rawdata inodes weren't refcounted to avoid a circular refcount and
were supposed to be held by the profile rawdata reference.  However
during profile removal there is a window where the vfs and profile
destruction race, resulting in the use after free.

Fix this by moving to a double refcount scheme. Where the profile
refcount on rawdata is used to break the circular dependency. Allowing
for freeing of the rawdata once all inode references to the rawdata
are put.

Fixes: 5d5182cae401 ("apparmor: move to per loaddata files, instead of replicating in profiles")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Maxime Bélair <maxime.belair@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Tested-by: Salvatore Bonaccorso <carnil@debian.org>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c            | 35 +++++++++------
 security/apparmor/include/policy_unpack.h | 71 +++++++++++++++++++------------
 security/apparmor/policy.c                | 12 +++---
 security/apparmor/policy_unpack.c         | 32 ++++++++++----
 4 files changed, 93 insertions(+), 57 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 81e57666a56e..7a6ca7c5500d 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -79,7 +79,7 @@ static void rawdata_f_data_free(struct rawdata_f_data *private)
 	if (!private)
 		return;
 
-	aa_put_loaddata(private->loaddata);
+	aa_put_i_loaddata(private->loaddata);
 	kvfree(private);
 }
 
@@ -409,7 +409,8 @@ static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
 
 	data->size = copy_size;
 	if (copy_from_user(data->data, userbuf, copy_size)) {
-		aa_put_loaddata(data);
+		/* trigger free - don't need to put pcount */
+		aa_put_i_loaddata(data);
 		return ERR_PTR(-EFAULT);
 	}
 
@@ -437,7 +438,10 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
 	error = PTR_ERR(data);
 	if (!IS_ERR(data)) {
 		error = aa_replace_profiles(ns, label, mask, data);
-		aa_put_loaddata(data);
+		/* put pcount, which will put count and free if no
+		 * profiles referencing it.
+		 */
+		aa_put_profile_loaddata(data);
 	}
 end_section:
 	end_current_label_crit_section(label);
@@ -508,7 +512,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	if (!IS_ERR(data)) {
 		data->data[size] = 0;
 		error = aa_remove_profiles(ns, label, data->data, size);
-		aa_put_loaddata(data);
+		aa_put_profile_loaddata(data);
 	}
  out:
 	end_current_label_crit_section(label);
@@ -1255,18 +1259,17 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = {	      \
 static int seq_rawdata_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_loaddata *data = __aa_get_loaddata(inode->i_private);
+	struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private);
 	int error;
 
 	if (!data)
-		/* lost race this ent is being reaped */
 		return -ENOENT;
 
 	error = single_open(file, show, data);
 	if (error) {
 		AA_BUG(file->private_data &&
 		       ((struct seq_file *)file->private_data)->private);
-		aa_put_loaddata(data);
+		aa_put_i_loaddata(data);
 	}
 
 	return error;
@@ -1277,7 +1280,7 @@ static int seq_rawdata_release(struct inode *inode, struct file *file)
 	struct seq_file *seq = (struct seq_file *) file->private_data;
 
 	if (seq)
-		aa_put_loaddata(seq->private);
+		aa_put_i_loaddata(seq->private);
 
 	return single_release(inode, file);
 }
@@ -1389,9 +1392,8 @@ static int rawdata_open(struct inode *inode, struct file *file)
 	if (!aa_current_policy_view_capable(NULL))
 		return -EACCES;
 
-	loaddata = __aa_get_loaddata(inode->i_private);
+	loaddata = aa_get_i_loaddata(inode->i_private);
 	if (!loaddata)
-		/* lost race: this entry is being reaped */
 		return -ENOENT;
 
 	private = rawdata_f_data_alloc(loaddata->size);
@@ -1416,7 +1418,7 @@ fail_decompress:
 	return error;
 
 fail_private_alloc:
-	aa_put_loaddata(loaddata);
+	aa_put_i_loaddata(loaddata);
 	return error;
 }
 
@@ -1433,9 +1435,9 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata)
 
 	for (i = 0; i < AAFS_LOADDATA_NDENTS; i++) {
 		if (!IS_ERR_OR_NULL(rawdata->dents[i])) {
-			/* no refcounts on i_private */
 			aafs_remove(rawdata->dents[i]);
 			rawdata->dents[i] = NULL;
+			aa_put_i_loaddata(rawdata);
 		}
 	}
 }
@@ -1474,18 +1476,21 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	if (IS_ERR(dir))
 		/* ->name freed when rawdata freed */
 		return PTR_ERR(dir);
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DIR] = dir;
 
 	dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata,
 				      &seq_rawdata_abi_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_ABI] = dent;
 
 	dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata,
 				      &seq_rawdata_revision_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
@@ -1493,6 +1498,7 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 					      rawdata, &seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
+		aa_get_i_loaddata(rawdata);
 		rawdata->dents[AAFS_LOADDATA_HASH] = dent;
 	}
 
@@ -1501,24 +1507,25 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 				&seq_rawdata_compressed_size_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent;
 
 	dent = aafs_create_file("raw_data", S_IFREG | 0444,
 				      dir, rawdata, &rawdata_fops);
 	if (IS_ERR(dent))
 		goto fail;
+	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DATA] = dent;
 	d_inode(dent)->i_size = rawdata->size;
 
 	rawdata->ns = aa_get_ns(ns);
 	list_add(&rawdata->list, &ns->rawdata_list);
-	/* no refcount on inode rawdata */
 
 	return 0;
 
 fail:
 	remove_rawdata_dents(rawdata);
-
+	aa_put_i_loaddata(rawdata);
 	return PTR_ERR(dent);
 }
 #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
index a6f4611ee50c..4f800fbb805a 100644
--- a/security/apparmor/include/policy_unpack.h
+++ b/security/apparmor/include/policy_unpack.h
@@ -87,17 +87,29 @@ struct aa_ext {
 	u32 version;
 };
 
-/*
- * struct aa_loaddata - buffer of policy raw_data set
+/* struct aa_loaddata - buffer of policy raw_data set
+ * @count: inode/filesystem refcount - use aa_get_i_loaddata()
+ * @pcount: profile refcount - use aa_get_profile_loaddata()
+ * @list: list the loaddata is on
+ * @work: used to do a delayed cleanup
+ * @dents: refs to dents created in aafs
+ * @ns: the namespace this loaddata was loaded into
+ * @name:
+ * @size: the size of the data that was loaded
+ * @compressed_size: the size of the data when it is compressed
+ * @revision: unique revision count that this data was loaded as
+ * @abi: the abi number the loaddata uses
+ * @hash: a hash of the loaddata, used to help dedup data
  *
- * there is no loaddata ref for being on ns list, nor a ref from
- * d_inode(@dentry) when grab a ref from these, @ns->lock must be held
- * && __aa_get_loaddata() needs to be used, and the return value
- * checked, if NULL the loaddata is already being reaped and should be
- * considered dead.
+ * There is no loaddata ref for being on ns->rawdata_list, so
+ * @ns->lock must be held when walking the list. Dentries and
+ * inode opens hold refs on @count; profiles hold refs on @pcount.
+ * When the last @pcount drops, do_ploaddata_rmfs() removes the
+ * fs entries and drops the associated @count ref.
  */
 struct aa_loaddata {
 	struct kref count;
+	struct kref pcount;
 	struct list_head list;
 	struct work_struct work;
 	struct dentry *dents[AAFS_LOADDATA_NDENTS];
@@ -119,52 +131,55 @@ struct aa_loaddata {
 int aa_unpack(struct aa_loaddata *udata, struct list_head *lh, const char **ns);
 
 /**
- * __aa_get_loaddata - get a reference count to uncounted data reference
+ * aa_get_loaddata - get a reference count from a counted data reference
  * @data: reference to get a count on
  *
- * Returns: pointer to reference OR NULL if race is lost and reference is
- *          being repeated.
- * Requires: @data->ns->lock held, and the return code MUST be checked
- *
- * Use only from inode->i_private and @data->list found references
+ * Returns: pointer to reference
+ * Requires: @data to have a valid reference count on it. It is a bug
+ *           if the race to reap can be encountered when it is used.
  */
 static inline struct aa_loaddata *
-__aa_get_loaddata(struct aa_loaddata *data)
+aa_get_i_loaddata(struct aa_loaddata *data)
 {
-	if (data && kref_get_unless_zero(&(data->count)))
-		return data;
 
-	return NULL;
+	if (data)
+		kref_get(&(data->count));
+	return data;
 }
 
+
 /**
- * aa_get_loaddata - get a reference count from a counted data reference
+ * aa_get_profile_loaddata - get a profile reference count on loaddata
  * @data: reference to get a count on
  *
- * Returns: point to reference
- * Requires: @data to have a valid reference count on it. It is a bug
- *           if the race to reap can be encountered when it is used.
+ * Returns: pointer to reference
+ * Requires: @data to have a valid reference count on it.
  */
 static inline struct aa_loaddata *
-aa_get_loaddata(struct aa_loaddata *data)
+aa_get_profile_loaddata(struct aa_loaddata *data)
 {
-	struct aa_loaddata *tmp = __aa_get_loaddata(data);
-
-	AA_BUG(data && !tmp);
-
-	return tmp;
+	if (data)
+		kref_get(&(data->pcount));
+	return data;
 }
 
 void __aa_loaddata_update(struct aa_loaddata *data, long revision);
 bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r);
 void aa_loaddata_kref(struct kref *kref);
+void aa_ploaddata_kref(struct kref *kref);
 struct aa_loaddata *aa_loaddata_alloc(size_t size);
-static inline void aa_put_loaddata(struct aa_loaddata *data)
+static inline void aa_put_i_loaddata(struct aa_loaddata *data)
 {
 	if (data)
 		kref_put(&data->count, aa_loaddata_kref);
 }
 
+static inline void aa_put_profile_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_put(&data->pcount, aa_ploaddata_kref);
+}
+
 #if IS_ENABLED(CONFIG_KUNIT)
 bool aa_inbounds(struct aa_ext *e, size_t size);
 size_t aa_unpack_u16_chunk(struct aa_ext *e, char **chunk);
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
index e2bebf14a4d0..b6a5eb4021db 100644
--- a/security/apparmor/policy.c
+++ b/security/apparmor/policy.c
@@ -350,7 +350,7 @@ void aa_free_profile(struct aa_profile *profile)
 	}
 
 	kfree_sensitive(profile->hash);
-	aa_put_loaddata(profile->rawdata);
+	aa_put_profile_loaddata(profile->rawdata);
 	aa_label_destroy(&profile->label);
 
 	kfree_sensitive(profile);
@@ -1171,7 +1171,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 	LIST_HEAD(lh);
 
 	op = mask & AA_MAY_REPLACE_POLICY ? OP_PROF_REPL : OP_PROF_LOAD;
-	aa_get_loaddata(udata);
+	aa_get_profile_loaddata(udata);
 	/* released below */
 	error = aa_unpack(udata, &lh, &ns_name);
 	if (error)
@@ -1223,10 +1223,10 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 			if (aa_rawdata_eq(rawdata_ent, udata)) {
 				struct aa_loaddata *tmp;
 
-				tmp = __aa_get_loaddata(rawdata_ent);
+				tmp = aa_get_profile_loaddata(rawdata_ent);
 				/* check we didn't fail the race */
 				if (tmp) {
-					aa_put_loaddata(udata);
+					aa_put_profile_loaddata(udata);
 					udata = tmp;
 					break;
 				}
@@ -1239,7 +1239,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 		struct aa_profile *p;
 
 		if (aa_g_export_binary)
-			ent->new->rawdata = aa_get_loaddata(udata);
+			ent->new->rawdata = aa_get_profile_loaddata(udata);
 		error = __lookup_replace(ns, ent->new->base.hname,
 					 !(mask & AA_MAY_REPLACE_POLICY),
 					 &ent->old, &info);
@@ -1372,7 +1372,7 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
 
 out:
 	aa_put_ns(ns);
-	aa_put_loaddata(udata);
+	aa_put_profile_loaddata(udata);
 	kfree(ns_name);
 
 	if (error)
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 5d90ea55de82..69a040194e36 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -109,34 +109,47 @@ bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r)
 	return memcmp(l->data, r->data, r->compressed_size ?: r->size) == 0;
 }
 
+static void do_loaddata_free(struct aa_loaddata *d)
+{
+	kfree_sensitive(d->hash);
+	kfree_sensitive(d->name);
+	kvfree(d->data);
+	kfree_sensitive(d);
+}
+
+void aa_loaddata_kref(struct kref *kref)
+{
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count);
+
+	do_loaddata_free(d);
+}
+
 /*
  * need to take the ns mutex lock which is NOT safe most places that
  * put_loaddata is called, so we have to delay freeing it
  */
-static void do_loaddata_free(struct work_struct *work)
+static void do_ploaddata_rmfs(struct work_struct *work)
 {
 	struct aa_loaddata *d = container_of(work, struct aa_loaddata, work);
 	struct aa_ns *ns = aa_get_ns(d->ns);
 
 	if (ns) {
 		mutex_lock_nested(&ns->lock, ns->level);
+		/* remove fs ref to loaddata */
 		__aa_fs_remove_rawdata(d);
 		mutex_unlock(&ns->lock);
 		aa_put_ns(ns);
 	}
-
-	kfree_sensitive(d->hash);
-	kfree_sensitive(d->name);
-	kvfree(d->data);
-	kfree_sensitive(d);
+	/* called by dropping last pcount, so drop its associated icount */
+	aa_put_i_loaddata(d);
 }
 
-void aa_loaddata_kref(struct kref *kref)
+void aa_ploaddata_kref(struct kref *kref)
 {
-	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count);
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, pcount);
 
 	if (d) {
-		INIT_WORK(&d->work, do_loaddata_free);
+		INIT_WORK(&d->work, do_ploaddata_rmfs);
 		schedule_work(&d->work);
 	}
 }
@@ -154,6 +167,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size)
 		return ERR_PTR(-ENOMEM);
 	}
 	kref_init(&d->count);
+	kref_init(&d->pcount);
 	INIT_LIST_HEAD(&d->list);
 
 	return d;
-- 
cgit v1.2.3


From 8e135b8aee5a06c52a4347a5a6d51223c6f36ba3 Mon Sep 17 00:00:00 2001
From: John Johansen <john.johansen@canonical.com>
Date: Sun, 1 Mar 2026 16:10:51 -0800
Subject: apparmor: fix race between freeing data and fs accessing it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AppArmor was putting the reference to i_private data on its end after
removing the original entry from the file system. However the inode
can aand does live beyond that point and it is possible that some of
the fs call back functions will be invoked after the reference has
been put, which results in a race between freeing the data and
accessing it through the fs.

While the rawdata/loaddata is the most likely candidate to fail the
race, as it has the fewest references. If properly crafted it might be
possible to trigger a race for the other types stored in i_private.

Fix this by moving the put of i_private referenced data to the correct
place which is during inode eviction.

Fixes: c961ee5f21b20 ("apparmor: convert from securityfs to apparmorfs for policy ns files")
Reported-by: Qualys Security Advisory <qsa@qualys.com>
Reviewed-by: Georgia Garcia <georgia.garcia@canonical.com>
Reviewed-by: Maxime Bélair <maxime.belair@canonical.com>
Reviewed-by: Cengiz Can <cengiz.can@canonical.com>
Signed-off-by: John Johansen <john.johansen@canonical.com>
---
 security/apparmor/apparmorfs.c            | 194 ++++++++++++++++++------------
 security/apparmor/include/label.h         |  16 +--
 security/apparmor/include/lib.h           |  12 ++
 security/apparmor/include/policy.h        |   8 +-
 security/apparmor/include/policy_unpack.h |   6 +-
 security/apparmor/label.c                 |  12 +-
 security/apparmor/policy_unpack.c         |   6 +-
 7 files changed, 153 insertions(+), 101 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 7a6ca7c5500d..242c71b3fb6e 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -32,6 +32,7 @@
 #include "include/crypto.h"
 #include "include/ipc.h"
 #include "include/label.h"
+#include "include/lib.h"
 #include "include/policy.h"
 #include "include/policy_ns.h"
 #include "include/resource.h"
@@ -62,6 +63,7 @@
  * securityfs and apparmorfs filesystems.
  */
 
+#define IREF_POISON 101
 
 /*
  * support fns
@@ -153,6 +155,71 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
 	return 0;
 }
 
+static struct aa_ns *get_ns_common_ref(struct aa_common_ref *ref)
+{
+	if (ref) {
+		struct aa_label *reflabel = container_of(ref, struct aa_label,
+							 count);
+		return aa_get_ns(labels_ns(reflabel));
+	}
+
+	return NULL;
+}
+
+static struct aa_proxy *get_proxy_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_proxy(container_of(ref, struct aa_proxy, count));
+
+	return NULL;
+}
+
+static struct aa_loaddata *get_loaddata_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_i_loaddata(container_of(ref, struct aa_loaddata,
+						      count));
+	return NULL;
+}
+
+static void aa_put_common_ref(struct aa_common_ref *ref)
+{
+	if (!ref)
+		return;
+
+	switch (ref->reftype) {
+	case REF_RAWDATA:
+		aa_put_i_loaddata(container_of(ref, struct aa_loaddata,
+					       count));
+		break;
+	case REF_PROXY:
+		aa_put_proxy(container_of(ref, struct aa_proxy,
+					  count));
+		break;
+	case REF_NS:
+		/* ns count is held on its unconfined label */
+		aa_put_ns(labels_ns(container_of(ref, struct aa_label, count)));
+		break;
+	default:
+		AA_BUG(true, "unknown refcount type");
+		break;
+	}
+}
+
+static void aa_get_common_ref(struct aa_common_ref *ref)
+{
+	kref_get(&ref->count);
+}
+
+static void aafs_evict(struct inode *inode)
+{
+	struct aa_common_ref *ref = inode->i_private;
+
+	clear_inode(inode);
+	aa_put_common_ref(ref);
+	inode->i_private = (void *) IREF_POISON;
+}
+
 static void aafs_free_inode(struct inode *inode)
 {
 	if (S_ISLNK(inode->i_mode))
@@ -162,6 +229,7 @@ static void aafs_free_inode(struct inode *inode)
 
 static const struct super_operations aafs_super_ops = {
 	.statfs = simple_statfs,
+	.evict_inode = aafs_evict,
 	.free_inode = aafs_free_inode,
 	.show_path = aafs_show_path,
 };
@@ -262,7 +330,8 @@ static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry,
  * aafs_remove(). Will return ERR_PTR on failure.
  */
 static struct dentry *aafs_create(const char *name, umode_t mode,
-				  struct dentry *parent, void *data, void *link,
+				  struct dentry *parent,
+				  struct aa_common_ref *data, void *link,
 				  const struct file_operations *fops,
 				  const struct inode_operations *iops)
 {
@@ -299,6 +368,9 @@ static struct dentry *aafs_create(const char *name, umode_t mode,
 		goto fail_dentry;
 	inode_unlock(dir);
 
+	if (data)
+		aa_get_common_ref(data);
+
 	return dentry;
 
 fail_dentry:
@@ -323,7 +395,8 @@ fail_lock:
  * see aafs_create
  */
 static struct dentry *aafs_create_file(const char *name, umode_t mode,
-				       struct dentry *parent, void *data,
+				       struct dentry *parent,
+				       struct aa_common_ref *data,
 				       const struct file_operations *fops)
 {
 	return aafs_create(name, mode, parent, data, NULL, fops, NULL);
@@ -453,7 +526,7 @@ end_section:
 static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
 			    loff_t *pos)
 {
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns,
 				  f->f_cred);
 
@@ -471,7 +544,7 @@ static const struct file_operations aa_fs_profile_load = {
 static ssize_t profile_replace(struct file *f, const char __user *buf,
 			       size_t size, loff_t *pos)
 {
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 	int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY,
 				  buf, size, pos, ns, f->f_cred);
 	aa_put_ns(ns);
@@ -491,7 +564,7 @@ static ssize_t profile_remove(struct file *f, const char __user *buf,
 	struct aa_loaddata *data;
 	struct aa_label *label;
 	ssize_t error;
-	struct aa_ns *ns = aa_get_ns(f->f_inode->i_private);
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
 
 	label = begin_current_label_crit_section();
 	/* high level check about policy management - fine grained in
@@ -581,7 +654,7 @@ static int ns_revision_open(struct inode *inode, struct file *file)
 	if (!rev)
 		return -ENOMEM;
 
-	rev->ns = aa_get_ns(inode->i_private);
+	rev->ns = get_ns_common_ref(inode->i_private);
 	if (!rev->ns)
 		rev->ns = aa_get_current_ns();
 	file->private_data = rev;
@@ -1067,7 +1140,7 @@ static const struct file_operations seq_profile_ ##NAME ##_fops = {	      \
 static int seq_profile_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_proxy *proxy = aa_get_proxy(inode->i_private);
+	struct aa_proxy *proxy = get_proxy_common_ref(inode->i_private);
 	int error = single_open(file, show, proxy);
 
 	if (error) {
@@ -1259,7 +1332,7 @@ static const struct file_operations seq_rawdata_ ##NAME ##_fops = {	      \
 static int seq_rawdata_open(struct inode *inode, struct file *file,
 			    int (*show)(struct seq_file *, void *))
 {
-	struct aa_loaddata *data = aa_get_i_loaddata(inode->i_private);
+	struct aa_loaddata *data = get_loaddata_common_ref(inode->i_private);
 	int error;
 
 	if (!data)
@@ -1392,7 +1465,7 @@ static int rawdata_open(struct inode *inode, struct file *file)
 	if (!aa_current_policy_view_capable(NULL))
 		return -EACCES;
 
-	loaddata = aa_get_i_loaddata(inode->i_private);
+	loaddata = get_loaddata_common_ref(inode->i_private);
 	if (!loaddata)
 		return -ENOENT;
 
@@ -1437,7 +1510,6 @@ static void remove_rawdata_dents(struct aa_loaddata *rawdata)
 		if (!IS_ERR_OR_NULL(rawdata->dents[i])) {
 			aafs_remove(rawdata->dents[i]);
 			rawdata->dents[i] = NULL;
-			aa_put_i_loaddata(rawdata);
 		}
 	}
 }
@@ -1476,45 +1548,41 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 	if (IS_ERR(dir))
 		/* ->name freed when rawdata freed */
 		return PTR_ERR(dir);
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DIR] = dir;
 
-	dent = aafs_create_file("abi", S_IFREG | 0444, dir, rawdata,
+	dent = aafs_create_file("abi", S_IFREG | 0444, dir, &rawdata->count,
 				      &seq_rawdata_abi_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_ABI] = dent;
 
-	dent = aafs_create_file("revision", S_IFREG | 0444, dir, rawdata,
-				      &seq_rawdata_revision_fops);
+	dent = aafs_create_file("revision", S_IFREG | 0444, dir,
+				&rawdata->count,
+				&seq_rawdata_revision_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
 
 	if (aa_g_hash_policy) {
 		dent = aafs_create_file("sha256", S_IFREG | 0444, dir,
-					      rawdata, &seq_rawdata_hash_fops);
+					&rawdata->count,
+					&seq_rawdata_hash_fops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_i_loaddata(rawdata);
 		rawdata->dents[AAFS_LOADDATA_HASH] = dent;
 	}
 
 	dent = aafs_create_file("compressed_size", S_IFREG | 0444, dir,
-				rawdata,
+				&rawdata->count,
 				&seq_rawdata_compressed_size_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent;
 
-	dent = aafs_create_file("raw_data", S_IFREG | 0444,
-				      dir, rawdata, &rawdata_fops);
+	dent = aafs_create_file("raw_data", S_IFREG | 0444, dir,
+				&rawdata->count, &rawdata_fops);
 	if (IS_ERR(dent))
 		goto fail;
-	aa_get_i_loaddata(rawdata);
 	rawdata->dents[AAFS_LOADDATA_DATA] = dent;
 	d_inode(dent)->i_size = rawdata->size;
 
@@ -1525,7 +1593,6 @@ int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
 
 fail:
 	remove_rawdata_dents(rawdata);
-	aa_put_i_loaddata(rawdata);
 	return PTR_ERR(dent);
 }
 #endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
@@ -1549,13 +1616,10 @@ void __aafs_profile_rmdir(struct aa_profile *profile)
 		__aafs_profile_rmdir(child);
 
 	for (i = AAFS_PROF_SIZEOF - 1; i >= 0; --i) {
-		struct aa_proxy *proxy;
 		if (!profile->dents[i])
 			continue;
 
-		proxy = d_inode(profile->dents[i])->i_private;
 		aafs_remove(profile->dents[i]);
-		aa_put_proxy(proxy);
 		profile->dents[i] = NULL;
 	}
 }
@@ -1589,14 +1653,7 @@ static struct dentry *create_profile_file(struct dentry *dir, const char *name,
 					  struct aa_profile *profile,
 					  const struct file_operations *fops)
 {
-	struct aa_proxy *proxy = aa_get_proxy(profile->label.proxy);
-	struct dentry *dent;
-
-	dent = aafs_create_file(name, S_IFREG | 0444, dir, proxy, fops);
-	if (IS_ERR(dent))
-		aa_put_proxy(proxy);
-
-	return dent;
+	return aafs_create_file(name, S_IFREG | 0444, dir, &profile->label.proxy->count, fops);
 }
 
 #ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
@@ -1646,7 +1703,8 @@ static const char *rawdata_get_link_base(struct dentry *dentry,
 					 struct delayed_call *done,
 					 const char *name)
 {
-	struct aa_proxy *proxy = inode->i_private;
+	struct aa_common_ref *ref = inode->i_private;
+	struct aa_proxy *proxy = container_of(ref, struct aa_proxy, count);
 	struct aa_label *label;
 	struct aa_profile *profile;
 	char *target;
@@ -1788,27 +1846,24 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
 	if (profile->rawdata) {
 		if (aa_g_hash_policy) {
 			dent = aafs_create("raw_sha256", S_IFLNK | 0444, dir,
-					   profile->label.proxy, NULL, NULL,
-					   &rawdata_link_sha256_iops);
+					   &profile->label.proxy->count, NULL,
+					   NULL, &rawdata_link_sha256_iops);
 			if (IS_ERR(dent))
 				goto fail;
-			aa_get_proxy(profile->label.proxy);
 			profile->dents[AAFS_PROF_RAW_HASH] = dent;
 		}
 		dent = aafs_create("raw_abi", S_IFLNK | 0444, dir,
-				   profile->label.proxy, NULL, NULL,
+				   &profile->label.proxy->count, NULL, NULL,
 				   &rawdata_link_abi_iops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_proxy(profile->label.proxy);
 		profile->dents[AAFS_PROF_RAW_ABI] = dent;
 
 		dent = aafs_create("raw_data", S_IFLNK | 0444, dir,
-				   profile->label.proxy, NULL, NULL,
+				   &profile->label.proxy->count, NULL, NULL,
 				   &rawdata_link_data_iops);
 		if (IS_ERR(dent))
 			goto fail;
-		aa_get_proxy(profile->label.proxy);
 		profile->dents[AAFS_PROF_RAW_DATA] = dent;
 	}
 #endif /*CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
@@ -1845,7 +1900,7 @@ static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return ERR_PTR(error);
 
-	parent = aa_get_ns(dir->i_private);
+	parent = get_ns_common_ref(dir->i_private);
 	AA_BUG(d_inode(ns_subns_dir(parent)) != dir);
 
 	/* we have to unlock and then relock to get locking order right
@@ -1895,7 +1950,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry)
 	if (error)
 		return error;
 
-	parent = aa_get_ns(dir->i_private);
+	parent = get_ns_common_ref(dir->i_private);
 	/* rmdir calls the generic securityfs functions to remove files
 	 * from the apparmor dir. It is up to the apparmor ns locking
 	 * to avoid races.
@@ -1965,27 +2020,6 @@ void __aafs_ns_rmdir(struct aa_ns *ns)
 
 	__aa_fs_list_remove_rawdata(ns);
 
-	if (ns_subns_dir(ns)) {
-		sub = d_inode(ns_subns_dir(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subload(ns)) {
-		sub = d_inode(ns_subload(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subreplace(ns)) {
-		sub = d_inode(ns_subreplace(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subremove(ns)) {
-		sub = d_inode(ns_subremove(ns))->i_private;
-		aa_put_ns(sub);
-	}
-	if (ns_subrevision(ns)) {
-		sub = d_inode(ns_subrevision(ns))->i_private;
-		aa_put_ns(sub);
-	}
-
 	for (i = AAFS_NS_SIZEOF - 1; i >= 0; --i) {
 		aafs_remove(ns->dents[i]);
 		ns->dents[i] = NULL;
@@ -2010,40 +2044,40 @@ static int __aafs_ns_mkdir_entries(struct aa_ns *ns, struct dentry *dir)
 		return PTR_ERR(dent);
 	ns_subdata_dir(ns) = dent;
 
-	dent = aafs_create_file("revision", 0444, dir, ns,
+	dent = aafs_create_file("revision", 0444, dir,
+				&ns->unconfined->label.count,
 				&aa_fs_ns_revision_fops);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subrevision(ns) = dent;
 
-	dent = aafs_create_file(".load", 0640, dir, ns,
-				      &aa_fs_profile_load);
+	dent = aafs_create_file(".load", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_load);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subload(ns) = dent;
 
-	dent = aafs_create_file(".replace", 0640, dir, ns,
-				      &aa_fs_profile_replace);
+	dent = aafs_create_file(".replace", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_replace);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subreplace(ns) = dent;
 
-	dent = aafs_create_file(".remove", 0640, dir, ns,
-				      &aa_fs_profile_remove);
+	dent = aafs_create_file(".remove", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_remove);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subremove(ns) = dent;
 
 	  /* use create_dentry so we can supply private data */
-	dent = aafs_create("namespaces", S_IFDIR | 0755, dir, ns, NULL, NULL,
-			   &ns_dir_inode_operations);
+	dent = aafs_create("namespaces", S_IFDIR | 0755, dir,
+			   &ns->unconfined->label.count,
+			   NULL, NULL, &ns_dir_inode_operations);
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
-	aa_get_ns(ns);
 	ns_subns_dir(ns) = dent;
 
 	return 0;
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
index c0812dbc1b5b..335f21930702 100644
--- a/security/apparmor/include/label.h
+++ b/security/apparmor/include/label.h
@@ -102,7 +102,7 @@ enum label_flags {
 
 struct aa_label;
 struct aa_proxy {
-	struct kref count;
+	struct aa_common_ref count;
 	struct aa_label __rcu *label;
 };
 
@@ -125,7 +125,7 @@ struct label_it {
  * vec: vector of profiles comprising the compound label
  */
 struct aa_label {
-	struct kref count;
+	struct aa_common_ref count;
 	struct rb_node node;
 	struct rcu_head rcu;
 	struct aa_proxy *proxy;
@@ -357,7 +357,7 @@ int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules,
  */
 static inline struct aa_label *__aa_get_label(struct aa_label *l)
 {
-	if (l && kref_get_unless_zero(&l->count))
+	if (l && kref_get_unless_zero(&l->count.count))
 		return l;
 
 	return NULL;
@@ -366,7 +366,7 @@ static inline struct aa_label *__aa_get_label(struct aa_label *l)
 static inline struct aa_label *aa_get_label(struct aa_label *l)
 {
 	if (l)
-		kref_get(&(l->count));
+		kref_get(&(l->count.count));
 
 	return l;
 }
@@ -386,7 +386,7 @@ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l)
 	rcu_read_lock();
 	do {
 		c = rcu_dereference(*l);
-	} while (c && !kref_get_unless_zero(&c->count));
+	} while (c && !kref_get_unless_zero(&c->count.count));
 	rcu_read_unlock();
 
 	return c;
@@ -426,7 +426,7 @@ static inline struct aa_label *aa_get_newest_label(struct aa_label *l)
 static inline void aa_put_label(struct aa_label *l)
 {
 	if (l)
-		kref_put(&l->count, aa_label_kref);
+		kref_put(&l->count.count, aa_label_kref);
 }
 
 /* wrapper fn to indicate semantics of the check */
@@ -443,7 +443,7 @@ void aa_proxy_kref(struct kref *kref);
 static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy)
 {
 	if (proxy)
-		kref_get(&(proxy->count));
+		kref_get(&(proxy->count.count));
 
 	return proxy;
 }
@@ -451,7 +451,7 @@ static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy)
 static inline void aa_put_proxy(struct aa_proxy *proxy)
 {
 	if (proxy)
-		kref_put(&proxy->count, aa_proxy_kref);
+		kref_put(&proxy->count.count, aa_proxy_kref);
 }
 
 void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new);
diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h
index 1c5d1f60f6a7..8c6ce8484552 100644
--- a/security/apparmor/include/lib.h
+++ b/security/apparmor/include/lib.h
@@ -102,6 +102,18 @@ void aa_info_message(const char *str);
 /* Security blob offsets */
 extern struct lsm_blob_sizes apparmor_blob_sizes;
 
+enum reftype {
+	REF_NS,
+	REF_PROXY,
+	REF_RAWDATA,
+};
+
+/* common reference count used by data the shows up in aafs */
+struct aa_common_ref {
+	struct kref count;
+	enum reftype reftype;
+};
+
 /**
  * aa_strneq - compare null terminated @str to a non null terminated substring
  * @str: a null terminated string
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index fda9e75b8879..3895f8774a3f 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -379,7 +379,7 @@ static inline bool profile_mediates_safe(struct aa_profile *profile,
 static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
 {
 	if (p)
-		kref_get(&(p->label.count));
+		kref_get(&(p->label.count.count));
 
 	return p;
 }
@@ -393,7 +393,7 @@ static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
  */
 static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p)
 {
-	if (p && kref_get_unless_zero(&p->label.count))
+	if (p && kref_get_unless_zero(&p->label.count.count))
 		return p;
 
 	return NULL;
@@ -413,7 +413,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
 	rcu_read_lock();
 	do {
 		c = rcu_dereference(*p);
-	} while (c && !kref_get_unless_zero(&c->label.count));
+	} while (c && !kref_get_unless_zero(&c->label.count.count));
 	rcu_read_unlock();
 
 	return c;
@@ -426,7 +426,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
 static inline void aa_put_profile(struct aa_profile *p)
 {
 	if (p)
-		kref_put(&p->label.count, aa_label_kref);
+		kref_put(&p->label.count.count, aa_label_kref);
 }
 
 static inline int AUDIT_MODE(struct aa_profile *profile)
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
index 4f800fbb805a..e5a95dc4da1f 100644
--- a/security/apparmor/include/policy_unpack.h
+++ b/security/apparmor/include/policy_unpack.h
@@ -108,7 +108,7 @@ struct aa_ext {
  * fs entries and drops the associated @count ref.
  */
 struct aa_loaddata {
-	struct kref count;
+	struct aa_common_ref count;
 	struct kref pcount;
 	struct list_head list;
 	struct work_struct work;
@@ -143,7 +143,7 @@ aa_get_i_loaddata(struct aa_loaddata *data)
 {
 
 	if (data)
-		kref_get(&(data->count));
+		kref_get(&(data->count.count));
 	return data;
 }
 
@@ -171,7 +171,7 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size);
 static inline void aa_put_i_loaddata(struct aa_loaddata *data)
 {
 	if (data)
-		kref_put(&data->count, aa_loaddata_kref);
+		kref_put(&data->count.count, aa_loaddata_kref);
 }
 
 static inline void aa_put_profile_loaddata(struct aa_loaddata *data)
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index e478283bc514..3a721fdf1833 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -52,7 +52,8 @@ static void free_proxy(struct aa_proxy *proxy)
 
 void aa_proxy_kref(struct kref *kref)
 {
-	struct aa_proxy *proxy = container_of(kref, struct aa_proxy, count);
+	struct aa_proxy *proxy = container_of(kref, struct aa_proxy,
+					      count.count);
 
 	free_proxy(proxy);
 }
@@ -63,7 +64,8 @@ struct aa_proxy *aa_alloc_proxy(struct aa_label *label, gfp_t gfp)
 
 	new = kzalloc_obj(struct aa_proxy, gfp);
 	if (new) {
-		kref_init(&new->count);
+		kref_init(&new->count.count);
+		new->count.reftype = REF_PROXY;
 		rcu_assign_pointer(new->label, aa_get_label(label));
 	}
 	return new;
@@ -375,7 +377,8 @@ static void label_free_rcu(struct rcu_head *head)
 
 void aa_label_kref(struct kref *kref)
 {
-	struct aa_label *label = container_of(kref, struct aa_label, count);
+	struct aa_label *label = container_of(kref, struct aa_label,
+					      count.count);
 	struct aa_ns *ns = labels_ns(label);
 
 	if (!ns) {
@@ -412,7 +415,8 @@ bool aa_label_init(struct aa_label *label, int size, gfp_t gfp)
 
 	label->size = size;			/* doesn't include null */
 	label->vec[size] = NULL;		/* null terminate */
-	kref_init(&label->count);
+	kref_init(&label->count.count);
+	label->count.reftype = REF_NS;		/* for aafs purposes */
 	RB_CLEAR_NODE(&label->node);
 
 	return true;
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
index 69a040194e36..076d3ff14da6 100644
--- a/security/apparmor/policy_unpack.c
+++ b/security/apparmor/policy_unpack.c
@@ -119,7 +119,8 @@ static void do_loaddata_free(struct aa_loaddata *d)
 
 void aa_loaddata_kref(struct kref *kref)
 {
-	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count);
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata,
+					     count.count);
 
 	do_loaddata_free(d);
 }
@@ -166,7 +167,8 @@ struct aa_loaddata *aa_loaddata_alloc(size_t size)
 		kfree(d);
 		return ERR_PTR(-ENOMEM);
 	}
-	kref_init(&d->count);
+	kref_init(&d->count.count);
+	d->count.reftype = REF_RAWDATA;
 	kref_init(&d->pcount);
 	INIT_LIST_HEAD(&d->list);
 
-- 
cgit v1.2.3


From 4185b95f8a42d92d68c49289b4644546b51e252b Mon Sep 17 00:00:00 2001
From: Sen Wang <sen@ti.com>
Date: Sun, 8 Mar 2026 23:21:09 -0500
Subject: ASoC: simple-card-utils: fix graph_util_is_ports0() for DT overlays

graph_util_is_ports0() identifies DPCM front-end (ports@0) vs back-end
(ports@1) by calling of_get_child_by_name() to find the first "ports"
child and comparing pointers. This relies on child iteration order
matching DTS source order.

When the DPCM topology comes from a DT overlay, __of_attach_node()
inserts new children at the head of the sibling list, reversing the
order. of_get_child_by_name() then returns ports@1 instead of ports@0,
causing all front-end links to be classified as back-ends. The card
registers with no PCM devices.

Fix this by matching the unit address directly from the node name
instead of relying on sibling order.

Fixes: 92939252458f ("ASoC: simple-card-utils: add asoc_graph_is_ports0()")
Signed-off-by: Sen Wang <sen@ti.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/20260309042109.2576612-1-sen@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-card-utils.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index bdc02e85b089..9e5be0eaa77f 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1038,11 +1038,15 @@ int graph_util_is_ports0(struct device_node *np)
 	else
 		port = np;
 
-	struct device_node *ports  __free(device_node) = of_get_parent(port);
-	struct device_node *top    __free(device_node) = of_get_parent(ports);
-	struct device_node *ports0 __free(device_node) = of_get_child_by_name(top, "ports");
+	struct device_node *ports __free(device_node) = of_get_parent(port);
+	const char *at = strchr(kbasename(ports->full_name), '@');
 
-	return ports0 == ports;
+	/*
+	 * Since child iteration order may differ
+	 * between a base DT and DT overlays,
+	 * string match "ports" or "ports@0" in the node name instead.
+	 */
+	return !at || !strcmp(at, "@0");
 }
 EXPORT_SYMBOL_GPL(graph_util_is_ports0);
 
-- 
cgit v1.2.3


From 87d126852158467ab87d5cbc36ccfd3f15464a6c Mon Sep 17 00:00:00 2001
From: Álvaro Fernández Rojas <noltari@gmail.com>
Date: Fri, 6 Mar 2026 13:29:55 +0100
Subject: net: sfp: improve Huawei MA5671a fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the current sfp_fixup_ignore_tx_fault() fixup we ignore the TX_FAULT
signal, but we also need to apply sfp_fixup_ignore_los() in order to be
able to communicate with the module even if the fiber isn't connected for
configuration purposes.
This is needed for all the MA5671a firmwares, excluding the FS modded
firmware.

Fixes: 2069624dac19 ("net: sfp: Add tx-fault workaround for Huawei MA5671A SFP ONT")
Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260306125139.213637-1-noltari@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index f4bf53da3d4f..5db841377199 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -367,6 +367,12 @@ static void sfp_fixup_ignore_tx_fault(struct sfp *sfp)
 	sfp->state_ignore_mask |= SFP_F_TX_FAULT;
 }
 
+static void sfp_fixup_ignore_tx_fault_and_los(struct sfp *sfp)
+{
+	sfp_fixup_ignore_tx_fault(sfp);
+	sfp_fixup_ignore_los(sfp);
+}
+
 static void sfp_fixup_ignore_hw(struct sfp *sfp, unsigned int mask)
 {
 	sfp->state_hw_mask &= ~mask;
@@ -530,7 +536,7 @@ static const struct sfp_quirk sfp_quirks[] = {
 	// Huawei MA5671A can operate at 2500base-X, but report 1.2GBd NRZ in
 	// their EEPROM
 	SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex,
-		  sfp_fixup_ignore_tx_fault),
+		  sfp_fixup_ignore_tx_fault_and_los),
 
 	// Lantech 8330-262D-E and 8330-265D can operate at 2500base-X, but
 	// incorrectly report 2500MBd NRZ in their EEPROM.
-- 
cgit v1.2.3


From 288598d80a068a0e9281de35bcb4ce495f189e2a Mon Sep 17 00:00:00 2001
From: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
Date: Thu, 5 Mar 2026 22:40:06 -0500
Subject: serial: caif: hold tty->link reference in ldisc_open and ser_release

A reproducer triggers a KASAN slab-use-after-free in pty_write_room()
when caif_serial's TX path calls tty_write_room(). The faulting access
is on tty->link->port.

Hold an extra kref on tty->link for the lifetime of the caif_serial line
discipline: get it in ldisc_open() and drop it in ser_release(), and
also drop it on the ldisc_open() error path.

With this change applied, the reproducer no longer triggers the UAF in
my testing.

Link: https://gist.github.com/shuangpengbai/c898debad6bdf170a84be7e6b3d8707f
Link: https://lore.kernel.org/netdev/20260301220525.1546355-1-shuangpeng.kernel@gmail.com
Fixes: e31d5a05948e ("caif: tty's are kref objects so take a reference")
Signed-off-by: Shuangpeng Bai <shuangpeng.kernel@gmail.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://patch.msgid.link/20260306034006.3395740-1-shuangpeng.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/caif/caif_serial.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index b90890030751..1873d8287bb9 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -297,6 +297,7 @@ static void ser_release(struct work_struct *work)
 			dev_close(ser->dev);
 			unregister_netdevice(ser->dev);
 			debugfs_deinit(ser);
+			tty_kref_put(tty->link);
 			tty_kref_put(tty);
 		}
 		rtnl_unlock();
@@ -331,6 +332,7 @@ static int ldisc_open(struct tty_struct *tty)
 
 	ser = netdev_priv(dev);
 	ser->tty = tty_kref_get(tty);
+	tty_kref_get(tty->link);
 	ser->dev = dev;
 	debugfs_init(ser, tty);
 	tty->receive_room = 4096;
@@ -339,6 +341,7 @@ static int ldisc_open(struct tty_struct *tty)
 	rtnl_lock();
 	result = register_netdevice(dev);
 	if (result) {
+		tty_kref_put(tty->link);
 		tty_kref_put(tty);
 		rtnl_unlock();
 		free_netdev(dev);
-- 
cgit v1.2.3


From b2662e7593e94ae09b1cf7ee5f09160a3612bcb2 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Fri, 6 Mar 2026 18:38:20 -0500
Subject: net: nexthop: fix percpu use-after-free in remove_nh_grp_entry

When removing a nexthop from a group, remove_nh_grp_entry() publishes
the new group via rcu_assign_pointer() then immediately frees the
removed entry's percpu stats with free_percpu(). However, the
synchronize_net() grace period in the caller remove_nexthop_from_groups()
runs after the free. RCU readers that entered before the publish still
see the old group and can dereference the freed stats via
nh_grp_entry_stats_inc() -> get_cpu_ptr(nhge->stats), causing a
use-after-free on percpu memory.

Fix by deferring the free_percpu() until after synchronize_net() in the
caller. Removed entries are chained via nh_list onto a local deferred
free list. After the grace period completes and all RCU readers have
finished, the percpu stats are safely freed.

Fixes: f4676ea74b85 ("net: nexthop: Add nexthop group entry stats")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260306233821.196789-1-mehulrao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 1aa2b05ee8de..c942f1282236 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg)
 }
 
 static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
-				struct nl_info *nlinfo)
+				struct nl_info *nlinfo,
+				struct list_head *deferred_free)
 {
 	struct nh_grp_entry *nhges, *new_nhges;
 	struct nexthop *nhp = nhge->nh_parent;
@@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 	rcu_assign_pointer(nhp->nh_grp, newg);
 
 	list_del(&nhge->nh_list);
-	free_percpu(nhge->stats);
 	nexthop_put(nhge->nh);
+	list_add(&nhge->nh_list, deferred_free);
 
 	/* Removal of a NH from a resilient group is notified through
 	 * bucket notifications.
@@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 				       struct nl_info *nlinfo)
 {
 	struct nh_grp_entry *nhge, *tmp;
+	LIST_HEAD(deferred_free);
 
 	/* If there is nothing to do, let's avoid the costly call to
 	 * synchronize_net()
@@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 		return;
 
 	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
-		remove_nh_grp_entry(net, nhge, nlinfo);
+		remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free);
 
 	/* make sure all see the newly published array before releasing rtnl */
 	synchronize_net();
+
+	/* Now safe to free percpu stats — all RCU readers have finished */
+	list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) {
+		list_del(&nhge->nh_list);
+		free_percpu(nhge->stats);
+	}
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
-- 
cgit v1.2.3


From 7a85d370bbd0d55791ec57ea8ba13032410e8b9d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Mar 2026 12:06:07 +0000
Subject: MAINTAINERS: include/net/tc_wrapper.h belongs to TC subsystem

include/net/tc_wrapper.h changes should be reviewed by TC maintainers.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260307120607.3504191-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4f8e772808c7..07474a56821a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -25750,6 +25750,7 @@ F:	include/net/pkt_cls.h
 F:	include/net/pkt_sched.h
 F:	include/net/sch_priv.h
 F:	include/net/tc_act/
+F:	include/net/tc_wrapper.h
 F:	include/uapi/linux/pkt_cls.h
 F:	include/uapi/linux/pkt_sched.h
 F:	include/uapi/linux/tc_act/
-- 
cgit v1.2.3


From e4f774a0cc955ce762aec91c66915a6e15087ab7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:26 +0100
Subject: net: usb: lan78xx: fix silent drop of packets with checksum errors

Do not drop packets with checksum errors at the USB driver level;
pass them to the network stack.

Previously, the driver dropped all packets where the 'Receive Error
Detected' (RED) bit was set, regardless of the specific error type. This
caused packets with only IP or TCP/UDP checksum errors to be dropped
before reaching the kernel, preventing the network stack from accounting
for them or performing software fallback.

Add a mask for hard hardware errors to safely drop genuinely corrupt
frames, while allowing checksum-errored frames to pass with their
ip_summed field explicitly set to CHECKSUM_NONE.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 4 +++-
 drivers/net/usb/lan78xx.h | 3 +++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a0021df12fde..1c8f69190378 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3829,6 +3829,7 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 	 */
 	if (!(dev->net->features & NETIF_F_RXCSUM) ||
 	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+	    unlikely(rx_cmd_a & RX_CMD_A_CSE_MASK_) ||
 	    ((rx_cmd_a & RX_CMD_A_FVTG_) &&
 	     !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
 		skb->ip_summed = CHECKSUM_NONE;
@@ -3901,7 +3902,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb,
 			return 0;
 		}
 
-		if (unlikely(rx_cmd_a & RX_CMD_A_RED_)) {
+		if (unlikely(rx_cmd_a & RX_CMD_A_RED_) &&
+		    (rx_cmd_a & RX_CMD_A_RX_HARD_ERRS_MASK_)) {
 			netif_dbg(dev, rx_err, dev->net,
 				  "Error rx_cmd_a=0x%08x", rx_cmd_a);
 		} else {
diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h
index 968e5e5faee0..17a934acff3d 100644
--- a/drivers/net/usb/lan78xx.h
+++ b/drivers/net/usb/lan78xx.h
@@ -74,6 +74,9 @@
 #define RX_CMD_A_ICSM_			(0x00004000)
 #define RX_CMD_A_LEN_MASK_		(0x00003FFF)
 
+#define RX_CMD_A_RX_HARD_ERRS_MASK_ \
+	(RX_CMD_A_RX_ERRS_MASK_ & ~RX_CMD_A_CSE_MASK_)
+
 /* Rx Command B */
 #define RX_CMD_B_CSUM_SHIFT_		(16)
 #define RX_CMD_B_CSUM_MASK_		(0xFFFF0000)
-- 
cgit v1.2.3


From 50988747c30df47b73b787f234f746027cb7ec6c Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:27 +0100
Subject: net: usb: lan78xx: fix TX byte statistics for small packets

Account for hardware auto-padding in TX byte counters to reflect actual
wire traffic.

The LAN7850 hardware automatically pads undersized frames to the minimum
Ethernet frame length (ETH_ZLEN, 60 bytes). However, the driver tracks
the network statistics based on the unpadded socket buffer length. This
results in the tx_bytes counter under-reporting the actual physical
bytes placed on the Ethernet wire for small packets (like short ARP or
ICMP requests).

Use max_t() to ensure the transmission statistics accurately account for
the hardware-generated padding.

Fixes: d383216a7efe ("lan78xx: Introduce Tx URB processing improvements")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 1c8f69190378..507dbcf3b7b0 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4178,7 +4178,7 @@ static struct skb_data *lan78xx_tx_buf_fill(struct lan78xx_net *dev,
 		}
 
 		tx_data += len;
-		entry->length += len;
+		entry->length += max_t(unsigned int, len, ETH_ZLEN);
 		entry->num_of_packet += skb_shinfo(skb)->gso_segs ?: 1;
 
 		dev_kfree_skb_any(skb);
-- 
cgit v1.2.3


From d9cc0e440f0664f6f3e2c26e39ab9dd5f3badba7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:28 +0100
Subject: net: usb: lan78xx: skip LTM configuration for LAN7850

Do not configure Latency Tolerance Messaging (LTM) on USB 2.0 hardware.

The LAN7850 is a High-Speed (USB 2.0) only device and does not support
SuperSpeed features like LTM. Currently, the driver unconditionally
attempts to configure LTM registers during initialization. On the
LAN7850, these registers do not exist, resulting in writes to invalid
or undocumented memory space.

This issue was identified during a port to the regmap API with strict
register validation enabled. While no functional issues or crashes have
been observed from these invalid writes, bypassing LTM initialization
on the LAN7850 ensures the driver strictly adheres to the hardware's
valid register map.

Fixes: 55d7de9de6c3 ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 507dbcf3b7b0..f8558b87eaec 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3119,6 +3119,10 @@ static int lan78xx_init_ltm(struct lan78xx_net *dev)
 	int ret;
 	u32 buf;
 
+	/* LAN7850 is USB 2.0 and does not support LTM */
+	if (dev->chipid == ID_REV_CHIP_ID_7850_)
+		return 0;
+
 	ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
 	if (ret < 0)
 		goto init_ltm_failed;
-- 
cgit v1.2.3


From 312c816c6bc30342bc30dca0d6db617ab4d3ae4e Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 5 Mar 2026 15:34:29 +0100
Subject: net: usb: lan78xx: fix WARN in __netif_napi_del_locked on disconnect

Remove redundant netif_napi_del() call from disconnect path.

A WARN may be triggered in __netif_napi_del_locked() during USB device
disconnect:

  WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350

This happens because netif_napi_del() is called in the disconnect path while
NAPI is still enabled. However, it is not necessary to call netif_napi_del()
explicitly, since unregister_netdev() will handle NAPI teardown automatically
and safely. Removing the redundant call avoids triggering the warning.

Full trace:
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x000000c4. ret = -ENODEV
 lan78xx 1-1:1.0 enu1: Failed to set MAC down with error -ENODEV
 lan78xx 1-1:1.0 enu1: Link is Down
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x00000120. ret = -ENODEV
 ------------[ cut here ]------------
 WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350
 Modules linked in: flexcan can_dev fuse
 CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.0-rc2-00624-ge926949dab03 #9 PREEMPT
 Hardware name: SKOV IMX8MP CPU revC - bd500 (DT)
 Workqueue: usb_hub_wq hub_event
 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : __netif_napi_del_locked+0x2b4/0x350
 lr : __netif_napi_del_locked+0x7c/0x350
 sp : ffffffc085b673c0
 x29: ffffffc085b673c0 x28: ffffff800b7f2000 x27: ffffff800b7f20d8
 x26: ffffff80110bcf58 x25: ffffff80110bd978 x24: 1ffffff0022179eb
 x23: ffffff80110bc000 x22: ffffff800b7f5000 x21: ffffff80110bc000
 x20: ffffff80110bcf38 x19: ffffff80110bcf28 x18: dfffffc000000000
 x17: ffffffc081578940 x16: ffffffc08284cee0 x15: 0000000000000028
 x14: 0000000000000006 x13: 0000000000040000 x12: ffffffb0022179e8
 x11: 1ffffff0022179e7 x10: ffffffb0022179e7 x9 : dfffffc000000000
 x8 : 0000004ffdde8619 x7 : ffffff80110bcf3f x6 : 0000000000000001
 x5 : ffffff80110bcf38 x4 : ffffff80110bcf38 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 1ffffff0022179e7 x0 : 0000000000000000
 Call trace:
  __netif_napi_del_locked+0x2b4/0x350 (P)
  lan78xx_disconnect+0xf4/0x360
  usb_unbind_interface+0x158/0x718
  device_remove+0x100/0x150
  device_release_driver_internal+0x308/0x478
  device_release_driver+0x1c/0x30
  bus_remove_device+0x1a8/0x368
  device_del+0x2e0/0x7b0
  usb_disable_device+0x244/0x540
  usb_disconnect+0x220/0x758
  hub_event+0x105c/0x35e0
  process_one_work+0x760/0x17b0
  worker_thread+0x768/0xce8
  kthread+0x3bc/0x690
  ret_from_fork+0x10/0x20
 irq event stamp: 211604
 hardirqs last  enabled at (211603): [<ffffffc0828cc9ec>] _raw_spin_unlock_irqrestore+0x84/0x98
 hardirqs last disabled at (211604): [<ffffffc0828a9a84>] el1_dbg+0x24/0x80
 softirqs last  enabled at (211296): [<ffffffc080095f10>] handle_softirqs+0x820/0xbc8
 softirqs last disabled at (210993): [<ffffffc080010288>] __do_softirq+0x18/0x20
 ---[ end trace 0000000000000000 ]---
 lan78xx 1-1:1.0 enu1: failed to kill vid 0081/0

Fixes: e110bc825897 ("net: usb: lan78xx: Convert to PHYLINK for improved PHY and MAC management")
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20260305143429.530909-5-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f8558b87eaec..19cdf69fa589 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4552,8 +4552,6 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	phylink_disconnect_phy(dev->phylink);
 	rtnl_unlock();
 
-	netif_napi_del(&dev->napi);
-
 	unregister_netdev(net);
 
 	timer_shutdown_sync(&dev->stat_monitor);
-- 
cgit v1.2.3


From 0d9a60a0618d255530ca56072c5f39eb58e1ed4a Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Fri, 6 Mar 2026 14:58:54 -0800
Subject: bnxt_en: Fix RSS table size check when changing ethtool channels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When changing channels, the current check in bnxt_set_channels()
is not checking for non-default RSS contexts when the RSS table size
changes. The current check for IFF_RXFH_CONFIGURED is only sufficient
for the default RSS context. Expand the check to include the presence
of any non-default RSS contexts.

Allowing such change will result in incorrect configuration of the
context's RSS table when the table size changes.

Fixes: b3d0083caf9a ("bnxt_en: Support RSS contexts in ethtool .{get|set}_rxfh()")
Reported-by: Björn Töpel <bjorn@kernel.org>
Link: https://lore.kernel.org/netdev/20260303181535.2671734-1-bjorn@kernel.org/
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260306225854.3575672-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index ba47e8294fff..28d0ece2e7b1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -979,8 +979,8 @@ static int bnxt_set_channels(struct net_device *dev,
 
 	if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) !=
 	    bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) &&
-	    netif_is_rxfh_configured(dev)) {
-		netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n");
+	    (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) {
+		netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n");
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 237aab549676288d9255bb8dcc284738e56eaa31 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 3 Mar 2026 11:54:14 +0200
Subject: drm/i915/vrr: Configure VRR timings after enabling TRANS_DDI_FUNC_CTL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apparently ICL may hang with an MCE if we write TRANS_VRR_VMAX/FLIPLINE
before enabling TRANS_DDI_FUNC_CTL.

Personally I was only able to reproduce a hang (on an Dell XPS 7390
2-in-1) with an external display connected via a dock using a dodgy
type-C cable that made the link training fail. After the failed
link training the machine would hang. TGL seemed immune to the
problem for whatever reason.

BSpec does tell us to configure VRR after enabling TRANS_DDI_FUNC_CTL
as well. The DMC firmware also does the VRR restore in two stages:
- first stage seems to be unconditional and includes TRANS_VRR_CTL
  and a few other VRR registers, among other things
- second stage is conditional on the DDI being enabled,
  and includes TRANS_DDI_FUNC_CTL and TRANS_VRR_VMAX/VMIN/FLIPLINE,
  among other things

So let's reorder the steps to match to avoid the hang, and
toss in an extra WARN to make sure we don't screw this up later.

BSpec: 22243
Cc: stable@vger.kernel.org
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reported-by: Benjamin Tissoires <bentiss@kernel.org>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15777
Tested-by: Benjamin Tissoires <bentiss@kernel.org>
Fixes: dda7dcd9da73 ("drm/i915/vrr: Use fixed timings for platforms that support VRR")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260303095414.4331-1-ville.syrjala@linux.intel.com
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
(cherry picked from commit 93f3a267c3dd4d811b224bb9e179a10d81456a74)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_display.c |  1 -
 drivers/gpu/drm/i915/display/intel_vrr.c     | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3b8ba8ab76a1..c4246481fc2f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -1614,7 +1614,6 @@ static void hsw_configure_cpu_transcoder(const struct intel_crtc_state *crtc_sta
 	}
 
 	intel_set_transcoder_timings(crtc_state);
-	intel_vrr_set_transcoder_timings(crtc_state);
 
 	if (cpu_transcoder != TRANSCODER_EDP)
 		intel_de_write(display, TRANS_MULT(display, cpu_transcoder),
diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c
index db74744ddb31..bea005752327 100644
--- a/drivers/gpu/drm/i915/display/intel_vrr.c
+++ b/drivers/gpu/drm/i915/display/intel_vrr.c
@@ -597,6 +597,18 @@ void intel_vrr_set_transcoder_timings(const struct intel_crtc_state *crtc_state)
 	if (!HAS_VRR(display))
 		return;
 
+	/*
+	 * Bspec says:
+	 * "(note: VRR needs to be programmed after
+	 *  TRANS_DDI_FUNC_CTL and before TRANS_CONF)."
+	 *
+	 * In practice it turns out that ICL can hang if
+	 * TRANS_VRR_VMAX/FLIPLINE are written before
+	 * enabling TRANS_DDI_FUNC_CTL.
+	 */
+	drm_WARN_ON(display->drm,
+		    !(intel_de_read(display, TRANS_DDI_FUNC_CTL(display, cpu_transcoder)) & TRANS_DDI_FUNC_ENABLE));
+
 	/*
 	 * This bit seems to have two meanings depending on the platform:
 	 * TGL: generate VRR "safe window" for DSB vblank waits
@@ -939,6 +951,8 @@ void intel_vrr_transcoder_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(crtc_state);
 
+	intel_vrr_set_transcoder_timings(crtc_state);
+
 	if (!intel_vrr_possible(crtc_state))
 		return;
 
-- 
cgit v1.2.3


From 029ae067431ab9d0fca479bdabe780fa436706ea Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Date: Tue, 24 Feb 2026 10:49:06 +0100
Subject: drm/i915: Fix potential overflow of shmem scatterlist length

When a scatterlists table of a GEM shmem object of size 4 GB or more is
populated with pages allocated from a folio, unsigned int .length
attribute of a scatterlist may get overflowed if total byte length of
pages allocated to that single scatterlist happens to reach or cross the
4GB limit.  As a consequence, users of the object may suffer from hitting
unexpected, premature end of the object's backing pages.

[278.780187] ------------[ cut here ]------------
[278.780377] WARNING: CPU: 1 PID: 2326 at drivers/gpu/drm/i915/i915_mm.c:55 remap_sg+0x199/0x1d0 [i915]
...
[278.780654] CPU: 1 UID: 0 PID: 2326 Comm: gem_mmap_offset Tainted: G S   U              6.17.0-rc1-CI_DRM_16981-ged823aaa0607+ #1 PREEMPT(voluntary)
[278.780656] Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER
[278.780658] Hardware name: Intel Corporation Meteor Lake Client Platform/MTL-P LP5x T3 RVP, BIOS MTLPFWI1.R00.3471.D91.2401310918 01/31/2024
[278.780659] RIP: 0010:remap_sg+0x199/0x1d0 [i915]
...
[278.780786] Call Trace:
[278.780787]  <TASK>
[278.780788]  ? __apply_to_page_range+0x3e6/0x910
[278.780795]  ? __pfx_remap_sg+0x10/0x10 [i915]
[278.780906]  apply_to_page_range+0x14/0x30
[278.780908]  remap_io_sg+0x14d/0x260 [i915]
[278.781013]  vm_fault_cpu+0xd2/0x330 [i915]
[278.781137]  __do_fault+0x3a/0x1b0
[278.781140]  do_fault+0x322/0x640
[278.781143]  __handle_mm_fault+0x938/0xfd0
[278.781150]  handle_mm_fault+0x12c/0x300
[278.781152]  ? lock_mm_and_find_vma+0x4b/0x760
[278.781155]  do_user_addr_fault+0x2d6/0x8e0
[278.781160]  exc_page_fault+0x96/0x2c0
[278.781165]  asm_exc_page_fault+0x27/0x30
...

That issue was apprehended by the author of a change that introduced it,
and potential risk even annotated with a comment, but then never addressed.

When adding folio pages to a scatterlist table, take care of byte length
of any single scatterlist not exceeding max_segment.

Fixes: 0b62af28f249b ("i915: convert shmem_sg_free_table() to use a folio_batch")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14809
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org # v6.5+
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20260224094944.2447913-2-janusz.krzysztofik@linux.intel.com
(cherry picked from commit 06249b4e691a75694c014a61708c007fb5755f60)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index c6c64ba29bc4..720a9ad39aa2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -153,8 +153,12 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 			}
 		} while (1);
 
-		nr_pages = min_t(unsigned long,
-				folio_nr_pages(folio), page_count - i);
+		nr_pages = min_array(((unsigned long[]) {
+					folio_nr_pages(folio),
+					page_count - i,
+					max_segment / PAGE_SIZE,
+				      }), 3);
+
 		if (!i ||
 		    sg->length >= max_segment ||
 		    folio_pfn(folio) != next_pfn) {
@@ -164,7 +168,9 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
 			st->nents++;
 			sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0);
 		} else {
-			/* XXX: could overflow? */
+			nr_pages = min_t(unsigned long, nr_pages,
+					 (max_segment - sg->length) / PAGE_SIZE);
+
 			sg->length += nr_pages * PAGE_SIZE;
 		}
 		next_pfn = folio_pfn(folio) + nr_pages;
-- 
cgit v1.2.3


From 1be2fca84f520105413d0d89ed04bb0ff742ab16 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:08 +0200
Subject: drm/i915/psr: Repeat Selective Update area alignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are aligning Selective Update area to cover cursor fully if
needed only once. It may happen that cursor is in Selective Update area
after pipe alignment and after that covering cursor plane only
partially. Fix this by looping alignment as long as alignment isn't needed
anymore.

v2:
  - do not unecessarily loop if cursor was already fully covered
  - rename aligned as su_area_changed

Fixes: 1bff93b8bc27 ("drm/i915/psr: Extend SU area to cover cursor fully if needed")
Cc: <stable@vger.kernel.org> # v6.9+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-2-jouni.hogander@intel.com
(cherry picked from commit 681e12440d8b110350a5709101169f319e10ccbb)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 50 ++++++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 4ce1173a2e91..3848cd4fba0e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2689,11 +2689,12 @@ static void clip_area_update(struct drm_rect *overlap_damage_area,
 		overlap_damage_area->y2 = damage_area->y2;
 }
 
-static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state)
+static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(crtc_state);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	u16 y_alignment;
+	bool su_area_changed = false;
 
 	/* ADLP aligns the SU region to vdsc slice height in case dsc is enabled */
 	if (crtc_state->dsc.compression_enable &&
@@ -2702,10 +2703,18 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st
 	else
 		y_alignment = crtc_state->su_y_granularity;
 
-	crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment;
-	if (crtc_state->psr2_su_area.y2 % y_alignment)
+	if (crtc_state->psr2_su_area.y1 % y_alignment) {
+		crtc_state->psr2_su_area.y1 -= crtc_state->psr2_su_area.y1 % y_alignment;
+		su_area_changed = true;
+	}
+
+	if (crtc_state->psr2_su_area.y2 % y_alignment) {
 		crtc_state->psr2_su_area.y2 = ((crtc_state->psr2_su_area.y2 /
 						y_alignment) + 1) * y_alignment;
+		su_area_changed = true;
+	}
+
+	return su_area_changed;
 }
 
 /*
@@ -2839,7 +2848,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_plane_state *new_plane_state, *old_plane_state;
 	struct intel_plane *plane;
-	bool full_update = false, cursor_in_su_area = false;
+	bool full_update = false, su_area_changed;
 	int i, ret;
 
 	if (!crtc_state->enable_psr2_sel_fetch)
@@ -2946,15 +2955,32 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	if (ret)
 		return ret;
 
-	/*
-	 * Adjust su area to cover cursor fully as necessary (early
-	 * transport). This needs to be done after
-	 * drm_atomic_add_affected_planes to ensure visible cursor is added into
-	 * affected planes even when cursor is not updated by itself.
-	 */
-	intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area);
+	do {
+		bool cursor_in_su_area;
 
-	intel_psr2_sel_fetch_pipe_alignment(crtc_state);
+		/*
+		 * Adjust su area to cover cursor fully as necessary
+		 * (early transport). This needs to be done after
+		 * drm_atomic_add_affected_planes to ensure visible
+		 * cursor is added into affected planes even when
+		 * cursor is not updated by itself.
+		 */
+		intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area);
+
+		su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state);
+
+		/*
+		 * If the cursor was outside the SU area before
+		 * alignment, the alignment step (which only expands
+		 * SU) may pull the cursor partially inside, so we
+		 * must run ET alignment again to fully cover it. But
+		 * if the cursor was already fully inside before
+		 * alignment, expanding the SU area won't change that,
+		 * so no further work is needed.
+		 */
+		if (cursor_in_su_area)
+			break;
+	} while (su_area_changed);
 
 	/*
 	 * Now that we have the pipe damaged area check if it intersect with
-- 
cgit v1.2.3


From c2c79c6d5b939ae8a42ddb884f576bddae685672 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:09 +0200
Subject: drm/i915/dsc: Add Selective Update register definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add definitions for DSC_SU_PARAMETER_SET_0_DSC0 and
DSC_SU_PARAMETER_SET_0_DSC1 registers. These are for Selective Update Early
Transport configuration.

Bspec: 71709
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-3-jouni.hogander@intel.com
(cherry picked from commit 24f96d903daf3dcf8fafe84d3d22b80ef47ba493)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_vdsc_regs.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
index 2d478a84b07c..2b2e3c1b8138 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc_regs.h
@@ -196,6 +196,18 @@
 #define   DSC_PPS18_NSL_BPG_OFFSET(offset)	REG_FIELD_PREP(DSC_PPS18_NSL_BPG_OFFSET_MASK, offset)
 #define   DSC_PPS18_SL_OFFSET_ADJ(offset)	REG_FIELD_PREP(DSC_PPS18_SL_OFFSET_ADJ_MASK, offset)
 
+#define _LNL_DSC0_SU_PARAMETER_SET_0_PA		0x78064
+#define _LNL_DSC1_SU_PARAMETER_SET_0_PA		0x78164
+#define _LNL_DSC0_SU_PARAMETER_SET_0_PB		0x78264
+#define _LNL_DSC1_SU_PARAMETER_SET_0_PB		0x78364
+#define LNL_DSC0_SU_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe), _LNL_DSC0_SU_PARAMETER_SET_0_PA, _LNL_DSC0_SU_PARAMETER_SET_0_PB)
+#define LNL_DSC1_SU_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe), _LNL_DSC1_SU_PARAMETER_SET_0_PA, _LNL_DSC1_SU_PARAMETER_SET_0_PB)
+
+#define   DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK		REG_GENMASK(31, 20)
+#define   DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(rows)	REG_FIELD_PREP(DSC_SUPS0_SU_SLICE_ROW_PER_FRAME_MASK, (rows))
+#define   DSC_SUPS0_SU_PIC_HEIGHT_MASK			REG_GENMASK(15, 0)
+#define   DSC_SUPS0_SU_PIC_HEIGHT(h)			REG_FIELD_PREP(DSC_SUPS0_SU_PIC_HEIGHT_MASK, (h))
+
 /* Icelake Rate Control Buffer Threshold Registers */
 #define DSCA_RC_BUF_THRESH_0			_MMIO(0x6B230)
 #define DSCA_RC_BUF_THRESH_0_UDW		_MMIO(0x6B230 + 4)
-- 
cgit v1.2.3


From bb5f1cd10101c2567bff4d0e760b74aee7c42f44 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:10 +0200
Subject: drm/i915/dsc: Add helper for writing DSC Selective Update ET
 parameters
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are slice row per frame and pic height configuration in DSC Selective
Update Parameter Set 1 register. Add helper for configuring these.

v2:
  - Add WARN_ON_ONCE if vdsc instances per pipe > 2
  - instead of checking vdsc instances per pipe being > 1 check == 2

Bspec: 71709
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-4-jouni.hogander@intel.com
(cherry picked from commit c8698d61aeb3f70fe33761ee9d3d0e131b5bc2eb)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
[tursulin: fixup forward declaration conflict]
---
 drivers/gpu/drm/i915/display/intel_vdsc.c | 23 +++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_vdsc.h |  3 +++
 2 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 5493082f30a7..2065dac1e3fd 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -767,6 +767,29 @@ void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
 				  sizeof(dp_dsc_pps_sdp));
 }
 
+void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state, int su_lines)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	enum pipe pipe = crtc->pipe;
+	int vdsc_instances_per_pipe = intel_dsc_get_vdsc_per_pipe(crtc_state);
+	int slice_row_per_frame = su_lines / vdsc_cfg->slice_height;
+	u32 val;
+
+	drm_WARN_ON_ONCE(display->drm, su_lines % vdsc_cfg->slice_height);
+	drm_WARN_ON_ONCE(display->drm, vdsc_instances_per_pipe > 2);
+
+	val = DSC_SUPS0_SU_SLICE_ROW_PER_FRAME(slice_row_per_frame);
+	val |= DSC_SUPS0_SU_PIC_HEIGHT(su_lines);
+
+	intel_de_write_dsb(display, dsb, LNL_DSC0_SU_PARAMETER_SET_0(pipe), val);
+
+	if (vdsc_instances_per_pipe == 2)
+		intel_de_write_dsb(display, dsb, LNL_DSC1_SU_PARAMETER_SET_0(pipe), val);
+}
+
 static i915_reg_t dss_ctl1_reg(struct intel_crtc *crtc, enum transcoder cpu_transcoder)
 {
 	return is_pipe_dsc(crtc, cpu_transcoder) ?
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h
index 99f64ac54b27..99bb9042592a 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.h
@@ -13,6 +13,7 @@ struct drm_printer;
 enum transcoder;
 struct intel_crtc;
 struct intel_crtc_state;
+struct intel_dsb;
 struct intel_encoder;
 
 bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state);
@@ -31,6 +32,8 @@ void intel_dsc_dsi_pps_write(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *crtc_state);
 void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state);
+void intel_dsc_su_et_parameters_configure(struct intel_dsb *dsb, struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state, int su_lines);
 void intel_vdsc_state_dump(struct drm_printer *p, int indent,
 			   const struct intel_crtc_state *crtc_state);
 int intel_vdsc_min_cdclk(const struct intel_crtc_state *crtc_state);
-- 
cgit v1.2.3


From 5923a6e0459fdd3edac4ad5abccb24d777d8f1b6 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Wed, 4 Mar 2026 13:30:11 +0200
Subject: drm/i915/psr: Write DSC parameters on Selective Update in ET mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are slice row per frame and pic height parameters in DSC that needs
to be configured on every Selective Update in Early Transport mode. Use
helper provided by DSC code to configure these on Selective Update when in
Early Transport mode. Also fill crtc_state->psr2_su_area with full frame
area on full frame update for DSC calculation.

v2: move psr2_su_area under skip_sel_fetch_set_loop label

Bspec: 68927, 71709
Fixes: 467e4e061c44 ("drm/i915/psr: Enable psr2 early transport as possible")
Cc: <stable@vger.kernel.org> # v6.9+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://patch.msgid.link/20260304113011.626542-5-jouni.hogander@intel.com
(cherry picked from commit 3140af2fab505a4cd47d516284529bf1585628be)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 3848cd4fba0e..b7302a32ded4 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2619,6 +2619,12 @@ void intel_psr2_program_trans_man_trk_ctl(struct intel_dsb *dsb,
 
 	intel_de_write_dsb(display, dsb, PIPE_SRCSZ_ERLY_TPT(crtc->pipe),
 			   crtc_state->pipe_srcsz_early_tpt);
+
+	if (!crtc_state->dsc.compression_enable)
+		return;
+
+	intel_dsc_su_et_parameters_configure(dsb, encoder, crtc_state,
+					     drm_rect_height(&crtc_state->psr2_su_area));
 }
 
 static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
@@ -3040,6 +3046,10 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	}
 
 skip_sel_fetch_set_loop:
+	if (full_update)
+		clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src,
+				 &crtc_state->pipe_src);
+
 	psr2_man_trk_ctl_calc(crtc_state, full_update);
 	crtc_state->pipe_srcsz_early_tpt =
 		psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update);
-- 
cgit v1.2.3


From 335b237d902c7362cb7228802e68374406b24acf Mon Sep 17 00:00:00 2001
From: Arun R Murthy <arun.r.murthy@intel.com>
Date: Wed, 4 Mar 2026 12:51:57 +0530
Subject: drm/i915/dp: Read ALPM caps after DPCD init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For eDP read the ALPM DPCD caps after DPCD initalization and just before
the PSR init.

v2: Move intel_alpm_init to intel_edp_init_dpcd (Jouni)
v3: Add Fixes with commit-id (Jouni)
v4: Separated the alpm dpcd read caps from alpm_init and moved to
intel_edp_init_dpcd.
v5: Read alpm_caps always for eDP irrespective of the eDP version (Jouni)
v6: replace drm_dp_dpcd_readb with drm_dp_dpcd_read_byte (Jouni)

Fixes: 15438b325987 ("drm/i915/alpm: Add compute config for lobf")
Signed-off-by: Arun R Murthy <arun.r.murthy@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Link: https://patch.msgid.link/20260304072157.1123283-1-arun.r.murthy@intel.com
(cherry picked from commit 88442ba208dd5d3405de3f5000cf5b2c86876ae3)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 6 ------
 drivers/gpu/drm/i915/display/intel_dp.c   | 7 +++++++
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index 07ffee38974b..f4f1b68f7543 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -43,12 +43,6 @@ bool intel_alpm_is_alpm_aux_less(struct intel_dp *intel_dp,
 
 void intel_alpm_init(struct intel_dp *intel_dp)
 {
-	u8 dpcd;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_RECEIVER_ALPM_CAP, &dpcd) < 0)
-		return;
-
-	intel_dp->alpm_dpcd = dpcd;
 	mutex_init(&intel_dp->alpm.lock);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 559cf3bb23fd..696edf40b243 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4577,6 +4577,7 @@ static bool
 intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
+	int ret;
 
 	/* this function is meant to be called only once */
 	drm_WARN_ON(display->drm, intel_dp->dpcd[DP_DPCD_REV] != 0);
@@ -4616,6 +4617,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector
 	 */
 	intel_dp_init_source_oui(intel_dp);
 
+	/* Read the ALPM DPCD caps */
+	ret = drm_dp_dpcd_read_byte(&intel_dp->aux, DP_RECEIVER_ALPM_CAP,
+				    &intel_dp->alpm_dpcd);
+	if (ret < 0)
+		return false;
+
 	/*
 	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
 	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]
-- 
cgit v1.2.3


From df1d8abf36ca3681c21a6809eaa9a1e01ef897a6 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 9 Mar 2026 11:46:27 +0100
Subject: ALSA: usb-audio: Check endpoint numbers at parsing Scarlett2 mixer
 interfaces

The Scarlett2 mixer quirk in USB-audio driver may hit a NULL
dereference when a malformed USB descriptor is passed, since it
assumes the presence of an endpoint in the parsed interface in
scarlett2_find_fc_interface(), as reported by fuzzer.

For avoiding the NULL dereference, just add the sanity check of
bNumEndpoints and skip the invalid interface.

Reported-by: syzbot+8f29539ef9a1c8334f42@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/69acbbe1.050a0220.310d8.0001.GAE@google.com
Reported-by: syzbot+ae893a8901067fde2741@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/69acf72a.050a0220.310d8.0004.GAE@google.com
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20260309104632.141895-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_scarlett2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index ef3150581eab..fd1fb668929a 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -8251,6 +8251,8 @@ static int scarlett2_find_fc_interface(struct usb_device *dev,
 
 		if (desc->bInterfaceClass != 255)
 			continue;
+		if (desc->bNumEndpoints < 1)
+			continue;
 
 		epd = get_endpoint(intf->altsetting, 0);
 		private->bInterfaceNumber = desc->bInterfaceNumber;
-- 
cgit v1.2.3


From f1d77b863b414586ee45e10d9837c9ab27d8692d Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Thu, 5 Mar 2026 16:49:21 +0800
Subject: xfs: remove redundant set null for ip->i_itemp

ip->i_itemp has been set null in xfs_inode_item_destroy(), so there is
no need set it null again in xfs_inode_free_callback().

Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_icache.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index a7a09e7eec81..2040a9292ee6 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -159,7 +159,6 @@ xfs_inode_free_callback(
 		ASSERT(!test_bit(XFS_LI_IN_AIL,
 				 &ip->i_itemp->ili_item.li_flags));
 		xfs_inode_item_destroy(ip);
-		ip->i_itemp = NULL;
 	}
 
 	kmem_cache_free(xfs_inode_cache, ip);
-- 
cgit v1.2.3


From 186ac39b8a7d3ec7ce9c5dd45e5c2730177f375c Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Thu, 5 Mar 2026 16:49:22 +0800
Subject: xfs: ensure dquot item is deleted from AIL only after log shutdown

In xfs_qm_dqflush(), when a dquot flush fails due to corruption
(the out_abort error path), the original code removed the dquot log
item from the AIL before calling xfs_force_shutdown(). This ordering
introduces a subtle race condition that can lead to data loss after
a crash.

The AIL tracks the oldest dirty metadata in the journal. The position
of the tail item in the AIL determines the log tail LSN, which is the
oldest LSN that must be preserved for crash recovery. When an item is
removed from the AIL, the log tail can advance past the LSN of that item.

The race window is as follows: if the dquot item happens to be at
the tail of the log, removing it from the AIL allows the log tail
to advance. If a concurrent log write is sampling the tail LSN at
the same time and subsequently writes a complete checkpoint (i.e.,
one containing a commit record) to disk before the shutdown takes
effect, the journal will no longer protect the dquot's last
modification. On the next mount, log recovery will not replay the
dquot changes, even though they were never written back to disk,
resulting in silent data loss.

Fix this by calling xfs_force_shutdown() before xfs_trans_ail_delete()
in the out_abort path. Once the log is shut down, no new log writes
can complete with an updated tail LSN, making it safe to remove the
dquot item from the AIL.

Cc: stable@vger.kernel.org
Fixes: b707fffda6a3 ("xfs: abort consistently on dquot flush failure")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_dquot.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 2b208e2c5264..69e9bc588c8b 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1439,9 +1439,15 @@ xfs_qm_dqflush(
 	return 0;
 
 out_abort:
+	/*
+	 * Shut down the log before removing the dquot item from the AIL.
+	 * Otherwise, the log tail may advance past this item's LSN while
+	 * log writes are still in progress, making these unflushed changes
+	 * unrecoverable on the next mount.
+	 */
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	dqp->q_flags &= ~XFS_DQFLAG_DIRTY;
 	xfs_trans_ail_delete(lip, 0);
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	xfs_dqfunlock(dqp);
 	return error;
 }
-- 
cgit v1.2.3


From 263447532463cf4444a3595e835b99a4e90952fa Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Wed, 4 Mar 2026 18:41:08 +0100
Subject: pinctrl: qcom: spmi-gpio: implement .get_direction()

GPIO controller driver should typically implement the .get_direction()
callback as GPIOLIB internals may try to use it to determine the state
of a pin. Since introduction of shared proxy, it prints a warning splat
when using a shared spmi gpio.

The implementation is not easy because the controller supports enabling
the input and output logic at the same time, so we aligns on the
behaviour of the .get() operation and return -EINVAL in other
situations.

Fixes: eadff3024472 ("pinctrl: Qualcomm SPMI PMIC GPIO pin controller driver")
Fixes: d7b5f5cc5eb4 ("pinctrl: qcom: spmi-gpio: Add support for GPIO LV/MV subtype")
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 83f940fe30b2..d02d42513ebb 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -723,6 +723,21 @@ static const struct pinconf_ops pmic_gpio_pinconf_ops = {
 	.pin_config_group_dbg_show	= pmic_gpio_config_dbg_show,
 };
 
+static int pmic_gpio_get_direction(struct gpio_chip *chip, unsigned pin)
+{
+	struct pmic_gpio_state *state = gpiochip_get_data(chip);
+	struct pmic_gpio_pad *pad;
+
+	pad = state->ctrl->desc->pins[pin].drv_data;
+
+	if (!pad->is_enabled || pad->analog_pass ||
+	    (!pad->input_enabled && !pad->output_enabled))
+		return -EINVAL;
+
+	/* Make sure the state is aligned on what pmic_gpio_get() returns */
+	return pad->input_enabled ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT;
+}
+
 static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned pin)
 {
 	struct pmic_gpio_state *state = gpiochip_get_data(chip);
@@ -801,6 +816,7 @@ static void pmic_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 }
 
 static const struct gpio_chip pmic_gpio_gpio_template = {
+	.get_direction		= pmic_gpio_get_direction,
 	.direction_input	= pmic_gpio_direction_input,
 	.direction_output	= pmic_gpio_direction_output,
 	.get			= pmic_gpio_get,
-- 
cgit v1.2.3


From fb22bb9701d48c4b0e81fe204c2f96a37a520568 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 18 Feb 2026 12:58:09 -0800
Subject: pinctrl: renesas: rza1: Normalize return value of gpio_get()

The GPIO .get() callback is expected to return 0 or 1 (or a negative
error code).  Ensure that the value returned by rza1_gpio_get() is
normalized to the [0, 1] range.

Fixes: 86ef402d805d606a ("gpiolib: sanitize the return value of gpio_chip::get()")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/aZYnyl-Nf4S1U2yj@google.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/pinctrl/renesas/pinctrl-rza1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c
index bc8b9b9ad05b..d2949e4dbaf7 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza1.c
@@ -589,7 +589,7 @@ static inline unsigned int rza1_get_bit(struct rza1_port *port,
 {
 	void __iomem *mem = RZA1_ADDR(port->base, reg, port->id);
 
-	return ioread16(mem) & BIT(bit);
+	return !!(ioread16(mem) & BIT(bit));
 }
 
 /**
-- 
cgit v1.2.3


From 246953f33e8cf95621d6c00332e2780ce1594082 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 5 Mar 2026 11:12:10 +0800
Subject: net: enetc: fix incorrect fallback PHY address handling

The current netc_get_phy_addr() implementation falls back to PHY address
0 when the "mdio" node or the PHY child node is missing. On i.MX95, this
causes failures when a real PHY is actually assigned address 0 and is
managed through the EMDIO interface. Because the bit 0 of phy_mask will
be set, leading imx95_enetc_mdio_phyaddr_config() to return an error, and
the netc_blk_ctrl driver probe subsequently fails. Fix this by returning
-ENODEV when neither an "mdio" node nor any PHY node is present, it means
that ENETC port MDIO is not used to manage the PHY, so there is no need
to configure LaBCR[MDIO_PHYAD_PRTAD].

Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Closes: https://lore.kernel.org/all/7825188.GXAFRqVoOG@steina-w
Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage")
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260305031211.904812-2-wei.fang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
index 7fd39f895290..f0e103615e88 100644
--- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
+++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
@@ -333,11 +333,13 @@ static int netc_get_phy_addr(struct device_node *np)
 
 	mdio_node = of_get_child_by_name(np, "mdio");
 	if (!mdio_node)
-		return 0;
+		return -ENODEV;
 
 	phy_node = of_get_next_child(mdio_node, NULL);
-	if (!phy_node)
+	if (!phy_node) {
+		err = -ENODEV;
 		goto of_put_mdio_node;
+	}
 
 	err = of_property_read_u32(phy_node, "reg", &addr);
 	if (err)
@@ -423,6 +425,9 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 
 			addr = netc_get_phy_addr(gchild);
 			if (addr < 0) {
+				if (addr == -ENODEV)
+					continue;
+
 				dev_err(dev, "Failed to get PHY address\n");
 				return addr;
 			}
@@ -578,6 +583,9 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
 
 	addr = netc_get_phy_addr(np);
 	if (addr < 0) {
+		if (addr == -ENODEV)
+			return 0;
+
 		dev_err(dev, "Failed to get PHY address\n");
 		return addr;
 	}
-- 
cgit v1.2.3


From dbe17e7783cb5d6451ff1217d0464865857e97e1 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 5 Mar 2026 11:12:11 +0800
Subject: net: enetc: do not skip setting LaBCR[MDIO_PHYAD_PRTAD] for addr 0

Given that some platforms may use PHY address 0 (I suppose the PHY may
not treat address 0 as a broadcast address or default response address).
It is possible for some boards to connect multiple PHYs to the same
ENETC MAC, for example:

  - a PHY with a non-zero address connects to ENETC MAC through SGMII
    interface (selected via DTS_A)
  - a PHY with address 0 connects to ENETC MAC through RGMII interface
    (selected via DTS_B)

For the case where the ENETC port MDIO is used to manage the PHY, when
switching from DTS_A to DTS_B via soft reboot, LaBCR[MDIO_PHYAD_PRTAD]
must be updated to 0 because the NETCMIX block is not reset during soft
reboot. However, the current driver explicitly skips configuring address
0, causing LaBCR[MDIO_PHYAD_PRTAD] to retain its old value.

Therefore, remove the special-case skip of PHY address 0 so that valid
configurations using address 0 are properly supported.

Fixes: 6633df05f3ad ("net: enetc: set the external PHY address in IERB for port MDIO usage")
Fixes: 50bfd9c06f0f ("net: enetc: set external PHY address in IERB for i.MX94 ENETC")
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260305031211.904812-3-wei.fang@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
index f0e103615e88..92a0f824dae7 100644
--- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
+++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c
@@ -438,12 +438,6 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev)
 				return -EINVAL;
 			}
 
-			/* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is
-			 * 0, so no need to set the register.
-			 */
-			if (!addr)
-				continue;
-
 			switch (bus_devfn) {
 			case IMX95_ENETC0_BUS_DEVFN:
 				netc_reg_write(priv->ierb, IERB_LBCR(0),
@@ -590,12 +584,6 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv,
 		return addr;
 	}
 
-	/* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0,
-	 * so no need to set the register.
-	 */
-	if (!addr)
-		return 0;
-
 	if (phy_mask & BIT(addr)) {
 		dev_err(dev,
 			"Find same PHY address in EMDIO and ENETC node\n");
-- 
cgit v1.2.3


From a79f7b4aeb8e7562cd6dbf9c223e2c2a04b1a85f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 10 Mar 2026 08:54:33 +0000
Subject: KVM: arm64: pkvm: Don't reprobe for ICH_VTR_EL2.TDS on CPU hotplug

Hotplugging a CPU off and back on fails with pKVM, as we try to
probe for ICH_VTR_EL2.TDS. In a non-VHE setup, this is achieved
by using an EL2 stub helper. However, the stubs are out of reach
once pKVM has deprivileged the kernel. The CPU never boots.

Since pKVM doesn't allow late onlining of CPUs, we can detect
that protected mode is enforced early on, and return the current
state of the capability.

Fixes: 2a28810cbb8b2 ("KVM: arm64: GICv3: Detect and work around the lack of ICV_DIR_EL1 trapping")
Reported-by: Vincent Donnefort <vdonnefort@google.com>
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://patch.msgid.link/20260310085433.3936742-1-maz@kernel.org
Cc: stable@vger.kernel.org
---
 arch/arm64/kernel/cpufeature.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c31f8e17732a..32c2dbcc0c64 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2345,6 +2345,15 @@ static bool can_trap_icv_dir_el1(const struct arm64_cpu_capabilities *entry,
 	    !is_midr_in_range_list(has_vgic_v3))
 		return false;
 
+	/*
+	 * pKVM prevents late onlining of CPUs. This means that whatever
+	 * state the capability is in after deprivilege cannot be affected
+	 * by a new CPU booting -- this is garanteed to be a CPU we have
+	 * already seen, and the cap is therefore unchanged.
+	 */
+	if (system_capabilities_finalized() && is_protected_kvm_enabled())
+		return cpus_have_final_cap(ARM64_HAS_ICH_HCR_EL2_TDIR);
+
 	if (is_kernel_in_hyp_mode())
 		res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2);
 	else
-- 
cgit v1.2.3


From 8dafa9f5900c4855a65dbfee51e3bd00636deee1 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 9 Mar 2026 16:22:19 +0900
Subject: mm/slab: fix an incorrect check in obj_exts_alloc_size()

obj_exts_alloc_size() prevents recursive allocation of slabobj_ext
array from the same cache, to avoid creating slabs that are never freed.

There is one mistake that returns the original size when memory
allocation profiling is disabled. The assumption was that
memcg-triggered slabobj_ext allocation is always served from
KMALLOC_CGROUP type. But this is wrong [1]: when the caller specifies
both __GFP_RECLAIMABLE and __GFP_ACCOUNT with SLUB_TINY enabled, the
allocation is served from normal kmalloc. This is because kmalloc_type()
prioritizes __GFP_RECLAIMABLE over __GFP_ACCOUNT, and SLUB_TINY aliases
KMALLOC_RECLAIM with KMALLOC_NORMAL.

As a result, the recursion guard is bypassed and the problematic slabs
can be created. Fix this by removing the mem_alloc_profiling_enabled()
check entirely. The remaining is_kmalloc_normal() check is still
sufficient to detect whether the cache is of KMALLOC_NORMAL type and
avoid bumping the size if it's not.

Without SLUB_TINY, no functional change intended.
With SLUB_TINY, allocations with __GFP_ACCOUNT|__GFP_RECLAIMABLE
now allocate a larger array if the sizes equal.

Reported-by: Zw Tang <shicenci@gmail.com>
Fixes: 280ea9c3154b ("mm/slab: avoid allocating slabobj_ext array from its own slab")
Closes: https://lore.kernel.org/linux-mm/CAPHJ_VKuMKSke8b11AZQw1PTSFN4n2C0gFxC6xGOG0ZLHgPmnA@mail.gmail.com [1]
Cc: stable@vger.kernel.org
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Link: https://patch.msgid.link/20260309072219.22653-1-harry.yoo@oracle.com
Tested-by: Zw Tang <shicenci@gmail.com>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 20cb4f3b636d..6371838d2352 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2119,13 +2119,6 @@ static inline size_t obj_exts_alloc_size(struct kmem_cache *s,
 	size_t sz = sizeof(struct slabobj_ext) * slab->objects;
 	struct kmem_cache *obj_exts_cache;
 
-	/*
-	 * slabobj_ext array for KMALLOC_CGROUP allocations
-	 * are served from KMALLOC_NORMAL caches.
-	 */
-	if (!mem_alloc_profiling_enabled())
-		return sz;
-
 	if (sz > KMALLOC_MAX_CACHE_SIZE)
 		return sz;
 
-- 
cgit v1.2.3


From e3f5e0f22cfc2371e7471c9fd5b4da78f9df7c69 Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Thu, 5 Mar 2026 22:32:34 +0800
Subject: mctp: i2c: fix skb memory leak in receive path

When 'midev->allow_rx' is false, the newly allocated skb isn't consumed
by netif_rx(), it needs to free the skb directly.

Fixes: f5b8abf9fc3d ("mctp i2c: MCTP I2C binding driver")
Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Link: https://patch.msgid.link/20260305143240.97592-1-haiyuewa@163.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mctp/mctp-i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c
index de6bc1736734..15fe4d1163c1 100644
--- a/drivers/net/mctp/mctp-i2c.c
+++ b/drivers/net/mctp/mctp-i2c.c
@@ -343,6 +343,7 @@ static int mctp_i2c_recv(struct mctp_i2c_dev *midev)
 	} else {
 		status = NET_RX_DROP;
 		spin_unlock_irqrestore(&midev->lock, flags);
+		kfree_skb(skb);
 	}
 
 	if (status == NET_RX_SUCCESS) {
-- 
cgit v1.2.3


From 1eea46908c57abb7109b1fce024f366ae6c69c4f Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Fri, 6 Mar 2026 17:04:48 +0800
Subject: can: dev: keep the max bitrate error at 5%

Commit b360a13d44db ("can: dev: print bitrate error with two decimal
digits") changed calculation of the bit rate error from on-tenth of a
percent to on-hundredth of a percent, but forgot to adjust the scale of the
CAN_CALC_MAX_ERROR constant.

Keeping the existing logic unchanged: Only when the bitrate error exceeds
5% should an error be returned. Otherwise, simply output a warning log.

Fixes: b360a13d44db ("can: dev: print bitrate error with two decimal digits")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Link: https://patch.msgid.link/20260306-can-fix-v1-1-ac526cec6777@nxp.com
Cc: stable@kernel.org
[mkl: improve commit message]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/calc_bittiming.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c
index cc4022241553..42498e9d3f38 100644
--- a/drivers/net/can/dev/calc_bittiming.c
+++ b/drivers/net/can/dev/calc_bittiming.c
@@ -8,7 +8,7 @@
 #include <linux/units.h>
 #include <linux/can/dev.h>
 
-#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
+#define CAN_CALC_MAX_ERROR 500 /* max error 5% */
 
 /* CiA recommended sample points for Non Return to Zero encoding. */
 static int can_calc_sample_point_nrz(const struct can_bittiming *bt)
-- 
cgit v1.2.3


From 47bba09b14fa21712398febf36cb14fd4fc3bded Mon Sep 17 00:00:00 2001
From: Wenyuan Li <2063309626@qq.com>
Date: Tue, 10 Mar 2026 13:08:44 +0800
Subject: can: hi311x: hi3110_open(): add check for hi3110_power_enable()
 return value

In hi3110_open(), the return value of hi3110_power_enable() is not checked.
If power enable fails, the device may not function correctly, while the
driver still returns success.

Add a check for the return value and propagate the error accordingly.

Signed-off-by: Wenyuan Li <2063309626@qq.com>
Link: https://patch.msgid.link/tencent_B5E2E7528BB28AA8A2A56E16C49BD58B8B07@qq.com
Fixes: 57e83fb9b746 ("can: hi311x: Add Holt HI-311x CAN driver")
[mkl: adjust subject, commit message and jump label]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/hi311x.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index e00d3dbc4cf4..91b1fa970f8f 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -755,7 +755,9 @@ static int hi3110_open(struct net_device *net)
 		return ret;
 
 	mutex_lock(&priv->hi3110_lock);
-	hi3110_power_enable(priv->transceiver, 1);
+	ret = hi3110_power_enable(priv->transceiver, 1);
+	if (ret)
+		goto out_close_candev;
 
 	priv->force_quit = 0;
 	priv->tx_skb = NULL;
@@ -790,6 +792,7 @@ static int hi3110_open(struct net_device *net)
 	hi3110_hw_sleep(spi);
  out_close:
 	hi3110_power_enable(priv->transceiver, 0);
+ out_close_candev:
 	close_candev(net);
 	mutex_unlock(&priv->hi3110_lock);
 	return ret;
-- 
cgit v1.2.3


From 950803f7254721c1c15858fbbfae3deaaeeecb11 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Fri, 6 Mar 2026 10:15:07 +0800
Subject: bonding: fix type confusion in bond_setup_by_slave()

kernel BUG at net/core/skbuff.c:2306!
Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
RIP: 0010:pskb_expand_head+0xa08/0xfe0 net/core/skbuff.c:2306
RSP: 0018:ffffc90004aff760 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffff88807e3c8780 RCX: ffffffff89593e0e
RDX: ffff88807b7c4900 RSI: ffffffff89594747 RDI: ffff88807b7c4900
RBP: 0000000000000820 R08: 0000000000000005 R09: 0000000000000000
R10: 00000000961a63e0 R11: 0000000000000000 R12: ffff88807e3c8780
R13: 00000000961a6560 R14: dffffc0000000000 R15: 00000000961a63e0
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fe1a0ed8df0 CR3: 000000002d816000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 ipgre_header+0xdd/0x540 net/ipv4/ip_gre.c:900
 dev_hard_header include/linux/netdevice.h:3439 [inline]
 packet_snd net/packet/af_packet.c:3028 [inline]
 packet_sendmsg+0x3ae5/0x53c0 net/packet/af_packet.c:3108
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg net/socket.c:742 [inline]
 ____sys_sendmsg+0xa54/0xc30 net/socket.c:2592
 ___sys_sendmsg+0x190/0x1e0 net/socket.c:2646
 __sys_sendmsg+0x170/0x220 net/socket.c:2678
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fe1a0e6c1a9

When a non-Ethernet device (e.g. GRE tunnel) is enslaved to a bond,
bond_setup_by_slave() directly copies the slave's header_ops to the
bond device:

    bond_dev->header_ops = slave_dev->header_ops;

This causes a type confusion when dev_hard_header() is later called
on the bond device. Functions like ipgre_header(), ip6gre_header(),all use
netdev_priv(dev) to access their device-specific private data. When
called with the bond device, netdev_priv() returns the bond's private
data (struct bonding) instead of the expected type (e.g. struct
ip_tunnel), leading to garbage values being read and kernel crashes.

Fix this by introducing bond_header_ops with wrapper functions that
delegate to the active slave's header_ops using the slave's own
device. This ensures netdev_priv() in the slave's header functions
always receives the correct device.

The fix is placed in the bonding driver rather than individual device
drivers, as the root cause is bond blindly inheriting header_ops from
the slave without considering that these callbacks expect a specific
netdev_priv() layout.

The type confusion can be observed by adding a printk in
ipgre_header() and running the following commands:

    ip link add dummy0 type dummy
    ip addr add 10.0.0.1/24 dev dummy0
    ip link set dummy0 up
    ip link add gre1 type gre local 10.0.0.1
    ip link add bond1 type bond mode active-backup
    ip link set gre1 master bond1
    ip link set gre1 up
    ip link set bond1 up
    ip addr add fe80::1/64 dev bond1

Fixes: 1284cd3a2b74 ("bonding: two small fixes for IPoIB support")
Suggested-by: Jay Vosburgh <jv@jvosburgh.net>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260306021508.222062-1-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 47 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 444519078da3..c1fb92602e46 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1509,6 +1509,50 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	return features;
 }
 
+static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned int len)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->create)
+			ret = slave_ops->create(skb, slave->dev,
+						type, daddr, saddr, len);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+	struct bonding *bond = netdev_priv(skb->dev);
+	const struct header_ops *slave_ops;
+	struct slave *slave;
+	int ret = 0;
+
+	rcu_read_lock();
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (slave) {
+		slave_ops = READ_ONCE(slave->dev->header_ops);
+		if (slave_ops && slave_ops->parse)
+			ret = slave_ops->parse(skb, haddr);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static const struct header_ops bond_header_ops = {
+	.create	= bond_header_create,
+	.parse	= bond_header_parse,
+};
+
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
@@ -1516,7 +1560,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 
 	dev_close(bond_dev);
 
-	bond_dev->header_ops	    = slave_dev->header_ops;
+	bond_dev->header_ops	    = slave_dev->header_ops ?
+				      &bond_header_ops : NULL;
 
 	bond_dev->type		    = slave_dev->type;
 	bond_dev->hard_header_len   = slave_dev->hard_header_len;
-- 
cgit v1.2.3


From 7d86aa41c073c4e7eb75fd2e674f1fd8f289728a Mon Sep 17 00:00:00 2001
From: Chengfeng Ye <dg573847474@gmail.com>
Date: Fri, 6 Mar 2026 03:14:02 +0000
Subject: mctp: route: hold key->lock in mctp_flow_prepare_output()

mctp_flow_prepare_output() checks key->dev and may call
mctp_dev_set_key(), but it does not hold key->lock while doing so.

mctp_dev_set_key() and mctp_dev_release_key() are annotated with
__must_hold(&key->lock), so key->dev access is intended to be
serialized by key->lock. The mctp_sendmsg() transmit path reaches
mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output()
without holding key->lock, so the check-and-set sequence is racy.

Example interleaving:

  CPU0                                  CPU1
  ----                                  ----
  mctp_flow_prepare_output(key, devA)
    if (!key->dev)  // sees NULL
                                        mctp_flow_prepare_output(
                                            key, devB)
                                          if (!key->dev)  // still NULL
                                          mctp_dev_set_key(devB, key)
                                            mctp_dev_hold(devB)
                                            key->dev = devB
    mctp_dev_set_key(devA, key)
      mctp_dev_hold(devA)
      key->dev = devA   // overwrites devB

Now both devA and devB references were acquired, but only the final
key->dev value is tracked for release. One reference can be lost,
causing a resource leak as mctp_dev_release_key() would only decrease
the reference on one dev.

Fix by taking key->lock around the key->dev check and
mctp_dev_set_key() call.

Fixes: 67737c457281 ("mctp: Pass flow data & flow release events to drivers")
Signed-off-by: Chengfeng Ye <dg573847474@gmail.com>
Link: https://patch.msgid.link/20260306031402.857224-1-dg573847474@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mctp/route.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/mctp/route.c b/net/mctp/route.c
index 0381377ab760..59ad60b88563 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -359,6 +359,7 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
 {
 	struct mctp_sk_key *key;
 	struct mctp_flow *flow;
+	unsigned long flags;
 
 	flow = skb_ext_find(skb, SKB_EXT_MCTP);
 	if (!flow)
@@ -366,12 +367,14 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev)
 
 	key = flow->key;
 
-	if (key->dev) {
+	spin_lock_irqsave(&key->lock, flags);
+
+	if (!key->dev)
+		mctp_dev_set_key(dev, key);
+	else
 		WARN_ON(key->dev != dev);
-		return;
-	}
 
-	mctp_dev_set_key(dev, key);
+	spin_unlock_irqrestore(&key->lock, flags);
 }
 #else
 static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {}
-- 
cgit v1.2.3


From 8cc7dd77a1466f0ec58c03478b2e735a5b289b96 Mon Sep 17 00:00:00 2001
From: Shashank Balaji <shashank.mahadasyam@sony.com>
Date: Fri, 6 Mar 2026 14:46:28 +0900
Subject: x86/apic: Disable x2apic on resume if the kernel expects so

When resuming from s2ram, firmware may re-enable x2apic mode, which may have
been disabled by the kernel during boot either because it doesn't support IRQ
remapping or for other reasons. This causes the kernel to continue using the
xapic interface, while the hardware is in x2apic mode, which causes hangs.
This happens on defconfig + bare metal + s2ram.

Fix this in lapic_resume() by disabling x2apic if the kernel expects it to be
disabled, i.e. when x2apic_mode = 0.

The ACPI v6.6 spec, Section 16.3 [1] says firmware restores either the
pre-sleep configuration or initial boot configuration for each CPU, including
MSR state:

  When executing from the power-on reset vector as a result of waking from an
  S2 or S3 sleep state, the platform firmware performs only the hardware
  initialization required to restore the system to either the state the
  platform was in prior to the initial operating system boot, or to the
  pre-sleep configuration state. In multiprocessor systems, non-boot
  processors should be placed in the same state as prior to the initial
  operating system boot.

  (further ahead)

  If this is an S2 or S3 wake, then the platform runtime firmware restores
  minimum context of the system before jumping to the waking vector. This
  includes:

	CPU configuration. Platform runtime firmware restores the pre-sleep
	configuration or initial boot configuration of each CPU (MSR, MTRR,
	firmware update, SMBase, and so on). Interrupts must be disabled (for
	IA-32 processors, disabled by CLI instruction).

	(and other things)

So at least as per the spec, re-enablement of x2apic by the firmware is
allowed if "x2apic on" is a part of the initial boot configuration.

  [1] https://uefi.org/specs/ACPI/6.6/16_Waking_and_Sleeping.html#initialization

  [ bp: Massage. ]

Fixes: 6e1cb38a2aef ("x64, x2apic/intr-remap: add x2apic support, including enabling interrupt-remapping")
Co-developed-by: Rahul Bukte <rahul.bukte@sony.com>
Signed-off-by: Rahul Bukte <rahul.bukte@sony.com>
Signed-off-by: Shashank Balaji <shashank.mahadasyam@sony.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260306-x2apic-fix-v2-1-bee99c12efa3@sony.com
---
 arch/x86/kernel/apic/apic.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d93f87f29d03..961714e6adae 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1894,6 +1894,7 @@ void __init check_x2apic(void)
 
 static inline void try_to_enable_x2apic(int remap_mode) { }
 static inline void __x2apic_enable(void) { }
+static inline void __x2apic_disable(void) { }
 #endif /* !CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
@@ -2456,6 +2457,11 @@ static void lapic_resume(void *data)
 	if (x2apic_mode) {
 		__x2apic_enable();
 	} else {
+		if (x2apic_enabled()) {
+			pr_warn_once("x2apic: re-enabled by firmware during resume. Disabling\n");
+			__x2apic_disable();
+		}
+
 		/*
 		 * Make sure the APICBASE points to the right address
 		 *
-- 
cgit v1.2.3


From 6485cb96be5cd0f4bf39554737ba11322cc9b053 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:27 +0530
Subject: amd-xgbe: fix link status handling in xgbe_rx_adaptation

The link status bit is latched low to allow detection of momentary
link drops. If the status indicates that the link is already down,
read it again to obtain the current state.

Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-2-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index c63ddb12237e..13c556dc0d67 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -1942,7 +1942,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata,
 static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
+	int reg;
 
 	/* step 2: force PCS to send RX_ADAPT Req to PHY */
 	XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4,
@@ -1964,11 +1964,20 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata)
 
 	/* Step 4: Check for Block lock */
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
-	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
 	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		goto set_mode;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
+	 */
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			goto set_mode;
+	}
+
 	if (reg & MDIO_STAT1_LSTATUS) {
 		/* If the block lock is found, update the helpers
 		 * and declare the link up
-- 
cgit v1.2.3


From 27a4dd0c702b3b2b9cf2c045d100cc2fe8720b81 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:28 +0530
Subject: amd-xgbe: prevent CRC errors during RX adaptation with AN disabled

When operating in 10GBASE-KR mode with auto-negotiation disabled and RX
adaptation enabled, CRC errors can occur during the RX adaptation
process. This happens because the driver continues transmitting and
receiving packets while adaptation is in progress.

Fix this by stopping TX/RX immediately when the link goes down and RX
adaptation needs to be re-triggered, and only re-enabling TX/RX after
adaptation completes and the link is confirmed up. Introduce a flag to
track whether TX/RX was disabled for adaptation so it can be restored
correctly.

This prevents packets from being transmitted or received during the RX
adaptation window and avoids CRC errors from corrupted frames.

The flag tracking the data path state is synchronized with hardware
state in xgbe_start() to prevent stale state after device restarts.
This ensures that after a restart cycle (where xgbe_stop disables
TX/RX and xgbe_start re-enables them), the flag correctly reflects
that the data path is active.

Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-3-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c    |  4 ++
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 63 ++++++++++++++++++++++++++++-
 drivers/net/ethernet/amd/xgbe/xgbe.h        |  4 ++
 3 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 8b79d88480db..39da2f811858 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1277,6 +1277,10 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	hw_if->enable_tx(pdata);
 	hw_if->enable_rx(pdata);
+	/* Synchronize flag with hardware state after enabling TX/RX.
+	 * This prevents stale state after device restart cycles.
+	 */
+	pdata->data_path_stopped = false;
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 13c556dc0d67..b8cf6ccfe641 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -2017,6 +2017,48 @@ rx_adapt_reinit:
 	xgbe_rx_adaptation(pdata);
 }
 
+/*
+ * xgbe_phy_stop_data_path - Stop TX/RX to prevent packet corruption
+ * @pdata: driver private data
+ *
+ * This function stops the data path (TX and RX) to prevent packet
+ * corruption during critical PHY operations like RX adaptation.
+ * Must be called before initiating RX adaptation when link goes down.
+ */
+static void xgbe_phy_stop_data_path(struct xgbe_prv_data *pdata)
+{
+	if (pdata->data_path_stopped)
+		return;
+
+	/* Stop TX/RX to prevent packet corruption during RX adaptation */
+	pdata->hw_if.disable_tx(pdata);
+	pdata->hw_if.disable_rx(pdata);
+	pdata->data_path_stopped = true;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "stopping data path for RX adaptation\n");
+}
+
+/*
+ * xgbe_phy_start_data_path - Re-enable TX/RX after RX adaptation
+ * @pdata: driver private data
+ *
+ * This function re-enables the data path (TX and RX) after RX adaptation
+ * has completed successfully. Only called when link is confirmed up.
+ */
+static void xgbe_phy_start_data_path(struct xgbe_prv_data *pdata)
+{
+	if (!pdata->data_path_stopped)
+		return;
+
+	pdata->hw_if.enable_rx(pdata);
+	pdata->hw_if.enable_tx(pdata);
+	pdata->data_path_stopped = false;
+
+	netif_dbg(pdata, link, pdata->netdev,
+		  "restarting data path after RX adaptation\n");
+}
+
 static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata)
 {
 	int reg;
@@ -2810,13 +2852,27 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
 		 * declare link up
+		 *
+		 * Note: When link is up and adaptation is done, we can
+		 * safely re-enable the data path if it was stopped
+		 * for adaptation.
 		 */
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) {
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 		/* If either link is not available or adaptation is not done,
 		 * retrigger the adaptation logic. (if the mode is not set,
 		 * then issue mailbox command first)
 		 */
+
+		/* CRITICAL: Stop data path BEFORE triggering RX adaptation
+		 * to prevent CRC errors from packets corrupted during
+		 * the adaptation process. This is especially important
+		 * when AN is OFF in 10G KR mode.
+		 */
+		xgbe_phy_stop_data_path(pdata);
+
 		if (pdata->mode_set) {
 			xgbe_phy_rx_adaptation(pdata);
 		} else {
@@ -2824,8 +2880,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		if (pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done) {
+			/* Adaptation complete, safe to re-enable data path */
+			xgbe_phy_start_data_path(pdata);
 			return 1;
+		}
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index e1d7d7150e16..438033a71523 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1243,6 +1243,10 @@ struct xgbe_prv_data {
 	bool en_rx_adap;
 	int rx_adapt_retries;
 	bool rx_adapt_done;
+	/* Flag to track if data path (TX/RX) was stopped for RX adaptation.
+	 * This prevents packet corruption during the adaptation window.
+	 */
+	bool data_path_stopped;
 	bool mode_set;
 	bool sph;
 };
-- 
cgit v1.2.3


From a8ba129af46856112981c124850ec6a85a1c1ab6 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 6 Mar 2026 16:46:29 +0530
Subject: amd-xgbe: reset PHY settings before starting PHY

commit f93505f35745 ("amd-xgbe: let the MAC manage PHY PM") moved
xgbe_phy_reset() from xgbe_open() to xgbe_start(), placing it after
phy_start(). As a result, the PHY settings were being reset after the
PHY had already started.

Reorder the calls so that the PHY settings are reset before
phy_start() is invoked.

Fixes: f93505f35745 ("amd-xgbe: let the MAC manage PHY PM")
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260306111629.1515676-4-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 39da2f811858..23beea48ae26 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1271,6 +1271,12 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 	if (ret)
 		goto err_napi;
 
+	/* Reset the phy settings */
+	ret = xgbe_phy_reset(pdata);
+	if (ret)
+		goto err_irqs;
+
+	/* Start the phy */
 	ret = phy_if->phy_start(pdata);
 	if (ret)
 		goto err_irqs;
@@ -1284,11 +1290,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	udp_tunnel_nic_reset_ntf(netdev);
 
-	/* Reset the phy settings */
-	ret = xgbe_phy_reset(pdata);
-	if (ret)
-		goto err_txrx;
-
 	netif_tx_start_all_queues(netdev);
 
 	xgbe_start_timers(pdata);
@@ -1298,10 +1299,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	return 0;
 
-err_txrx:
-	hw_if->disable_rx(pdata);
-	hw_if->disable_tx(pdata);
-
 err_irqs:
 	xgbe_free_irqs(pdata);
 
-- 
cgit v1.2.3


From 69fb5d91bba44ecf7eb80530b85fa4fb028921d5 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 17:38:00 +0100
Subject: libceph: prevent potential out-of-bounds reads in
 process_message_header()

If the message frame is (maliciously) corrupted in a way that the
length of the control segment ends up being less than the size of the
message header or a different frame is made to look like a message
frame, out-of-bounds reads may ensue in process_message_header().

Perform an explicit bounds check before decoding the message header.

Cc: stable@vger.kernel.org
Reported-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
---
 net/ceph/messenger_v2.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 5ec3272cd2dd..ed618435d33a 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -2833,12 +2833,15 @@ static int process_message_header(struct ceph_connection *con,
 				  void *p, void *end)
 {
 	struct ceph_frame_desc *desc = &con->v2.in_desc;
-	struct ceph_msg_header2 *hdr2 = p;
+	struct ceph_msg_header2 *hdr2;
 	struct ceph_msg_header hdr;
 	int skip;
 	int ret;
 	u64 seq;
 
+	ceph_decode_need(&p, end, sizeof(*hdr2), bad);
+	hdr2 = p;
+
 	/* verify seq# */
 	seq = le64_to_cpu(hdr2->seq);
 	if ((s64)seq - (s64)con->in_seq < 1) {
@@ -2869,6 +2872,10 @@ static int process_message_header(struct ceph_connection *con,
 	WARN_ON(!con->in_msg);
 	WARN_ON(con->in_msg->con != con);
 	return 1;
+
+bad:
+	pr_err("failed to decode message header\n");
+	return -EINVAL;
 }
 
 static int process_message(struct ceph_connection *con)
-- 
cgit v1.2.3


From a5a373705081d7cc6363e16990e2361b0b362314 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 17:57:23 +0100
Subject: libceph: admit message frames only in CEPH_CON_S_OPEN state

Similar checks are performed for all control frames, but an early check
for message frames was missing.  process_message() is already set up to
terminate the loop in case the state changes while con->ops->dispatch()
handler is being executed.

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
---
 net/ceph/messenger_v2.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index ed618435d33a..c4ddf7911f7d 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -2905,6 +2905,11 @@ static int __handle_control(struct ceph_connection *con, void *p)
 	if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE)
 		return process_control(con, p, end);
 
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected message";
+		return -EINVAL;
+	}
+
 	ret = process_message_header(con, p, end);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.2.3


From c4c22b846eceff05b1129b8844a80310e55a7f87 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Sun, 8 Mar 2026 20:01:27 +0100
Subject: libceph: reject preamble if control segment is empty

While head_onwire_len() has a branch to handle ctrl_len == 0 case,
prepare_read_control() always sets up a kvec for the CRC meaning that
a non-empty control segment is effectively assumed.  All frames that
clients deal with meet that assumption, so let's make it official and
treat the preamble with an empty control segment as malformed.

Cc: stable@vger.kernel.org
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
---
 net/ceph/messenger_v2.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c4ddf7911f7d..50f65820f623 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -392,7 +392,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 	int head_len;
 	int rem_len;
 
-	BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
+	BUG_ON(ctrl_len < 1 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN);
 
 	if (secure) {
 		head_len = CEPH_PREAMBLE_SECURE_LEN;
@@ -401,9 +401,7 @@ static int head_onwire_len(int ctrl_len, bool secure)
 			head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN;
 		}
 	} else {
-		head_len = CEPH_PREAMBLE_PLAIN_LEN;
-		if (ctrl_len)
-			head_len += ctrl_len + CEPH_CRC_LEN;
+		head_len = CEPH_PREAMBLE_PLAIN_LEN + ctrl_len + CEPH_CRC_LEN;
 	}
 	return head_len;
 }
@@ -528,11 +526,16 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		desc->fd_aligns[i] = ceph_decode_16(&p);
 	}
 
-	if (desc->fd_lens[0] < 0 ||
+	/*
+	 * This would fire for FRAME_TAG_WAIT (it has one empty
+	 * segment), but we should never get it as client.
+	 */
+	if (desc->fd_lens[0] < 1 ||
 	    desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) {
 		pr_err("bad control segment length %d\n", desc->fd_lens[0]);
 		return -EINVAL;
 	}
+
 	if (desc->fd_lens[1] < 0 ||
 	    desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) {
 		pr_err("bad front segment length %d\n", desc->fd_lens[1]);
@@ -549,10 +552,6 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc)
 		return -EINVAL;
 	}
 
-	/*
-	 * This would fire for FRAME_TAG_WAIT (it has one empty
-	 * segment), but we should never get it as client.
-	 */
 	if (!desc->fd_lens[desc->fd_seg_cnt - 1]) {
 		pr_err("last segment empty, segment count %d\n",
 		       desc->fd_seg_cnt);
-- 
cgit v1.2.3


From a5f930eebde6f27c1e404f566c09332f42f349fb Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <dongsheng.yang@linux.dev>
Date: Tue, 10 Mar 2026 07:05:14 +0000
Subject: MAINTAINERS: update email address of Dongsheng Yang

My easystack email will be unreachable soon, update my email address to
linux.dev one.

Signed-off-by: Dongsheng Yang <dongsheng.yang@linux.dev>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 77fdfcb55f06..8a9d35b29dbe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21938,7 +21938,7 @@ F:	drivers/media/radio/radio-tea5777.c
 
 RADOS BLOCK DEVICE (RBD)
 M:	Ilya Dryomov <idryomov@gmail.com>
-R:	Dongsheng Yang <dongsheng.yang@easystack.cn>
+R:	Dongsheng Yang <dongsheng.yang@linux.dev>
 L:	ceph-devel@vger.kernel.org
 S:	Supported
 W:	http://ceph.com/
-- 
cgit v1.2.3


From 6f1a9140ecda3baba3d945b9a6155af4268aafc4 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Sat, 7 Mar 2026 00:01:34 +0800
Subject: net: add xmit recursion limit to tunnel xmit functions

Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own
recursion limit. When a bond device in broadcast mode has GRE tap
interfaces as slaves, and those GRE tunnels route back through the
bond, multicast/broadcast traffic triggers infinite recursion between
bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing
kernel stack overflow.

The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not
sufficient because tunnel recursion involves route lookups and full IP
output, consuming much more stack per level. Use a lower limit of 4
(IP_TUNNEL_RECURSION_LIMIT) to prevent overflow.

Add recursion detection using dev_xmit_recursion helpers directly in
iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel
paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.).

Move dev_xmit_recursion helpers from net/core/dev.h to public header
include/linux/netdevice.h so they can be used by tunnel code.

 BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160
 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11
 Workqueue: mld mld_ifc_work
 Call Trace:
  <TASK>
  __build_flow_key.constprop.0 (net/ipv4/route.c:515)
  ip_rt_update_pmtu (net/ipv4/route.c:1073)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84)
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  ip_output (net/ipv4/ip_output.c:438)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  ip_finish_output2 (net/ipv4/ip_output.c:237)
  ip_output (net/ipv4/ip_output.c:438)
  iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86)
  ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847)
  gre_tap_xmit (net/ipv4/ip_gre.c:779)
  dev_hard_start_xmit (net/core/dev.c:3887)
  sch_direct_xmit (net/sched/sch_generic.c:347)
  __dev_queue_xmit (net/core/dev.c:4802)
  bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312)
  bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279)
  bond_start_xmit (drivers/net/bonding/bond_main.c:5530)
  dev_hard_start_xmit (net/core/dev.c:3887)
  __dev_queue_xmit (net/core/dev.c:4841)
  mld_sendpack
  mld_ifc_work
  process_one_work
  worker_thread
  </TASK>

Fixes: 745e20f1b626 ("net: add a recursion limit in xmit path")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260306160133.3852900-2-bestswngs@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++++
 include/net/ip6_tunnel.h  | 12 ++++++++++++
 include/net/ip_tunnels.h  |  7 +++++++
 net/core/dev.h            | 35 -----------------------------------
 net/ipv4/ip_tunnel_core.c | 13 +++++++++++++
 5 files changed, 64 insertions(+), 35 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67e25f6d15a4..ae269a2e7f4d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3576,17 +3576,49 @@ struct page_pool_bh {
 };
 DECLARE_PER_CPU(struct page_pool_bh, system_page_pool);
 
+#define XMIT_RECURSION_LIMIT	8
+
 #ifndef CONFIG_PREEMPT_RT
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
+
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
+			XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	__this_cpu_inc(softnet_data.xmit.recursion);
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	__this_cpu_dec(softnet_data.xmit.recursion);
+}
 #else
 static inline int dev_recursion_level(void)
 {
 	return current->net_xmit.recursion;
 }
 
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	current->net_xmit.recursion++;
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	current->net_xmit.recursion--;
+}
 #endif
 
 void __netif_schedule(struct Qdisc *q);
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 120db2865811..1253cbb4b0a4 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -156,6 +156,16 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 {
 	int pkt_len, err;
 
+	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
+		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+				     dev->name);
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return;
+	}
+
+	dev_xmit_recursion_inc();
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 	IP6CB(skb)->flags = ip6cb_flags;
 	pkt_len = skb->len - skb_inner_network_offset(skb);
@@ -166,6 +176,8 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 			pkt_len = -1;
 		iptunnel_xmit_stats(dev, pkt_len);
 	}
+
+	dev_xmit_recursion_dec();
 }
 #endif
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 4021e6a73e32..80662f812080 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -27,6 +27,13 @@
 #include <net/ip6_route.h>
 #endif
 
+/* Recursion limit for tunnel xmit to detect routing loops.
+ * Unlike XMIT_RECURSION_LIMIT (8) used in the no-qdisc path, tunnel
+ * recursion involves route lookups and full IP output, consuming much
+ * more stack per level, so a lower limit is needed.
+ */
+#define IP_TUNNEL_RECURSION_LIMIT	4
+
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
 
diff --git a/net/core/dev.h b/net/core/dev.h
index 98793a738f43..781619e76b3e 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -366,41 +366,6 @@ static inline void napi_assert_will_not_race(const struct napi_struct *napi)
 
 void kick_defer_list_purge(unsigned int cpu);
 
-#define XMIT_RECURSION_LIMIT	8
-
-#ifndef CONFIG_PREEMPT_RT
-static inline bool dev_xmit_recursion(void)
-{
-	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-			XMIT_RECURSION_LIMIT);
-}
-
-static inline void dev_xmit_recursion_inc(void)
-{
-	__this_cpu_inc(softnet_data.xmit.recursion);
-}
-
-static inline void dev_xmit_recursion_dec(void)
-{
-	__this_cpu_dec(softnet_data.xmit.recursion);
-}
-#else
-static inline bool dev_xmit_recursion(void)
-{
-	return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT);
-}
-
-static inline void dev_xmit_recursion_inc(void)
-{
-	current->net_xmit.recursion++;
-}
-
-static inline void dev_xmit_recursion_dec(void)
-{
-	current->net_xmit.recursion--;
-}
-#endif
-
 int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct kernel_hwtstamp_config *cfg,
 			    struct netlink_ext_ack *extack);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 2e61ac137128..b1b6bf949f65 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -58,6 +58,17 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	struct iphdr *iph;
 	int err;
 
+	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
+		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+				     dev->name);
+		DEV_STATS_INC(dev, tx_errors);
+		ip_rt_put(rt);
+		kfree_skb(skb);
+		return;
+	}
+
+	dev_xmit_recursion_inc();
+
 	skb_scrub_packet(skb, xnet);
 
 	skb_clear_hash_if_not_l4(skb);
@@ -88,6 +99,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 			pkt_len = 0;
 		iptunnel_xmit_stats(dev, pkt_len);
 	}
+
+	dev_xmit_recursion_dec();
 }
 EXPORT_SYMBOL_GPL(iptunnel_xmit);
 
-- 
cgit v1.2.3


From 3c3b41e5911db7668e3938eae8df7ed80c76c153 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 6 Mar 2026 14:08:34 +0000
Subject: perf cs-etm: Finish removal of ETM_OPT_*

These #defines have been removed from the kernel headers in favour of
the string based PMU format attributes. Usages were previously removed
from the recording side of cs-etm in Perf. Finish the removal by
removing usages from the decode side too.

It's a straight replacement of the old #defines with the new register
bit definitions. Except cs_etm__setup_timeless_decoding() which wasn't
looking at the saved metadata and was instead hard coding an access to
'attr.config'. This was vulnerable to the same issue of .config being
moved to .config2 etc that the original removal of ETM_OPT_* tried to
fix. So fix that too.

Signed-off-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/util/cs-etm.c               | 14 ----------
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c |  2 +-
 tools/perf/util/cs-etm.c                        | 36 +++++++++----------------
 tools/perf/util/cs-etm.h                        | 15 +++++++++++
 4 files changed, 29 insertions(+), 38 deletions(-)

diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index dc3f4e86b075..4418d21708d6 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -68,20 +68,6 @@ static const char * const metadata_ete_ro[] = {
 
 enum cs_etm_version { CS_NOT_PRESENT, CS_ETMV3, CS_ETMV4, CS_ETE };
 
-/* ETMv4 CONFIGR register bits */
-#define TRCCONFIGR_BB		BIT(3)
-#define TRCCONFIGR_CCI		BIT(4)
-#define TRCCONFIGR_CID		BIT(6)
-#define TRCCONFIGR_VMID		BIT(7)
-#define TRCCONFIGR_TS		BIT(11)
-#define TRCCONFIGR_RS		BIT(12)
-#define TRCCONFIGR_VMIDOPT	BIT(15)
-
-/* ETMv3 ETMCR register bits */
-#define ETMCR_CYC_ACC		BIT(12)
-#define ETMCR_TIMESTAMP_EN	BIT(28)
-#define ETMCR_RETURN_STACK	BIT(29)
-
 static bool cs_etm_is_ete(struct perf_pmu *cs_etm_pmu, struct perf_cpu cpu);
 static int cs_etm_get_ro(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path, __u64 *val);
 static bool cs_etm_pmu_path_exists(struct perf_pmu *pmu, struct perf_cpu cpu, const char *path);
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 3050fe212666..212f17a3dc72 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -549,7 +549,7 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq,
 	/*
 	 * Process the PE_CONTEXT packets if we have a valid contextID or VMID.
 	 * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2
-	 * as VMID, Bit ETM_OPT_CTXTID2 is set in this case.
+	 * as VMID, Format attribute 'contextid2' is set in this case.
 	 */
 	switch (cs_etm__get_pid_fmt(etmq)) {
 	case CS_ETM_PIDFMT_CTXTID:
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 95f439c96180..8a639d2e51a4 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -194,7 +194,7 @@ int cs_etm__get_cpu(struct cs_etm_queue *etmq, u8 trace_chan_id, int *cpu)
  *   CS_ETM_PIDFMT_CTXTID2: CONTEXTIDR_EL2 is traced.
  *   CS_ETM_PIDFMT_NONE: No context IDs
  *
- * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2
+ * It's possible that the two format attributes 'contextid1' and 'contextid2'
  * are enabled at the same time when the session runs on an EL2 kernel.
  * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be
  * recorded in the trace data, the tool will selectively use
@@ -210,15 +210,15 @@ static enum cs_etm_pid_fmt cs_etm__init_pid_fmt(u64 *metadata)
 	if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) {
 		val = metadata[CS_ETM_ETMCR];
 		/* CONTEXTIDR is traced */
-		if (val & BIT(ETM_OPT_CTXTID))
+		if (val & ETMCR_CTXTID)
 			return CS_ETM_PIDFMT_CTXTID;
 	} else {
 		val = metadata[CS_ETMV4_TRCCONFIGR];
 		/* CONTEXTIDR_EL2 is traced */
-		if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT)))
+		if (val & (TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT))
 			return CS_ETM_PIDFMT_CTXTID2;
 		/* CONTEXTIDR_EL1 is traced */
-		else if (val & BIT(ETM4_CFG_BIT_CTXTID))
+		else if (val & TRCCONFIGR_CID)
 			return CS_ETM_PIDFMT_CTXTID;
 	}
 
@@ -2914,29 +2914,21 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
 	return 0;
 }
 
-static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm)
+static void cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm)
 {
-	struct evsel *evsel;
-	struct evlist *evlist = etm->session->evlist;
+	/* Take first ETM as all options will be the same for all ETMs */
+	u64 *metadata = etm->metadata[0];
 
 	/* Override timeless mode with user input from --itrace=Z */
 	if (etm->synth_opts.timeless_decoding) {
 		etm->timeless_decoding = true;
-		return 0;
+		return;
 	}
 
-	/*
-	 * Find the cs_etm evsel and look at what its timestamp setting was
-	 */
-	evlist__for_each_entry(evlist, evsel)
-		if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) {
-			etm->timeless_decoding =
-				!(evsel->core.attr.config & BIT(ETM_OPT_TS));
-			return 0;
-		}
-
-	pr_err("CS ETM: Couldn't find ETM evsel\n");
-	return -EINVAL;
+	if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic)
+		etm->timeless_decoding = !(metadata[CS_ETM_ETMCR] & ETMCR_TIMESTAMP_EN);
+	else
+		etm->timeless_decoding = !(metadata[CS_ETMV4_TRCCONFIGR] & TRCCONFIGR_TS);
 }
 
 /*
@@ -3499,9 +3491,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 	etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace;
 	session->auxtrace = &etm->auxtrace;
 
-	err = cs_etm__setup_timeless_decoding(etm);
-	if (err)
-		return err;
+	cs_etm__setup_timeless_decoding(etm);
 
 	etm->tc.time_shift = tc->time_shift;
 	etm->tc.time_mult = tc->time_mult;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index a8caeea720aa..aa9bb4a32eca 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -230,6 +230,21 @@ struct cs_etm_packet_queue {
 /* CoreSight trace ID is currently the bottom 7 bits of the value */
 #define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
 
+/* ETMv4 CONFIGR register bits */
+#define TRCCONFIGR_BB		BIT(3)
+#define TRCCONFIGR_CCI		BIT(4)
+#define TRCCONFIGR_CID		BIT(6)
+#define TRCCONFIGR_VMID		BIT(7)
+#define TRCCONFIGR_TS		BIT(11)
+#define TRCCONFIGR_RS		BIT(12)
+#define TRCCONFIGR_VMIDOPT	BIT(15)
+
+/* ETMv3 ETMCR register bits */
+#define ETMCR_CYC_ACC		BIT(12)
+#define ETMCR_CTXTID		BIT(14)
+#define ETMCR_TIMESTAMP_EN	BIT(28)
+#define ETMCR_RETURN_STACK	BIT(29)
+
 int cs_etm__process_auxtrace_info(union perf_event *event,
 				  struct perf_session *session);
 void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr);
-- 
cgit v1.2.3


From e3741935a341983885aba1b09c6dfbc9e6ff5466 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 6 Mar 2026 14:08:35 +0000
Subject: perf cs-etm: Sync coresight-pmu.h header with the kernel sources

Update the header to pull in the changes from commit 3285c471d0c0b991
("coresight: Remove misleading definitions").

Signed-off-by: James Clark <james.clark@linaro.org>
Requested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/557db631-aef8-43b1-9f45-fae75910ccb4@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/coresight-pmu.h | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
index 89b0ac0014b0..2e179abe472a 100644
--- a/tools/include/linux/coresight-pmu.h
+++ b/tools/include/linux/coresight-pmu.h
@@ -21,30 +21,6 @@
  */
 #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu)  (0x10 + (cpu * 2))
 
-/*
- * Below are the definition of bit offsets for perf option, and works as
- * arbitrary values for all ETM versions.
- *
- * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
- * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
- * directly use below macros as config bits.
- */
-#define ETM_OPT_BRANCH_BROADCAST 8
-#define ETM_OPT_CYCACC		12
-#define ETM_OPT_CTXTID		14
-#define ETM_OPT_CTXTID2		15
-#define ETM_OPT_TS		28
-#define ETM_OPT_RETSTK		29
-
-/* ETMv4 CONFIGR programming bits for the ETM OPTs */
-#define ETM4_CFG_BIT_BB         3
-#define ETM4_CFG_BIT_CYCACC	4
-#define ETM4_CFG_BIT_CTXTID	6
-#define ETM4_CFG_BIT_VMID	7
-#define ETM4_CFG_BIT_TS		11
-#define ETM4_CFG_BIT_RETSTK	12
-#define ETM4_CFG_BIT_VMID_OPT	15
-
 /*
  * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
  * Used to associate a CPU with the CoreSight Trace ID.
-- 
cgit v1.2.3


From b7cdc5a97d02c943f4bdde4d5767ad0c13cad92b Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 5 Mar 2026 13:01:44 +0100
Subject: netfilter: nf_tables: Fix for duplicate device in netdev hooks

When handling NETDEV_REGISTER notification, duplicate device
registration must be avoided since the device may have been added by
nft_netdev_hook_alloc() already when creating the hook.

Suggested-by: Florian Westphal <fw@strlen.de>
Reported-by: syzbot+bb9127e278fa198e110c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=bb9127e278fa198e110c
Fixes: a331b78a5525 ("netfilter: nf_tables: Respect NETDEV_REGISTER events")
Tested-by: Helen Koike <koike@igalia.com>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c    | 2 +-
 net/netfilter/nft_chain_filter.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1862bd7fe804..710f0ee21a34 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9688,7 +9688,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev,
 			break;
 		case NETDEV_REGISTER:
 			/* NOP if not matching or already registered */
-			if (!match || (changename && ops))
+			if (!match || ops)
 				continue;
 
 			ops = kzalloc_obj(struct nf_hook_ops,
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index b16185e9a6dd..041426e3bdbf 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -344,7 +344,7 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev,
 			break;
 		case NETDEV_REGISTER:
 			/* NOP if not matching or already registered */
-			if (!match || (changename && ops))
+			if (!match || ops)
 				continue;
 
 			ops = kmemdup(&basechain->ops,
-- 
cgit v1.2.3


From 7cb9a23d7ae40a702577d3d8bacb7026f04ac2a9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 5 Mar 2026 21:32:00 +0100
Subject: netfilter: nf_tables: always walk all pending catchall elements

During transaction processing we might have more than one catchall element:
1 live catchall element and 1 pending element that is coming as part of the
new batch.

If the map holding the catchall elements is also going away, its
required to toggle all catchall elements and not just the first viable
candidate.

Otherwise, we get:
 WARNING: ./include/net/netfilter/nf_tables.h:1281 at nft_data_release+0xb7/0xe0 [nf_tables], CPU#2: nft/1404
 RIP: 0010:nft_data_release+0xb7/0xe0 [nf_tables]
 [..]
 __nft_set_elem_destroy+0x106/0x380 [nf_tables]
 nf_tables_abort_release+0x348/0x8d0 [nf_tables]
 nf_tables_abort+0xcf2/0x3ac0 [nf_tables]
 nfnetlink_rcv_batch+0x9c9/0x20e0 [..]

Fixes: 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 710f0ee21a34..dacec5f8a11c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -829,7 +829,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 
 		nft_set_elem_change_active(ctx->net, set, ext);
 		nft_setelem_data_deactivate(ctx->net, set, catchall->elem);
-		break;
 	}
 }
 
@@ -5873,7 +5872,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx,
 
 		nft_clear(ctx->net, ext);
 		nft_setelem_data_activate(ctx->net, set, catchall->elem);
-		break;
 	}
 }
 
-- 
cgit v1.2.3


From d6d8cd2db236a9dd13dbc2d05843b3445cc964b5 Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Fri, 6 Mar 2026 19:12:38 +0000
Subject: netfilter: nft_set_pipapo: fix stack out-of-bounds read in
 pipapo_drop()

pipapo_drop() passes rulemap[i + 1].n to pipapo_unmap() as the
to_offset argument on every iteration, including the last one where
i == m->field_count - 1. This reads one element past the end of the
stack-allocated rulemap array (declared as rulemap[NFT_PIPAPO_MAX_FIELDS]
with NFT_PIPAPO_MAX_FIELDS == 16).

Although pipapo_unmap() returns early when is_last is true without
using the to_offset value, the argument is evaluated at the call site
before the function body executes, making this a genuine out-of-bounds
stack read confirmed by KASAN:

  BUG: KASAN: stack-out-of-bounds in pipapo_drop+0x50c/0x57c [nf_tables]
  Read of size 4 at addr ffff8000810e71a4

  This frame has 1 object:
   [32, 160) 'rulemap'

  The buggy address is at offset 164 -- exactly 4 bytes past the end
  of the rulemap array.

Pass 0 instead of rulemap[i + 1].n on the last iteration to avoid
the out-of-bounds read.

Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_pipapo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index a34632ae6048..7fd24e0cc428 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1640,6 +1640,7 @@ static void pipapo_drop(struct nft_pipapo_match *m,
 	int i;
 
 	nft_pipapo_for_each_field(f, i, m) {
+		bool last = i == m->field_count - 1;
 		int g;
 
 		for (g = 0; g < f->groups; g++) {
@@ -1659,7 +1660,7 @@ static void pipapo_drop(struct nft_pipapo_match *m,
 		}
 
 		pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n,
-			     rulemap[i + 1].n, i == m->field_count - 1);
+			     last ? 0 : rulemap[i + 1].n, last);
 		if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) {
 			/* We can ignore this, a failure to shrink tables down
 			 * doesn't make tables invalid.
-- 
cgit v1.2.3


From cfe770220ac2dbd3e104c6b45094037455da81d4 Mon Sep 17 00:00:00 2001
From: David Dull <monderasdor@gmail.com>
Date: Sat, 7 Mar 2026 20:26:21 +0200
Subject: netfilter: x_tables: guard option walkers against 1-byte tail reads

When the last byte of options is a non-single-byte option kind, walkers
that advance with i += op[i + 1] ? : 1 can read op[i + 1] past the end
of the option area.

Add an explicit i == optlen - 1 check before dereferencing op[i + 1]
in xt_tcpudp and xt_dccp option walkers.

Fixes: 2e4e6a17af35 ("[NETFILTER] x_tables: Abstraction layer for {ip,ip6,arp}_tables")
Signed-off-by: David Dull <monderasdor@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_dccp.c   | 4 ++--
 net/netfilter/xt_tcpudp.c | 6 ++++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c
index e5a13ecbe67a..037ab93e25d0 100644
--- a/net/netfilter/xt_dccp.c
+++ b/net/netfilter/xt_dccp.c
@@ -62,10 +62,10 @@ dccp_find_option(u_int8_t option,
 			return true;
 		}
 
-		if (op[i] < 2)
+		if (op[i] < 2 || i == optlen - 1)
 			i++;
 		else
-			i += op[i+1]?:1;
+			i += op[i + 1] ? : 1;
 	}
 
 	spin_unlock_bh(&dccp_buflock);
diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c
index e8991130a3de..f76cf18f1a24 100644
--- a/net/netfilter/xt_tcpudp.c
+++ b/net/netfilter/xt_tcpudp.c
@@ -59,8 +59,10 @@ tcp_find_option(u_int8_t option,
 
 	for (i = 0; i < optlen; ) {
 		if (op[i] == option) return !invert;
-		if (op[i] < 2) i++;
-		else i += op[i+1]?:1;
+		if (op[i] < 2 || i == optlen - 1)
+			i++;
+		else
+			i += op[i + 1] ? : 1;
 	}
 
 	return invert;
-- 
cgit v1.2.3


From f1ba83755d81c6fc66ac7acd723d238f974091e9 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Sun, 8 Mar 2026 02:24:06 +0900
Subject: netfilter: nfnetlink_queue: fix entry leak in bridge verdict error
 path

nfqnl_recv_verdict() calls find_dequeue_entry() to remove the queue
entry from the queue data structures, taking ownership of the entry.
For PF_BRIDGE packets, it then calls nfqa_parse_bridge() to parse VLAN
attributes.  If nfqa_parse_bridge() returns an error (e.g. NFQA_VLAN
present but NFQA_VLAN_TCI missing), the function returns immediately
without freeing the dequeued entry or its sk_buff.

This leaks the nf_queue_entry, its associated sk_buff, and all held
references (net_device refcounts, struct net refcount).  Repeated
triggering exhausts kernel memory.

Fix this by dropping the entry via nfqnl_reinject() with NF_DROP verdict
on the error path, consistent with other error handling in this file.

Fixes: 8d45ff22f1b4 ("netfilter: bridge: nf queue verdict to use NFQA_VLAN and NFQA_L2HDR")
Reviewed-by: David Dull <monderasdor@gmail.com>
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_queue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 7f5248b5f1ee..47f7f62906e2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1546,8 +1546,10 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 
 	if (entry->state.pf == PF_BRIDGE) {
 		err = nfqa_parse_bridge(entry, nfqa);
-		if (err < 0)
+		if (err < 0) {
+			nfqnl_reinject(entry, NF_DROP);
 			return err;
+		}
 	}
 
 	if (nfqa[NFQA_PAYLOAD]) {
-- 
cgit v1.2.3


From 6dcee8496d53165b2d8a5909b3050b62ae71fe89 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Sun, 8 Mar 2026 02:23:34 +0900
Subject: netfilter: nfnetlink_cthelper: fix OOB read in
 nfnl_cthelper_dump_table()

nfnl_cthelper_dump_table() has a 'goto restart' that jumps to a label
inside the for loop body.  When the "last" helper saved in cb->args[1]
is deleted between dump rounds, every entry fails the (cur != last)
check, so cb->args[1] is never cleared.  The for loop finishes with
cb->args[0] == nf_ct_helper_hsize, and the 'goto restart' jumps back
into the loop body bypassing the bounds check, causing an 8-byte
out-of-bounds read on nf_ct_helper_hash[nf_ct_helper_hsize].

The 'goto restart' block was meant to re-traverse the current bucket
when "last" is no longer found, but it was placed after the for loop
instead of inside it.  Move the block into the for loop body so that
the restart only occurs while cb->args[0] is still within bounds.

 BUG: KASAN: slab-out-of-bounds in nfnl_cthelper_dump_table+0x9f/0x1b0
 Read of size 8 at addr ffff888104ca3000 by task poc_cthelper/131
 Call Trace:
  nfnl_cthelper_dump_table+0x9f/0x1b0
  netlink_dump+0x333/0x880
  netlink_recvmsg+0x3e2/0x4b0
  sock_recvmsg+0xde/0xf0
  __sys_recvfrom+0x150/0x200
  __x64_sys_recvfrom+0x76/0x90
  do_syscall_64+0xc3/0x6e0

 Allocated by task 1:
  __kvmalloc_node_noprof+0x21b/0x700
  nf_ct_alloc_hashtable+0x65/0xd0
  nf_conntrack_helper_init+0x21/0x60
  nf_conntrack_init_start+0x18d/0x300
  nf_conntrack_standalone_init+0x12/0xc0

Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_cthelper.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index d658b1478fa0..d545fa459455 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -601,10 +601,10 @@ restart:
 				goto out;
 			}
 		}
-	}
-	if (cb->args[1]) {
-		cb->args[1] = 0;
-		goto restart;
+		if (cb->args[1]) {
+			cb->args[1] = 0;
+			goto restart;
+		}
 	}
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 329f0b9b48ee6ab59d1ab72fef55fe8c6463a6cf Mon Sep 17 00:00:00 2001
From: Yuan Tan <tanyuan98@outlook.com>
Date: Mon, 9 Mar 2026 03:41:46 -0700
Subject: netfilter: xt_IDLETIMER: reject rev0 reuse of ALARM timer labels

IDLETIMER revision 0 rules reuse existing timers by label and always call
mod_timer() on timer->timer.

If the label was created first by revision 1 with XT_IDLETIMER_ALARM,
the object uses alarm timer semantics and timer->timer is never initialized.
Reusing that object from revision 0 causes mod_timer() on an uninitialized
timer_list, triggering debugobjects warnings and possible panic when
panic_on_warn=1.

Fix this by rejecting revision 0 rule insertion when an existing timer with
the same label is of ALARM type.

Fixes: 68983a354a65 ("netfilter: xtables: Add snapshot of hardidletimer target")
Co-developed-by: Yifan Wu <yifanwucs@gmail.com>
Signed-off-by: Yifan Wu <yifanwucs@gmail.com>
Co-developed-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Xin Liu <dstsmallbird@foxmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_IDLETIMER.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 5d93e225d0f8..517106165ad2 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -318,6 +318,12 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
 
 	info->timer = __idletimer_tg_find_by_label(info->label);
 	if (info->timer) {
+		if (info->timer->timer_type & XT_IDLETIMER_ALARM) {
+			pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n");
+			mutex_unlock(&list_mutex);
+			return -EINVAL;
+		}
+
 		info->timer->refcnt++;
 		mod_timer(&info->timer->timer,
 			  secs_to_jiffies(info->timeout) + jiffies);
-- 
cgit v1.2.3


From bf29cb3641b80bac759c3332b02e0b270e16bf94 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Fri, 6 Mar 2026 11:56:48 +0800
Subject: perf annotate: Fix hashmap__new() error checking

The hashmap__new() function never returns NULL, it returns error
pointers. Fix the error checking to match.

Additionally, set src->samples to NULL to prevent any later code from
accidentally using the error pointer.

Fixes: d3e7cad6f36d9e80 ("perf annotate: Add a hashmap for symbol histogram")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tianyou Li <tianyou.li@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2e3522905046..63f0ee9d4c03 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -44,6 +44,7 @@
 #include "strbuf.h"
 #include <regex.h>
 #include <linux/bitops.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
@@ -137,8 +138,10 @@ static int annotated_source__alloc_histograms(struct annotated_source *src,
 		return -1;
 
 	src->samples = hashmap__new(sym_hist_hash, sym_hist_equal, NULL);
-	if (src->samples == NULL)
+	if (IS_ERR(src->samples)) {
 		zfree(&src->histograms);
+		src->samples = NULL;
+	}
 
 	return src->histograms ? 0 : -1;
 }
-- 
cgit v1.2.3


From 6ab3532b4c98f4e51969f0e5f3fc919c535f3ce1 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 9 Mar 2026 21:54:17 +0100
Subject: ACPI: video: Switch over to auxiliary bus type

Commit 02c057ddefef ("ACPI: video: Convert the driver to a platform one")
switched over the ACPI video bus driver from an ACPI driver to a platform
driver, but that change introduced an unwanted and unexpected side effect.
Namely, on some systems, the ACPI device object of the ACPI video bus
device is an ACPI companion of multiple platform devices and, after
adding video_device_ids[] as an acpi_match_table to the acpi_video_bus
platform driver, all of those devices started to match that driver and
its probe callback is invoked for all of them (it fails, but it leaves
a confusing message in the log).  Moreover, the MODULE_DEVICE_TABLE()
of the ACPI video driver module matches all of the devices sharing the
ACPI companion with the ACPI video bus device.

To address this, make the core ACPI device enumeration code create an
auxiliary device for the ACPI video bus device object instead of a
platform device and switch over the ACPI video bus driver (once more)
to an auxiliary driver.

Auxiliary driver generally is a better match for ACPI video bus than
platform driver, among other things because the ACPI video bus device
does not require any resources to be allocated for it during
enumeration.  It also allows the ACPI video bus driver to stop abusing
device matching based on ACPI device IDs and it allows a special case
to be dropped from acpi_create_platform_device() because that function
need not worry about the ACPI video bus device any more.

Fixes: 02c057ddefef ("ACPI: video: Convert the driver to a platform one")
Reported-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Closes: https://lore.kernel.org/linux-acpi/007e3390-6b2b-457e-83c7-c794c5952018@amd.com/
Tested-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
[ rjw: Added AUXILIARY_BUS selection to CONFIG_ACPI to fix build issue ]
[ rjw: Fixed error path in acpi_create_video_bus_device() ]
Link: https://patch.msgid.link/5986516.DvuYhMxLoT@rafael.j.wysocki
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Kconfig         |  1 +
 drivers/acpi/acpi_platform.c |  2 +-
 drivers/acpi/acpi_video.c    | 45 ++++++++++++++++++++++----------------------
 drivers/acpi/scan.c          | 45 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 69 insertions(+), 24 deletions(-)

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index df0ff0764d0d..6f4b545f7377 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -9,6 +9,7 @@ config ARCH_SUPPORTS_ACPI
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
 	depends on ARCH_SUPPORTS_ACPI
+	select AUXILIARY_BUS
 	select PNP
 	select NLS
 	select CRC32
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 64199b19ceff..a09636a4168e 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -135,7 +135,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev,
 		}
 	}
 
-	if (adev->device_type == ACPI_BUS_TYPE_DEVICE && !adev->pnp.type.backlight) {
+	if (adev->device_type == ACPI_BUS_TYPE_DEVICE) {
 		LIST_HEAD(resource_list);
 
 		count = acpi_dev_get_resources(adev, &resource_list, NULL, NULL);
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index 3fa28f1abca3..adbaf0226c90 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -9,6 +9,7 @@
 
 #define pr_fmt(fmt) "ACPI: video: " fmt
 
+#include <linux/auxiliary_bus.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -21,7 +22,6 @@
 #include <linux/sort.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/dmi.h>
 #include <linux/suspend.h>
@@ -77,8 +77,9 @@ static int register_count;
 static DEFINE_MUTEX(register_count_mutex);
 static DEFINE_MUTEX(video_list_lock);
 static LIST_HEAD(video_bus_head);
-static int acpi_video_bus_probe(struct platform_device *pdev);
-static void acpi_video_bus_remove(struct platform_device *pdev);
+static int acpi_video_bus_probe(struct auxiliary_device *aux_dev,
+				const struct auxiliary_device_id *id);
+static void acpi_video_bus_remove(struct auxiliary_device *aux);
 static void acpi_video_bus_notify(acpi_handle handle, u32 event, void *data);
 
 /*
@@ -93,19 +94,16 @@ enum acpi_video_level_idx {
 	ACPI_VIDEO_FIRST_LEVEL,		/* actual supported levels begin here */
 };
 
-static const struct acpi_device_id video_device_ids[] = {
-	{ACPI_VIDEO_HID, 0},
-	{"", 0},
+static const struct auxiliary_device_id video_bus_auxiliary_id_table[] = {
+	{ .name = "acpi.video_bus" },
+	{},
 };
-MODULE_DEVICE_TABLE(acpi, video_device_ids);
+MODULE_DEVICE_TABLE(auxiliary, video_bus_auxiliary_id_table);
 
-static struct platform_driver acpi_video_bus = {
+static struct auxiliary_driver acpi_video_bus = {
 	.probe = acpi_video_bus_probe,
 	.remove = acpi_video_bus_remove,
-	.driver = {
-		.name = "acpi-video",
-		.acpi_match_table = video_device_ids,
-	},
+	.id_table = video_bus_auxiliary_id_table,
 };
 
 struct acpi_video_bus_flags {
@@ -1885,7 +1883,7 @@ static void acpi_video_dev_add_notify_handler(struct acpi_video_device *device)
 }
 
 static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video,
-					     struct platform_device *pdev)
+					     struct device *parent)
 {
 	struct input_dev *input;
 	struct acpi_video_device *dev;
@@ -1908,7 +1906,7 @@ static int acpi_video_bus_add_notify_handler(struct acpi_video_bus *video,
 	input->phys = video->phys;
 	input->id.bustype = BUS_HOST;
 	input->id.product = 0x06;
-	input->dev.parent = &pdev->dev;
+	input->dev.parent = parent;
 	input->evbit[0] = BIT(EV_KEY);
 	set_bit(KEY_SWITCHVIDEOMODE, input->keybit);
 	set_bit(KEY_VIDEO_NEXT, input->keybit);
@@ -1980,9 +1978,10 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video)
 
 static int instance;
 
-static int acpi_video_bus_probe(struct platform_device *pdev)
+static int acpi_video_bus_probe(struct auxiliary_device *aux_dev,
+				const struct auxiliary_device_id *id_unused)
 {
-	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+	struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev);
 	struct acpi_video_bus *video;
 	bool auto_detect;
 	int error;
@@ -2019,7 +2018,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev)
 		instance++;
 	}
 
-	platform_set_drvdata(pdev, video);
+	auxiliary_set_drvdata(aux_dev, video);
 
 	video->device = device;
 	strscpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
@@ -2068,7 +2067,7 @@ static int acpi_video_bus_probe(struct platform_device *pdev)
 	    !auto_detect)
 		acpi_video_bus_register_backlight(video);
 
-	error = acpi_video_bus_add_notify_handler(video, pdev);
+	error = acpi_video_bus_add_notify_handler(video, &aux_dev->dev);
 	if (error)
 		goto err_del;
 
@@ -2096,10 +2095,10 @@ err_free_video:
 	return error;
 }
 
-static void acpi_video_bus_remove(struct platform_device *pdev)
+static void acpi_video_bus_remove(struct auxiliary_device *aux_dev)
 {
-	struct acpi_video_bus *video = platform_get_drvdata(pdev);
-	struct acpi_device *device = ACPI_COMPANION(&pdev->dev);
+	struct acpi_video_bus *video = auxiliary_get_drvdata(aux_dev);
+	struct acpi_device *device = ACPI_COMPANION(&aux_dev->dev);
 
 	acpi_dev_remove_notify_handler(device, ACPI_DEVICE_NOTIFY,
 				       acpi_video_bus_notify);
@@ -2163,7 +2162,7 @@ int acpi_video_register(void)
 
 	dmi_check_system(video_dmi_table);
 
-	ret = platform_driver_register(&acpi_video_bus);
+	ret = auxiliary_driver_register(&acpi_video_bus);
 	if (ret)
 		goto leave;
 
@@ -2183,7 +2182,7 @@ void acpi_video_unregister(void)
 {
 	mutex_lock(&register_count_mutex);
 	if (register_count) {
-		platform_driver_unregister(&acpi_video_bus);
+		auxiliary_driver_unregister(&acpi_video_bus);
 		register_count = 0;
 		may_report_brightness_keys = false;
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index dfdd004fb1a9..e8cdbdb46fdb 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -6,6 +6,7 @@
 #define pr_fmt(fmt) "ACPI: " fmt
 
 #include <linux/async.h>
+#include <linux/auxiliary_bus.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -2192,6 +2193,44 @@ static acpi_status acpi_bus_check_add_2(acpi_handle handle, u32 lvl_not_used,
 	return acpi_bus_check_add(handle, false, (struct acpi_device **)ret_p);
 }
 
+static void acpi_video_bus_device_release(struct device *dev)
+{
+	struct auxiliary_device *aux_dev = to_auxiliary_dev(dev);
+
+	kfree(aux_dev);
+}
+
+static void acpi_create_video_bus_device(struct acpi_device *adev,
+					 struct acpi_device *parent)
+{
+	struct auxiliary_device *aux_dev;
+	static unsigned int aux_dev_id;
+
+	aux_dev = kzalloc_obj(*aux_dev);
+	if (!aux_dev)
+		return;
+
+	aux_dev->id = aux_dev_id++;
+	aux_dev->name = "video_bus";
+	aux_dev->dev.parent = acpi_get_first_physical_node(parent);
+	if (!aux_dev->dev.parent)
+		goto err;
+
+	aux_dev->dev.release = acpi_video_bus_device_release;
+
+	if (auxiliary_device_init(aux_dev))
+		goto err;
+
+	ACPI_COMPANION_SET(&aux_dev->dev, adev);
+	if (__auxiliary_device_add(aux_dev, "acpi"))
+		auxiliary_device_uninit(aux_dev);
+
+	return;
+
+err:
+	kfree(aux_dev);
+}
+
 struct acpi_scan_system_dev {
 	struct list_head node;
 	struct acpi_device *adev;
@@ -2229,6 +2268,12 @@ static void acpi_default_enumeration(struct acpi_device *device)
 			sd->adev = device;
 			list_add_tail(&sd->node, &acpi_scan_system_dev_list);
 		}
+	} else if (device->pnp.type.backlight) {
+		struct acpi_device *parent;
+
+		parent = acpi_dev_parent(device);
+		if (parent)
+			acpi_create_video_bus_device(device, parent);
 	} else {
 		/* For a regular device object, create a platform device. */
 		acpi_create_platform_device(device, NULL);
-- 
cgit v1.2.3


From e53c0e99fd93da200c413deb57875f9f5fdb314a Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Sat, 7 Mar 2026 09:50:35 +0000
Subject: spi: cadence-qspi: Fix requesting of APB and AHB clocks on JH7110

The move of the AHB and APB clocks from a JH7110 specific quirk to the
main clock init dropped the specification of the clock names to request
for the AHB and APB clocks, resulting in the clock framework requesting
a clock with a NULL name three times.  On most platforms where the
clocks are physically the same or some are always on this makes no
difference but the reason we had the specific quirk for JH7110 is that
it does actually have separate, controllable clocks.  Update the new
code to request the AHB and APB clocks by name to restore the original
behaviour on JH7110.

Fixes: 324ecc7788c2 ("spi: cadence-qspi: Kill cqspi_jh7110_clk_init")
Reported-by: Ron Economos <re@w6rz.net>
Closes: https://lore.kernel.org/r/a3ca5e9b-7446-497e-8df2-7ef2b42a02e9@w6rz.net
Tested-by: Ron Economos <re@w6rz.net>
Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20260307-spi-cadence-qspi-fix-jh7110-v1-1-c9f37b8c58b1@kernel.org
---
 drivers/spi/spi-cadence-quadspi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 649ff55333f0..5fb0cb07c110 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -76,6 +76,11 @@ struct cqspi_flash_pdata {
 	u8		cs;
 };
 
+static const struct clk_bulk_data cqspi_clks[CLK_QSPI_NUM] = {
+	[CLK_QSPI_APB] = { .id = "apb" },
+	[CLK_QSPI_AHB] = { .id = "ahb" },
+};
+
 struct cqspi_st {
 	struct platform_device	*pdev;
 	struct spi_controller	*host;
@@ -1823,6 +1828,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	}
 
 	/* Obtain QSPI clocks. */
+	memcpy(&cqspi->clks, &cqspi_clks, sizeof(cqspi->clks));
 	ret = devm_clk_bulk_get_optional(dev, CLK_QSPI_NUM, cqspi->clks);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to get clocks\n");
-- 
cgit v1.2.3


From 5d0efaf47ee90ac60efae790acee3a3ed99ebf80 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Tue, 10 Mar 2026 12:25:52 +0800
Subject: regulator: pca9450: Correct interrupt type

Kernel warning on i.MX8MP-EVK when doing module test:
irq: type mismatch, failed to map hwirq-3 for gpio@30200000!

Per PCA945[X] specification: The IRQ_B pin is pulled low when any unmasked
interrupt bit status is changed and it is released high once application
processor read INT1 register.

So the interrupt should be configured as IRQF_TRIGGER_LOW, not
IRQF_TRIGGER_FALLING.

Fixes: 0935ff5f1f0a4 ("regulator: pca9450: add pca9450 pmic driver")
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20260310-pca9450-irq-v1-1-36adf52c2c55@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 5fa868264250..2205f6de37e7 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -1369,7 +1369,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	if (pca9450->irq) {
 		ret = devm_request_threaded_irq(pca9450->dev, pca9450->irq, NULL,
 						pca9450_irq_handler,
-						(IRQF_TRIGGER_FALLING | IRQF_ONESHOT),
+						(IRQF_TRIGGER_LOW | IRQF_ONESHOT),
 						"pca9450-irq", pca9450);
 		if (ret != 0)
 			return dev_err_probe(pca9450->dev, ret, "Failed to request IRQ: %d\n",
-- 
cgit v1.2.3


From 21b3fb7dc19caa488d285e3c47999f7f1a179334 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Tue, 10 Mar 2026 12:25:53 +0800
Subject: regulator: pca9450: Correct probed name for PCA9452

An incorrect device name was logged for PCA9452 because the dev_info()
ternary omitted PCA9452 and fell through to "pca9450bc". Introduce a
type_name and set it per device type so the probed message matches the
actual PMIC. While here, make the PCA9451A case explicit.

No functional changes.

Fixes: 017b76fb8e5b6 ("regulator: pca9450: Add PMIC pca9452 support")
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20260310-pca9450-irq-v1-2-36adf52c2c55@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index 2205f6de37e7..45d7dc44c2cd 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -1293,6 +1293,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	struct regulator_dev *ldo5;
 	struct pca9450 *pca9450;
 	unsigned int device_id, i;
+	const char *type_name;
 	int ret;
 
 	pca9450 = devm_kzalloc(&i2c->dev, sizeof(struct pca9450), GFP_KERNEL);
@@ -1303,15 +1304,22 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	case PCA9450_TYPE_PCA9450A:
 		regulator_desc = pca9450a_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9450a_regulators);
+		type_name = "pca9450a";
 		break;
 	case PCA9450_TYPE_PCA9450BC:
 		regulator_desc = pca9450bc_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators);
+		type_name = "pca9450bc";
 		break;
 	case PCA9450_TYPE_PCA9451A:
+		regulator_desc = pca9451a_regulators;
+		pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators);
+		type_name = "pca9451a";
+		break;
 	case PCA9450_TYPE_PCA9452:
 		regulator_desc = pca9451a_regulators;
 		pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators);
+		type_name = "pca9452";
 		break;
 	default:
 		dev_err(&i2c->dev, "Unknown device type");
@@ -1413,9 +1421,7 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 					  pca9450_i2c_restart_handler, pca9450))
 		dev_warn(&i2c->dev, "Failed to register restart handler\n");
 
-	dev_info(&i2c->dev, "%s probed.\n",
-		type == PCA9450_TYPE_PCA9450A ? "pca9450a" :
-		(type == PCA9450_TYPE_PCA9451A ? "pca9451a" : "pca9450bc"));
+	dev_info(&i2c->dev, "%s probed.\n", type_name);
 
 	return 0;
 }
-- 
cgit v1.2.3


From be34705aa527872e5ce83927b7bc9307ba8095ca Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Fri, 6 Mar 2026 12:10:52 +0800
Subject: perf ftrace: Fix hashmap__new() error checking

The hashmap__new() function never returns NULL, it returns error
pointers. Fix the error checking to match.

Additionally, set ftrace->profile_hash to NULL on error, and return the
exact error code from hashmap__new().

Fixes: 0f223813edd051a5 ("perf ftrace: Add 'profile' command")
Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-ftrace.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 6b6eec65f93f..4cc33452d79b 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -18,6 +18,7 @@
 #include <poll.h>
 #include <ctype.h>
 #include <linux/capability.h>
+#include <linux/err.h>
 #include <linux/string.h>
 #include <sys/stat.h>
 
@@ -1209,8 +1210,12 @@ static int prepare_func_profile(struct perf_ftrace *ftrace)
 	ftrace->graph_verbose = 0;
 
 	ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL);
-	if (ftrace->profile_hash == NULL)
-		return -ENOMEM;
+	if (IS_ERR(ftrace->profile_hash)) {
+		int err = PTR_ERR(ftrace->profile_hash);
+
+		ftrace->profile_hash = NULL;
+		return err;
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 40e9cd4ae8ec43b107ed2bff422a8fa39dcf4e4b Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Tue, 10 Mar 2026 15:23:29 +0100
Subject: s390/dasd: Move quiesce state with pprc swap

Quiesce and resume is a mechanism to suspend operations on DASD devices.
In the context of a controlled copy pair swap operation, the quiesce
operation is usually issued before the actual swap and a resume
afterwards.

During the swap operation, the underlying device is exchanged. Therefore,
the quiesce flag must be moved to the secondary device to ensure a
consistent quiesce state after the swap.

The secondary device itself cannot be suspended separately because there
is no separate block device representation for it.

Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability")
Cc: stable@vger.kernel.org #6.1
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Link: https://patch.msgid.link/20260310142330.4080106-2-sth@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index b08e900687f3..e8f0e302a625 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -6182,6 +6182,11 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 			dev_name(&secondary->cdev->dev), rc);
 	}
 
+	if (primary->stopped & DASD_STOPPED_QUIESCE) {
+		dasd_device_set_stop_bits(secondary, DASD_STOPPED_QUIESCE);
+		dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE);
+	}
+
 	/* re-enable device */
 	dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC);
 	dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC);
-- 
cgit v1.2.3


From 4c527c7e030672efd788d0806d7a68972a7ba3c1 Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Tue, 10 Mar 2026 15:23:30 +0100
Subject: s390/dasd: Copy detected format information to secondary device

During online processing for a DASD device an IO operation is started to
determine the format of the device. CDL format contains specifically
sized blocks at the beginning of the disk.

For a PPRC secondary device no real IO operation is possible therefore
this IO request can not be started and this step is skipped for online
processing of secondary devices. This is generally fine since the
secondary is a copy of the primary device.

In case of an additional partition detection that is run after a swap
operation the format information is needed to properly drive partition
detection IO.

Currently the information is not passed leading to IO errors during
partition detection and a wrongly detected partition table which in turn
might lead to data corruption on the disk with the wrong partition table.

Fix by passing the format information from primary to secondary device.

Fixes: 413862caad6f ("s390/dasd: add copy pair swap capability")
Cc: stable@vger.kernel.org #6.1
Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Acked-by: Eduard Shishkin <edward6@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Link: https://patch.msgid.link/20260310142330.4080106-3-sth@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index e8f0e302a625..c0f665a2929d 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -6135,6 +6135,7 @@ static void copy_pair_set_active(struct dasd_copy_relation *copy, char *new_busi
 static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid,
 				    char *sec_busid)
 {
+	struct dasd_eckd_private *prim_priv, *sec_priv;
 	struct dasd_device *primary, *secondary;
 	struct dasd_copy_relation *copy;
 	struct dasd_block *block;
@@ -6155,6 +6156,9 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 	if (!secondary)
 		return DASD_COPYPAIRSWAP_SECONDARY;
 
+	prim_priv = primary->private;
+	sec_priv = secondary->private;
+
 	/*
 	 * usually the device should be quiesced for swap
 	 * for paranoia stop device and requeue requests again
@@ -6187,6 +6191,13 @@ static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid
 		dasd_device_remove_stop_bits(primary, DASD_STOPPED_QUIESCE);
 	}
 
+	/*
+	 * The secondary device never got through format detection, but since it
+	 * is a copy of the primary device, the format is exactly the same;
+	 * therefore, the detected layout can simply be copied.
+	 */
+	sec_priv->uses_cdl = prim_priv->uses_cdl;
+
 	/* re-enable device */
 	dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC);
 	dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC);
-- 
cgit v1.2.3


From d557640e4ce589a24dca5ca7ce3b9680f471325f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sat, 7 Mar 2026 17:12:05 +0100
Subject: sched: idle: Make skipping governor callbacks more consistent

If the cpuidle governor .select() callback is skipped because there
is only one idle state in the cpuidle driver, the .reflect() callback
should be skipped as well, at least for consistency (if not for
correctness), so do it.

Fixes: e5c9ffc6ae1b ("cpuidle: Skip governor when only one idle state is available")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Reviewed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://patch.msgid.link/12857700.O9o76ZdvQC@rafael.j.wysocki
---
 drivers/cpuidle/cpuidle.c | 10 ----------
 kernel/sched/idle.c       | 11 ++++++++++-
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 65fbb8e807b9..c7876e9e024f 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -359,16 +359,6 @@ noinstr int cpuidle_enter_state(struct cpuidle_device *dev,
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		   bool *stop_tick)
 {
-	/*
-	 * If there is only a single idle state (or none), there is nothing
-	 * meaningful for the governor to choose. Skip the governor and
-	 * always use state 0 with the tick running.
-	 */
-	if (drv->state_count <= 1) {
-		*stop_tick = false;
-		return 0;
-	}
-
 	return cpuidle_curr_governor->select(drv, dev, stop_tick);
 }
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 3681b6ad9276..b95449165122 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -221,7 +221,7 @@ static void cpuidle_idle_call(void)
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
-	} else {
+	} else if (drv->state_count > 1) {
 		bool stop_tick = true;
 
 		/*
@@ -239,6 +239,15 @@ static void cpuidle_idle_call(void)
 		 * Give the governor an opportunity to reflect on the outcome
 		 */
 		cpuidle_reflect(dev, entered_state);
+	} else {
+		tick_nohz_idle_retain_tick();
+
+		/*
+		 * If there is only a single idle state (or none), there is
+		 * nothing meaningful for the governor to choose.  Skip the
+		 * governor and always use state 0.
+		 */
+		call_cpuidle(drv, dev, 0);
 	}
 
 exit_idle:
-- 
cgit v1.2.3


From c7c92f76f90a81dcc5c48cefa3343556501870b9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Mar 2026 10:53:06 -0800
Subject: perf annotate loongarch: Fix off-by-one bug in outside check

A copy-paste of a similar issue fixed by Peter Collingbourne in:
https://lore.kernel.org/linux-perf-users/20260304190613.2507582-1-pcc@google.com/

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <nick.desaulniers+lkml@gmail.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate-arch/annotate-loongarch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate-arch/annotate-loongarch.c b/tools/perf/util/annotate-arch/annotate-loongarch.c
index 3aeab453a059..950f34e59e5c 100644
--- a/tools/perf/util/annotate-arch/annotate-loongarch.c
+++ b/tools/perf/util/annotate-arch/annotate-loongarch.c
@@ -93,7 +93,7 @@ static int loongarch_jump__parse(const struct arch *arch, struct ins_operands *o
 	start = map__unmap_ip(map, sym->start);
 	end = map__unmap_ip(map, sym->end);
 
-	ops->target.outside = target.addr < start || target.addr > end;
+	ops->target.outside = target.addr < start || target.addr >= end;
 
 	if (maps__find_ams(thread__maps(ms->thread), &target) == 0 &&
 	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
-- 
cgit v1.2.3


From 52a8a1ba883defbfe3200baa22cf4cd21985d51a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 4 Mar 2026 20:26:20 -0800
Subject: xfs: fix undersized l_iclog_roundoff values

If the superblock doesn't list a log stripe unit, we set the incore log
roundoff value to 512.  This leads to corrupt logs and unmountable
filesystems in generic/617 on a disk with 4k physical sectors...

XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c
XFS (sda1): Torn write (CRC failure) detected at log block 0x318e. Truncating head block from 0x3197.
XFS (sda1): failed to locate log tail
XFS (sda1): log mount/recovery failed: error -74
XFS (sda1): log mount failed
XFS (sda1): Mounting V5 Filesystem ff3121ca-26e6-4b77-b742-aaff9a449e1c
XFS (sda1): Ending clean mount

...on the current xfsprogs for-next which has a broken mkfs.  xfs_info
shows this...

meta-data=/dev/sda1              isize=512    agcount=4, agsize=644992 blks
         =                       sectsz=4096  attr=2, projid32bit=1
         =                       crc=1        finobt=1, sparse=1, rmapbt=1
         =                       reflink=1    bigtime=1 inobtcount=1 nrext64=1
         =                       exchange=1   metadir=1
data     =                       bsize=4096   blocks=2579968, imaxpct=25
         =                       sunit=0      swidth=0 blks
naming   =version 2              bsize=4096   ascii-ci=0, ftype=1, parent=1
log      =internal log           bsize=4096   blocks=16384, version=2
         =                       sectsz=4096  sunit=0 blks, lazy-count=1
realtime =none                   extsz=4096   blocks=0, rtextents=0
         =                       rgcount=0    rgsize=268435456 extents
         =                       zoned=0      start=0 reserved=0

...observe that the log section has sectsz=4096 sunit=0, which means
that the roundoff factor is 512, not 4096 as you'd expect.  We should
fix mkfs not to generate broken filesystems, but anyone can fuzz the
ondisk superblock so we should be more cautious.  I think the inadequate
logic predates commit a6a65fef5ef8d0, but that's clearly going to
require a different backport.

Cc: stable@vger.kernel.org # v5.14
Fixes: a6a65fef5ef8d0 ("xfs: log stripe roundoff is a property of the log")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_log.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index b96f262ba139..f807f8f4f705 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1357,6 +1357,8 @@ xlog_alloc_log(
 
 	if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1)
 		log->l_iclog_roundoff = mp->m_sb.sb_logsunit;
+	else if (mp->m_sb.sb_logsectsize > 0)
+		log->l_iclog_roundoff = mp->m_sb.sb_logsectsize;
 	else
 		log->l_iclog_roundoff = BBSIZE;
 
-- 
cgit v1.2.3


From b4e78f1427c7d6859229ae9616df54e1fc05a516 Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Sun, 8 Mar 2026 14:20:59 -0400
Subject: nvme-pci: Fix slab-out-of-bounds in nvme_dbbuf_set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dev->online_queues is a count incremented in nvme_init_queue. Thus,
valid indices are 0 through dev->online_queues − 1.

This patch fixes the loop condition to ensure the index stays within the
valid range. Index 0 is excluded because it is the admin queue.

KASAN splat:

==================================================================
BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline]
BUG: KASAN: slab-out-of-bounds in nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404
Read of size 2 at addr ffff88800592a574 by task kworker/u8:5/74

CPU: 0 UID: 0 PID: 74 Comm: kworker/u8:5 Not tainted 6.19.0-dirty #10 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
Workqueue: nvme-reset-wq nvme_reset_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0xea/0x150 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xce/0x5d0 mm/kasan/report.c:482
 kasan_report+0xdc/0x110 mm/kasan/report.c:595
 __asan_report_load2_noabort+0x18/0x20 mm/kasan/report_generic.c:379
 nvme_dbbuf_free drivers/nvme/host/pci.c:377 [inline]
 nvme_dbbuf_set+0x39c/0x400 drivers/nvme/host/pci.c:404
 nvme_reset_work+0x36b/0x8c0 drivers/nvme/host/pci.c:3252
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246
 </TASK>

Allocated by task 34 on cpu 1 at 4.241550s:
 kasan_save_stack+0x2c/0x60 mm/kasan/common.c:57
 kasan_save_track+0x1c/0x70 mm/kasan/common.c:78
 kasan_save_alloc_info+0x3c/0x50 mm/kasan/generic.c:570
 poison_kmalloc_redzone mm/kasan/common.c:398 [inline]
 __kasan_kmalloc+0xb5/0xc0 mm/kasan/common.c:415
 kasan_kmalloc include/linux/kasan.h:263 [inline]
 __do_kmalloc_node mm/slub.c:5657 [inline]
 __kmalloc_node_noprof+0x2bf/0x8d0 mm/slub.c:5663
 kmalloc_array_node_noprof include/linux/slab.h:1075 [inline]
 nvme_pci_alloc_dev drivers/nvme/host/pci.c:3479 [inline]
 nvme_probe+0x2f1/0x1820 drivers/nvme/host/pci.c:3534
 local_pci_probe+0xef/0x1c0 drivers/pci/pci-driver.c:324
 pci_call_probe drivers/pci/pci-driver.c:392 [inline]
 __pci_device_probe drivers/pci/pci-driver.c:417 [inline]
 pci_device_probe+0x743/0x920 drivers/pci/pci-driver.c:451
 call_driver_probe drivers/base/dd.c:583 [inline]
 really_probe+0x29b/0xb70 drivers/base/dd.c:661
 __driver_probe_device+0x3b0/0x4a0 drivers/base/dd.c:803
 driver_probe_device+0x56/0x1f0 drivers/base/dd.c:833
 __driver_attach_async_helper+0x155/0x340 drivers/base/dd.c:1159
 async_run_entry_fn+0xa6/0x4b0 kernel/async.c:129
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246

The buggy address belongs to the object at ffff88800592a000
 which belongs to the cache kmalloc-2k of size 2048
The buggy address is located 244 bytes to the right of
 allocated 1152-byte region [ffff88800592a000, ffff88800592a480)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5928
head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
anon flags: 0xfffffc0000040(head|node=0|zone=1|lastcpupid=0x1fffff)
page_type: f5(slab)
raw: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001
raw: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000
head: 000fffffc0000040 ffff888001042000 0000000000000000 dead000000000001
head: 0000000000000000 0000000000080008 00000000f5000000 0000000000000000
head: 000fffffc0000003 ffffea0000164a01 00000000ffffffff 00000000ffffffff
head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff88800592a400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff88800592a480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff88800592a500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                                                             ^
 ffff88800592a580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff88800592a600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================

Fixes: 0f0d2c876c96 (nvme: free sq/cq dbbuf pointers when dbbuf set fails)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9a7863e2001e..d90db12c7cd8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -544,7 +544,7 @@ static void nvme_dbbuf_set(struct nvme_dev *dev)
 		/* Free memory and continue on */
 		nvme_dbbuf_dma_free(dev);
 
-		for (i = 1; i <= dev->online_queues; i++)
+		for (i = 1; i < dev->online_queues; i++)
 			nvme_dbbuf_free(&dev->queues[i]);
 	}
 }
-- 
cgit v1.2.3


From 2922e3507f6d5caa7f1d07f145e186fc6f317a4e Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <kch@nvidia.com>
Date: Wed, 25 Feb 2026 20:30:03 -0800
Subject: nvmet: move async event work off nvmet-wq

For target nvmet_ctrl_free() flushes ctrl->async_event_work.
If nvmet_ctrl_free() runs on nvmet-wq, the flush re-enters workqueue
completion for the same worker:-

A. Async event work queued on nvmet-wq (prior to disconnect):
  nvmet_execute_async_event()
     queue_work(nvmet_wq, &ctrl->async_event_work)

  nvmet_add_async_event()
     queue_work(nvmet_wq, &ctrl->async_event_work)

B. Full pre-work chain (RDMA CM path):
  nvmet_rdma_cm_handler()
     nvmet_rdma_queue_disconnect()
       __nvmet_rdma_queue_disconnect()
         queue_work(nvmet_wq, &queue->release_work)
           process_one_work()
             lock((wq_completion)nvmet-wq)  <--------- 1st
             nvmet_rdma_release_queue_work()

C. Recursive path (same worker):
  nvmet_rdma_release_queue_work()
     nvmet_rdma_free_queue()
       nvmet_sq_destroy()
         nvmet_ctrl_put()
           nvmet_ctrl_free()
             flush_work(&ctrl->async_event_work)
               __flush_work()
                 touch_wq_lockdep_map()
                 lock((wq_completion)nvmet-wq) <--------- 2nd

Lockdep splat:

  ============================================
  WARNING: possible recursive locking detected
  6.19.0-rc3nvme+ #14 Tainted: G                 N
  --------------------------------------------
  kworker/u192:42/44933 is trying to acquire lock:
  ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x26/0x90

  but task is already holding lock:
  ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660

  3 locks held by kworker/u192:42/44933:
   #0: ffff888118a00948 ((wq_completion)nvmet-wq){+.+.}-{0:0}, at: process_one_work+0x53e/0x660
   #1: ffffc9000e6cbe28 ((work_completion)(&queue->release_work)){+.+.}-{0:0}, at: process_one_work+0x1c5/0x660
   #2: ffffffff82d4db60 (rcu_read_lock){....}-{1:3}, at: __flush_work+0x62/0x530

  Workqueue: nvmet-wq nvmet_rdma_release_queue_work [nvmet_rdma]
  Call Trace:
   __flush_work+0x268/0x530
   nvmet_ctrl_free+0x140/0x310 [nvmet]
   nvmet_cq_put+0x74/0x90 [nvmet]
   nvmet_rdma_free_queue+0x23/0xe0 [nvmet_rdma]
   nvmet_rdma_release_queue_work+0x19/0x50 [nvmet_rdma]
   process_one_work+0x206/0x660
   worker_thread+0x184/0x320
   kthread+0x10c/0x240
   ret_from_fork+0x319/0x390

Move async event work to a dedicated nvmet-aen-wq to avoid reentrant
flush on nvmet-wq.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/admin-cmd.c |  2 +-
 drivers/nvme/target/core.c      | 14 ++++++++++++--
 drivers/nvme/target/nvmet.h     |  1 +
 drivers/nvme/target/rdma.c      |  1 +
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 5e366502fb75..66fc8d2a7fe3 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1586,7 +1586,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
 	ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
 	mutex_unlock(&ctrl->lock);
 
-	queue_work(nvmet_wq, &ctrl->async_event_work);
+	queue_work(nvmet_aen_wq, &ctrl->async_event_work);
 }
 
 void nvmet_execute_keep_alive(struct nvmet_req *req)
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index eab3e4fc0f74..a25ac4bf9972 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -27,6 +27,8 @@ static DEFINE_IDA(cntlid_ida);
 
 struct workqueue_struct *nvmet_wq;
 EXPORT_SYMBOL_GPL(nvmet_wq);
+struct workqueue_struct *nvmet_aen_wq;
+EXPORT_SYMBOL_GPL(nvmet_aen_wq);
 
 /*
  * This read/write semaphore is used to synchronize access to configuration
@@ -206,7 +208,7 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	list_add_tail(&aen->entry, &ctrl->async_events);
 	mutex_unlock(&ctrl->lock);
 
-	queue_work(nvmet_wq, &ctrl->async_event_work);
+	queue_work(nvmet_aen_wq, &ctrl->async_event_work);
 }
 
 static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
@@ -1959,9 +1961,14 @@ static int __init nvmet_init(void)
 	if (!nvmet_wq)
 		goto out_free_buffered_work_queue;
 
+	nvmet_aen_wq = alloc_workqueue("nvmet-aen-wq",
+			WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+	if (!nvmet_aen_wq)
+		goto out_free_nvmet_work_queue;
+
 	error = nvmet_init_debugfs();
 	if (error)
-		goto out_free_nvmet_work_queue;
+		goto out_free_nvmet_aen_work_queue;
 
 	error = nvmet_init_discovery();
 	if (error)
@@ -1977,6 +1984,8 @@ out_exit_discovery:
 	nvmet_exit_discovery();
 out_exit_debugfs:
 	nvmet_exit_debugfs();
+out_free_nvmet_aen_work_queue:
+	destroy_workqueue(nvmet_aen_wq);
 out_free_nvmet_work_queue:
 	destroy_workqueue(nvmet_wq);
 out_free_buffered_work_queue:
@@ -1994,6 +2003,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_discovery();
 	nvmet_exit_debugfs();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(nvmet_aen_wq);
 	destroy_workqueue(nvmet_wq);
 	destroy_workqueue(buffered_io_wq);
 	destroy_workqueue(zbd_wq);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index b664b584fdc8..319d6a5e9cf0 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -501,6 +501,7 @@ extern struct kmem_cache *nvmet_bvec_cache;
 extern struct workqueue_struct *buffered_io_wq;
 extern struct workqueue_struct *zbd_wq;
 extern struct workqueue_struct *nvmet_wq;
+extern struct workqueue_struct *nvmet_aen_wq;
 
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 9c12b2361a6d..038432364967 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -2088,6 +2088,7 @@ static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 
 	flush_workqueue(nvmet_wq);
+	flush_workqueue(nvmet_aen_wq);
 }
 
 static struct ib_client nvmet_rdma_ib_client = {
-- 
cgit v1.2.3


From fc71f409b22ca831a9f87a2712eaa09ef2bb4a5e Mon Sep 17 00:00:00 2001
From: Sungwoo Kim <iam@sung-woo.kim>
Date: Sat, 7 Mar 2026 14:46:36 -0500
Subject: nvme-pci: Fix race bug in nvme_poll_irqdisable()

In the following scenario, pdev can be disabled between (1) and (3) by
(2). This sets pdev->msix_enabled = 0. Then, pci_irq_vector() will
return MSI-X IRQ(>15) for (1) whereas return INTx IRQ(<=15) for (2).
This causes IRQ warning because it tries to enable INTx IRQ that has
never been disabled before.

To fix this, save IRQ number into a local variable and ensure
disable_irq() and enable_irq() operate on the same IRQ number.  Even if
pci_free_irq_vectors() frees the IRQ concurrently, disable_irq() and
enable_irq() on a stale IRQ number is still valid and safe, and the
depth accounting reamins balanced.

task 1:
nvme_poll_irqdisable()
  disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)) ...(1)
  enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector))  ...(3)

task 2:
nvme_reset_work()
  nvme_dev_disable()
    pdev->msix_enable = 0;  ...(2)

crash log:

------------[ cut here ]------------
Unbalanced enable for IRQ 10
WARNING: kernel/irq/manage.c:753 at __enable_irq+0x102/0x190 kernel/irq/manage.c:753, CPU#1: kworker/1:0H/26
Modules linked in:
CPU: 1 UID: 0 PID: 26 Comm: kworker/1:0H Not tainted 6.19.0-dirty #9 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
Workqueue: kblockd blk_mq_timeout_work
RIP: 0010:__enable_irq+0x107/0x190 kernel/irq/manage.c:753
Code: ff df 48 89 fa 48 c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 79 48 8d 3d 2e 7a 3f 05 41 8b 74 24 2c <67> 48 0f b9 3a e8 ef b9 21 00 5b 41 5c 5d e9 46 54 66 03 e8 e1 b9
RSP: 0018:ffffc900001bf550 EFLAGS: 00010046
RAX: 0000000000000007 RBX: 0000000000000000 RCX: ffffffffb20c0e90
RDX: 0000000000000000 RSI: 000000000000000a RDI: ffffffffb74b88f0
RBP: ffffc900001bf560 R08: ffff88800197cf00 R09: 0000000000000001
R10: 0000000000000003 R11: 0000000000000003 R12: ffff8880012a6000
R13: 1ffff92000037eae R14: 000000000000000a R15: 0000000000000293
FS:  0000000000000000(0000) GS:ffff8880b49f7000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000555da4a25fa8 CR3: 00000000208e8000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 enable_irq+0x121/0x1e0 kernel/irq/manage.c:797
 nvme_poll_irqdisable+0x162/0x1c0 drivers/nvme/host/pci.c:1494
 nvme_timeout+0x965/0x14b0 drivers/nvme/host/pci.c:1744
 blk_mq_rq_timed_out block/blk-mq.c:1653 [inline]
 blk_mq_handle_expired+0x227/0x2d0 block/blk-mq.c:1721
 bt_iter+0x2fc/0x3a0 block/blk-mq-tag.c:292
 __sbitmap_for_each_set include/linux/sbitmap.h:269 [inline]
 sbitmap_for_each_set include/linux/sbitmap.h:290 [inline]
 bt_for_each block/blk-mq-tag.c:324 [inline]
 blk_mq_queue_tag_busy_iter+0x969/0x1e80 block/blk-mq-tag.c:536
 blk_mq_timeout_work+0x627/0x870 block/blk-mq.c:1763
 process_one_work+0x956/0x1aa0 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x65c/0xe60 kernel/workqueue.c:3421
 kthread+0x41a/0x930 kernel/kthread.c:463
 ret_from_fork+0x6f8/0x8c0 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246
 </TASK>
irq event stamp: 74478
hardirqs last  enabled at (74477): [<ffffffffb5720a9c>] __raw_spin_unlock_irq include/linux/spinlock_api_smp.h:159 [inline]
hardirqs last  enabled at (74477): [<ffffffffb5720a9c>] _raw_spin_unlock_irq+0x2c/0x60 kernel/locking/spinlock.c:202
hardirqs last disabled at (74478): [<ffffffffb57207b5>] __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
hardirqs last disabled at (74478): [<ffffffffb57207b5>] _raw_spin_lock_irqsave+0x85/0xa0 kernel/locking/spinlock.c:162
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last  enabled at (74304): [<ffffffffb1e9466c>] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723
softirqs last disabled at (74287): [<ffffffffb1e9466c>] __do_softirq kernel/softirq.c:656 [inline]
softirqs last disabled at (74287): [<ffffffffb1e9466c>] invoke_softirq kernel/softirq.c:496 [inline]
softirqs last disabled at (74287): [<ffffffffb1e9466c>] __irq_exit_rcu+0xdc/0x120 kernel/softirq.c:723
---[ end trace 0000000000000000 ]---

Fixes: fa059b856a59 (nvme-pci: Simplify nvme_poll_irqdisable)
Acked-by: Chao Shi <cshi008@fiu.edu>
Acked-by: Weidong Zhu <weizhu@fiu.edu>
Acked-by: Dave Tian <daveti@purdue.edu>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sungwoo Kim <iam@sung-woo.kim>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d90db12c7cd8..93eb9f1cf9c1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1625,14 +1625,16 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
 {
 	struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
+	int irq;
 
 	WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
 
-	disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	irq = pci_irq_vector(pdev, nvmeq->cq_vector);
+	disable_irq(irq);
 	spin_lock(&nvmeq->cq_poll_lock);
 	nvme_poll_cq(nvmeq, NULL);
 	spin_unlock(&nvmeq->cq_poll_lock);
-	enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+	enable_irq(irq);
 }
 
 static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
-- 
cgit v1.2.3


From 0375c81eb2256366cd9602441d48b8b937e79635 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Fri, 20 Feb 2026 14:30:16 +0100
Subject: nvme-core: do not pass empty queue_limits to blk_mq_alloc_queue()

In nvme_alloc_admin_tag_set(), an empty queue_limits struct is
currently allocated on the stack and passed by reference to
blk_mq_alloc_queue().

This is redundant because blk_mq_alloc_queue() already handles
a NULL limits pointer by internally substituting it with a default
empty queue_limits struct.
Remove the unnecessary local variable and pass a NULL value.

Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3bc0b9ea00ce..6370aa35cc06 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4834,7 +4834,6 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 		const struct blk_mq_ops *ops, unsigned int cmd_size)
 {
-	struct queue_limits lim = {};
 	int ret;
 
 	memset(set, 0, sizeof(*set));
@@ -4861,7 +4860,7 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ctrl->admin_q)
 		blk_put_queue(ctrl->admin_q);
 
-	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
+	ctrl->admin_q = blk_mq_alloc_queue(set, NULL, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
 		goto out_free_tagset;
-- 
cgit v1.2.3


From fa655a9ca73f7df32b8ca4d14ce11742f9578288 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 3 Mar 2026 22:31:01 +0100
Subject: nvme: Annotate struct nvme_dhchap_key with __counted_by

Add the __counted_by() compiler attribute to the flexible array member
'key' to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and
CONFIG_FORTIFY_SOURCE.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme-auth.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h
index 60e069a6757f..e75c29c51464 100644
--- a/include/linux/nvme-auth.h
+++ b/include/linux/nvme-auth.h
@@ -11,7 +11,7 @@
 struct nvme_dhchap_key {
 	size_t len;
 	u8 hash;
-	u8 key[];
+	u8 key[] __counted_by(len);
 };
 
 u32 nvme_auth_get_seqnum(void);
-- 
cgit v1.2.3


From bd98c6204d1195973b1760fe45860863deb6200c Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Fri, 13 Feb 2026 10:48:41 +0200
Subject: drivers: net: ice: fix devlink parameters get without irdma

If CONFIG_IRDMA isn't enabled but there are ice NICs in the system, the
driver will prevent full devlink dev param show dump because its rdma get
callbacks return ENODEV and stop the dump. For example:
 $ devlink dev param show
 pci/0000:82:00.0:
   name msix_vec_per_pf_max type generic
     values:
       cmode driverinit value 2
   name msix_vec_per_pf_min type generic
     values:
       cmode driverinit value 2
 kernel answers: No such device

Returning EOPNOTSUPP allows the dump to continue so we can see all devices'
devlink parameters.

Fixes: c24a65b6a27c ("iidc/ice/irdma: Update IDC to support multiple consumers")
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 6c72bd15db6d..6144cee8034d 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1360,7 +1360,7 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 
 	cdev = pf->cdev_info;
 	if (!cdev)
-		return -ENODEV;
+		return -EOPNOTSUPP;
 
 	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2);
 
@@ -1427,7 +1427,7 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id,
 
 	cdev = pf->cdev_info;
 	if (!cdev)
-		return -ENODEV;
+		return -EOPNOTSUPP;
 
 	ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP);
 
-- 
cgit v1.2.3


From efc54fb13d79117a825fef17364315a58682c7ec Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Thu, 29 Jan 2026 10:57:23 +0100
Subject: iavf: fix PTP use-after-free during reset

Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a
worker to cache PHC time, but failed to stop it during reset or disable.

This creates a race condition where `iavf_reset_task()` or
`iavf_disable_vf()` free adapter resources (AQ) while the worker is still
running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it
accesses freed memory/locks, leading to a crash.

Fix this by calling `iavf_ptp_release()` before tearing down the adapter.
This ensures `ptp_clock_unregister()` synchronously cancels the worker and
cleans up the chardev before the backing resources are destroyed.

Fixes: 7c01dbfc8a1c5f ("iavf: periodically cache PHC time")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 86c1964f42e1..c7abd3331e03 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3036,6 +3036,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 
 	adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 
+	iavf_ptp_release(adapter);
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.
@@ -3211,6 +3213,8 @@ continue_reset:
 	iavf_change_state(adapter, __IAVF_RESETTING);
 	adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
 
+	iavf_ptp_release(adapter);
+
 	/* free the Tx/Rx rings and descriptors, might be better to just
 	 * re-use them sometime in the future
 	 */
-- 
cgit v1.2.3


From fdadbf6e84c44df8dbb85cfdd38bc10e4431501d Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 11 Feb 2026 20:18:55 +0100
Subject: iavf: fix incorrect reset handling in callbacks

Three driver callbacks schedule a reset and wait for its completion:
ndo_change_mtu(), ethtool set_ringparam(), and ethtool set_channels().

Waiting for reset in ndo_change_mtu() and set_ringparam() was added by
commit c2ed2403f12c ("iavf: Wait for reset in callbacks which trigger
it") to fix a race condition where adding an interface to bonding
immediately after MTU or ring parameter change failed because the
interface was still in __RESETTING state. The same commit also added
waiting in iavf_set_priv_flags(), which was later removed by commit
53844673d555 ("iavf: kill "legacy-rx" for good").

Waiting in set_channels() was introduced earlier by commit 4e5e6b5d9d13
("iavf: Fix return of set the new channel count") to ensure the PF has
enough time to complete the VF reset when changing channel count, and to
return correct error codes to userspace.

Commit ef490bbb2267 ("iavf: Add net_shaper_ops support") added
net_shaper_ops to iavf, which required reset_task to use _locked NAPI
variants (napi_enable_locked, napi_disable_locked) that need the netdev
instance lock.

Later, commit 7e4d784f5810 ("net: hold netdev instance lock during
rtnetlink operations") and commit 2bcf4772e45a ("net: ethtool: try to
protect all callback with netdev instance lock") started holding the
netdev instance lock during ndo and ethtool callbacks for drivers with
net_shaper_ops.

Finally, commit 120f28a6f314 ("iavf: get rid of the crit lock")
replaced the driver's crit_lock with netdev_lock in reset_task, causing
incorrect behavior: the callback holds netdev_lock and waits for
reset_task, but reset_task needs the same lock:

  Thread 1 (callback)               Thread 2 (reset_task)
  -------------------               ---------------------
  netdev_lock()                     [blocked on workqueue]
  ndo_change_mtu() or ethtool op
    iavf_schedule_reset()
    iavf_wait_for_reset()           iavf_reset_task()
      waiting...                      netdev_lock() <- blocked

This does not strictly deadlock because iavf_wait_for_reset() uses
wait_event_interruptible_timeout() with a 5-second timeout. The wait
eventually times out, the callback returns an error to userspace, and
after the lock is released reset_task completes the reset. This leads to
incorrect behavior: userspace sees an error even though the configuration
change silently takes effect after the timeout.

Fix this by extracting the reset logic from iavf_reset_task() into a new
iavf_reset_step() function that expects netdev_lock to be already held.
The three callbacks now call iavf_reset_step() directly instead of
scheduling the work and waiting, performing the reset synchronously in
the caller's context which already holds netdev_lock. This eliminates
both the incorrect error reporting and the need for
iavf_wait_for_reset(), which is removed along with the now-unused
reset_waitqueue.

The workqueue-based iavf_reset_task() becomes a thin wrapper that
acquires netdev_lock and calls iavf_reset_step(), preserving its use
for PF-initiated resets.

The callbacks may block for several seconds while iavf_reset_step()
polls hardware registers, but this is acceptable since netdev_lock is a
per-device mutex and only serializes operations on the same interface.

v3:
- Remove netif_running() guard from iavf_set_channels(). Unlike
  set_ringparam where descriptor counts are picked up by iavf_open()
  directly, num_req_queues is only consumed during
  iavf_reinit_interrupt_scheme() in the reset path. Skipping the reset
  on a down device would silently discard the channel count change.
- Remove dead reset_waitqueue code (struct field, init, and all
  wake_up calls) since iavf_wait_for_reset() was the only consumer.

Fixes: 120f28a6f314 ("iavf: get rid of the crit lock")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h          |  3 +-
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c  | 19 ++----
 drivers/net/ethernet/intel/iavf/iavf_main.c     | 77 ++++++++-----------------
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c |  1 -
 4 files changed, 31 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index a87e0c6d4017..e9fb0a0919e3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -260,7 +260,6 @@ struct iavf_adapter {
 	struct work_struct adminq_task;
 	struct work_struct finish_config;
 	wait_queue_head_t down_waitqueue;
-	wait_queue_head_t reset_waitqueue;
 	wait_queue_head_t vc_waitqueue;
 	struct iavf_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -626,5 +625,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter);
 void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter);
 struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 					const u8 *macaddr);
-int iavf_wait_for_reset(struct iavf_adapter *adapter);
+void iavf_reset_step(struct iavf_adapter *adapter);
 #endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index f3a1b2fb9bf8..ab67c709d5a0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -492,7 +492,6 @@ static int iavf_set_ringparam(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 new_rx_count, new_tx_count;
-	int ret = 0;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
@@ -537,13 +536,11 @@ static int iavf_set_ringparam(struct net_device *netdev,
 	}
 
 	if (netif_running(netdev)) {
-		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
-		ret = iavf_wait_for_reset(adapter);
-		if (ret)
-			netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset");
+		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+		iavf_reset_step(adapter);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -1723,7 +1720,6 @@ static int iavf_set_channels(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 num_req = ch->combined_count;
-	int ret = 0;
 
 	if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
 	    adapter->num_tc) {
@@ -1745,13 +1741,10 @@ static int iavf_set_channels(struct net_device *netdev,
 
 	adapter->num_req_queues = num_req;
 	adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
-	iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+	adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+	iavf_reset_step(adapter);
 
-	ret = iavf_wait_for_reset(adapter);
-	if (ret)
-		netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset");
-
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c7abd3331e03..7925ee152c76 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -185,31 +185,6 @@ static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter)
 	return false;
 }
 
-/**
- * iavf_wait_for_reset - Wait for reset to finish.
- * @adapter: board private structure
- *
- * Returns 0 if reset finished successfully, negative on timeout or interrupt.
- */
-int iavf_wait_for_reset(struct iavf_adapter *adapter)
-{
-	int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue,
-					!iavf_is_reset_in_progress(adapter),
-					msecs_to_jiffies(5000));
-
-	/* If ret < 0 then it means wait was interrupted.
-	 * If ret == 0 then it means we got a timeout while waiting
-	 * for reset to finish.
-	 * If ret > 0 it means reset has finished.
-	 */
-	if (ret > 0)
-		return 0;
-	else if (ret < 0)
-		return -EINTR;
-	else
-		return -EBUSY;
-}
-
 /**
  * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code
  * @hw:   pointer to the HW structure
@@ -3113,18 +3088,16 @@ static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_reset_task - Call-back task to handle hardware reset
- * @work: pointer to work_struct
+ * iavf_reset_step - Perform the VF reset sequence
+ * @adapter: board private structure
  *
- * During reset we need to shut down and reinitialize the admin queue
- * before we can use it to communicate with the PF again. We also clear
- * and reinit the rings because that context is lost as well.
- **/
-static void iavf_reset_task(struct work_struct *work)
+ * Requests a reset from PF, polls for completion, and reconfigures
+ * the driver. Caller must hold the netdev instance lock.
+ *
+ * This can sleep for several seconds while polling HW registers.
+ */
+void iavf_reset_step(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						      struct iavf_adapter,
-						      reset_task);
 	struct virtchnl_vf_resource *vfres = adapter->vf_res;
 	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
@@ -3135,7 +3108,7 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;
 
-	netdev_lock(netdev);
+	netdev_assert_locked(netdev);
 
 	iavf_misc_irq_disable(adapter);
 	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
@@ -3180,7 +3153,6 @@ static void iavf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		iavf_disable_vf(adapter);
-		netdev_unlock(netdev);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -3192,7 +3164,6 @@ continue_reset:
 		iavf_startup(adapter);
 		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
 				   msecs_to_jiffies(30));
-		netdev_unlock(netdev);
 		return;
 	}
 
@@ -3335,9 +3306,6 @@ continue_reset:
 
 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
 
-	wake_up(&adapter->reset_waitqueue);
-	netdev_unlock(netdev);
-
 	return;
 reset_err:
 	if (running) {
@@ -3346,10 +3314,21 @@ reset_err:
 	}
 	iavf_disable_vf(adapter);
 
-	netdev_unlock(netdev);
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 }
 
+static void iavf_reset_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						      struct iavf_adapter,
+						      reset_task);
+	struct net_device *netdev = adapter->netdev;
+
+	netdev_lock(netdev);
+	iavf_reset_step(adapter);
+	netdev_unlock(netdev);
+}
+
 /**
  * iavf_adminq_task - worker thread to clean the admin queue
  * @work: pointer to work_struct containing our data
@@ -4615,22 +4594,17 @@ static int iavf_close(struct net_device *netdev)
 static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
-	int ret = 0;
 
 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
 	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	if (netif_running(netdev)) {
-		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
-		ret = iavf_wait_for_reset(adapter);
-		if (ret < 0)
-			netdev_warn(netdev, "MTU change interrupted waiting for reset");
-		else if (ret)
-			netdev_warn(netdev, "MTU change timed out waiting for reset");
+		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+		iavf_reset_step(adapter);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -5435,9 +5409,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating transition to down status */
 	init_waitqueue_head(&adapter->down_waitqueue);
 
-	/* Setup the wait queue for indicating transition to running state */
-	init_waitqueue_head(&adapter->reset_waitqueue);
-
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 88156082a41d..a52c100dcbc5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -2736,7 +2736,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);
-		wake_up(&adapter->reset_waitqueue);
 		adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED;
 		break;
 	case VIRTCHNL_OP_DISABLE_QUEUES:
-- 
cgit v1.2.3


From 22fd7f7fed2ae3702f90d1985c326354e86b9c75 Mon Sep 17 00:00:00 2001
From: Muhammad Amirul Asyraf Mohamad Jamian
 <muhammad.amirul.asyraf.mohamad.jamian@altera.com>
Date: Thu, 5 Mar 2026 01:31:51 -0800
Subject: firmware: stratix10-svc: Add Multi SVC clients support

In the current implementation, SVC client drivers such as socfpga-hwmon,
intel_fcs, stratix10-soc, stratix10-rsu each send an SMC command that
triggers a single thread in the stratix10-svc driver. Upon receiving a
callback, the initiating client driver sends a stratix10-svc-done signal,
terminating the thread without waiting for other pending SMC commands to
complete. This leads to a timeout issue in the firmware SVC mailbox service
when multiple client drivers send SMC commands concurrently.

To resolve this issue, a dedicated thread is now created per channel. The
stratix10-svc driver will support up to the number of channels defined by
SVC_NUM_CHANNEL. Thread synchronization is handled using a mutex to prevent
simultaneous issuance of SMC commands by multiple threads.

SVC_NUM_DATA_IN_FIFO is reduced from 32 to 8, since each channel now has
its own dedicated FIFO and the SDM processes commands one at a time.
8 entries per channel is sufficient while keeping the total aggregate
capacity the same (4 channels x 8 = 32 entries).

Additionally, a thread task is now validated before invoking kthread_stop
when the user aborts, ensuring safe termination.

Timeout values have also been adjusted to accommodate the increased load
from concurrent client driver activity.

Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver")
Cc: stable@vger.kernel.org
Signed-off-by: Ang Tien Sung <tien.sung.ang@altera.com>
Signed-off-by: Fong, Yan Kei <yankei.fong@altera.com>
Signed-off-by: Muhammad Amirul Asyraf Mohamad Jamian <muhammad.amirul.asyraf.mohamad.jamian@altera.com>
Link: https://lore.kernel.org/all/20260305093151.2678-1-muhammad.amirul.asyraf.mohamad.jamian@altera.com
Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
---
 drivers/firmware/stratix10-svc.c                   | 228 ++++++++++++---------
 .../linux/firmware/intel/stratix10-svc-client.h    |   8 +-
 2 files changed, 130 insertions(+), 106 deletions(-)

diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index 6f5c298582ab..e9e35d67ef96 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -37,15 +37,14 @@
  * service layer will return error to FPGA manager when timeout occurs,
  * timeout is set to 30 seconds (30 * 1000) at Intel Stratix10 SoC.
  */
-#define SVC_NUM_DATA_IN_FIFO			32
+#define SVC_NUM_DATA_IN_FIFO			8
 #define SVC_NUM_CHANNEL				4
-#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS	200
+#define FPGA_CONFIG_DATA_CLAIM_TIMEOUT_MS	2000
 #define FPGA_CONFIG_STATUS_TIMEOUT_SEC		30
 #define BYTE_TO_WORD_SIZE              4
 
 /* stratix10 service layer clients */
 #define STRATIX10_RSU				"stratix10-rsu"
-#define INTEL_FCS				"intel-fcs"
 
 /* Maximum number of SDM client IDs. */
 #define MAX_SDM_CLIENT_IDS			16
@@ -105,11 +104,9 @@ struct stratix10_svc_chan;
 /**
  * struct stratix10_svc - svc private data
  * @stratix10_svc_rsu: pointer to stratix10 RSU device
- * @intel_svc_fcs: pointer to the FCS device
  */
 struct stratix10_svc {
 	struct platform_device *stratix10_svc_rsu;
-	struct platform_device *intel_svc_fcs;
 };
 
 /**
@@ -251,12 +248,10 @@ struct stratix10_async_ctrl {
  * @num_active_client: number of active service client
  * @node: list management
  * @genpool: memory pool pointing to the memory region
- * @task: pointer to the thread task which handles SMC or HVC call
- * @svc_fifo: a queue for storing service message data
  * @complete_status: state for completion
- * @svc_fifo_lock: protect access to service message data queue
  * @invoke_fn: function to issue secure monitor call or hypervisor call
  * @svc: manages the list of client svc drivers
+ * @sdm_lock: only allows a single command single response to SDM
  * @actrl: async control structure
  *
  * This struct is used to create communication channels for service clients, to
@@ -269,12 +264,10 @@ struct stratix10_svc_controller {
 	int num_active_client;
 	struct list_head node;
 	struct gen_pool *genpool;
-	struct task_struct *task;
-	struct kfifo svc_fifo;
 	struct completion complete_status;
-	spinlock_t svc_fifo_lock;
 	svc_invoke_fn *invoke_fn;
 	struct stratix10_svc *svc;
+	struct mutex sdm_lock;
 	struct stratix10_async_ctrl actrl;
 };
 
@@ -283,6 +276,9 @@ struct stratix10_svc_controller {
  * @ctrl: pointer to service controller which is the provider of this channel
  * @scl: pointer to service client which owns the channel
  * @name: service client name associated with the channel
+ * @task: pointer to the thread task which handles SMC or HVC call
+ * @svc_fifo: a queue for storing service message data (separate fifo for every channel)
+ * @svc_fifo_lock: protect access to service message data queue (locking pending fifo)
  * @lock: protect access to the channel
  * @async_chan: reference to asynchronous channel object for this channel
  *
@@ -293,6 +289,9 @@ struct stratix10_svc_chan {
 	struct stratix10_svc_controller *ctrl;
 	struct stratix10_svc_client *scl;
 	char *name;
+	struct task_struct *task;
+	struct kfifo svc_fifo;
+	spinlock_t svc_fifo_lock;
 	spinlock_t lock;
 	struct stratix10_async_chan *async_chan;
 };
@@ -527,10 +526,10 @@ static void svc_thread_recv_status_ok(struct stratix10_svc_data *p_data,
  */
 static int svc_normal_to_secure_thread(void *data)
 {
-	struct stratix10_svc_controller
-			*ctrl = (struct stratix10_svc_controller *)data;
-	struct stratix10_svc_data *pdata;
-	struct stratix10_svc_cb_data *cbdata;
+	struct stratix10_svc_chan *chan = (struct stratix10_svc_chan *)data;
+	struct stratix10_svc_controller *ctrl = chan->ctrl;
+	struct stratix10_svc_data *pdata = NULL;
+	struct stratix10_svc_cb_data *cbdata = NULL;
 	struct arm_smccc_res res;
 	unsigned long a0, a1, a2, a3, a4, a5, a6, a7;
 	int ret_fifo = 0;
@@ -555,12 +554,12 @@ static int svc_normal_to_secure_thread(void *data)
 	a6 = 0;
 	a7 = 0;
 
-	pr_debug("smc_hvc_shm_thread is running\n");
+	pr_debug("%s: %s: Thread is running!\n", __func__, chan->name);
 
 	while (!kthread_should_stop()) {
-		ret_fifo = kfifo_out_spinlocked(&ctrl->svc_fifo,
+		ret_fifo = kfifo_out_spinlocked(&chan->svc_fifo,
 						pdata, sizeof(*pdata),
-						&ctrl->svc_fifo_lock);
+						&chan->svc_fifo_lock);
 
 		if (!ret_fifo)
 			continue;
@@ -569,9 +568,25 @@ static int svc_normal_to_secure_thread(void *data)
 			 (unsigned int)pdata->paddr, pdata->command,
 			 (unsigned int)pdata->size);
 
+		/* SDM can only process one command at a time */
+		pr_debug("%s: %s: Thread is waiting for mutex!\n",
+			 __func__, chan->name);
+		if (mutex_lock_interruptible(&ctrl->sdm_lock)) {
+			/* item already dequeued; notify client to unblock it */
+			cbdata->status = BIT(SVC_STATUS_ERROR);
+			cbdata->kaddr1 = NULL;
+			cbdata->kaddr2 = NULL;
+			cbdata->kaddr3 = NULL;
+			if (pdata->chan->scl)
+				pdata->chan->scl->receive_cb(pdata->chan->scl,
+							     cbdata);
+			break;
+		}
+
 		switch (pdata->command) {
 		case COMMAND_RECONFIG_DATA_CLAIM:
 			svc_thread_cmd_data_claim(ctrl, pdata, cbdata);
+			mutex_unlock(&ctrl->sdm_lock);
 			continue;
 		case COMMAND_RECONFIG:
 			a0 = INTEL_SIP_SMC_FPGA_CONFIG_START;
@@ -700,10 +715,11 @@ static int svc_normal_to_secure_thread(void *data)
 			break;
 		default:
 			pr_warn("it shouldn't happen\n");
-			break;
+			mutex_unlock(&ctrl->sdm_lock);
+			continue;
 		}
-		pr_debug("%s: before SMC call -- a0=0x%016x a1=0x%016x",
-			 __func__,
+		pr_debug("%s: %s: before SMC call -- a0=0x%016x a1=0x%016x",
+			 __func__, chan->name,
 			 (unsigned int)a0,
 			 (unsigned int)a1);
 		pr_debug(" a2=0x%016x\n", (unsigned int)a2);
@@ -712,8 +728,8 @@ static int svc_normal_to_secure_thread(void *data)
 		pr_debug(" a5=0x%016x\n", (unsigned int)a5);
 		ctrl->invoke_fn(a0, a1, a2, a3, a4, a5, a6, a7, &res);
 
-		pr_debug("%s: after SMC call -- res.a0=0x%016x",
-			 __func__, (unsigned int)res.a0);
+		pr_debug("%s: %s: after SMC call -- res.a0=0x%016x",
+			 __func__, chan->name, (unsigned int)res.a0);
 		pr_debug(" res.a1=0x%016x, res.a2=0x%016x",
 			 (unsigned int)res.a1, (unsigned int)res.a2);
 		pr_debug(" res.a3=0x%016x\n", (unsigned int)res.a3);
@@ -728,6 +744,7 @@ static int svc_normal_to_secure_thread(void *data)
 			cbdata->kaddr2 = NULL;
 			cbdata->kaddr3 = NULL;
 			pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata);
+			mutex_unlock(&ctrl->sdm_lock);
 			continue;
 		}
 
@@ -801,6 +818,8 @@ static int svc_normal_to_secure_thread(void *data)
 			break;
 
 		}
+
+		mutex_unlock(&ctrl->sdm_lock);
 	}
 
 	kfree(cbdata);
@@ -1696,22 +1715,33 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg)
 	if (!p_data)
 		return -ENOMEM;
 
-	/* first client will create kernel thread */
-	if (!chan->ctrl->task) {
-		chan->ctrl->task =
-			kthread_run_on_cpu(svc_normal_to_secure_thread,
-					   (void *)chan->ctrl,
-					   cpu, "svc_smc_hvc_thread");
-		if (IS_ERR(chan->ctrl->task)) {
+	/* first caller creates the per-channel kthread */
+	if (!chan->task) {
+		struct task_struct *task;
+
+		task = kthread_run_on_cpu(svc_normal_to_secure_thread,
+					  (void *)chan,
+					  cpu, "svc_smc_hvc_thread");
+		if (IS_ERR(task)) {
 			dev_err(chan->ctrl->dev,
 				"failed to create svc_smc_hvc_thread\n");
 			kfree(p_data);
 			return -EINVAL;
 		}
+
+		spin_lock(&chan->lock);
+		if (chan->task) {
+			/* another caller won the race; discard our thread */
+			spin_unlock(&chan->lock);
+			kthread_stop(task);
+		} else {
+			chan->task = task;
+			spin_unlock(&chan->lock);
+		}
 	}
 
-	pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__,
-		 p_msg->payload, p_msg->command,
+	pr_debug("%s: %s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__,
+		 chan->name, p_msg->payload, p_msg->command,
 		 (unsigned int)p_msg->payload_length);
 
 	if (list_empty(&svc_data_mem)) {
@@ -1747,12 +1777,16 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg)
 	p_data->arg[2] = p_msg->arg[2];
 	p_data->size = p_msg->payload_length;
 	p_data->chan = chan;
-	pr_debug("%s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n", __func__,
-	       (unsigned int)p_data->paddr, p_data->command,
-	       (unsigned int)p_data->size);
-	ret = kfifo_in_spinlocked(&chan->ctrl->svc_fifo, p_data,
+	pr_debug("%s: %s: put to FIFO pa=0x%016x, cmd=%x, size=%u\n",
+		 __func__,
+		 chan->name,
+		 (unsigned int)p_data->paddr,
+		 p_data->command,
+		 (unsigned int)p_data->size);
+
+	ret = kfifo_in_spinlocked(&chan->svc_fifo, p_data,
 				  sizeof(*p_data),
-				  &chan->ctrl->svc_fifo_lock);
+				  &chan->svc_fifo_lock);
 
 	kfree(p_data);
 
@@ -1773,11 +1807,12 @@ EXPORT_SYMBOL_GPL(stratix10_svc_send);
  */
 void stratix10_svc_done(struct stratix10_svc_chan *chan)
 {
-	/* stop thread when thread is running AND only one active client */
-	if (chan->ctrl->task && chan->ctrl->num_active_client <= 1) {
-		pr_debug("svc_smc_hvc_shm_thread is stopped\n");
-		kthread_stop(chan->ctrl->task);
-		chan->ctrl->task = NULL;
+	/* stop thread when thread is running */
+	if (chan->task) {
+		pr_debug("%s: %s: svc_smc_hvc_shm_thread is stopping\n",
+			 __func__, chan->name);
+		kthread_stop(chan->task);
+		chan->task = NULL;
 	}
 }
 EXPORT_SYMBOL_GPL(stratix10_svc_done);
@@ -1817,8 +1852,8 @@ void *stratix10_svc_allocate_memory(struct stratix10_svc_chan *chan,
 	pmem->paddr = pa;
 	pmem->size = s;
 	list_add_tail(&pmem->node, &svc_data_mem);
-	pr_debug("%s: va=%p, pa=0x%016x\n", __func__,
-		 pmem->vaddr, (unsigned int)pmem->paddr);
+	pr_debug("%s: %s: va=%p, pa=0x%016x\n", __func__,
+		 chan->name, pmem->vaddr, (unsigned int)pmem->paddr);
 
 	return (void *)va;
 }
@@ -1855,6 +1890,13 @@ static const struct of_device_id stratix10_svc_drv_match[] = {
 	{},
 };
 
+static const char * const chan_names[SVC_NUM_CHANNEL] = {
+	SVC_CLIENT_FPGA,
+	SVC_CLIENT_RSU,
+	SVC_CLIENT_FCS,
+	SVC_CLIENT_HWMON
+};
+
 static int stratix10_svc_drv_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1862,11 +1904,11 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	struct stratix10_svc_chan *chans;
 	struct gen_pool *genpool;
 	struct stratix10_svc_sh_memory *sh_memory;
-	struct stratix10_svc *svc;
+	struct stratix10_svc *svc = NULL;
 
 	svc_invoke_fn *invoke_fn;
 	size_t fifo_size;
-	int ret;
+	int ret, i = 0;
 
 	/* get SMC or HVC function */
 	invoke_fn = get_invoke_func(dev);
@@ -1905,8 +1947,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	controller->num_active_client = 0;
 	controller->chans = chans;
 	controller->genpool = genpool;
-	controller->task = NULL;
 	controller->invoke_fn = invoke_fn;
+	INIT_LIST_HEAD(&controller->node);
 	init_completion(&controller->complete_status);
 
 	ret = stratix10_svc_async_init(controller);
@@ -1917,32 +1959,20 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	}
 
 	fifo_size = sizeof(struct stratix10_svc_data) * SVC_NUM_DATA_IN_FIFO;
-	ret = kfifo_alloc(&controller->svc_fifo, fifo_size, GFP_KERNEL);
-	if (ret) {
-		dev_err(dev, "failed to allocate FIFO\n");
-		goto err_async_exit;
-	}
-	spin_lock_init(&controller->svc_fifo_lock);
-
-	chans[0].scl = NULL;
-	chans[0].ctrl = controller;
-	chans[0].name = SVC_CLIENT_FPGA;
-	spin_lock_init(&chans[0].lock);
+	mutex_init(&controller->sdm_lock);
 
-	chans[1].scl = NULL;
-	chans[1].ctrl = controller;
-	chans[1].name = SVC_CLIENT_RSU;
-	spin_lock_init(&chans[1].lock);
-
-	chans[2].scl = NULL;
-	chans[2].ctrl = controller;
-	chans[2].name = SVC_CLIENT_FCS;
-	spin_lock_init(&chans[2].lock);
-
-	chans[3].scl = NULL;
-	chans[3].ctrl = controller;
-	chans[3].name = SVC_CLIENT_HWMON;
-	spin_lock_init(&chans[3].lock);
+	for (i = 0; i < SVC_NUM_CHANNEL; i++) {
+		chans[i].scl = NULL;
+		chans[i].ctrl = controller;
+		chans[i].name = (char *)chan_names[i];
+		spin_lock_init(&chans[i].lock);
+		ret = kfifo_alloc(&chans[i].svc_fifo, fifo_size, GFP_KERNEL);
+		if (ret) {
+			dev_err(dev, "failed to allocate FIFO %d\n", i);
+			goto err_free_fifos;
+		}
+		spin_lock_init(&chans[i].svc_fifo_lock);
+	}
 
 	list_add_tail(&controller->node, &svc_ctrl);
 	platform_set_drvdata(pdev, controller);
@@ -1951,7 +1981,7 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	svc = devm_kzalloc(dev, sizeof(*svc), GFP_KERNEL);
 	if (!svc) {
 		ret = -ENOMEM;
-		goto err_free_kfifo;
+		goto err_free_fifos;
 	}
 	controller->svc = svc;
 
@@ -1959,51 +1989,43 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev)
 	if (!svc->stratix10_svc_rsu) {
 		dev_err(dev, "failed to allocate %s device\n", STRATIX10_RSU);
 		ret = -ENOMEM;
-		goto err_free_kfifo;
+		goto err_free_fifos;
 	}
 
 	ret = platform_device_add(svc->stratix10_svc_rsu);
-	if (ret) {
-		platform_device_put(svc->stratix10_svc_rsu);
-		goto err_free_kfifo;
-	}
-
-	svc->intel_svc_fcs = platform_device_alloc(INTEL_FCS, 1);
-	if (!svc->intel_svc_fcs) {
-		dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
-		ret = -ENOMEM;
-		goto err_unregister_rsu_dev;
-	}
-
-	ret = platform_device_add(svc->intel_svc_fcs);
-	if (ret) {
-		platform_device_put(svc->intel_svc_fcs);
-		goto err_unregister_rsu_dev;
-	}
+	if (ret)
+		goto err_put_device;
 
 	ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
 	if (ret)
-		goto err_unregister_fcs_dev;
+		goto err_unregister_rsu_dev;
 
 	pr_info("Intel Service Layer Driver Initialized\n");
 
 	return 0;
 
-err_unregister_fcs_dev:
-	platform_device_unregister(svc->intel_svc_fcs);
 err_unregister_rsu_dev:
 	platform_device_unregister(svc->stratix10_svc_rsu);
-err_free_kfifo:
-	kfifo_free(&controller->svc_fifo);
-err_async_exit:
+	goto err_free_fifos;
+err_put_device:
+	platform_device_put(svc->stratix10_svc_rsu);
+err_free_fifos:
+	/* only remove from list if list_add_tail() was reached */
+	if (!list_empty(&controller->node))
+		list_del(&controller->node);
+	/* free only the FIFOs that were successfully allocated */
+	while (i--)
+		kfifo_free(&chans[i].svc_fifo);
 	stratix10_svc_async_exit(controller);
 err_destroy_pool:
 	gen_pool_destroy(genpool);
+
 	return ret;
 }
 
 static void stratix10_svc_drv_remove(struct platform_device *pdev)
 {
+	int i;
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
 	struct stratix10_svc *svc = ctrl->svc;
 
@@ -2011,14 +2033,16 @@ static void stratix10_svc_drv_remove(struct platform_device *pdev)
 
 	of_platform_depopulate(ctrl->dev);
 
-	platform_device_unregister(svc->intel_svc_fcs);
 	platform_device_unregister(svc->stratix10_svc_rsu);
 
-	kfifo_free(&ctrl->svc_fifo);
-	if (ctrl->task) {
-		kthread_stop(ctrl->task);
-		ctrl->task = NULL;
+	for (i = 0; i < SVC_NUM_CHANNEL; i++) {
+		if (ctrl->chans[i].task) {
+			kthread_stop(ctrl->chans[i].task);
+			ctrl->chans[i].task = NULL;
+		}
+		kfifo_free(&ctrl->chans[i].svc_fifo);
 	}
+
 	if (ctrl->genpool)
 		gen_pool_destroy(ctrl->genpool);
 	list_del(&ctrl->node);
diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index d290060f4c73..91013161e9db 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -68,12 +68,12 @@
  * timeout value used in Stratix10 FPGA manager driver.
  * timeout value used in RSU driver
  */
-#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         300
-#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          720
-#define SVC_RSU_REQUEST_TIMEOUT_MS              300
+#define SVC_RECONFIG_REQUEST_TIMEOUT_MS         5000
+#define SVC_RECONFIG_BUFFER_TIMEOUT_MS          5000
+#define SVC_RSU_REQUEST_TIMEOUT_MS              2000
 #define SVC_FCS_REQUEST_TIMEOUT_MS		2000
 #define SVC_COMPLETED_TIMEOUT_MS		30000
-#define SVC_HWMON_REQUEST_TIMEOUT_MS		300
+#define SVC_HWMON_REQUEST_TIMEOUT_MS		2000
 
 struct stratix10_svc_chan;
 
-- 
cgit v1.2.3


From d1afcd71658220aa03453dc263064e42ff30b1e5 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Sat, 28 Feb 2026 20:10:05 +0100
Subject: HID: asus: add xg mobile 2022 external hardware support

XG mobile station 2022 has a different PID than the 2023 model: add it
that model to hid-asus.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-asus.c | 3 +++
 drivers/hid/hid-ids.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 687b785e2d0c..bc93b27f9b13 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1497,6 +1497,9 @@ static const struct hid_device_id asus_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD | QUIRK_ROG_ALLY_XPAD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+	    USB_DEVICE_ID_ASUSTEK_XGM_2022),
+	},
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_XGM_2023),
 	},
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 4ab7640b119a..5e85921049e0 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -229,6 +229,7 @@
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X		0x1b4c
 #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD	0x196b
 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD	0x1869
+#define USB_DEVICE_ID_ASUSTEK_XGM_2022	0x1970
 #define USB_DEVICE_ID_ASUSTEK_XGM_2023	0x1a9a
 
 #define USB_VENDOR_ID_ATEN		0x0557
-- 
cgit v1.2.3


From ff88df67dbf78b5eb909f8a3da4115b1cfd998ab Mon Sep 17 00:00:00 2001
From: Yihan Ding <dingyihan@uniontech.com>
Date: Fri, 6 Mar 2026 10:16:50 +0800
Subject: landlock: Serialize TSYNC thread restriction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

syzbot found a deadlock in landlock_restrict_sibling_threads().
When multiple threads concurrently call landlock_restrict_self() with
sibling thread restriction enabled, they can deadlock by mutually
queueing task_works on each other and then blocking in kernel space
(waiting for the other to finish).

Fix this by serializing the TSYNC operations within the same process
using the exec_update_lock. This prevents concurrent invocations
from deadlocking.

We use down_write_trylock() and restart the syscall if the lock
cannot be acquired immediately. This ensures that if a thread fails
to get the lock, it will return to userspace, allowing it to process
any pending TSYNC task_works from the lock holder, and then
transparently restart the syscall.

Fixes: 42fc7e6543f6 ("landlock: Multithreading support for landlock_restrict_self()")
Reported-by: syzbot+7ea2f5e9dfd468201817@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7ea2f5e9dfd468201817
Suggested-by: Günther Noack <gnoack3000@gmail.com>
Suggested-by: Tingmao Wang <m@maowtm.org>
Tested-by: Justin Suess <utilityemal77@gmail.com>
Signed-off-by: Yihan Ding <dingyihan@uniontech.com>
Tested-by: Günther Noack <gnoack3000@gmail.com>
Reviewed-by: Günther Noack <gnoack3000@gmail.com>
Link: https://lore.kernel.org/r/20260306021651.744723-2-dingyihan@uniontech.com
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/tsync.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c
index 1e738ef2cff5..f0e5f8102001 100644
--- a/security/landlock/tsync.c
+++ b/security/landlock/tsync.c
@@ -485,6 +485,16 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred,
 	shared_ctx.new_cred = new_cred;
 	shared_ctx.set_no_new_privs = task_no_new_privs(current);
 
+	/*
+	 * Serialize concurrent TSYNC operations to prevent deadlocks when
+	 * multiple threads call landlock_restrict_self() simultaneously.
+	 * If the lock is already held, we gracefully yield by restarting the
+	 * syscall. This allows the current thread to process pending
+	 * task_works before retrying.
+	 */
+	if (!down_write_trylock(&current->signal->exec_update_lock))
+		return restart_syscall();
+
 	/*
 	 * We schedule a pseudo-signal task_work for each of the calling task's
 	 * sibling threads.  In the task work, each thread:
@@ -594,6 +604,6 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred,
 		wait_for_completion(&shared_ctx.all_finished);
 
 	tsync_works_release(&works);
-
+	up_write(&current->signal->exec_update_lock);
 	return atomic_read(&shared_ctx.preparation_error);
 }
-- 
cgit v1.2.3


From 697f514ad9dbe600a808326d80b02caab03b7f90 Mon Sep 17 00:00:00 2001
From: Yihan Ding <dingyihan@uniontech.com>
Date: Fri, 6 Mar 2026 10:16:51 +0800
Subject: landlock: Clean up interrupted thread logic in TSYNC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In landlock_restrict_sibling_threads(), when the calling thread is
interrupted while waiting for sibling threads to prepare, it executes
a recovery path.

Previously, this path included a wait_for_completion() call on
all_prepared to prevent a Use-After-Free of the local shared_ctx.
However, this wait is redundant. Exiting the main do-while loop
already leads to a bottom cleanup section that unconditionally waits
for all_finished. Therefore, replacing the wait with a simple break
is safe, prevents UAF, and correctly unblocks the remaining task_works.

Clean up the error path by breaking the loop and updating the
surrounding comments to accurately reflect the state machine.

Suggested-by: Günther Noack <gnoack3000@gmail.com>
Signed-off-by: Yihan Ding <dingyihan@uniontech.com>
Tested-by: Günther Noack <gnoack3000@gmail.com>
Reviewed-by: Günther Noack <gnoack3000@gmail.com>
Link: https://lore.kernel.org/r/20260306021651.744723-3-dingyihan@uniontech.com
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/tsync.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c
index f0e5f8102001..4d4427ba8d93 100644
--- a/security/landlock/tsync.c
+++ b/security/landlock/tsync.c
@@ -575,24 +575,30 @@ int landlock_restrict_sibling_threads(const struct cred *old_cred,
 					   -ERESTARTNOINTR);
 
 				/*
-				 * Cancel task works for tasks that did not start running yet,
-				 * and decrement all_prepared and num_unfinished accordingly.
+				 * Opportunistic improvement: try to cancel task
+				 * works for tasks that did not start running
+				 * yet. We do not have a guarantee that it
+				 * cancels any of the enqueued task works
+				 * because task_work_run() might already have
+				 * dequeued them.
 				 */
 				cancel_tsync_works(&works, &shared_ctx);
 
 				/*
-				 * The remaining task works have started running, so waiting for
-				 * their completion will finish.
+				 * Break the loop with error. The cleanup code
+				 * after the loop unblocks the remaining
+				 * task_works.
 				 */
-				wait_for_completion(&shared_ctx.all_prepared);
+				break;
 			}
 		}
 	} while (found_more_threads &&
 		 !atomic_read(&shared_ctx.preparation_error));
 
 	/*
-	 * We now have all sibling threads blocking and in "prepared" state in the
-	 * task work. Ask all threads to commit.
+	 * We now have either (a) all sibling threads blocking and in "prepared"
+	 * state in the task work, or (b) the preparation error is set. Ask all
+	 * threads to commit (or abort).
 	 */
 	complete_all(&shared_ctx.ready_to_commit);
 
-- 
cgit v1.2.3


From c7940c8bf215b9dc6211781c77ce80e76982a723 Mon Sep 17 00:00:00 2001
From: Tim Kovalenko <tim.kovalenko@proton.me>
Date: Mon, 9 Mar 2026 12:34:21 -0400
Subject: gpu: nova-core: fix stack overflow in GSP memory allocation

The `Cmdq::new` function was allocating a `PteArray` struct on the stack
and was causing a stack overflow with 8216 bytes.

Modify the `PteArray` to calculate and write the Page Table Entries
directly into the coherent DMA buffer one-by-one. This reduces the stack
usage quite a lot.

Reported-by: Gary Guo <gary@garyguo.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/509436-Nova/topic/.60Cmdq.3A.3Anew.60.20uses.20excessive.20stack.20size/near/570375549
Link: https://lore.kernel.org/rust-for-linux/CANiq72mAQxbRJZDnik3Qmd4phvFwPA01O2jwaaXRh_T+2=L-qA@mail.gmail.com/
Fixes: f38b4f105cfc ("gpu: nova-core: Create initial Gsp")
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Tim Kovalenko <tim.kovalenko@proton.me>
Link: https://patch.msgid.link/20260309-drm-rust-next-v4-4-4ef485b19a4c@proton.me
[ * Use PteArray::entry() in LogBuffer::new(),
  * Add TODO comment to use IoView projections once available,
  * Add PTE_ARRAY_SIZE constant to avoid duplication.

    - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp.rs      | 32 +++++++++++++++++---------------
 drivers/gpu/nova-core/gsp/cmdq.rs | 14 ++++++++++++--
 2 files changed, 29 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 25cd48514c77..c69adaa92bbe 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -47,16 +47,12 @@ struct PteArray<const NUM_ENTRIES: usize>([u64; NUM_ENTRIES]);
 unsafe impl<const NUM_ENTRIES: usize> AsBytes for PteArray<NUM_ENTRIES> {}
 
 impl<const NUM_PAGES: usize> PteArray<NUM_PAGES> {
-    /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`.
-    fn new(start: DmaAddress) -> Result<Self> {
-        let mut ptes = [0u64; NUM_PAGES];
-        for (i, pte) in ptes.iter_mut().enumerate() {
-            *pte = start
-                .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT)
-                .ok_or(EOVERFLOW)?;
-        }
-
-        Ok(Self(ptes))
+    /// Returns the page table entry for `index`, for a mapping starting at `start`.
+    // TODO: Replace with `IoView` projection once available.
+    fn entry(start: DmaAddress, index: usize) -> Result<u64> {
+        start
+            .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT)
+            .ok_or(EOVERFLOW)
     }
 }
 
@@ -86,16 +82,22 @@ impl LogBuffer {
             NUM_PAGES * GSP_PAGE_SIZE,
             GFP_KERNEL | __GFP_ZERO,
         )?);
-        let ptes = PteArray::<NUM_PAGES>::new(obj.0.dma_handle())?;
+
+        let start_addr = obj.0.dma_handle();
 
         // SAFETY: `obj` has just been created and we are its sole user.
-        unsafe {
-            // Copy the self-mapping PTE at the expected location.
+        let pte_region = unsafe {
             obj.0
-                .as_slice_mut(size_of::<u64>(), size_of_val(&ptes))?
-                .copy_from_slice(ptes.as_bytes())
+                .as_slice_mut(size_of::<u64>(), NUM_PAGES * size_of::<u64>())?
         };
 
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for (i, chunk) in pte_region.chunks_exact_mut(size_of::<u64>()).enumerate() {
+            let pte_value = PteArray::<0>::entry(start_addr, i)?;
+
+            chunk.copy_from_slice(&pte_value.to_ne_bytes());
+        }
+
         Ok(obj)
     }
 }
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index ae54708c38eb..9c5efd2daf45 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -159,7 +159,7 @@ struct Msgq {
 #[repr(C)]
 struct GspMem {
     /// Self-mapping page table entries.
-    ptes: PteArray<{ GSP_PAGE_SIZE / size_of::<u64>() }>,
+    ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>,
     /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the
     /// write and read pointers that the CPU updates.
     ///
@@ -172,6 +172,10 @@ struct GspMem {
     gspq: Msgq,
 }
 
+impl GspMem {
+    const PTE_ARRAY_SIZE: usize = GSP_PAGE_SIZE / size_of::<u64>();
+}
+
 // SAFETY: These structs don't meet the no-padding requirements of AsBytes but
 // that is not a problem because they are not used outside the kernel.
 unsafe impl AsBytes for GspMem {}
@@ -201,7 +205,13 @@ impl DmaGspMem {
 
         let gsp_mem =
             CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?);
+
+        let start = gsp_mem.dma_handle();
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for i in 0..GspMem::PTE_ARRAY_SIZE {
+            dma_write!(gsp_mem, [0]?.ptes.0[i], PteArray::<0>::entry(start, i)?);
+        }
+
         dma_write!(
             gsp_mem,
             [0]?.cpuq.tx,
-- 
cgit v1.2.3


From 620b6ded72a7f0f77be6ec44d0462bb85729ab7a Mon Sep 17 00:00:00 2001
From: Jessica Liu <liu.xuemei1@zte.com.cn>
Date: Tue, 10 Mar 2026 14:16:00 +0800
Subject: irqchip/riscv-aplic: Do not clear ACPI dependencies on probe failure

aplic_probe() calls acpi_dev_clear_dependencies() unconditionally at the
end, even when the preceding setup (MSI or direct mode) has failed. This is
incorrect because if the device failed to probe, it should not be
considered as active and should not clear dependencies for other devices
waiting on it.

Fix this by returning immediately when the setup fails, skipping the ACPI
dependency cleanup. Also, explicitly return 0 on success instead of relying
on the value of 'rc' to make the success path clear.

Fixes: 5122e380c23b ("irqchip/riscv-aplic: Add ACPI support")
Signed-off-by: Jessica Liu <liu.xuemei1@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260310141600411Fu8H8-GXOOgKISU48Tjgx@zte.com.cn
---
 drivers/irqchip/irq-riscv-aplic-main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 4495ca26abf5..8775f188ea4f 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -372,18 +372,21 @@ static int aplic_probe(struct platform_device *pdev)
 		rc = aplic_msi_setup(dev, regs);
 	else
 		rc = aplic_direct_setup(dev, regs);
-	if (rc)
+
+	if (rc) {
 		dev_err_probe(dev, rc, "failed to setup APLIC in %s mode\n",
 			      msi_mode ? "MSI" : "direct");
-	else
-		register_syscore(&aplic_syscore);
+		return rc;
+	}
+
+	register_syscore(&aplic_syscore);
 
 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)
 		acpi_dev_clear_dependencies(ACPI_COMPANION(dev));
 #endif
 
-	return rc;
+	return 0;
 }
 
 static const struct of_device_id aplic_match[] = {
-- 
cgit v1.2.3


From b330fbfd34d7624bec62b99ad88dba2614326a19 Mon Sep 17 00:00:00 2001
From: Jessica Liu <liu.xuemei1@zte.com.cn>
Date: Tue, 10 Mar 2026 14:17:31 +0800
Subject: irqchip/riscv-aplic: Register syscore operations only once

Since commit 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC
states across suspend/resume"), when multiple NUMA nodes exist
and AIA is not configured as "none", aplic_probe() is called
multiple times. This leads to register_syscore(&aplic_syscore)
being invoked repeatedly, causing the following Oops:

 list_add double add: new=ffffffffb91461f0, prev=ffffffffb91461f0, next=ffffffffb915c408.
 [<ffffffffb7b5c8ca>] __list_add_valid_or_report+0x60/0xc0
 [<ffffffffb7cc3236>] register_syscore+0x3e/0x70
 [<ffffffffb7b8d61c>] aplic_probe+0xc6/0x112

Fix this by registering syscore operations only once, using a static
variable aplic_syscore_registered to track registration.

[ tglx: Trim backtrace properly ]

Fixes: 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume")
Signed-off-by: Jessica Liu <liu.xuemei1@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260310141731145xMwLsyvXl9Gw-m6A4VRYj@zte.com.cn
---
 drivers/irqchip/irq-riscv-aplic-main.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 8775f188ea4f..9f53979b6962 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -116,6 +116,16 @@ static struct syscore aplic_syscore = {
 	.ops = &aplic_syscore_ops,
 };
 
+static bool aplic_syscore_registered __ro_after_init;
+
+static void aplic_syscore_init(void)
+{
+	if (!aplic_syscore_registered) {
+		register_syscore(&aplic_syscore);
+		aplic_syscore_registered = true;
+	}
+}
+
 static int aplic_pm_notifier(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct aplic_priv *priv = container_of(nb, struct aplic_priv, genpd_nb);
@@ -379,7 +389,7 @@ static int aplic_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	register_syscore(&aplic_syscore);
+	aplic_syscore_init();
 
 #ifdef CONFIG_ACPI
 	if (!acpi_disabled)
-- 
cgit v1.2.3


From a3125bc01884431d30d731461634c8295b6f0529 Mon Sep 17 00:00:00 2001
From: Yazhou Tang <tangyazhou518@outlook.com>
Date: Wed, 4 Mar 2026 16:32:27 +0800
Subject: bpf: Reset register ID for BPF_END value tracking

When a register undergoes a BPF_END (byte swap) operation, its scalar
value is mutated in-place. If this register previously shared a scalar ID
with another register (e.g., after an `r1 = r0` assignment), this tie must
be broken.

Currently, the verifier misses resetting `dst_reg->id` to 0 for BPF_END.
Consequently, if a conditional jump checks the swapped register, the
verifier incorrectly propagates the learned bounds to the linked register,
leading to false confidence in the linked register's value and potentially
allowing out-of-bounds memory accesses.

Fix this by explicitly resetting `dst_reg->id` to 0 in the BPF_END case
to break the scalar tie, similar to how BPF_NEG handles it via
`__mark_reg_known`.

Fixes: 9d2119984224 ("bpf: Add bitwise tracking for BPF_END")
Closes: https://lore.kernel.org/bpf/AMBPR06MB108683CFEB1CB8D9E02FC95ECF17EA@AMBPR06MB10868.eurprd06.prod.outlook.com/
Link: https://lore.kernel.org/bpf/4be25f7442a52244d0dd1abb47bc6750e57984c9.camel@gmail.com/
Reported-by: Guillaume Laporte <glapt.pro@outlook.com>
Co-developed-by: Tianci Cao <ziye@zju.edu.cn>
Signed-off-by: Tianci Cao <ziye@zju.edu.cn>
Co-developed-by: Shenghao Yuan <shenghaoyuan0928@163.com>
Signed-off-by: Shenghao Yuan <shenghaoyuan0928@163.com>
Signed-off-by: Yazhou Tang <tangyazhou518@outlook.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260304083228.142016-2-tangyazhou@zju.edu.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 159b25f8269d..df22bfc572e2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -15910,6 +15910,13 @@ static void scalar_byte_swap(struct bpf_reg_state *dst_reg, struct bpf_insn *ins
 	/* Apply bswap if alu64 or switch between big-endian and little-endian machines */
 	bool need_bswap = alu64 || (to_le == is_big_endian);
 
+	/*
+	 * If the register is mutated, manually reset its scalar ID to break
+	 * any existing ties and avoid incorrect bounds propagation.
+	 */
+	if (need_bswap || insn->imm == 16 || insn->imm == 32)
+		dst_reg->id = 0;
+
 	if (need_bswap) {
 		if (insn->imm == 16)
 			dst_reg->var_off = tnum_bswap16(dst_reg->var_off);
-- 
cgit v1.2.3


From ea1989746b77c3f63bce43af247e1de29ed6bf4a Mon Sep 17 00:00:00 2001
From: Yazhou Tang <tangyazhou518@outlook.com>
Date: Wed, 4 Mar 2026 16:32:28 +0800
Subject: selftests/bpf: Add test for BPF_END register ID reset

Add a test case to ensure that BPF_END operations correctly break
register's scalar ID ties.

The test creates a scenario where r1 is a copy of r0, r0 undergoes a
byte swap, and then r0 is checked against a constant.

- Without the fix in the verifier, the bounds learned from r0 are
  incorrectly propagated to r1, making the verifier believe r1 is
  bounded and wrongly allowing subsequent pointer arithmetic.

- With the fix, r1 remains an unbounded scalar, and the verifier
  correctly rejects the arithmetic operation between the frame pointer
  and the unbounded register.

Co-developed-by: Tianci Cao <ziye@zju.edu.cn>
Signed-off-by: Tianci Cao <ziye@zju.edu.cn>
Co-developed-by: Shenghao Yuan <shenghaoyuan0928@163.com>
Signed-off-by: Shenghao Yuan <shenghaoyuan0928@163.com>
Signed-off-by: Yazhou Tang <tangyazhou518@outlook.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260304083228.142016-3-tangyazhou@zju.edu.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/verifier_bswap.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 4b779deee767..cffaf36192bc 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -91,6 +91,28 @@ BSWAP_RANGE_TEST(le32_range, "le32", 0x3f00, 0x3f0000)
 BSWAP_RANGE_TEST(le64_range, "le64", 0x3f00, 0x3f000000000000)
 #endif
 
+SEC("socket")
+__description("BSWAP, reset reg id")
+__failure __msg("math between fp pointer and register with unbounded min value is not allowed")
+__naked void bswap_reset_reg_id(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	r1 = r0;					\
+	r0 = be16 r0;					\
+	if r0 != 1 goto l0_%=;				\
+	r2 = r10;					\
+	r2 += -512;					\
+	r2 += r1;					\
+	*(u8 *)(r2 + 0) = 0;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
-- 
cgit v1.2.3


From 2321a9596d2260310267622e0ad8fbfa6f95378f Mon Sep 17 00:00:00 2001
From: Sachin Kumar <xcyfun@protonmail.com>
Date: Mon, 9 Mar 2026 18:25:42 +0000
Subject: bpf: Fix constant blinding for PROBE_MEM32 stores

BPF_ST | BPF_PROBE_MEM32 immediate stores are not handled by
bpf_jit_blind_insn(), allowing user-controlled 32-bit immediates to
survive unblinded into JIT-compiled native code when bpf_jit_harden >= 1.

The root cause is that convert_ctx_accesses() rewrites BPF_ST|BPF_MEM
to BPF_ST|BPF_PROBE_MEM32 for arena pointer stores during verification,
before bpf_jit_blind_constants() runs during JIT compilation. The
blinding switch only matches BPF_ST|BPF_MEM (mode 0x60), not
BPF_ST|BPF_PROBE_MEM32 (mode 0xa0). The instruction falls through
unblinded.

Add BPF_ST|BPF_PROBE_MEM32 cases to bpf_jit_blind_insn() alongside the
existing BPF_ST|BPF_MEM cases. The blinding transformation is identical:
load the blinded immediate into BPF_REG_AX via mov+xor, then convert
the immediate store to a register store (BPF_STX).

The rewritten STX instruction must preserve the BPF_PROBE_MEM32 mode so
the architecture JIT emits the correct arena addressing (R12-based on
x86-64). Cannot use the BPF_STX_MEM() macro here because it hardcodes
BPF_MEM mode; construct the instruction directly instead.

Fixes: 6082b6c328b5 ("bpf: Recognize addr_space_cast instruction in the verifier.")
Reviewed-by: Puranjay Mohan <puranjay@kernel.org>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Sachin Kumar <xcyfun@protonmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/Y6IT5VvNRchPBLI5D7JZHBzZrU9rb0ycRJPJzJSXGj7kJlX8RJwZFSM2YZjcDxoQKABkxt1T8Os2gi23PYyFuQe6KkZGWVyfz8K5afdy9ak=@protonmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 3ece2da55625..9e126be33755 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1422,6 +1422,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from,
 		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
 		*to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off);
 		break;
+
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
+		*to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^
+				      from->imm);
+		*to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+		/*
+		 * Cannot use BPF_STX_MEM() macro here as it
+		 * hardcodes BPF_MEM mode, losing PROBE_MEM32
+		 * and breaking arena addressing in the JIT.
+		 */
+		*to++ = (struct bpf_insn) {
+			.code  = BPF_STX | BPF_PROBE_MEM32 |
+				 BPF_SIZE(from->code),
+			.dst_reg = from->dst_reg,
+			.src_reg = BPF_REG_AX,
+			.off   = from->off,
+		};
+		break;
 	}
 out:
 	return to - to_buff;
-- 
cgit v1.2.3


From 57d2371d52be1d574b33382bfbf8052485b99d8b Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Wed, 4 Mar 2026 08:30:12 +0800
Subject: tools/power turbostat: Fix illegal memory access when SMT is present
 and disabled

When SMT is present and disabled, turbostat may under-size
the thread_data array.  This can corrupt results or
cause turbostat to exit with a segmentation fault.

[lenb: commit message]
Fixes: a2b4d0f8bf07 ("tools/power turbostat: Favor cpu# over core#")
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 1a2671c28209..ae827485950d 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -9702,13 +9702,12 @@ void allocate_counters(struct counters *counters)
 {
 	int i;
 	int num_cores = topo.cores_per_node * topo.nodes_per_pkg * topo.num_packages;
-	int num_threads = topo.threads_per_core * num_cores;
 
-	counters->threads = calloc(num_threads, sizeof(struct thread_data));
+	counters->threads = calloc(topo.max_cpu_num + 1, sizeof(struct thread_data));
 	if (counters->threads == NULL)
 		goto error;
 
-	for (i = 0; i < num_threads; i++)
+	for (i = 0; i < topo.max_cpu_num + 1; i++)
 		(counters->threads)[i].cpu_id = -1;
 
 	counters->cores = calloc(num_cores, sizeof(struct core_data));
-- 
cgit v1.2.3


From e06e6b8001233241eb5b2e2791162f0585f50f4b Mon Sep 17 00:00:00 2001
From: Paul Chaignon <paul.chaignon@gmail.com>
Date: Tue, 10 Mar 2026 12:39:51 +0100
Subject: selftests/bpf: Fix pkg-config call on static builds

For commit b0dcdcb9ae75 ("resolve_btfids: Fix linker flags detection"),
I suggested setting HOSTPKG_CONFIG to $PKG_CONFIG when compiling
resolve_btfids, but I forgot the quotes around that variable.

As a result, when running vmtest.sh with static linking, it fails as
follows:

    $ LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh
    [...]
    make: unrecognized option '--static'
    Usage: make [options] [target] ...
    [...]

This worked when I tested it because HOSTPKG_CONFIG didn't have a
default value in the resolve_btfids Makefile, but once it does, the
quotes aren't preserved and it fails on the next make call.

Fixes: b0dcdcb9ae75 ("resolve_btfids: Fix linker flags detection")
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Acked-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://lore.kernel.org/r/abADBwn_ykblpABE@mail.gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d5acbeba0383..65485967c968 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -409,7 +409,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
 		EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \
-		HOSTPKG_CONFIG=$(PKG_CONFIG) \
+		HOSTPKG_CONFIG='$(PKG_CONFIG)' \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-- 
cgit v1.2.3


From 30e4b2290cc2a8d1b9ddb9dcb9c981df1f2a7399 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 10 Mar 2026 08:53:50 +0200
Subject: ASoC: codecs: rt1011: Use component to get the dapm context in
 spk_mode_put

The correct helper to use in rt1011_recv_spk_mode_put() to retrieve the
DAPM context is snd_soc_component_to_dapm(), from kcontrol we will
receive NULL pointer.

Closes: https://github.com/thesofproject/linux/issues/5691
Fixes: 5b35bb517f27 ("ASoC: codecs: rt1011: convert to snd_soc_dapm_xxx()")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20260310065350.18921-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1011.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c
index 9f34a6a35487..03f31d9d916e 100644
--- a/sound/soc/codecs/rt1011.c
+++ b/sound/soc/codecs/rt1011.c
@@ -1047,7 +1047,7 @@ static int rt1011_recv_spk_mode_put(struct snd_kcontrol *kcontrol,
 		struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
-	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_to_dapm(kcontrol);
+	struct snd_soc_dapm_context *dapm = snd_soc_component_to_dapm(component);
 	struct rt1011_priv *rt1011 =
 		snd_soc_component_get_drvdata(component);
 
-- 
cgit v1.2.3


From e809085f492842ce7a519c9ef72d40f4bca89c13 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Mon, 10 Nov 2025 11:13:38 -0800
Subject: i40e: fix src IP mask checks and memcpy argument names in cloud
 filter

Fix following issues in the IPv4 and IPv6 cloud filter handling logic in
both the add and delete paths:

- The source-IP mask check incorrectly compares mask.src_ip[0] against
  tcf.dst_ip[0]. Update it to compare against tcf.src_ip[0]. This likely
  goes unnoticed because the check is in an "else if" path that only
  executes when dst_ip is not set, most cloud filter use cases focus on
  destination-IP matching, and the buggy condition can accidentally
  evaluate true in some cases.

- memcpy() for the IPv4 source address incorrectly uses
  ARRAY_SIZE(tcf.dst_ip) instead of ARRAY_SIZE(tcf.src_ip), although
  both arrays are the same size.

- The IPv4 memcpy operations used ARRAY_SIZE(tcf.dst_ip) and ARRAY_SIZE
  (tcf.src_ip), Update these to use sizeof(cfilter->ip.v4.dst_ip) and
  sizeof(cfilter->ip.v4.src_ip) to ensure correct and explicit copy size.

- In the IPv6 delete path, memcmp() uses sizeof(src_ip6) when comparing
  dst_ip6 fields. Replace this with sizeof(dst_ip6) to make the intent
  explicit, even though both fields are struct in6_addr.

Fixes: e284fc280473 ("i40e: Add and delete cloud filter")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index fdf40f8fb239..a26c3d47ec15 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -3833,10 +3833,10 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		cfilter.n_proto = ETH_P_IP;
 		if (mask.dst_ip[0] & tcf.dst_ip[0])
 			memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
-		else if (mask.src_ip[0] & tcf.dst_ip[0])
+			       sizeof(cfilter.ip.v4.dst_ip));
+		else if (mask.src_ip[0] & tcf.src_ip[0])
 			memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
+			       sizeof(cfilter.ip.v4.src_ip));
 		break;
 	case VIRTCHNL_TCP_V6_FLOW:
 		cfilter.n_proto = ETH_P_IPV6;
@@ -3891,7 +3891,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		/* for ipv6, mask is set for all sixteen bytes (4 words) */
 		if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3])
 			if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6,
-				   sizeof(cfilter.ip.v6.src_ip6)))
+				   sizeof(cfilter.ip.v6.dst_ip6)))
 				continue;
 		if (mask.vlan_id)
 			if (cfilter.vlan_id != cf->vlan_id)
@@ -3979,10 +3979,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		cfilter->n_proto = ETH_P_IP;
 		if (mask.dst_ip[0] & tcf.dst_ip[0])
 			memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
-		else if (mask.src_ip[0] & tcf.dst_ip[0])
+			       sizeof(cfilter->ip.v4.dst_ip));
+		else if (mask.src_ip[0] & tcf.src_ip[0])
 			memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip,
-			       ARRAY_SIZE(tcf.dst_ip));
+			       sizeof(cfilter->ip.v4.src_ip));
 		break;
 	case VIRTCHNL_TCP_V6_FLOW:
 		cfilter->n_proto = ETH_P_IPV6;
-- 
cgit v1.2.3


From e94eaef11142b01f77bf8ba4d0b59720b7858109 Mon Sep 17 00:00:00 2001
From: Matt Vollrath <tactii@gmail.com>
Date: Tue, 24 Feb 2026 18:28:33 -0500
Subject: e1000/e1000e: Fix leak in DMA error cleanup

If an error is encountered while mapping TX buffers, the driver should
unmap any buffers already mapped for that skb.

Because count is incremented after a successful mapping, it will always
match the correct number of unmappings needed when dma_error is reached.
Decrementing count before the while loop in dma_error causes an
off-by-one error. If any mapping was successful before an unsuccessful
mapping, exactly one DMA mapping would leak.

In these commits, a faulty while condition caused an infinite loop in
dma_error:
Commit 03b1320dfcee ("e1000e: remove use of skb_dma_map from e1000e
driver")
Commit 602c0554d7b0 ("e1000: remove use of skb_dma_map from e1000 driver")

Commit c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of
unsigned in *_tx_map()") fixed the infinite loop, but introduced the
off-by-one error.

This issue may still exist in the igbvf driver, but I did not address it
in this patch.

Fixes: c1fa347f20f1 ("e1000/e1000e/igb/igbvf/ixgb/ixgbe: Fix tests of unsigned in *_tx_map()")
Assisted-by: Claude:claude-4.6-opus
Signed-off-by: Matt Vollrath <tactii@gmail.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 2 --
 drivers/net/ethernet/intel/e1000e/netdev.c    | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3d7648a119e5..9b09eb144b81 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2952,8 +2952,6 @@ static int e1000_tx_map(struct e1000_adapter *adapter,
 dma_error:
 	dev_err(&pdev->dev, "TX DMA map failed\n");
 	buffer_info->dma = 0;
-	if (count)
-		count--;
 
 	while (count--) {
 		if (i == 0)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 35dab1e3132f..9befdacd6730 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5652,8 +5652,6 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb,
 dma_error:
 	dev_err(&pdev->dev, "Tx DMA map failed\n");
 	buffer_info->dma = 0;
-	if (count)
-		count--;
 
 	while (count--) {
 		if (i == 0)
-- 
cgit v1.2.3


From 4a7d2729dc99437dbb880a64c47828c0d191b308 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Sat, 7 Mar 2026 18:20:16 -0300
Subject: smb: client: fix atomic open with O_DIRECT & O_SYNC

When user application requests O_DIRECT|O_SYNC along with O_CREAT on
open(2), CREATE_NO_BUFFER and CREATE_WRITE_THROUGH bits were missed in
CREATE request when performing an atomic open, thus leading to
potentially data integrity issues.

Fix this by setting those missing bits in CREATE request when
O_DIRECT|O_SYNC has been specified in cifs_do_create().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Acked-by: Henrique Carvalho <henrique.carvalho@suse.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h | 11 +++++++++++
 fs/smb/client/dir.c      |  1 +
 fs/smb/client/file.c     | 18 +++---------------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 6f9b6c72962b..bb0fe4b60240 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -20,6 +20,7 @@
 #include <linux/utsname.h>
 #include <linux/sched/mm.h>
 #include <linux/netfs.h>
+#include <linux/fcntl.h>
 #include "cifs_fs_sb.h"
 #include "cifsacl.h"
 #include <crypto/internal/hash.h>
@@ -2375,4 +2376,14 @@ static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi)
 	return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN;
 }
 
+static inline int cifs_open_create_options(unsigned int oflags, int opts)
+{
+	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
+	if (oflags & O_SYNC)
+		opts |= CREATE_WRITE_THROUGH;
+	if (oflags & O_DIRECT)
+		opts |= CREATE_NO_BUFFER;
+	return opts;
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 953f1fee8cb8..4bc217e9a727 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -308,6 +308,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 		goto out;
 	}
 
+	create_options |= cifs_open_create_options(oflags, create_options);
 	/*
 	 * if we're not using unix extensions, see if we need to set
 	 * ATTR_READONLY on the create call
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index cffcf82c1b69..13dda87f7711 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -584,15 +584,8 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
  *********************************************************************/
 
 	disposition = cifs_get_disposition(f_flags);
-
 	/* BB pass O_SYNC flag through on file attributes .. BB */
-
-	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
-	if (f_flags & O_SYNC)
-		create_options |= CREATE_WRITE_THROUGH;
-
-	if (f_flags & O_DIRECT)
-		create_options |= CREATE_NO_BUFFER;
+	create_options |= cifs_open_create_options(f_flags, create_options);
 
 retry_open:
 	oparms = (struct cifs_open_parms) {
@@ -1314,13 +1307,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
 		rdwr_for_fscache = 1;
 
 	desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache);
-
-	/* O_SYNC also has bit for O_DSYNC so following check picks up either */
-	if (cfile->f_flags & O_SYNC)
-		create_options |= CREATE_WRITE_THROUGH;
-
-	if (cfile->f_flags & O_DIRECT)
-		create_options |= CREATE_NO_BUFFER;
+	create_options |= cifs_open_create_options(cfile->f_flags,
+						   create_options);
 
 	if (server->ops->get_lease_key)
 		server->ops->get_lease_key(inode, &cfile->fid);
-- 
cgit v1.2.3


From fae11330dc0642065568d6c0045322293fe59bc6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Mar 2026 16:07:13 +0100
Subject: smb: client: fix sbflags initialization

The newly introduced variable is initialized in an #ifdef block
but used outside of it, leading to undefined behavior when
CONFIG_CIFS_ALLOW_INSECURE_LEGACY is disabled:

fs/smb/client/dir.c:417:9: error: variable 'sbflags' is uninitialized when used here [-Werror,-Wuninitialized]
  417 |                                 if (sbflags & CIFS_MOUNT_DYNPERM)
      |                                     ^~~~~~~

Move the initialization into the declaration, the same way as the
other similar function do it.

Fixes: 4fc3a433c139 ("smb: client: use atomic_t for mnt_cifs_flags")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/dir.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 4bc217e9a727..6d2378eeb7f6 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -187,7 +187,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
 	const char *full_path;
 	void *page = alloc_dentry_path();
 	struct inode *newinode = NULL;
-	unsigned int sbflags;
+	unsigned int sbflags = cifs_sb_flags(cifs_sb);
 	int disposition;
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
@@ -368,7 +368,6 @@ retry_open:
 	 * If Open reported that we actually created a file then we now have to
 	 * set the mode if possible.
 	 */
-	sbflags = cifs_sb_flags(cifs_sb);
 	if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
 		struct cifs_unix_set_info_args args = {
 				.mode	= mode,
-- 
cgit v1.2.3


From d78840a6a38d312dc1a51a65317bb67e46f0b929 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Mon, 9 Mar 2026 16:00:49 +0530
Subject: smb: client: fix in-place encryption corruption in SMB2_write()

SMB2_write() places write payload in iov[1..n] as part of rq_iov.
smb3_init_transform_rq() pointer-shares rq_iov, so crypt_message()
encrypts iov[1] in-place, replacing the original plaintext with
ciphertext. On a replayable error, the retry sends the same iov[1]
which now contains ciphertext instead of the original data,
resulting in corruption.

The corruption is most likely to be observed when connections are
unstable, as reconnects trigger write retries that re-send the
already-encrypted data.

This affects SFU mknod, MF symlinks, etc. On kernels before
6.10 (prior to the netfs conversion), sync writes also used
this path and were similarly affected. The async write path
wasn't unaffected as it uses rq_iter which gets deep-copied.

Fix by moving the write payload into rq_iter via iov_iter_kvec(),
so smb3_init_transform_rq() deep-copies it before encryption.

Cc: stable@vger.kernel.org #6.3+
Acked-by: Henrique Carvalho <henrique.carvalho@suse.com>
Acked-by: Shyam Prasad N <sprasad@microsoft.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2pdu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c43ca74e8704..5188218c25be 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -5307,7 +5307,10 @@ replay_again:
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = n_vec + 1;
+	/* iov[0] is the SMB header; move payload to rq_iter for encryption safety */
+	rqst.rq_nvec = 1;
+	iov_iter_kvec(&rqst.rq_iter, ITER_SOURCE, &iov[1], n_vec,
+		      io_parms->length);
 
 	if (retries) {
 		/* Back-off before retry */
-- 
cgit v1.2.3


From 88d37abb366be95d772ceb4c7f26772e78447252 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Tue, 10 Mar 2026 21:08:47 +0800
Subject: smb/client: only export symbol for 'smb2maperror-test' module

Only export smb2_get_err_map_test smb2_error_map_table_test and
smb2_error_map_num symbol for 'smb2maperror-test' module.

Fixes: 7d0bf050a587 ("smb/client: make SMB2 maperror KUnit tests a separate module")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2maperror.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index f4cff44e2796..2b8782c4f684 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -109,6 +109,9 @@ int __init smb2_init_maperror(void)
 }
 
 #if IS_ENABLED(CONFIG_SMB_KUNIT_TESTS)
+#define EXPORT_SYMBOL_FOR_SMB_TEST(sym) \
+	EXPORT_SYMBOL_FOR_MODULES(sym, "smb2maperror_test")
+
 /* Previous prototype for eliminating the build warning. */
 const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status);
 
@@ -116,11 +119,11 @@ const struct status_to_posix_error *smb2_get_err_map_test(__u32 smb2_status)
 {
 	return smb2_get_err_map(smb2_status);
 }
-EXPORT_SYMBOL_GPL(smb2_get_err_map_test);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_get_err_map_test);
 
 const struct status_to_posix_error *smb2_error_map_table_test = smb2_error_map_table;
-EXPORT_SYMBOL_GPL(smb2_error_map_table_test);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_table_test);
 
 unsigned int smb2_error_map_num = ARRAY_SIZE(smb2_error_map_table);
-EXPORT_SYMBOL_GPL(smb2_error_map_num);
+EXPORT_SYMBOL_FOR_SMB_TEST(smb2_error_map_num);
 #endif
-- 
cgit v1.2.3


From 36f46b0e36892eba08978eef7502ff3c94ddba77 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Sat, 28 Feb 2026 00:00:09 +0100
Subject: crash_dump: don't log dm-crypt key bytes in read_key_from_user_keying

When debug logging is enabled, read_key_from_user_keying() logs the first
8 bytes of the key payload and partially exposes the dm-crypt key.  Stop
logging any key bytes.

Link: https://lkml.kernel.org/r/20260227230008.858641-2-thorsten.blum@linux.dev
Fixes: 479e58549b0f ("crash_dump: store dm crypt keys in kdump reserved memory")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Cc: Baoquan He <bhe@redhat.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/crash_dump_dm_crypt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/crash_dump_dm_crypt.c b/kernel/crash_dump_dm_crypt.c
index 1f4067fbdb94..a20d4097744a 100644
--- a/kernel/crash_dump_dm_crypt.c
+++ b/kernel/crash_dump_dm_crypt.c
@@ -168,8 +168,8 @@ static int read_key_from_user_keying(struct dm_crypt_key *dm_key)
 
 	memcpy(dm_key->data, ukp->data, ukp->datalen);
 	dm_key->key_size = ukp->datalen;
-	kexec_dprintk("Get dm crypt key (size=%u) %s: %8ph\n", dm_key->key_size,
-		      dm_key->key_desc, dm_key->data);
+	kexec_dprintk("Get dm crypt key (size=%u) %s\n", dm_key->key_size,
+		      dm_key->key_desc);
 
 out:
 	up_read(&key->sem);
-- 
cgit v1.2.3


From 6ffd853b0b10e1e292cef0bfd0997986471254de Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:51:44 -0800
Subject: build_bug.h: correct function parameters names in kernel-doc

Use the correct function (or macro) names to avoid kernel-doc warnings:

Warning: include/linux/build_bug.h:38 function parameter 'cond' not
 described in 'BUILD_BUG_ON_MSG'
Warning: include/linux/build_bug.h:38 function parameter 'msg' not
 described in 'BUILD_BUG_ON_MSG'
Warning: include/linux/build_bug.h:76 function parameter 'expr' not
 described in 'static_assert'

Link: https://lkml.kernel.org/r/20260302005144.3467019-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/build_bug.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 2cfbb4c65c78..d3dc5dc5f916 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -32,7 +32,8 @@
 /**
  * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
  *		      error message.
- * @condition: the condition which the compiler should know is false.
+ * @cond: the condition which the compiler should know is false.
+ * @msg: build-time error message
  *
  * See BUILD_BUG_ON for description.
  */
@@ -60,6 +61,7 @@
 
 /**
  * static_assert - check integer constant expression at build time
+ * @expr: expression to be checked
  *
  * static_assert() is a wrapper for the C11 _Static_assert, with a
  * little macro magic to make the message optional (defaulting to the
-- 
cgit v1.2.3


From fae654083bfa409bb2244f390232e2be47f05bfc Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Tue, 3 Mar 2026 07:21:21 +0000
Subject: mm/huge_memory: fix use of NULL folio in move_pages_huge_pmd()

move_pages_huge_pmd() handles UFFDIO_MOVE for both normal THPs and huge
zero pages.  For the huge zero page path, src_folio is explicitly set to
NULL, and is used as a sentinel to skip folio operations like lock and
rmap.

In the huge zero page branch, src_folio is NULL, so folio_mk_pmd(NULL,
pgprot) passes NULL through folio_pfn() and page_to_pfn().  With
SPARSEMEM_VMEMMAP this silently produces a bogus PFN, installing a PMD
pointing to non-existent physical memory.  On other memory models it is a
NULL dereference.

Use page_folio(src_page) to obtain the valid huge zero folio from the
page, which was obtained from pmd_page() and remains valid throughout.

After commit d82d09e48219 ("mm/huge_memory: mark PMD mappings of the huge
zero folio special"), moved huge zero PMDs must remain special so
vm_normal_page_pmd() continues to treat them as special mappings.

move_pages_huge_pmd() currently reconstructs the destination PMD in the
huge zero page branch, which drops PMD state such as pmd_special() on
architectures with CONFIG_ARCH_HAS_PTE_SPECIAL.  As a result,
vm_normal_page_pmd() can treat the moved huge zero PMD as a normal page
and corrupt its refcount.

Instead of reconstructing the PMD from the folio, derive the destination
entry from src_pmdval after pmdp_huge_clear_flush(), then handle the PMD
metadata the same way move_huge_pmd() does for moved entries by marking it
soft-dirty and clearing uffd-wp.

Link: https://lkml.kernel.org/r/a1e787dd-b911-474d-8570-f37685357d86@lucifer.local
Fixes: e3981db444a0 ("mm: add folio_mk_pmd()")
Signed-off-by: Chris Down <chris@chrisdown.name>
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 912c248a3f7e..b298cba853ab 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2797,7 +2797,8 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm
 		_dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
 	} else {
 		src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
-		_dst_pmd = folio_mk_pmd(src_folio, dst_vma->vm_page_prot);
+		_dst_pmd = move_soft_dirty_pmd(src_pmdval);
+		_dst_pmd = clear_uffd_wp_pmd(_dst_pmd);
 	}
 	set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);
 
-- 
cgit v1.2.3


From 29f40594a28114b9a9bc87f6cf7bbee9609628f2 Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Tue, 3 Mar 2026 11:45:28 +0530
Subject: mm/rmap: fix incorrect pte restoration for lazyfree folios

We batch unmap anonymous lazyfree folios by folio_unmap_pte_batch.  If the
batch has a mix of writable and non-writable bits, we may end up setting
the entire batch writable.  Fix this by respecting writable bit during
batching.

Although on a successful unmap of a lazyfree folio, the soft-dirty bit is
lost, preserve it on pte restoration by respecting the bit during
batching, to make the fix consistent w.r.t both writable bit and
soft-dirty bit.

I was able to write the below reproducer and crash the kernel.
Explanation of reproducer (set 64K mTHP to always):

Fault in a 64K large folio.  Split the VMA at mid-point with
MADV_DONTFORK.  fork() - parent points to the folio with 8 writable ptes
and 8 non-writable ptes.  Merge the VMAs with MADV_DOFORK so that
folio_unmap_pte_batch() can determine all the 16 ptes as a batch.  Do
MADV_FREE on the range to mark the folio as lazyfree.  Write to the memory
to dirty the pte, eventually rmap will dirty the folio.  Then trigger
reclaim, we will hit the pte restoration path, and the kernel will crash
with the trace given below.

The BUG happens at:

	BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw);

The code path is asking for anonymous page to be mapped writable into the
pagetable.  The BUG_ON() firing implies that such a writable page has been
mapped into the pagetables of more than one process, which breaks
anonymous memory/CoW semantics.

[   21.134473] kernel BUG at mm/page_table_check.c:118!
[   21.134497] Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
[   21.135917] Modules linked in:
[   21.136085] CPU: 1 UID: 0 PID: 1735 Comm: dup-lazyfree Not tainted 7.0.0-rc1-00116-g018018a17770 #1028 PREEMPT
[   21.136858] Hardware name: linux,dummy-virt (DT)
[   21.137019] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[   21.137308] pc : page_table_check_set+0x28c/0x2a8
[   21.137607] lr : page_table_check_set+0x134/0x2a8
[   21.137885] sp : ffff80008a3b3340
[   21.138124] x29: ffff80008a3b3340 x28: fffffdffc3d14400 x27: ffffd1a55e03d000
[   21.138623] x26: 0040000000000040 x25: ffffd1a55f7dd000 x24: 0000000000000001
[   21.139045] x23: 0000000000000001 x22: 0000000000000001 x21: ffffd1a55f217f30
[   21.139629] x20: 0000000000134521 x19: 0000000000134519 x18: 005c43e000040000
[   21.140027] x17: 0001400000000000 x16: 0001700000000000 x15: 000000000000ffff
[   21.140578] x14: 000000000000000c x13: 005c006000000000 x12: 0000000000000020
[   21.140828] x11: 0000000000000000 x10: 005c000000000000 x9 : ffffd1a55c079ee0
[   21.141077] x8 : 0000000000000001 x7 : 005c03e000040000 x6 : 000000004000ffff
[   21.141490] x5 : ffff00017fffce00 x4 : 0000000000000001 x3 : 0000000000000002
[   21.141741] x2 : 0000000000134510 x1 : 0000000000000000 x0 : ffff0000c08228c0
[   21.141991] Call trace:
[   21.142093]  page_table_check_set+0x28c/0x2a8 (P)
[   21.142265]  __page_table_check_ptes_set+0x144/0x1e8
[   21.142441]  __set_ptes_anysz.constprop.0+0x160/0x1a8
[   21.142766]  contpte_set_ptes+0xe8/0x140
[   21.142907]  try_to_unmap_one+0x10c4/0x10d0
[   21.143177]  rmap_walk_anon+0x100/0x250
[   21.143315]  try_to_unmap+0xa0/0xc8
[   21.143441]  shrink_folio_list+0x59c/0x18a8
[   21.143759]  shrink_lruvec+0x664/0xbf0
[   21.144043]  shrink_node+0x218/0x878
[   21.144285]  __node_reclaim.constprop.0+0x98/0x338
[   21.144763]  user_proactive_reclaim+0x2a4/0x340
[   21.145056]  reclaim_store+0x3c/0x60
[   21.145216]  dev_attr_store+0x20/0x40
[   21.145585]  sysfs_kf_write+0x84/0xa8
[   21.145835]  kernfs_fop_write_iter+0x130/0x1c8
[   21.145994]  vfs_write+0x2b8/0x368
[   21.146119]  ksys_write+0x70/0x110
[   21.146240]  __arm64_sys_write+0x24/0x38
[   21.146380]  invoke_syscall+0x50/0x120
[   21.146513]  el0_svc_common.constprop.0+0x48/0xf8
[   21.146679]  do_el0_svc+0x28/0x40
[   21.146798]  el0_svc+0x34/0x110
[   21.146926]  el0t_64_sync_handler+0xa0/0xe8
[   21.147074]  el0t_64_sync+0x198/0x1a0
[   21.147225] Code: f9400441 b4fff241 17ffff94 d4210000 (d4210000)
[   21.147440] ---[ end trace 0000000000000000 ]---

#define _GNU_SOURCE
#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <string.h>
#include <sys/wait.h>
#include <sched.h>
#include <fcntl.h>

void write_to_reclaim() {
    const char *path = "/sys/devices/system/node/node0/reclaim";
    const char *value = "409600000000";
    int fd = open(path, O_WRONLY);
    if (fd == -1) {
        perror("open");
        exit(EXIT_FAILURE);
    }

    if (write(fd, value, sizeof("409600000000") - 1) == -1) {
        perror("write");
        close(fd);
        exit(EXIT_FAILURE);
    }

    printf("Successfully wrote %s to %s\n", value, path);
    close(fd);
}

int main()
{
	char *ptr = mmap((void *)(1UL << 30), 1UL << 16, PROT_READ | PROT_WRITE,
			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
	if ((unsigned long)ptr != (1UL << 30)) {
		perror("mmap");
		return 1;
	}

	/* a 64K folio gets faulted in */
	memset(ptr, 0, 1UL << 16);

	/* 32K half will not be shared into child */
	if (madvise(ptr, 1UL << 15, MADV_DONTFORK)) {
		perror("madvise madv dontfork");
		return 1;
	}

	pid_t pid = fork();

	if (pid < 0) {
		perror("fork");
		return 1;
	} else if (pid == 0) {
		sleep(15);
	} else {
		/* merge VMAs. now first half of the 16 ptes are writable, the other half not. */
		if (madvise(ptr, 1UL << 15, MADV_DOFORK)) {
			perror("madvise madv fork");
			return 1;
		}
		if (madvise(ptr, (1UL << 16), MADV_FREE)) {
			perror("madvise madv free");
			return 1;
		}

		/* dirty the large folio */
		(*ptr) += 10;

		write_to_reclaim();
		// sleep(10);
		waitpid(pid, NULL, 0);

	}
}

Link: https://lkml.kernel.org/r/20260303061528.2429162-1-dev.jain@arm.com
Fixes: 354dffd29575 ("mm: support batched unmap for lazyfree large folios during reclamation")
Signed-off-by: Dev Jain <dev.jain@arm.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Tested-by: Lance Yang <lance.yang@linux.dev>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/rmap.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index 0f00570d1b9e..b1ba1236ffba 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1955,7 +1955,14 @@ static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
 	if (userfaultfd_wp(vma))
 		return 1;
 
-	return folio_pte_batch(folio, pvmw->pte, pte, max_nr);
+	/*
+	 * If unmap fails, we need to restore the ptes. To avoid accidentally
+	 * upgrading write permissions for ptes that were not originally
+	 * writable, and to avoid losing the soft-dirty bit, use the
+	 * appropriate FPB flags.
+	 */
+	return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr,
+				     FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY);
 }
 
 /*
-- 
cgit v1.2.3


From 939080834fef3ce42fdbcfef33fd29c9ffe5bbed Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Thu, 5 Mar 2026 01:50:06 +0000
Subject: mm/huge_memory: fix early failure try_to_migrate() when split huge
 pmd for shared THP

Commit 60fbb14396d5 ("mm/huge_memory: adjust try_to_migrate_one() and
split_huge_pmd_locked()") return false unconditionally after
split_huge_pmd_locked().  This may fail try_to_migrate() early when
TTU_SPLIT_HUGE_PMD is specified.

The reason is the above commit adjusted try_to_migrate_one() to, when a
PMD-mapped THP entry is found, and TTU_SPLIT_HUGE_PMD is specified (for
example, via unmap_folio()), return false unconditionally.  This breaks
the rmap walk and fail try_to_migrate() early, if this PMD-mapped THP is
mapped in multiple processes.

The user sensible impact of this bug could be:

  * On memory pressure, shrink_folio_list() may split partially mapped
    folio with split_folio_to_list(). Then free unmapped pages without IO.
    If failed, it may not be reclaimed.
  * On memory failure, memory_failure() would call try_to_split_thp_page()
    to split folio contains the bad page. If succeed, the PG_has_hwpoisoned
    bit is only set in the after-split folio contains @split_at. By doing
    so, we limit bad memory. If failed to split, the whole folios is not
    usable.

One way to reproduce:

    Create an anonymous THP range and fork 512 children, so we have a
    THP shared mapped in 513 processes. Then trigger folio split with
    /sys/kernel/debug/split_huge_pages debugfs to split the THP folio to
    order 0.

Without the above commit, we can successfully split to order 0.  With the
above commit, the folio is still a large folio.

And currently there are two core users of TTU_SPLIT_HUGE_PMD:

  * try_to_unmap_one()
  * try_to_migrate_one()

try_to_unmap_one() would restart the rmap walk, so only
try_to_migrate_one() is affected.

We can't simply revert commit 60fbb14396d5 ("mm/huge_memory: adjust
try_to_migrate_one() and split_huge_pmd_locked()"), since it removed some
duplicated check covered by page_vma_mapped_walk().

This patch fixes this by restart page_vma_mapped_walk() after
split_huge_pmd_locked().  Since we cannot simply return "true" to fix the
problem, as that would affect another case:

    When invoking folio_try_share_anon_rmap_pmd() from
    split_huge_pmd_locked(), the latter can fail and leave a large folio
    mapped through PTEs, in which case we ought to return true from
    try_to_migrate_one(). This might result in unnecessary walking of the
    rmap but is relatively harmless.

Link: https://lkml.kernel.org/r/20260305015006.27343-1-richard.weiyang@gmail.com
Fixes: 60fbb14396d5 ("mm/huge_memory: adjust try_to_migrate_one() and split_huge_pmd_locked()")
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Tested-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Gavin Guo <gavinguo@igalia.com>
Acked-by: David Hildenbrand (arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/rmap.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index b1ba1236ffba..391337282e3f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2450,11 +2450,17 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			__maybe_unused pmd_t pmdval;
 
 			if (flags & TTU_SPLIT_HUGE_PMD) {
+				/*
+				 * split_huge_pmd_locked() might leave the
+				 * folio mapped through PTEs. Retry the walk
+				 * so we can detect this scenario and properly
+				 * abort the walk.
+				 */
 				split_huge_pmd_locked(vma, pvmw.address,
 						      pvmw.pmd, true);
-				ret = false;
-				page_vma_mapped_walk_done(&pvmw);
-				break;
+				flags &= ~TTU_SPLIT_HUGE_PMD;
+				page_vma_mapped_walk_restart(&pvmw);
+				continue;
 			}
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 			pmdval = pmdp_get(pvmw.pmd);
-- 
cgit v1.2.3


From 182b9b3d8d1d36500f58e4f3dc82b144d6487bdf Mon Sep 17 00:00:00 2001
From: Ignat Korchagin <ignat@cloudflare.com>
Date: Mon, 9 Mar 2026 17:34:45 +0000
Subject: MAINTAINERS: update email address for Ignat Korchagin

Since I'm moving from Cloudflare update my email address in the
MAINTAINERS file and add an entry to .mailmap so nothing gets lost.

Link: https://lkml.kernel.org/r/20260309173445.71393-1-ignat@cloudflare.com
Signed-off-by: Ignat Korchagin <ignat@cloudflare.com>
Acked-by: Lukas Wunner <lukas@wunner.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/.mailmap b/.mailmap
index 63c11ea7e35d..40b4db2b2d60 100644
--- a/.mailmap
+++ b/.mailmap
@@ -327,6 +327,7 @@ Henrik Rydberg <rydberg@bitmath.org>
 Herbert Xu <herbert@gondor.apana.org.au>
 Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com>
 Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn>
+Ignat Korchagin <ignat@linux.win> <ignat@cloudflare.com>
 Ike Panhc <ikepanhc@gmail.com> <ike.pan@canonical.com>
 J. Bruce Fields <bfields@fieldses.org> <bfields@redhat.com>
 J. Bruce Fields <bfields@fieldses.org> <bfields@citi.umich.edu>
diff --git a/MAINTAINERS b/MAINTAINERS
index 837db4f7bcca..4a24c6bca0d6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4022,7 +4022,7 @@ F:	drivers/hwmon/asus_wmi_sensors.c
 ASYMMETRIC KEYS
 M:	David Howells <dhowells@redhat.com>
 M:	Lukas Wunner <lukas@wunner.de>
-M:	Ignat Korchagin <ignat@cloudflare.com>
+M:	Ignat Korchagin <ignat@linux.win>
 L:	keyrings@vger.kernel.org
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
@@ -4035,7 +4035,7 @@ F:	include/linux/verification.h
 
 ASYMMETRIC KEYS - ECDSA
 M:	Lukas Wunner <lukas@wunner.de>
-M:	Ignat Korchagin <ignat@cloudflare.com>
+M:	Ignat Korchagin <ignat@linux.win>
 R:	Stefan Berger <stefanb@linux.ibm.com>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
@@ -4045,14 +4045,14 @@ F:	include/crypto/ecc*
 
 ASYMMETRIC KEYS - GOST
 M:	Lukas Wunner <lukas@wunner.de>
-M:	Ignat Korchagin <ignat@cloudflare.com>
+M:	Ignat Korchagin <ignat@linux.win>
 L:	linux-crypto@vger.kernel.org
 S:	Odd fixes
 F:	crypto/ecrdsa*
 
 ASYMMETRIC KEYS - RSA
 M:	Lukas Wunner <lukas@wunner.de>
-M:	Ignat Korchagin <ignat@cloudflare.com>
+M:	Ignat Korchagin <ignat@linux.win>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	crypto/rsa*
-- 
cgit v1.2.3


From 85b731ad4bbf6eb3fedf267ab00be3596f148432 Mon Sep 17 00:00:00 2001
From: Alan Borzeszkowski <alan.borzeszkowski@linux.intel.com>
Date: Mon, 9 Mar 2026 16:37:03 +0100
Subject: spi: intel-pci: Add support for Nova Lake mobile SPI flash

Add Intel Nova Lake PCD-H SPI serial flash PCI ID to the list of
supported devices.

Signed-off-by: Alan Borzeszkowski <alan.borzeszkowski@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://patch.msgid.link/20260309153703.74282-1-alan.borzeszkowski@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-intel-pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c
index bce3d149bea1..d8ef8f89330a 100644
--- a/drivers/spi/spi-intel-pci.c
+++ b/drivers/spi/spi-intel-pci.c
@@ -96,6 +96,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0xd323), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xe323), (unsigned long)&cnl_info },
 	{ PCI_VDEVICE(INTEL, 0xe423), (unsigned long)&cnl_info },
 	{ },
-- 
cgit v1.2.3


From 881a0263d502e1a93ebc13a78254e9ad19520232 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Sat, 7 Mar 2026 15:08:54 +0800
Subject: net: macb: Shuffle the tx ring before enabling tx

Quanyang observed that when using an NFS rootfs on an AMD ZynqMp board,
the rootfs may take an extended time to recover after a suspend.
Upon investigation, it was determined that the issue originates from a
problem in the macb driver.

According to the Zynq UltraScale TRM [1], when transmit is disabled,
the transmit buffer queue pointer resets to point to the address
specified by the transmit buffer queue base address register.

In the current implementation, the code merely resets `queue->tx_head`
and `queue->tx_tail` to '0'. This approach presents several issues:

- Packets already queued in the tx ring are silently lost,
  leading to memory leaks since the associated skbs cannot be released.

- Concurrent write access to `queue->tx_head` and `queue->tx_tail` may
  occur from `macb_tx_poll()` or `macb_start_xmit()` when these values
  are reset to '0'.

- The transmission may become stuck on a packet that has already been sent
  out, with its 'TX_USED' bit set, but has not yet been processed. However,
  due to the manipulation of 'queue->tx_head' and 'queue->tx_tail',
  `macb_tx_poll()` incorrectly assumes there are no packets to handle
  because `queue->tx_head == queue->tx_tail`. This issue is only resolved
  when a new packet is placed at this position. This is the root cause of
  the prolonged recovery time observed for the NFS root filesystem.

To resolve this issue, shuffle the tx ring and tx skb array so that
the first unsent packet is positioned at the start of the tx ring.
Additionally, ensure that updates to `queue->tx_head` and
`queue->tx_tail` are properly protected with the appropriate lock.

[1] https://docs.amd.com/v/u/en-US/ug1085-zynq-ultrascale-trm

Fixes: bf9cf80cab81 ("net: macb: Fix tx/rx malfunction after phy link down and up")
Reported-by: Quanyang Wang <quanyang.wang@windriver.com>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260307-zynqmp-v2-1-6ef98a70e1d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 98 +++++++++++++++++++++++++++++++-
 1 file changed, 95 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 5bc35f651ebd..f290d608b409 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -36,6 +36,7 @@
 #include <linux/tcp.h>
 #include <linux/types.h>
 #include <linux/udp.h>
+#include <linux/gcd.h>
 #include <net/pkt_sched.h>
 #include "macb.h"
 
@@ -668,6 +669,97 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode,
 	netif_tx_stop_all_queues(ndev);
 }
 
+/* Use juggling algorithm to left rotate tx ring and tx skb array */
+static void gem_shuffle_tx_one_ring(struct macb_queue *queue)
+{
+	unsigned int head, tail, count, ring_size, desc_size;
+	struct macb_tx_skb tx_skb, *skb_curr, *skb_next;
+	struct macb_dma_desc *desc_curr, *desc_next;
+	unsigned int i, cycles, shift, curr, next;
+	struct macb *bp = queue->bp;
+	unsigned char desc[24];
+	unsigned long flags;
+
+	desc_size = macb_dma_desc_get_size(bp);
+
+	if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc)))
+		return;
+
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
+	head = queue->tx_head;
+	tail = queue->tx_tail;
+	ring_size = bp->tx_ring_size;
+	count = CIRC_CNT(head, tail, ring_size);
+
+	if (!(tail % ring_size))
+		goto unlock;
+
+	if (!count) {
+		queue->tx_head = 0;
+		queue->tx_tail = 0;
+		goto unlock;
+	}
+
+	shift = tail % ring_size;
+	cycles = gcd(ring_size, shift);
+
+	for (i = 0; i < cycles; i++) {
+		memcpy(&desc, macb_tx_desc(queue, i), desc_size);
+		memcpy(&tx_skb, macb_tx_skb(queue, i),
+		       sizeof(struct macb_tx_skb));
+
+		curr = i;
+		next = (curr + shift) % ring_size;
+
+		while (next != i) {
+			desc_curr = macb_tx_desc(queue, curr);
+			desc_next = macb_tx_desc(queue, next);
+
+			memcpy(desc_curr, desc_next, desc_size);
+
+			if (next == ring_size - 1)
+				desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+			if (curr == ring_size - 1)
+				desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+
+			skb_curr = macb_tx_skb(queue, curr);
+			skb_next = macb_tx_skb(queue, next);
+			memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb));
+
+			curr = next;
+			next = (curr + shift) % ring_size;
+		}
+
+		desc_curr = macb_tx_desc(queue, curr);
+		memcpy(desc_curr, &desc, desc_size);
+		if (i == ring_size - 1)
+			desc_curr->ctrl &= ~MACB_BIT(TX_WRAP);
+		if (curr == ring_size - 1)
+			desc_curr->ctrl |= MACB_BIT(TX_WRAP);
+		memcpy(macb_tx_skb(queue, curr), &tx_skb,
+		       sizeof(struct macb_tx_skb));
+	}
+
+	queue->tx_head = count;
+	queue->tx_tail = 0;
+
+	/* Make descriptor updates visible to hardware */
+	wmb();
+
+unlock:
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
+}
+
+/* Rotate the queue so that the tail is at index 0 */
+static void gem_shuffle_tx_rings(struct macb *bp)
+{
+	struct macb_queue *queue;
+	int q;
+
+	for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++)
+		gem_shuffle_tx_one_ring(queue);
+}
+
 static void macb_mac_link_up(struct phylink_config *config,
 			     struct phy_device *phy,
 			     unsigned int mode, phy_interface_t interface,
@@ -706,8 +798,6 @@ static void macb_mac_link_up(struct phylink_config *config,
 			ctrl |= MACB_BIT(PAE);
 
 		for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-			queue->tx_head = 0;
-			queue->tx_tail = 0;
 			queue_writel(queue, IER,
 				     bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP));
 		}
@@ -721,8 +811,10 @@ static void macb_mac_link_up(struct phylink_config *config,
 
 	spin_unlock_irqrestore(&bp->lock, flags);
 
-	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
 		macb_set_tx_clk(bp, speed);
+		gem_shuffle_tx_rings(bp);
+	}
 
 	/* Enable Rx and Tx; Enable PTP unicast */
 	ctrl = macb_readl(bp, NCR);
-- 
cgit v1.2.3


From 28b225282d44e2ef40e7f46cfdbd5d1b20b8874f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 Mar 2026 17:39:07 -0700
Subject: page_pool: store detach_time as ktime_t to avoid false-negatives

While testing other changes in vng I noticed that
nl_netdev.page_pool_check flakes. This never happens in real CI.

Turns out vng may boot and get to that test in less than a second.
page_pool_detached() records the detach time in seconds, so if
vng is fast enough detach time is set to 0. Other code treats
0 as "not detached". detach_time is only used to report the state
to the user, so it's not a huge deal in practice but let's fix it.
Store the raw ktime_t (nanoseconds) instead. A nanosecond value
of 0 is practically impossible.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Fixes: 69cb4952b6f6 ("net: page_pool: report when page pool was destroyed")
Link: https://patch.msgid.link/20260310003907.3540019-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 2 +-
 net/core/page_pool_user.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 0d453484a585..cdd95477af7a 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -247,7 +247,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
-		u64 detach_time;
+		ktime_t detach_time;
 		u32 id;
 	} user;
 };
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index c82a95beceff..ee5060d8eec0 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -245,7 +245,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		goto err_cancel;
 	if (pool->user.detach_time &&
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME,
-			 pool->user.detach_time))
+			 ktime_divns(pool->user.detach_time, NSEC_PER_SEC)))
 		goto err_cancel;
 
 	if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL))
@@ -337,7 +337,7 @@ err_unlock:
 void page_pool_detached(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
-	pool->user.detach_time = ktime_get_boottime_seconds();
+	pool->user.detach_time = ktime_get_boottime();
 	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
 	mutex_unlock(&page_pools_lock);
 }
-- 
cgit v1.2.3


From 2503d08f8a2de618e5c3a8183b250ff4a2e2d52c Mon Sep 17 00:00:00 2001
From: Fan Wu <fanwu01@zju.edu.cn>
Date: Mon, 9 Mar 2026 13:24:09 +0000
Subject: net: ethernet: arc: emac: quiesce interrupts before requesting IRQ

Normal RX/TX interrupts are enabled later, in arc_emac_open(), so probe
should not see interrupt delivery in the usual case. However, hardware may
still present stale or latched interrupt status left by firmware or the
bootloader.

If probe later unwinds after devm_request_irq() has installed the handler,
such a stale interrupt can still reach arc_emac_intr() during teardown and
race with release of the associated net_device.

Avoid that window by putting the device into a known quiescent state before
requesting the IRQ: disable all EMAC interrupt sources and clear any
pending EMAC interrupt status bits. This keeps the change hardware-focused
and minimal, while preventing spurious IRQ delivery from leftover state.

Fixes: e4f2379db6c6 ("ethernet/arc/arc_emac - Add new driver")
Cc: stable@vger.kernel.org
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Link: https://patch.msgid.link/20260309132409.584966-1-fanwu01@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/arc/emac_main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 8283aeee35fb..dde4046cbf01 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -934,6 +934,17 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	/* Set poll rate so that it polls every 1 ms */
 	arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000);
 
+	/*
+	 * Put the device into a known quiescent state before requesting
+	 * the IRQ. Clear only EMAC interrupt status bits here; leave the
+	 * MDIO completion bit alone and avoid writing TXPL_MASK, which is
+	 * used to force TX polling rather than acknowledge interrupts.
+	 */
+	arc_reg_set(priv, R_ENABLE, 0);
+	arc_reg_set(priv, R_STATUS, RXINT_MASK | TXINT_MASK | ERR_MASK |
+		    TXCH_MASK | MSER_MASK | RXCR_MASK |
+		    RXFR_MASK | RXFL_MASK);
+
 	ndev->irq = irq;
 	dev_info(dev, "IRQ is %d\n", ndev->irq);
 
-- 
cgit v1.2.3


From f441b489cc66fbc44d78b6c123e74283b8077431 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 10 Mar 2026 00:41:56 +0000
Subject: net: dsa: mxl862xx: don't set user_mii_bus

The PHY addresses in the MII bus are not equal to the port addresses,
so the bus cannot be assigned as user_mii_bus. Falling back on the
user_mii_bus in case a PHY isn't declared in device tree will result in
using the wrong (in this case: off-by-+1) PHY.
Remove the wrong assignment.

Fixes: 23794bec1cb60 ("net: dsa: add basic initial driver for MxL862xx switches")
Suggested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/0f0df310fd8cab57e0e5e3d0831dd057fd05bcd5.1773103271.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mxl862xx/mxl862xx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c
index b1e2094b5816..d7ab04f5afef 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx.c
+++ b/drivers/net/dsa/mxl862xx/mxl862xx.c
@@ -149,7 +149,6 @@ static int mxl862xx_setup_mdio(struct dsa_switch *ds)
 		return -ENOMEM;
 
 	bus->priv = priv;
-	ds->user_mii_bus = bus;
 	bus->name = KBUILD_MODNAME "-mii";
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev));
 	bus->read_c45 = mxl862xx_phy_read_c45_mii_bus;
-- 
cgit v1.2.3


From 57885276cc16a2e2b76282c808a4e84cbecb3aae Mon Sep 17 00:00:00 2001
From: Paul Moses <p@1g4.org>
Date: Mon, 9 Mar 2026 17:35:10 +0000
Subject: net-shapers: don't free reply skb after genlmsg_reply()

genlmsg_reply() hands the reply skb to netlink, and
netlink_unicast() consumes it on all return paths, whether the
skb is queued successfully or freed on an error path.

net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit()
currently jump to free_msg after genlmsg_reply() fails and call
nlmsg_free(msg), which can hit the same skb twice.

Return the genlmsg_reply() error directly and keep free_msg
only for pre-reply failures.

Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation")
Fixes: 553ea9f1efd6 ("net: shaper: implement introspection support")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moses <p@1g4.org>
Link: https://patch.msgid.link/20260309173450.538026-2-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/shaper/shaper.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
index 005bfc766e22..3fd6629cb999 100644
--- a/net/shaper/shaper.c
+++ b/net/shaper/shaper.c
@@ -759,11 +759,7 @@ int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret)
 		goto free_msg;
 
-	ret = genlmsg_reply(msg, info);
-	if (ret)
-		goto free_msg;
-
-	return 0;
+	return genlmsg_reply(msg, info);
 
 free_msg:
 	nlmsg_free(msg);
@@ -1313,10 +1309,7 @@ int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret)
 		goto free_msg;
 
-	ret =  genlmsg_reply(msg, info);
-	if (ret)
-		goto free_msg;
-	return 0;
+	return genlmsg_reply(msg, info);
 
 free_msg:
 	nlmsg_free(msg);
-- 
cgit v1.2.3


From 908c344d5cfac4160f49715da9efacdf5b6a28bd Mon Sep 17 00:00:00 2001
From: Nicolai Buchwitz <nb@tipi-net.de>
Date: Tue, 10 Mar 2026 06:49:35 +0100
Subject: net: bcmgenet: fix broken EEE by converting to phylib-managed state

The bcmgenet EEE implementation is broken in several ways.
phy_support_eee() is never called, so the PHY never advertises EEE
and phylib never sets phydev->enable_tx_lpi.  bcmgenet_mac_config()
checks priv->eee.eee_enabled to decide whether to enable the MAC
LPI logic, but that field is never initialised to true, so the MAC
never enters Low Power Idle even when EEE is negotiated - wasting
the power savings EEE is designed to provide.  The only way to get
EEE working at all is a manual 'ethtool --set-eee eth0 eee on' after
every link-up, and even then bcmgenet_get_eee() immediately clobbers
the reported state because phy_ethtool_get_eee() overwrites
eee_enabled and tx_lpi_enabled with the uninitialised PHY eee_cfg
values.  Finally, bcmgenet_mac_config() is only called on link-up,
so EEE is never disabled in hardware on link-down.

Fix all of this by removing the MAC-side EEE state tracking
(priv->eee) and aligning with the pattern used by other non-phylink
MAC drivers such as FEC.

Call phy_support_eee() in bcmgenet_mii_probe() so the PHY advertises
EEE link modes and phylib tracks negotiation state.  Move the EEE
hardware control to bcmgenet_mii_setup(), which is called on every
link event, and drive it directly from phydev->enable_tx_lpi - the
flag phylib sets when EEE is negotiated and the user has not disabled
it.  This enables EEE automatically once the link partner agrees and
disables it cleanly on link-down.

Make bcmgenet_get_eee() and bcmgenet_set_eee() pure passthroughs to
phy_ethtool_get_eee() and phy_ethtool_set_eee(), with the MAC
hardware register read/written for tx_lpi_timer.  Drop struct
ethtool_keee eee from struct bcmgenet_priv.

Fixes: fe0d4fd9285e ("net: phy: Keep track of EEE configuration")
Link: https://lore.kernel.org/netdev/d352039f-4cbb-41e6-9aeb-0b4f3941b54c@lunn.ch/
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Nicolai Buchwitz <nb@tipi-net.de>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260310054935.1238594-1-nb@tipi-net.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 31 ++++++++++----------------
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |  5 +----
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 10 ++++-----
 3 files changed, 18 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index a71cd729fde6..482a31e7b72b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1342,8 +1342,7 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev,
 	}
 }
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled)
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL;
@@ -1363,7 +1362,7 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 
 	/* Enable EEE and switch to a 27Mhz clock automatically */
 	reg = bcmgenet_readl(priv->base + off);
-	if (tx_lpi_enabled)
+	if (enable)
 		reg |= TBUF_EEE_EN | TBUF_PM_EN;
 	else
 		reg &= ~(TBUF_EEE_EN | TBUF_PM_EN);
@@ -1382,14 +1381,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 		priv->clk_eee_enabled = false;
 	}
 
-	priv->eee.eee_enabled = enable;
-	priv->eee.tx_lpi_enabled = tx_lpi_enabled;
 }
 
 static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
+	int ret;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1397,17 +1394,21 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	e->tx_lpi_enabled = p->tx_lpi_enabled;
+	ret = phy_ethtool_get_eee(dev->phydev, e);
+	if (ret)
+		return ret;
+
+	/* tx_lpi_timer is maintained by the MAC hardware register; the
+	 * PHY-level eee_cfg timer is not set for GENET.
+	 */
 	e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER);
 
-	return phy_ethtool_get_eee(dev->phydev, e);
+	return 0;
 }
 
 static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct ethtool_keee *p = &priv->eee;
-	bool active;
 
 	if (GENET_IS_V1(priv))
 		return -EOPNOTSUPP;
@@ -1415,15 +1416,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!dev->phydev)
 		return -ENODEV;
 
-	p->eee_enabled = e->eee_enabled;
-
-	if (!p->eee_enabled) {
-		bcmgenet_eee_enable_set(dev, false, false);
-	} else {
-		active = phy_init_eee(dev->phydev, false) >= 0;
-		bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
-		bcmgenet_eee_enable_set(dev, active, e->tx_lpi_enabled);
-	}
+	bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER);
 
 	return phy_ethtool_set_eee(dev->phydev, e);
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 5ec3979779ec..9e4110c7fdf6 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -665,8 +665,6 @@ struct bcmgenet_priv {
 	u8 sopass[SOPASS_MAX];
 
 	struct bcmgenet_mib_counters mib;
-
-	struct ethtool_keee eee;
 };
 
 static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
@@ -749,7 +747,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			      enum bcmgenet_power_mode mode);
 
-void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
-			     bool tx_lpi_enabled);
+void bcmgenet_eee_enable_set(struct net_device *dev, bool enable);
 
 #endif /* __BCMGENET_H__ */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 38f854b94a79..a4e0d5a68268 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -29,7 +29,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct phy_device *phydev = dev->phydev;
 	u32 reg, cmd_bits = 0;
-	bool active;
 
 	/* speed */
 	if (phydev->speed == SPEED_1000)
@@ -90,10 +89,6 @@ static void bcmgenet_mac_config(struct net_device *dev)
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
-	active = phy_init_eee(phydev, 0) >= 0;
-	bcmgenet_eee_enable_set(dev,
-				priv->eee.eee_enabled && active,
-				priv->eee.tx_lpi_enabled);
 }
 
 /* setup netdev link state when PHY link status change and
@@ -113,6 +108,8 @@ void bcmgenet_mii_setup(struct net_device *dev)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
+	bcmgenet_eee_enable_set(dev, phydev->enable_tx_lpi);
+
 	phy_print_status(phydev);
 }
 
@@ -412,6 +409,9 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	/* Indicate that the MAC is responsible for PHY PM */
 	dev->phydev->mac_managed_pm = true;
 
+	if (!GENET_IS_V1(priv))
+		phy_support_eee(dev->phydev);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 5f47be1b44bf2754c45e8c58ca036b474c9ecbc7 Mon Sep 17 00:00:00 2001
From: Daniel Gomez <da.gomez@samsung.com>
Date: Tue, 10 Mar 2026 12:36:23 +0100
Subject: scripts: kconfig: merge_config.sh: pass output file as awk variable

The refactoring commit 5fa9b82cbcfc5 ("scripts: kconfig:
merge_config.sh: refactor from shell/sed/grep to awk") passes
$TMP_FILE.new as ARGV[3] to awk, using it as both an output destination
and an input file argument. When the base file is empty, nothing is
written to ARGV[3] during processing, so awk fails trying to open it
for reading:

    awk: cmd. line:52: fatal: cannot open file
    `./.tmp.config.grcQin34jb.new' for reading: No such file or directory
    mv: cannot stat './.tmp.config.grcQin34jb.new': No such file or directory

Pass the output path via -v outfile instead and drop the FILENAME ==
ARGV[3] { nextfile }.

Fixes: 5fa9b82cbcfc5 ("scripts: kconfig: merge_config.sh: refactor from shell/sed/grep to awk")
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://patch.msgid.link/20260310-fixes-merge-config-v1-1-beaeeaded6bd@samsung.com
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/kconfig/merge_config.sh | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index 073c6bec5245..45e6400c68b6 100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -151,6 +151,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 	if ! "$AWK" -v prefix="$CONFIG_PREFIX" \
 		-v warnoverride="$WARNOVERRIDE" \
 		-v strict="$STRICT" \
+		-v outfile="$TMP_FILE.new" \
 		-v builtin="$BUILTIN" \
 		-v warnredun="$WARNREDUN" '
 	BEGIN {
@@ -212,7 +213,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 
 		# Not a config or not in merge file - keep it
 		if (cfg == "" || !(cfg in merge_cfg)) {
-			print $0 >> ARGV[3]
+			print $0 >> outfile
 			next
 		}
 
@@ -222,7 +223,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 		# BUILTIN: do not demote y to m
 		if (builtin == "true" && new_val ~ /=m$/ && prev_val ~ /=y$/) {
 			warn_builtin(cfg, prev_val, new_val)
-			print $0 >> ARGV[3]
+			print $0 >> outfile
 			skip_merge[merge_cfg_line[cfg]] = 1
 			next
 		}
@@ -235,7 +236,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 
 		# "=n" is the same as "is not set"
 		if (prev_val ~ /=n$/ && new_val ~ / is not set$/) {
-			print $0 >> ARGV[3]
+			print $0 >> outfile
 			next
 		}
 
@@ -246,25 +247,20 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 		}
 	}
 
-	# output file, skip all lines
-	FILENAME == ARGV[3] {
-		nextfile
-	}
-
 	END {
 		# Newline in case base file lacks trailing newline
-		print "" >> ARGV[3]
+		print "" >> outfile
 		# Append merge file, skipping lines marked for builtin preservation
 		for (i = 1; i <= merge_total; i++) {
 			if (!(i in skip_merge)) {
-				print merge_lines[i] >> ARGV[3]
+				print merge_lines[i] >> outfile
 			}
 		}
 		if (strict_violated) {
 			exit 1
 		}
 	}' \
-	"$ORIG_MERGE_FILE" "$TMP_FILE" "$TMP_FILE.new"; then
+	"$ORIG_MERGE_FILE" "$TMP_FILE"; then
 		# awk exited non-zero, strict mode was violated
 		STRICT_MODE_VIOLATED=true
 	fi
-- 
cgit v1.2.3


From 775af5cbb22c1de2ad0f486959739c35cfc55ac8 Mon Sep 17 00:00:00 2001
From: Daniel Gomez <da.gomez@samsung.com>
Date: Tue, 10 Mar 2026 12:36:24 +0100
Subject: scripts: kconfig: merge_config.sh: fix indentation

Replace spaces with tabs for consistency with the rest of the script.

Fixes: 5fa9b82cbcfc5 ("scripts: kconfig: merge_config.sh: refactor from shell/sed/grep to awk")
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://patch.msgid.link/20260310-fixes-merge-config-v1-2-beaeeaded6bd@samsung.com
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/kconfig/merge_config.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
index 45e6400c68b6..f08e0863b712 100755
--- a/scripts/kconfig/merge_config.sh
+++ b/scripts/kconfig/merge_config.sh
@@ -196,7 +196,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 
 	# First pass: read merge file, store all lines and index
 	FILENAME == ARGV[1] {
-	        mergefile = FILENAME
+		mergefile = FILENAME
 		merge_lines[FNR] = $0
 		merge_total = FNR
 		cfg = get_cfg($0)
@@ -217,7 +217,7 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
 			next
 		}
 
-	        prev_val = $0
+		prev_val = $0
 		new_val = merge_cfg[cfg]
 
 		# BUILTIN: do not demote y to m
-- 
cgit v1.2.3


From 5182e5ec4355dd690307f5d5c28cbfc5b2c06a97 Mon Sep 17 00:00:00 2001
From: Lianqin Hu <hulianqin@vivo.com>
Date: Wed, 11 Mar 2026 07:22:38 +0000
Subject: ALSA: usb-audio: Add iface reset and delay quirk for SPACETOUCH USB
 Audio

Setting up the interface when suspended/resumeing fail on this card.
Adding a reset and delay quirk will eliminate this problem.

usb 1-1: New USB device found, idVendor=0666, idProduct=0880
usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
usb 1-1: Product: USB Audio
usb 1-1: Manufacturer: SPACETOUCH
usb 1-1: SerialNumber: 000000000

Signed-off-by: Lianqin Hu <hulianqin@vivo.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/TYUPR06MB6217ACC80B70BE25D87456B0D247A@TYUPR06MB6217.apcprd06.prod.outlook.com
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index d54a1a44a69b..049a94079f9e 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2243,6 +2243,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IFACE_DELAY | QUIRK_FLAG_FORCE_IFACE_RESET),
 	DEVICE_FLG(0x0661, 0x0883, /* iBasso DC04 Ultra */
 		   QUIRK_FLAG_DSD_RAW),
+	DEVICE_FLG(0x0666, 0x0880, /* SPACETOUCH USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x06f8, 0xb000, /* Hercules DJ Console (Windows Edition) */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x06f8, 0xd002, /* Hercules DJ Console (Macintosh Edition) */
-- 
cgit v1.2.3


From 6df6ea4b3d1567dbe6442f308735c23b63007c7f Mon Sep 17 00:00:00 2001
From: Barnabás Pőcze <pobrn@protonmail.com>
Date: Tue, 10 Mar 2026 20:44:03 +0000
Subject: gpiolib: clear requested flag if line is invalid
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If `gpiochip_line_is_valid()` fails, then `-EINVAL` is returned, but
`desc->flags` will have `GPIOD_FLAG_REQUESTED` set, which will result
in subsequent calls misleadingly returning `-EBUSY`.

Fix that by clearing the flag in case of failure.

Fixes: a501624864f3 ("gpio: Respect valid_mask when requesting GPIOs")
Signed-off-by: Barnabás Pőcze <pobrn@protonmail.com>
Reviewed-by: Matti Vaittinen <mazziesaccount@gmail.com>
Link: https://patch.msgid.link/20260310204359.1202451-1-pobrn@protonmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ada572aaebd6..9550500e1690 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2465,8 +2465,10 @@ int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 		return -EBUSY;
 
 	offset = gpiod_hwgpio(desc);
-	if (!gpiochip_line_is_valid(guard.gc, offset))
-		return -EINVAL;
+	if (!gpiochip_line_is_valid(guard.gc, offset)) {
+		ret = -EINVAL;
+		goto out_clear_bit;
+	}
 
 	/* NOTE:  gpio_request() can be called in early boot,
 	 * before IRQs are enabled, for non-sleeping (SOC) GPIOs.
-- 
cgit v1.2.3


From 770444611f047dbfd4517ec0bc1b179d40c2f346 Mon Sep 17 00:00:00 2001
From: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Date: Thu, 26 Feb 2026 16:07:31 +0100
Subject: libceph: Use u32 for non-negative values in ceph_monmap_decode()

This patch fixes unnecessary implicit conversions that change signedness
of blob_len and num_mon in ceph_monmap_decode().
Currently blob_len and num_mon are (signed) int variables. They are used
to hold values that are always non-negative and get assigned in
ceph_decode_32_safe(), which is meant to assign u32 values. Both
variables are subsequently used as unsigned values, and the value of
num_mon is further assigned to monmap->num_mon, which is of type u32.
Therefore, both variables should be of type u32. This is especially
relevant for num_mon. If the value read from the incoming message is
very large, it is interpreted as a negative value, and the check for
num_mon > CEPH_MAX_MON does not catch it. This leads to the attempt to
allocate a very large chunk of memory for monmap, which will most likely
fail. In this case, an unnecessary attempt to allocate memory is
performed, and -ENOMEM is returned instead of -EINVAL.

Cc: stable@vger.kernel.org
Signed-off-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/mon_client.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 5136b3766c44..d5080530ce0c 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -72,8 +72,8 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	struct ceph_monmap *monmap = NULL;
 	struct ceph_fsid fsid;
 	u32 struct_len;
-	int blob_len;
-	int num_mon;
+	u32 blob_len;
+	u32 num_mon;
 	u8 struct_v;
 	u32 epoch;
 	int ret;
@@ -112,7 +112,7 @@ static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 	}
 	ceph_decode_32_safe(p, end, num_mon, e_inval);
 
-	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
+	dout("%s fsid %pU epoch %u num_mon %u\n", __func__, &fsid, epoch,
 	     num_mon);
 	if (num_mon > CEPH_MAX_MON)
 		goto e_inval;
-- 
cgit v1.2.3


From b282c43ed156ae15ea76748fc15cd5c39dc9ab72 Mon Sep 17 00:00:00 2001
From: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Date: Tue, 10 Mar 2026 15:28:15 +0100
Subject: libceph: Fix potential out-of-bounds access in
 ceph_handle_auth_reply()

This patch fixes an out-of-bounds access in ceph_handle_auth_reply()
that can be triggered by a message of type CEPH_MSG_AUTH_REPLY. In
ceph_handle_auth_reply(), the value of the payload_len field of such a
message is stored in a variable of type int. A value greater than
INT_MAX leads to an integer overflow and is interpreted as a negative
value. This leads to decrementing the pointer address by this value and
subsequently accessing it because ceph_decode_need() only checks that
the memory access does not exceed the end address of the allocation.

This patch fixes the issue by changing the data type of payload_len to
u32. Additionally, the data type of result_msg_len is changed to u32,
as it is also a variable holding a non-negative length.

Also, an additional layer of sanity checks is introduced, ensuring that
directly after reading it from the message, payload_len and
result_msg_len are not greater than the overall segment length.

BUG: KASAN: slab-out-of-bounds in ceph_handle_auth_reply+0x642/0x7a0 [libceph]
Read of size 4 at addr ffff88811404df14 by task kworker/20:1/262

CPU: 20 UID: 0 PID: 262 Comm: kworker/20:1 Not tainted 6.19.2 #5 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Workqueue: ceph-msgr ceph_con_workfn [libceph]
Call Trace:
 <TASK>
 dump_stack_lvl+0x76/0xa0
 print_report+0xd1/0x620
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? kasan_complete_mode_report_info+0x72/0x210
 kasan_report+0xe7/0x130
 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 ? ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 __asan_report_load_n_noabort+0xf/0x20
 ceph_handle_auth_reply+0x642/0x7a0 [libceph]
 mon_dispatch+0x973/0x23d0 [libceph]
 ? apparmor_socket_recvmsg+0x6b/0xa0
 ? __pfx_mon_dispatch+0x10/0x10 [libceph]
 ? __kasan_check_write+0x14/0x30i
 ? mutex_unlock+0x7f/0xd0
 ? __pfx_mutex_unlock+0x10/0x10
 ? __pfx_do_recvmsg+0x10/0x10 [libceph]
 ceph_con_process_message+0x1f1/0x650 [libceph]
 process_message+0x1e/0x450 [libceph]
 ceph_con_v2_try_read+0x2e48/0x6c80 [libceph]
 ? __pfx_ceph_con_v2_try_read+0x10/0x10 [libceph]
 ? save_fpregs_to_fpstate+0xb0/0x230
 ? raw_spin_rq_unlock+0x17/0xa0
 ? finish_task_switch.isra.0+0x13b/0x760
 ? __switch_to+0x385/0xda0
 ? __kasan_check_write+0x14/0x30
 ? mutex_lock+0x8d/0xe0
 ? __pfx_mutex_lock+0x10/0x10
 ceph_con_workfn+0x248/0x10c0 [libceph]
 process_one_work+0x629/0xf80
 ? __kasan_check_write+0x14/0x30
 worker_thread+0x87f/0x1570
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? __pfx_try_to_wake_up+0x10/0x10
 ? kasan_print_address_stack_frame+0x1f7/0x280
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x396/0x830
 ? __pfx__raw_spin_lock_irq+0x10/0x10
 ? __pfx_kthread+0x10/0x10
 ? __kasan_check_write+0x14/0x30
 ? recalc_sigpending+0x180/0x210
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x3f7/0x610
 ? __pfx_ret_from_fork+0x10/0x10
 ? __switch_to+0x385/0xda0
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>

[ idryomov: replace if statements with ceph_decode_need() for
  payload_len and result_msg_len ]

Cc: stable@vger.kernel.org
Signed-off-by: Raphael Zimmer <raphael.zimmer@tu-ilmenau.de>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 net/ceph/auth.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index 343c841784ce..901b93530b21 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -205,9 +205,9 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	s32 result;
 	u64 global_id;
 	void *payload, *payload_end;
-	int payload_len;
+	u32 payload_len;
 	char *result_msg;
-	int result_msg_len;
+	u32 result_msg_len;
 	int ret = -EINVAL;
 
 	mutex_lock(&ac->mutex);
@@ -217,10 +217,12 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 	result = ceph_decode_32(&p);
 	global_id = ceph_decode_64(&p);
 	payload_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, payload_len, bad);
 	payload = p;
 	p += payload_len;
 	ceph_decode_need(&p, end, sizeof(u32), bad);
 	result_msg_len = ceph_decode_32(&p);
+	ceph_decode_need(&p, end, result_msg_len, bad);
 	result_msg = p;
 	p += result_msg_len;
 	if (p != end)
-- 
cgit v1.2.3


From 755a648e78f12574482d4698d877375793867fa1 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 6 Mar 2026 21:24:03 -0500
Subject: time/jiffies: Mark jiffies_64_to_clock_t() notrace

The trace_clock_jiffies() function that handles the "uptime" clock for
tracing calls jiffies_64_to_clock_t(). This causes the function tracer to
constantly recurse when the tracing clock is set to "uptime". Mark it
notrace to prevent unnecessary recursion when using the "uptime" clock.

Fixes: 58d4e21e50ff3 ("tracing: Fix wraparound problems in "uptime" trace clock")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260306212403.72270bb2@robin
---
 kernel/time/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/time.c b/kernel/time/time.c
index 36fd2313ae7e..0d832317d576 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -697,7 +697,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies);
  *
  * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC)
  */
-u64 jiffies_64_to_clock_t(u64 x)
+notrace u64 jiffies_64_to_clock_t(u64 x)
 {
 #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
 # if HZ < USER_HZ
-- 
cgit v1.2.3


From b2e48c429ec54715d16fefa719dd2fbded2e65be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:28:53 +0100
Subject: sched/mmcid: Prevent CID stalls due to concurrent forks

A newly forked task is accounted as MMCID user before the task is visible
in the process' thread list and the global task list. This creates the
following problem:

 CPU1			CPU2
 fork()
   sched_mm_cid_fork(tnew1)
     tnew1->mm.mm_cid_users++;
     tnew1->mm_cid.cid = getcid()
-> preemption
			fork()
			  sched_mm_cid_fork(tnew2)
			    tnew2->mm.mm_cid_users++;
                            // Reaches the per CPU threshold
			    mm_cid_fixup_tasks_to_cpus()
			    for_each_other(current, p)
			         ....

As tnew1 is not visible yet, this fails to fix up the already allocated CID
of tnew1. As a consequence a subsequent schedule in might fail to acquire a
(transitional) CID and the machine stalls.

Move the invocation of sched_mm_cid_fork() after the new task becomes
visible in the thread and the task list to prevent this.

This also makes it symmetrical vs. exit() where the task is removed as CID
user before the task is removed from the thread and task lists.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202525.969061974@kernel.org
---
 include/linux/sched.h |  2 --
 kernel/fork.c         |  2 --
 kernel/sched/core.c   | 22 +++++++++++++++-------
 3 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a7b4a980eb2f..5a5d3dbc9cdf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
 #ifdef CONFIG_SCHED_MM_CID
 void sched_mm_cid_before_execve(struct task_struct *t);
 void sched_mm_cid_after_execve(struct task_struct *t);
-void sched_mm_cid_fork(struct task_struct *t);
 void sched_mm_cid_exit(struct task_struct *t);
 static __always_inline int task_mm_cid(struct task_struct *t)
 {
@@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t)
 #else
 static inline void sched_mm_cid_before_execve(struct task_struct *t) { }
 static inline void sched_mm_cid_after_execve(struct task_struct *t) { }
-static inline void sched_mm_cid_fork(struct task_struct *t) { }
 static inline void sched_mm_cid_exit(struct task_struct *t) { }
 static __always_inline int task_mm_cid(struct task_struct *t)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 65113a304518..7febf4c2889e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1586,7 +1586,6 @@ static int copy_mm(u64 clone_flags, struct task_struct *tsk)
 
 	tsk->mm = mm;
 	tsk->active_mm = mm;
-	sched_mm_cid_fork(tsk);
 	return 0;
 }
 
@@ -2498,7 +2497,6 @@ bad_fork_cleanup_namespaces:
 	exit_nsproxy_namespaces(p);
 bad_fork_cleanup_mm:
 	if (p->mm) {
-		sched_mm_cid_exit(p);
 		mm_clear_owner(p->mm, p);
 		mmput(p->mm);
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7f77c165a6e..d25427855b5d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4729,8 +4729,11 @@ void sched_cancel_fork(struct task_struct *p)
 	scx_cancel_fork(p);
 }
 
+static void sched_mm_cid_fork(struct task_struct *t);
+
 void sched_post_fork(struct task_struct *p)
 {
+	sched_mm_cid_fork(p);
 	uclamp_post_fork(p);
 	scx_post_fork(p);
 }
@@ -10646,12 +10649,13 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
 	 * possible switch back to per task mode happens either in the
 	 * deferred handler function or in the next fork()/exit().
 	 *
-	 * The caller has already transferred. The newly incoming task is
-	 * already accounted for, but not yet visible.
+	 * The caller has already transferred so remove it from the users
+	 * count. The incoming task is already visible and has mm_cid.active,
+	 * but has task::mm_cid::cid == UNSET. Still it needs to be accounted
+	 * for. Concurrent fork()s might add more threads, but all of them have
+	 * task::mm_cid::active = 0, so they don't affect the accounting here.
 	 */
-	users = mm->mm_cid.users - 2;
-	if (!users)
-		return;
+	users = mm->mm_cid.users - 1;
 
 	guard(rcu)();
 	for_other_threads(current, t) {
@@ -10688,12 +10692,15 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 	return mm_update_max_cids(mm);
 }
 
-void sched_mm_cid_fork(struct task_struct *t)
+static void sched_mm_cid_fork(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
 	bool percpu;
 
-	WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET);
+	if (!mm)
+		return;
+
+	WARN_ON_ONCE(t->mm_cid.cid != MM_CID_UNSET);
 
 	guard(mutex)(&mm->mm_cid.mutex);
 	scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) {
@@ -10885,6 +10892,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 }
 #else /* CONFIG_SCHED_MM_CID */
 static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { }
+static inline void sched_mm_cid_fork(struct task_struct *t) { }
 #endif /* !CONFIG_SCHED_MM_CID */
 
 static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);
-- 
cgit v1.2.3


From 28b5a1395036d6c7a6c8034d85ad3d7d365f192c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:28:58 +0100
Subject: sched/mmcid: Handle vfork()/CLONE_VM correctly

Matthieu and Jiri reported stalls where a task endlessly loops in
mm_get_cid() when scheduling in.

It turned out that the logic which handles vfork()'ed tasks is broken. It
is invoked when the number of tasks associated to a process is smaller than
the number of MMCID users. It then walks the task list to find the
vfork()'ed task, but accounts all the already processed tasks as well.

If that double processing brings the number of to be handled tasks to 0,
the walk stops and the vfork()'ed task's CID is not fixed up. As a
consequence a subsequent schedule in fails to acquire a (transitional) CID
and the machine stalls.

Cure this by removing the accounting condition and make the fixup always
walk the full task list if it could not find the exact number of users in
the process' thread list.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Closes: https://lore.kernel.org/b24ffcb3-09d5-4e48-9070-0b69bc654281@kernel.org
Reported-by: Matthieu Baerts <matttbe@kernel.org>
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.048657665@kernel.org
---
 kernel/sched/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d25427855b5d..ee59cd19b9a8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10670,10 +10670,7 @@ static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
 	for_each_process_thread(p, t) {
 		if (t == current || t->mm != mm)
 			continue;
-		if (mm_cid_fixup_task_to_cpu(t, mm)) {
-			if (--users == 0)
-				return;
-		}
+		mm_cid_fixup_task_to_cpu(t, mm);
 	}
 }
 
-- 
cgit v1.2.3


From 7574ac6e49789ddee1b1be9b2afb42b4a1b4b1f4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:29:04 +0100
Subject: sched/mmcid: Remove pointless preempt guard

This is a leftover from the early versions of this function where it could
be invoked without mm::mm_cid::lock held.

Remove it and add lockdep asserts instead.

Fixes: 653fda7ae73d ("sched/mmcid: Switch over to the new mechanism")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.116363613@kernel.org
---
 kernel/sched/core.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ee59cd19b9a8..f56156f91d08 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10684,6 +10684,8 @@ static void mm_cid_fixup_tasks_to_cpus(void)
 
 static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 {
+	lockdep_assert_held(&mm->mm_cid.lock);
+
 	t->mm_cid.active = 1;
 	mm->mm_cid.users++;
 	return mm_update_max_cids(mm);
@@ -10736,12 +10738,12 @@ static void sched_mm_cid_fork(struct task_struct *t)
 
 static bool sched_mm_cid_remove_user(struct task_struct *t)
 {
+	lockdep_assert_held(&t->mm->mm_cid.lock);
+
 	t->mm_cid.active = 0;
-	scoped_guard(preempt) {
-		/* Clear the transition bit */
-		t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
-		mm_unset_cid_on_task(t);
-	}
+	/* Clear the transition bit */
+	t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
+	mm_unset_cid_on_task(t);
 	t->mm->mm_cid.users--;
 	return mm_update_max_cids(t->mm);
 }
-- 
cgit v1.2.3


From 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 10 Mar 2026 21:29:09 +0100
Subject: sched/mmcid: Avoid full tasklist walks

Chasing vfork()'ed tasks on a CID ownership mode switch requires a full
task list walk, which is obviously expensive on large systems.

Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid
and walk this list instead. This removes the proven to be flaky counting
logic and avoids a full task list walk in the case of vfork()'ed tasks.

Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions")
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260310202526.183824481@kernel.org
---
 include/linux/rseq_types.h |  6 +++++-
 kernel/fork.c              |  1 +
 kernel/sched/core.c        | 54 +++++++++++-----------------------------------
 3 files changed, 18 insertions(+), 43 deletions(-)

diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index da5fa6f40294..0b42045988db 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -133,10 +133,12 @@ struct rseq_data { };
  * @active:	MM CID is active for the task
  * @cid:	The CID associated to the task either permanently or
  *		borrowed from the CPU
+ * @node:	Queued in the per MM MMCID list
  */
 struct sched_mm_cid {
 	unsigned int		active;
 	unsigned int		cid;
+	struct hlist_node	node;
 };
 
 /**
@@ -157,6 +159,7 @@ struct mm_cid_pcpu {
  * @work:		Regular work to handle the affinity mode change case
  * @lock:		Spinlock to protect against affinity setting which can't take @mutex
  * @mutex:		Mutex to serialize forks and exits related to this mm
+ * @user_list:		List of the MM CID users of a MM
  * @nr_cpus_allowed:	The number of CPUs in the per MM allowed CPUs map. The map
  *			is growth only.
  * @users:		The number of tasks sharing this MM. Separate from mm::mm_users
@@ -177,13 +180,14 @@ struct mm_mm_cid {
 
 	raw_spinlock_t		lock;
 	struct mutex		mutex;
+	struct hlist_head	user_list;
 
 	/* Low frequency modified */
 	unsigned int		nr_cpus_allowed;
 	unsigned int		users;
 	unsigned int		pcpu_thrs;
 	unsigned int		update_deferred;
-}____cacheline_aligned_in_smp;
+} ____cacheline_aligned;
 #else /* CONFIG_SCHED_MM_CID */
 struct mm_mm_cid { };
 struct sched_mm_cid { };
diff --git a/kernel/fork.c b/kernel/fork.c
index 7febf4c2889e..bc2bf58b93b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1000,6 +1000,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_SCHED_MM_CID
 	tsk->mm_cid.cid = MM_CID_UNSET;
 	tsk->mm_cid.active = 0;
+	INIT_HLIST_NODE(&tsk->mm_cid.node);
 #endif
 	return tsk;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f56156f91d08..496dff740dca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10620,13 +10620,10 @@ static inline void mm_cid_transit_to_cpu(struct task_struct *t, struct mm_cid_pc
 	}
 }
 
-static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
+static void mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm)
 {
 	/* Remote access to mm::mm_cid::pcpu requires rq_lock */
 	guard(task_rq_lock)(t);
-	/* If the task is not active it is not in the users count */
-	if (!t->mm_cid.active)
-		return false;
 	if (cid_on_task(t->mm_cid.cid)) {
 		/* If running on the CPU, put the CID in transit mode, otherwise drop it */
 		if (task_rq(t)->curr == t)
@@ -10634,51 +10631,21 @@ static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm
 		else
 			mm_unset_cid_on_task(t);
 	}
-	return true;
 }
 
-static void mm_cid_do_fixup_tasks_to_cpus(struct mm_struct *mm)
+static void mm_cid_fixup_tasks_to_cpus(void)
 {
-	struct task_struct *p, *t;
-	unsigned int users;
-
-	/*
-	 * This can obviously race with a concurrent affinity change, which
-	 * increases the number of allowed CPUs for this mm, but that does
-	 * not affect the mode and only changes the CID constraints. A
-	 * possible switch back to per task mode happens either in the
-	 * deferred handler function or in the next fork()/exit().
-	 *
-	 * The caller has already transferred so remove it from the users
-	 * count. The incoming task is already visible and has mm_cid.active,
-	 * but has task::mm_cid::cid == UNSET. Still it needs to be accounted
-	 * for. Concurrent fork()s might add more threads, but all of them have
-	 * task::mm_cid::active = 0, so they don't affect the accounting here.
-	 */
-	users = mm->mm_cid.users - 1;
-
-	guard(rcu)();
-	for_other_threads(current, t) {
-		if (mm_cid_fixup_task_to_cpu(t, mm))
-			users--;
-	}
+	struct mm_struct *mm = current->mm;
+	struct task_struct *t;
 
-	if (!users)
-		return;
+	lockdep_assert_held(&mm->mm_cid.mutex);
 
-	/* Happens only for VM_CLONE processes. */
-	for_each_process_thread(p, t) {
-		if (t == current || t->mm != mm)
-			continue;
-		mm_cid_fixup_task_to_cpu(t, mm);
+	hlist_for_each_entry(t, &mm->mm_cid.user_list, mm_cid.node) {
+		/* Current has already transferred before invoking the fixup. */
+		if (t != current)
+			mm_cid_fixup_task_to_cpu(t, mm);
 	}
-}
-
-static void mm_cid_fixup_tasks_to_cpus(void)
-{
-	struct mm_struct *mm = current->mm;
 
-	mm_cid_do_fixup_tasks_to_cpus(mm);
 	mm_cid_complete_transit(mm, MM_CID_ONCPU);
 }
 
@@ -10687,6 +10654,7 @@ static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm)
 	lockdep_assert_held(&mm->mm_cid.lock);
 
 	t->mm_cid.active = 1;
+	hlist_add_head(&t->mm_cid.node, &mm->mm_cid.user_list);
 	mm->mm_cid.users++;
 	return mm_update_max_cids(mm);
 }
@@ -10744,6 +10712,7 @@ static bool sched_mm_cid_remove_user(struct task_struct *t)
 	/* Clear the transition bit */
 	t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid);
 	mm_unset_cid_on_task(t);
+	hlist_del_init(&t->mm_cid.node);
 	t->mm->mm_cid.users--;
 	return mm_update_max_cids(t->mm);
 }
@@ -10886,6 +10855,7 @@ void mm_init_cid(struct mm_struct *mm, struct task_struct *p)
 	mutex_init(&mm->mm_cid.mutex);
 	mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work);
 	INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn);
+	INIT_HLIST_HEAD(&mm->mm_cid.user_list);
 	cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask);
 	bitmap_zero(mm_cidmask(mm), num_possible_cpus());
 }
-- 
cgit v1.2.3


From 393815f57651101f1590632092986d1d5a3a41bd Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 11 Mar 2026 10:58:35 +0000
Subject: ACPI: OSL: fix __iomem type on return from
 acpi_os_map_generic_address()

The pointer returned from acpi_os_map_generic_address() is
tagged with __iomem, so make the rv it is returned to also
of void __iomem * type.

Fixes the following sparse warning:

drivers/acpi/osl.c:1686:20: warning: incorrect type in assignment (different address spaces)
drivers/acpi/osl.c:1686:20:    expected void *rv
drivers/acpi/osl.c:1686:20:    got void [noderef] __iomem *

Fixes: 6915564dc5a8 ("ACPI: OSL: Change the type of acpi_os_map_generic_address() return value")
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
[ rjw: Subject tweak, added Fixes tag ]
Link: https://patch.msgid.link/20260311105835.463030-1-ben.dooks@codethink.co.uk
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 5b777316b9ac..62b9c83d4f20 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -1681,7 +1681,7 @@ acpi_status __init acpi_os_initialize(void)
 		 * Use acpi_os_map_generic_address to pre-map the reset
 		 * register if it's in system memory.
 		 */
-		void *rv;
+		void __iomem *rv;
 
 		rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
 		pr_debug("%s: Reset register mapping %s\n", __func__,
-- 
cgit v1.2.3


From 743956bb9990214ff1dac66ef59e27221dc3c2d8 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@kernel.org>
Date: Mon, 2 Mar 2026 23:35:56 +0800
Subject: spi: dt-bindings: sun6i: Allow Dual SPI and Quad SPI for newer SoCs

Support for Dual SPI and Quad SPI was added to the Linux driver in
commit 0605d9fb411f ("spi: sun6i: add quirk for dual and quad SPI modes
support") and commit 25453d797d7a ("spi: sun6i: add dual and quad SPI
modes support for R329/D1/R528/T113s").

However the binding was never updated to allow these modes. Allow them
by adding 2 and 4 to the allowed bus widths for the newer variants.

While at it, also add 0 to the allowed bus widths. This signals that
RX or TX is not available, i.e. the MISO or MOSI pin is disconnected.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Chen-Yu Tsai <wens@kernel.org>
Link: https://patch.msgid.link/20260302153559.3199783-2-wens@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/spi/allwinner,sun6i-a31-spi.yaml      | 29 ++++++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
index a6067030c5ed..6af4ff233158 100644
--- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
@@ -6,9 +6,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Allwinner A31 SPI Controller
 
-allOf:
-  - $ref: spi-controller.yaml
-
 maintainers:
   - Chen-Yu Tsai <wens@csie.org>
   - Maxime Ripard <mripard@kernel.org>
@@ -82,11 +79,11 @@ patternProperties:
 
       spi-rx-bus-width:
         items:
-          - const: 1
+          enum: [0, 1, 2, 4]
 
       spi-tx-bus-width:
         items:
-          - const: 1
+          enum: [0, 1, 2, 4]
 
 required:
   - compatible
@@ -95,6 +92,28 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - $ref: spi-controller.yaml
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - allwinner,sun50i-r329-spi
+                - allwinner,sun55i-a523-spi
+    then:
+      patternProperties:
+        "^.*@[0-9a-f]+":
+          properties:
+            spi-rx-bus-width:
+              items:
+                enum: [0, 1]
+
+            spi-tx-bus-width:
+              items:
+                enum: [0, 1]
+
 unevaluatedProperties: false
 
 examples:
-- 
cgit v1.2.3


From 362c490980867930a098b99f421268fbd7ca05fd Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 10 Mar 2026 20:32:33 +0800
Subject: xfs: fix integer overflow in bmap intent sort comparator

xfs_bmap_update_diff_items() sorts bmap intents by inode number using
a subtraction of two xfs_ino_t (uint64_t) values, with the result
truncated to int. This is incorrect when two inode numbers differ by
more than INT_MAX (2^31 - 1), which is entirely possible on large XFS
filesystems.

Fix this by replacing the subtraction with cmp_int().

Cc: <stable@vger.kernel.org> # v4.9
Fixes: 9f3afb57d5f1 ("xfs: implement deferred bmbt map/unmap operations")
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_bmap_item.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e8775f254c89..b237a25d6045 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -245,7 +245,7 @@ xfs_bmap_update_diff_items(
 	struct xfs_bmap_intent		*ba = bi_entry(a);
 	struct xfs_bmap_intent		*bb = bi_entry(b);
 
-	return ba->bi_owner->i_ino - bb->bi_owner->i_ino;
+	return cmp_int(ba->bi_owner->i_ino, bb->bi_owner->i_ino);
 }
 
 /* Log bmap updates in the intent item. */
-- 
cgit v1.2.3


From 53f3a900e9a383d47af7253076e19f510c5708d0 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Tue, 10 Mar 2026 10:42:46 +0800
Subject: ASoC: amd: acp3x-rt5682-max9836: Add missing error check for clock
 acquisition

The acp3x_5682_init() function did not check the return value of
clk_get(), which could lead to dereferencing error pointers in
rt5682_clk_enable().

Fix this by:
1. Changing clk_get() to the device-managed devm_clk_get().
2. Adding proper IS_ERR() checks for both clock acquisitions.

Fixes: 6b8e4e7db3cd ("ASoC: amd: Add machine driver for Raven based platform")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Link: https://patch.msgid.link/20260310024246.2153827-1-nichen@iscas.ac.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp3x-rt5682-max9836.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c
index 4ca1978020a9..d1eb6f12a183 100644
--- a/sound/soc/amd/acp3x-rt5682-max9836.c
+++ b/sound/soc/amd/acp3x-rt5682-max9836.c
@@ -94,8 +94,13 @@ static int acp3x_5682_init(struct snd_soc_pcm_runtime *rtd)
 		return ret;
 	}
 
-	rt5682_dai_wclk = clk_get(component->dev, "rt5682-dai-wclk");
-	rt5682_dai_bclk = clk_get(component->dev, "rt5682-dai-bclk");
+	rt5682_dai_wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+	if (IS_ERR(rt5682_dai_wclk))
+		return PTR_ERR(rt5682_dai_wclk);
+
+	rt5682_dai_bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+	if (IS_ERR(rt5682_dai_bclk))
+		return PTR_ERR(rt5682_dai_bclk);
 
 	ret = snd_soc_card_jack_new_pins(card, "Headset Jack",
 					 SND_JACK_HEADSET |
-- 
cgit v1.2.3


From 487b23afaf4b258a70d3e4a8febf66f09850e75f Mon Sep 17 00:00:00 2001
From: Hans de Goede <johannes.goede@oss.qualcomm.com>
Date: Sat, 28 Feb 2026 15:52:57 +0100
Subject: HID: input: Drop Asus UX550* touchscreen ignore battery quirks

Drop the Asus UX550* touchscreen ignore battery quirks, there is a blanket
HID_BATTERY_QUIRK_IGNORE for all USB_VENDOR_ID_ELAN USB touchscreens now,
so these are just a duplicate of those.

Signed-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h   | 2 --
 drivers/hid/hid-input.c | 4 ----
 2 files changed, 6 deletions(-)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5e85921049e0..afcee13bad61 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -455,8 +455,6 @@
 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W	0x0401
 #define USB_DEVICE_ID_HP_X2		0x074d
 #define USB_DEVICE_ID_HP_X2_10_COVER	0x0755
-#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN	0x2544
-#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN	0x2706
 #define I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM	0x2F81
 
 #define USB_VENDOR_ID_ELECOM		0x056e
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 2633fcd8f910..67ca1e88ce13 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -386,10 +386,6 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD),
 	  HID_BATTERY_QUIRK_IGNORE },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
-	  HID_BATTERY_QUIRK_IGNORE },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN),
-	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L),
 	  HID_BATTERY_QUIRK_AVOID_QUERY },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_MW),
-- 
cgit v1.2.3


From 227312b4a65c373d5d8b4683b7fc36203fedc516 Mon Sep 17 00:00:00 2001
From: Hans de Goede <johannes.goede@oss.qualcomm.com>
Date: Sat, 28 Feb 2026 15:52:58 +0100
Subject: HID: input: Add HID_BATTERY_QUIRK_DYNAMIC for Elan touchscreens

Elan touchscreens have a HID-battery device for the stylus which is always
there even if there is no stylus.

This is causing upower to report an empty battery for the stylus and some
desktop-environments will show a notification about this, which is quite
annoying.

Because of this the HID-battery is being ignored on all Elan I2c and USB
touchscreens, but this causes there to be no battery reporting for
the stylus at all.

This adds a new HID_BATTERY_QUIRK_DYNAMIC and uses these for the Elan
touchscreens.

This new quirks causes the present value of the battery to start at 0,
which will make userspace ignore it and only sets present to 1 after
receiving a battery input report which only happens when the stylus
gets in range.

Reported-by: ggrundik@gmail.com
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221118
Signed-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-input.c | 14 +++++++++++---
 include/linux/hid.h     |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 67ca1e88ce13..8fc20df99b97 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -354,6 +354,7 @@ static enum power_supply_property hidinput_battery_props[] = {
 #define HID_BATTERY_QUIRK_FEATURE	(1 << 1) /* ask for feature report */
 #define HID_BATTERY_QUIRK_IGNORE	(1 << 2) /* completely ignore the battery */
 #define HID_BATTERY_QUIRK_AVOID_QUERY	(1 << 3) /* do not query the battery */
+#define HID_BATTERY_QUIRK_DYNAMIC	(1 << 4) /* report present only after life signs */
 
 static const struct hid_device_id hid_battery_quirks[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
@@ -398,8 +399,8 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	 * Elan HID touchscreens seem to all report a non present battery,
 	 * set HID_BATTERY_QUIRK_IGNORE for all Elan I2C and USB HID devices.
 	 */
-	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_DYNAMIC },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_DYNAMIC },
 	{}
 };
 
@@ -456,11 +457,14 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 	int ret = 0;
 
 	switch (prop) {
-	case POWER_SUPPLY_PROP_PRESENT:
 	case POWER_SUPPLY_PROP_ONLINE:
 		val->intval = 1;
 		break;
 
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = dev->battery_present;
+		break;
+
 	case POWER_SUPPLY_PROP_CAPACITY:
 		if (dev->battery_status != HID_BATTERY_REPORTED &&
 		    !dev->battery_avoid_query) {
@@ -573,6 +577,8 @@ static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 	if (quirks & HID_BATTERY_QUIRK_AVOID_QUERY)
 		dev->battery_avoid_query = true;
 
+	dev->battery_present = (quirks & HID_BATTERY_QUIRK_DYNAMIC) ? false : true;
+
 	dev->battery = power_supply_register(&dev->dev, psy_desc, &psy_cfg);
 	if (IS_ERR(dev->battery)) {
 		error = PTR_ERR(dev->battery);
@@ -628,6 +634,7 @@ static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
 		return;
 
 	if (hidinput_update_battery_charge_status(dev, usage, value)) {
+		dev->battery_present = true;
 		power_supply_changed(dev->battery);
 		return;
 	}
@@ -643,6 +650,7 @@ static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
 	if (dev->battery_status != HID_BATTERY_REPORTED ||
 	    capacity != dev->battery_capacity ||
 	    ktime_after(ktime_get_coarse(), dev->battery_ratelimit_time)) {
+		dev->battery_present = true;
 		dev->battery_capacity = capacity;
 		dev->battery_status = HID_BATTERY_REPORTED;
 		dev->battery_ratelimit_time =
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 2990b9f94cb5..31324609af4d 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -682,6 +682,7 @@ struct hid_device {
 	__s32 battery_charge_status;
 	enum hid_battery_status battery_status;
 	bool battery_avoid_query;
+	bool battery_present;
 	ktime_t battery_ratelimit_time;
 #endif
 
-- 
cgit v1.2.3


From e293015ba76eb96ce4ebed7e3b2cb1a7d319f3e9 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 18 Feb 2026 21:21:07 +0100
Subject: usb: core: don't power off roothub PHYs if phy_set_mode() fails

Remove the error path from the usb_phy_roothub_set_mode() function.
The code is clearly wrong, because phy_set_mode() calls can't be
balanced with phy_power_off() calls.

Additionally, the usb_phy_roothub_set_mode() function is called only
from usb_add_hcd() before it powers on the PHYs, so powering off those
makes no sense anyway.

Presumably, the code is copy-pasted from the phy_power_on() function
without adjusting the error handling.

Cc: stable@vger.kernel.org # v5.1+
Fixes: b97a31348379 ("usb: core: comply to PHY framework")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://patch.msgid.link/20260218-usb-phy-poweroff-fix-v1-1-66e6831e860e@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/phy.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c
index faa20054ad5a..4bba1c275740 100644
--- a/drivers/usb/core/phy.c
+++ b/drivers/usb/core/phy.c
@@ -200,16 +200,10 @@ int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub,
 	list_for_each_entry(roothub_entry, head, list) {
 		err = phy_set_mode(roothub_entry->phy, mode);
 		if (err)
-			goto err_out;
+			return err;
 	}
 
 	return 0;
-
-err_out:
-	list_for_each_entry_continue_reverse(roothub_entry, head, list)
-		phy_power_off(roothub_entry->phy);
-
-	return err;
 }
 EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode);
 
-- 
cgit v1.2.3


From 416909962e7cdf29fd01ac523c953f37708df93d Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:07:47 -0500
Subject: USB: usbcore: Introduce usb_bulk_msg_killable()

The synchronous message API in usbcore (usb_control_msg(),
usb_bulk_msg(), and so on) uses uninterruptible waits.  However,
drivers may call these routines in the context of a user thread, which
means it ought to be possible to at least kill them.

For this reason, introduce a new usb_bulk_msg_killable() function
which behaves the same as usb_bulk_msg() except for using
wait_for_completion_killable_timeout() instead of
wait_for_completion_timeout().  The same can be done later for
usb_control_msg() later on, if it turns out to be needed.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Suggested-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/248628b4-cc83-4e81-a620-3ce4e0376d41@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 79 ++++++++++++++++++++++++++++++++++++++++------
 include/linux/usb.h        |  5 +--
 2 files changed, 72 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index ea970ddf8879..d97ec7e8c280 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -42,16 +42,17 @@ static void usb_api_blocking_completion(struct urb *urb)
 
 
 /*
- * Starts urb and waits for completion or timeout. Note that this call
- * is NOT interruptible. Many device driver i/o requests should be
- * interruptible and therefore these drivers should implement their
- * own interruptible routines.
+ * Starts urb and waits for completion or timeout.
+ * Whether or not the wait is killable depends on the flag passed in.
+ * For example, compare usb_bulk_msg() and usb_bulk_msg_killable().
  */
-static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length)
+static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
+		bool killable)
 {
 	struct api_context ctx;
 	unsigned long expire;
 	int retval;
+	long rc;
 
 	init_completion(&ctx.done);
 	urb->context = &ctx;
@@ -61,12 +62,21 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length)
 		goto out;
 
 	expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
-	if (!wait_for_completion_timeout(&ctx.done, expire)) {
+	if (killable)
+		rc = wait_for_completion_killable_timeout(&ctx.done, expire);
+	else
+		rc = wait_for_completion_timeout(&ctx.done, expire);
+	if (rc <= 0) {
 		usb_kill_urb(urb);
-		retval = (ctx.status == -ENOENT ? -ETIMEDOUT : ctx.status);
+		if (ctx.status != -ENOENT)
+			retval = ctx.status;
+		else if (rc == 0)
+			retval = -ETIMEDOUT;
+		else
+			retval = rc;
 
 		dev_dbg(&urb->dev->dev,
-			"%s timed out on ep%d%s len=%u/%u\n",
+			"%s timed out or killed on ep%d%s len=%u/%u\n",
 			current->comm,
 			usb_endpoint_num(&urb->ep->desc),
 			usb_urb_dir_in(urb) ? "in" : "out",
@@ -100,7 +110,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev,
 	usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char *)cmd, data,
 			     len, usb_api_blocking_completion, NULL);
 
-	retv = usb_start_wait_urb(urb, timeout, &length);
+	retv = usb_start_wait_urb(urb, timeout, &length, false);
 	if (retv < 0)
 		return retv;
 	else
@@ -385,10 +395,59 @@ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 		usb_fill_bulk_urb(urb, usb_dev, pipe, data, len,
 				usb_api_blocking_completion, NULL);
 
-	return usb_start_wait_urb(urb, timeout, actual_length);
+	return usb_start_wait_urb(urb, timeout, actual_length, false);
 }
 EXPORT_SYMBOL_GPL(usb_bulk_msg);
 
+/**
+ * usb_bulk_msg_killable - Builds a bulk urb, sends it off and waits for completion in a killable state
+ * @usb_dev: pointer to the usb device to send the message to
+ * @pipe: endpoint "pipe" to send the message to
+ * @data: pointer to the data to send
+ * @len: length in bytes of the data to send
+ * @actual_length: pointer to a location to put the actual length transferred
+ *	in bytes
+ * @timeout: time in msecs to wait for the message to complete before
+ *	timing out (if 0 the wait is forever)
+ *
+ * Context: task context, might sleep.
+ *
+ * This function is just like usb_blk_msg() except that it waits in a
+ * killable state.
+ *
+ * Return:
+ * If successful, 0. Otherwise a negative error number. The number of actual
+ * bytes transferred will be stored in the @actual_length parameter.
+ *
+ */
+int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe,
+		 void *data, int len, int *actual_length, int timeout)
+{
+	struct urb *urb;
+	struct usb_host_endpoint *ep;
+
+	ep = usb_pipe_endpoint(usb_dev, pipe);
+	if (!ep || len < 0)
+		return -EINVAL;
+
+	urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!urb)
+		return -ENOMEM;
+
+	if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+			USB_ENDPOINT_XFER_INT) {
+		pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30);
+		usb_fill_int_urb(urb, usb_dev, pipe, data, len,
+				usb_api_blocking_completion, NULL,
+				ep->desc.bInterval);
+	} else
+		usb_fill_bulk_urb(urb, usb_dev, pipe, data, len,
+				usb_api_blocking_completion, NULL);
+
+	return usb_start_wait_urb(urb, timeout, actual_length, true);
+}
+EXPORT_SYMBOL_GPL(usb_bulk_msg_killable);
+
 /*-------------------------------------------------------------------*/
 
 static void sg_clean(struct usb_sg_request *io)
diff --git a/include/linux/usb.h b/include/linux/usb.h
index fbfcc70b07fb..57ceeb02a7cb 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1868,8 +1868,9 @@ extern int usb_control_msg(struct usb_device *dev, unsigned int pipe,
 extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe,
 	void *data, int len, int *actual_length, int timeout);
 extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
-	void *data, int len, int *actual_length,
-	int timeout);
+	void *data, int len, int *actual_length, int timeout);
+extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe,
+	void *data, int len, int *actual_length, int timeout);
 
 /* wrappers around usb_control_msg() for the most common standard requests */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
-- 
cgit v1.2.3


From 7784caa413a89487dd14dd5c41db8753483b2acb Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:09:22 -0500
Subject: USB: usbtmc: Use usb_bulk_msg_killable() with user-specified timeouts

The usbtmc driver accepts timeout values specified by the user in an
ioctl command, and uses these timeouts for some usb_bulk_msg() calls.
Since the user can specify arbitrarily long timeouts and
usb_bulk_msg() uses unkillable waits, call usb_bulk_msg_killable()
instead to avoid the possibility of the user hanging a kernel thread
indefinitely.

Reported-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-usb/8e1c7ac5-e076-44b0-84b8-1b34b20f0ae1@suse.com/T/#t
Tested-by: syzbot+25ba18e2c5040447585d@syzkaller.appspotmail.com
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Fixes: 048c6d88a021 ("usb: usbtmc: Add ioctls to set/get usb timeout")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/81c6fc24-0607-40f1-8c20-5270dab2fad5@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/usbtmc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 2526a0e03cde..d39bbfd7fd18 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -727,7 +727,7 @@ static int usbtmc488_ioctl_trigger(struct usbtmc_file_data *file_data)
 	buffer[1] = data->bTag;
 	buffer[2] = ~data->bTag;
 
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_sndbulkpipe(data->usb_dev,
 					      data->bulk_out),
 			      buffer, USBTMC_HEADER_SIZE,
@@ -1347,7 +1347,7 @@ static int send_request_dev_dep_msg_in(struct usbtmc_file_data *file_data,
 	buffer[11] = 0; /* Reserved */
 
 	/* Send bulk URB */
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_sndbulkpipe(data->usb_dev,
 					      data->bulk_out),
 			      buffer, USBTMC_HEADER_SIZE,
@@ -1419,7 +1419,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf,
 	actual = 0;
 
 	/* Send bulk URB */
-	retval = usb_bulk_msg(data->usb_dev,
+	retval = usb_bulk_msg_killable(data->usb_dev,
 			      usb_rcvbulkpipe(data->usb_dev,
 					      data->bulk_in),
 			      buffer, bufsize, &actual,
-- 
cgit v1.2.3


From 1015c27a5e1a63efae2b18a9901494474b4d1dc3 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Feb 2026 22:10:32 -0500
Subject: USB: core: Limit the length of unkillable synchronous timeouts

The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in
usbcore allow unlimited timeout durations.  And since they use
uninterruptible waits, this leaves open the possibility of hanging a
task for an indefinitely long time, with no way to kill it short of
unplugging the target device.

To prevent this sort of problem, enforce a maximum limit on the length
of these unkillable timeouts.  The limit chosen here, somewhat
arbitrarily, is 60 seconds.  On many systems (although not all) this
is short enough to avoid triggering the kernel's hung-task detector.

In addition, clear up the ambiguity of negative timeout values by
treating them the same as 0, i.e., using the maximum allowed timeout.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
CC: stable@vger.kernel.org
Link: https://patch.msgid.link/15fc9773-a007-47b0-a703-df89a8cf83dd@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 27 +++++++++++++--------------
 include/linux/usb.h        |  3 +++
 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index d97ec7e8c280..2ab120ce2fa8 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -45,6 +45,8 @@ static void usb_api_blocking_completion(struct urb *urb)
  * Starts urb and waits for completion or timeout.
  * Whether or not the wait is killable depends on the flag passed in.
  * For example, compare usb_bulk_msg() and usb_bulk_msg_killable().
+ *
+ * For non-killable waits, we enforce a maximum limit on the timeout value.
  */
 static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
 		bool killable)
@@ -61,7 +63,9 @@ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length,
 	if (unlikely(retval))
 		goto out;
 
-	expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
+	if (!killable && (timeout <= 0 || timeout > USB_MAX_SYNCHRONOUS_TIMEOUT))
+		timeout = USB_MAX_SYNCHRONOUS_TIMEOUT;
+	expire = (timeout > 0) ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
 	if (killable)
 		rc = wait_for_completion_killable_timeout(&ctx.done, expire);
 	else
@@ -127,8 +131,7 @@ static int usb_internal_control_msg(struct usb_device *usb_dev,
  * @index: USB message index value
  * @data: pointer to the data to send
  * @size: length in bytes of the data to send
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -183,8 +186,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  * @index: USB message index value
  * @driver_data: pointer to the data to send
  * @size: length in bytes of the data to send
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
@@ -242,8 +244,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  * @index: USB message index value
  * @driver_data: pointer to the data to be filled in by the message
  * @size: length in bytes of the data to be received
- * @timeout: time in msecs to wait for the message to complete before timing
- *	out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
@@ -314,8 +315,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_recv);
  * @len: length in bytes of the data to send
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
- * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -347,8 +347,7 @@ EXPORT_SYMBOL_GPL(usb_interrupt_msg);
  * @len: length in bytes of the data to send
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
- * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ * @timeout: time in msecs to wait for the message to complete before timing out
  *
  * Context: task context, might sleep.
  *
@@ -408,12 +407,12 @@ EXPORT_SYMBOL_GPL(usb_bulk_msg);
  * @actual_length: pointer to a location to put the actual length transferred
  *	in bytes
  * @timeout: time in msecs to wait for the message to complete before
- *	timing out (if 0 the wait is forever)
+ *	timing out (if <= 0, the wait is as long as possible)
  *
  * Context: task context, might sleep.
  *
- * This function is just like usb_blk_msg() except that it waits in a
- * killable state.
+ * This function is just like usb_blk_msg(), except that it waits in a
+ * killable state and there is no limit on the timeout length.
  *
  * Return:
  * If successful, 0. Otherwise a negative error number. The number of actual
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 57ceeb02a7cb..04277af4bb9d 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1862,6 +1862,9 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size,
  *                         SYNCHRONOUS CALL SUPPORT                  *
  *-------------------------------------------------------------------*/
 
+/* Maximum value allowed for timeout in synchronous routines below */
+#define USB_MAX_SYNCHRONOUS_TIMEOUT		60000	/* ms */
+
 extern int usb_control_msg(struct usb_device *dev, unsigned int pipe,
 	__u8 request, __u8 requesttype, __u16 value, __u16 index,
 	void *data, __u16 size, int timeout);
-- 
cgit v1.2.3


From 45dba8011efac11a2f360383221b541f5ea53ce5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 13:19:43 +0100
Subject: usb: misc: uss720: properly clean up reference in uss720_probe()

If get_1284_register() fails, the usb device reference count is
incorrect and needs to be properly dropped before returning.  That will
happen when the kref is dropped in the call to destroy_priv(), so jump
to that error path instead of returning directly.

Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026022342-smokiness-stove-d792@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/uss720.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index ec8bd968c4de..a8af7615b1bf 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -736,7 +736,7 @@ static int uss720_probe(struct usb_interface *intf,
 	ret = get_1284_register(pp, 0, &reg, GFP_KERNEL);
 	dev_dbg(&intf->dev, "reg: %7ph\n", priv->reg);
 	if (ret < 0)
-		return ret;
+		goto probe_abort;
 
 	ret = usb_find_last_int_in_endpoint(interface, &epd);
 	if (!ret) {
-- 
cgit v1.2.3


From 9f6a983cfa22ac662c86e60816d3a357d4b551e9 Mon Sep 17 00:00:00 2001
From: Jie Deng <dengjie03@kylinos.cn>
Date: Fri, 27 Feb 2026 16:49:31 +0800
Subject: usb: core: new quirk to handle devices with zero configurations

Some USB devices incorrectly report bNumConfigurations as 0 in their
device descriptor, which causes the USB core to reject them during
enumeration.
logs:
usb 1-2: device descriptor read/64, error -71
usb 1-2: no configurations
usb 1-2: can't read configurations, error -22

However, these devices actually work correctly when
treated as having a single configuration.

Add a new quirk USB_QUIRK_FORCE_ONE_CONFIG to handle such devices.
When this quirk is set, assume the device has 1 configuration instead
of failing with -EINVAL.

This quirk is applied to the device with VID:PID 5131:2007 which
exhibits this behavior.

Signed-off-by: Jie Deng <dengjie03@kylinos.cn>
Link: https://patch.msgid.link/20260227084931.1527461-1-dengjie03@kylinos.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 3 +++
 drivers/usb/core/config.c                       | 6 +++++-
 drivers/usb/core/quirks.c                       | 5 +++++
 include/linux/usb/quirks.h                      | 3 +++
 4 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index cb850e5290c2..7d907efe9f49 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -8183,6 +8183,9 @@ Kernel parameters
 				p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
 					(Reduce timeout of the SET_ADDRESS
 					request from 5000 ms to 500 ms);
+				q = USB_QUIRK_FORCE_ONE_CONFIG (Device
+					claims zero configurations,
+					forcing to 1);
 			Example: quirks=0781:5580:bk,0a5c:5834:gij
 
 	usbhid.mousepoll=
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 1cd5fa61dc76..6a1fd967e0a6 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -927,7 +927,11 @@ int usb_get_configuration(struct usb_device *dev)
 		dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG;
 	}
 
-	if (ncfg < 1) {
+	if (ncfg < 1 && dev->quirks & USB_QUIRK_FORCE_ONE_CONFIG) {
+		dev_info(ddev, "Device claims zero configurations, forcing to 1\n");
+		dev->descriptor.bNumConfigurations = 1;
+		ncfg = 1;
+	} else if (ncfg < 1) {
 		dev_err(ddev, "no configurations\n");
 		return -EINVAL;
 	}
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index e347236d83e8..7bd408db05f4 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -140,6 +140,8 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 			case 'p':
 				flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT;
 				break;
+			case 'q':
+				flags |= USB_QUIRK_FORCE_ONE_CONFIG;
 			/* Ignore unrecognized flag characters */
 			}
 		}
@@ -589,6 +591,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* VCOM device */
 	{ USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* Noji-MCS SmartCard Reader */
+	{ USB_DEVICE(0x5131, 0x2007), .driver_info = USB_QUIRK_FORCE_ONE_CONFIG },
+
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 2f7bd2fdc616..b3cc7beab4a3 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -78,4 +78,7 @@
 /* skip BOS descriptor request */
 #define USB_QUIRK_NO_BOS			BIT(17)
 
+/* Device claims zero configurations, forcing to 1 */
+#define USB_QUIRK_FORCE_ONE_CONFIG		BIT(18)
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 7f58b4148ef5d8ee0fb7d8113dcc38ff5374babc Mon Sep 17 00:00:00 2001
From: John Keeping <jkeeping@inmusicbrands.com>
Date: Fri, 27 Feb 2026 11:15:39 +0000
Subject: usb: gadget: f_hid: fix SuperSpeed descriptors

When adding dynamic configuration for bInterval, the value was removed
from the static SuperSpeed endpoint descriptors but was not set from the
configured value in hidg_bind().  Thus at SuperSpeed the interrupt
endpoints have bInterval as zero which is not valid per the USB
specification.

Add the missing setting for SuperSpeed endpoints.

Fixes: ea34925f5b2ee ("usb: gadget: hid: allow dynamic interval configuration via configfs")
Cc: stable <stable@kernel.org>
Signed-off-by: John Keeping <jkeeping@inmusicbrands.com>
Acked-by: Peter Korsgaard <peter@korsgaard.com>
Link: https://patch.msgid.link/20260227111540.431521-1-jkeeping@inmusicbrands.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_hid.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 8c855c00b887..8812ebf33d14 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -1207,9 +1207,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	if (!hidg->interval_user_set) {
 		hidg_fs_in_ep_desc.bInterval = 10;
 		hidg_hs_in_ep_desc.bInterval = 4;
+		hidg_ss_in_ep_desc.bInterval = 4;
 	} else {
 		hidg_fs_in_ep_desc.bInterval = hidg->interval;
 		hidg_hs_in_ep_desc.bInterval = hidg->interval;
+		hidg_ss_in_ep_desc.bInterval = hidg->interval;
 	}
 
 	hidg_ss_out_comp_desc.wBytesPerInterval =
@@ -1239,9 +1241,11 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 		if (!hidg->interval_user_set) {
 			hidg_fs_out_ep_desc.bInterval = 10;
 			hidg_hs_out_ep_desc.bInterval = 4;
+			hidg_ss_out_ep_desc.bInterval = 4;
 		} else {
 			hidg_fs_out_ep_desc.bInterval = hidg->interval;
 			hidg_hs_out_ep_desc.bInterval = hidg->interval;
+			hidg_ss_out_ep_desc.bInterval = hidg->interval;
 		}
 		status = usb_assign_descriptors(f,
 			    hidg_fs_descriptors_intout,
-- 
cgit v1.2.3


From 8479891d1f04a8ce55366fe4ca361ccdb96f02e1 Mon Sep 17 00:00:00 2001
From: Seungjin Bae <eeodqql09@gmail.com>
Date: Sat, 28 Feb 2026 05:43:25 -0500
Subject: usb: gadget: f_mass_storage: Fix potential integer overflow in
 check_command_size_in_blocks()

The `check_command_size_in_blocks()` function calculates the data size
in bytes by left shifting `common->data_size_from_cmnd` by the block
size (`common->curlun->blkbits`). However, it does not validate whether
this shift operation will cause an integer overflow.

Initially, the block size is set up in `fsg_lun_open()` , and the
`common->data_size_from_cmnd` is set up in `do_scsi_command()`. During
initialization, there is no integer overflow check for the interaction
between two variables.

So if a malicious USB host sends a SCSI READ or WRITE command
requesting a large amount of data (`common->data_size_from_cmnd`), the
left shift operation can wrap around. This results in a truncated data
size, which can bypass boundary checks and potentially lead to memory
corruption or out-of-bounds accesses.

Fix this by using the check_shl_overflow() macro to safely perform the
shift and catch any overflows.

Fixes: 144974e7f9e3 ("usb: gadget: mass_storage: support multi-luns with different logic block size")
Signed-off-by: Seungjin Bae <eeodqql09@gmail.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://patch.msgid.link/20260228104324.1696455-2-eeodqql09@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_mass_storage.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 6af96e2b44eb..b7b06cb79ff5 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -180,6 +180,7 @@
 #include <linux/kthread.h>
 #include <linux/sched/signal.h>
 #include <linux/limits.h>
+#include <linux/overflow.h>
 #include <linux/pagemap.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
@@ -1853,8 +1854,15 @@ static int check_command_size_in_blocks(struct fsg_common *common,
 		int cmnd_size, enum data_direction data_dir,
 		unsigned int mask, int needs_medium, const char *name)
 {
-	if (common->curlun)
-		common->data_size_from_cmnd <<= common->curlun->blkbits;
+	if (common->curlun) {
+		if (check_shl_overflow(common->data_size_from_cmnd,
+				       common->curlun->blkbits,
+				       &common->data_size_from_cmnd)) {
+			common->phase_error = 1;
+			return -EINVAL;
+		}
+	}
+
 	return check_command(common, cmnd_size, data_dir,
 			mask, needs_medium, name);
 }
-- 
cgit v1.2.3


From 14ae24cba291bddfdc296bbcbfd00cd09d0498ef Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 1 Mar 2026 12:44:40 +0000
Subject: usb: cdc-acm: Restore CAP_BRK functionnality to CH343

The CH343 USB/serial adapter is as buggy as it is popular (very).
One of its quirks is that despite being capable of signalling a
BREAK condition, it doesn't advertise it.

This used to work nonetheless until 66aad7d8d3ec5 ("usb: cdc-acm:
return correct error code on unsupported break") applied some
reasonable restrictions, preventing breaks from being emitted on
devices that do not advertise CAP_BRK.

Add a quirk for this particular device, so that breaks can still
be produced on some of my machines attached to my console server.

Fixes: 66aad7d8d3ec5 ("usb: cdc-acm: return correct error code on unsupported break")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable <stable@kernel.org>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/20260301124440.1192752-1-maz@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 5 +++++
 drivers/usb/class/cdc-acm.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index ad38c746270a..7ede29d4c7c1 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1379,6 +1379,8 @@ made_compressed_probe:
 		acm->ctrl_caps = h.usb_cdc_acm_descriptor->bmCapabilities;
 	if (quirks & NO_CAP_LINE)
 		acm->ctrl_caps &= ~USB_CDC_CAP_LINE;
+	if (quirks & MISSING_CAP_BRK)
+		acm->ctrl_caps |= USB_CDC_CAP_BRK;
 	acm->ctrlsize = ctrlsize;
 	acm->readsize = readsize;
 	acm->rx_buflimit = num_rx_buf;
@@ -2002,6 +2004,9 @@ static const struct usb_device_id acm_ids[] = {
 	.driver_info = IGNORE_DEVICE,
 	},
 
+	/* CH343 supports CAP_BRK, but doesn't advertise it */
+	{ USB_DEVICE(0x1a86, 0x55d3), .driver_info = MISSING_CAP_BRK, },
+
 	/* control interfaces without any protocol set */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_PROTO_NONE) },
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 759ac15631d3..76f73853a60b 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -113,3 +113,4 @@ struct acm {
 #define CLEAR_HALT_CONDITIONS		BIT(5)
 #define SEND_ZERO_PACKET		BIT(6)
 #define DISABLE_ECHO			BIT(7)
+#define MISSING_CAP_BRK			BIT(8)
-- 
cgit v1.2.3


From 3cbc242b88c607f55da3d0d0d336b49bf1e20412 Mon Sep 17 00:00:00 2001
From: Fan Wu <fanwu01@zju.edu.cn>
Date: Tue, 3 Mar 2026 07:33:44 +0000
Subject: usb: renesas_usbhs: fix use-after-free in ISR during device removal

In usbhs_remove(), the driver frees resources (including the pipe array)
while the interrupt handler (usbhs_interrupt) is still registered. If an
interrupt fires after usbhs_pipe_remove() but before the driver is fully
unbound, the ISR may access freed memory, causing a use-after-free.

Fix this by calling devm_free_irq() before freeing resources. This ensures
the interrupt handler is both disabled and synchronized (waits for any
running ISR to complete) before usbhs_pipe_remove() is called.

Fixes: f1407d5c6624 ("usb: renesas_usbhs: Add Renesas USBHS common code")
Cc: stable <stable@kernel.org>
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Link: https://patch.msgid.link/20260303073344.34577-1-fanwu01@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index cf4a0367d6d6..8c93bde4b816 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -815,6 +815,15 @@ static void usbhs_remove(struct platform_device *pdev)
 
 	usbhs_platform_call(priv, hardware_exit, pdev);
 	reset_control_assert(priv->rsts);
+
+	/*
+	 * Explicitly free the IRQ to ensure the interrupt handler is
+	 * disabled and synchronized before freeing resources.
+	 * devm_free_irq() calls free_irq() which waits for any running
+	 * ISR to complete, preventing UAF.
+	 */
+	devm_free_irq(&pdev->dev, priv->irq, priv);
+
 	usbhs_mod_remove(priv);
 	usbhs_fifo_remove(priv);
 	usbhs_pipe_remove(priv);
-- 
cgit v1.2.3


From 8df672bfe3ec2268c2636584202755898e547173 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Wed, 4 Mar 2026 14:01:12 +0100
Subject: usb: class: cdc-wdm: fix reordering issue in read code path

Quoting the bug report:

Due to compiler optimization or CPU out-of-order execution, the
desc->length update can be reordered before the memmove. If this
happens, wdm_read() can see the new length and call copy_to_user() on
uninitialized memory. This also violates LKMM data race rules [1].

Fix it by using WRITE_ONCE and memory barriers.

Fixes: afba937e540c9 ("USB: CDC WDM driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Closes: https://lore.kernel.org/linux-usb/CALbr=LbrUZn_cfp7CfR-7Z5wDTHF96qeuM=3fO2m-q4cDrnC4A@mail.gmail.com/
Reported-by: Gui-Dong Han <hanguidong02@gmail.com>
Reviewed-by: Gui-Dong Han <hanguidong02@gmail.com>
Link: https://patch.msgid.link/20260304130116.1721682-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-wdm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index f2d94cfc70af..7556c0dac908 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -225,7 +225,8 @@ static void wdm_in_callback(struct urb *urb)
 		/* we may already be in overflow */
 		if (!test_bit(WDM_OVERFLOW, &desc->flags)) {
 			memmove(desc->ubuf + desc->length, desc->inbuf, length);
-			desc->length += length;
+			smp_wmb(); /* against wdm_read() */
+			WRITE_ONCE(desc->length, desc->length + length);
 		}
 	}
 skip_error:
@@ -533,6 +534,7 @@ static ssize_t wdm_read
 		return -ERESTARTSYS;
 
 	cntr = READ_ONCE(desc->length);
+	smp_rmb(); /* against wdm_in_callback() */
 	if (cntr == 0) {
 		desc->read = 0;
 retry:
-- 
cgit v1.2.3


From c1c8550e70401159184130a1afc6261db01fc0ce Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Thu, 5 Mar 2026 00:36:37 +0200
Subject: usb: xhci: Fix memory leak in xhci_disable_slot()

xhci_alloc_command() allocates a command structure and, when the
second argument is true, also allocates a completion structure.
Currently, the error handling path in xhci_disable_slot() only frees
the command structure using kfree(), causing the completion structure
to leak.

Use xhci_free_command() instead of kfree(). xhci_free_command() correctly
frees both the command structure and the associated completion structure.
Since the command structure is allocated with zero-initialization,
command->in_ctx is NULL and will not be erroneously freed by
xhci_free_command().

This bug was found using an experimental static analysis tool we are
developing. The tool is based on the LLVM framework and is specifically
designed to detect memory management issues. It is currently under
active development and not yet publicly available, but we plan to
open-source it after our research is published.

The bug was originally detected on v6.13-rc1 using our static analysis
tool, and we have verified that the issue persists in the latest mainline
kernel.

We performed build testing on x86_64 with allyesconfig using GCC=11.4.0.
Since triggering these error paths in xhci_disable_slot() requires specific
hardware conditions or abnormal state, we were unable to construct a test
case to reliably trigger these specific error paths at runtime.

Fixes: 7faac1953ed1 ("xhci: avoid race between disable slot command and host runtime suspend")
CC: stable@vger.kernel.org
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index c36ab323d68e..ef6d8662adec 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4146,7 +4146,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 	if (state == 0xffffffff || (xhci->xhc_state & XHCI_STATE_DYING) ||
 			(xhci->xhc_state & XHCI_STATE_HALTED)) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		kfree(command);
+		xhci_free_command(xhci, command);
 		return -ENODEV;
 	}
 
@@ -4154,7 +4154,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 				slot_id);
 	if (ret) {
 		spin_unlock_irqrestore(&xhci->lock, flags);
-		kfree(command);
+		xhci_free_command(xhci, command);
 		return ret;
 	}
 	xhci_ring_cmd_db(xhci);
-- 
cgit v1.2.3


From d6d5febd12452b7fd951fdd15c3ec262f01901a4 Mon Sep 17 00:00:00 2001
From: Dayu Jiang <jiangdayu@xiaomi.com>
Date: Thu, 5 Mar 2026 00:36:38 +0200
Subject: usb: xhci: Prevent interrupt storm on host controller error (HCE)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The xHCI controller reports a Host Controller Error (HCE) in UAS Storage
Device plug/unplug scenarios on Android devices. HCE is checked in
xhci_irq() function and causes an interrupt storm (since the interrupt
isn’t cleared), leading to severe system-level faults.

When the xHC controller reports HCE in the interrupt handler, the driver
only logs a warning and assumes xHC activity will stop as stated in xHCI
specification. An interrupt storm does however continue on some hosts
even after HCE, and only ceases after manually disabling xHC interrupt
and stopping the controller by calling xhci_halt().

Add xhci_halt() to xhci_irq() function where STS_HCE status is checked,
mirroring the existing error handling pattern used for STS_FATAL errors.

This only fixes the interrupt storm. Proper HCE recovery requires resetting
and re-initializing the xHC.

CC: stable@vger.kernel.org
Signed-off-by: Dayu Jiang <jiangdayu@xiaomi.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 9315ba18310d..1cbefee3c4ca 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3195,6 +3195,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
 
 	if (status & STS_HCE) {
 		xhci_warn(xhci, "WARNING: Host Controller Error\n");
+		xhci_halt(xhci);
 		goto out;
 	}
 
-- 
cgit v1.2.3


From ae4ff9dead5efa2025eddfcdb29411432bf40a7c Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 5 Mar 2026 00:36:39 +0200
Subject: xhci: Fix NULL pointer dereference when reading portli debugfs files

Michal reported and debgged a NULL pointer dereference bug in the
recently added portli debugfs files

Oops is caused when there are more port registers counted in
xhci->max_ports than ports reported by Supported Protocol capabilities.
This is possible if max_ports is more than maximum port number, or
if there are gaps between ports of different speeds the 'Supported
Protocol' capabilities.

In such cases port->rhub will be NULL so we can't reach xhci behind it.
Add an explicit NULL check for this case, and print portli in hex
without dereferencing port->rhub.

Reported-by: Michal Pecio <michal.pecio@gmail.com>
Closes: https://lore.kernel.org/linux-usb/20260304103856.48b785fd.michal.pecio@gmail.com
Fixes: 384c57ec7205 ("usb: xhci: Add debugfs support for xHCI Port Link Info (PORTLI) register.")
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260304223639.3882398-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-debugfs.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 890fc5e892f1..ade178ab34a7 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -386,11 +386,19 @@ static const struct file_operations port_fops = {
 static int xhci_portli_show(struct seq_file *s, void *unused)
 {
 	struct xhci_port	*port = s->private;
-	struct xhci_hcd		*xhci = hcd_to_xhci(port->rhub->hcd);
+	struct xhci_hcd		*xhci;
 	u32			portli;
 
 	portli = readl(&port->port_reg->portli);
 
+	/* port without protocol capability isn't added to a roothub */
+	if (!port->rhub) {
+		seq_printf(s, "0x%08x\n", portli);
+		return 0;
+	}
+
+	xhci = hcd_to_xhci(port->rhub->hcd);
+
 	/* PORTLI fields are valid if port is a USB3 or eUSB2V2 port */
 	if (port->rhub == &xhci->usb3_rhub)
 		seq_printf(s, "0x%08x LEC=%u RLC=%u TLC=%u\n", portli,
-- 
cgit v1.2.3


From 56135c0c60b07729401af9d329fa9c0eded845a6 Mon Sep 17 00:00:00 2001
From: Junzhong Pan <panjunzhong@linux.spacemit.com>
Date: Fri, 6 Mar 2026 11:30:09 +0800
Subject: usb: gadget: uvc: fix interval_duration calculation

To correctly convert bInterval as interval_duration:
  interval_duration = 2^(bInterval-1) * frame_interval

Current code uses a wrong left shift operand, computing 2^bInterval
instead of 2^(bInterval-1).

Fixes: 010dc57cb516 ("usb: gadget: uvc: fix interval_duration calculation")
Cc: stable <stable@kernel.org>
Signed-off-by: Junzhong Pan <panjunzhong@linux.spacemit.com>
Reviewed-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://patch.msgid.link/20260306-fix-uvc-interval-v1-1-9a2df6859859@linux.spacemit.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/uvc_video.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index 7cea641b06b4..2f9700b3f1b6 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -513,7 +513,7 @@ uvc_video_prep_requests(struct uvc_video *video)
 		return;
 	}
 
-	interval_duration = 2 << (video->ep->desc->bInterval - 1);
+	interval_duration = 1 << (video->ep->desc->bInterval - 1);
 	if (cdev->gadget->speed < USB_SPEED_HIGH)
 		interval_duration *= 10000;
 	else
-- 
cgit v1.2.3


From 0326ff28d56b4fa202de36ffc8462a354f383a64 Mon Sep 17 00:00:00 2001
From: Christoffer Sandberg <cs@tuxedo.de>
Date: Fri, 6 Mar 2026 18:28:14 +0100
Subject: usb/core/quirks: Add Huawei ME906S-device to wakeup quirk

Similar to other Huawei LTE modules using this quirk, this version with
another vid/pid suffers from spurious wakeups.

Setting the quirk fixes the issue for this device as well.

Cc: stable <stable@kernel.org>
Signed-off-by: Christoffer Sandberg <cs@tuxedo.de>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://patch.msgid.link/20260306172817.2098898-1-wse@tuxedocomputers.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 7bd408db05f4..e3f402e0c351 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -209,6 +209,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* HP v222w 16GB Mini USB Drive */
 	{ USB_DEVICE(0x03f0, 0x3f40), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Huawei 4G LTE module ME906S  */
+	{ USB_DEVICE(0x03f0, 0xa31d), .driver_info =
+			USB_QUIRK_DISCONNECT_SUSPEND },
+
 	/* Creative SB Audigy 2 NX */
 	{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
 
-- 
cgit v1.2.3


From 17ab4d4078e22be7fd8fd6fc710c15c085a4cb1b Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 9 Mar 2026 14:02:04 +0100
Subject: usb: dwc3: pci: add support for the Intel Nova Lake -H

This patch adds the necessary PCI ID for Intel Nova Lake -H
devices.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: stable <stable@kernel.org>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260309130204.208661-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 6ecadc81bd6b..6c1cbb722ca8 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -56,6 +56,7 @@
 #define PCI_DEVICE_ID_INTEL_CNPH		0xa36e
 #define PCI_DEVICE_ID_INTEL_CNPV		0xa3b0
 #define PCI_DEVICE_ID_INTEL_RPL			0xa70e
+#define PCI_DEVICE_ID_INTEL_NVLH		0xd37f
 #define PCI_DEVICE_ID_INTEL_PTLH		0xe332
 #define PCI_DEVICE_ID_INTEL_PTLH_PCH		0xe37e
 #define PCI_DEVICE_ID_INTEL_PTLU		0xe432
@@ -447,6 +448,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, CNPH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, CNPV, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, RPL, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, NVLH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLH_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, PTLU, &dwc3_pci_intel_swnode) },
-- 
cgit v1.2.3


From e8557acfa079a54b59a21f447c82a31aec7717df Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 10 Mar 2026 20:41:05 +0000
Subject: usb: typec: altmode/displayport: set displayport signaling rate in
 configure message

dp_altmode_configure sets the signaling rate to the current
configuration's rate and then shifts the value to the Select
Configuration bitfield. On the initial configuration, dp->data.conf
is 0 to begin with, so the signaling rate field is never set, which
leads to some DisplayPort Alt Mode partners sending NAK to the
Configure message.

Set the signaling rate to the capabilities supported by both the
port and the port partner. If the cable supports DisplayPort Alt Mode,
then include its capabilities as well.

Fixes: a17fae8fc38e ("usb: typec: Add Displayport Alternate Mode 2.1 Support")
Cc: stable <stable@kernel.org>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260310204106.3939862-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/displayport.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index d185688a16b1..35d9c3086990 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -100,9 +100,14 @@ static int dp_altmode_configure(struct dp_altmode *dp, u8 con)
 {
 	u8 pin_assign = 0;
 	u32 conf;
+	u32 signal;
 
 	/* DP Signalling */
-	conf = (dp->data.conf & DP_CONF_SIGNALLING_MASK) >> DP_CONF_SIGNALLING_SHIFT;
+	signal = DP_CAP_DP_SIGNALLING(dp->port->vdo) & DP_CAP_DP_SIGNALLING(dp->alt->vdo);
+	if (dp->plug_prime)
+		signal &= DP_CAP_DP_SIGNALLING(dp->plug_prime->vdo);
+
+	conf = signal << DP_CONF_SIGNALLING_SHIFT;
 
 	switch (con) {
 	case DP_STATUS_CON_DISABLED:
-- 
cgit v1.2.3


From 11199720fac2debbe718aec11e026ab3330dc80d Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:46 +0800
Subject: Revert "usb: gadget: f_ncm: Fix atomic context locking issue"

This reverts commit 0d6c8144ca4d93253de952a5ea0028c19ed7ab68.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-1-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c            | 29 +++++++++++++++-----------
 drivers/usb/gadget/function/u_ether_configfs.h | 11 +++++++++-
 drivers/usb/gadget/function/u_ncm.h            |  1 +
 3 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 4da19864d70b..14fc7dce6f39 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -58,7 +58,6 @@ struct f_ncm {
 	u8				notify_state;
 	atomic_t			notify_count;
 	bool				is_open;
-	bool				is_connected;
 
 	const struct ndp_parser_opts	*parser_opts;
 	bool				is_crc;
@@ -865,6 +864,7 @@ invalid:
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
+	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,12 +887,13 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		if (ncm->is_connected) {
-			DBG(cdev, "reset ncm\n");
-			ncm->is_connected = false;
-			gether_disconnect(&ncm->port);
-			ncm_reset_values(ncm);
-		}
+		scoped_guard(mutex, &opts->lock)
+			if (opts->net) {
+				DBG(cdev, "reset ncm\n");
+				opts->net = NULL;
+				gether_disconnect(&ncm->port);
+				ncm_reset_values(ncm);
+			}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -925,7 +926,8 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			ncm->is_connected = true;
+			scoped_guard(mutex, &opts->lock)
+				opts->net = net;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1372,14 +1374,16 @@ err:
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
+	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	if (ncm->is_connected) {
-		ncm->is_connected = false;
-		gether_disconnect(&ncm->port);
-	}
+	scoped_guard(mutex, &opts->lock)
+		if (opts->net) {
+			opts->net = NULL;
+			gether_disconnect(&ncm->port);
+		}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1683,6 +1687,7 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
 
+	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
 	gether_setup_opts_default(&opts->net_opts, "usb");
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 25d8fb05b598..217990a266b2 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -327,9 +327,18 @@ out:									\
 					      char *page)			\
 	{									\
 		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
+		const char *name;						\
 										\
 		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%s\n", opts->net_opts.name);		\
+		rtnl_lock();							\
+		if (opts->net_opts.ifname_set)					\
+			name = opts->net_opts.name;				\
+		else if (opts->net)						\
+			name = netdev_name(opts->net);				\
+		else								\
+			name = "(inactive net_device)";				\
+		rtnl_unlock();							\
+		return sysfs_emit(page, "%s\n", name);				\
 	}									\
 										\
 	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 6d7538855744..d99330fe31e8 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -19,6 +19,7 @@
 
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
+	struct net_device		*net;
 
 	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;
-- 
cgit v1.2.3


From f2524c0e6ff0a5f72f1e1a32441c69d3b56430c4 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:47 +0800
Subject: Revert "usb: legacy: ncm: Fix NPE in gncm_bind"

This reverts commit fde0634ad9856b3943a2d1a8cc8de174a63ac840.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-2-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/legacy/ncm.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c
index e8d565534053..0f1b45e3abd1 100644
--- a/drivers/usb/gadget/legacy/ncm.c
+++ b/drivers/usb/gadget/legacy/ncm.c
@@ -15,10 +15,8 @@
 /* #define DEBUG */
 /* #define VERBOSE_DEBUG */
 
-#include <linux/hex.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/string.h>
 #include <linux/usb/composite.h>
 
 #include "u_ether.h"
@@ -131,7 +129,6 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 	struct usb_gadget	*gadget = cdev->gadget;
 	struct f_ncm_opts	*ncm_opts;
 	int			status;
-	u8			mac[ETH_ALEN];
 
 	f_ncm_inst = usb_get_function_instance("ncm");
 	if (IS_ERR(f_ncm_inst))
@@ -139,15 +136,11 @@ static int gncm_bind(struct usb_composite_dev *cdev)
 
 	ncm_opts = container_of(f_ncm_inst, struct f_ncm_opts, func_inst);
 
-	ncm_opts->net_opts.qmult = qmult;
-	if (host_addr && mac_pton(host_addr, mac)) {
-		memcpy(&ncm_opts->net_opts.host_mac, mac, ETH_ALEN);
+	gether_set_qmult(ncm_opts->net, qmult);
+	if (!gether_set_host_addr(ncm_opts->net, host_addr))
 		pr_info("using host ethernet address: %s", host_addr);
-	}
-	if (dev_addr && mac_pton(dev_addr, mac)) {
-		memcpy(&ncm_opts->net_opts.dev_mac, mac, ETH_ALEN);
+	if (!gether_set_dev_addr(ncm_opts->net, dev_addr))
 		pr_info("using self ethernet address: %s", dev_addr);
-	}
 
 	/* Allocate string descriptor numbers ... note that string
 	 * contents can be overridden by the composite_dev glue.
-- 
cgit v1.2.3


From 37893bc5de2460c543ec1aa8250c37a305234054 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:48 +0800
Subject: Revert "usb: gadget: f_ncm: align net_device lifecycle with
 bind/unbind"

This reverts commit 56a512a9b4107079f68701e7d55da8507eb963d9.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-3-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c | 128 ++++++++++++++++++------------------
 drivers/usb/gadget/function/u_ncm.h |   4 +-
 2 files changed, 66 insertions(+), 66 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 14fc7dce6f39..3d772c9beb91 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -83,11 +83,6 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
 	return container_of(f, struct f_ncm, port.func);
 }
 
-static inline struct f_ncm_opts *func_to_ncm_opts(struct usb_function *f)
-{
-	return container_of(f->fi, struct f_ncm_opts, func_inst);
-}
-
 /*-------------------------------------------------------------------------*/
 
 /*
@@ -864,7 +859,6 @@ invalid:
 static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	/* Control interface has only altsetting 0 */
@@ -887,13 +881,12 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 		if (alt > 1)
 			goto fail;
 
-		scoped_guard(mutex, &opts->lock)
-			if (opts->net) {
-				DBG(cdev, "reset ncm\n");
-				opts->net = NULL;
-				gether_disconnect(&ncm->port);
-				ncm_reset_values(ncm);
-			}
+		if (ncm->netdev) {
+			DBG(cdev, "reset ncm\n");
+			ncm->netdev = NULL;
+			gether_disconnect(&ncm->port);
+			ncm_reset_values(ncm);
+		}
 
 		/*
 		 * CDC Network only sends data in non-default altsettings.
@@ -926,8 +919,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 			net = gether_connect(&ncm->port);
 			if (IS_ERR(net))
 				return PTR_ERR(net);
-			scoped_guard(mutex, &opts->lock)
-				opts->net = net;
+			ncm->netdev = net;
 		}
 
 		spin_lock(&ncm->lock);
@@ -1374,16 +1366,14 @@ err:
 static void ncm_disable(struct usb_function *f)
 {
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*opts = func_to_ncm_opts(f);
 	struct usb_composite_dev *cdev = f->config->cdev;
 
 	DBG(cdev, "ncm deactivated\n");
 
-	scoped_guard(mutex, &opts->lock)
-		if (opts->net) {
-			opts->net = NULL;
-			gether_disconnect(&ncm->port);
-		}
+	if (ncm->netdev) {
+		ncm->netdev = NULL;
+		gether_disconnect(&ncm->port);
+	}
 
 	if (ncm->notify->enabled) {
 		usb_ep_disable(ncm->notify);
@@ -1443,44 +1433,39 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_ncm		*ncm = func_to_ncm(f);
-	struct f_ncm_opts	*ncm_opts = func_to_ncm_opts(f);
 	struct usb_string	*us;
 	int			status = 0;
 	struct usb_ep		*ep;
+	struct f_ncm_opts	*ncm_opts;
 
 	struct usb_os_desc_table	*os_desc_table __free(kfree) = NULL;
-	struct net_device		*netdev __free(free_gether_netdev) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
 		return -EINVAL;
 
+	ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+
 	if (cdev->use_os_string) {
 		os_desc_table = kzalloc(sizeof(*os_desc_table), GFP_KERNEL);
 		if (!os_desc_table)
 			return -ENOMEM;
 	}
 
-	netdev = gether_setup_default();
-	if (IS_ERR(netdev))
-		return -ENOMEM;
-
-	scoped_guard(mutex, &ncm_opts->lock) {
-		gether_apply_opts(netdev, &ncm_opts->net_opts);
-		netdev->mtu = ncm_opts->max_segment_size - ETH_HLEN;
+	mutex_lock(&ncm_opts->lock);
+	gether_set_gadget(ncm_opts->net, cdev->gadget);
+	if (!ncm_opts->bound) {
+		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
+		status = gether_register_netdev(ncm_opts->net);
 	}
+	mutex_unlock(&ncm_opts->lock);
 
-	gether_set_gadget(netdev, cdev->gadget);
-	status = gether_register_netdev(netdev);
 	if (status)
 		return status;
 
-	/* export host's Ethernet address in CDC format */
-	status = gether_get_host_addr_cdc(netdev, ncm->ethaddr,
-					  sizeof(ncm->ethaddr));
-	if (status < 12)
-		return -EINVAL;
-	ncm_string_defs[STRING_MAC_IDX].s = ncm->ethaddr;
+	ncm_opts->bound = true;
+
+	ncm_string_defs[1].s = ncm->ethaddr;
 
 	us = usb_gstrings_attach(cdev, ncm_strings,
 				 ARRAY_SIZE(ncm_string_defs));
@@ -1578,8 +1563,6 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 		f->os_desc_n = 1;
 	}
 	ncm->notify_req = no_free_ptr(request);
-	ncm->netdev = no_free_ptr(netdev);
-	ncm->port.ioport = netdev_priv(ncm->netdev);
 
 	DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n",
 			ncm->port.in_ep->name, ncm->port.out_ep->name,
@@ -1594,19 +1577,19 @@ static inline struct f_ncm_opts *to_f_ncm_opts(struct config_item *item)
 }
 
 /* f_ncm_item_ops */
-USB_ETHER_OPTS_ITEM(ncm);
+USB_ETHERNET_CONFIGFS_ITEM(ncm);
 
 /* f_ncm_opts_dev_addr */
-USB_ETHER_OPTS_ATTR_DEV_ADDR(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_DEV_ADDR(ncm);
 
 /* f_ncm_opts_host_addr */
-USB_ETHER_OPTS_ATTR_HOST_ADDR(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_HOST_ADDR(ncm);
 
 /* f_ncm_opts_qmult */
-USB_ETHER_OPTS_ATTR_QMULT(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_QMULT(ncm);
 
 /* f_ncm_opts_ifname */
-USB_ETHER_OPTS_ATTR_IFNAME(ncm);
+USB_ETHERNET_CONFIGFS_ITEM_ATTR_IFNAME(ncm);
 
 static ssize_t ncm_opts_max_segment_size_show(struct config_item *item,
 					      char *page)
@@ -1672,27 +1655,34 @@ static void ncm_free_inst(struct usb_function_instance *f)
 	struct f_ncm_opts *opts;
 
 	opts = container_of(f, struct f_ncm_opts, func_inst);
+	if (opts->bound)
+		gether_cleanup(netdev_priv(opts->net));
+	else
+		free_netdev(opts->net);
 	kfree(opts->ncm_interf_group);
 	kfree(opts);
 }
 
 static struct usb_function_instance *ncm_alloc_inst(void)
 {
-	struct usb_function_instance *ret;
+	struct f_ncm_opts *opts;
 	struct usb_os_desc *descs[1];
 	char *names[1];
 	struct config_group *ncm_interf_group;
 
-	struct f_ncm_opts *opts __free(kfree) = kzalloc_obj(*opts);
+	opts = kzalloc_obj(*opts);
 	if (!opts)
 		return ERR_PTR(-ENOMEM);
-
-	opts->net = NULL;
 	opts->ncm_os_desc.ext_compat_id = opts->ncm_ext_compat_id;
-	gether_setup_opts_default(&opts->net_opts, "usb");
 
 	mutex_init(&opts->lock);
 	opts->func_inst.free_func_inst = ncm_free_inst;
+	opts->net = gether_setup_default();
+	if (IS_ERR(opts->net)) {
+		struct net_device *net = opts->net;
+		kfree(opts);
+		return ERR_CAST(net);
+	}
 	opts->max_segment_size = ETH_FRAME_LEN;
 	INIT_LIST_HEAD(&opts->ncm_os_desc.ext_prop);
 
@@ -1703,22 +1693,26 @@ static struct usb_function_instance *ncm_alloc_inst(void)
 	ncm_interf_group =
 		usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs,
 					       names, THIS_MODULE);
-	if (IS_ERR(ncm_interf_group))
+	if (IS_ERR(ncm_interf_group)) {
+		ncm_free_inst(&opts->func_inst);
 		return ERR_CAST(ncm_interf_group);
+	}
 	opts->ncm_interf_group = ncm_interf_group;
 
-	ret = &opts->func_inst;
-	retain_and_null_ptr(opts);
-	return ret;
+	return &opts->func_inst;
 }
 
 static void ncm_free(struct usb_function *f)
 {
-	struct f_ncm_opts *opts = func_to_ncm_opts(f);
+	struct f_ncm *ncm;
+	struct f_ncm_opts *opts;
 
-	scoped_guard(mutex, &opts->lock)
-		opts->refcnt--;
-	kfree(func_to_ncm(f));
+	ncm = func_to_ncm(f);
+	opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+	kfree(ncm);
+	mutex_lock(&opts->lock);
+	opts->refcnt--;
+	mutex_unlock(&opts->lock);
 }
 
 static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
@@ -1742,15 +1736,13 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
-
-	ncm->port.ioport = NULL;
-	gether_cleanup(netdev_priv(ncm->netdev));
 }
 
 static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
 {
 	struct f_ncm		*ncm;
 	struct f_ncm_opts	*opts;
+	int status;
 
 	/* allocate and initialize one new instance */
 	ncm = kzalloc(sizeof(*ncm), GFP_KERNEL);
@@ -1758,12 +1750,22 @@ static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
 		return ERR_PTR(-ENOMEM);
 
 	opts = container_of(fi, struct f_ncm_opts, func_inst);
+	mutex_lock(&opts->lock);
+	opts->refcnt++;
 
-	scoped_guard(mutex, &opts->lock)
-		opts->refcnt++;
+	/* export host's Ethernet address in CDC format */
+	status = gether_get_host_addr_cdc(opts->net, ncm->ethaddr,
+				      sizeof(ncm->ethaddr));
+	if (status < 12) { /* strlen("01234567890a") */
+		kfree(ncm);
+		mutex_unlock(&opts->lock);
+		return ERR_PTR(-EINVAL);
+	}
 
 	spin_lock_init(&ncm->lock);
 	ncm_reset_values(ncm);
+	ncm->port.ioport = netdev_priv(opts->net);
+	mutex_unlock(&opts->lock);
 	ncm->port.is_fixed = true;
 	ncm->port.supports_multi_frame = true;
 
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index d99330fe31e8..49ec095cdb4b 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -15,13 +15,11 @@
 
 #include <linux/usb/composite.h>
 
-#include "u_ether.h"
-
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
+	bool				bound;
 
-	struct gether_opts		net_opts;
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;
 	char				ncm_ext_compat_id[16];
-- 
cgit v1.2.3


From 46662d3a1ad40282ba9f753cccc6f909ec4468cc Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:49 +0800
Subject: Revert "usb: gadget: u_ether: Add auto-cleanup helper for freeing
 net_device"

This reverts commit 0c0981126b99288ed354d3d414c8a5fd42ac9e25.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-4-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 15 ---------------
 drivers/usb/gadget/function/u_ether.h |  2 --
 2 files changed, 17 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 338f6e2a85a9..15685b2f8887 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1126,21 +1126,6 @@ void gether_cleanup(struct eth_dev *dev)
 }
 EXPORT_SYMBOL_GPL(gether_cleanup);
 
-void gether_unregister_free_netdev(struct net_device *net)
-{
-	if (!net)
-		return;
-
-	struct eth_dev *dev = netdev_priv(net);
-
-	if (net->reg_state == NETREG_REGISTERED) {
-		unregister_netdev(net);
-		flush_work(&dev->work);
-	}
-	free_netdev(net);
-}
-EXPORT_SYMBOL_GPL(gether_unregister_free_netdev);
-
 /**
  * gether_connect - notify network layer that USB link is active
  * @link: the USB link, set up with endpoints, descriptors matching
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index a212a8ec5eb1..63a0240df4d7 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -283,8 +283,6 @@ int gether_get_ifname(struct net_device *net, char *name, int len);
 int gether_set_ifname(struct net_device *net, const char *name, int len);
 
 void gether_cleanup(struct eth_dev *dev);
-void gether_unregister_free_netdev(struct net_device *net);
-DEFINE_FREE(free_gether_netdev, struct net_device *, gether_unregister_free_netdev(_T));
 
 void gether_setup_opts_default(struct gether_opts *opts, const char *name);
 void gether_apply_opts(struct net_device *net, struct gether_opts *opts);
-- 
cgit v1.2.3


From 3549d0ae5f7e647ffd09d69f927a18ae7a520f6f Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:50 +0800
Subject: Revert "usb: gadget: u_ether: use <linux/hex.h> header file"

This reverts commit 7a7930c0f934fb0c46de6e7ca08e14e11df35dd6.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-5-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether_configfs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 217990a266b2..39d3a261496d 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -14,7 +14,6 @@
 #define __U_ETHER_CONFIGFS_H
 
 #include <linux/cleanup.h>
-#include <linux/hex.h>
 #include <linux/if_ether.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
-- 
cgit v1.2.3


From 3131c1aff7cdffb96239f06f98e16188cbc2083f Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:51 +0800
Subject: Revert "usb: gadget: u_ether: add gether_opts for config caching"

This reverts commit e065c6a7e46c2ee9c677fdbf50035323d2de1215.

This commit is being reverted as part of a series-wide revert.

By deferring the net_device allocation to the bind() phase, a single
function instance will spawn multiple network devices if it is symlinked
to multiple USB configurations.

This causes regressions for userspace tools (like the postmarketOS DHCP
daemon) that rely on reading the interface name (e.g., "usb0") from
configfs. Currently, configfs returns the template "usb%d", causing the
userspace network setup to fail.

Crucially, because this patch breaks the 1:1 mapping between the
function instance and the network device, this naming issue cannot
simply be patched. Configfs only exposes a single 'ifname' attribute per
instance, making it impossible to accurately report the actual interface
name when multiple underlying network devices can exist for that single
instance.

All configurations tied to the same function instance are meant to share
a single network device. Revert this change to restore the 1:1 mapping
by allocating the network device at the instance level (alloc_inst).

Reported-by: David Heidelberg <david@ixit.cz>
Closes: https://lore.kernel.org/linux-usb/70b558ea-a12e-4170-9b8e-c951131249af@ixit.cz/
Fixes: 56a512a9b410 ("usb: gadget: f_ncm: align net_device lifecycle with bind/unbind")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-6-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c          |  30 -----
 drivers/usb/gadget/function/u_ether.h          |  28 ----
 drivers/usb/gadget/function/u_ether_configfs.h | 176 -------------------------
 3 files changed, 234 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 15685b2f8887..c47965d850d4 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1040,36 +1040,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len)
 }
 EXPORT_SYMBOL_GPL(gether_set_ifname);
 
-void gether_setup_opts_default(struct gether_opts *opts, const char *name)
-{
-	opts->qmult = QMULT_DEFAULT;
-	snprintf(opts->name, sizeof(opts->name), "%s%%d", name);
-	eth_random_addr(opts->dev_mac);
-	opts->addr_assign_type = NET_ADDR_RANDOM;
-	eth_random_addr(opts->host_mac);
-}
-EXPORT_SYMBOL_GPL(gether_setup_opts_default);
-
-void gether_apply_opts(struct net_device *net, struct gether_opts *opts)
-{
-	struct eth_dev *dev = netdev_priv(net);
-
-	dev->qmult = opts->qmult;
-
-	if (opts->ifname_set) {
-		strscpy(net->name, opts->name, sizeof(net->name));
-		dev->ifname_set = true;
-	}
-
-	memcpy(dev->host_mac, opts->host_mac, sizeof(dev->host_mac));
-
-	if (opts->addr_assign_type == NET_ADDR_SET) {
-		memcpy(dev->dev_mac, opts->dev_mac, sizeof(dev->dev_mac));
-		net->addr_assign_type = opts->addr_assign_type;
-	}
-}
-EXPORT_SYMBOL_GPL(gether_apply_opts);
-
 void gether_suspend(struct gether *link)
 {
 	struct eth_dev *dev = link->ioport;
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index 63a0240df4d7..34be220cef77 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -38,31 +38,6 @@
 
 struct eth_dev;
 
-/**
- * struct gether_opts - Options for Ethernet gadget function instances
- * @name: Pattern for the network interface name (e.g., "usb%d").
- *        Used to generate the net device name.
- * @qmult: Queue length multiplier for high/super speed.
- * @host_mac: The MAC address to be used by the host side.
- * @dev_mac: The MAC address to be used by the device side.
- * @ifname_set: True if the interface name pattern has been set by userspace.
- * @addr_assign_type: The method used for assigning the device MAC address
- *                    (e.g., NET_ADDR_RANDOM, NET_ADDR_SET).
- *
- * This structure caches network-related settings provided through configfs
- * before the net_device is fully instantiated. This allows for early
- * configuration while deferring net_device allocation until the function
- * is bound.
- */
-struct gether_opts {
-	char			name[IFNAMSIZ];
-	unsigned int		qmult;
-	u8			host_mac[ETH_ALEN];
-	u8			dev_mac[ETH_ALEN];
-	bool			ifname_set;
-	unsigned char		addr_assign_type;
-};
-
 /*
  * This represents the USB side of an "ethernet" link, managed by a USB
  * function which provides control and (maybe) framing.  Two functions
@@ -284,9 +259,6 @@ int gether_set_ifname(struct net_device *net, const char *name, int len);
 
 void gether_cleanup(struct eth_dev *dev);
 
-void gether_setup_opts_default(struct gether_opts *opts, const char *name);
-void gether_apply_opts(struct net_device *net, struct gether_opts *opts);
-
 void gether_suspend(struct gether *link);
 void gether_resume(struct gether *link);
 
diff --git a/drivers/usb/gadget/function/u_ether_configfs.h b/drivers/usb/gadget/function/u_ether_configfs.h
index 39d3a261496d..51f0d79e5eca 100644
--- a/drivers/usb/gadget/function/u_ether_configfs.h
+++ b/drivers/usb/gadget/function/u_ether_configfs.h
@@ -13,12 +13,6 @@
 #ifndef __U_ETHER_CONFIGFS_H
 #define __U_ETHER_CONFIGFS_H
 
-#include <linux/cleanup.h>
-#include <linux/if_ether.h>
-#include <linux/mutex.h>
-#include <linux/netdevice.h>
-#include <linux/rtnetlink.h>
-
 #define USB_ETHERNET_CONFIGFS_ITEM(_f_)					\
 	static void _f_##_attr_release(struct config_item *item)	\
 	{								\
@@ -203,174 +197,4 @@ out:									\
 									\
 	CONFIGFS_ATTR(_f_##_opts_, _n_)
 
-#define USB_ETHER_OPTS_ITEM(_f_)						\
-	static void _f_##_attr_release(struct config_item *item)		\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		usb_put_function_instance(&opts->func_inst);			\
-	}									\
-										\
-	static struct configfs_item_operations _f_##_item_ops = {		\
-		.release	= _f_##_attr_release,				\
-	}
-
-#define USB_ETHER_OPTS_ATTR_DEV_ADDR(_f_)					\
-	static ssize_t _f_##_opts_dev_addr_show(struct config_item *item,	\
-						char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%pM\n", opts->net_opts.dev_mac);	\
-	}									\
-										\
-	static ssize_t _f_##_opts_dev_addr_store(struct config_item *item,	\
-						 const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u8 new_addr[ETH_ALEN];						\
-		const char *p = page;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		for (int i = 0; i < ETH_ALEN; i++) {				\
-			unsigned char num;					\
-			if ((*p == '.') || (*p == ':'))				\
-				p++;						\
-			num = hex_to_bin(*p++) << 4;				\
-			num |= hex_to_bin(*p++);				\
-			new_addr[i] = num;					\
-		}								\
-		if (!is_valid_ether_addr(new_addr))				\
-			return -EINVAL;						\
-		memcpy(opts->net_opts.dev_mac, new_addr, ETH_ALEN);		\
-		opts->net_opts.addr_assign_type = NET_ADDR_SET;			\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, dev_addr)
-
-#define USB_ETHER_OPTS_ATTR_HOST_ADDR(_f_)					\
-	static ssize_t _f_##_opts_host_addr_show(struct config_item *item,	\
-						 char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%pM\n", opts->net_opts.host_mac);	\
-	}									\
-										\
-	static ssize_t _f_##_opts_host_addr_store(struct config_item *item,	\
-						  const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u8 new_addr[ETH_ALEN];						\
-		const char *p = page;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		for (int i = 0; i < ETH_ALEN; i++) {				\
-			unsigned char num;					\
-			if ((*p == '.') || (*p == ':'))				\
-				p++;						\
-			num = hex_to_bin(*p++) << 4;				\
-			num |= hex_to_bin(*p++);				\
-			new_addr[i] = num;					\
-		}								\
-		if (!is_valid_ether_addr(new_addr))				\
-			return -EINVAL;						\
-		memcpy(opts->net_opts.host_mac, new_addr, ETH_ALEN);		\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, host_addr)
-
-#define USB_ETHER_OPTS_ATTR_QMULT(_f_)						\
-	static ssize_t _f_##_opts_qmult_show(struct config_item *item,		\
-					     char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-										\
-		guard(mutex)(&opts->lock);					\
-		return sysfs_emit(page, "%u\n", opts->net_opts.qmult);		\
-	}									\
-										\
-	static ssize_t _f_##_opts_qmult_store(struct config_item *item,		\
-					      const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		u32 val;							\
-		int ret;							\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-										\
-		ret = kstrtou32(page, 0, &val);					\
-		if (ret)							\
-			return ret;						\
-										\
-		opts->net_opts.qmult = val;					\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, qmult)
-
-#define USB_ETHER_OPTS_ATTR_IFNAME(_f_)						\
-	static ssize_t _f_##_opts_ifname_show(struct config_item *item,		\
-					      char *page)			\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		const char *name;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		rtnl_lock();							\
-		if (opts->net_opts.ifname_set)					\
-			name = opts->net_opts.name;				\
-		else if (opts->net)						\
-			name = netdev_name(opts->net);				\
-		else								\
-			name = "(inactive net_device)";				\
-		rtnl_unlock();							\
-		return sysfs_emit(page, "%s\n", name);				\
-	}									\
-										\
-	static ssize_t _f_##_opts_ifname_store(struct config_item *item,	\
-					       const char *page, size_t len)	\
-	{									\
-		struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item);		\
-		char tmp[IFNAMSIZ];						\
-		const char *p;							\
-		size_t c_len = len;						\
-										\
-		if (c_len > 0 && page[c_len - 1] == '\n')			\
-			c_len--;						\
-										\
-		if (c_len >= sizeof(tmp))					\
-			return -E2BIG;						\
-										\
-		strscpy(tmp, page, c_len + 1);					\
-		if (!dev_valid_name(tmp))					\
-			return -EINVAL;						\
-										\
-		/* Require exactly one %d */					\
-		p = strchr(tmp, '%');						\
-		if (!p || p[1] != 'd' || strchr(p + 2, '%'))			\
-			return -EINVAL;						\
-										\
-		guard(mutex)(&opts->lock);					\
-		if (opts->refcnt)						\
-			return -EBUSY;						\
-		strscpy(opts->net_opts.name, tmp, sizeof(opts->net_opts.name));	\
-		opts->net_opts.ifname_set = true;				\
-		return len;							\
-	}									\
-										\
-	CONFIGFS_ATTR(_f_##_opts_, ifname)
-
 #endif /* __U_ETHER_CONFIGFS_H */
-- 
cgit v1.2.3


From ec35c1969650e7cb6c8a91020e568ed46e3551b0 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 9 Mar 2026 20:04:52 +0800
Subject: usb: gadget: f_ncm: Fix net_device lifecycle with device_move

The network device outlived its parent gadget device during
disconnection, resulting in dangling sysfs links and null pointer
dereference problems.

A prior attempt to solve this by removing SET_NETDEV_DEV entirely [1]
was reverted due to power management ordering concerns and a NO-CARRIER
regression.

A subsequent attempt to defer net_device allocation to bind [2] broke
1:1 mapping between function instance and network device, making it
impossible for configfs to report the resolved interface name. This
results in a regression where the DHCP server fails on pmOS.

Use device_move to reparent the net_device between the gadget device and
/sys/devices/virtual/ across bind/unbind cycles. This preserves the
network interface across USB reconnection, allowing the DHCP server to
retain their binding.

Introduce gether_attach_gadget()/gether_detach_gadget() helpers and use
__free(detach_gadget) macro to undo attachment on bind failure. The
bind_count ensures device_move executes only on the first bind.

[1] https://lore.kernel.org/lkml/f2a4f9847617a0929d62025748384092e5f35cce.camel@crapouillou.net/
[2] https://lore.kernel.org/linux-usb/795ea759-7eaf-4f78-81f4-01ffbf2d7961@ixit.cz/

Fixes: 40d133d7f542 ("usb: gadget: f_ncm: convert to new function interface with backward compatibility")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260309-f-ncm-revert-v2-7-ea2afbc7d9b2@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ncm.c   | 38 +++++++++++++++++++++++------------
 drivers/usb/gadget/function/u_ether.c | 22 ++++++++++++++++++++
 drivers/usb/gadget/function/u_ether.h | 26 ++++++++++++++++++++++++
 drivers/usb/gadget/function/u_ncm.h   |  2 +-
 4 files changed, 74 insertions(+), 14 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 3d772c9beb91..a6fa5ed3d6cb 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -1439,6 +1439,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	struct f_ncm_opts	*ncm_opts;
 
 	struct usb_os_desc_table	*os_desc_table __free(kfree) = NULL;
+	struct net_device		*net __free(detach_gadget) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
@@ -1452,18 +1453,19 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 			return -ENOMEM;
 	}
 
-	mutex_lock(&ncm_opts->lock);
-	gether_set_gadget(ncm_opts->net, cdev->gadget);
-	if (!ncm_opts->bound) {
-		ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
-		status = gether_register_netdev(ncm_opts->net);
-	}
-	mutex_unlock(&ncm_opts->lock);
-
-	if (status)
-		return status;
-
-	ncm_opts->bound = true;
+	scoped_guard(mutex, &ncm_opts->lock)
+		if (ncm_opts->bind_count == 0) {
+			if (!device_is_registered(&ncm_opts->net->dev)) {
+				ncm_opts->net->mtu = (ncm_opts->max_segment_size - ETH_HLEN);
+				gether_set_gadget(ncm_opts->net, cdev->gadget);
+				status = gether_register_netdev(ncm_opts->net);
+			} else
+				status = gether_attach_gadget(ncm_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = ncm_opts->net;
+		}
 
 	ncm_string_defs[1].s = ncm->ethaddr;
 
@@ -1564,6 +1566,9 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 	ncm->notify_req = no_free_ptr(request);
 
+	ncm_opts->bind_count++;
+	retain_and_null_ptr(net);
+
 	DBG(cdev, "CDC Network: IN/%s OUT/%s NOTIFY/%s\n",
 			ncm->port.in_ep->name, ncm->port.out_ep->name,
 			ncm->notify->name);
@@ -1655,7 +1660,7 @@ static void ncm_free_inst(struct usb_function_instance *f)
 	struct f_ncm_opts *opts;
 
 	opts = container_of(f, struct f_ncm_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -1718,9 +1723,12 @@ static void ncm_free(struct usb_function *f)
 static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_ncm *ncm = func_to_ncm(f);
+	struct f_ncm_opts *ncm_opts;
 
 	DBG(c->cdev, "ncm unbind\n");
 
+	ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+
 	hrtimer_cancel(&ncm->task_timer);
 
 	kfree(f->os_desc_table);
@@ -1736,6 +1744,10 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
+
+	ncm_opts->bind_count--;
+	if (ncm_opts->bind_count == 0)
+		gether_detach_gadget(ncm_opts->net);
 }
 
 static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index c47965d850d4..1a9e7c495e2e 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -897,6 +897,28 @@ void gether_set_gadget(struct net_device *net, struct usb_gadget *g)
 }
 EXPORT_SYMBOL_GPL(gether_set_gadget);
 
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g)
+{
+	int ret;
+
+	ret = device_move(&net->dev, &g->dev, DPM_ORDER_DEV_AFTER_PARENT);
+	if (ret)
+		return ret;
+
+	gether_set_gadget(net, g);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gether_attach_gadget);
+
+void gether_detach_gadget(struct net_device *net)
+{
+	struct eth_dev *dev = netdev_priv(net);
+
+	device_move(&net->dev, NULL, DPM_ORDER_NONE);
+	dev->gadget = NULL;
+}
+EXPORT_SYMBOL_GPL(gether_detach_gadget);
+
 int gether_set_dev_addr(struct net_device *net, const char *dev_addr)
 {
 	struct eth_dev *dev;
diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h
index 34be220cef77..c85a1cf3c115 100644
--- a/drivers/usb/gadget/function/u_ether.h
+++ b/drivers/usb/gadget/function/u_ether.h
@@ -150,6 +150,32 @@ static inline struct net_device *gether_setup_default(void)
  */
 void gether_set_gadget(struct net_device *net, struct usb_gadget *g);
 
+/**
+ * gether_attach_gadget - Reparent net_device to the gadget device.
+ * @net: The network device to reparent.
+ * @g: The target USB gadget device to parent to.
+ *
+ * This function moves the network device to be a child of the USB gadget
+ * device in the device hierarchy. This is typically done when the function
+ * is bound to a configuration.
+ *
+ * Returns 0 on success, or a negative error code on failure.
+ */
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g);
+
+/**
+ * gether_detach_gadget - Detach net_device from its gadget parent.
+ * @net: The network device to detach.
+ *
+ * This function moves the network device to be a child of the virtual
+ * devices parent, effectively detaching it from the USB gadget device
+ * hierarchy. This is typically done when the function is unbound
+ * from a configuration but the instance is not yet freed.
+ */
+void gether_detach_gadget(struct net_device *net);
+
+DEFINE_FREE(detach_gadget, struct net_device *, if (_T) gether_detach_gadget(_T))
+
 /**
  * gether_set_dev_addr - initialize an ethernet-over-usb link with eth address
  * @net: device representing this link
diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index 49ec095cdb4b..b1f3db8b68c1 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -18,7 +18,7 @@
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
-	bool				bound;
+	int				bind_count;
 
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;
-- 
cgit v1.2.3


From 6b275bfaa16be3fb1689fa6794e445ecd127a1b4 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 9 Mar 2026 15:43:12 +0800
Subject: Revert "tcpm: allow looking for role_sw device in the main node"

This reverts commit 1366cd228b0c67b60a2c0c26ef37fe9f7cfedb7f.

The fwnode_usb_role_switch_get() returns NULL only if no connection is
found, returns ERR_PTR(-EPROBE_DEFER) if connection is found but deferred
probe is needed, or a valid pointer of usb_role_switch.

When switching from a NULL check to IS_ERR_OR_NULL(), usb_role_switch_get()
returns NULL and overwrites the ERR_PTR(-EPROBE_DEFER) returned by
fwnode_usb_role_switch_get(). This causes the deferred probe indication to
be lost, preventing the USB role switch from ever being retrieved.

Fixes: 1366cd228b0c ("tcpm: allow looking for role_sw device in the main node")
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Tested-by: Arnaud Ferraris <arnaud.ferraris@collabora.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260309074313.2809867-2-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 1d2f3af034c5..8e0e14a2704e 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -7890,7 +7890,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	port->partner_desc.identity = &port->partner_ident;
 
 	port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode);
-	if (IS_ERR_OR_NULL(port->role_sw))
+	if (!port->role_sw)
 		port->role_sw = usb_role_switch_get(port->dev);
 	if (IS_ERR(port->role_sw)) {
 		err = PTR_ERR(port->role_sw);
-- 
cgit v1.2.3


From 8345b1539faa49fcf9c9439c3cbd97dac6eca171 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 9 Mar 2026 15:43:13 +0800
Subject: usb: roles: get usb role switch from parent only for usb-b-connector

usb_role_switch_is_parent() was walking up to the parent node and checking
for the "usb-role-switch" property regardless of the type of the passed
fwnode. This could cause unrelated device nodes to be probed as potential
role switch parent, leading to spurious matches and "-EPROBE_DEFER" being
returned infinitely.

Till now only Type-B connector node will have a parent node which may
present "usb-role-switch" property and register the role switch device.
For Type-C connector node, its parent node will always be a Type-C chip
device which will never register the role switch device. However, it may
still present a non-boolean "usb-role-switch = <&usb_controller>" property
for historical compatibility.

So restrict the helper to only operate on Type-B connector when attempting
to get the role switch from parent node.

Fixes: 6fadd72943b8 ("usb: roles: get usb-role-switch from parent")
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Tested-by: Arnaud Ferraris <arnaud.ferraris@collabora.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260309074313.2809867-3-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/roles/class.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index b8e28ceca51e..edec139b68b5 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -139,9 +139,14 @@ static void *usb_role_switch_match(const struct fwnode_handle *fwnode, const cha
 static struct usb_role_switch *
 usb_role_switch_is_parent(struct fwnode_handle *fwnode)
 {
-	struct fwnode_handle *parent = fwnode_get_parent(fwnode);
+	struct fwnode_handle *parent;
 	struct device *dev;
 
+	if (!fwnode_device_is_compatible(fwnode, "usb-b-connector"))
+		return NULL;
+
+	parent = fwnode_get_parent(fwnode);
+
 	if (!fwnode_property_present(parent, "usb-role-switch")) {
 		fwnode_handle_put(parent);
 		return NULL;
-- 
cgit v1.2.3


From 163cc462dea7d5b75be4db49ca78a2b99c55375e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 5 Mar 2026 16:17:28 +0100
Subject: gpib: lpvo_usb: fix unintended binding of FTDI 8U232AM devices

The LPVO USB GPIB adapter apparently uses an FTDI 8U232AM with the
default PID, but this device id is already handled by the ftdi_sio
serial driver.

Stop binding to the default PID to avoid breaking existing setups with
FTDI 8U232AM.

Anyone using this driver should blacklist the ftdi_sio driver and add
the device id manually through sysfs (e.g. using udev rules).

Fixes: fce79512a96a ("staging: gpib: Add LPVO DIY USB GPIB driver")
Fixes: e6ab504633e4 ("staging: gpib: Destage gpib")
Cc: Dave Penkler <dpenkler@gmail.com>
Cc: stable <stable@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260305151729.10501-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
index 6fc4e3452b88..ee781d2f0b8e 100644
--- a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
+++ b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
@@ -38,8 +38,10 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices");
 /*
  * Table of devices that work with this driver.
  *
- * Currently, only one device is known to be used in the
- * lpvo_usb_gpib adapter (FTDI 0403:6001).
+ * Currently, only one device is known to be used in the lpvo_usb_gpib
+ * adapter (FTDI 0403:6001) but as this device id is already handled by the
+ * ftdi_sio USB serial driver the LPVO driver must not bind to it by default.
+ *
  * If your adapter uses a different chip, insert a line
  * in the following table with proper <Vendor-id>, <Product-id>.
  *
@@ -50,7 +52,6 @@ MODULE_DESCRIPTION("GPIB driver for LPVO usb devices");
  */
 
 static const struct usb_device_id skel_table[] = {
-	{ USB_DEVICE(0x0403, 0x6001) },
 	{ }					   /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, skel_table);
-- 
cgit v1.2.3


From 0073a17b466684413ac87cf8ff6c19560db44e7a Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 9 Mar 2026 23:53:24 +0100
Subject: gpu: nova-core: gsp: fix UB in DmaGspMem pointer accessors

The DmaGspMem pointer accessor methods (gsp_write_ptr, gsp_read_ptr,
cpu_read_ptr, cpu_write_ptr, advance_cpu_read_ptr,
advance_cpu_write_ptr) dereference a raw pointer to DMA memory, creating
an intermediate reference before calling volatile read/write methods.

This is undefined behavior since DMA memory can be concurrently modified
by the device.

Fix this by moving the implementations into a gsp_mem module in fw.rs
that uses the dma_read!() / dma_write!() macros, making the original
methods on DmaGspMem thin forwarding wrappers.

An alternative approach would have been to wrap the shared memory in
Opaque, but that would have required even more unsafe code.

Since the gsp_mem module lives in fw.rs (to access firmware-specific
binding field names), GspMem, Msgq and their relevant fields are
temporarily widened to pub(super). This will be reverted once IoView
projections are available.

Cc: Gary Guo <gary@garyguo.net>
Closes: https://lore.kernel.org/nouveau/DGUT14ILG35P.1UMNRKU93JUM1@kernel.org/
Fixes: 75f6b1de8133 ("gpu: nova-core: gsp: Add GSP command queue bindings and handling")
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://patch.msgid.link/20260309225408.27714-1-dakr@kernel.org
[ Use pub(super) where possible; replace bitwise-and with modulo
  operator analogous to [1]. - Danilo ]
Link: https://lore.kernel.org/all/20260129-nova-core-cmdq1-v3-1-2ede85493a27@nvidia.com/ [1]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/gsp/cmdq.rs |  71 ++++++---------------------
 drivers/gpu/nova-core/gsp/fw.rs   | 101 ++++++++++++++++++++++++++------------
 2 files changed, 84 insertions(+), 88 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 9c5efd2daf45..03a4f3599849 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -2,11 +2,7 @@
 
 use core::{
     cmp,
-    mem,
-    sync::atomic::{
-        fence,
-        Ordering, //
-    }, //
+    mem, //
 };
 
 use kernel::{
@@ -146,30 +142,32 @@ static_assert!(align_of::<MsgqData>() == GSP_PAGE_SIZE);
 #[repr(C)]
 // There is no struct defined for this in the open-gpu-kernel-source headers.
 // Instead it is defined by code in `GspMsgQueuesInit()`.
-struct Msgq {
+// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module.
+pub(super) struct Msgq {
     /// Header for sending messages, including the write pointer.
-    tx: MsgqTxHeader,
+    pub(super) tx: MsgqTxHeader,
     /// Header for receiving messages, including the read pointer.
-    rx: MsgqRxHeader,
+    pub(super) rx: MsgqRxHeader,
     /// The message queue proper.
     msgq: MsgqData,
 }
 
 /// Structure shared between the driver and the GSP and containing the command and message queues.
 #[repr(C)]
-struct GspMem {
+// TODO: Revert to private once `IoView` projections replace the `gsp_mem` module.
+pub(super) struct GspMem {
     /// Self-mapping page table entries.
     ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>,
     /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the
     /// write and read pointers that the CPU updates.
     ///
     /// This member is read-only for the GSP.
-    cpuq: Msgq,
+    pub(super) cpuq: Msgq,
     /// GSP queue: the GSP writes messages here, and the driver reads them. It also contains the
     /// write and read pointers that the GSP updates.
     ///
     /// This member is read-only for the driver.
-    gspq: Msgq,
+    pub(super) gspq: Msgq,
 }
 
 impl GspMem {
@@ -331,12 +329,7 @@ impl DmaGspMem {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn gsp_write_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).gspq.tx.write_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::gsp_write_ptr(&self.0)
     }
 
     // Returns the index of the memory page the GSP will read the next command from.
@@ -345,12 +338,7 @@ impl DmaGspMem {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn gsp_read_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).gspq.rx.read_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::gsp_read_ptr(&self.0)
     }
 
     // Returns the index of the memory page the CPU can read the next message from.
@@ -359,27 +347,12 @@ impl DmaGspMem {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn cpu_read_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The ['CoherentAllocation'] contains at least one object.
-        //  - By the invariants of CoherentAllocation the pointer is valid.
-        (unsafe { (*gsp_mem).cpuq.rx.read_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::cpu_read_ptr(&self.0)
     }
 
     // Informs the GSP that it can send `elem_count` new pages into the message queue.
     fn advance_cpu_read_ptr(&mut self, elem_count: u32) {
-        let rptr = self.cpu_read_ptr().wrapping_add(elem_count) % MSGQ_NUM_PAGES;
-
-        // Ensure read pointer is properly ordered.
-        fence(Ordering::SeqCst);
-
-        let gsp_mem = self.0.start_ptr_mut();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        unsafe { (*gsp_mem).cpuq.rx.set_read_ptr(rptr) };
+        super::fw::gsp_mem::advance_cpu_read_ptr(&self.0, elem_count)
     }
 
     // Returns the index of the memory page the CPU can write the next command to.
@@ -388,26 +361,12 @@ impl DmaGspMem {
     //
     // - The returned value is between `0` and `MSGQ_NUM_PAGES`.
     fn cpu_write_ptr(&self) -> u32 {
-        let gsp_mem = self.0.start_ptr();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        (unsafe { (*gsp_mem).cpuq.tx.write_ptr() } % MSGQ_NUM_PAGES)
+        super::fw::gsp_mem::cpu_write_ptr(&self.0)
     }
 
     // Informs the GSP that it can process `elem_count` new pages from the command queue.
     fn advance_cpu_write_ptr(&mut self, elem_count: u32) {
-        let wptr = self.cpu_write_ptr().wrapping_add(elem_count) & MSGQ_NUM_PAGES;
-        let gsp_mem = self.0.start_ptr_mut();
-
-        // SAFETY:
-        //  - The 'CoherentAllocation' contains at least one object.
-        //  - By the invariants of `CoherentAllocation` the pointer is valid.
-        unsafe { (*gsp_mem).cpuq.tx.set_write_ptr(wptr) };
-
-        // Ensure all command data is visible before triggering the GSP read.
-        fence(Ordering::SeqCst);
+        super::fw::gsp_mem::advance_cpu_write_ptr(&self.0, elem_count)
     }
 }
 
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index 83ff91614e36..040b30ec3089 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -40,6 +40,75 @@ use crate::{
     },
 };
 
+// TODO: Replace with `IoView` projections once available; the `unwrap()` calls go away once we
+// switch to the new `dma::Coherent` API.
+pub(super) mod gsp_mem {
+    use core::sync::atomic::{
+        fence,
+        Ordering, //
+    };
+
+    use kernel::{
+        dma::CoherentAllocation,
+        dma_read,
+        dma_write,
+        prelude::*, //
+    };
+
+    use crate::gsp::cmdq::{
+        GspMem,
+        MSGQ_NUM_PAGES, //
+    };
+
+    pub(in crate::gsp) fn gsp_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn gsp_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.gspq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn cpu_read_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.rx.0.readPtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn advance_cpu_read_ptr(qs: &CoherentAllocation<GspMem>, count: u32) {
+        let rptr = cpu_read_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
+
+        // Ensure read pointer is properly ordered.
+        fence(Ordering::SeqCst);
+
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result {
+            dma_write!(qs, [0]?.cpuq.rx.0.readPtr, rptr);
+            Ok(())
+        }()
+        .unwrap()
+    }
+
+    pub(in crate::gsp) fn cpu_write_ptr(qs: &CoherentAllocation<GspMem>) -> u32 {
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result<u32> { Ok(dma_read!(qs, [0]?.cpuq.tx.0.writePtr) % MSGQ_NUM_PAGES) }().unwrap()
+    }
+
+    pub(in crate::gsp) fn advance_cpu_write_ptr(qs: &CoherentAllocation<GspMem>, count: u32) {
+        let wptr = cpu_write_ptr(qs).wrapping_add(count) % MSGQ_NUM_PAGES;
+
+        // PANIC: A `dma::CoherentAllocation` always contains at least one element.
+        || -> Result {
+            dma_write!(qs, [0]?.cpuq.tx.0.writePtr, wptr);
+            Ok(())
+        }()
+        .unwrap();
+
+        // Ensure all command data is visible before triggering the GSP read.
+        fence(Ordering::SeqCst);
+    }
+}
+
 /// Empty type to group methods related to heap parameters for running the GSP firmware.
 enum GspFwHeapParams {}
 
@@ -708,22 +777,6 @@ impl MsgqTxHeader {
             entryOff: num::usize_into_u32::<GSP_PAGE_SIZE>(),
         })
     }
-
-    /// Returns the value of the write pointer for this queue.
-    pub(crate) fn write_ptr(&self) -> u32 {
-        let ptr = core::ptr::from_ref(&self.0.writePtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.read_volatile() }
-    }
-
-    /// Sets the value of the write pointer for this queue.
-    pub(crate) fn set_write_ptr(&mut self, val: u32) {
-        let ptr = core::ptr::from_mut(&mut self.0.writePtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.write_volatile(val) }
-    }
 }
 
 // SAFETY: Padding is explicit and does not contain uninitialized data.
@@ -739,22 +792,6 @@ impl MsgqRxHeader {
     pub(crate) fn new() -> Self {
         Self(Default::default())
     }
-
-    /// Returns the value of the read pointer for this queue.
-    pub(crate) fn read_ptr(&self) -> u32 {
-        let ptr = core::ptr::from_ref(&self.0.readPtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.read_volatile() }
-    }
-
-    /// Sets the value of the read pointer for this queue.
-    pub(crate) fn set_read_ptr(&mut self, val: u32) {
-        let ptr = core::ptr::from_mut(&mut self.0.readPtr);
-
-        // SAFETY: `ptr` is a valid pointer to a `u32`.
-        unsafe { ptr.write_volatile(val) }
-    }
 }
 
 // SAFETY: Padding is explicit and does not contain uninitialized data.
-- 
cgit v1.2.3


From db9a26765010c55712d8cff32ea9d99732407c55 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Feb 2026 17:24:43 +0100
Subject: dt-bindings: mtd: st,spear600-smi: Fix description

The description mixes two nodes. There is the controller, and there is
the flash. Describe the flash (which itself can be considered an mtd
device, unlike the top level controller), and move the st,smi-fast-mode
property inside, as this property is flash specific and should not live
in the parent controller node.

Fixes: 68cd8ef48452 ("dt-bindings: mtd: st,spear600-smi: convert to DT schema")
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 .../devicetree/bindings/mtd/st,spear600-smi.yaml   | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
index 8fe27aae7527..d065df269657 100644
--- a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
+++ b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
@@ -19,9 +19,6 @@ description:
   Flash sub nodes describe the memory range and optional per-flash
   properties.
 
-allOf:
-  - $ref: mtd.yaml#
-
 properties:
   compatible:
     const: st,spear600-smi
@@ -42,9 +39,22 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     description: Functional clock rate of the SMI controller in Hz.
 
-  st,smi-fast-mode:
-    type: boolean
-    description: Indicates that the attached flash supports fast read mode.
+patternProperties:
+  "^flash@.*$":
+    $ref: /schemas/mtd/mtd.yaml#
+
+    properties:
+      reg:
+        maxItems: 1
+
+      st,smi-fast-mode:
+        type: boolean
+        description: Indicates that the attached flash supports fast read mode.
+
+    unevaluatedProperties: false
+
+    required:
+      - reg
 
 required:
   - compatible
-- 
cgit v1.2.3


From c21cac8cdcdcb7940c0aab85246ffbb649b73937 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Feb 2026 17:24:44 +0100
Subject: dt-bindings: mtd: st,spear600-smi: #address/size-cells is mandatory

These properties must be set because they overwrite the default values,
especially #size-cells which is 0 for most controllers and is 'const: 1'
here.

Fixes: 68cd8ef48452 ("dt-bindings: mtd: st,spear600-smi: convert to DT schema")
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
index d065df269657..62d4359908f2 100644
--- a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
+++ b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
@@ -60,6 +60,8 @@ required:
   - compatible
   - reg
   - clock-rate
+  - "#address-cells"
+  - "#size-cells"
 
 unevaluatedProperties: false
 
-- 
cgit v1.2.3


From 073b2db72426adee591a0f5a967009ea459ef688 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Feb 2026 17:24:45 +0100
Subject: dt-bindings: mtd: st,spear600-smi: Fix example

Example is wrong, the reg property of the flash is always matching the
node name.

Fixes: 68cd8ef48452 ("dt-bindings: mtd: st,spear600-smi: convert to DT schema")
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
index 62d4359908f2..e7385d906591 100644
--- a/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
+++ b/Documentation/devicetree/bindings/mtd/st,spear600-smi.yaml
@@ -76,7 +76,7 @@ examples:
         interrupts = <12>;
         clock-rate = <50000000>;  /* 50 MHz */
 
-        flash@f8000000 {
+        flash@fc000000 {
             reg = <0xfc000000 0x1000>;
             st,smi-fast-mode;
         };
-- 
cgit v1.2.3


From a9683730e8b1d632674f81844ed03ddfbe4821c0 Mon Sep 17 00:00:00 2001
From: Casey Connolly <casey.connolly@linaro.org>
Date: Fri, 6 Mar 2026 18:47:07 +0100
Subject: ASoC: detect empty DMI strings

Some bootloaders like recent versions of U-Boot may install some DMI
properties with empty values rather than not populate them. This manages
to make its way through the validator and cleanup resulting in a rogue
hyphen being appended to the card longname.

Fixes: 4e01e5dbba96 ("ASoC: improve the DMI long card code in asoc-core")
Signed-off-by: Casey Connolly <casey.connolly@linaro.org>
Link: https://patch.msgid.link/20260306174707.283071-2-casey.connolly@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index cf826c2a8b59..573693e21780 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1863,12 +1863,15 @@ static void cleanup_dmi_name(char *name)
 
 /*
  * Check if a DMI field is valid, i.e. not containing any string
- * in the black list.
+ * in the black list and not the empty string.
  */
 static int is_dmi_valid(const char *field)
 {
 	int i = 0;
 
+	if (!field[0])
+		return 0;
+
 	while (dmi_blacklist[i]) {
 		if (strstr(field, dmi_blacklist[i]))
 			return 0;
-- 
cgit v1.2.3


From bab2bc6e850a697a23b9e5f0e21bb8c187615e95 Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Thu, 5 Mar 2026 14:49:06 -0500
Subject: mtd: rawnand: serialize lock/unlock against other NAND operations

nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area
without holding the NAND device lock. On controllers that implement
SET_FEATURES via multiple low-level PIO commands, these can race with
concurrent UBI/UBIFS background erase/write operations that hold the
device lock, resulting in cmd_pending conflicts on the NAND controller.

Add nand_get_device()/nand_release_device() around the lock/unlock
operations to serialize them against all other NAND controller access.

Fixes: 92270086b7e5 ("mtd: rawnand: Add support for manufacturer specific lock/unlock operation")
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Reviewed-by: William Zhang <william.zhang@broadcom.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 38429363251c..dfd8361bdd36 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4737,11 +4737,16 @@ static void nand_shutdown(struct mtd_info *mtd)
 static int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
+	int ret;
 
 	if (!chip->ops.lock_area)
 		return -ENOTSUPP;
 
-	return chip->ops.lock_area(chip, ofs, len);
+	nand_get_device(chip);
+	ret = chip->ops.lock_area(chip, ofs, len);
+	nand_release_device(chip);
+
+	return ret;
 }
 
 /**
@@ -4753,11 +4758,16 @@ static int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 static int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
+	int ret;
 
 	if (!chip->ops.unlock_area)
 		return -ENOTSUPP;
 
-	return chip->ops.unlock_area(chip, ofs, len);
+	nand_get_device(chip);
+	ret = chip->ops.unlock_area(chip, ofs, len);
+	nand_release_device(chip);
+
+	return ret;
 }
 
 /* Set default functions */
-- 
cgit v1.2.3


From da9ba4dcc01e7cf52b7676f0ee9607b8358c2171 Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Thu, 5 Mar 2026 15:21:57 -0500
Subject: mtd: rawnand: brcmnand: skip DMA during panic write

When oops_panic_write is set, the driver disables interrupts and
switches to PIO polling mode but still falls through into the DMA
path. DMA cannot be used reliably in panic context, so make the
DMA path an else branch to ensure only PIO is used during panic
writes.

Fixes: c1ac2dc34b51 ("mtd: rawnand: brcmnand: When oops in progress use pio and interrupt polling")
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Reviewed-by: William Zhang <william.zhang@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/brcmnand/brcmnand.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 0427d76f45d0..5b9dadd5405e 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2350,14 +2350,12 @@ static int brcmnand_write(struct mtd_info *mtd, struct nand_chip *chip,
 	for (i = 0; i < ctrl->max_oob; i += 4)
 		oob_reg_write(ctrl, i, 0xffffffff);
 
-	if (mtd->oops_panic_write)
+	if (mtd->oops_panic_write) {
 		/* switch to interrupt polling and PIO mode */
 		disable_ctrl_irqs(ctrl);
-
-	if (use_dma(ctrl) && (has_edu(ctrl) || !oob) && flash_dma_buf_ok(buf)) {
+	} else if (use_dma(ctrl) && (has_edu(ctrl) || !oob) && flash_dma_buf_ok(buf)) {
 		if (ctrl->dma_trans(host, addr, (u32 *)buf, oob, mtd->writesize,
 				    CMD_PROGRAM_PAGE))
-
 			ret = -EIO;
 
 		goto out;
-- 
cgit v1.2.3


From edd20cb693d9cb5e3d6fcecd858093dab4e2b0aa Mon Sep 17 00:00:00 2001
From: Wei Liu <wei.liu@kernel.org>
Date: Wed, 11 Mar 2026 16:51:00 +0000
Subject: Revert "mshv: expose the scrub partition hypercall"

This reverts commit 36d6cbb62133fc6eea28f380409e0fb190f3dfbe.

Calling this as a passthrough hypercall leaves the VM in an inconsistent
state. Revert before it is released.

Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_root_main.c | 1 -
 include/hyperv/hvgdk_mini.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 54c3e44d24ee..9d1b881764ed 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -120,7 +120,6 @@ static u16 mshv_passthru_hvcalls[] = {
 	HVCALL_SET_VP_REGISTERS,
 	HVCALL_TRANSLATE_VIRTUAL_ADDRESS,
 	HVCALL_CLEAR_VIRTUAL_INTERRUPT,
-	HVCALL_SCRUB_PARTITION,
 	HVCALL_REGISTER_INTERCEPT_RESULT,
 	HVCALL_ASSERT_VIRTUAL_INTERRUPT,
 	HVCALL_GET_GPA_PAGES_ACCESS_STATES,
diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 8bb3dd71c5b4..1823a290a7b7 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/include/hyperv/hvgdk_mini.h
@@ -477,7 +477,6 @@ union hv_vp_assist_msr_contents {	 /* HV_REGISTER_VP_ASSIST_PAGE */
 #define HVCALL_NOTIFY_PARTITION_EVENT                   0x0087
 #define HVCALL_ENTER_SLEEP_STATE			0x0084
 #define HVCALL_NOTIFY_PORT_RING_EMPTY			0x008b
-#define HVCALL_SCRUB_PARTITION				0x008d
 #define HVCALL_REGISTER_INTERCEPT_RESULT		0x0091
 #define HVCALL_ASSERT_VIRTUAL_INTERRUPT			0x0094
 #define HVCALL_CREATE_PORT				0x0095
-- 
cgit v1.2.3


From 3fde5281b805370a6c3bd2ef462ebff70a0ea2c6 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 2 Mar 2026 17:45:31 +0100
Subject: x86/hyperv: Use __naked attribute to fix stackless C function

hv_crash_c_entry() is a C function that is entered without a stack,
and this is only allowed for functions that have the __naked attribute,
which informs the compiler that it must not emit the usual prologue and
epilogue or emit any other kind of instrumentation that relies on a
stack frame.

So split up the function, and set the __naked attribute on the initial
part that sets up the stack, GDT, IDT and other pieces that are needed
for ordinary C execution. Given that function calls are not permitted
either, use the existing long return coded in an asm() block to call the
second part of the function, which is an ordinary function that is
permitted to call other functions as usual.

Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com> # asm parts, not hv parts
Reviewed-by: Mukesh Rathor <mrathor@linux.microsoft.com>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: linux-hyperv@vger.kernel.org
Fixes: 94212d34618c ("x86/hyperv: Implement hypervisor RAM collection into vmcore")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/hyperv/hv_crash.c | 82 ++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 39 deletions(-)

diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c
index 92da1b4f2e73..fdb277bf73d8 100644
--- a/arch/x86/hyperv/hv_crash.c
+++ b/arch/x86/hyperv/hv_crash.c
@@ -107,14 +107,12 @@ static void __noreturn hv_panic_timeout_reboot(void)
 		cpu_relax();
 }
 
-/* This cannot be inlined as it needs stack */
-static noinline __noclone void hv_crash_restore_tss(void)
+static void hv_crash_restore_tss(void)
 {
 	load_TR_desc();
 }
 
-/* This cannot be inlined as it needs stack */
-static noinline void hv_crash_clear_kernpt(void)
+static void hv_crash_clear_kernpt(void)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -125,6 +123,25 @@ static noinline void hv_crash_clear_kernpt(void)
 	native_p4d_clear(p4d);
 }
 
+
+static void __noreturn hv_crash_handle(void)
+{
+	hv_crash_restore_tss();
+	hv_crash_clear_kernpt();
+
+	/* we are now fully in devirtualized normal kernel mode */
+	__crash_kexec(NULL);
+
+	hv_panic_timeout_reboot();
+}
+
+/*
+ * __naked functions do not permit function calls, not even to __always_inline
+ * functions that only contain asm() blocks themselves. So use a macro instead.
+ */
+#define hv_wrmsr(msr, val) \
+	asm volatile("wrmsr" :: "c"(msr), "a"((u32)val), "d"((u32)(val >> 32)) : "memory")
+
 /*
  * This is the C entry point from the asm glue code after the disable hypercall.
  * We enter here in IA32-e long mode, ie, full 64bit mode running on kernel
@@ -133,51 +150,38 @@ static noinline void hv_crash_clear_kernpt(void)
  * available. We restore kernel GDT, and rest of the context, and continue
  * to kexec.
  */
-static asmlinkage void __noreturn hv_crash_c_entry(void)
+static void __naked hv_crash_c_entry(void)
 {
-	struct hv_crash_ctxt *ctxt = &hv_crash_ctxt;
-
 	/* first thing, restore kernel gdt */
-	native_load_gdt(&ctxt->gdtr);
+	asm volatile("lgdt %0" : : "m" (hv_crash_ctxt.gdtr));
 
-	asm volatile("movw %%ax, %%ss" : : "a"(ctxt->ss));
-	asm volatile("movq %0, %%rsp" : : "m"(ctxt->rsp));
+	asm volatile("movw %0, %%ss\n\t"
+		     "movq %1, %%rsp"
+		     :: "m"(hv_crash_ctxt.ss), "m"(hv_crash_ctxt.rsp));
 
-	asm volatile("movw %%ax, %%ds" : : "a"(ctxt->ds));
-	asm volatile("movw %%ax, %%es" : : "a"(ctxt->es));
-	asm volatile("movw %%ax, %%fs" : : "a"(ctxt->fs));
-	asm volatile("movw %%ax, %%gs" : : "a"(ctxt->gs));
+	asm volatile("movw %0, %%ds" : : "m"(hv_crash_ctxt.ds));
+	asm volatile("movw %0, %%es" : : "m"(hv_crash_ctxt.es));
+	asm volatile("movw %0, %%fs" : : "m"(hv_crash_ctxt.fs));
+	asm volatile("movw %0, %%gs" : : "m"(hv_crash_ctxt.gs));
 
-	native_wrmsrq(MSR_IA32_CR_PAT, ctxt->pat);
-	asm volatile("movq %0, %%cr0" : : "r"(ctxt->cr0));
+	hv_wrmsr(MSR_IA32_CR_PAT, hv_crash_ctxt.pat);
+	asm volatile("movq %0, %%cr0" : : "r"(hv_crash_ctxt.cr0));
 
-	asm volatile("movq %0, %%cr8" : : "r"(ctxt->cr8));
-	asm volatile("movq %0, %%cr4" : : "r"(ctxt->cr4));
-	asm volatile("movq %0, %%cr2" : : "r"(ctxt->cr4));
+	asm volatile("movq %0, %%cr8" : : "r"(hv_crash_ctxt.cr8));
+	asm volatile("movq %0, %%cr4" : : "r"(hv_crash_ctxt.cr4));
+	asm volatile("movq %0, %%cr2" : : "r"(hv_crash_ctxt.cr2));
 
-	native_load_idt(&ctxt->idtr);
-	native_wrmsrq(MSR_GS_BASE, ctxt->gsbase);
-	native_wrmsrq(MSR_EFER, ctxt->efer);
+	asm volatile("lidt %0" : : "m" (hv_crash_ctxt.idtr));
+	hv_wrmsr(MSR_GS_BASE, hv_crash_ctxt.gsbase);
+	hv_wrmsr(MSR_EFER, hv_crash_ctxt.efer);
 
 	/* restore the original kernel CS now via far return */
-	asm volatile("movzwq %0, %%rax\n\t"
-		     "pushq %%rax\n\t"
-		     "pushq $1f\n\t"
-		     "lretq\n\t"
-		     "1:nop\n\t" : : "m"(ctxt->cs) : "rax");
-
-	/* We are in asmlinkage without stack frame, hence make C function
-	 * calls which will buy stack frames.
-	 */
-	hv_crash_restore_tss();
-	hv_crash_clear_kernpt();
-
-	/* we are now fully in devirtualized normal kernel mode */
-	__crash_kexec(NULL);
-
-	hv_panic_timeout_reboot();
+	asm volatile("pushq %q0\n\t"
+		     "pushq %q1\n\t"
+		     "lretq"
+		     :: "r"(hv_crash_ctxt.cs), "r"(hv_crash_handle));
 }
-/* Tell gcc we are using lretq long jump in the above function intentionally */
+/* Tell objtool we are using lretq long jump in the above function intentionally */
 STACK_FRAME_NON_STANDARD(hv_crash_c_entry);
 
 static void hv_mark_tss_not_busy(void)
-- 
cgit v1.2.3


From 464b1c115852fe025635ae2065e00caced184d92 Mon Sep 17 00:00:00 2001
From: Qing Wang <wangqing7171@gmail.com>
Date: Wed, 11 Mar 2026 17:36:17 +0800
Subject: slab: fix memory leak when refill_sheaf() fails

When refill_sheaf() partially fills one sheaf (e.g., fills 5 objects
but need to fill 10), it will update sheaf->size and return -ENOMEM.
However, the callers (alloc_full_sheaf() and __pcs_replace_empty_main())
directly call free_empty_sheaf() on failure, which only does kfree(sheaf),
causing the partially allocated objects memory in sheaf->objects[] leaked.

Fix this by calling sheaf_flush_unused() before free_empty_sheaf() to
free objects of sheaf->objects[]. And also add a WARN_ON() in
free_empty_sheaf() to catch any future cases where a non-empty sheaf is
being freed.

Fixes: ed30c4adfc2b ("slab: add optimized sheaf refill from partial list")
Signed-off-by: Qing Wang <wangqing7171@gmail.com>
Link: https://patch.msgid.link/20260311093617.4155965-1-wangqing7171@gmail.com
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Signed-off-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/slub.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index 6371838d2352..2b2d33cc735c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2790,6 +2790,7 @@ static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf)
 	if (s->flags & SLAB_KMALLOC)
 		mark_obj_codetag_empty(sheaf);
 
+	VM_WARN_ON_ONCE(sheaf->size > 0);
 	kfree(sheaf);
 
 	stat(s, SHEAF_FREE);
@@ -2821,6 +2822,7 @@ static int refill_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf,
 	return 0;
 }
 
+static void sheaf_flush_unused(struct kmem_cache *s, struct slab_sheaf *sheaf);
 
 static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 {
@@ -2830,6 +2832,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp)
 		return NULL;
 
 	if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
+		sheaf_flush_unused(s, sheaf);
 		free_empty_sheaf(s, sheaf);
 		return NULL;
 	}
@@ -4616,6 +4619,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 			 * we must be very low on memory so don't bother
 			 * with the barn
 			 */
+			sheaf_flush_unused(s, empty);
 			free_empty_sheaf(s, empty);
 		}
 	} else {
-- 
cgit v1.2.3


From cf534a09fb621b0aa875613e3cd88aee336e16d7 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Tue, 3 Mar 2026 09:51:58 +1300
Subject: KVM: selftests: Increase 'maxnode' for guest_memfd tests

Increase 'maxnode' when using 'get_mempolicy' syscall in guest_memfd
mmap and NUMA policy tests to fix a failure on one Intel GNR platform.

On a CXL-capable platform, the memory affinity of CXL memory regions may
not be covered by the SRAT.  Since each CXL memory region is enumerated
via a CFMWS table, at early boot the kernel parses all CFMWS tables to
detect all CXL memory regions and assigns a 'faked' NUMA node for each
of them, starting from the highest NUMA node ID enumerated via the SRAT.

This increases the 'nr_node_ids'.  E.g., on the aforementioned Intel GNR
platform which has 4 NUMA nodes and 18 CFMWS tables, it increases to 22.

This results in the 'get_mempolicy' syscall failure on that platform,
because currently 'maxnode' is hard-coded to 8 but the 'get_mempolicy'
syscall requires the 'maxnode' to be not smaller than the 'nr_node_ids'.

Increase the 'maxnode' to the number of bits of 'nodemask', which is
'unsigned long', to fix this.

This may not cover all systems.  Perhaps a better way is to always set
the 'nodemask' and 'maxnode' based on the actual maximum NUMA node ID on
the system, but for now just do the simple way.

Reported-by: Yi Lai <yi1.lai@intel.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221014
Closes: https://lore.kernel.org/all/bug-221014-28872@https.bugzilla.kernel.org%2F
Signed-off-by: Kai Huang <kai.huang@intel.com>
Reviewed-by: Yuan Yao <yaoyuan@linux.alibaba.com>
Link: https://patch.msgid.link/20260302205158.178058-1-kai.huang@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/guest_memfd_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index 618c937f3c90..cc329b57ce2e 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -80,7 +80,7 @@ static void test_mbind(int fd, size_t total_size)
 {
 	const unsigned long nodemask_0 = 1; /* nid: 0 */
 	unsigned long nodemask = 0;
-	unsigned long maxnode = 8;
+	unsigned long maxnode = BITS_PER_TYPE(nodemask);
 	int policy;
 	char *mem;
 	int ret;
-- 
cgit v1.2.3


From 4c0134639694fcdc4ab041d7c53d6188a3e18040 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Mar 2026 11:03:38 -0800
Subject: KVM: PPC: e500: Fix build error due to using kmalloc_obj() with wrong
 type

Fix a build error in kvmppc_e500_tlb_init() that was introduced by the
conversion to use kzalloc_objs(), as KVM confusingly uses the size of the
structure that is one and only field in tlbe_priv:

  arch/powerpc/kvm/e500_mmu.c:923:33: error: assignment to 'struct tlbe_priv *'
    from incompatible pointer type 'struct tlbe_ref *' [-Wincompatible-pointer-types]
  923 |         vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref,
      |                                 ^

KVM has been flawed since commit 0164c0f0c404 ("KVM: PPC: e500: clear up
confusion between host and guest entries"), but the issue went unnoticed
until kmalloc_obj() came along and enforced types, as "struct tlbe_priv"
was just a wrapper of "struct tlbe_ref" (why on earth the two ever existed
separately...).

Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types")
Cc: Kees Cook <kees@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Link: https://patch.msgid.link/20260303190339.974325-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/e500_mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 48580c85f23b..75ed1496ead5 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -920,12 +920,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
 
-	vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_ref,
+	vcpu_e500->gtlb_priv[0] = kzalloc_objs(struct tlbe_priv,
 					       vcpu_e500->gtlb_params[0].entries);
 	if (!vcpu_e500->gtlb_priv[0])
 		goto free_vcpu;
 
-	vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_ref,
+	vcpu_e500->gtlb_priv[1] = kzalloc_objs(struct tlbe_priv,
 					       vcpu_e500->gtlb_params[1].entries);
 	if (!vcpu_e500->gtlb_priv[1])
 		goto free_vcpu;
-- 
cgit v1.2.3


From fe2a08eca5caa77398bfa321bd321d087b0b44b0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Mar 2026 11:03:39 -0800
Subject: KVM: PPC: e500: Rip out "struct tlbe_ref"

Complete the ~13 year journey started by commit 47bf379742bf
("kvm/ppc/e500: eliminate tlb_refs"), and actually remove "struct
tlbe_ref".

No functional change intended (verified disassembly of e500_mmu.o and
e500_mmu_host.o is identical before and after).

Link: https://patch.msgid.link/20260303190339.974325-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/e500.h          |  6 +--
 arch/powerpc/kvm/e500_mmu_host.c | 91 +++++++++++++++++++---------------------
 2 files changed, 45 insertions(+), 52 deletions(-)

diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index f9acf866c709..e4469ad73a2e 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -39,15 +39,11 @@ enum vcpu_ftr {
 /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */
 #define E500_TLB_MAS2_ATTR	(0x7f)
 
-struct tlbe_ref {
+struct tlbe_priv {
 	kvm_pfn_t pfn;		/* valid only for TLB0, except briefly */
 	unsigned int flags;	/* E500_TLB_* */
 };
 
-struct tlbe_priv {
-	struct tlbe_ref ref;
-};
-
 #ifdef CONFIG_KVM_E500V2
 struct vcpu_id_table;
 #endif
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 06caf8bbbe2b..37e0d3d9e244 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -189,16 +189,16 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe =
 		get_entry(vcpu_e500, tlbsel, esel);
-	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
+	struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
 	/* Don't bother with unmapped entries */
-	if (!(ref->flags & E500_TLB_VALID)) {
-		WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
-		     "%s: flags %x\n", __func__, ref->flags);
+	if (!(tlbe->flags & E500_TLB_VALID)) {
+		WARN(tlbe->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+		     "%s: flags %x\n", __func__, tlbe->flags);
 		WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
 	}
 
-	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
+	if (tlbsel == 1 && tlbe->flags & E500_TLB_BITMAP) {
 		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
 		int hw_tlb_indx;
 		unsigned long flags;
@@ -216,28 +216,28 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 		}
 		mb();
 		vcpu_e500->g2h_tlb1_map[esel] = 0;
-		ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
+		tlbe->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
 		local_irq_restore(flags);
 	}
 
-	if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) {
+	if (tlbsel == 1 && tlbe->flags & E500_TLB_TLB0) {
 		/*
 		 * TLB1 entry is backed by 4k pages. This should happen
 		 * rarely and is not worth optimizing. Invalidate everything.
 		 */
 		kvmppc_e500_tlbil_all(vcpu_e500);
-		ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
+		tlbe->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
 	}
 
 	/*
 	 * If TLB entry is still valid then it's a TLB0 entry, and thus
 	 * backed by at most one host tlbe per shadow pid
 	 */
-	if (ref->flags & E500_TLB_VALID)
+	if (tlbe->flags & E500_TLB_VALID)
 		kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
 
 	/* Mark the TLB as not backed by the host anymore */
-	ref->flags = 0;
+	tlbe->flags = 0;
 }
 
 static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
@@ -245,26 +245,26 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
 }
 
-static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
-					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 kvm_pfn_t pfn, unsigned int wimg,
-					 bool writable)
+static inline void kvmppc_e500_tlbe_setup(struct tlbe_priv *tlbe,
+					  struct kvm_book3e_206_tlb_entry *gtlbe,
+					  kvm_pfn_t pfn, unsigned int wimg,
+					  bool writable)
 {
-	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
+	tlbe->pfn = pfn;
+	tlbe->flags = E500_TLB_VALID;
 	if (writable)
-		ref->flags |= E500_TLB_WRITABLE;
+		tlbe->flags |= E500_TLB_WRITABLE;
 
 	/* Use guest supplied MAS2_G and MAS2_E */
-	ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
+	tlbe->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg;
 }
 
-static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
+static inline void kvmppc_e500_tlbe_release(struct tlbe_priv *tlbe)
 {
-	if (ref->flags & E500_TLB_VALID) {
+	if (tlbe->flags & E500_TLB_VALID) {
 		/* FIXME: don't log bogus pfn for TLB1 */
-		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
-		ref->flags = 0;
+		trace_kvm_booke206_ref_release(tlbe->pfn, tlbe->flags);
+		tlbe->flags = 0;
 	}
 }
 
@@ -284,11 +284,8 @@ static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int i;
 
 	for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
-		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-			struct tlbe_ref *ref =
-				&vcpu_e500->gtlb_priv[tlbsel][i].ref;
-			kvmppc_e500_ref_release(ref);
-		}
+		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++)
+			kvmppc_e500_tlbe_release(&vcpu_e500->gtlb_priv[tlbsel][i]);
 	}
 }
 
@@ -304,18 +301,18 @@ void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
 static void kvmppc_e500_setup_stlbe(
 	struct kvm_vcpu *vcpu,
 	struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tsize, struct tlbe_ref *ref, u64 gvaddr,
+	int tsize, struct tlbe_priv *tlbe, u64 gvaddr,
 	struct kvm_book3e_206_tlb_entry *stlbe)
 {
-	kvm_pfn_t pfn = ref->pfn;
+	kvm_pfn_t pfn = tlbe->pfn;
 	u32 pr = vcpu->arch.shared->msr & MSR_PR;
-	bool writable = !!(ref->flags & E500_TLB_WRITABLE);
+	bool writable = !!(tlbe->flags & E500_TLB_WRITABLE);
 
-	BUG_ON(!(ref->flags & E500_TLB_VALID));
+	BUG_ON(!(tlbe->flags & E500_TLB_VALID));
 
 	/* Force IPROT=0 for all guest mappings. */
 	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
+	stlbe->mas2 = (gvaddr & MAS2_EPN) | (tlbe->flags & E500_TLB_MAS2_ATTR);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
 			e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr);
 }
@@ -323,7 +320,7 @@ static void kvmppc_e500_setup_stlbe(
 static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
-	struct tlbe_ref *ref)
+	struct tlbe_priv *tlbe)
 {
 	struct kvm_memory_slot *slot;
 	unsigned int psize;
@@ -455,9 +452,9 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		}
 	}
 
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable);
+	kvmppc_e500_tlbe_setup(tlbe, gtlbe, pfn, wimg, writable);
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
-				ref, gvaddr, stlbe);
+				tlbe, gvaddr, stlbe);
 	writable = tlbe_is_writable(stlbe);
 
 	/* Clear i-cache for new pages */
@@ -474,17 +471,17 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
 				struct kvm_book3e_206_tlb_entry *stlbe)
 {
 	struct kvm_book3e_206_tlb_entry *gtlbe;
-	struct tlbe_ref *ref;
+	struct tlbe_priv *tlbe;
 	int stlbsel = 0;
 	int sesel = 0;
 	int r;
 
 	gtlbe = get_entry(vcpu_e500, 0, esel);
-	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
+	tlbe = &vcpu_e500->gtlb_priv[0][esel];
 
 	r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
 			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-			gtlbe, 0, stlbe, ref);
+			gtlbe, 0, stlbe, tlbe);
 	if (r)
 		return r;
 
@@ -494,7 +491,7 @@ static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
 }
 
 static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
-				     struct tlbe_ref *ref,
+				     struct tlbe_priv *tlbe,
 				     int esel)
 {
 	unsigned int sesel = vcpu_e500->host_tlb1_nv++;
@@ -507,10 +504,10 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
 		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
 	}
 
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_BITMAP;
 	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
 	vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
-	WARN_ON(!(ref->flags & E500_TLB_VALID));
+	WARN_ON(!(tlbe->flags & E500_TLB_VALID));
 
 	return sesel;
 }
@@ -522,24 +519,24 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
-	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
+	struct tlbe_priv *tlbe = &vcpu_e500->gtlb_priv[1][esel];
 	int sesel;
 	int r;
 
 	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
-				   ref);
+				   tlbe);
 	if (r)
 		return r;
 
 	/* Use TLB0 when we can only map a page with 4k */
 	if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) {
-		vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0;
+		vcpu_e500->gtlb_priv[1][esel].flags |= E500_TLB_TLB0;
 		write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0);
 		return 0;
 	}
 
 	/* Otherwise map into TLB1 */
-	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, tlbe, esel);
 	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
 
 	return 0;
@@ -561,11 +558,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
 		/* Triggers after clear_tlb_privs or on initial mapping */
-		if (!(priv->ref.flags & E500_TLB_VALID)) {
+		if (!(priv->flags & E500_TLB_VALID)) {
 			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
 		} else {
 			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
-						&priv->ref, eaddr, &stlbe);
+						priv, eaddr, &stlbe);
 			write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0);
 		}
 		break;
-- 
cgit v1.2.3


From 4b3b8a8b0df1a5e7a1af04ff512df2c80db35dc8 Mon Sep 17 00:00:00 2001
From: Carlos López <clopez@suse.de>
Date: Mon, 9 Feb 2026 16:31:09 +0100
Subject: KVM: x86: synthesize CPUID bits only if CPU capability is set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

KVM incorrectly synthesizes CPUID bits for KVM-only leaves, as the
following branch in kvm_cpu_cap_init() is never taken:

    if (leaf < NCAPINTS)
        kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf];

This means that bits set via SYNTHESIZED_F() for KVM-only leaves are
unconditionally set. This for example can cause issues for SEV-SNP
guests running on Family 19h CPUs, as TSA_SQ_NO and TSA_L1_NO are
always enabled by KVM in 80000021[ECX]. When userspace issues a
SNP_LAUNCH_UPDATE command to update the CPUID page for the guest, SNP
firmware will explicitly reject the command if the page sets sets these
bits on vulnerable CPUs.

To fix this, check in SYNTHESIZED_F() that the corresponding X86
capability is set before adding it to to kvm_cpu_cap_features.

Fixes: 31272abd5974 ("KVM: SVM: Advertise TSA CPUID bits to guests")
Link: https://lore.kernel.org/all/20260208164233.30405-1-clopez@suse.de/
Signed-off-by: Carlos López <clopez@suse.de>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Link: https://patch.msgid.link/20260209153108.70667-2-clopez@suse.de
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index d2486506a808..8137927e7387 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -776,7 +776,10 @@ do {									\
 #define SYNTHESIZED_F(name)					\
 ({								\
 	kvm_cpu_cap_synthesized |= feature_bit(name);		\
-	F(name);						\
+								\
+	BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES);	\
+	if (boot_cpu_has(X86_FEATURE_##name))			\
+		F(name);					\
 })
 
 /*
-- 
cgit v1.2.3


From a5264387c2ee42fca92ac792199008fc60ee82f1 Mon Sep 17 00:00:00 2001
From: Manuel Andreas <manuel.andreas@tum.de>
Date: Thu, 19 Feb 2026 21:05:49 +0100
Subject: KVM: x86: hyper-v: Validate all GVAs during PV TLB flush

In KVM guests with Hyper-V hypercalls enabled, the hypercalls
HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST and HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX
allow a guest to request invalidation of portions of a virtual TLB.
For this, the hypercall parameter includes a list of GVAs that are supposed
to be invalidated.

Currently, only the base GVA is checked to be canonical. In reality, this
check needs to be performed for the entire range of GVAs, as checking only
the base GVA enables guests running on Intel hardware to trigger a
WARN_ONCE in the host (see Fixes commit below).

Move the check for non-canonical addresses to be performed for every GVA
of the supplied range to avoid the splat, and to be more in line with the
Hyper-V specification, since, although unlikely, a range starting with an
invalid GVA may still contain GVAs that are valid.

Fixes: fa787ac07b3c ("KVM: x86/hyper-v: Skip non-canonical addresses during PV TLB flush")
Signed-off-by: Manuel Andreas <manuel.andreas@tum.de>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://patch.msgid.link/00a7a31b-573b-4d92-91f8-7d7e2f88ea48@tum.de
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 30202942289a..9b140bbdc1d8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1981,16 +1981,17 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
-		if (is_noncanonical_invlpg_address(entries[i], vcpu))
-			continue;
-
 		/*
 		 * Lower 12 bits of 'address' encode the number of additional
 		 * pages to flush.
 		 */
 		gva = entries[i] & PAGE_MASK;
-		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++)
+		for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) {
+			if (is_noncanonical_invlpg_address(gva + j * PAGE_SIZE, vcpu))
+				continue;
+
 			kvm_x86_call(flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+		}
 
 		++vcpu->stat.tlb_flush;
 	}
-- 
cgit v1.2.3


From f78e627a01bd4ec0219566d2c9c40f3c3614f875 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 20 Feb 2026 14:02:16 -0800
Subject: KVM: VMX: Fix a wrong MSR update in add_atomic_switch_msr()

The previous change had a bug to update a guest MSR with a host value.

Fixes: c3d6a7210a4de9096 ("KVM: VMX: Dedup code for adding MSR to VMCS's auto list")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20260220220216.389475-1-namhyung@kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 967b58a8ab9d..83d057cfa816 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1149,7 +1149,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	}
 
 	vmx_add_auto_msr(&m->guest, msr, guest_val, VM_ENTRY_MSR_LOAD_COUNT, kvm);
-	vmx_add_auto_msr(&m->guest, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm);
+	vmx_add_auto_msr(&m->host, msr, host_val, VM_EXIT_MSR_LOAD_COUNT, kvm);
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx)
-- 
cgit v1.2.3


From b54e4707a64be93a8ab3348e32e89817229b5eaa Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 4 Feb 2026 04:12:06 -0500
Subject: KVM: x86: Fix SRCU list traversal in kvm_fire_mask_notifiers()

The mask_notifier_list is protected by kvm->irq_srcu, but the traversal
in kvm_fire_mask_notifiers() incorrectly uses hlist_for_each_entry_rcu().
This leads to lockdep warnings because the standard RCU iterator expects
to be under rcu_read_lock(), not SRCU.

Replace the RCU variant with hlist_for_each_entry_srcu() and provide
the proper srcu_read_lock_held() annotation to ensure correct
synchronization and silence lockdep.

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://patch.msgid.link/20260204091206.2617-1-lirongqing@baidu.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/ioapic.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index bb257793b6cb..eed96ff6e722 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -321,7 +321,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
 	if (gsi != -1)
-		hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link)
+		hlist_for_each_entry_srcu(kimn, &ioapic->mask_notifier_list, link,
+				srcu_read_lock_held(&kvm->irq_srcu))
 			if (kimn->irq == gsi)
 				kimn->func(kimn, mask);
 	srcu_read_unlock(&kvm->irq_srcu, idx);
-- 
cgit v1.2.3


From e2ffe85b6d2bb7780174b87aa4468a39be17eb81 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Thu, 5 Feb 2026 15:15:26 -0800
Subject: KVM: x86: Introduce KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM

Add KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM to allow L1 to set
FREEZE_IN_SMM in vmcs12's GUEST_IA32_DEBUGCTL field, as permitted
prior to commit 6b1dd26544d0 ("KVM: VMX: Preserve host's
DEBUGCTLMSR_FREEZE_IN_SMM while running the guest").  Enable the quirk
by default for backwards compatibility (like all quirks); userspace
can disable it via KVM_CAP_DISABLE_QUIRKS2 for consistency with the
constraints on WRMSR(IA32_DEBUGCTL).

Note that the quirk only bypasses the consistency check.  The vmcs02 bit is
still owned by the host, and PMCs are not frozen during virtualized SMM.
In particular, if a host administrator decides that PMCs should not be
frozen during physical SMM, then L1 has no say in the matter.

Fixes: 095686e6fcb4 ("KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter")
Cc: stable@vger.kernel.org
Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260205231537.1278753-1-jmattson@google.com
[sean: tag for stable@, clean-up and fix goofs in the comment and docs]
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Rename quirk. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |  8 ++++++++
 arch/x86/include/asm/kvm_host.h |  3 ++-
 arch/x86/include/uapi/asm/kvm.h |  1 +
 arch/x86/kvm/vmx/nested.c       | 22 ++++++++++++++++++----
 4 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 6f85e1b321dd..19365b284395 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8543,6 +8543,14 @@ KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
                                     guest software, for example if it does not
                                     expose a bochs graphics device (which is
                                     known to have had a buggy driver).
+
+KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM   By default, KVM relaxes the consistency
+                                      check for GUEST_IA32_DEBUGCTL in vmcs12
+                                      to allow FREEZE_IN_SMM to be set.  When
+                                      this quirk is disabled, KVM requires this
+                                      bit to be cleared.  Note that the vmcs02
+                                      bit is still completely controlled by the
+                                      host, regardless of the quirk setting.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ff07c45e3c73..6e4e3ef9b8c7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
 	 KVM_X86_QUIRK_SLOT_ZAP_ALL |		\
 	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS |	\
-	 KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+	 KVM_X86_QUIRK_IGNORE_GUEST_PAT |	\
+	 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)
 
 #define KVM_X86_CONDITIONAL_QUIRKS		\
 	(KVM_X86_QUIRK_CD_NW_CLEARED |		\
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 846a63215ce1..0d4538fa6c31 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -476,6 +476,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 #define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
+#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 248635da6766..603c98de2cc8 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP)))
 		return -EINVAL;
 
-	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
-	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
-		return -EINVAL;
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+		u64 debugctl = vmcs12->guest_ia32_debugctl;
+
+		/*
+		 * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in
+		 * vmcs12's DEBUGCTL under a quirk for backwards compatibility.
+		 * Note that the quirk only relaxes the consistency check.  The
+		 * vmcc02 bit is still under the control of the host.  In
+		 * particular, if a host administrator decides to clear the bit,
+		 * then L1 has no say in the matter.
+		 */
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM))
+			debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM;
+
+		if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+		    CC(!vmx_is_valid_debugctl(vcpu, debugctl, false)))
+			return -EINVAL;
+	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
 	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))
-- 
cgit v1.2.3


From 3989a6d036c8ec82c0de3614bed23a1dacd45de5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Feb 2026 11:07:09 -0800
Subject: KVM: SVM: Initialize AVIC VMCB fields if AVIC is enabled with
 in-kernel APIC

Initialize all per-vCPU AVIC control fields in the VMCB if AVIC is enabled
in KVM and the VM has an in-kernel local APIC, i.e. if it's _possible_ the
vCPU could activate AVIC at any point in its lifecycle.  Configuring the
VMCB if and only if AVIC is active "works" purely because of optimizations
in kvm_create_lapic() to speculatively set apicv_active if AVIC is enabled
*and* to defer updates until the first KVM_RUN.  In quotes because KVM
likely won't do the right thing if kvm_apicv_activated() is false, i.e. if
a vCPU is created while APICv is inhibited at the VM level for whatever
reason.  E.g. if the inhibit is *removed* before KVM_REQ_APICV_UPDATE is
handled in KVM_RUN, then __kvm_vcpu_update_apicv() will elide calls to
vendor code due to seeing "apicv_active == activate".

Cleaning up the initialization code will also allow fixing a bug where KVM
incorrectly leaves CR8 interception enabled when AVIC is activated without
creating a mess with respect to whether AVIC is activated or not.

Cc: stable@vger.kernel.org
Fixes: 67034bb9dd5e ("KVM: SVM: Add irqchip_split() checks before enabling AVIC")
Fixes: 6c3e4422dd20 ("svm: Add support for dynamic APICv")
Reviewed-by: Naveen N Rao (AMD) <naveen@kernel.org>
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260203190711.458413-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/avic.c | 2 +-
 arch/x86/kvm/svm/svm.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index f92214b1a938..44e07c27b190 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -368,7 +368,7 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 	vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table));
 	vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE;
 
-	if (kvm_apicv_activated(svm->vcpu.kvm))
+	if (kvm_vcpu_apicv_active(&svm->vcpu))
 		avic_activate_vmcb(svm);
 	else
 		avic_deactivate_vmcb(svm);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8f8bc863e214..7806321c37bc 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1189,7 +1189,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event)
 	if (guest_cpu_cap_has(vcpu, X86_FEATURE_ERAPS))
 		svm->vmcb->control.erap_ctl |= ERAP_CONTROL_ALLOW_LARGER_RAP;
 
-	if (kvm_vcpu_apicv_active(vcpu))
+	if (enable_apicv && irqchip_in_kernel(vcpu->kvm))
 		avic_init_vmcb(svm, vmcb);
 
 	if (vnmi)
-- 
cgit v1.2.3


From 87d0f901a9bd8ae6be57249c737f20ac0cace93d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 3 Feb 2026 11:07:10 -0800
Subject: KVM: SVM: Set/clear CR8 write interception when AVIC is (de)activated

Explicitly set/clear CR8 write interception when AVIC is (de)activated to
fix a bug where KVM leaves the interception enabled after AVIC is
activated.  E.g. if KVM emulates INIT=>WFS while AVIC is deactivated, CR8
will remain intercepted in perpetuity.

On its own, the dangling CR8 intercept is "just" a performance issue, but
combined with the TPR sync bug fixed by commit d02e48830e3f ("KVM: SVM:
Sync TPR from LAPIC into VMCB::V_TPR even if AVIC is active"), the danging
intercept is fatal to Windows guests as the TPR seen by hardware gets
wildly out of sync with reality.

Note, VMX isn't affected by the bug as TPR_THRESHOLD is explicitly ignored
when Virtual Interrupt Delivery is enabled, i.e. when APICv is active in
KVM's world.  I.e. there's no need to trigger update_cr8_intercept(), this
is firmly an SVM implementation flaw/detail.

WARN if KVM gets a CR8 write #VMEXIT while AVIC is active, as KVM should
never enter the guest with AVIC enabled and CR8 writes intercepted.

Fixes: 3bbf3565f48c ("svm: Do not intercept CR8 when enable AVIC")
Cc: stable@vger.kernel.org
Cc: Jim Mattson <jmattson@google.com>
Cc: Naveen N Rao (AMD) <naveen@kernel.org>
Cc: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Reviewed-by: Naveen N Rao (AMD) <naveen@kernel.org>
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260203190711.458413-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Squash fix to avic_deactivate_vmcb. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/avic.c | 7 +++++--
 arch/x86/kvm/svm/svm.c  | 7 ++++---
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 44e07c27b190..f7ec7914e3c4 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -189,12 +189,12 @@ static void avic_activate_vmcb(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
-
 	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
 	vmcb->control.avic_physical_id |= avic_get_max_physical_id(vcpu);
-
 	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
 
+	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	/*
 	 * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR
 	 * accesses, while interrupt injection to a running vCPU can be
@@ -226,6 +226,9 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm)
 	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
 	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
 
+	if (!sev_es_guest(svm->vcpu.kvm))
+		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
+
 	/*
 	 * If running nested and the guest uses its own MSR bitmap, there
 	 * is no need to update L0's msr bitmap
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7806321c37bc..2772f22df7ed 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1077,8 +1077,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu, bool init_event)
 	svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
 	svm_set_intercept(svm, INTERCEPT_CR3_WRITE);
 	svm_set_intercept(svm, INTERCEPT_CR4_WRITE);
-	if (!kvm_vcpu_apicv_active(vcpu))
-		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
+	svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
 
 	set_dr_intercepts(svm);
 
@@ -2674,9 +2673,11 @@ static int dr_interception(struct kvm_vcpu *vcpu)
 
 static int cr8_write_interception(struct kvm_vcpu *vcpu)
 {
+	u8 cr8_prev = kvm_get_cr8(vcpu);
 	int r;
 
-	u8 cr8_prev = kvm_get_cr8(vcpu);
+	WARN_ON_ONCE(kvm_vcpu_apicv_active(vcpu));
+
 	/* instruction emulation calls kvm_set_cr8() */
 	r = cr_interception(vcpu);
 	if (lapic_in_kernel(vcpu))
-- 
cgit v1.2.3


From 5a30e8aea079b3e4e79d6ce7a878f5f42efe9d0b Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 12:40:40 +0100
Subject: KVM: VMX: check validity of VMCS controls when returning from SMM

The VMCS12 is not available while in SMM.  However, it can be overwritten
if userspace manages to trigger copy_enlightened_to_vmcs12() - for example
via KVM_GET_NESTED_STATE.

Because of this, the VMCS12 has to be checked for validity before it is
used to generate the VMCS02.  Move the check code out of vmx_set_nested_state()
(the other "not a VMLAUNCH/VMRESUME" path that emulates a nested vmentry)
and reuse it in vmx_leave_smm().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 39 +++++++++++++++++++++++++++------------
 arch/x86/kvm/vmx/nested.h |  1 +
 arch/x86/kvm/vmx/vmx.c    |  4 ++++
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 603c98de2cc8..937aeb474af7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6856,13 +6856,34 @@ void vmx_leave_nested(struct kvm_vcpu *vcpu)
 	free_nested(vcpu);
 }
 
+int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu)
+{
+	enum vm_entry_failure_code ignored;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
+	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
+		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
+
+		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
+		    !shadow_vmcs12->hdr.shadow_vmcs)
+			return -EINVAL;
+	}
+
+	if (nested_vmx_check_controls(vcpu, vmcs12) ||
+	    nested_vmx_check_host_state(vcpu, vmcs12) ||
+	    nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				struct kvm_nested_state *kvm_state)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12;
-	enum vm_entry_failure_code ignored;
 	struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
 		&user_kvm_nested_state->data.vmx[0];
 	int ret;
@@ -6993,25 +7014,20 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	vmx->nested.mtf_pending =
 		!!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
 
-	ret = -EINVAL;
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != INVALID_GPA) {
 		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
 
+		ret = -EINVAL;
 		if (kvm_state->size <
 		    sizeof(*kvm_state) +
 		    sizeof(user_vmx_nested_state->vmcs12) + sizeof(*shadow_vmcs12))
 			goto error_guest_mode;
 
+		ret = -EFAULT;
 		if (copy_from_user(shadow_vmcs12,
 				   user_vmx_nested_state->shadow_vmcs12,
-				   sizeof(*shadow_vmcs12))) {
-			ret = -EFAULT;
-			goto error_guest_mode;
-		}
-
-		if (shadow_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    !shadow_vmcs12->hdr.shadow_vmcs)
+				   sizeof(*shadow_vmcs12)))
 			goto error_guest_mode;
 	}
 
@@ -7022,9 +7038,8 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			kvm_state->hdr.vmx.preemption_timer_deadline;
 	}
 
-	if (nested_vmx_check_controls(vcpu, vmcs12) ||
-	    nested_vmx_check_host_state(vcpu, vmcs12) ||
-	    nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
+	ret = nested_vmx_check_restored_vmcs12(vcpu);
+	if (ret < 0)
 		goto error_guest_mode;
 
 	vmx->nested.dirty_vmcs12 = true;
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index b844c5d59025..213a448104af 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -22,6 +22,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);
+int nested_vmx_check_restored_vmcs12(struct kvm_vcpu *vcpu);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 83d057cfa816..bccc91a999d9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8528,6 +8528,10 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	}
 
 	if (vmx->nested.smm.guest_mode) {
+		/* Triple fault if the state is invalid.  */
+		if (nested_vmx_check_restored_vmcs12(vcpu) < 0)
+			return 1;
+
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From be5fa8737d42c5ba16d2ea72c23681f8abbb07e8 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 12:40:52 +0100
Subject: KVM: SVM: check validity of VMCB controls when returning from SMM

The VMCB12 is stored in guest memory and can be mangled while in SMM; it
is then reloaded by svm_leave_smm(), but it is not checked again for
validity.

Move the cached vmcb12 control and save consistency checks out of
svm_set_nested_state() and into a helper, and reuse it in
svm_leave_smm().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/nested.c | 12 ++++++++++--
 arch/x86/kvm/svm/svm.c    |  4 ++++
 arch/x86/kvm/svm/svm.h    |  1 +
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 53ab6ce3cc26..b36c33255bed 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -418,6 +418,15 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu)
 	return __nested_vmcb_check_controls(vcpu, ctl);
 }
 
+int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu)
+{
+	if (!nested_vmcb_check_save(vcpu) ||
+	    !nested_vmcb_check_controls(vcpu))
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * If a feature is not advertised to L1, clear the corresponding vmcb12
  * intercept.
@@ -1028,8 +1037,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
 	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
 
-	if (!nested_vmcb_check_save(vcpu) ||
-	    !nested_vmcb_check_controls(vcpu)) {
+	if (nested_svm_check_cached_vmcb12(vcpu) < 0) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_info_1  = 0;
 		vmcb12->control.exit_info_2  = 0;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2772f22df7ed..4eb2c36b8ff2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4880,6 +4880,10 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	vmcb12 = map.hva;
 	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
 	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
+
+	if (nested_svm_check_cached_vmcb12(vcpu) < 0)
+		goto unmap_save;
+
 	ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
 
 	if (ret)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index ebd7b36b1ceb..6942e6b0eda6 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -797,6 +797,7 @@ static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
 
 int nested_svm_exit_handled(struct vcpu_svm *svm);
 int nested_svm_check_permissions(struct kvm_vcpu *vcpu);
+int nested_svm_check_cached_vmcb12(struct kvm_vcpu *vcpu);
 int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 			       bool has_error_code, u32 error_code);
 int nested_svm_exit_special(struct vcpu_svm *svm);
-- 
cgit v1.2.3


From c52b534f26574ddf2f67cf07992ae2c25e8932c8 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 13:43:57 +0100
Subject: selftests: kvm: extract common functionality out of smm_test.c

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/x86/smm.h   | 17 ++++++++++++++++
 tools/testing/selftests/kvm/lib/x86/processor.c | 26 ++++++++++++++++++++++++
 tools/testing/selftests/kvm/x86/smm_test.c      | 27 ++-----------------------
 3 files changed, 45 insertions(+), 25 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/x86/smm.h

diff --git a/tools/testing/selftests/kvm/include/x86/smm.h b/tools/testing/selftests/kvm/include/x86/smm.h
new file mode 100644
index 000000000000..19337c34f13e
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86/smm.h
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#ifndef SELFTEST_KVM_SMM_H
+#define SELFTEST_KVM_SMM_H
+
+#include "kvm_util.h"
+
+#define SMRAM_SIZE	65536
+#define SMRAM_MEMSLOT	((1 << 16) | 1)
+#define SMRAM_PAGES	(SMRAM_SIZE / PAGE_SIZE)
+
+void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
+		 uint64_t smram_gpa,
+		 const void *smi_handler, size_t handler_size);
+
+void inject_smi(struct kvm_vcpu *vcpu);
+
+#endif /* SELFTEST_KVM_SMM_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index fab18e9be66c..23a44941e283 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -8,6 +8,7 @@
 #include "kvm_util.h"
 #include "pmu.h"
 #include "processor.h"
+#include "smm.h"
 #include "svm_util.h"
 #include "sev.h"
 #include "vmx.h"
@@ -1444,3 +1445,28 @@ bool kvm_arch_has_default_irqchip(void)
 {
 	return true;
 }
+
+void setup_smram(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
+		 uint64_t smram_gpa,
+		 const void *smi_handler, size_t handler_size)
+{
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, smram_gpa,
+				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, smram_gpa,
+				       SMRAM_MEMSLOT) == smram_gpa,
+		    "Could not allocate guest physical addresses for SMRAM");
+
+	memset(addr_gpa2hva(vm, smram_gpa), 0x0, SMRAM_SIZE);
+	memcpy(addr_gpa2hva(vm, smram_gpa) + 0x8000, smi_handler, handler_size);
+	vcpu_set_msr(vcpu, MSR_IA32_SMBASE, smram_gpa);
+}
+
+void inject_smi(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_events events;
+
+	vcpu_events_get(vcpu, &events);
+	events.smi.pending = 1;
+	events.flags |= KVM_VCPUEVENT_VALID_SMM;
+	vcpu_events_set(vcpu, &events);
+}
diff --git a/tools/testing/selftests/kvm/x86/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c
index 55c88d664a94..ade8412bf94a 100644
--- a/tools/testing/selftests/kvm/x86/smm_test.c
+++ b/tools/testing/selftests/kvm/x86/smm_test.c
@@ -14,13 +14,11 @@
 #include "test_util.h"
 
 #include "kvm_util.h"
+#include "smm.h"
 
 #include "vmx.h"
 #include "svm_util.h"
 
-#define SMRAM_SIZE 65536
-#define SMRAM_MEMSLOT ((1 << 16) | 1)
-#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
 #define SMRAM_GPA 0x1000000
 #define SMRAM_STAGE 0xfe
 
@@ -113,18 +111,6 @@ static void guest_code(void *arg)
 	sync_with_host(DONE);
 }
 
-void inject_smi(struct kvm_vcpu *vcpu)
-{
-	struct kvm_vcpu_events events;
-
-	vcpu_events_get(vcpu, &events);
-
-	events.smi.pending = 1;
-	events.flags |= KVM_VCPUEVENT_VALID_SMM;
-
-	vcpu_events_set(vcpu, &events);
-}
-
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t nested_gva = 0;
@@ -140,16 +126,7 @@ int main(int argc, char *argv[])
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
-				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
-	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
-		    == SMRAM_GPA, "could not allocate guest physical addresses?");
-
-	memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
-	memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
-	       sizeof(smi_handler));
-
-	vcpu_set_msr(vcpu, MSR_IA32_SMBASE, SMRAM_GPA);
+	setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler));
 
 	if (kvm_has_cap(KVM_CAP_NESTED_STATE)) {
 		if (kvm_cpu_has(X86_FEATURE_SVM))
-- 
cgit v1.2.3


From 3e745694b032b405ff1ced74a8b3b95cdd00a385 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Mar 2026 13:44:40 +0100
Subject: selftests: kvm: add a test that VMX validates controls on RSM

Add a test checking that invalid eVMCS contents are validated after an
RSM instruction is emulated.

The failure mode is simply that the RSM succeeds, because KVM virtualizes
NMIs anyway while running L2; the two pin-based execution controls used
by the test are entirely handled by KVM and not by the processor.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile.kvm           |   1 +
 .../selftests/kvm/x86/evmcs_smm_controls_test.c    | 150 +++++++++++++++++++++
 2 files changed, 151 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index fdec90e85467..dc68371f76a3 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86 += x86/cpuid_test
 TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
 TEST_GEN_PROGS_x86 += x86/feature_msrs_test
+TEST_GEN_PROGS_x86 += x86/evmcs_smm_controls_test
 TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test
 TEST_GEN_PROGS_x86 += x86/fastops_test
 TEST_GEN_PROGS_x86 += x86/fix_hypercall_test
diff --git a/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c
new file mode 100644
index 000000000000..af7c90103396
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86/evmcs_smm_controls_test.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2026, Red Hat, Inc.
+ *
+ * Test that vmx_leave_smm() validates vmcs12 controls before re-entering
+ * nested guest mode on RSM.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "smm.h"
+#include "hyperv.h"
+#include "vmx.h"
+
+#define SMRAM_GPA	0x1000000
+#define SMRAM_STAGE	0xfe
+
+#define SYNC_PORT	0xe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+/*
+ * SMI handler: runs in real-address mode.
+ * Reports SMRAM_STAGE via port IO, then does RSM.
+ */
+static uint8_t smi_handler[] = {
+	0xb0, SMRAM_STAGE,    /* mov $SMRAM_STAGE, %al */
+	0xe4, SYNC_PORT,      /* in $SYNC_PORT, %al */
+	0x0f, 0xaa,           /* rsm */
+};
+
+static inline void sync_with_host(uint64_t phase)
+{
+	asm volatile("in $" XSTR(SYNC_PORT) ", %%al \n"
+		     : "+a" (phase));
+}
+
+static void l2_guest_code(void)
+{
+	sync_with_host(1);
+
+	/* After SMI+RSM with invalid controls, we should not reach here. */
+	vmcall();
+}
+
+static void guest_code(struct vmx_pages *vmx_pages,
+		       struct hyperv_test_pages *hv_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	/* Set up Hyper-V enlightenments and eVMCS */
+	wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+	enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist);
+	evmcs_enable();
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_evmcs(hv_pages));
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_ASSERT(!vmlaunch());
+
+	/* L2 exits via vmcall if test fails */
+	sync_with_host(2);
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0;
+	struct hyperv_test_pages *hv;
+	struct hv_enlightened_vmcs *evmcs;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct kvm_regs regs;
+	int stage_reported;
+
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM));
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	setup_smram(vm, vcpu, SMRAM_GPA, smi_handler, sizeof(smi_handler));
+
+	vcpu_set_hv_cpuid(vcpu);
+	vcpu_enable_evmcs(vcpu);
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	hv = vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva);
+	vcpu_args_set(vcpu, 2, vmx_pages_gva, hv_pages_gva);
+
+	vcpu_run(vcpu);
+
+	/* L2 is running and syncs with host.  */
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+	vcpu_regs_get(vcpu, &regs);
+	stage_reported = regs.rax & 0xff;
+	TEST_ASSERT(stage_reported == 1,
+		    "Expected stage 1, got %d", stage_reported);
+
+	/* Inject SMI while L2 is running.  */
+	inject_smi(vcpu);
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
+	vcpu_regs_get(vcpu, &regs);
+	stage_reported = regs.rax & 0xff;
+	TEST_ASSERT(stage_reported == SMRAM_STAGE,
+		    "Expected SMM handler stage %#x, got %#x",
+		    SMRAM_STAGE, stage_reported);
+
+	/*
+	 * Guest is now paused in the SMI handler, about to execute RSM.
+	 * Hack the eVMCS page to set-up invalid pin-based execution
+	 * control (PIN_BASED_VIRTUAL_NMIS without PIN_BASED_NMI_EXITING).
+	 */
+	evmcs = hv->enlightened_vmcs_hva;
+	evmcs->pin_based_vm_exec_control |= PIN_BASED_VIRTUAL_NMIS;
+	evmcs->hv_clean_fields = 0;
+
+	/*
+	 * Trigger copy_enlightened_to_vmcs12() via KVM_GET_NESTED_STATE,
+	 * copying the invalid pin_based_vm_exec_control into cached_vmcs12.
+	 */
+	union {
+		struct kvm_nested_state state;
+		char state_[16384];
+	} nested_state_buf;
+
+	memset(&nested_state_buf, 0, sizeof(nested_state_buf));
+	nested_state_buf.state.size = sizeof(nested_state_buf);
+	vcpu_nested_state_get(vcpu, &nested_state_buf.state);
+
+	/*
+	 * Resume the guest.  The SMI handler executes RSM, which calls
+	 * vmx_leave_smm().  nested_vmx_check_controls() should detect
+	 * VIRTUAL_NMIS without NMI_EXITING and cause a triple fault.
+	 */
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN);
+
+	kvm_vm_free(vm);
+	return 0;
+}
-- 
cgit v1.2.3


From 6b1ca262a943a3307ee905faac0f4ff61ec3d656 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 10 Mar 2026 20:33:39 +0100
Subject: KVM: x86: clarify leave_smm() return value

The return value of vmx_leave_smm() is unrelated from that of
nested_vmx_enter_non_root_mode().  Check explicitly for success
(which happens to be 0) and return 1 just like everywhere
else in vmx_leave_smm().

Likewise, in svm_leave_smm() return 0/1 instead of the 0/1/-errno
returned by tenter_svm_guest_mode().

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.c | 6 +++---
 arch/x86/kvm/vmx/vmx.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4eb2c36b8ff2..e6477affac9a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4884,11 +4884,11 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 	if (nested_svm_check_cached_vmcb12(vcpu) < 0)
 		goto unmap_save;
 
-	ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
-
-	if (ret)
+	if (enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa,
+				 vmcb12, false) != 0)
 		goto unmap_save;
 
+	ret = 0;
 	svm->nested.nested_run_pending = 1;
 
 unmap_save:
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bccc91a999d9..8b24e682535b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -8533,8 +8533,8 @@ int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
 			return 1;
 
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
-		if (ret)
-			return ret;
+		if (ret != NVMX_VMENTRY_SUCCESS)
+			return 1;
 
 		vmx->nested.nested_run_pending = 1;
 		vmx->nested.smm.guest_mode = false;
-- 
cgit v1.2.3


From 33efc6346e8cf75219673fe1ca1916ab40643728 Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Tue, 24 Feb 2026 16:28:00 -0500
Subject: drm/amd/display: Add missing DCCG register entries for DCN20-DCN316

Commit 4c595e75110e ("drm/amd/display: Migrate DCCG registers access
from hwseq to dccg component.") moved register writes from hwseq to
dccg2_*() functions but did not add the registers to the DCCG register
list macros. The struct fields default to 0, so REG_WRITE() targets
MMIO offset 0, causing a GPU hang on resume (seen on DCN21/DCN30
during IGT kms_cursor_crc@cursor-suspend).

Add
- MICROSECOND_TIME_BASE_DIV
- MILLISECOND_TIME_BASE_DIV
- DCCG_GATE_DISABLE_CNTL
- DCCG_GATE_DISABLE_CNTL2
- DC_MEM_GLOBAL_PWR_REQ_CNTL
to macros in  dcn20_dccg.h, dcn301_dccg.h, dcn31_dccg.h, and dcn314_dccg.h.

Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.")
Reported-by: Rafael Passos <rafael@rcpassos.me>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e6e2b956fc814de766d3480be7018297c41d3ce0)
---
 drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h   | 6 +++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h | 8 +++++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h   | 5 ++++-
 drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h | 5 ++++-
 4 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
index 3711d400773a..4c4e61bc91b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
@@ -38,7 +38,11 @@
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\
 	SR(DISPCLK_FREQ_CHANGE_CNTL),\
-	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL)
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_REG_LIST_DCN2() \
 	DCCG_COMMON_REG_LIST_DCN_BASE(),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
index 067e49cb238e..e2381ca0be0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
@@ -34,7 +34,13 @@
 	DCCG_SRII(DTO_PARAM, DPPCLK, 1),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 2),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 3),\
-	SR(REFCLK_CNTL)
+	SR(REFCLK_CNTL),\
+	SR(DISPCLK_FREQ_CHANGE_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
index bf659920d4cc..b5e3849ef12a 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
@@ -64,9 +64,12 @@
 	SR(DSCCLK1_DTO_PARAM),\
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
-	SR(HDMISTREAMCLK0_DTO_PARAM)
+	SR(HDMISTREAMCLK0_DTO_PARAM),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 
 #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
index a609635f35db..ecbdc05f7c45 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
@@ -70,11 +70,14 @@
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK3_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
 	SR(HDMISTREAMCLK0_DTO_PARAM),\
 	SR(OTG_PIXEL_RATE_DIV),\
-	SR(DTBCLK_P_CNTL)
+	SR(DTBCLK_P_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\
-- 
cgit v1.2.3


From becbab4a5a02156000f3aaff8bb70e8fd3e0d4cf Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Wed, 25 Feb 2026 21:48:36 -0500
Subject: drm/amd/display: Check for S0i3 to be done before DCCG init on DCN21

[WHY]
On DCN21, dccg2_init() is called in dcn10_init_hw() before
bios_golden_init(). During S0i3 resume, BIOS sets MICROSECOND_TIME_BASE_DIV
to 0x00120464 as a marker. dccg2_init() overwrites this to 0x00120264,
causing dcn21_s0i3_golden_init_wa() to misdetect the state and skip golden
init.
Eventually during the resume sequence, a flip timeout occurs.

[HOW]
Skip DCCG on dccg2_is_s0i3_golden_init_wa_done() on DCN21.

Fixes: 4c595e75110e ("drm/amd/display: Migrate DCCG registers access from hwseq to dccg component.")
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c61eda434336cf2c033aa35efdc9a08b31d2fdfa)
---
 .../gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c  | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
index 75c69348027e..c4d4eea140f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
@@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 
+/*
+ * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to
+ * 0x00120464 as a marker that golden init has already been done.
+ * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init()
+ * to decide whether to skip golden init.
+ *
+ * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to
+ * 0x00120264, destroying the marker before it can be read.
+ *
+ * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the
+ * WA can function correctly. bios_golden_init() will handle init in that case.
+ */
+static void dccg21_init(struct dccg *dccg)
+{
+	if (dccg2_is_s0i3_golden_init_wa_done(dccg))
+		return;
+
+	dccg2_init(dccg);
+}
 
 static const struct dccg_funcs dccg21_funcs = {
 	.update_dpp_dto = dccg21_update_dpp_dto,
@@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = {
 	.set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en,
 	.otg_add_pixel = dccg2_otg_add_pixel,
 	.otg_drop_pixel = dccg2_otg_drop_pixel,
-	.dccg_init = dccg2_init,
+	.dccg_init = dccg21_init,
 	.refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */
 	.allow_clock_gating = dccg2_allow_clock_gating,
 	.enable_memory_low_power = dccg2_enable_memory_low_power,
-- 
cgit v1.2.3


From 2ce75a0b7e1bfddbcb9bc8aeb2e5e7fa99971acf Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Tue, 9 Dec 2025 15:13:23 -0500
Subject: drm/amdkfd: Unreserve bo if queue update failed

Error handling path should unreserve bo then return failed.

Fixes: 305cd109b761 ("drm/amdkfd: Validate user queue update")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c24afed7de9ecce341825d8ab55a43a254348b33)
---
 drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 8ea31699d38b..f5d2847e1cbb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm,
 					 p->queue_size)) {
 			pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n",
 				 p->queue_address, p->queue_size);
+			amdgpu_bo_unreserve(vm->root.bo);
 			return -EFAULT;
 		}
 
-- 
cgit v1.2.3


From 3646ff28780b4c52c5b5081443199e7a430110e5 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Mar 2026 11:58:22 -0500
Subject: drm/amd: Set num IP blocks to 0 if discovery fails

If discovery has failed for any reason (such as no support for a block)
then there is no need to unwind all the IP blocks in fini. In this
condition there can actually be failures during the unwind too.

Reset num_ip_blocks to zero during failure path and skip the unnecessary
cleanup path.

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fae5984296b981c8cc3acca35b701c1f332a6cd8)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 761ee5ebb4f5..d8296dfc5e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		break;
 	default:
 		r = amdgpu_discovery_set_ip_blocks(adev);
-		if (r)
+		if (r) {
+			adev->num_ip_blocks = 0;
 			return r;
+		}
 		break;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 77e2133de5cf..7f19554b9ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
-	if (adev == NULL)
+	if (adev == NULL || !adev->num_ip_blocks)
 		return;
 
 	amdgpu_unregister_gpu_instance(adev);
-- 
cgit v1.2.3


From dca01b0a264642929732c4db4a07e7b213304c15 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 11 Mar 2026 19:16:52 +0100
Subject: Documentation: kvm: fix formatting of the quirks table

A recently added quirk does not fit in the left column of the table,
so it all has to be reformatted and realigned.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 230 ++++++++++++++++++++---------------------
 1 file changed, 115 insertions(+), 115 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 19365b284395..032516783e96 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8435,123 +8435,123 @@ KVM_CHECK_EXTENSION.
 
 The valid bits in cap.args[0] are:
 
-=================================== ============================================
- KVM_X86_QUIRK_LINT0_REENABLED      By default, the reset value for the LVT
-                                    LINT0 register is 0x700 (APIC_MODE_EXTINT).
-                                    When this quirk is disabled, the reset value
-                                    is 0x10000 (APIC_LVT_MASKED).
-
- KVM_X86_QUIRK_CD_NW_CLEARED        By default, KVM clears CR0.CD and CR0.NW on
-                                    AMD CPUs to workaround buggy guest firmware
-                                    that runs in perpetuity with CR0.CD, i.e.
-                                    with caches in "no fill" mode.
-
-                                    When this quirk is disabled, KVM does not
-                                    change the value of CR0.CD and CR0.NW.
-
- KVM_X86_QUIRK_LAPIC_MMIO_HOLE      By default, the MMIO LAPIC interface is
-                                    available even when configured for x2APIC
-                                    mode. When this quirk is disabled, KVM
-                                    disables the MMIO LAPIC interface if the
-                                    LAPIC is in x2APIC mode.
-
- KVM_X86_QUIRK_OUT_7E_INC_RIP       By default, KVM pre-increments %rip before
-                                    exiting to userspace for an OUT instruction
-                                    to port 0x7e. When this quirk is disabled,
-                                    KVM does not pre-increment %rip before
-                                    exiting to userspace.
-
- KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets
-                                    CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if
-                                    IA32_MISC_ENABLE[bit 18] (MWAIT) is set.
-                                    Additionally, when this quirk is disabled,
-                                    KVM clears CPUID.01H:ECX[bit 3] if
-                                    IA32_MISC_ENABLE[bit 18] is cleared.
-
- KVM_X86_QUIRK_FIX_HYPERCALL_INSN   By default, KVM rewrites guest
-                                    VMMCALL/VMCALL instructions to match the
-                                    vendor's hypercall instruction for the
-                                    system. When this quirk is disabled, KVM
-                                    will no longer rewrite invalid guest
-                                    hypercall instructions. Executing the
-                                    incorrect hypercall instruction will
-                                    generate a #UD within the guest.
-
-KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
-                                    they are intercepted) as NOPs regardless of
-                                    whether or not MONITOR/MWAIT are supported
-                                    according to guest CPUID.  When this quirk
-                                    is disabled and KVM_X86_DISABLE_EXITS_MWAIT
-                                    is not set (MONITOR/MWAIT are intercepted),
-                                    KVM will inject a #UD on MONITOR/MWAIT if
-                                    they're unsupported per guest CPUID.  Note,
-                                    KVM will modify MONITOR/MWAIT support in
-                                    guest CPUID on writes to MISC_ENABLE if
-                                    KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
-                                    disabled.
-
-KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, for KVM_X86_DEFAULT_VM VMs, KVM
-                                    invalidates all SPTEs in all memslots and
-                                    address spaces when a memslot is deleted or
-                                    moved.  When this quirk is disabled (or the
-                                    VM type isn't KVM_X86_DEFAULT_VM), KVM only
-                                    ensures the backing memory of the deleted
-                                    or moved memslot isn't reachable, i.e KVM
-                                    _may_ invalidate only SPTEs related to the
-                                    memslot.
-
-KVM_X86_QUIRK_STUFF_FEATURE_MSRS    By default, at vCPU creation, KVM sets the
-                                    vCPU's MSR_IA32_PERF_CAPABILITIES (0x345),
-                                    MSR_IA32_ARCH_CAPABILITIES (0x10a),
-                                    MSR_PLATFORM_INFO (0xce), and all VMX MSRs
-                                    (0x480..0x492) to the maximal capabilities
-                                    supported by KVM.  KVM also sets
-                                    MSR_IA32_UCODE_REV (0x8b) to an arbitrary
-                                    value (which is different for Intel vs.
-                                    AMD).  Lastly, when guest CPUID is set (by
-                                    userspace), KVM modifies select VMX MSR
-                                    fields to force consistency between guest
-                                    CPUID and L2's effective ISA.  When this
-                                    quirk is disabled, KVM zeroes the vCPU's MSR
-                                    values (with two exceptions, see below),
-                                    i.e. treats the feature MSRs like CPUID
-                                    leaves and gives userspace full control of
-                                    the vCPU model definition.  This quirk does
-                                    not affect VMX MSRs CR0/CR4_FIXED1 (0x487
-                                    and 0x489), as KVM does now allow them to
-                                    be set by userspace (KVM sets them based on
-                                    guest CPUID, for safety purposes).
-
-KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
-                                    guest PAT and forces the effective memory
-                                    type to WB in EPT.  The quirk is not available
-                                    on Intel platforms which are incapable of
-                                    safely honoring guest PAT (i.e., without CPU
-                                    self-snoop, KVM always ignores guest PAT and
-                                    forces effective memory type to WB).  It is
-                                    also ignored on AMD platforms or, on Intel,
-                                    when a VM has non-coherent DMA devices
-                                    assigned; KVM always honors guest PAT in
-                                    such case. The quirk is needed to avoid
-                                    slowdowns on certain Intel Xeon platforms
-                                    (e.g. ICX, SPR) where self-snoop feature is
-                                    supported but UC is slow enough to cause
-                                    issues with some older guests that use
-                                    UC instead of WC to map the video RAM.
-                                    Userspace can disable the quirk to honor
-                                    guest PAT if it knows that there is no such
-                                    guest software, for example if it does not
-                                    expose a bochs graphics device (which is
-                                    known to have had a buggy driver).
+========================================   ================================================
+KVM_X86_QUIRK_LINT0_REENABLED              By default, the reset value for the LVT
+                                           LINT0 register is 0x700 (APIC_MODE_EXTINT).
+                                           When this quirk is disabled, the reset value
+                                           is 0x10000 (APIC_LVT_MASKED).
+
+KVM_X86_QUIRK_CD_NW_CLEARED                By default, KVM clears CR0.CD and CR0.NW on
+                                           AMD CPUs to workaround buggy guest firmware
+                                           that runs in perpetuity with CR0.CD, i.e.
+                                           with caches in "no fill" mode.
+
+                                           When this quirk is disabled, KVM does not
+                                           change the value of CR0.CD and CR0.NW.
+
+KVM_X86_QUIRK_LAPIC_MMIO_HOLE              By default, the MMIO LAPIC interface is
+                                           available even when configured for x2APIC
+                                           mode. When this quirk is disabled, KVM
+                                           disables the MMIO LAPIC interface if the
+                                           LAPIC is in x2APIC mode.
+
+KVM_X86_QUIRK_OUT_7E_INC_RIP               By default, KVM pre-increments %rip before
+                                           exiting to userspace for an OUT instruction
+                                           to port 0x7e. When this quirk is disabled,
+                                           KVM does not pre-increment %rip before
+                                           exiting to userspace.
+
+KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT         When this quirk is disabled, KVM sets
+                                           CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if
+                                           IA32_MISC_ENABLE[bit 18] (MWAIT) is set.
+                                           Additionally, when this quirk is disabled,
+                                           KVM clears CPUID.01H:ECX[bit 3] if
+                                           IA32_MISC_ENABLE[bit 18] is cleared.
+
+KVM_X86_QUIRK_FIX_HYPERCALL_INSN           By default, KVM rewrites guest
+                                           VMMCALL/VMCALL instructions to match the
+                                           vendor's hypercall instruction for the
+                                           system. When this quirk is disabled, KVM
+                                           will no longer rewrite invalid guest
+                                           hypercall instructions. Executing the
+                                           incorrect hypercall instruction will
+                                           generate a #UD within the guest.
+
+KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS        By default, KVM emulates MONITOR/MWAIT (if
+                                           they are intercepted) as NOPs regardless of
+                                           whether or not MONITOR/MWAIT are supported
+                                           according to guest CPUID.  When this quirk
+                                           is disabled and KVM_X86_DISABLE_EXITS_MWAIT
+                                           is not set (MONITOR/MWAIT are intercepted),
+                                           KVM will inject a #UD on MONITOR/MWAIT if
+                                           they're unsupported per guest CPUID.  Note,
+                                           KVM will modify MONITOR/MWAIT support in
+                                           guest CPUID on writes to MISC_ENABLE if
+                                           KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
+                                           disabled.
+
+KVM_X86_QUIRK_SLOT_ZAP_ALL                 By default, for KVM_X86_DEFAULT_VM VMs, KVM
+                                           invalidates all SPTEs in all memslots and
+                                           address spaces when a memslot is deleted or
+                                           moved.  When this quirk is disabled (or the
+                                           VM type isn't KVM_X86_DEFAULT_VM), KVM only
+                                           ensures the backing memory of the deleted
+                                           or moved memslot isn't reachable, i.e KVM
+                                           _may_ invalidate only SPTEs related to the
+                                           memslot.
+
+KVM_X86_QUIRK_STUFF_FEATURE_MSRS           By default, at vCPU creation, KVM sets the
+                                           vCPU's MSR_IA32_PERF_CAPABILITIES (0x345),
+                                           MSR_IA32_ARCH_CAPABILITIES (0x10a),
+                                           MSR_PLATFORM_INFO (0xce), and all VMX MSRs
+                                           (0x480..0x492) to the maximal capabilities
+                                           supported by KVM.  KVM also sets
+                                           MSR_IA32_UCODE_REV (0x8b) to an arbitrary
+                                           value (which is different for Intel vs.
+                                           AMD).  Lastly, when guest CPUID is set (by
+                                           userspace), KVM modifies select VMX MSR
+                                           fields to force consistency between guest
+                                           CPUID and L2's effective ISA.  When this
+                                           quirk is disabled, KVM zeroes the vCPU's MSR
+                                           values (with two exceptions, see below),
+                                           i.e. treats the feature MSRs like CPUID
+                                           leaves and gives userspace full control of
+                                           the vCPU model definition.  This quirk does
+                                           not affect VMX MSRs CR0/CR4_FIXED1 (0x487
+                                           and 0x489), as KVM does now allow them to
+                                           be set by userspace (KVM sets them based on
+                                           guest CPUID, for safety purposes).
+
+KVM_X86_QUIRK_IGNORE_GUEST_PAT             By default, on Intel platforms, KVM ignores
+                                           guest PAT and forces the effective memory
+                                           type to WB in EPT.  The quirk is not available
+                                           on Intel platforms which are incapable of
+                                           safely honoring guest PAT (i.e., without CPU
+                                           self-snoop, KVM always ignores guest PAT and
+                                           forces effective memory type to WB).  It is
+                                           also ignored on AMD platforms or, on Intel,
+                                           when a VM has non-coherent DMA devices
+                                           assigned; KVM always honors guest PAT in
+                                           such case. The quirk is needed to avoid
+                                           slowdowns on certain Intel Xeon platforms
+                                           (e.g. ICX, SPR) where self-snoop feature is
+                                           supported but UC is slow enough to cause
+                                           issues with some older guests that use
+                                           UC instead of WC to map the video RAM.
+                                           Userspace can disable the quirk to honor
+                                           guest PAT if it knows that there is no such
+                                           guest software, for example if it does not
+                                           expose a bochs graphics device (which is
+                                           known to have had a buggy driver).
 
 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM   By default, KVM relaxes the consistency
-                                      check for GUEST_IA32_DEBUGCTL in vmcs12
-                                      to allow FREEZE_IN_SMM to be set.  When
-                                      this quirk is disabled, KVM requires this
-                                      bit to be cleared.  Note that the vmcs02
-                                      bit is still completely controlled by the
-                                      host, regardless of the quirk setting.
-=================================== ============================================
+                                           check for GUEST_IA32_DEBUGCTL in vmcs12
+                                           to allow FREEZE_IN_SMM to be set.  When
+                                           this quirk is disabled, KVM requires this
+                                           bit to be cleared.  Note that the vmcs02
+                                           bit is still completely controlled by the
+                                           host, regardless of the quirk setting.
+========================================   ================================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
 ------------------------
-- 
cgit v1.2.3


From f879365c5bb210ed0d0b0aae1a0202d0c0b4b9d0 Mon Sep 17 00:00:00 2001
From: CL Wang <cl634@andestech.com>
Date: Tue, 3 Mar 2026 10:47:37 +0800
Subject: spi: atcspi200: Handle invalid buswidth and fix compiler warning

The kernel test robot reported a compile-time error regarding the
FIELD_PREP() value being too large for the TRANS_DUAL_QUAD field:

  error: FIELD_PREP: value too large for the field
  note: in expansion of macro 'TRANS_DUAL_QUAD'
  tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1);

This occurs because TRANS_DUAL_QUAD is defined as a 2-bit field, and
GCC's static analysis cannot deduce that `ffs(op->data.buswidth) - 1`
will strictly fall within the 0~3 range. Although the SPI framework
guarantees that `op->data.buswidth` is valid at runtime (e.g., 1, 2,
4, 8), an explicit bounds check is necessary to satisfy the compiler.

To resolve the build warning, introduce a safe fallback mechanism.
If an unexpected buswidth is encountered, the driver will trigger
a WARN_ON_ONCE to leave a trace and fall back to width_code = 0
(standard 1-bit SPI mode). This approach guarantees predictable
hardware behavior.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602140738.P7ZozxzI-lkp@intel.com/
Suggested-by: Pei Xiao <xiaopei01@kylinos.cn>
Signed-off-by: CL Wang <cl634@andestech.com>
Link: https://patch.msgid.link/20260303024737.1791196-1-cl634@andestech.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-atcspi200.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-atcspi200.c b/drivers/spi/spi-atcspi200.c
index fef6954d27e1..2665f31a49ce 100644
--- a/drivers/spi/spi-atcspi200.c
+++ b/drivers/spi/spi-atcspi200.c
@@ -195,7 +195,15 @@ static void atcspi_set_trans_ctl(struct atcspi_dev *spi,
 	if (op->addr.buswidth > 1)
 		tc |= TRANS_ADDR_FMT;
 	if (op->data.nbytes) {
-		tc |= TRANS_DUAL_QUAD(ffs(op->data.buswidth) - 1);
+		unsigned int width_code;
+
+		width_code = ffs(op->data.buswidth) - 1;
+		if (unlikely(width_code > 3)) {
+			WARN_ON_ONCE(1);
+			width_code = 0;
+		}
+		tc |= TRANS_DUAL_QUAD(width_code);
+
 		if (op->data.dir == SPI_MEM_DATA_IN) {
 			if (op->dummy.nbytes)
 				tc |= TRANS_MODE_DMY_READ |
-- 
cgit v1.2.3


From 30c64fb9839949f085c8eb55b979cbd8a4c51f00 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Tue, 10 Mar 2026 12:43:27 +0800
Subject: ASoC: amd: acp-mach-common: Add missing error check for clock
 acquisition

The acp_card_rt5682_init() and acp_card_rt5682s_init() functions did not
check the return values of clk_get(). This could lead to a kernel crash
when the invalid pointers are later dereferenced by clock core
functions.

Fix this by:
1. Changing clk_get() to the device-managed devm_clk_get().
2. Adding IS_ERR() checks immediately after each clock acquisition.

Fixes: 8b7256266848 ("ASoC: amd: acp: Add support for RT5682-VS codec")
Fixes: d4c750f2c7d4 ("ASoC: amd: acp: Add generic machine driver support for ACP cards")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Link: https://patch.msgid.link/20260310044327.2582018-1-nichen@iscas.ac.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-mach-common.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c
index 4d99472c75ba..09f6c9a2c041 100644
--- a/sound/soc/amd/acp/acp-mach-common.c
+++ b/sound/soc/amd/acp/acp-mach-common.c
@@ -127,8 +127,13 @@ static int acp_card_rt5682_init(struct snd_soc_pcm_runtime *rtd)
 	if (drvdata->hs_codec_id != RT5682)
 		return -EINVAL;
 
-	drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk");
-	drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk");
+	drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+	if (IS_ERR(drvdata->wclk))
+		return PTR_ERR(drvdata->wclk);
+
+	drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+	if (IS_ERR(drvdata->bclk))
+		return PTR_ERR(drvdata->bclk);
 
 	ret = snd_soc_dapm_new_controls(dapm, rt5682_widgets,
 					ARRAY_SIZE(rt5682_widgets));
@@ -370,8 +375,13 @@ static int acp_card_rt5682s_init(struct snd_soc_pcm_runtime *rtd)
 		return -EINVAL;
 
 	if (!drvdata->soc_mclk) {
-		drvdata->wclk = clk_get(component->dev, "rt5682-dai-wclk");
-		drvdata->bclk = clk_get(component->dev, "rt5682-dai-bclk");
+		drvdata->wclk = devm_clk_get(component->dev, "rt5682-dai-wclk");
+		if (IS_ERR(drvdata->wclk))
+			return PTR_ERR(drvdata->wclk);
+
+		drvdata->bclk = devm_clk_get(component->dev, "rt5682-dai-bclk");
+		if (IS_ERR(drvdata->bclk))
+			return PTR_ERR(drvdata->bclk);
 	}
 
 	ret = snd_soc_dapm_new_controls(dapm, rt5682s_widgets,
-- 
cgit v1.2.3


From 96189080265e6bb5dde3a4afbaf947af493e3f82 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:21:37 -0600
Subject: io_uring: ensure ctx->rings is stable for task work flags
 manipulation

If DEFER_TASKRUN | SETUP_TASKRUN is used and task work is added while
the ring is being resized, it's possible for the OR'ing of
IORING_SQ_TASKRUN to happen in the small window of swapping into the
new rings and the old rings being freed.

Prevent this by adding a 2nd ->rings pointer, ->rings_rcu, which is
protected by RCU. The task work flags manipulation is inside RCU
already, and if the resize ring freeing is done post an RCU synchronize,
then there's no need to add locking to the fast path of task work
additions.

Note: this is only done for DEFER_TASKRUN, as that's the only setup mode
that supports ring resizing. If this ever changes, then they too need to
use the io_ctx_mark_taskrun() helper.

Link: https://lore.kernel.org/io-uring/20260309062759.482210-1-naup96721@gmail.com/
Cc: stable@vger.kernel.org
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Reported-by: Hao-Yu Yang <naup96721@gmail.com>
Suggested-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  1 +
 io_uring/io_uring.c            |  2 ++
 io_uring/register.c            | 11 +++++++++++
 io_uring/tw.c                  | 22 ++++++++++++++++++++--
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 3e4a82a6f817..dd1420bfcb73 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -388,6 +388,7 @@ struct io_ring_ctx {
 	 * regularly bounce b/w CPUs.
 	 */
 	struct {
+		struct io_rings	__rcu	*rings_rcu;
 		struct llist_head	work_llist;
 		struct llist_head	retry_llist;
 		unsigned long		check_cq;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ccab8562d273..20fdc442e014 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2066,6 +2066,7 @@ static void io_rings_free(struct io_ring_ctx *ctx)
 	io_free_region(ctx->user, &ctx->sq_region);
 	io_free_region(ctx->user, &ctx->ring_region);
 	ctx->rings = NULL;
+	RCU_INIT_POINTER(ctx->rings_rcu, NULL);
 	ctx->sq_sqes = NULL;
 }
 
@@ -2703,6 +2704,7 @@ static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 	if (ret)
 		return ret;
 	ctx->rings = rings = io_region_get_ptr(&ctx->ring_region);
+	rcu_assign_pointer(ctx->rings_rcu, rings);
 	if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
 		ctx->sq_array = (u32 *)((char *)rings + rl->sq_array_offset);
 
diff --git a/io_uring/register.c b/io_uring/register.c
index a839b22fd392..5f3eb018fb32 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -633,7 +633,15 @@ overflow:
 	ctx->sq_entries = p->sq_entries;
 	ctx->cq_entries = p->cq_entries;
 
+	/*
+	 * Just mark any flag we may have missed and that the application
+	 * should act on unconditionally. Worst case it'll be an extra
+	 * syscall.
+	 */
+	atomic_or(IORING_SQ_TASKRUN | IORING_SQ_NEED_WAKEUP, &n.rings->sq_flags);
 	ctx->rings = n.rings;
+	rcu_assign_pointer(ctx->rings_rcu, n.rings);
+
 	ctx->sq_sqes = n.sq_sqes;
 	swap_old(ctx, o, n, ring_region);
 	swap_old(ctx, o, n, sq_region);
@@ -642,6 +650,9 @@ overflow:
 out:
 	spin_unlock(&ctx->completion_lock);
 	mutex_unlock(&ctx->mmap_lock);
+	/* Wait for concurrent io_ctx_mark_taskrun() */
+	if (to_free == &o)
+		synchronize_rcu_expedited();
 	io_register_free_rings(ctx, to_free);
 
 	if (ctx->sq_data)
diff --git a/io_uring/tw.c b/io_uring/tw.c
index 1ee2b8ab07c8..2f2b4ac4b126 100644
--- a/io_uring/tw.c
+++ b/io_uring/tw.c
@@ -152,6 +152,21 @@ void tctx_task_work(struct callback_head *cb)
 	WARN_ON_ONCE(ret);
 }
 
+/*
+ * Sets IORING_SQ_TASKRUN in the sq_flags shared with userspace, using the
+ * RCU protected rings pointer to be safe against concurrent ring resizing.
+ */
+static void io_ctx_mark_taskrun(struct io_ring_ctx *ctx)
+{
+	lockdep_assert_in_rcu_read_lock();
+
+	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG) {
+		struct io_rings *rings = rcu_dereference(ctx->rings_rcu);
+
+		atomic_or(IORING_SQ_TASKRUN, &rings->sq_flags);
+	}
+}
+
 void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;
@@ -206,8 +221,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 	 */
 
 	if (!head) {
-		if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
-			atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+		io_ctx_mark_taskrun(ctx);
 		if (ctx->has_evfd)
 			io_eventfd_signal(ctx, false);
 	}
@@ -231,6 +245,10 @@ void io_req_normal_work_add(struct io_kiocb *req)
 	if (!llist_add(&req->io_task_work.node, &tctx->task_list))
 		return;
 
+	/*
+	 * Doesn't need to use ->rings_rcu, as resizing isn't supported for
+	 * !DEFER_TASKRUN.
+	 */
 	if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
 		atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
 
-- 
cgit v1.2.3


From 177c69432161f6e4bab07ccacf8a1748a6898a6b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Mar 2026 14:35:49 -0600
Subject: io_uring/eventfd: use ctx->rings_rcu for flags checking

Similarly to what commit e78f7b70e837 did for local task work additions,
use ->rings_rcu under RCU rather than dereference ->rings directly. See
that commit for more details.

Cc: stable@vger.kernel.org
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/eventfd.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c
index 78f8ab7db104..ab789e1ebe91 100644
--- a/io_uring/eventfd.c
+++ b/io_uring/eventfd.c
@@ -76,11 +76,15 @@ void io_eventfd_signal(struct io_ring_ctx *ctx, bool cqe_event)
 {
 	bool skip = false;
 	struct io_ev_fd *ev_fd;
-
-	if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
-		return;
+	struct io_rings *rings;
 
 	guard(rcu)();
+
+	rings = rcu_dereference(ctx->rings_rcu);
+	if (!rings)
+		return;
+	if (READ_ONCE(rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
+		return;
 	ev_fd = rcu_dereference(ctx->io_ev_fd);
 	/*
 	 * Check again if ev_fd exists in case an io_eventfd_unregister call
-- 
cgit v1.2.3


From 6f02c6b196036dbb6defb4647d8707d29b7fe95b Mon Sep 17 00:00:00 2001
From: Tom Ryan <ryan36005@gmail.com>
Date: Mon, 9 Mar 2026 22:20:02 -0700
Subject: io_uring: fix physical SQE bounds check for SQE_MIXED 128-byte ops

When IORING_SETUP_SQE_MIXED is used without IORING_SETUP_NO_SQARRAY,
the boundary check for 128-byte SQE operations in io_init_req()
validated the logical SQ head position rather than the physical SQE
index.

The existing check:

  !(ctx->cached_sq_head & (ctx->sq_entries - 1))

ensures the logical position isn't at the end of the ring, which is
correct for NO_SQARRAY rings where physical == logical. However, when
sq_array is present, an unprivileged user can remap any logical
position to an arbitrary physical index via sq_array. Setting
sq_array[N] = sq_entries - 1 places a 128-byte operation at the last
physical SQE slot, causing the 128-byte memcpy in
io_uring_cmd_sqe_copy() to read 64 bytes past the end of the SQE
array.

Replace the cached_sq_head alignment check with a direct validation
of the physical SQE index, which correctly handles both sq_array and
NO_SQARRAY cases.

Fixes: 1cba30bf9fdd ("io_uring: add support for IORING_SETUP_SQE_MIXED")
Signed-off-by: Tom Ryan <ryan36005@gmail.com>
Link: https://patch.msgid.link/20260310052003.72871-1-ryan36005@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 20fdc442e014..20ec8fdafcae 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1745,7 +1745,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		 * well as 2 contiguous entries.
 		 */
 		if (!(ctx->flags & IORING_SETUP_SQE_MIXED) || *left < 2 ||
-		    !(ctx->cached_sq_head & (ctx->sq_entries - 1)))
+		    (unsigned)(sqe - ctx->sq_sqes) >= ctx->sq_entries - 1)
 			return io_init_fail_req(req, -EINVAL);
 		/*
 		 * A 128b operation on a mixed SQ uses two entries, so we have
-- 
cgit v1.2.3


From 35b16a7a2c4fc458304447128b86514ce9f70f3c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 10 Mar 2026 13:59:51 -0400
Subject: perf synthetic-events: Fix stale build ID in module MMAP2 records

perf_event__synthesize_modules() allocates a single union perf_event and
reuses it across every kernel module callback.

After the first module is processed, perf_record_mmap2__read_build_id()
sets PERF_RECORD_MISC_MMAP_BUILD_ID in header.misc and writes that
module's build ID into the event.

On subsequent iterations the callback overwrites start, len, pid, and
filename for the next module but never clears the stale build ID fields
or the MMAP_BUILD_ID flag.

When perf_record_mmap2__read_build_id() runs for the second module it
sees the flag, reads the stale build ID into a dso_id, and
__dso__improve_id() permanently poisons the DSO with the wrong build ID.

Every module after the first therefore receives the first module's build
ID in its MMAP2 record.

On a system with the sunrpc and nfsd modules loaded, this causes perf
script and perf report to show [unknown] for all module symbols.

The latent bug has existed since commit d9f2ecbc5e47fca7 ("perf dso:
Move build_id to dso_id") introduced the PERF_RECORD_MISC_MMAP_BUILD_ID
check in perf_record_mmap2__read_build_id().

Commit 53b00ff358dc75b1 ("perf record: Make --buildid-mmap the default")
then exposed it to all users by making the MMAP2-with-build-ID path the
default.  Both commits were merged in the same series.

Clear the MMAP_BUILD_ID flag and zero the build_id union before each
call to perf_record_mmap2__read_build_id() so that every module starts
with a clean slate.

Fixes: d9f2ecbc5e47fca7 ("perf dso: Move build_id to dso_id")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/synthetic-events.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index ef79433ebc3a..ddf1cbda1902 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -703,6 +703,11 @@ static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data)
 
 		memcpy(event->mmap2.filename, dso__long_name(dso), dso__long_name_len(dso) + 1);
 
+		/* Clear stale build ID from previous module iteration */
+		event->mmap2.header.misc &= ~PERF_RECORD_MISC_MMAP_BUILD_ID;
+		memset(event->mmap2.build_id, 0, sizeof(event->mmap2.build_id));
+		event->mmap2.build_id_size = 0;
+
 		perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false);
 	} else {
 		size = PERF_ALIGN(dso__long_name_len(dso) + 1, sizeof(u64));
-- 
cgit v1.2.3


From 4167b8914463132654e01e16259847d097f8a7f7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:38 +0200
Subject: i3c: mipi-i3c-hci: Use ETIMEDOUT instead of ETIME for timeout errors

The MIPI I3C HCI driver currently returns -ETIME for various timeout
conditions, while other I3C master drivers consistently use -ETIMEDOUT
for the same class of errors.  Align the HCI driver with the rest of the
subsystem by replacing all uses of -ETIME with -ETIMEDOUT.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-2-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c | 2 +-
 drivers/i3c/master/mipi-i3c-hci/cmd_v2.c | 2 +-
 drivers/i3c/master/mipi-i3c-hci/core.c   | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index fe260461e7e6..831a261f6c56 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -334,7 +334,7 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 		hci->io->queue_xfer(hci, xfer, 1);
 		if (!wait_for_completion_timeout(&done, HZ) &&
 		    hci->io->dequeue_xfer(hci, xfer, 1)) {
-			ret = -ETIME;
+			ret = -ETIMEDOUT;
 			break;
 		}
 		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
index 3729e6419581..054beee36da5 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
@@ -275,7 +275,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 		hci->io->queue_xfer(hci, xfer, 2);
 		if (!wait_for_completion_timeout(&done, HZ) &&
 		    hci->io->dequeue_xfer(hci, xfer, 2)) {
-			ret = -ETIME;
+			ret = -ETIMEDOUT;
 			break;
 		}
 		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 5879bba78164..dbe93df0c70e 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -261,7 +261,7 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 		goto out;
 	if (!wait_for_completion_timeout(&done, HZ) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = prefixed; i < nxfers; i++) {
@@ -340,7 +340,7 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev,
 		goto out;
 	if (!wait_for_completion_timeout(&done, HZ) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = 0; i < nxfers; i++) {
@@ -388,7 +388,7 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 		goto out;
 	if (!wait_for_completion_timeout(&done, m->i2c.timeout) &&
 	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIME;
+		ret = -ETIMEDOUT;
 		goto out;
 	}
 	for (i = 0; i < nxfers; i++) {
-- 
cgit v1.2.3


From fa9586bd77ada1e3861c7bef65f6bb9dcf8d9481 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:39 +0200
Subject: i3c: mipi-i3c-hci: Fix Hot-Join NACK

The MIPI I3C HCI host controller driver does not implement Hot-Join
handling, yet Hot-Join response control defaults to allowing devices to
Hot-Join the bus.  Configure HC_CONTROL_HOT_JOIN_CTRL to NACK all Hot-Join
attempts.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-3-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index dbe93df0c70e..4877a321edf9 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -152,7 +152,8 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m)
 	if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD)
 		amd_set_resp_buf_thld(hci);
 
-	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE);
+	/* Enable bus with Hot-Join disabled */
+	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 	dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL));
 
 	return 0;
@@ -764,7 +765,8 @@ static int i3c_hci_runtime_resume(struct device *dev)
 
 	hci->io->resume(hci);
 
-	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE);
+	/* Enable bus with Hot-Join disabled */
+	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f3bcbfe1b8b0b836b772927f75f8cb6e759eb00a Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:40 +0200
Subject: i3c: mipi-i3c-hci: Factor out DMA mapping from queuing path

Prepare for fixing a race in the DMA ring enqueue path when handling
parallel transfers.  Move all DMA mapping out of hci_dma_queue_xfer()
and into a new helper that performs the mapping up front.

This refactoring allows the upcoming fix to extend the spinlock coverage
around the enqueue operation without performing DMA mapping under the
spinlock.

No functional change is intended in this patch.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-4-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 49 +++++++++++++++++++++++------------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index b903a2da1fd1..ba451f026386 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -439,6 +439,33 @@ static void hci_dma_unmap_xfer(struct i3c_hci *hci,
 	}
 }
 
+static struct i3c_dma *hci_dma_map_xfer(struct device *dev, struct hci_xfer *xfer)
+{
+	enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	bool need_bounce = device_iommu_mapped(dev) && xfer->rnw && (xfer->data_len & 3);
+
+	return i3c_master_dma_map_single(dev, xfer->data, xfer->data_len, need_bounce, dir);
+}
+
+static int hci_dma_map_xfer_list(struct i3c_hci *hci, struct device *dev,
+				 struct hci_xfer *xfer_list, int n)
+{
+	for (int i = 0; i < n; i++) {
+		struct hci_xfer *xfer = xfer_list + i;
+
+		if (!xfer->data)
+			continue;
+
+		xfer->dma = hci_dma_map_xfer(dev, xfer);
+		if (!xfer->dma) {
+			hci_dma_unmap_xfer(hci, xfer_list, i);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
 static int hci_dma_queue_xfer(struct i3c_hci *hci,
 			      struct hci_xfer *xfer_list, int n)
 {
@@ -446,6 +473,11 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
 	u32 op1_val, op2_val;
+	int ret;
+
+	ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n);
+	if (ret)
+		return ret;
 
 	/* For now we only use ring 0 */
 	ring = 0;
@@ -456,9 +488,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	for (i = 0; i < n; i++) {
 		struct hci_xfer *xfer = xfer_list + i;
 		u32 *ring_data = rh->xfer + rh->xfer_struct_sz * enqueue_ptr;
-		enum dma_data_direction dir = xfer->rnw ? DMA_FROM_DEVICE :
-							  DMA_TO_DEVICE;
-		bool need_bounce;
 
 		/* store cmd descriptor */
 		*ring_data++ = xfer->cmd_desc[0];
@@ -477,18 +506,6 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 
 		/* 2nd and 3rd words of Data Buffer Descriptor Structure */
 		if (xfer->data) {
-			need_bounce = device_iommu_mapped(rings->sysdev) &&
-				      xfer->rnw &&
-				      xfer->data_len != ALIGN(xfer->data_len, 4);
-			xfer->dma = i3c_master_dma_map_single(rings->sysdev,
-							      xfer->data,
-							      xfer->data_len,
-							      need_bounce,
-							      dir);
-			if (!xfer->dma) {
-				hci_dma_unmap_xfer(hci, xfer_list, i);
-				return -ENOMEM;
-			}
 			*ring_data++ = lower_32_bits(xfer->dma->addr);
 			*ring_data++ = upper_32_bits(xfer->dma->addr);
 		} else {
@@ -511,7 +528,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 		op2_val = rh_reg_read(RING_OPERATION2);
 		if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) {
 			/* the ring is full */
-			hci_dma_unmap_xfer(hci, xfer_list, i + 1);
+			hci_dma_unmap_xfer(hci, xfer_list, n);
 			return -EBUSY;
 		}
 	}
-- 
cgit v1.2.3


From fa12bb903bc3ed1826e355d267fe134bde95e23c Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:41 +0200
Subject: i3c: mipi-i3c-hci: Consolidate spinlocks

The MIPI I3C HCI driver currently uses separate spinlocks for different
contexts (PIO vs. DMA rings).  This split is unnecessary and complicates
upcoming fixes.  The driver does not support concurrent PIO and DMA
operation, and it only supports a single DMA ring, so a single lock is
sufficient for all paths.

Introduce a unified spinlock in struct i3c_hci, switch both PIO and DMA
code to use it, and remove the per-context locks.

No functional change is intended in this patch.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-5-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c |  2 ++
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 14 ++++++--------
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  1 +
 drivers/i3c/master/mipi-i3c-hci/pio.c  | 16 +++++++---------
 4 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 4877a321edf9..faf5eae2409f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -926,6 +926,8 @@ static int i3c_hci_probe(struct platform_device *pdev)
 	if (!hci)
 		return -ENOMEM;
 
+	spin_lock_init(&hci->lock);
+
 	/*
 	 * Multi-bus instances share the same MMIO address range, but not
 	 * necessarily in separate contiguous sub-ranges. To avoid overlapping
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index ba451f026386..2442cedd5c2a 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -131,7 +131,6 @@ struct hci_rh_data {
 	unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz;
 	unsigned int done_ptr, ibi_chunk_ptr;
 	struct hci_xfer **src_xfers;
-	spinlock_t lock;
 	struct completion op_done;
 };
 
@@ -344,7 +343,6 @@ static int hci_dma_init(struct i3c_hci *hci)
 			goto err_out;
 		rh = &rings->headers[i];
 		rh->regs = hci->base_regs + offset;
-		spin_lock_init(&rh->lock);
 		init_completion(&rh->op_done);
 
 		rh->xfer_entries = XFER_RING_ENTRIES;
@@ -534,12 +532,12 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	}
 
 	/* take care to update the hardware enqueue pointer atomically */
-	spin_lock_irq(&rh->lock);
+	spin_lock_irq(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_ENQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock_irq(&rh->lock);
+	spin_unlock_irq(&hci->lock);
 
 	return 0;
 }
@@ -637,12 +635,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 	}
 
 	/* take care to update the software dequeue pointer atomically */
-	spin_lock(&rh->lock);
+	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&rh->lock);
+	spin_unlock(&hci->lock);
 }
 
 static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev,
@@ -823,12 +821,12 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh)
 
 done:
 	/* take care to update the ibi dequeue pointer atomically */
-	spin_lock(&rh->lock);
+	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_IBI_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&rh->lock);
+	spin_unlock(&hci->lock);
 
 	/* update the chunk pointer */
 	rh->ibi_chunk_ptr += ibi_chunks;
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 337b7ab1cb06..f1dd502c071f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -50,6 +50,7 @@ struct i3c_hci {
 	const struct hci_io_ops *io;
 	void *io_data;
 	const struct hci_cmd_ops *cmd;
+	spinlock_t lock;
 	atomic_t next_cmd_tid;
 	bool irq_inactive;
 	u32 caps;
diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c
index f8825ac81408..02866c2237fa 100644
--- a/drivers/i3c/master/mipi-i3c-hci/pio.c
+++ b/drivers/i3c/master/mipi-i3c-hci/pio.c
@@ -123,7 +123,6 @@ struct hci_pio_ibi_data {
 };
 
 struct hci_pio_data {
-	spinlock_t lock;
 	struct hci_xfer *curr_xfer, *xfer_queue;
 	struct hci_xfer *curr_rx, *rx_queue;
 	struct hci_xfer *curr_tx, *tx_queue;
@@ -212,7 +211,6 @@ static int hci_pio_init(struct i3c_hci *hci)
 		return -ENOMEM;
 
 	hci->io_data = pio;
-	spin_lock_init(&pio->lock);
 
 	__hci_pio_init(hci, &size_val);
 
@@ -631,7 +629,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 		xfer[i].data_left = xfer[i].data_len;
 	}
 
-	spin_lock_irq(&pio->lock);
+	spin_lock_irq(&hci->lock);
 	prev_queue_tail = pio->xfer_queue;
 	pio->xfer_queue = &xfer[n - 1];
 	if (pio->curr_xfer) {
@@ -645,7 +643,7 @@ static int hci_pio_queue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 			pio_reg_read(INTR_STATUS),
 			pio_reg_read(INTR_SIGNAL_ENABLE));
 	}
-	spin_unlock_irq(&pio->lock);
+	spin_unlock_irq(&hci->lock);
 	return 0;
 }
 
@@ -716,14 +714,14 @@ static bool hci_pio_dequeue_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int
 	struct hci_pio_data *pio = hci->io_data;
 	int ret;
 
-	spin_lock_irq(&pio->lock);
+	spin_lock_irq(&hci->lock);
 	dev_dbg(&hci->master.dev, "n=%d status=%#x/%#x", n,
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
 	dev_dbg(&hci->master.dev, "main_status = %#x/%#x",
 		readl(hci->base_regs + 0x20), readl(hci->base_regs + 0x28));
 
 	ret = hci_pio_dequeue_xfer_common(hci, pio, xfer, n);
-	spin_unlock_irq(&pio->lock);
+	spin_unlock_irq(&hci->lock);
 	return ret;
 }
 
@@ -1016,13 +1014,13 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	struct hci_pio_data *pio = hci->io_data;
 	u32 status;
 
-	spin_lock(&pio->lock);
+	spin_lock(&hci->lock);
 	status = pio_reg_read(INTR_STATUS);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		status, pio->enabled_irqs);
 	status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS;
 	if (!status) {
-		spin_unlock(&pio->lock);
+		spin_unlock(&hci->lock);
 		return false;
 	}
 
@@ -1058,7 +1056,7 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
-	spin_unlock(&pio->lock);
+	spin_unlock(&hci->lock);
 	return true;
 }
 
-- 
cgit v1.2.3


From 4decbbc8a8cf0a69ab011d7c2c88ed3cd0a00ddd Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:42 +0200
Subject: i3c: mipi-i3c-hci: Fix race in DMA ring enqueue for parallel xfers

The I3C subsystem allows multiple transfers to be queued concurrently.
However, the MIPI I3C HCI driver's DMA enqueue path, hci_dma_queue_xfer(),
lacks sufficient serialization.

In particular, the allocation of the enqueue_ptr and its subsequent update
in the RING_OPERATION1 register, must be done atomically.  Otherwise, for
example, it would be possible for 2 transfers to be allocated the same
enqueue_ptr.

Extend the use of the existing spinlock for that purpose.  Keep a count of
the number of xfers enqueued so that it is easy to determine if the ring
has enough space.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-6-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 2442cedd5c2a..74b255ad6d0f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -129,7 +129,7 @@ struct hci_rh_data {
 	dma_addr_t xfer_dma, resp_dma, ibi_status_dma, ibi_data_dma;
 	unsigned int xfer_entries, ibi_status_entries, ibi_chunks_total;
 	unsigned int xfer_struct_sz, resp_struct_sz, ibi_status_sz, ibi_chunk_sz;
-	unsigned int done_ptr, ibi_chunk_ptr;
+	unsigned int done_ptr, ibi_chunk_ptr, xfer_space;
 	struct hci_xfer **src_xfers;
 	struct completion op_done;
 };
@@ -260,6 +260,7 @@ ring_ready:
 
 	rh->done_ptr = 0;
 	rh->ibi_chunk_ptr = 0;
+	rh->xfer_space = rh->xfer_entries;
 }
 
 static void hci_dma_init_rings(struct i3c_hci *hci)
@@ -470,7 +471,7 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	struct hci_rings_data *rings = hci->io_data;
 	struct hci_rh_data *rh;
 	unsigned int i, ring, enqueue_ptr;
-	u32 op1_val, op2_val;
+	u32 op1_val;
 	int ret;
 
 	ret = hci_dma_map_xfer_list(hci, rings->sysdev, xfer_list, n);
@@ -481,6 +482,14 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 	ring = 0;
 	rh = &rings->headers[ring];
 
+	spin_lock_irq(&hci->lock);
+
+	if (n > rh->xfer_space) {
+		spin_unlock_irq(&hci->lock);
+		hci_dma_unmap_xfer(hci, xfer_list, n);
+		return -EBUSY;
+	}
+
 	op1_val = rh_reg_read(RING_OPERATION1);
 	enqueue_ptr = FIELD_GET(RING_OP1_CR_ENQ_PTR, op1_val);
 	for (i = 0; i < n; i++) {
@@ -518,22 +527,10 @@ static int hci_dma_queue_xfer(struct i3c_hci *hci,
 		xfer->ring_entry = enqueue_ptr;
 
 		enqueue_ptr = (enqueue_ptr + 1) % rh->xfer_entries;
-
-		/*
-		 * We may update the hardware view of the enqueue pointer
-		 * only if we didn't reach its dequeue pointer.
-		 */
-		op2_val = rh_reg_read(RING_OPERATION2);
-		if (enqueue_ptr == FIELD_GET(RING_OP2_CR_DEQ_PTR, op2_val)) {
-			/* the ring is full */
-			hci_dma_unmap_xfer(hci, xfer_list, n);
-			return -EBUSY;
-		}
 	}
 
-	/* take care to update the hardware enqueue pointer atomically */
-	spin_lock_irq(&hci->lock);
-	op1_val = rh_reg_read(RING_OPERATION1);
+	rh->xfer_space -= n;
+
 	op1_val &= ~RING_OP1_CR_ENQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_ENQ_PTR, enqueue_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
@@ -601,6 +598,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 {
 	u32 op1_val, op2_val, resp, *ring_resp;
 	unsigned int tid, done_ptr = rh->done_ptr;
+	unsigned int done_cnt = 0;
 	struct hci_xfer *xfer;
 
 	for (;;) {
@@ -632,10 +630,12 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 
 		done_ptr = (done_ptr + 1) % rh->xfer_entries;
 		rh->done_ptr = done_ptr;
+		done_cnt += 1;
 	}
 
 	/* take care to update the software dequeue pointer atomically */
 	spin_lock(&hci->lock);
+	rh->xfer_space += done_cnt;
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);
-- 
cgit v1.2.3


From 1dca8aee80eea76d2aae21265de5dd64f6ba0f09 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:43 +0200
Subject: i3c: mipi-i3c-hci: Fix race in DMA ring dequeue

The HCI DMA dequeue path (hci_dma_dequeue_xfer()) may be invoked for
multiple transfers that timeout around the same time.  However, the
function is not serialized and can race with itself.

When a timeout occurs, hci_dma_dequeue_xfer() stops the ring, processes
incomplete transfers, and then restarts the ring.  If another timeout
triggers a parallel call into the same function, the two instances may
interfere with each other - stopping or restarting the ring at unexpected
times.

Add a mutex so that hci_dma_dequeue_xfer() is serialized with respect to
itself.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-7-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 1 +
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 2 ++
 drivers/i3c/master/mipi-i3c-hci/hci.h  | 1 +
 3 files changed, 4 insertions(+)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index faf5eae2409f..061e84a5c412 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -927,6 +927,7 @@ static int i3c_hci_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	spin_lock_init(&hci->lock);
+	mutex_init(&hci->control_mutex);
 
 	/*
 	 * Multi-bus instances share the same MMIO address range, but not
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 74b255ad6d0f..f7d411e5e11f 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -547,6 +547,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	unsigned int i;
 	bool did_unqueue = false;
 
+	guard(mutex)(&hci->control_mutex);
+
 	/* stop the ring */
 	rh_reg_write(RING_CONTROL, RING_CTRL_ABORT);
 	if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index f1dd502c071f..9c63d80f7fc4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -51,6 +51,7 @@ struct i3c_hci {
 	void *io_data;
 	const struct hci_cmd_ops *cmd;
 	spinlock_t lock;
+	struct mutex control_mutex;
 	atomic_t next_cmd_tid;
 	bool irq_inactive;
 	u32 caps;
-- 
cgit v1.2.3


From f0b5159637ca0b8feaaa95de0f5ea38f1ba26729 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:44 +0200
Subject: i3c: mipi-i3c-hci: Fix race between DMA ring dequeue and interrupt
 handler

The DMA ring bookkeeping in the MIPI I3C HCI driver is updated from two
contexts: the DMA ring dequeue path (hci_dma_dequeue_xfer()) and the
interrupt handler (hci_dma_xfer_done()).  Both modify the ring's
in-flight transfer state - specifically rh->src_xfers[] and
xfer->ring_entry - but without any serialization.  This allows the two
paths to race, potentially leading to inconsistent ring state.

Serialize access to the shared ring state by extending the existing
spinlock to cover the DMA dequeue path and the entire interrupt handler.
Since the core IRQ handler now holds this lock, remove the per-function
locking from the PIO and DMA sub-handlers.

Additionally, clear the completed entry in rh->src_xfers[] in
hci_dma_xfer_done() so it cannot be matched or completed again.

Finally, place the ring restart sequence under the same lock in
hci_dma_dequeue_xfer() to avoid concurrent enqueue or completion
operations while the ring state is being modified.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-8-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c |  2 ++
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 11 +++++------
 drivers/i3c/master/mipi-i3c-hci/pio.c  |  6 +-----
 3 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 061e84a5c412..adf35b7fa498 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -567,6 +567,8 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 	irqreturn_t result = IRQ_NONE;
 	u32 val;
 
+	guard(spinlock)(&hci->lock);
+
 	/*
 	 * The IRQ can be shared, so the handler may be called when the IRQ is
 	 * due to a different device. That could happen when runtime suspended,
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index f7d411e5e11f..d7840ff69e59 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -560,6 +560,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 		WARN_ON(1);
 	}
 
+	spin_lock_irq(&hci->lock);
+
 	for (i = 0; i < n; i++) {
 		struct hci_xfer *xfer = xfer_list + i;
 		int idx = xfer->ring_entry;
@@ -593,6 +595,8 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	/* restart the ring */
 	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
 
+	spin_unlock_irq(&hci->lock);
+
 	return did_unqueue;
 }
 
@@ -618,6 +622,7 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 			dev_dbg(&hci->master.dev, "orphaned ring entry");
 		} else {
 			hci_dma_unmap_xfer(hci, xfer, 1);
+			rh->src_xfers[done_ptr] = NULL;
 			xfer->ring_entry = -1;
 			xfer->response = resp;
 			if (tid != xfer->cmd_tid) {
@@ -635,14 +640,11 @@ static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 		done_cnt += 1;
 	}
 
-	/* take care to update the software dequeue pointer atomically */
-	spin_lock(&hci->lock);
 	rh->xfer_space += done_cnt;
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_CR_SW_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_CR_SW_DEQ_PTR, done_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&hci->lock);
 }
 
 static int hci_dma_request_ibi(struct i3c_hci *hci, struct i3c_dev_desc *dev,
@@ -822,13 +824,10 @@ static void hci_dma_process_ibi(struct i3c_hci *hci, struct hci_rh_data *rh)
 	i3c_master_queue_ibi(dev, slot);
 
 done:
-	/* take care to update the ibi dequeue pointer atomically */
-	spin_lock(&hci->lock);
 	op1_val = rh_reg_read(RING_OPERATION1);
 	op1_val &= ~RING_OP1_IBI_DEQ_PTR;
 	op1_val |= FIELD_PREP(RING_OP1_IBI_DEQ_PTR, deq_ptr);
 	rh_reg_write(RING_OPERATION1, op1_val);
-	spin_unlock(&hci->lock);
 
 	/* update the chunk pointer */
 	rh->ibi_chunk_ptr += ibi_chunks;
diff --git a/drivers/i3c/master/mipi-i3c-hci/pio.c b/drivers/i3c/master/mipi-i3c-hci/pio.c
index 02866c2237fa..8f48a81e65ab 100644
--- a/drivers/i3c/master/mipi-i3c-hci/pio.c
+++ b/drivers/i3c/master/mipi-i3c-hci/pio.c
@@ -1014,15 +1014,12 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	struct hci_pio_data *pio = hci->io_data;
 	u32 status;
 
-	spin_lock(&hci->lock);
 	status = pio_reg_read(INTR_STATUS);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		status, pio->enabled_irqs);
 	status &= pio->enabled_irqs | STAT_LATENCY_WARNINGS;
-	if (!status) {
-		spin_unlock(&hci->lock);
+	if (!status)
 		return false;
-	}
 
 	if (status & STAT_IBI_STATUS_THLD)
 		hci_pio_process_ibi(hci, pio);
@@ -1056,7 +1053,6 @@ static bool hci_pio_irq_handler(struct i3c_hci *hci)
 	pio_reg_write(INTR_SIGNAL_ENABLE, pio->enabled_irqs);
 	dev_dbg(&hci->master.dev, "PIO_INTR_STATUS %#x/%#x",
 		pio_reg_read(INTR_STATUS), pio_reg_read(INTR_SIGNAL_ENABLE));
-	spin_unlock(&hci->lock);
 	return true;
 }
 
-- 
cgit v1.2.3


From b795e68bf3073d67bebbb5a44d93f49efc5b8cc7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:45 +0200
Subject: i3c: mipi-i3c-hci: Correct RING_CTRL_ABORT handling in DMA dequeue

The logic used to abort the DMA ring contains several flaws:

 1. The driver unconditionally issues a ring abort even when the ring has
    already stopped.
 2. The completion used to wait for abort completion is never
    re-initialized, resulting in incorrect wait behavior.
 3. The abort sequence unintentionally clears RING_CTRL_ENABLE, which
    resets hardware ring pointers and disrupts the controller state.
 4. If the ring is already stopped, the abort operation should be
    considered successful without attempting further action.

Fix the abort handling by checking whether the ring is running before
issuing an abort, re-initializing the completion when needed, ensuring that
RING_CTRL_ENABLE remains asserted during abort, and treating an already
stopped ring as a successful condition.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-9-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index d7840ff69e59..a3e8e01a35c9 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -546,18 +546,25 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	struct hci_rh_data *rh = &rings->headers[xfer_list[0].ring_number];
 	unsigned int i;
 	bool did_unqueue = false;
+	u32 ring_status;
 
 	guard(mutex)(&hci->control_mutex);
 
-	/* stop the ring */
-	rh_reg_write(RING_CONTROL, RING_CTRL_ABORT);
-	if (wait_for_completion_timeout(&rh->op_done, HZ) == 0) {
-		/*
-		 * We're deep in it if ever this condition is ever met.
-		 * Hardware might still be writing to memory, etc.
-		 */
-		dev_crit(&hci->master.dev, "unable to abort the ring\n");
-		WARN_ON(1);
+	ring_status = rh_reg_read(RING_STATUS);
+	if (ring_status & RING_STATUS_RUNNING) {
+		/* stop the ring */
+		reinit_completion(&rh->op_done);
+		rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_ABORT);
+		wait_for_completion_timeout(&rh->op_done, HZ);
+		ring_status = rh_reg_read(RING_STATUS);
+		if (ring_status & RING_STATUS_RUNNING) {
+			/*
+			 * We're deep in it if ever this condition is ever met.
+			 * Hardware might still be writing to memory, etc.
+			 */
+			dev_crit(&hci->master.dev, "unable to abort the ring\n");
+			WARN_ON(1);
+		}
 	}
 
 	spin_lock_irq(&hci->lock);
-- 
cgit v1.2.3


From ec3cfd835f7c4bbd23bc9ad909d2fdc772a578bb Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:46 +0200
Subject: i3c: mipi-i3c-hci: Add missing TID field to no-op command descriptor

The internal control command descriptor used for no-op commands includes a
Transaction ID (TID) field, but the no-op command constructed in
hci_dma_dequeue_xfer() omitted it.  As a result, the hardware receives a
no-op descriptor without the expected TID.

This bug has gone unnoticed because the TID is currently not validated in
the no-op completion path, but the descriptor format requires it to be
present.

Add the missing TID field when generating a no-op descriptor so that its
layout matches the defined command structure.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-10-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd.h | 1 +
 drivers/i3c/master/mipi-i3c-hci/dma.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd.h b/drivers/i3c/master/mipi-i3c-hci/cmd.h
index 1d6dd2c5d01a..b1bf87daa651 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd.h
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd.h
@@ -17,6 +17,7 @@
 #define CMD_0_TOC			W0_BIT_(31)
 #define CMD_0_ROC			W0_BIT_(30)
 #define CMD_0_ATTR			W0_MASK(2, 0)
+#define CMD_0_TID			W0_MASK(6, 3)
 
 /*
  * Response Descriptor Structure
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index a3e8e01a35c9..239a195df7c7 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -582,7 +582,7 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 			u32 *ring_data = rh->xfer + rh->xfer_struct_sz * idx;
 
 			/* store no-op cmd descriptor */
-			*ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7);
+			*ring_data++ = FIELD_PREP(CMD_0_ATTR, 0x7) | FIELD_PREP(CMD_0_TID, xfer->cmd_tid);
 			*ring_data++ = 0;
 			if (hci->cmd == &mipi_i3c_hci_cmd_v2) {
 				*ring_data++ = 0;
-- 
cgit v1.2.3


From b6d586431ae20d5157ee468d0ef62ad26798ef13 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:47 +0200
Subject: i3c: mipi-i3c-hci: Restart DMA ring correctly after dequeue abort

The DMA dequeue path attempts to restart the ring after aborting an
in-flight transfer, but the current sequence is incomplete. The controller
must be brought out of the aborted state and the ring control registers
must be programmed in the correct order: first clearing ABORT, then
re-enabling the ring and asserting RUN_STOP to resume operation.

Add the missing controller resume step and update the ring control writes
so that the ring is restarted using the proper sequence.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-11-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 239a195df7c7..41b83f07fdab 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -600,7 +600,9 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	}
 
 	/* restart the ring */
+	mipi_i3c_hci_resume(hci);
 	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
+	rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE | RING_CTRL_RUN_STOP);
 
 	spin_unlock_irq(&hci->lock);
 
-- 
cgit v1.2.3


From 7ac45bc68f089887ab3a70358057edb7e6b6084e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:48 +0200
Subject: i3c: mipi-i3c-hci: Consolidate common xfer processing logic

Several parts of the MIPI I3C HCI driver duplicate the same sequence for
queuing a transfer, waiting for completion, and handling timeouts. This
logic appears in five separate locations and will be affected by an
upcoming fix.

Refactor the repeated code into a new helper, i3c_hci_process_xfer(), and
store the timeout value in the hci_xfer structure so that callers do not
need to pass it as a separate parameter.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-12-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/cmd_v1.c |  8 +++---
 drivers/i3c/master/mipi-i3c-hci/cmd_v2.c |  8 +++---
 drivers/i3c/master/mipi-i3c-hci/core.c   | 43 +++++++++++++++++++-------------
 drivers/i3c/master/mipi-i3c-hci/hci.h    |  2 ++
 4 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
index 831a261f6c56..75d452d7f6af 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v1.c
@@ -331,12 +331,10 @@ static int hci_cmd_v1_daa(struct i3c_hci *hci)
 			CMD_A0_ROC | CMD_A0_TOC;
 		xfer->cmd_desc[1] = 0;
 		xfer->completion = &done;
-		hci->io->queue_xfer(hci, xfer, 1);
-		if (!wait_for_completion_timeout(&done, HZ) &&
-		    hci->io->dequeue_xfer(hci, xfer, 1)) {
-			ret = -ETIMEDOUT;
+		xfer->timeout = HZ;
+		ret = i3c_hci_process_xfer(hci, xfer, 1);
+		if (ret)
 			break;
-		}
 		if ((RESP_STATUS(xfer->response) == RESP_ERR_ADDR_HEADER ||
 		     RESP_STATUS(xfer->response) == RESP_ERR_NACK) &&
 		    RESP_DATA_LENGTH(xfer->response) == 1) {
diff --git a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
index 054beee36da5..39eec26a363c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
+++ b/drivers/i3c/master/mipi-i3c-hci/cmd_v2.c
@@ -253,6 +253,7 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 	xfer[0].rnw = true;
 	xfer[0].cmd_desc[1] = CMD_A1_DATA_LENGTH(8);
 	xfer[1].completion = &done;
+	xfer[1].timeout = HZ;
 
 	for (;;) {
 		ret = i3c_master_get_free_addr(&hci->master, next_addr);
@@ -272,12 +273,9 @@ static int hci_cmd_v2_daa(struct i3c_hci *hci)
 			CMD_A0_ASSIGN_ADDRESS(next_addr) |
 			CMD_A0_ROC |
 			CMD_A0_TOC;
-		hci->io->queue_xfer(hci, xfer, 2);
-		if (!wait_for_completion_timeout(&done, HZ) &&
-		    hci->io->dequeue_xfer(hci, xfer, 2)) {
-			ret = -ETIMEDOUT;
+		ret = i3c_hci_process_xfer(hci, xfer, 2);
+		if (ret)
 			break;
-		}
 		if (RESP_STATUS(xfer[0].response) != RESP_SUCCESS) {
 			ret = 0;  /* no more devices to be assigned */
 			break;
diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index adf35b7fa498..4a80671536f0 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -213,6 +213,25 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci)
 	reg_write(DCT_SECTION, FIELD_PREP(DCT_TABLE_INDEX, 0));
 }
 
+int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
+{
+	struct completion *done = xfer[n - 1].completion;
+	unsigned long timeout = xfer[n - 1].timeout;
+	int ret;
+
+	ret = hci->io->queue_xfer(hci, xfer, n);
+	if (ret)
+		return ret;
+
+	if (!wait_for_completion_timeout(done, timeout) &&
+	    hci->io->dequeue_xfer(hci, xfer, n)) {
+		dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
 static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 				struct i3c_ccc_cmd *ccc)
 {
@@ -253,18 +272,14 @@ static int i3c_hci_send_ccc_cmd(struct i3c_master_controller *m,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = HZ;
 
 	if (prefixed)
 		xfer--;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, HZ) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = prefixed; i < nxfers; i++) {
 		if (ccc->rnw)
 			ccc->dests[i - prefixed].payload.len =
@@ -335,15 +350,11 @@ static int i3c_hci_i3c_xfers(struct i3c_dev_desc *dev,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = HZ;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, HZ) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = 0; i < nxfers; i++) {
 		if (i3c_xfers[i].rnw)
 			i3c_xfers[i].len = RESP_DATA_LENGTH(xfer[i].response);
@@ -383,15 +394,11 @@ static int i3c_hci_i2c_xfers(struct i2c_dev_desc *dev,
 	last = i - 1;
 	xfer[last].cmd_desc[0] |= CMD_0_TOC;
 	xfer[last].completion = &done;
+	xfer[last].timeout = m->i2c.timeout;
 
-	ret = hci->io->queue_xfer(hci, xfer, nxfers);
+	ret = i3c_hci_process_xfer(hci, xfer, nxfers);
 	if (ret)
 		goto out;
-	if (!wait_for_completion_timeout(&done, m->i2c.timeout) &&
-	    hci->io->dequeue_xfer(hci, xfer, nxfers)) {
-		ret = -ETIMEDOUT;
-		goto out;
-	}
 	for (i = 0; i < nxfers; i++) {
 		if (RESP_STATUS(xfer[i].response) != RESP_SUCCESS) {
 			ret = -EIO;
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 9c63d80f7fc4..850016e3d4fe 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -89,6 +89,7 @@ struct hci_xfer {
 	unsigned int data_len;
 	unsigned int cmd_tid;
 	struct completion *completion;
+	unsigned long timeout;
 	union {
 		struct {
 			/* PIO specific */
@@ -156,5 +157,6 @@ void mipi_i3c_hci_dct_index_reset(struct i3c_hci *hci);
 void amd_set_od_pp_timing(struct i3c_hci *hci);
 void amd_set_resp_buf_thld(struct i3c_hci *hci);
 void i3c_hci_sync_irq_inactive(struct i3c_hci *hci);
+int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 
 #endif
-- 
cgit v1.2.3


From e44d2719225e618dde74c7056f8e6949f884095e Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:49 +0200
Subject: i3c: mipi-i3c-hci: Fix race in DMA error handling in interrupt
 context

The DMA ring halts whenever a transfer encounters an error. The interrupt
handler previously attempted to detect this situation and restart the ring
if a transfer completed at the same time. However, this restart logic runs
entirely in interrupt context and is inherently racy: it interacts with
other paths manipulating the ring state, and fully serializing it within
the interrupt handler is not practical.

Move this error-recovery logic out of the interrupt handler and into the
transfer-processing path (i3c_hci_process_xfer()), where serialization and
state management are already controlled. Introduce a new optional I/O-ops
callback, handle_error(), invoked when a completed transfer reports an
error. For DMA operation, the implementation simply calls the existing
dequeue function, which safely aborts and restarts the ring when needed.

This removes the fragile ring-restart logic from the interrupt handler and
centralizes error handling where proper sequencing can be ensured.

Fixes: ccdb2e0e3b00d ("i3c: mipi-i3c-hci: Add Intel specific quirk to ring resuming")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-13-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 19 +++++++++++++++----
 drivers/i3c/master/mipi-i3c-hci/dma.c  | 31 ++++++++-----------------------
 drivers/i3c/master/mipi-i3c-hci/hci.h  |  1 +
 3 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index 4a80671536f0..b98952d12d7c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -223,10 +223,21 @@ int i3c_hci_process_xfer(struct i3c_hci *hci, struct hci_xfer *xfer, int n)
 	if (ret)
 		return ret;
 
-	if (!wait_for_completion_timeout(done, timeout) &&
-	    hci->io->dequeue_xfer(hci, xfer, n)) {
-		dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
-		return -ETIMEDOUT;
+	if (!wait_for_completion_timeout(done, timeout)) {
+		if (hci->io->dequeue_xfer(hci, xfer, n)) {
+			dev_err(&hci->master.dev, "%s: timeout error\n", __func__);
+			return -ETIMEDOUT;
+		}
+		return 0;
+	}
+
+	if (hci->io->handle_error) {
+		bool error = false;
+
+		for (int i = 0; i < n && !error; i++)
+			error = RESP_STATUS(xfer[i].response);
+		if (error)
+			return hci->io->handle_error(hci, xfer, n);
 	}
 
 	return 0;
diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
index 41b83f07fdab..e487ef52f6b4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
+++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
@@ -609,6 +609,11 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci,
 	return did_unqueue;
 }
 
+static int hci_dma_handle_error(struct i3c_hci *hci, struct hci_xfer *xfer_list, int n)
+{
+	return hci_dma_dequeue_xfer(hci, xfer_list, n) ? -EIO : 0;
+}
+
 static void hci_dma_xfer_done(struct i3c_hci *hci, struct hci_rh_data *rh)
 {
 	u32 op1_val, op2_val, resp, *ring_resp;
@@ -870,29 +875,8 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci)
 			hci_dma_xfer_done(hci, rh);
 		if (status & INTR_RING_OP)
 			complete(&rh->op_done);
-
-		if (status & INTR_TRANSFER_ABORT) {
-			u32 ring_status;
-
-			dev_notice_ratelimited(&hci->master.dev,
-				"Ring %d: Transfer Aborted\n", i);
-			mipi_i3c_hci_resume(hci);
-			ring_status = rh_reg_read(RING_STATUS);
-			if (!(ring_status & RING_STATUS_RUNNING) &&
-			    status & INTR_TRANSFER_COMPLETION &&
-			    status & INTR_TRANSFER_ERR) {
-				/*
-				 * Ring stop followed by run is an Intel
-				 * specific required quirk after resuming the
-				 * halted controller. Do it only when the ring
-				 * is not in running state after a transfer
-				 * error.
-				 */
-				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE);
-				rh_reg_write(RING_CONTROL, RING_CTRL_ENABLE |
-							   RING_CTRL_RUN_STOP);
-			}
-		}
+		if (status & INTR_TRANSFER_ABORT)
+			dev_dbg(&hci->master.dev, "Ring %d: Transfer Aborted\n", i);
 		if (status & INTR_IBI_RING_FULL)
 			dev_err_ratelimited(&hci->master.dev,
 				"Ring %d: IBI Ring Full Condition\n", i);
@@ -908,6 +892,7 @@ const struct hci_io_ops mipi_i3c_hci_dma = {
 	.cleanup		= hci_dma_cleanup,
 	.queue_xfer		= hci_dma_queue_xfer,
 	.dequeue_xfer		= hci_dma_dequeue_xfer,
+	.handle_error		= hci_dma_handle_error,
 	.irq_handler		= hci_dma_irq_handler,
 	.request_ibi		= hci_dma_request_ibi,
 	.free_ibi		= hci_dma_free_ibi,
diff --git a/drivers/i3c/master/mipi-i3c-hci/hci.h b/drivers/i3c/master/mipi-i3c-hci/hci.h
index 850016e3d4fe..9ac9d0e342f4 100644
--- a/drivers/i3c/master/mipi-i3c-hci/hci.h
+++ b/drivers/i3c/master/mipi-i3c-hci/hci.h
@@ -123,6 +123,7 @@ struct hci_io_ops {
 	bool (*irq_handler)(struct i3c_hci *hci);
 	int (*queue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	bool (*dequeue_xfer)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
+	int (*handle_error)(struct i3c_hci *hci, struct hci_xfer *xfer, int n);
 	int (*request_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev,
 			   const struct i3c_ibi_setup *req);
 	void (*free_ibi)(struct i3c_hci *hci, struct i3c_dev_desc *dev);
-- 
cgit v1.2.3


From c6396b835a5e599c4df656112140f065bb544a24 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:50 +0200
Subject: i3c: mipi-i3c-hci: Fix handling of shared IRQs during early
 initialization

Shared interrupts may fire unexpectedly, including during periods when the
controller is not yet fully initialized. Commit b9a15012a1452
("i3c: mipi-i3c-hci: Add optional Runtime PM support") addressed this issue
for the runtime-suspended state, but the same problem can also occur before
the bus is enabled for the first time.

Ensure the IRQ handler ignores interrupts until initialization is complete
by making consistent use of the existing irq_inactive flag.  The flag is
now set to false immediately before enabling the bus.

To guarantee correct ordering with respect to the IRQ handler, protect
all transitions of irq_inactive with the same spinlock used inside the
handler.

Fixes: b8460480f62e1 ("i3c: mipi-i3c-hci: Allow for Multi-Bus Instances")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-14-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index b98952d12d7c..d5e91af7d569 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -152,6 +152,9 @@ static int i3c_hci_bus_init(struct i3c_master_controller *m)
 	if (hci->quirks & HCI_QUIRK_RESP_BUF_THLD)
 		amd_set_resp_buf_thld(hci);
 
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = false;
+
 	/* Enable bus with Hot-Join disabled */
 	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 	dev_dbg(&hci->master.dev, "HC_CONTROL = %#x", reg_read(HC_CONTROL));
@@ -184,8 +187,9 @@ void i3c_hci_sync_irq_inactive(struct i3c_hci *hci)
 	int irq = platform_get_irq(pdev, 0);
 
 	reg_write(INTR_SIGNAL_ENABLE, 0x0);
-	hci->irq_inactive = true;
 	synchronize_irq(irq);
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = true;
 }
 
 static void i3c_hci_bus_cleanup(struct i3c_master_controller *m)
@@ -781,10 +785,11 @@ static int i3c_hci_runtime_resume(struct device *dev)
 
 	mipi_i3c_hci_dat_v1.restore(hci);
 
-	hci->irq_inactive = false;
-
 	hci->io->resume(hci);
 
+	scoped_guard(spinlock_irqsave, &hci->lock)
+		hci->irq_inactive = false;
+
 	/* Enable bus with Hot-Join disabled */
 	reg_set(HC_CONTROL, HC_CONTROL_BUS_ENABLE | HC_CONTROL_HOT_JOIN_CTRL);
 
@@ -975,6 +980,8 @@ static int i3c_hci_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	hci->irq_inactive = true;
+
 	irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, irq, i3c_hci_irq_handler,
 			       IRQF_SHARED, NULL, hci);
-- 
cgit v1.2.3


From 9a258d1336f7ff3add8b92d566d3a421f03bf4d2 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Mar 2026 09:24:51 +0200
Subject: i3c: mipi-i3c-hci: Fallback to software reset when bus disable fails

Disruption of the MIPI I3C HCI controller's internal state can cause
i3c_hci_bus_disable() to fail when attempting to shut down the bus.

In the code paths where bus disable is invoked - bus clean-up and runtime
suspend - the controller does not need to remain operational afterward, so
a full controller reset is a safe recovery mechanism.

Add a fallback to issue a software reset when disabling the bus fails.
This ensures the bus is reliably halted even if the controller's state
machine is stuck or unresponsive.

The fallback is used both during bus clean-up and in the runtime suspend
path.  In the latter case, ensure interrupts are quiesced after reset.

Fixes: 9ad9a52cce282 ("i3c/master: introduce the mipi-i3c-hci driver")
Cc: stable@vger.kernel.org
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260306072451.11131-15-adrian.hunter@intel.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/mipi-i3c-hci/core.c | 65 ++++++++++++++++++----------------
 1 file changed, 35 insertions(+), 30 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
index d5e91af7d569..284f3ed7af8c 100644
--- a/drivers/i3c/master/mipi-i3c-hci/core.c
+++ b/drivers/i3c/master/mipi-i3c-hci/core.c
@@ -181,6 +181,34 @@ static int i3c_hci_bus_disable(struct i3c_hci *hci)
 	return ret;
 }
 
+static int i3c_hci_software_reset(struct i3c_hci *hci)
+{
+	u32 regval;
+	int ret;
+
+	/*
+	 * SOFT_RST must be clear before we write to it.
+	 * Then we must wait until it clears again.
+	 */
+	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
+				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
+	if (ret) {
+		dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__);
+		return ret;
+	}
+
+	reg_write(RESET_CONTROL, SOFT_RST);
+
+	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
+				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
+	if (ret) {
+		dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__);
+		return ret;
+	}
+
+	return 0;
+}
+
 void i3c_hci_sync_irq_inactive(struct i3c_hci *hci)
 {
 	struct platform_device *pdev = to_platform_device(hci->master.dev.parent);
@@ -196,7 +224,8 @@ static void i3c_hci_bus_cleanup(struct i3c_master_controller *m)
 {
 	struct i3c_hci *hci = to_i3c_hci(m);
 
-	i3c_hci_bus_disable(hci);
+	if (i3c_hci_bus_disable(hci))
+		i3c_hci_software_reset(hci);
 	hci->io->cleanup(hci);
 }
 
@@ -626,34 +655,6 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
 	return result;
 }
 
-static int i3c_hci_software_reset(struct i3c_hci *hci)
-{
-	u32 regval;
-	int ret;
-
-	/*
-	 * SOFT_RST must be clear before we write to it.
-	 * Then we must wait until it clears again.
-	 */
-	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
-				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
-	if (ret) {
-		dev_err(&hci->master.dev, "%s: Software reset stuck\n", __func__);
-		return ret;
-	}
-
-	reg_write(RESET_CONTROL, SOFT_RST);
-
-	ret = readx_poll_timeout(reg_read, RESET_CONTROL, regval,
-				 !(regval & SOFT_RST), 0, 10 * USEC_PER_MSEC);
-	if (ret) {
-		dev_err(&hci->master.dev, "%s: Software reset failed\n", __func__);
-		return ret;
-	}
-
-	return 0;
-}
-
 static inline bool is_version_1_1_or_newer(struct i3c_hci *hci)
 {
 	return hci->version_major > 1 || (hci->version_major == 1 && hci->version_minor > 0);
@@ -764,8 +765,12 @@ static int i3c_hci_runtime_suspend(struct device *dev)
 	int ret;
 
 	ret = i3c_hci_bus_disable(hci);
-	if (ret)
+	if (ret) {
+		/* Fall back to software reset to disable the bus */
+		ret = i3c_hci_software_reset(hci);
+		i3c_hci_sync_irq_inactive(hci);
 		return ret;
+	}
 
 	hci->io->suspend(hci);
 
-- 
cgit v1.2.3


From f26ecaa0f0abfe5db173416214098a00d3b7db79 Mon Sep 17 00:00:00 2001
From: Peter Yin <peteryin.openbmc@gmail.com>
Date: Mon, 2 Mar 2026 15:56:42 +0800
Subject: i3c: master: dw-i3c: Fix missing of_node for virtual I2C adapter

The DesignWare I3C master driver creates a virtual I2C adapter to
provide backward compatibility with I2C devices. However, the current
implementation does not associate this virtual adapter with any
Device Tree node.

Propagate the of_node from the I3C master platform device to the
virtual I2C adapter's device structure. This ensures that standard
I2C aliases are correctly resolved and bus numbering remains consistent.

Signed-off-by: Peter Yin <peteryin.openbmc@gmail.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20260302075645.1492766-1-peteryin.openbmc@gmail.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index d87bde3f7700..d334c217c7a3 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1659,6 +1659,8 @@ int dw_i3c_common_probe(struct dw_i3c_master *master,
 		pm_runtime_get_noresume(&pdev->dev);
 
 	INIT_WORK(&master->hj_work, dw_i3c_hj_work);
+
+	device_set_of_node_from_dev(&master->base.i2c.dev, &pdev->dev);
 	ret = i3c_master_register(&master->base, &pdev->dev,
 				  &dw_mipi_i3c_ops, false);
 	if (ret)
-- 
cgit v1.2.3


From f311a05784634febd299f03476b80f3f18489767 Mon Sep 17 00:00:00 2001
From: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Date: Fri, 13 Feb 2026 14:00:48 +0800
Subject: i3c: dw-i3c-master: Set SIR_REJECT in DAT on device attach and
 reattach

The DesignWare I3C master controller ACKs IBIs as soon as a valid
Device Address Table (DAT) entry is present. This can create a race
between device attachment (after DAA) and the point where the client
driver enables IBIs via i3c_device_enable_ibi().

Set DEV_ADDR_TABLE_SIR_REJECT in the DAT entry during
attach_i3c_dev() and reattach_i3c_dev() so that IBIs are rejected
by default. The bit is managed thereafter by the existing
dw_i3c_master_set_sir_enabled() function, which clears it in
enable_ibi() after ENEC is issued, and restores it in disable_ibi()
after DISEC.

Fixes: 1dd728f5d4d4 ("i3c: master: Add driver for Synopsys DesignWare IP")
Signed-off-by: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/53f5b8cbdd8af789ec38b95b02873f32f9182dd6.1770962368.git.adrianhoyin.ng@altera.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master/dw-i3c-master.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index d334c217c7a3..d6bdb32397fb 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -1024,7 +1024,7 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev,
 		master->free_pos &= ~BIT(pos);
 	}
 
-	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr),
+	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(dev->info.dyn_addr) | DEV_ADDR_TABLE_SIR_REJECT,
 	       master->regs +
 	       DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index));
 
@@ -1053,7 +1053,7 @@ static int dw_i3c_master_attach_i3c_dev(struct i3c_dev_desc *dev)
 	master->free_pos &= ~BIT(pos);
 	i3c_dev_set_master_data(dev, data);
 
-	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr),
+	writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr) | DEV_ADDR_TABLE_SIR_REJECT,
 	       master->regs +
 	       DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index));
 
-- 
cgit v1.2.3


From d4c7210d2f3ea481a6481f03040a64d9077a6172 Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Wed, 11 Mar 2026 20:17:23 -0300
Subject: smb: client: fix iface port assignment in parse_server_interfaces

parse_server_interfaces() initializes interface socket addresses with
CIFS_PORT. When the mount uses a non-default port this overwrites the
configured destination port.

Later, cifs_chan_update_iface() copies this sockaddr into server->dstaddr,
causing reconnect attempts to use the wrong port after server interface
updates.

Use the existing port from server->dstaddr instead.

Cc: stable@vger.kernel.org
Fixes: fe856be475f7 ("CIFS: parse and store info on iface queries")
Tested-by: Dr. Thomas Orgis <thomas.orgis@uni-hamburg.de>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 7f2d3459cbf9..612057318de2 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -628,6 +628,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 	struct smb_sockaddr_in6 *p6;
 	struct cifs_server_iface *info = NULL, *iface = NULL, *niface = NULL;
 	struct cifs_server_iface tmp_iface;
+	__be16 port;
 	ssize_t bytes_left;
 	size_t next = 0;
 	int nb_iface = 0;
@@ -662,6 +663,15 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 		goto out;
 	}
 
+	spin_lock(&ses->server->srv_lock);
+	if (ses->server->dstaddr.ss_family == AF_INET)
+		port = ((struct sockaddr_in *)&ses->server->dstaddr)->sin_port;
+	else if (ses->server->dstaddr.ss_family == AF_INET6)
+		port = ((struct sockaddr_in6 *)&ses->server->dstaddr)->sin6_port;
+	else
+		port = cpu_to_be16(CIFS_PORT);
+	spin_unlock(&ses->server->srv_lock);
+
 	while (bytes_left >= (ssize_t)sizeof(*p)) {
 		memset(&tmp_iface, 0, sizeof(tmp_iface));
 		/* default to 1Gbps when link speed is unset */
@@ -682,7 +692,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 			memcpy(&addr4->sin_addr, &p4->IPv4Address, 4);
 
 			/* [MS-SMB2] 2.2.32.5.1.1 Clients MUST ignore these */
-			addr4->sin_port = cpu_to_be16(CIFS_PORT);
+			addr4->sin_port = port;
 
 			cifs_dbg(FYI, "%s: ipv4 %pI4\n", __func__,
 				 &addr4->sin_addr);
@@ -696,7 +706,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
 			/* [MS-SMB2] 2.2.32.5.1.2 Clients MUST ignore these */
 			addr6->sin6_flowinfo = 0;
 			addr6->sin6_scope_id = 0;
-			addr6->sin6_port = cpu_to_be16(CIFS_PORT);
+			addr6->sin6_port = port;
 
 			cifs_dbg(FYI, "%s: ipv6 %pI6\n", __func__,
 				 &addr6->sin6_addr);
-- 
cgit v1.2.3


From 40e75e42f49ca54b4ff41f3edb94f5ef0299140c Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 11 Mar 2026 15:00:52 -0300
Subject: smb: client: fix open handle lookup in cifs_open()

When looking up open handles to be re-used in cifs_open(), calling
cifs_get_{writable,readable}_path() is wrong as it will look up for
the first matching open handle, and if @file->f_flags doesn't match,
it will ignore the remaining open handles in
cifsInodeInfo::openFileList that might potentially match
@file->f_flags.

For writable and readable handles, fix this by calling
__cifs_get_writable_file() and __find_readable_file(), respectively,
with FIND_OPEN_FLAGS set.

With the patch, the following program ends up with two opens instead
of three sent over the wire.

```
  #define _GNU_SOURCE
  #include <unistd.h>
  #include <string.h>
  #include <fcntl.h>

  int main(int argc, char *argv[])
  {
          int fd;

          fd = open("/mnt/1/foo", O_CREAT | O_WRONLY | O_TRUNC, 0664);
          close(fd);
          fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY);
          close(fd);
          fd = open("/mnt/1/foo", O_WRONLY);
          close(fd);
          fd = open("/mnt/1/foo", O_DIRECT | O_WRONLY);
          close(fd);
          return 0;
  }
```

```
$ mount.cifs //srv/share /mnt/1 -o ...
$ gcc test.c && ./a.out
```

Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c   |   2 +-
 fs/smb/client/cifsfs.c    |   2 +-
 fs/smb/client/cifsglob.h  |  12 ++---
 fs/smb/client/cifsproto.h |  26 +++++++++--
 fs/smb/client/file.c      | 113 +++++++++++++++++++++++++++-------------------
 fs/smb/client/inode.c     |   6 +--
 fs/smb/client/smb1ops.c   |   2 +-
 fs/smb/client/smb2inode.c |  22 ++++-----
 fs/smb/client/smb2ops.c   |   4 +-
 9 files changed, 113 insertions(+), 76 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index f4cb3018a358..c920039d733c 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -1489,7 +1489,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 	struct cifsFileInfo *open_file = NULL;
 
 	if (inode)
-		open_file = find_readable_file(CIFS_I(inode), true);
+		open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY);
 	if (!open_file)
 		return get_cifs_acl_by_path(cifs_sb, path, pacllen, info);
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index b6e3db993cc6..32d0305a1239 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1269,7 +1269,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s
 	struct cifsFileInfo *writeable_srcfile;
 	int rc = -EINVAL;
 
-	writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY);
+	writeable_srcfile = find_writable_file(src_cifsi, FIND_FSUID_ONLY);
 	if (writeable_srcfile) {
 		if (src_tcon->ses->server->ops->set_file_size)
 			rc = src_tcon->ses->server->ops->set_file_size(
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index bb0fe4b60240..7877d327dbb0 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1885,12 +1885,12 @@ static inline bool is_replayable_error(int error)
 }
 
 
-/* cifs_get_writable_file() flags */
-enum cifs_writable_file_flags {
-	FIND_WR_ANY			= 0U,
-	FIND_WR_FSUID_ONLY		= (1U << 0),
-	FIND_WR_WITH_DELETE		= (1U << 1),
-	FIND_WR_NO_PENDING_DELETE	= (1U << 2),
+enum cifs_find_flags {
+	FIND_ANY		= 0U,
+	FIND_FSUID_ONLY		= (1U << 0),
+	FIND_WITH_DELETE	= (1U << 1),
+	FIND_NO_PENDING_DELETE	= (1U << 2),
+	FIND_OPEN_FLAGS		= (1U << 3),
 };
 
 #define   MID_FREE 0
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 800a7e418c32..884bfa1cf0b4 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -138,12 +138,14 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata,
 				      ssize_t result);
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
 					int flags);
-int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
-			   struct cifsFileInfo **ret_file);
+int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+			     unsigned int find_flags, unsigned int open_flags,
+			     struct cifsFileInfo **ret_file);
 int cifs_get_writable_path(struct cifs_tcon *tcon, const char *name, int flags,
 			   struct cifsFileInfo **ret_file);
-struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
-					bool fsuid_only);
+struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode,
+					  unsigned int find_flags,
+					  unsigned int open_flags);
 int cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 			   struct cifsFileInfo **ret_file);
 int cifs_get_hardlink_path(struct cifs_tcon *tcon, struct inode *inode,
@@ -596,4 +598,20 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable,
 	}
 }
 
+static inline int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+					 unsigned int find_flags,
+					 struct cifsFileInfo **ret_file)
+{
+	find_flags &= ~FIND_OPEN_FLAGS;
+	return __cifs_get_writable_file(cifs_inode, find_flags, 0, ret_file);
+}
+
+static inline struct cifsFileInfo *
+find_readable_file(struct cifsInodeInfo *cinode, unsigned int find_flags)
+{
+	find_flags &= ~FIND_OPEN_FLAGS;
+	find_flags |= FIND_NO_PENDING_DELETE;
+	return __find_readable_file(cinode, find_flags, 0);
+}
+
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 13dda87f7711..27f61fe7e4e2 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -255,7 +255,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq)
 	struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq);
 	int ret;
 
-	ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile);
+	ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_ANY, &req->cfile);
 	if (ret) {
 		cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret);
 		return;
@@ -956,7 +956,7 @@ int cifs_file_flush(const unsigned int xid, struct inode *inode,
 		return tcon->ses->server->ops->flush(xid, tcon,
 						     &cfile->fid);
 	}
-	rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
+	rc = cifs_get_writable_file(CIFS_I(inode), FIND_ANY, &cfile);
 	if (!rc) {
 		tcon = tlink_tcon(cfile->tlink);
 		rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid);
@@ -981,7 +981,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 		return -ERESTARTSYS;
 	mapping_set_error(inode->i_mapping, rc);
 
-	cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+	cfile = find_writable_file(cinode, FIND_FSUID_ONLY);
 	rc = cifs_file_flush(xid, inode, cfile);
 	if (!rc) {
 		if (cfile) {
@@ -1061,32 +1061,29 @@ int cifs_open(struct inode *inode, struct file *file)
 
 	/* Get the cached handle as SMB2 close is deferred */
 	if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) {
-		rc = cifs_get_writable_path(tcon, full_path,
-					    FIND_WR_FSUID_ONLY |
-					    FIND_WR_NO_PENDING_DELETE,
-					    &cfile);
+		rc = __cifs_get_writable_file(CIFS_I(inode),
+					      FIND_FSUID_ONLY |
+					      FIND_NO_PENDING_DELETE |
+					      FIND_OPEN_FLAGS,
+					      file->f_flags, &cfile);
 	} else {
-		rc = cifs_get_readable_path(tcon, full_path, &cfile);
+		cfile = __find_readable_file(CIFS_I(inode),
+					     FIND_NO_PENDING_DELETE |
+					     FIND_OPEN_FLAGS,
+					     file->f_flags);
+		rc = cfile ? 0 : -ENOENT;
 	}
 	if (rc == 0) {
-		unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
-		unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
-
-		if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
-		    (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
-			file->private_data = cfile;
-			spin_lock(&CIFS_I(inode)->deferred_lock);
-			cifs_del_deferred_close(cfile);
-			spin_unlock(&CIFS_I(inode)->deferred_lock);
-			goto use_cache;
-		}
-		_cifsFileInfo_put(cfile, true, false);
-	} else {
-		/* hard link on the defeered close file */
-		rc = cifs_get_hardlink_path(tcon, inode, file);
-		if (rc)
-			cifs_close_deferred_file(CIFS_I(inode));
-	}
+		file->private_data = cfile;
+		spin_lock(&CIFS_I(inode)->deferred_lock);
+		cifs_del_deferred_close(cfile);
+		spin_unlock(&CIFS_I(inode)->deferred_lock);
+		goto use_cache;
+	}
+	/* hard link on the deferred close file */
+	rc = cifs_get_hardlink_path(tcon, inode, file);
+	if (rc)
+		cifs_close_deferred_file(CIFS_I(inode));
 
 	if (server->oplocks)
 		oplock = REQ_OPLOCK;
@@ -2512,10 +2509,33 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
 	netfs_write_subrequest_terminated(&wdata->subreq, result);
 }
 
-struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
-					bool fsuid_only)
+static bool open_flags_match(struct cifsInodeInfo *cinode,
+			     unsigned int oflags, unsigned int cflags)
+{
+	struct inode *inode = &cinode->netfs.inode;
+	int crw = 0, orw = 0;
+
+	oflags &= ~(O_CREAT | O_EXCL | O_TRUNC);
+	cflags &= ~(O_CREAT | O_EXCL | O_TRUNC);
+
+	if (cifs_fscache_enabled(inode)) {
+		if (OPEN_FMODE(cflags) & FMODE_WRITE)
+			crw = 1;
+		if (OPEN_FMODE(oflags) & FMODE_WRITE)
+			orw = 1;
+	}
+	if (cifs_convert_flags(oflags, orw) != cifs_convert_flags(cflags, crw))
+		return false;
+
+	return (oflags & (O_SYNC | O_DIRECT)) == (cflags & (O_SYNC | O_DIRECT));
+}
+
+struct cifsFileInfo *__find_readable_file(struct cifsInodeInfo *cifs_inode,
+					  unsigned int find_flags,
+					  unsigned int open_flags)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode);
+	bool fsuid_only = find_flags & FIND_FSUID_ONLY;
 	struct cifsFileInfo *open_file = NULL;
 
 	/* only filter by fsuid on multiuser mounts */
@@ -2529,6 +2549,13 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
 		if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
 			continue;
+		if ((find_flags & FIND_NO_PENDING_DELETE) &&
+		    open_file->status_file_deleted)
+			continue;
+		if ((find_flags & FIND_OPEN_FLAGS) &&
+		    !open_flags_match(cifs_inode, open_flags,
+				      open_file->f_flags))
+			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) {
 			if ((!open_file->invalidHandle)) {
 				/* found a good file */
@@ -2547,17 +2574,17 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 }
 
 /* Return -EBADF if no handle is found and general rc otherwise */
-int
-cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags,
-		       struct cifsFileInfo **ret_file)
+int __cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
+			     unsigned int find_flags, unsigned int open_flags,
+			     struct cifsFileInfo **ret_file)
 {
 	struct cifsFileInfo *open_file, *inv_file = NULL;
 	struct cifs_sb_info *cifs_sb;
 	bool any_available = false;
 	int rc = -EBADF;
 	unsigned int refind = 0;
-	bool fsuid_only = flags & FIND_WR_FSUID_ONLY;
-	bool with_delete = flags & FIND_WR_WITH_DELETE;
+	bool fsuid_only = find_flags & FIND_FSUID_ONLY;
+	bool with_delete = find_flags & FIND_WITH_DELETE;
 	*ret_file = NULL;
 
 	/*
@@ -2591,9 +2618,13 @@ refind_writable:
 			continue;
 		if (with_delete && !(open_file->fid.access & DELETE))
 			continue;
-		if ((flags & FIND_WR_NO_PENDING_DELETE) &&
+		if ((find_flags & FIND_NO_PENDING_DELETE) &&
 		    open_file->status_file_deleted)
 			continue;
+		if ((find_flags & FIND_OPEN_FLAGS) &&
+		    !open_flags_match(cifs_inode, open_flags,
+				      open_file->f_flags))
+			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
@@ -2710,17 +2741,7 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 		cinode = CIFS_I(d_inode(cfile->dentry));
 		spin_unlock(&tcon->open_file_lock);
 		free_dentry_path(page);
-		*ret_file = find_readable_file(cinode, 0);
-		if (*ret_file) {
-			spin_lock(&cinode->open_file_lock);
-			if ((*ret_file)->status_file_deleted) {
-				spin_unlock(&cinode->open_file_lock);
-				cifsFileInfo_put(*ret_file);
-				*ret_file = NULL;
-			} else {
-				spin_unlock(&cinode->open_file_lock);
-			}
-		}
+		*ret_file = find_readable_file(cinode, FIND_ANY);
 		return *ret_file ? 0 : -ENOENT;
 	}
 
@@ -2792,7 +2813,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 		}
 
 		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
-			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			smbfile = find_writable_file(CIFS_I(inode), FIND_ANY);
 			if (smbfile) {
 				rc = server->ops->flush(xid, tcon, &smbfile->fid);
 				cifsFileInfo_put(smbfile);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 3e844c55ab8a..143fa2e665ed 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -2997,7 +2997,7 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start,
 		}
 	}
 
-	cfile = find_readable_file(cifs_i, false);
+	cfile = find_readable_file(cifs_i, FIND_ANY);
 	if (cfile == NULL)
 		return -EINVAL;
 
@@ -3050,7 +3050,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry,
 						size, false);
 		cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc);
 	} else {
-		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY);
 		if (open_file) {
 			tcon = tlink_tcon(open_file->tlink);
 			server = tcon->ses->server;
@@ -3219,7 +3219,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 					    open_file->fid.netfid,
 					    open_file->pid);
 	} else {
-		open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY);
+		open_file = find_writable_file(cifsInode, FIND_FSUID_ONLY);
 		if (open_file) {
 			pTcon = tlink_tcon(open_file->tlink);
 			rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args,
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 9643eca0cb70..9694117050a6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -960,7 +960,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 	struct cifs_tcon *tcon;
 
 	/* if the file is already open for write, just use that fileid */
-	open_file = find_writable_file(cinode, FIND_WR_FSUID_ONLY);
+	open_file = find_writable_file(cinode, FIND_FSUID_ONLY);
 
 	if (open_file) {
 		fid.netfid = open_file->fid.netfid;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 5280c5c869ad..364bdcff9c9d 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1156,7 +1156,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name,
 	cifs_i = CIFS_I(inode);
 	dosattrs = cifs_i->cifsAttrs | ATTR_READONLY;
 	data.Attributes = cpu_to_le32(dosattrs);
-	cifs_get_writable_path(tcon, name, FIND_WR_ANY, &cfile);
+	cifs_get_writable_path(tcon, name, FIND_ANY, &cfile);
 	oparms = CIFS_OPARMS(cifs_sb, tcon, name, FILE_WRITE_ATTRIBUTES,
 			     FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE);
 	tmprc = smb2_compound_op(xid, tcon, cifs_sb, name,
@@ -1336,14 +1336,13 @@ int smb2_rename_path(const unsigned int xid,
 	__u32 co = file_create_options(source_dentry);
 
 	drop_cached_dir_by_name(xid, tcon, from_name, cifs_sb);
-	cifs_get_writable_path(tcon, from_name, FIND_WR_WITH_DELETE, &cfile);
+	cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile);
 
 	int rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
 				  co, DELETE, SMB2_OP_RENAME, cfile, source_dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease");
-		cifs_get_writable_path(tcon, from_name,
-				       FIND_WR_WITH_DELETE, &cfile);
+		cifs_get_writable_path(tcon, from_name, FIND_WITH_DELETE, &cfile);
 		rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
 				  co, DELETE, SMB2_OP_RENAME, cfile, NULL);
 	}
@@ -1377,7 +1376,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 
 	in_iov.iov_base = &eof;
 	in_iov.iov_len = sizeof(eof);
-	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+	cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 
 	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_DATA,
 			     FILE_OPEN, 0, ACL_NO_MODE);
@@ -1387,7 +1386,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 			      cfile, NULL, NULL, dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease");
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb,
 				      full_path, &oparms, &in_iov,
 				      &(int){SMB2_OP_SET_EOF}, 1,
@@ -1417,7 +1416,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) {
 		if (buf->Attributes == 0)
 			goto out; /* would be a no op, no sense sending this */
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 	}
 
 	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES,
@@ -1476,7 +1475,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data,
 
 	if (tcon->posix_extensions) {
 		cmds[1] = SMB2_OP_POSIX_QUERY_INFO;
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
 				      in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
 		if (!rc) {
@@ -1485,7 +1484,7 @@ struct inode *smb2_create_reparse_inode(struct cifs_open_info_data *data,
 		}
 	} else {
 		cmds[1] = SMB2_OP_QUERY_INFO;
-		cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_ANY, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
 				      in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
 		if (!rc) {
@@ -1636,13 +1635,12 @@ int smb2_rename_pending_delete(const char *full_path,
 	iov[1].iov_base = utf16_path;
 	iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path);
 
-	cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile);
+	cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile);
 	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
 			      cmds, num_cmds, cfile, NULL, NULL, dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease\n");
-		cifs_get_writable_path(tcon, full_path,
-				       FIND_WR_WITH_DELETE, &cfile);
+		cifs_get_writable_path(tcon, full_path, FIND_WITH_DELETE, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
 				      cmds, num_cmds, cfile, NULL, NULL, NULL);
 	}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 612057318de2..98ac4e86bf99 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3362,7 +3362,7 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb,
 	struct cifsFileInfo *open_file = NULL;
 
 	if (inode && !(info & SACL_SECINFO))
-		open_file = find_readable_file(CIFS_I(inode), true);
+		open_file = find_readable_file(CIFS_I(inode), FIND_FSUID_ONLY);
 	if (!open_file || (info & SACL_SECINFO))
 		return get_smb2_acl_by_path(cifs_sb, path, pacllen, info);
 
@@ -3908,7 +3908,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs
 	 * some servers (Windows2016) will not reflect recent writes in
 	 * QUERY_ALLOCATED_RANGES until SMB2_flush is called.
 	 */
-	wrcfile = find_writable_file(cifsi, FIND_WR_ANY);
+	wrcfile = find_writable_file(cifsi, FIND_ANY);
 	if (wrcfile) {
 		filemap_write_and_wait(inode->i_mapping);
 		smb2_flush_file(xid, tcon, &wrcfile->fid);
-- 
cgit v1.2.3


From e3beefd3af09f8e460ddaf39063d3d7664d7ab59 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Wed, 11 Mar 2026 10:48:54 +0530
Subject: cifs: make default value of retrans as zero

When retrans mount option was introduced, the default value was set
as 1. However, in the light of some bugs that this has exposed recently
we should change it to 0 and retain the old behaviour before this option
was introduced.

Cc: <stable@vger.kernel.org>
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 54090739535f..a4a7c7eee038 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1997,7 +1997,7 @@ int smb3_init_fs_context(struct fs_context *fc)
 	ctx->backupuid_specified = false; /* no backup intent for a user */
 	ctx->backupgid_specified = false; /* no backup intent for a group */
 
-	ctx->retrans = 1;
+	ctx->retrans = 0;
 	ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT;
 	ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT;
 	ctx->nonativesocket = 0;
-- 
cgit v1.2.3


From 94a4b1f959989de9c54d43c3a102fb1ee92e1414 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 7 Mar 2026 17:50:53 -0300
Subject: ipv6: move the disable_ipv6_mod knob to core code

From: Jakub Kicinski <kuba@kernel.org>

Make sure disable_ipv6_mod itself is not part of the IPv6 module,
in case core code wants to refer to it. We will remove support
for IPv6=m soon, this change helps make fixes we commit before
that less messy.

Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-1-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ipv6.h | 7 ++++++-
 net/ipv4/af_inet.c   | 6 ++++++
 net/ipv6/af_inet6.c  | 8 --------
 3 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 443053a76dcf..a7421382a916 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -333,7 +333,12 @@ struct tcp6_timewait_sock {
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
-bool ipv6_mod_enabled(void);
+extern int disable_ipv6_mod;
+
+static inline bool ipv6_mod_enabled(void)
+{
+	return disable_ipv6_mod == 0;
+}
 
 static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8036e76aa1e4..c7731e300a44 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -124,6 +124,12 @@
 
 #include <trace/events/sock.h>
 
+/* Keep the definition of IPv6 disable here for now, to avoid annoying linker
+ * issues in case IPv6=m
+ */
+int disable_ipv6_mod;
+EXPORT_SYMBOL(disable_ipv6_mod);
+
 /* The inetsw table contains everything that inet_create needs to
  * build a new socket.
  */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 23cc9b4cb2f1..4cbd45b68088 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -86,8 +86,6 @@ struct ipv6_params ipv6_defaults = {
 	.autoconf = 1,
 };
 
-static int disable_ipv6_mod;
-
 module_param_named(disable, disable_ipv6_mod, int, 0444);
 MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional");
 
@@ -97,12 +95,6 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces");
 module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444);
 MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces");
 
-bool ipv6_mod_enabled(void)
-{
-	return disable_ipv6_mod == 0;
-}
-EXPORT_SYMBOL_GPL(ipv6_mod_enabled);
-
 static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
 	const int offset = sk->sk_prot->ipv6_pinfo_offset;
-- 
cgit v1.2.3


From 30021e969d48e5819d5ae56936c2f34c0f7ce997 Mon Sep 17 00:00:00 2001
From: "Ricardo B. Marlière" <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:54 -0300
Subject: net: bonding: Fix nd_tbl NULL dereference when IPv6 is disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called
which initializes it. If bonding ARP/NS validation is enabled, an IPv6
NS/NA packet received on a slave can reach bond_validate_na(), which
calls bond_has_this_ip6(). That path calls ipv6_chk_addr() and can
crash in __ipv6_chk_addr_and_flags().

 BUG: kernel NULL pointer dereference, address: 00000000000005d8
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:__ipv6_chk_addr_and_flags+0x69/0x170
 Call Trace:
  <IRQ>
  ipv6_chk_addr+0x1f/0x30
  bond_validate_na+0x12e/0x1d0 [bonding]
  ? __pfx_bond_handle_frame+0x10/0x10 [bonding]
  bond_rcv_validate+0x1a0/0x450 [bonding]
  bond_handle_frame+0x5e/0x290 [bonding]
  ? srso_alias_return_thunk+0x5/0xfbef5
  __netif_receive_skb_core.constprop.0+0x3e8/0xe50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? update_cfs_rq_load_avg+0x1a/0x240
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __enqueue_entity+0x5e/0x240
  __netif_receive_skb_one_core+0x39/0xa0
  process_backlog+0x9c/0x150
  __napi_poll+0x30/0x200
  ? srso_alias_return_thunk+0x5/0xfbef5
  net_rx_action+0x338/0x3b0
  handle_softirqs+0xc9/0x2a0
  do_softirq+0x42/0x60
  </IRQ>
  <TASK>
  __local_bh_enable_ip+0x62/0x70
  __dev_queue_xmit+0x2d3/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? packet_parse_headers+0x10a/0x1a0
  packet_sendmsg+0x10da/0x1700
  ? kick_pool+0x5f/0x140
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __queue_work+0x12d/0x4f0
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by checking ipv6_mod_enabled() before dispatching IPv6 packets to
bond_na_rcv(). If IPv6 is disabled, return early from bond_rcv_validate()
and avoid the path to ipv6_chk_addr().

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-2-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c1fb92602e46..707419270ebf 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3428,7 +3428,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond,
 	} else if (is_arp) {
 		return bond_arp_rcv(skb, bond, slave);
 #if IS_ENABLED(CONFIG_IPV6)
-	} else if (is_ipv6) {
+	} else if (is_ipv6 && likely(ipv6_mod_enabled())) {
 		return bond_na_rcv(skb, bond, slave);
 #endif
 	} else {
-- 
cgit v1.2.3


From dcb4e2231469523d20cf0a2477d68245795c205d Mon Sep 17 00:00:00 2001
From: "Ricardo B. Marlière" <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:55 -0300
Subject: bpf: bpf_out_neigh_v4: Fix nd_tbl NULL dereference when IPv6 is
 disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called which
initializes it. If bpf_redirect_neigh() is called from tc with an explicit
nexthop of nh_family == AF_INET6, bpf_out_neigh_v4() takes the AF_INET6
branch and calls ip_neigh_gw6(), which relies on ipv6_stub->nd_tbl.

 BUG: kernel NULL pointer dereference, address: 0000000000000248
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:skb_do_redirect+0xb93/0xf00
 Call Trace:
  <TASK>
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __tcf_classify.constprop.0+0x83/0x160
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tcf_classify+0x2b/0x50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tc_run+0xb8/0x120
  ? srso_alias_return_thunk+0x5/0xfbef5
  __dev_queue_xmit+0x6fa/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? alloc_skb_with_frags+0x58/0x200
  packet_sendmsg+0x10da/0x1700
  ? srso_alias_return_thunk+0x5/0xfbef5
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by adding an early check in the AF_INET6 branch of
bpf_out_neigh_v4(). If IPv6 is disabled, unlock RCU and drop the packet.

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-3-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index a77d23fe2359..fd38b6f8b7a8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2335,6 +2335,10 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
 
 		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	} else if (nh->nh_family == AF_INET6) {
+		if (unlikely(!ipv6_mod_enabled())) {
+			rcu_read_unlock();
+			goto out_drop;
+		}
 		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
 		is_v6gw = true;
 	} else if (nh->nh_family == AF_INET) {
-- 
cgit v1.2.3


From d56b5d163458c45ab8fa1f00bd875af01b3ce28c Mon Sep 17 00:00:00 2001
From: "Ricardo B. Marlière" <rbm@suse.com>
Date: Sat, 7 Mar 2026 17:50:56 -0300
Subject: bpf: bpf_out_neigh_v6: Fix nd_tbl NULL dereference when IPv6 is
 disabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never
initialized because inet6_init() exits before ndisc_init() is called which
initializes it. If bpf_redirect_neigh() is called with explicit AF_INET6
nexthop parameters, __bpf_redirect_neigh_v6() can skip the IPv6 FIB lookup
and call bpf_out_neigh_v6() directly. bpf_out_neigh_v6() then calls
ip_neigh_gw6(), which uses ipv6_stub->nd_tbl.

 BUG: kernel NULL pointer dereference, address: 0000000000000248
 Oops: Oops: 0000 [#1] SMP NOPTI
 RIP: 0010:skb_do_redirect+0x44f/0xf40
 Call Trace:
  <TASK>
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? __tcf_classify.constprop.0+0x83/0x160
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tcf_classify+0x2b/0x50
  ? srso_alias_return_thunk+0x5/0xfbef5
  ? tc_run+0xb8/0x120
  ? srso_alias_return_thunk+0x5/0xfbef5
  __dev_queue_xmit+0x6fa/0x1000
  ? srso_alias_return_thunk+0x5/0xfbef5
  packet_sendmsg+0x10da/0x1700
  ? srso_alias_return_thunk+0x5/0xfbef5
  __sys_sendto+0x1f3/0x220
  __x64_sys_sendto+0x24/0x30
  do_syscall_64+0x101/0xf80
  ? exc_page_fault+0x6e/0x170
  ? srso_alias_return_thunk+0x5/0xfbef5
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

Fix this by adding an early check in bpf_out_neigh_v6(). If IPv6 is
disabled, drop the packet before neighbor lookup.

Suggested-by: Fernando Fernandez Mancera <fmancera@suse.de>
Fixes: ba452c9e996d ("bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop")
Signed-off-by: Ricardo B. Marlière <rbm@suse.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-4-e2677e85628c@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index fd38b6f8b7a8..78b548158fb0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2228,6 +2228,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
 			return -ENOMEM;
 	}
 
+	if (unlikely(!ipv6_mod_enabled()))
+		goto out_drop;
+
 	rcu_read_lock();
 	if (!nh) {
 		dst = skb_dst(skb);
-- 
cgit v1.2.3


From 99c8c16a4aad0b37293cae213e15957c573cf79b Mon Sep 17 00:00:00 2001
From: "Bastien Curutchet (Schneider Electric)" <bastien.curutchet@bootlin.com>
Date: Mon, 9 Mar 2026 14:15:43 +0100
Subject: net: dsa: microchip: Fix error path in PTP IRQ setup

If request_threaded_irq() fails during the PTP message IRQ setup, the
newly created IRQ mapping is never disposed. Indeed, the
ksz_ptp_irq_setup()'s error path only frees the mappings that were
successfully set up.

Dispose the newly created mapping if the associated
request_threaded_irq() fails at setup.

Cc: stable@vger.kernel.org
Fixes: d0b8fec8ae505 ("net: dsa: microchip: Fix symetry in ksz_ptp_msg_irq_{setup/free}()")
Signed-off-by: Bastien Curutchet (Schneider Electric) <bastien.curutchet@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20260309-ksz-ptp-irq-fix-v1-1-757b3b985955@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_ptp.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index 4a2cc57a628f..8b98039320ad 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -1108,6 +1108,7 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 	const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops;
 	struct ksz_irq *ptpirq = &port->ptpirq;
 	struct ksz_ptp_irq *ptpmsg_irq;
+	int ret;
 
 	ptpmsg_irq = &port->ptpmsg_irq[n];
 	ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n);
@@ -1119,9 +1120,13 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n)
 
 	strscpy(ptpmsg_irq->name, name[n]);
 
-	return request_threaded_irq(ptpmsg_irq->num, NULL,
-				    ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
-				    ptpmsg_irq->name, ptpmsg_irq);
+	ret = request_threaded_irq(ptpmsg_irq->num, NULL,
+				   ksz_ptp_msg_thread_fn, IRQF_ONESHOT,
+				   ptpmsg_irq->name, ptpmsg_irq);
+	if (ret)
+		irq_dispose_mapping(ptpmsg_irq->num);
+
+	return ret;
 }
 
 int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p)
-- 
cgit v1.2.3


From 6c5a9baa15de240e747263aba435a0951da8d8d2 Mon Sep 17 00:00:00 2001
From: Mehul Rao <mehulrao@gmail.com>
Date: Tue, 10 Mar 2026 13:07:30 -0400
Subject: tipc: fix divide-by-zero in tipc_sk_filter_connect()

A user can set conn_timeout to any value via
setsockopt(TIPC_CONN_TIMEOUT), including values less than 4.  When a
SYN is rejected with TIPC_ERR_OVERLOAD and the retry path in
tipc_sk_filter_connect() executes:

    delay %= (tsk->conn_timeout / 4);

If conn_timeout is in the range [0, 3], the integer division yields 0,
and the modulo operation triggers a divide-by-zero exception, causing a
kernel oops/panic.

Fix this by clamping conn_timeout to a minimum of 4 at the point of use
in tipc_sk_filter_connect().

Oops: divide error: 0000 [#1] SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 119 Comm: poc-F144 Not tainted 7.0.0-rc2+
RIP: 0010:tipc_sk_filter_rcv (net/tipc/socket.c:2236 net/tipc/socket.c:2362)
Call Trace:
 tipc_sk_backlog_rcv (include/linux/instrumented.h:82 include/linux/atomic/atomic-instrumented.h:32 include/net/sock.h:2357 net/tipc/socket.c:2406)
 __release_sock (include/net/sock.h:1185 net/core/sock.c:3213)
 release_sock (net/core/sock.c:3797)
 tipc_connect (net/tipc/socket.c:2570)
 __sys_connect (include/linux/file.h:62 include/linux/file.h:83 net/socket.c:2098)

Fixes: 6787927475e5 ("tipc: buffer overflow handling in listener socket")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Link: https://patch.msgid.link/20260310170730.28841-1-mehulrao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/socket.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 4c618c2b871d..9329919fb07f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2233,6 +2233,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
 		if (skb_queue_empty(&sk->sk_write_queue))
 			break;
 		get_random_bytes(&delay, 2);
+		if (tsk->conn_timeout < 4)
+			tsk->conn_timeout = 4;
 		delay %= (tsk->conn_timeout / 4);
 		delay = msecs_to_jiffies(delay + 100);
 		sk_reset_timer(sk, &sk->sk_timer, jiffies + delay);
-- 
cgit v1.2.3


From e8f0dc024ce55451ebd54bad975134ba802e4fcc Mon Sep 17 00:00:00 2001
From: Marek Behún <kabel@kernel.org>
Date: Wed, 11 Mar 2026 12:12:37 +0100
Subject: net: dsa: realtek: Fix LED group port bit for non-zero LED group
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The rtl8366rb_led_group_port_mask() function always returns LED port
bit in LED group 0; the switch statement returns the same thing in all
non-default cases.

This means that the driver does not currently support configuring LEDs
in non-zero LED groups.

Fix this.

Fixes: 32d617005475a71e ("net: dsa: realtek: add LED drivers for rtl8366rb")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260311111237.29002-1-kabel@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8366rb-leds.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
index 99c890681ae6..509ffd3f8db5 100644
--- a/drivers/net/dsa/realtek/rtl8366rb-leds.c
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -12,11 +12,11 @@ static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
 	case 0:
 		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
 	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_1_CTRL_MASK, BIT(port));
 	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_2_X_CTRL_MASK, BIT(port));
 	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+		return FIELD_PREP(RTL8366RB_LED_X_3_CTRL_MASK, BIT(port));
 	default:
 		return 0;
 	}
-- 
cgit v1.2.3


From cbada1048847a348797aec63a1d8056621cbe653 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Mar 2026 22:59:16 +0100
Subject: neighbour: restore protocol != 0 check in pneigh update

Prior to commit dc2a27e524ac ("neighbour: Update pneigh_entry in
pneigh_create()."), a pneigh's protocol was updated only when the
value of the NDA_PROTOCOL attribute was non-0. While moving the code,
that check was removed. This is a small change of user-visible
behavior, and inconsistent with the (non-proxy) neighbour behavior.

Fixes: dc2a27e524ac ("neighbour: Update pneigh_entry in pneigh_create().")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/38c61de1bb032871a886aff9b9b52fe1cdd4cada.1772894876.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a95cfe77f7f0..c56a4e7bf790 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -820,7 +820,8 @@ int pneigh_create(struct neigh_table *tbl, struct net *net,
 update:
 	WRITE_ONCE(n->flags, flags);
 	n->permanent = permanent;
-	WRITE_ONCE(n->protocol, protocol);
+	if (protocol)
+		WRITE_ONCE(n->protocol, protocol);
 out:
 	mutex_unlock(&tbl->phash_lock);
 	return err;
-- 
cgit v1.2.3


From 68e76fc12df091b04ede5f6244385a35abae0a80 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 10 Mar 2026 22:59:17 +0100
Subject: selftests: rtnetlink: add neighbour update test

Check that protocol and flags are updated correctly for
neighbour and pneigh entries.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/d28f72b5b4ff4c9ecbbbde06146a938dcc4c264a.1772894876.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rtnetlink.sh | 55 ++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 248c2b91fe42..5a5ff88321d5 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -28,6 +28,7 @@ ALL_TESTS="
 	kci_test_fdb_get
 	kci_test_fdb_del
 	kci_test_neigh_get
+	kci_test_neigh_update
 	kci_test_bridge_parent_id
 	kci_test_address_proto
 	kci_test_enslave_bonding
@@ -1160,6 +1161,60 @@ kci_test_neigh_get()
 	end_test "PASS: neigh get"
 }
 
+kci_test_neigh_update()
+{
+	dstip=10.0.2.4
+	dstmac=de:ad:be:ef:13:37
+	local ret=0
+
+	for proxy in "" "proxy" ; do
+		# add a neighbour entry without any flags
+		run_cmd ip neigh add $proxy $dstip dev "$devdummy" lladdr $dstmac nud permanent
+		run_cmd_grep $dstip ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .*\(managed\|use\|router\|extern\)" ip neigh show $proxy
+
+		# set the extern_learn flag, but no other
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" extern_learn
+		run_cmd_grep "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .* \(managed\|use\|router\)" ip neigh show $proxy
+
+		# flags are reset when not provided
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy"
+		run_cmd_grep $dstip ip neigh show $proxy
+		run_cmd_grep_fail "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy
+
+		# add a protocol
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol boot
+		run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy
+
+		# protocol is retained when not provided
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy"
+		run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy
+
+		# change protocol
+		run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol static
+		run_cmd_grep "$dstip dev $devdummy .* proto static" ip neigh show $proxy
+
+		# also check an extended flag for non-proxy neighs
+		if [ "$proxy" = "" ]; then
+			run_cmd ip neigh change $proxy $dstip dev "$devdummy" managed
+			run_cmd_grep "$dstip dev $devdummy managed" ip neigh show $proxy
+
+			run_cmd ip neigh change $proxy $dstip dev "$devdummy" lladdr $dstmac
+			run_cmd_grep_fail "$dstip dev $devdummy managed" ip neigh show $proxy
+		fi
+
+		run_cmd ip neigh del $proxy $dstip dev "$devdummy"
+	done
+
+	if [ $ret -ne 0 ];then
+		end_test "FAIL: neigh update"
+		return 1
+	fi
+
+	end_test "PASS: neigh update"
+}
+
 kci_test_bridge_parent_id()
 {
 	local ret=0
-- 
cgit v1.2.3


From 87c2302813abc55c46485711a678e3c312b00666 Mon Sep 17 00:00:00 2001
From: Shiraz Saleem <shirazsaleem@microsoft.com>
Date: Mon, 9 Mar 2026 10:24:43 -0700
Subject: net/mana: Null service_wq on setup error to prevent double destroy

In mana_gd_setup() error path, set gc->service_wq to NULL after
destroy_workqueue() to match the cleanup in mana_gd_cleanup().
This prevents a use-after-free if the workqueue pointer is checked
after a failed setup.

Fixes: f975a0955276 ("net: mana: Fix double destroy_workqueue on service rescan PCI path")
Signed-off-by: Shiraz Saleem <shirazsaleem@microsoft.com>
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260309172443.688392-1-kotaranov@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 37d2f108a839..786186c9a115 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1934,6 +1934,7 @@ remove_irq:
 	mana_gd_remove_irqs(pdev);
 free_workqueue:
 	destroy_workqueue(gc->service_wq);
+	gc->service_wq = NULL;
 	dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err);
 	return err;
 }
-- 
cgit v1.2.3


From 840c9d13cb1ca96683a5307ee8e221be163a2c1e Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Tue, 10 Mar 2026 21:39:40 +0530
Subject: net: ethernet: ti: am65-cpsw-nuss: Fix rx_filter value for PTP
 support

The "rx_filter" member of "hwtstamp_config" structure is an enum field and
does not support bitwise OR combination of multiple filter values. It
causes error while linuxptp application tries to match rx filter version.
Fix this by storing the requested filter type in a new port field.

Fixes: 97248adb5a3b ("net: ti: am65-cpsw: Update hw timestamping filter for PTPv1 RX packets")
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Link: https://patch.msgid.link/20260310160940.109822-1-c-vankar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 16 +++++++++-------
 drivers/net/ethernet/ti/am65-cpsw-nuss.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 967918050433..265ce5479915 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1351,7 +1351,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	ndev_priv = netdev_priv(ndev);
 	am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark);
 	skb_put(skb, pkt_len);
-	if (port->rx_ts_enabled)
+	if (port->rx_ts_filter)
 		am65_cpts_rx_timestamp(common->cpts, skb);
 	skb_mark_for_recycle(skb);
 	skb->protocol = eth_type_trans(skb, ndev);
@@ -1811,11 +1811,14 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 
 	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		port->rx_ts_enabled = false;
+		port->rx_ts_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
@@ -1825,8 +1828,8 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		port->rx_ts_enabled = true;
-		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
@@ -1863,7 +1866,7 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev,
 		ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN |
 			   AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN;
 
-	if (port->rx_ts_enabled)
+	if (port->rx_ts_filter)
 		ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN |
 			   AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN;
 
@@ -1888,8 +1891,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev,
 	cfg->flags = 0;
 	cfg->tx_type = port->tx_ts_enabled ?
 		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg->rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT |
-			HWTSTAMP_FILTER_PTP_V1_L4_EVENT : HWTSTAMP_FILTER_NONE;
+	cfg->rx_filter = port->rx_ts_filter;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index 917c37e4e89b..7750448e4746 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -52,7 +52,7 @@ struct am65_cpsw_port {
 	bool				disabled;
 	struct am65_cpsw_slave_data	slave;
 	bool				tx_ts_enabled;
-	bool				rx_ts_enabled;
+	enum hwtstamp_rx_filters	rx_ts_filter;
 	struct am65_cpsw_qos		qos;
 	struct devlink_port		devlink_port;
 	struct bpf_prog			*xdp_prog;
-- 
cgit v1.2.3


From dc26ca99b835e21e76a58b1463b84adb0ca34f58 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 11:48:16 -0700
Subject: octeontx2-af: devlink: fix NIX RAS reporter recovery condition

The NIX RAS health reporter recovery routine checks nix_af_rvu_int to
decide whether to re-enable NIX_AF_RAS interrupts. This is the RVU
interrupt status field and is unrelated to RAS events, so the recovery
flow may incorrectly skip re-enabling NIX_AF_RAS interrupts.

Check nix_af_rvu_ras instead before writing NIX_AF_RAS_ENA_W1S.

Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20260310184824.1183651-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index fb15c794efc9..7ef3da0f6a88 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -475,7 +475,7 @@ static int rvu_hw_nix_ras_recover(struct devlink_health_reporter *reporter,
 	if (blkaddr < 0)
 		return blkaddr;
 
-	if (nix_event_ctx->nix_af_rvu_int)
+	if (nix_event_ctx->nix_af_rvu_ras)
 		rvu_write64(rvu, blkaddr, NIX_AF_RAS_ENA_W1S, ~0ULL);
 
 	return 0;
-- 
cgit v1.2.3


From 87f7dff3ec75b91def0024ebaaf732457f47a63b Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 11:48:17 -0700
Subject: octeontx2-af: devlink: fix NIX RAS reporter to use RAS interrupt
 status

The NIX RAS health report path uses nix_af_rvu_err when handling the
NIX_AF_RVU_RAS case, so the report prints the ERR interrupt status rather
than the RAS interrupt status.

Use nix_af_rvu_ras for the NIX_AF_RVU_RAS report.

Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20260310184824.1183651-2-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 7ef3da0f6a88..a29f1ea04c7d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -327,10 +327,10 @@ static int rvu_nix_report_show(struct devlink_fmsg *fmsg, void *ctx,
 		rvu_report_pair_end(fmsg);
 		break;
 	case NIX_AF_RVU_RAS:
-		intr_val = nix_event_context->nix_af_rvu_err;
+		intr_val = nix_event_context->nix_af_rvu_ras;
 		rvu_report_pair_start(fmsg, "NIX_AF_RAS");
 		devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ",
-					  nix_event_context->nix_af_rvu_err);
+					  nix_event_context->nix_af_rvu_ras);
 		devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:");
 		if (intr_val & BIT_ULL(34))
 			devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S");
-- 
cgit v1.2.3


From 3484127c19aca9e93ef6631e7a47bc4f56212da9 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 11 Mar 2026 11:25:58 +0100
Subject: x86/hyperv: Save segment registers directly to memory in
 hv_hvcrash_ctxt_save()

hv_hvcrash_ctxt_save() in arch/x86/hyperv/hv_crash.c currently saves
segment registers via a general-purpose register (%eax). Update the
code to save segment registers (cs, ss, ds, es, fs, gs) directly to
the crash context memory using movw. This avoids unnecessary use of
a general-purpose register, making the code simpler and more efficient.

The size of the corresponding object file improves as follows:

   text    data     bss     dec     hex filename
   4167     176     200    4543    11bf hv_crash-old.o
   4151     176     200    4527    11af hv_crash-new.o

No functional change occurs to the saved context contents; this is
purely a code-quality improvement.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Long Li <longli@microsoft.com>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/hyperv/hv_crash.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c
index fdb277bf73d8..2c7ea7e70854 100644
--- a/arch/x86/hyperv/hv_crash.c
+++ b/arch/x86/hyperv/hv_crash.c
@@ -207,12 +207,12 @@ static void hv_hvcrash_ctxt_save(void)
 	asm volatile("movq %%cr2, %0" : "=a"(ctxt->cr2));
 	asm volatile("movq %%cr8, %0" : "=a"(ctxt->cr8));
 
-	asm volatile("movl %%cs, %%eax" : "=a"(ctxt->cs));
-	asm volatile("movl %%ss, %%eax" : "=a"(ctxt->ss));
-	asm volatile("movl %%ds, %%eax" : "=a"(ctxt->ds));
-	asm volatile("movl %%es, %%eax" : "=a"(ctxt->es));
-	asm volatile("movl %%fs, %%eax" : "=a"(ctxt->fs));
-	asm volatile("movl %%gs, %%eax" : "=a"(ctxt->gs));
+	asm volatile("movw %%cs, %0" : "=m"(ctxt->cs));
+	asm volatile("movw %%ss, %0" : "=m"(ctxt->ss));
+	asm volatile("movw %%ds, %0" : "=m"(ctxt->ds));
+	asm volatile("movw %%es, %0" : "=m"(ctxt->es));
+	asm volatile("movw %%fs, %0" : "=m"(ctxt->fs));
+	asm volatile("movw %%gs, %0" : "=m"(ctxt->gs));
 
 	native_store_gdt(&ctxt->gdtr);
 	store_idt(&ctxt->idtr);
-- 
cgit v1.2.3


From 2536091d585ac0b60ccf80cbe7a0bf4bfb75ec00 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 11 Mar 2026 11:25:59 +0100
Subject: x86/hyperv: Use current_stack_pointer to avoid asm() in
 hv_hvcrash_ctxt_save()

Use current_stack_pointer to avoid asm() when saving %rsp to the
crash context memory in hv_hvcrash_ctxt_save(). The new code is
more readable and results in exactly the same object file.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Long Li <longli@microsoft.com>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/hyperv/hv_crash.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c
index 2c7ea7e70854..d0f95a278fdb 100644
--- a/arch/x86/hyperv/hv_crash.c
+++ b/arch/x86/hyperv/hv_crash.c
@@ -199,7 +199,7 @@ static void hv_hvcrash_ctxt_save(void)
 {
 	struct hv_crash_ctxt *ctxt = &hv_crash_ctxt;
 
-	asm volatile("movq %%rsp,%0" : "=m"(ctxt->rsp));
+	ctxt->rsp = current_stack_pointer;
 
 	ctxt->cr0 = native_read_cr0();
 	ctxt->cr4 = native_read_cr4();
-- 
cgit v1.2.3


From afeb96cb188d44a61033d838fda0acaa11d1ff24 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 11 Mar 2026 11:26:00 +0100
Subject: x86/hyperv: Use any general-purpose register when saving %cr2 and
 %cr8

hv_hvcrash_ctxt_save() in arch/x86/hyperv/hv_crash.c currently saves %cr2
and %cr8 using %eax ("=a"). This unnecessarily forces a specific register.
Update the inline assembly to use a general-purpose register ("=r") for
both %cr2 and %cr8. This makes the code more flexible for the compiler
while producing the same saved context contents.

No functional changes.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Long Li <longli@microsoft.com>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/hyperv/hv_crash.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/hv_crash.c b/arch/x86/hyperv/hv_crash.c
index d0f95a278fdb..5ffcc23255de 100644
--- a/arch/x86/hyperv/hv_crash.c
+++ b/arch/x86/hyperv/hv_crash.c
@@ -204,8 +204,8 @@ static void hv_hvcrash_ctxt_save(void)
 	ctxt->cr0 = native_read_cr0();
 	ctxt->cr4 = native_read_cr4();
 
-	asm volatile("movq %%cr2, %0" : "=a"(ctxt->cr2));
-	asm volatile("movq %%cr8, %0" : "=a"(ctxt->cr8));
+	asm volatile("movq %%cr2, %0" : "=r"(ctxt->cr2));
+	asm volatile("movq %%cr8, %0" : "=r"(ctxt->cr8));
 
 	asm volatile("movw %%cs, %0" : "=m"(ctxt->cs));
 	asm volatile("movw %%ss, %0" : "=m"(ctxt->ss));
-- 
cgit v1.2.3


From 0fc773b0e4c1d9fe7cbf56d4df08d7bf90b58fb2 Mon Sep 17 00:00:00 2001
From: Mukesh R <mrathor@linux.microsoft.com>
Date: Tue, 3 Mar 2026 16:02:51 -0800
Subject: mshv: pass struct mshv_user_mem_region by reference

For unstated reasons, function mshv_partition_ioctl_set_memory passes
struct mshv_user_mem_region by value instead of by reference. Change
it to pass by reference.

Signed-off-by: Mukesh R <mrathor@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_root_main.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 9d1b881764ed..e281311b6a9d 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -1288,7 +1288,7 @@ err_out:
  */
 static long
 mshv_map_user_memory(struct mshv_partition *partition,
-		     struct mshv_user_mem_region mem)
+		     struct mshv_user_mem_region *mem)
 {
 	struct mshv_mem_region *region;
 	struct vm_area_struct *vma;
@@ -1296,12 +1296,12 @@ mshv_map_user_memory(struct mshv_partition *partition,
 	ulong mmio_pfn;
 	long ret;
 
-	if (mem.flags & BIT(MSHV_SET_MEM_BIT_UNMAP) ||
-	    !access_ok((const void __user *)mem.userspace_addr, mem.size))
+	if (mem->flags & BIT(MSHV_SET_MEM_BIT_UNMAP) ||
+	    !access_ok((const void __user *)mem->userspace_addr, mem->size))
 		return -EINVAL;
 
 	mmap_read_lock(current->mm);
-	vma = vma_lookup(current->mm, mem.userspace_addr);
+	vma = vma_lookup(current->mm, mem->userspace_addr);
 	is_mmio = vma ? !!(vma->vm_flags & (VM_IO | VM_PFNMAP)) : 0;
 	mmio_pfn = is_mmio ? vma->vm_pgoff : 0;
 	mmap_read_unlock(current->mm);
@@ -1309,7 +1309,7 @@ mshv_map_user_memory(struct mshv_partition *partition,
 	if (!vma)
 		return -EINVAL;
 
-	ret = mshv_partition_create_region(partition, &mem, &region,
+	ret = mshv_partition_create_region(partition, mem, &region,
 					   is_mmio);
 	if (ret)
 		return ret;
@@ -1354,25 +1354,25 @@ errout:
 /* Called for unmapping both the guest ram and the mmio space */
 static long
 mshv_unmap_user_memory(struct mshv_partition *partition,
-		       struct mshv_user_mem_region mem)
+		       struct mshv_user_mem_region *mem)
 {
 	struct mshv_mem_region *region;
 
-	if (!(mem.flags & BIT(MSHV_SET_MEM_BIT_UNMAP)))
+	if (!(mem->flags & BIT(MSHV_SET_MEM_BIT_UNMAP)))
 		return -EINVAL;
 
 	spin_lock(&partition->pt_mem_regions_lock);
 
-	region = mshv_partition_region_by_gfn(partition, mem.guest_pfn);
+	region = mshv_partition_region_by_gfn(partition, mem->guest_pfn);
 	if (!region) {
 		spin_unlock(&partition->pt_mem_regions_lock);
 		return -ENOENT;
 	}
 
 	/* Paranoia check */
-	if (region->start_uaddr != mem.userspace_addr ||
-	    region->start_gfn != mem.guest_pfn ||
-	    region->nr_pages != HVPFN_DOWN(mem.size)) {
+	if (region->start_uaddr != mem->userspace_addr ||
+	    region->start_gfn != mem->guest_pfn ||
+	    region->nr_pages != HVPFN_DOWN(mem->size)) {
 		spin_unlock(&partition->pt_mem_regions_lock);
 		return -EINVAL;
 	}
@@ -1403,9 +1403,9 @@ mshv_partition_ioctl_set_memory(struct mshv_partition *partition,
 		return -EINVAL;
 
 	if (mem.flags & BIT(MSHV_SET_MEM_BIT_UNMAP))
-		return mshv_unmap_user_memory(partition, mem);
+		return mshv_unmap_user_memory(partition, &mem);
 
-	return mshv_map_user_memory(partition, mem);
+	return mshv_map_user_memory(partition, &mem);
 }
 
 static long
-- 
cgit v1.2.3


From 0a8321dde01ffdbd9455a028194d57484def59eb Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Sun, 1 Mar 2026 00:17:59 +0530
Subject: powerpc/mem: Move CMA reservations to arch_mm_preinit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model"),
changed the initialization order of "pageblock_order" from...
start_kernel()
    - setup_arch()
       - initmem_init()
         - sparse_init()
           - set_pageblock_order();  // this sets the pageblock_order
       - xxx_cma_reserve();

to...
start_kernel()
    - setup_arch()
       - xxx_cma_reserve();
    - mm_core_init_early()
       - free_area_init()
          - sparse_init()
             - set_pageblock_order() // this sets the pageblock_order.

So this means, pageblock_order is not initialized before these cma
reservation function calls, hence we are seeing CMA failures like...

[    0.000000] kvm_cma_reserve: reserving 3276 MiB for global area
[    0.000000] cma: pageblock_order not yet initialized. Called during early boot?
[    0.000000] cma: Failed to reserve 3276 MiB
....
[    0.000000][    T0] cma: pageblock_order not yet initialized. Called during early boot?
[    0.000000][    T0] cma: Failed to reserve 1024 MiB

This patch moves these CMA reservations to arch_mm_preinit() which
happens in mm_core_init() (which happens after pageblock_order is
initialized), but before the memblock moves the free memory to buddy.

Fixes: 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model")
Suggested-by: Mike Rapoport <rppt@kernel.org>
Reported-and-tested-by: Sourabh Jain <sourabhjain@linux.ibm.com>
Closes: https://lore.kernel.org/linuxppc-dev/4c338a29-d190-44f3-8874-6cfa0a031f0b@linux.ibm.com/
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Tested-by: Dan Horák <dan@danny.cz>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/6e532cf0db5be99afbe20eed699163d5e86cd71f.1772303986.git.ritesh.list@gmail.com
---
 arch/powerpc/kernel/setup-common.c | 10 ----------
 arch/powerpc/mm/mem.c              | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index cb5b73adc250..b1761909c23f 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -35,7 +35,6 @@
 #include <linux/of_irq.h>
 #include <linux/hugetlb.h>
 #include <linux/pgtable.h>
-#include <asm/kexec.h>
 #include <asm/io.h>
 #include <asm/paca.h>
 #include <asm/processor.h>
@@ -995,15 +994,6 @@ void __init setup_arch(char **cmdline_p)
 
 	initmem_init();
 
-	/*
-	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM and
-	 * hugetlb. These must be called after initmem_init(), so that
-	 * pageblock_order is initialised.
-	 */
-	fadump_cma_init();
-	kdump_cma_reserve();
-	kvm_cma_reserve();
-
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 
 	if (ppc_md.setup_arch)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index a985fc96b953..b7982d0243d4 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -30,6 +30,10 @@
 #include <asm/setup.h>
 #include <asm/fixmap.h>
 
+#include <asm/fadump.h>
+#include <asm/kexec.h>
+#include <asm/kvm_ppc.h>
+
 #include <mm/mmu_decl.h>
 
 unsigned long long memory_limit __initdata;
@@ -268,6 +272,16 @@ void __init paging_init(void)
 
 void __init arch_mm_preinit(void)
 {
+
+	/*
+	 * Reserve large chunks of memory for use by CMA for kdump, fadump, KVM
+	 * and hugetlb. These must be called after pageblock_order is
+	 * initialised.
+	 */
+	fadump_cma_init();
+	kdump_cma_reserve();
+	kvm_cma_reserve();
+
 	/*
 	 * book3s is limited to 16 page sizes due to encoding this in
 	 * a 4-bit field for slices.
-- 
cgit v1.2.3


From e9bbfb4bfa86c6b5515b868d6982ac60505d7e39 Mon Sep 17 00:00:00 2001
From: Viktor Malik <vmalik@redhat.com>
Date: Mon, 9 Mar 2026 15:40:45 +0100
Subject: powerpc, perf: Check that current->mm is alive before getting user
 callchain

It may happen that mm is already released, which leads to kernel panic.
This adds the NULL check for current->mm, similarly to
commit 20afc60f892d ("x86, perf: Check that current->mm is alive before getting user callchain").

I was getting this panic when running a profiling BPF program
(profile.py from bcc-tools):

    [26215.051935] Kernel attempted to read user page (588) - exploit attempt? (uid: 0)
    [26215.051950] BUG: Kernel NULL pointer dereference on read at 0x00000588
    [26215.051952] Faulting instruction address: 0xc00000000020fac0
    [26215.051957] Oops: Kernel access of bad area, sig: 11 [#1]
    [...]
    [26215.052049] Call Trace:
    [26215.052050] [c000000061da6d30] [c00000000020fc10] perf_callchain_user_64+0x2d0/0x490 (unreliable)
    [26215.052054] [c000000061da6dc0] [c00000000020f92c] perf_callchain_user+0x1c/0x30
    [26215.052057] [c000000061da6de0] [c0000000005ab2a0] get_perf_callchain+0x100/0x360
    [26215.052063] [c000000061da6e70] [c000000000573bc8] bpf_get_stackid+0x88/0xf0
    [26215.052067] [c000000061da6ea0] [c008000000042258] bpf_prog_16d4ab9ab662f669_do_perf_event+0xf8/0x274
    [...]

In addition, move storing the top-level stack entry to generic
perf_callchain_user to make sure the top-evel entry is always captured,
even if current->mm is NULL.

Fixes: 20002ded4d93 ("perf_counter: powerpc: Add callchain support")
Signed-off-by: Viktor Malik <vmalik@redhat.com>
Tested-by: Qiao Zhao <qzhao@redhat.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Reviewed-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
[Maddy: fixed message to avoid checkpatch format style error]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260309144045.169427-1-vmalik@redhat.com
---
 arch/powerpc/perf/callchain.c    | 5 +++++
 arch/powerpc/perf/callchain_32.c | 1 -
 arch/powerpc/perf/callchain_64.c | 1 -
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 26aa26482c9a..992cc5c98214 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -103,6 +103,11 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
+
+	if (!current->mm)
+		return;
+
 	if (!is_32bit_task())
 		perf_callchain_user_64(entry, regs);
 	else
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ddcc2d8aa64a..0de21c5d272c 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -142,7 +142,6 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 115d1c105e8a..30fb61c5f0cb 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -77,7 +77,6 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < entry->max_stack) {
 		fp = (unsigned long __user *) sp;
-- 
cgit v1.2.3


From 6bc9c0a905228bea5c53ec195fe54f5f0233dccc Mon Sep 17 00:00:00 2001
From: Sayali Patil <sayalip@linux.ibm.com>
Date: Wed, 4 Mar 2026 17:52:00 +0530
Subject: powerpc: fix KUAP warning in VMX usercopy path

On powerpc with PREEMPT_FULL or PREEMPT_LAZY and function tracing enabled,
KUAP warnings can be triggered from the VMX usercopy path under memory
stress workloads.

KUAP requires that no subfunctions are called once userspace access has
been enabled. The existing VMX copy implementation violates this
requirement by invoking enter_vmx_usercopy() from the assembly path after
userspace access has already been enabled. If preemption occurs
in this window, the AMR state may not be preserved correctly,
leading to unexpected userspace access state and resulting in
KUAP warnings.

Fix this by restructuring the VMX usercopy flow so that VMX selection
and VMX state management are centralized in raw_copy_tofrom_user(),
which is invoked by the raw_copy_{to,from,in}_user() wrappers.

The new flow is:

  - raw_copy_{to,from,in}_user() calls raw_copy_tofrom_user()
  - raw_copy_tofrom_user() decides whether to use the VMX path
    based on size and CPU capability
  - Call enter_vmx_usercopy() before enabling userspace access
  - Enable userspace access as per the copy direction
    and perform the VMX copy
  - Disable userspace access as per the copy direction
  - Call exit_vmx_usercopy()
  - Fall back to the base copy routine if the VMX copy faults

With this change, the VMX assembly routines no longer perform VMX state
management or call helper functions; they only implement the
copy operations.
The previous feature-section based VMX selection inside
__copy_tofrom_user_power7() is removed, and a dedicated
__copy_tofrom_user_power7_vmx() entry point is introduced.

This ensures correct KUAP ordering, avoids subfunction calls
while KUAP is unlocked, and eliminates the warnings while preserving
the VMX fast path.

Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Reported-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Closes: https://lore.kernel.org/all/20260109064917.777587-2-sshegde@linux.ibm.com/
Suggested-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Reviewed-by: Christophe Leroy (CS GROUP) <chleroy@kernel.org>
Co-developed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Signed-off-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260304122201.153049-1-sayalip@linux.ibm.com
---
 arch/powerpc/include/asm/uaccess.h | 65 ++++++++++++++++++++++++++------------
 arch/powerpc/lib/copyuser_64.S     |  1 +
 arch/powerpc/lib/copyuser_power7.S | 45 +++++++++-----------------
 arch/powerpc/lib/vmx-helper.c      |  2 ++
 4 files changed, 63 insertions(+), 50 deletions(-)

diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 570b3d91e2e4..17e63244e885 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -15,6 +15,9 @@
 #define TASK_SIZE_MAX		TASK_SIZE_USER64
 #endif
 
+/* Threshold above which VMX copy path is used */
+#define VMX_COPY_THRESHOLD 3328
+
 #include <asm-generic/access_ok.h>
 
 /*
@@ -326,40 +329,62 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
-#ifdef __powerpc64__
-static inline unsigned long
-raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+unsigned long __copy_tofrom_user_base(void __user *to,
+				      const void __user *from, unsigned long size);
+
+unsigned long __copy_tofrom_user_power7_vmx(void __user *to,
+					    const void __user *from, unsigned long size);
+
+static __always_inline bool will_use_vmx(unsigned long n)
+{
+	return IS_ENABLED(CONFIG_ALTIVEC) && cpu_has_feature(CPU_FTR_VMX_COPY) &&
+	       n > VMX_COPY_THRESHOLD;
+}
+
+static __always_inline unsigned long
+raw_copy_tofrom_user(void __user *to, const void __user *from,
+		     unsigned long n, unsigned long dir)
 {
 	unsigned long ret;
 
-	barrier_nospec();
-	allow_user_access(to, KUAP_READ_WRITE);
+	if (will_use_vmx(n) && enter_vmx_usercopy()) {
+		allow_user_access(to, dir);
+		ret = __copy_tofrom_user_power7_vmx(to, from, n);
+		prevent_user_access(dir);
+		exit_vmx_usercopy();
+
+		if (unlikely(ret)) {
+			allow_user_access(to, dir);
+			ret = __copy_tofrom_user_base(to, from, n);
+			prevent_user_access(dir);
+		}
+		return ret;
+	}
+
+	allow_user_access(to, dir);
 	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(KUAP_READ_WRITE);
+	prevent_user_access(dir);
 	return ret;
 }
-#endif /* __powerpc64__ */
 
-static inline unsigned long raw_copy_from_user(void *to,
-		const void __user *from, unsigned long n)
+#ifdef CONFIG_PPC64
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 {
-	unsigned long ret;
+	barrier_nospec();
+	return raw_copy_tofrom_user(to, from, n, KUAP_READ_WRITE);
+}
+#endif /* CONFIG_PPC64 */
 
-	allow_user_access(NULL, KUAP_READ);
-	ret = __copy_tofrom_user((__force void __user *)to, from, n);
-	prevent_user_access(KUAP_READ);
-	return ret;
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return raw_copy_tofrom_user((__force void __user *)to, from, n, KUAP_READ);
 }
 
 static inline unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
-
-	allow_user_access(to, KUAP_WRITE);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
-	prevent_user_access(KUAP_WRITE);
-	return ret;
+	return raw_copy_tofrom_user(to, (__force const void __user *)from, n, KUAP_WRITE);
 }
 
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 9af969d2cc0c..25a99108caff 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -562,3 +562,4 @@ exc;	std	r10,32(3)
 	li	r5,4096
 	b	.Ldst_aligned
 EXPORT_SYMBOL(__copy_tofrom_user)
+EXPORT_SYMBOL(__copy_tofrom_user_base)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 8474c682a178..17dbcfbae25f 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -5,13 +5,9 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
+#include <linux/export.h>
 #include <asm/ppc_asm.h>
 
-#ifndef SELFTEST_CASE
-/* 0 == don't use VMX, 1 == use VMX */
-#define SELFTEST_CASE	0
-#endif
-
 #ifdef __BIG_ENDIAN__
 #define LVS(VRT,RA,RB)		lvsl	VRT,RA,RB
 #define VPERM(VRT,VRA,VRB,VRC)	vperm	VRT,VRA,VRB,VRC
@@ -47,10 +43,14 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	CFUNC(exit_vmx_usercopy)
+	ld      r6,STK_REG(R31)(r1)	/* original destination pointer */
+	ld      r5,STK_REG(R29)(r1)	/* original number of bytes */
+	subf    r7,r6,r3		/* #bytes copied */
+	subf    r3,r7,r5		/* #bytes not copied in r3 */
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
-	b	.Lexit
+	addi    r1,r1,STACKFRAMESIZE
+	blr
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
@@ -74,7 +74,6 @@
 
 _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
-	cmpldi	cr1,r5,3328
 
 	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
@@ -82,12 +81,6 @@ _GLOBAL(__copy_tofrom_user_power7)
 
 	blt	.Lshort_copy
 
-#ifdef CONFIG_ALTIVEC
-test_feature = SELFTEST_CASE
-BEGIN_FTR_SECTION
-	bgt	cr1,.Lvmx_copy
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif
 
 .Lnonvmx_copy:
 	/* Get the source 8B aligned */
@@ -263,23 +256,14 @@ err1;	stb	r0,0(r3)
 15:	li	r3,0
 	blr
 
-.Lunwind_stack_nonvmx_copy:
-	addi	r1,r1,STACKFRAMESIZE
-	b	.Lnonvmx_copy
-
-.Lvmx_copy:
 #ifdef CONFIG_ALTIVEC
+_GLOBAL(__copy_tofrom_user_power7_vmx)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	CFUNC(enter_vmx_usercopy)
-	cmpwi	cr1,r3,0
-	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STK_REG(R31)(r1)
-	ld	r4,STK_REG(R30)(r1)
-	ld	r5,STK_REG(R29)(r1)
-	mtlr	r0
 
+	std     r3,STK_REG(R31)(r1)
+	std     r5,STK_REG(R29)(r1)
 	/*
 	 * We prefetch both the source and destination using enhanced touch
 	 * instructions. We use a stream ID of 0 for the load side and
@@ -300,8 +284,6 @@ err1;	stb	r0,0(r3)
 
 	DCBT_SETUP_STREAMS(r6, r7, r9, r10, r8)
 
-	beq	cr1,.Lunwind_stack_nonvmx_copy
-
 	/*
 	 * If source and destination are not relatively aligned we use a
 	 * slower permute loop.
@@ -478,7 +460,8 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -681,5 +664,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	CFUNC(exit_vmx_usercopy)	/* tail call optimise */
+	li r3,0
+	blr
+EXPORT_SYMBOL(__copy_tofrom_user_power7_vmx)
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 54340912398f..554b248002b4 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,6 +27,7 @@ int enter_vmx_usercopy(void)
 
 	return 1;
 }
+EXPORT_SYMBOL(enter_vmx_usercopy);
 
 /*
  * This function must return 0 because we tail call optimise when calling
@@ -49,6 +50,7 @@ int exit_vmx_usercopy(void)
 		set_dec(1);
 	return 0;
 }
+EXPORT_SYMBOL(exit_vmx_usercopy);
 
 int enter_vmx_ops(void)
 {
-- 
cgit v1.2.3


From 146c9ab38b48004b40735b6c1e1c2b5adf6436f9 Mon Sep 17 00:00:00 2001
From: Sayali Patil <sayalip@linux.ibm.com>
Date: Wed, 4 Mar 2026 17:52:01 +0530
Subject: powerpc/selftests/copyloops: extend selftest to exercise
 __copy_tofrom_user_power7_vmx

The new PowerPC VMX fast path (__copy_tofrom_user_power7_vmx) is not
exercised by existing copyloops selftests. This patch updates
the selftest to exercise the VMX variant, ensuring the VMX copy path
is validated.

Changes include:
  - COPY_LOOP=test___copy_tofrom_user_power7_vmx with -D VMX_TEST is used
    in existing selftest build targets.
  - Inclusion of ../utils.c to provide get_auxv_entry() for hardware
    feature detection.
  - At runtime, the test skips execution if Altivec is not available.
  - Copy sizes above VMX_COPY_THRESHOLD are used to ensure the VMX
    path is taken.

This enables validation of the VMX fast path without affecting systems
that do not support Altivec.

Signed-off-by: Sayali Patil <sayalip@linux.ibm.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260304122201.153049-2-sayalip@linux.ibm.com
---
 tools/testing/selftests/powerpc/copyloops/.gitignore |  4 ++--
 tools/testing/selftests/powerpc/copyloops/Makefile   | 11 ++++++++---
 tools/testing/selftests/powerpc/copyloops/stubs.S    |  8 --------
 tools/testing/selftests/powerpc/copyloops/validate.c | 15 ++++++++++++++-
 4 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index 7283e8b07b75..80d4270a71ac 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -2,8 +2,8 @@
 copyuser_64_t0
 copyuser_64_t1
 copyuser_64_t2
-copyuser_p7_t0
-copyuser_p7_t1
+copyuser_p7
+copyuser_p7_vmx
 memcpy_64_t0
 memcpy_64_t1
 memcpy_64_t2
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 42940f92d832..0c8efb0bddeb 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
-		copyuser_p7_t0 copyuser_p7_t1 \
+		copyuser_p7 copyuser_p7_vmx \
 		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
 		memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \
 		copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2 \
@@ -28,10 +28,15 @@ $(OUTPUT)/copyuser_64_t%:	copyuser_64.S $(EXTRA_SOURCES)
 		-D SELFTEST_CASE=$(subst copyuser_64_t,,$(notdir $@)) \
 		-o $@ $^
 
-$(OUTPUT)/copyuser_p7_t%:	copyuser_power7.S $(EXTRA_SOURCES)
+$(OUTPUT)/copyuser_p7:	copyuser_power7.S $(EXTRA_SOURCES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) \
 		-D COPY_LOOP=test___copy_tofrom_user_power7 \
-		-D SELFTEST_CASE=$(subst copyuser_p7_t,,$(notdir $@)) \
+		-o $@ $^
+
+$(OUTPUT)/copyuser_p7_vmx:       copyuser_power7.S $(EXTRA_SOURCES) ../utils.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) \
+		-D COPY_LOOP=test___copy_tofrom_user_power7_vmx \
+		-D VMX_TEST \
 		-o $@ $^
 
 # Strictly speaking, we only need the memcpy_64 test cases for big-endian
diff --git a/tools/testing/selftests/powerpc/copyloops/stubs.S b/tools/testing/selftests/powerpc/copyloops/stubs.S
index ec8bcf2bf1c2..3a9cb8c9a3ee 100644
--- a/tools/testing/selftests/powerpc/copyloops/stubs.S
+++ b/tools/testing/selftests/powerpc/copyloops/stubs.S
@@ -1,13 +1,5 @@
 #include <asm/ppc_asm.h>
 
-FUNC_START(enter_vmx_usercopy)
-	li	r3,1
-	blr
-
-FUNC_START(exit_vmx_usercopy)
-	li	r3,0
-	blr
-
 FUNC_START(enter_vmx_ops)
 	li	r3,1
 	blr
diff --git a/tools/testing/selftests/powerpc/copyloops/validate.c b/tools/testing/selftests/powerpc/copyloops/validate.c
index 0f6873618552..fb822534fbe9 100644
--- a/tools/testing/selftests/powerpc/copyloops/validate.c
+++ b/tools/testing/selftests/powerpc/copyloops/validate.c
@@ -12,6 +12,10 @@
 #define BUFLEN (MAX_LEN+MAX_OFFSET+2*MIN_REDZONE)
 #define POISON 0xa5
 
+#ifdef VMX_TEST
+#define VMX_COPY_THRESHOLD 3328
+#endif
+
 unsigned long COPY_LOOP(void *to, const void *from, unsigned long size);
 
 static void do_one(char *src, char *dst, unsigned long src_off,
@@ -81,8 +85,12 @@ int test_copy_loop(void)
 	/* Fill with sequential bytes */
 	for (i = 0; i < BUFLEN; i++)
 		fill[i] = i & 0xff;
-
+#ifdef VMX_TEST
+	/* Force sizes above kernel VMX threshold (3328) */
+	for (len = VMX_COPY_THRESHOLD + 1; len < MAX_LEN; len++) {
+#else
 	for (len = 1; len < MAX_LEN; len++) {
+#endif
 		for (src_off = 0; src_off < MAX_OFFSET; src_off++) {
 			for (dst_off = 0; dst_off < MAX_OFFSET; dst_off++) {
 				do_one(src, dst, src_off, dst_off, len,
@@ -96,5 +104,10 @@ int test_copy_loop(void)
 
 int main(void)
 {
+#ifdef VMX_TEST
+	/* Skip if Altivec not present */
+	SKIP_IF_MSG(!have_hwcap(PPC_FEATURE_HAS_ALTIVEC), "ALTIVEC not supported");
+#endif
+
 	return test_harness(test_copy_loop, str(COPY_LOOP));
 }
-- 
cgit v1.2.3


From 9f455aac17db0aa1486c94dd2c231353ebc9d8bc Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:34 +0100
Subject: xfrm: state: fix sparse warnings on xfrm_state_hold_rcu

In all callers, x is not an __rcu pointer. We can drop the annotation to
avoid sparse warnings:

net/xfrm/xfrm_state.c:58:39: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_state.c:58:39:    expected struct refcount_struct [usertype] *r
net/xfrm/xfrm_state.c:58:39:    got struct refcount_struct [noderef] __rcu *
net/xfrm/xfrm_state.c:1166:42: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_state.c:1166:42:    expected struct xfrm_state [noderef] __rcu *x
net/xfrm/xfrm_state.c:1166:42:    got struct xfrm_state *[assigned] x
(repeated for each caller)

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a00c4fe1ab0c..ad32085267a5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -53,7 +53,7 @@ static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
 static HLIST_HEAD(xfrm_state_gc_list);
 static HLIST_HEAD(xfrm_state_dev_gc_list);
 
-static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
+static inline bool xfrm_state_hold_rcu(struct xfrm_state *x)
 {
 	return refcount_inc_not_zero(&x->refcnt);
 }
-- 
cgit v1.2.3


From e2f845f672782b2522062cf1c9aad774276250d7 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:35 +0100
Subject: xfrm: state: fix sparse warnings in xfrm_state_init

Use rcu_assign_pointer, and tmp variables for freeing on the error
path without accessing net->xfrm.state_by*.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index ad32085267a5..b81303cccc5e 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -3259,6 +3259,7 @@ EXPORT_SYMBOL(xfrm_init_state);
 
 int __net_init xfrm_state_init(struct net *net)
 {
+	struct hlist_head *ndst, *nsrc, *nspi, *nseq;
 	unsigned int sz;
 
 	if (net_eq(net, &init_net))
@@ -3269,18 +3270,25 @@ int __net_init xfrm_state_init(struct net *net)
 
 	sz = sizeof(struct hlist_head) * 8;
 
-	net->xfrm.state_bydst = xfrm_hash_alloc(sz);
-	if (!net->xfrm.state_bydst)
+	ndst = xfrm_hash_alloc(sz);
+	if (!ndst)
 		goto out_bydst;
-	net->xfrm.state_bysrc = xfrm_hash_alloc(sz);
-	if (!net->xfrm.state_bysrc)
+	rcu_assign_pointer(net->xfrm.state_bydst, ndst);
+
+	nsrc = xfrm_hash_alloc(sz);
+	if (!nsrc)
 		goto out_bysrc;
-	net->xfrm.state_byspi = xfrm_hash_alloc(sz);
-	if (!net->xfrm.state_byspi)
+	rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
+
+	nspi = xfrm_hash_alloc(sz);
+	if (!nspi)
 		goto out_byspi;
-	net->xfrm.state_byseq = xfrm_hash_alloc(sz);
-	if (!net->xfrm.state_byseq)
+	rcu_assign_pointer(net->xfrm.state_byspi, nspi);
+
+	nseq = xfrm_hash_alloc(sz);
+	if (!nseq)
 		goto out_byseq;
+	rcu_assign_pointer(net->xfrm.state_byseq, nseq);
 
 	net->xfrm.state_cache_input = alloc_percpu(struct hlist_head);
 	if (!net->xfrm.state_cache_input)
@@ -3296,13 +3304,13 @@ int __net_init xfrm_state_init(struct net *net)
 	return 0;
 
 out_state_cache_input:
-	xfrm_hash_free(net->xfrm.state_byseq, sz);
+	xfrm_hash_free(nseq, sz);
 out_byseq:
-	xfrm_hash_free(net->xfrm.state_byspi, sz);
+	xfrm_hash_free(nspi, sz);
 out_byspi:
-	xfrm_hash_free(net->xfrm.state_bysrc, sz);
+	xfrm_hash_free(nsrc, sz);
 out_bysrc:
-	xfrm_hash_free(net->xfrm.state_bydst, sz);
+	xfrm_hash_free(ndst, sz);
 out_bydst:
 	return -ENOMEM;
 }
-- 
cgit v1.2.3


From 55b5bc03148b26ce8156bc47b637a7337aa7d257 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:36 +0100
Subject: xfrm: state: fix sparse warnings around XFRM_STATE_INSERT

We're under xfrm_state_lock in all those cases, use
xfrm_state_deref_prot(state_by*) to avoid sparse warnings:

net/xfrm/xfrm_state.c:2597:25: warning: cast removes address space '__rcu' of expression
net/xfrm/xfrm_state.c:2597:25: warning: incorrect type in argument 2 (different address spaces)
net/xfrm/xfrm_state.c:2597:25:    expected struct hlist_head *h
net/xfrm/xfrm_state.c:2597:25:    got struct hlist_head [noderef] __rcu *

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b81303cccc5e..34cf9f361683 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1563,23 +1563,23 @@ found:
 			list_add(&x->km.all, &net->xfrm.state_all);
 			h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 			XFRM_STATE_INSERT(bydst, &x->bydst,
-					  net->xfrm.state_bydst + h,
+					  xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h,
 					  x->xso.type);
 			h = xfrm_src_hash(net, daddr, saddr, encap_family);
 			XFRM_STATE_INSERT(bysrc, &x->bysrc,
-					  net->xfrm.state_bysrc + h,
+					  xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h,
 					  x->xso.type);
 			INIT_HLIST_NODE(&x->state_cache);
 			if (x->id.spi) {
 				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
 				XFRM_STATE_INSERT(byspi, &x->byspi,
-						  net->xfrm.state_byspi + h,
+						  xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h,
 						  x->xso.type);
 			}
 			if (x->km.seq) {
 				h = xfrm_seq_hash(net, x->km.seq);
 				XFRM_STATE_INSERT(byseq, &x->byseq,
-						  net->xfrm.state_byseq + h,
+						  xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h,
 						  x->xso.type);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
@@ -1730,25 +1730,29 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 
 	h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
 			  x->props.reqid, x->props.family);
-	XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+	XFRM_STATE_INSERT(bydst, &x->bydst,
+			  xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h,
 			  x->xso.type);
 
 	h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
-	XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+	XFRM_STATE_INSERT(bysrc, &x->bysrc,
+			  xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h,
 			  x->xso.type);
 
 	if (x->id.spi) {
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
 				  x->props.family);
 
-		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+		XFRM_STATE_INSERT(byspi, &x->byspi,
+				  xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h,
 				  x->xso.type);
 	}
 
 	if (x->km.seq) {
 		h = xfrm_seq_hash(net, x->km.seq);
 
-		XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h,
+		XFRM_STATE_INSERT(byseq, &x->byseq,
+				  xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h,
 				  x->xso.type);
 	}
 
@@ -1868,10 +1872,12 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		list_add(&x->km.all, &net->xfrm.state_all);
-		XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+		XFRM_STATE_INSERT(bydst, &x->bydst,
+				  xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h,
 				  x->xso.type);
 		h = xfrm_src_hash(net, daddr, saddr, family);
-		XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+		XFRM_STATE_INSERT(bysrc, &x->bysrc,
+				  xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h,
 				  x->xso.type);
 
 		net->xfrm.state_num++;
@@ -2603,7 +2609,9 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
 		if (!x0) {
 			x->id.spi = newspi;
 			h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family);
-			XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type);
+			XFRM_STATE_INSERT(byspi, &x->byspi,
+					  xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h,
+					  x->xso.type);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 			err = 0;
 			goto unlock;
-- 
cgit v1.2.3


From 33cefb76a8edee8af257abfe6f42fb987c77132f Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:37 +0100
Subject: xfrm: state: add xfrm_state_deref_prot to state_by* walk under lock

We're under xfrm_state_lock for all those walks, we can use
xfrm_state_deref_prot to silence sparse warnings such as:

net/xfrm/xfrm_state.c:933:17: warning: dereference of noderef expression

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 34cf9f361683..27192b11be43 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -870,7 +870,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
 		struct xfrm_state *x;
 
-		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) {
 			if (xfrm_id_proto_match(x->id.proto, proto) &&
 			   (err = security_xfrm_state_delete(x)) != 0) {
 				xfrm_audit_state_delete(x, 0, task_valid);
@@ -891,7 +891,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
 		struct xfrm_state *x;
 		struct xfrm_dev_offload *xso;
 
-		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) {
 			xso = &x->xso;
 
 			if (xso->dev == dev &&
@@ -931,7 +931,7 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
 		struct xfrm_state *x;
 restart:
-		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) {
 			if (!xfrm_state_kern(x) &&
 			    xfrm_id_proto_match(x->id.proto, proto)) {
 				xfrm_state_hold(x);
@@ -973,7 +973,7 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
 	err = -ESRCH;
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
 restart:
-		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) {
 			xso = &x->xso;
 
 			if (!xfrm_state_kern(x) && xso->dev == dev) {
@@ -1652,7 +1652,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
-	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+	hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) {
 		if (x->props.family == family &&
 		    x->props.reqid == reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -1779,7 +1779,7 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 	u32 cpu_id = xnew->pcpu_num;
 
 	h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
-	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+	hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) {
 		if (x->props.family	== family &&
 		    x->props.reqid	== reqid &&
 		    x->if_id		== if_id &&
@@ -1815,7 +1815,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 	struct xfrm_state *x;
 	u32 mark = m->v & m->m;
 
-	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+	hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) {
 		if (x->props.reqid  != reqid ||
 		    x->props.mode   != mode ||
 		    x->props.family != family ||
@@ -2097,7 +2097,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
 	if (m->reqid) {
 		h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->reqid, m->old_family);
-		hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -2116,7 +2116,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
 	} else {
 		h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr,
 				  m->old_family);
-		hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, bysrc) {
 			if (x->props.mode != m->mode ||
 			    x->id.proto != m->proto)
 				continue;
@@ -2319,7 +2319,7 @@ void xfrm_state_update_stats(struct net *net)
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
-		hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst)
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst)
 			xfrm_dev_state_update_stats(x);
 	}
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -2510,7 +2510,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s
 	unsigned int h = xfrm_seq_hash(net, seq);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) {
+	hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, byseq) {
 		if (x->km.seq == seq &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    x->pcpu_num == pcpu_num &&
-- 
cgit v1.2.3


From f468fdd52b97a63c4fb916fb882b936d8b43b8ae Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:38 +0100
Subject: xfrm: remove rcu/state_hold from xfrm_state_lookup_spi_proto

xfrm_state_lookup_spi_proto is called under xfrm_state_lock by
xfrm_alloc_spi, no need to take a reference on the state and pretend
to be under RCU.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 27192b11be43..f28cbe249c05 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1703,18 +1703,12 @@ static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 sp
 	struct xfrm_state *x;
 	unsigned int i;
 
-	rcu_read_lock();
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
-		hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) {
-			if (x->id.spi == spi && x->id.proto == proto) {
-				if (!xfrm_state_hold_rcu(x))
-					continue;
-				rcu_read_unlock();
+		hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + i, byspi) {
+			if (x->id.spi == spi && x->id.proto == proto)
 				return x;
-			}
 		}
 	}
-	rcu_read_unlock();
 	return NULL;
 }
 
@@ -2616,7 +2610,6 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
 			err = 0;
 			goto unlock;
 		}
-		xfrm_state_put(x0);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 next:
-- 
cgit v1.2.3


From 05b8673963c492fe36533e99a4a3c6661ca09ed0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:39 +0100
Subject: xfrm: state: silence sparse warnings during netns exit

Silence sparse warnings in xfrm_state_fini:
net/xfrm/xfrm_state.c:3327:9: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_state.c:3327:9:    expected struct hlist_head const *h
net/xfrm/xfrm_state.c:3327:9:    got struct hlist_head [noderef] __rcu *state_byseq

Add xfrm_state_deref_netexit() to wrap those calls. The netns is going
away, we don't have to worry about the state_by* pointers being
changed behind our backs.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index f28cbe249c05..1748d374abca 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -3316,6 +3316,8 @@ out_bydst:
 	return -ENOMEM;
 }
 
+#define xfrm_state_deref_netexit(table) \
+	rcu_dereference_protected((table), true /* netns is going away */)
 void xfrm_state_fini(struct net *net)
 {
 	unsigned int sz;
@@ -3328,17 +3330,17 @@ void xfrm_state_fini(struct net *net)
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
 	for (i = 0; i <= net->xfrm.state_hmask; i++) {
-		WARN_ON(!hlist_empty(net->xfrm.state_byseq + i));
-		WARN_ON(!hlist_empty(net->xfrm.state_byspi + i));
-		WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i));
-		WARN_ON(!hlist_empty(net->xfrm.state_bydst + i));
+		WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byseq) + i));
+		WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byspi) + i));
+		WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bysrc) + i));
+		WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bydst) + i));
 	}
 
 	sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
-	xfrm_hash_free(net->xfrm.state_byseq, sz);
-	xfrm_hash_free(net->xfrm.state_byspi, sz);
-	xfrm_hash_free(net->xfrm.state_bysrc, sz);
-	xfrm_hash_free(net->xfrm.state_bydst, sz);
+	xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byseq), sz);
+	xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byspi), sz);
+	xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bysrc), sz);
+	xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bydst), sz);
 	free_percpu(net->xfrm.state_cache_input);
 }
 
-- 
cgit v1.2.3


From b1f9c67781efd8a0ebd5019f14fbbac981cff7c1 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:40 +0100
Subject: xfrm: policy: fix sparse warnings in xfrm_policy_{init,fini}

In xfrm_policy_init:
add rcu_assign_pointer to fix warning:
net/xfrm/xfrm_policy.c:4238:29: warning: incorrect type in assignment (different address spaces)
net/xfrm/xfrm_policy.c:4238:29:    expected struct hlist_head [noderef] __rcu *table
net/xfrm/xfrm_policy.c:4238:29:    got struct hlist_head *

add rcu_dereference_protected to silence warning:
net/xfrm/xfrm_policy.c:4265:36: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_policy.c:4265:36:    expected struct hlist_head *n
net/xfrm/xfrm_policy.c:4265:36:    got struct hlist_head [noderef] __rcu *table

The netns is being created, no concurrent access is possible yet.

In xfrm_policy_fini, net is going away, there shouldn't be any
concurrent changes to the hashtables, so we can use
rcu_dereference_protected to silence warnings:
net/xfrm/xfrm_policy.c:4291:17: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_policy.c:4291:17:    expected struct hlist_head const *h
net/xfrm/xfrm_policy.c:4291:17:    got struct hlist_head [noderef] __rcu *table
net/xfrm/xfrm_policy.c:4292:36: warning: incorrect type in argument 1 (different address spaces)
net/xfrm/xfrm_policy.c:4292:36:    expected struct hlist_head *n
net/xfrm/xfrm_policy.c:4292:36:    got struct hlist_head [noderef] __rcu *table

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5428185196a1..49de5a6f4b85 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4242,7 +4242,7 @@ static int __net_init xfrm_policy_init(struct net *net)
 		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
 
 		htab = &net->xfrm.policy_bydst[dir];
-		htab->table = xfrm_hash_alloc(sz);
+		rcu_assign_pointer(htab->table, xfrm_hash_alloc(sz));
 		if (!htab->table)
 			goto out_bydst;
 		htab->hmask = hmask;
@@ -4269,7 +4269,7 @@ out_bydst:
 		struct xfrm_policy_hash *htab;
 
 		htab = &net->xfrm.policy_bydst[dir];
-		xfrm_hash_free(htab->table, sz);
+		xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz);
 	}
 	xfrm_hash_free(net->xfrm.policy_byidx, sz);
 out_byidx:
@@ -4295,8 +4295,8 @@ static void xfrm_policy_fini(struct net *net)
 
 		htab = &net->xfrm.policy_bydst[dir];
 		sz = (htab->hmask + 1) * sizeof(struct hlist_head);
-		WARN_ON(!hlist_empty(htab->table));
-		xfrm_hash_free(htab->table, sz);
+		WARN_ON(!hlist_empty(rcu_dereference_protected(htab->table, true)));
+		xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz);
 	}
 
 	sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head);
-- 
cgit v1.2.3


From 2da6901866e7137f4e1a51a5f0bd1fbd0848a4eb Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:41 +0100
Subject: xfrm: policy: silence sparse warning in xfrm_policy_unregister_afinfo

xfrm_policy_afinfo is __rcu, use rcu_access_pointer to silence:

net/xfrm/xfrm_policy.c:4152:43: error: incompatible types in comparison expression (different address spaces):
net/xfrm/xfrm_policy.c:4152:43:    struct xfrm_policy_afinfo const [noderef] __rcu *
net/xfrm/xfrm_policy.c:4152:43:    struct xfrm_policy_afinfo const *

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 49de5a6f4b85..66ac93e65264 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4156,7 +4156,7 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) {
-		if (xfrm_policy_afinfo[i] != afinfo)
+		if (rcu_access_pointer(xfrm_policy_afinfo[i]) != afinfo)
 			continue;
 		RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL);
 		break;
-- 
cgit v1.2.3


From 103b4f5b4007cb484f40b1c8095a7e0526e5aff6 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:42 +0100
Subject: xfrm: add rcu_access_pointer to silence sparse warning for
 xfrm_input_afinfo

xfrm_input_afinfo is __rcu, we should use rcu_access_pointer to avoid
a sparse warning:
net/xfrm/xfrm_input.c:78:21: error: incompatible types in comparison expression (different address spaces):
net/xfrm/xfrm_input.c:78:21:    struct xfrm_input_afinfo const [noderef] __rcu *
net/xfrm/xfrm_input.c:78:21:    struct xfrm_input_afinfo const *

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_input.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 4ed346e682c7..dc1312ed5a09 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -75,7 +75,10 @@ int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo)
 
 	spin_lock_bh(&xfrm_input_afinfo_lock);
 	if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) {
-		if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo))
+		const struct xfrm_input_afinfo *cur;
+
+		cur = rcu_access_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family]);
+		if (unlikely(cur != afinfo))
 			err = -EINVAL;
 		else
 			RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL);
-- 
cgit v1.2.3


From d87f8bc47fbf012a7f115e311d0603d97e47c34c Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Mar 2026 11:32:43 +0100
Subject: xfrm: avoid RCU warnings around the per-netns netlink socket

net->xfrm.nlsk is used in 2 types of contexts:
 - fully under RCU, with rcu_read_lock + rcu_dereference and a NULL check
 - in the netlink handlers, with requests coming from a userspace socket

In the 2nd case, net->xfrm.nlsk is guaranteed to stay non-NULL and the
object is alive, since we can't enter the netns destruction path while
the user socket holds a reference on the netns.

After adding the __rcu annotation to netns_xfrm.nlsk (which silences
sparse warnings in the RCU users and __net_init code), we need to tell
sparse that the 2nd case is safe. Add a helper for that.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h |  2 +-
 net/xfrm/xfrm_user.c     | 25 +++++++++++++++++--------
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 23dd647fe024..b73983a17e08 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -59,7 +59,7 @@ struct netns_xfrm {
 	struct list_head	inexact_bins;
 
 
-	struct sock		*nlsk;
+	struct sock		__rcu *nlsk;
 	struct sock		*nlsk_stash;
 
 	u32			sysctl_aevent_etime;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 4dd8341225bc..1656b487f833 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -35,6 +35,15 @@
 #endif
 #include <linux/unaligned.h>
 
+static struct sock *xfrm_net_nlsk(const struct net *net, const struct sk_buff *skb)
+{
+	/* get the source of this request, see netlink_unicast_kernel */
+	const struct sock *sk = NETLINK_CB(skb).sk;
+
+	/* sk is refcounted, the netns stays alive and nlsk with it */
+	return rcu_dereference_protected(net->xfrm.nlsk, sk->sk_net_refcnt);
+}
+
 static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type,
 			  struct netlink_ext_ack *extack)
 {
@@ -1727,7 +1736,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = build_spdinfo(r_skb, net, sportid, seq, *flags);
 	BUG_ON(err < 0);
 
-	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
+	return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid);
 }
 
 static inline unsigned int xfrm_sadinfo_msgsize(void)
@@ -1787,7 +1796,7 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = build_sadinfo(r_skb, net, sportid, seq, *flags);
 	BUG_ON(err < 0);
 
-	return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid);
+	return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, sportid);
 }
 
 static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1807,7 +1816,7 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (IS_ERR(resp_skb)) {
 		err = PTR_ERR(resp_skb);
 	} else {
-		err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
+		err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid);
 	}
 	xfrm_state_put(x);
 out_noput:
@@ -1898,7 +1907,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
+	err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb, NETLINK_CB(skb).portid);
 
 out:
 	xfrm_state_put(x);
@@ -2543,7 +2552,7 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh,
 	r_up->out = net->xfrm.policy_default[XFRM_POLICY_OUT];
 	nlmsg_end(r_skb, r_nlh);
 
-	return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid);
+	return nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, portid);
 }
 
 static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2609,7 +2618,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 		if (IS_ERR(resp_skb)) {
 			err = PTR_ERR(resp_skb);
 		} else {
-			err = nlmsg_unicast(net->xfrm.nlsk, resp_skb,
+			err = nlmsg_unicast(xfrm_net_nlsk(net, skb), resp_skb,
 					    NETLINK_CB(skb).portid);
 		}
 	} else {
@@ -2782,7 +2791,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = build_aevent(r_skb, x, &c);
 	BUG_ON(err < 0);
 
-	err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid);
+	err = nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, NETLINK_CB(skb).portid);
 	spin_unlock_bh(&x->lock);
 	xfrm_state_put(x);
 	return err;
@@ -3486,7 +3495,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			goto err;
 		}
 
-		err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		err = netlink_dump_start(xfrm_net_nlsk(net, skb), skb, nlh, &c);
 		goto err;
 	}
 
-- 
cgit v1.2.3


From fdbaa9d2b78e0da9e1aeb303bbdc3adfe6d8e749 Mon Sep 17 00:00:00 2001
From: Benno Lossin <lossin@kernel.org>
Date: Wed, 11 Mar 2026 11:50:49 +0100
Subject: rust: pin-init: replace shadowed return token by `unsafe`-to-create
 token

We use a unit struct `__InitOk` in the closure generated by the
initializer macros as the return value. We shadow it by creating a
struct with the same name again inside of the closure, preventing early
returns of `Ok` in the initializer (before all fields have been
initialized).

In the face of Type Alias Impl Trait (TAIT) and the next trait solver,
this solution no longer works [1]. The shadowed struct can be named
through type inference. In addition, there is an RFC proposing to add
the feature of path inference to Rust, which would similarly allow [2].

Thus remove the shadowed token and replace it with an `unsafe` to create
token.

The reason we initially used the shadowing solution was because an
alternative solution used a builder pattern. Gary writes [3]:

    In the early builder-pattern based InitOk, having a single InitOk
    type for token is unsound because one can launder an InitOk token
    used for one place to another initializer. I used a branded lifetime
    solution, and then you figured out that using a shadowed type would
    work better because nobody could construct it at all.

The laundering issue does not apply to the approach we ended up with
today.

With this change, the example by Tim Chirananthavat in [1] no longer
compiles and results in this error:

    error: cannot construct `pin_init::__internal::InitOk` with struct literal syntax due to private fields
      --> src/main.rs:26:17
       |
    26 |                 InferredType {}
       |                 ^^^^^^^^^^^^
       |
       = note: private field `0` that was not provided
    help: you might have meant to use the `new` associated function
       |
    26 -                 InferredType {}
    26 +                 InferredType::new()
       |

Applying the suggestion of using the `::new()` function, results in
another expected error:

    error[E0133]: call to unsafe function `pin_init::__internal::InitOk::new` is unsafe and requires unsafe block
      --> src/main.rs:26:17
       |
    26 |                 InferredType::new()
       |                 ^^^^^^^^^^^^^^^^^^^ call to unsafe function
       |
       = note: consult the function's documentation for information on how to avoid undefined behavior

Reported-by: Tim Chirananthavat <theemathas@gmail.com>
Link: https://github.com/rust-lang/rust/issues/153535 [1]
Link: https://github.com/rust-lang/rfcs/pull/3444#issuecomment-4016145373 [2]
Link: https://github.com/rust-lang/rust/issues/153535#issuecomment-4017620804 [3]
Fixes: fc6c6baa1f40 ("rust: init: add initialization macros")
Cc: stable@vger.kernel.org
Signed-off-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260311105056.1425041-1-lossin@kernel.org
[ Added period as mentioned. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/pin-init/internal/src/init.rs | 22 +++++++---------------
 rust/pin-init/src/__internal.rs    | 28 ++++++++++++++++++++++++----
 2 files changed, 31 insertions(+), 19 deletions(-)

diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs
index 738f62c8105c..2fe918f4d82a 100644
--- a/rust/pin-init/internal/src/init.rs
+++ b/rust/pin-init/internal/src/init.rs
@@ -148,11 +148,6 @@ pub(crate) fn expand(
     let init_fields = init_fields(&fields, pinned, &data, &slot);
     let field_check = make_field_check(&fields, init_kind, &path);
     Ok(quote! {{
-        // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return
-        // type and shadow it later when we insert the arbitrary user code. That way there will be
-        // no possibility of returning without `unsafe`.
-        struct __InitOk;
-
         // Get the data about fields from the supplied type.
         // SAFETY: TODO
         let #data = unsafe {
@@ -162,18 +157,15 @@ pub(crate) fn expand(
             #path::#get_data()
         };
         // Ensure that `#data` really is of type `#data` and help with type inference:
-        let init = ::pin_init::__internal::#data_trait::make_closure::<_, __InitOk, #error>(
+        let init = ::pin_init::__internal::#data_trait::make_closure::<_, #error>(
             #data,
             move |slot| {
-                {
-                    // Shadow the structure so it cannot be used to return early.
-                    struct __InitOk;
-                    #zeroable_check
-                    #this
-                    #init_fields
-                    #field_check
-                }
-                Ok(__InitOk)
+                #zeroable_check
+                #this
+                #init_fields
+                #field_check
+                // SAFETY: we are the `init!` macro that is allowed to call this.
+                Ok(unsafe { ::pin_init::__internal::InitOk::new() })
             }
         );
         let init = move |slot| -> ::core::result::Result<(), #error> {
diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs
index 90f18e9a2912..90adbdc1893b 100644
--- a/rust/pin-init/src/__internal.rs
+++ b/rust/pin-init/src/__internal.rs
@@ -46,6 +46,24 @@ where
     }
 }
 
+/// Token type to signify successful initialization.
+///
+/// Can only be constructed via the unsafe [`Self::new`] function. The initializer macros use this
+/// token type to prevent returning `Ok` from an initializer without initializing all fields.
+pub struct InitOk(());
+
+impl InitOk {
+    /// Creates a new token.
+    ///
+    /// # Safety
+    ///
+    /// This function may only be called from the `init!` macro in `../internal/src/init.rs`.
+    #[inline(always)]
+    pub unsafe fn new() -> Self {
+        Self(())
+    }
+}
+
 /// This trait is only implemented via the `#[pin_data]` proc-macro. It is used to facilitate
 /// the pin projections within the initializers.
 ///
@@ -68,9 +86,10 @@ pub unsafe trait PinData: Copy {
     type Datee: ?Sized + HasPinData;
 
     /// Type inference helper function.
-    fn make_closure<F, O, E>(self, f: F) -> F
+    #[inline(always)]
+    fn make_closure<F, E>(self, f: F) -> F
     where
-        F: FnOnce(*mut Self::Datee) -> Result<O, E>,
+        F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>,
     {
         f
     }
@@ -98,9 +117,10 @@ pub unsafe trait InitData: Copy {
     type Datee: ?Sized + HasInitData;
 
     /// Type inference helper function.
-    fn make_closure<F, O, E>(self, f: F) -> F
+    #[inline(always)]
+    fn make_closure<F, E>(self, f: F) -> F
     where
-        F: FnOnce(*mut Self::Datee) -> Result<O, E>,
+        F: FnOnce(*mut Self::Datee) -> Result<InitOk, E>,
     {
         f
     }
-- 
cgit v1.2.3


From 487f9b3dc6e507a982f1b984aa6bfbd9dc4b0567 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Wed, 11 Mar 2026 21:19:34 -0700
Subject: rust: cpufreq: suppress clippy::double_parens in Policy doctest

The kernel fmt! proc macro wraps each format argument as &(arg). Passing a
tuple such as (a, b) produces &((a, b)) after expansion. Clippy flags that
as double_parens, but it is a false positive fixed in Clippy 1.92 [1] [2].

Suppress the warning on the affected doctest function with a reason
attribute so it can be removed once the minimum toolchain moves past 1.92.

[ We may end up deciding to support per-version Clippy lints, in which
  case we will need [3].

  In the future, if [4] gets fixed, we may be able to use
  `Delimiter::None` as Gary suggested in [5].

  Link: https://lore.kernel.org/rust-for-linux/20260307170929.153892-1-ojeda@kernel.org/ [3]
  Link: https://github.com/rust-lang/rust/issues/67062 [4]
  Link: https://lore.kernel.org/rust-for-linux/DGUA5GY2DGYN.3PG0FKLG7GFN1@garyguo.net/ [5]

    - Miguel ]

Link: https://github.com/rust-lang/rust-clippy/issues/15852 [1]
Link: https://github.com/rust-lang/rust-clippy/pull/15939 [2]
Suggested-by: Gary Guo <gary@garyguo.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://patch.msgid.link/20260312041934.362840-2-jhubbard@nvidia.com
[ Reworded to replace GitHub-like short link with full URLs in Link tags.
  Reworded reason string to match the style of a couple others we have
  elsewhere. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/cpufreq.rs | 1 +
 1 file changed, 1 insertion(+)

diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 76faa1ac8501..f5adee48d40c 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -401,6 +401,7 @@ impl TableBuilder {
 /// ```
 /// use kernel::cpufreq::{DEFAULT_TRANSITION_LATENCY_NS, Policy};
 ///
+/// #[allow(clippy::double_parens, reason = "False positive before 1.92.0")]
 /// fn update_policy(policy: &mut Policy) {
 ///     policy
 ///         .set_dvfs_possible_from_any_cpu(true)
-- 
cgit v1.2.3


From 14de1552a4e3fece78bb20314887e70888c9d448 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 11 Mar 2026 16:14:55 -0700
Subject: include/linux/local_lock_internal.h: Make this header file again
 compatible with sparse

There are two versions of the __this_cpu_local_lock() definitions in
include/linux/local_lock_internal.h: one version that relies on the
Clang overloading functionality and another version that does not.
Select the latter version when using sparse. This patch fixes the
following errors reported by sparse:

   include/linux/local_lock_internal.h:331:40: sparse: sparse: multiple definitions for function '__this_cpu_local_lock'
   include/linux/local_lock_internal.h:325:37: sparse:  the previous one is here

Closes: https://lore.kernel.org/oe-kbuild-all/202603062334.wgI5htP0-lkp@intel.com/
Fixes: d3febf16dee2 ("locking/local_lock: Support Clang's context analysis")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Marco Elver <elver@google.com>
Link: https://patch.msgid.link/20260311231455.1961413-1-bvanassche@acm.org
---
 include/linux/local_lock_internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index eff711bf973f..234be7f12c15 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -315,7 +315,7 @@ do {								\
 
 #endif /* CONFIG_PREEMPT_RT */
 
-#if defined(WARN_CONTEXT_ANALYSIS)
+#if defined(WARN_CONTEXT_ANALYSIS) && !defined(__CHECKER__)
 /*
  * Because the compiler only knows about the base per-CPU variable, use this
  * helper function to make the compiler think we lock/unlock the @base variable,
-- 
cgit v1.2.3


From 8d5fae6011260de209aaf231120e8146b14bc8e0 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 10 Mar 2026 03:13:16 -0700
Subject: perf/x86: Move event pointer setup earlier in x86_pmu_enable()

A production AMD EPYC system crashed with a NULL pointer dereference
in the PMU NMI handler:

  BUG: kernel NULL pointer dereference, address: 0000000000000198
  RIP: x86_perf_event_update+0xc/0xa0
  Call Trace:
   <NMI>
   amd_pmu_v2_handle_irq+0x1a6/0x390
   perf_event_nmi_handler+0x24/0x40

The faulting instruction is `cmpq $0x0, 0x198(%rdi)` with RDI=0,
corresponding to the `if (unlikely(!hwc->event_base))` check in
x86_perf_event_update() where hwc = &event->hw and event is NULL.

drgn inspection of the vmcore on CPU 106 showed a mismatch between
cpuc->active_mask and cpuc->events[]:

  active_mask: 0x1e (bits 1, 2, 3, 4)
  events[1]:   0xff1100136cbd4f38  (valid)
  events[2]:   0x0                 (NULL, but active_mask bit 2 set)
  events[3]:   0xff1100076fd2cf38  (valid)
  events[4]:   0xff1100079e990a90  (valid)

The event that should occupy events[2] was found in event_list[2]
with hw.idx=2 and hw.state=0x0, confirming x86_pmu_start() had run
(which clears hw.state and sets active_mask) but events[2] was
never populated.

Another event (event_list[0]) had hw.state=0x7 (STOPPED|UPTODATE|ARCH),
showing it was stopped when the PMU rescheduled events, confirming the
throttle-then-reschedule sequence occurred.

The root cause is commit 7e772a93eb61 ("perf/x86: Fix NULL event access
and potential PEBS record loss") which moved the cpuc->events[idx]
assignment out of x86_pmu_start() and into step 2 of x86_pmu_enable(),
after the PERF_HES_ARCH check. This broke any path that calls
pmu->start() without going through x86_pmu_enable() -- specifically
the unthrottle path:

  perf_adjust_freq_unthr_events()
    -> perf_event_unthrottle_group()
      -> perf_event_unthrottle()
        -> event->pmu->start(event, 0)
          -> x86_pmu_start()     // sets active_mask but not events[]

The race sequence is:

  1. A group of perf events overflows, triggering group throttle via
     perf_event_throttle_group(). All events are stopped: active_mask
     bits cleared, events[] preserved (x86_pmu_stop no longer clears
     events[] after commit 7e772a93eb61).

  2. While still throttled (PERF_HES_STOPPED), x86_pmu_enable() runs
     due to other scheduling activity. Stopped events that need to
     move counters get PERF_HES_ARCH set and events[old_idx] cleared.
     In step 2 of x86_pmu_enable(), PERF_HES_ARCH causes these events
     to be skipped -- events[new_idx] is never set.

  3. The timer tick unthrottles the group via pmu->start(). Since
     commit 7e772a93eb61 removed the events[] assignment from
     x86_pmu_start(), active_mask[new_idx] is set but events[new_idx]
     remains NULL.

  4. A PMC overflow NMI fires. The handler iterates active counters,
     finds active_mask[2] set, reads events[2] which is NULL, and
     crashes dereferencing it.

Move the cpuc->events[hwc->idx] assignment in x86_pmu_enable() to
before the PERF_HES_ARCH check, so that events[] is populated even
for events that are not immediately started. This ensures the
unthrottle path via pmu->start() always finds a valid event pointer.

Fixes: 7e772a93eb61 ("perf/x86: Fix NULL event access and potential PEBS record loss")
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260310-perf-v2-1-4a3156fce43c@debian.org
---
 arch/x86/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 03ce1bc7ef2e..54b4c315d927 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1372,6 +1372,8 @@ static void x86_pmu_enable(struct pmu *pmu)
 			else if (i < n_running)
 				continue;
 
+			cpuc->events[hwc->idx] = event;
+
 			if (hwc->state & PERF_HES_ARCH)
 				continue;
 
@@ -1379,7 +1381,6 @@ static void x86_pmu_enable(struct pmu *pmu)
 			 * if cpuc->enabled = 0, then no wrmsr as
 			 * per x86_pmu_enable_event()
 			 */
-			cpuc->events[hwc->idx] = event;
 			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
-- 
cgit v1.2.3


From f1cac6ac62d28a9a57b17f51ac5795bf250c12d3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Mar 2026 21:29:14 +0100
Subject: x86/perf: Make sure to program the counter value for stopped events
 on migration

Both Mi Dapeng and Ian Rogers noted that not everything that sets HES_STOPPED
is required to EF_UPDATE. Specifically the 'step 1' loop of rescheduling
explicitly does EF_UPDATE to ensure the counter value is read.

However, then 'step 2' simply leaves the new counter uninitialized when
HES_STOPPED, even though, as noted above, the thing that stopped them might not
be aware it needs to EF_RELOAD -- since it didn't EF_UPDATE on stop.

One such location that is affected is throttling, throttle does pmu->stop(, 0);
and unthrottle does pmu->start(, 0); possibly restarting an uninitialized counter.

Fixes: a4eaf7f14675 ("perf: Rework the PMU methods")
Reported-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Reported-by: Ian Rogers <irogers@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20260311204035.GX606826@noisy.programming.kicks-ass.net
---
 arch/x86/events/core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 54b4c315d927..810ab21ffd99 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1374,8 +1374,10 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 			cpuc->events[hwc->idx] = event;
 
-			if (hwc->state & PERF_HES_ARCH)
+			if (hwc->state & PERF_HES_ARCH) {
+				static_call(x86_pmu_set_period)(event);
 				continue;
+			}
 
 			/*
 			 * if cpuc->enabled = 0, then no wrmsr as
-- 
cgit v1.2.3


From 4b9ce671960627b2505b3f64742544ae9801df97 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 9 Mar 2026 13:55:46 +0100
Subject: perf: Make sure to use pmu_ctx->pmu for groups

Oliver reported that x86_pmu_del() ended up doing an out-of-bound memory access
when group_sched_in() fails and needs to roll back.

This *should* be handled by the transaction callbacks, but he found that when
the group leader is a software event, the transaction handlers of the wrong PMU
are used. Despite the move_group case in perf_event_open() and group_sched_in()
using pmu_ctx->pmu.

Turns out, inherit uses event->pmu to clone the events, effectively undoing the
move_group case for all inherited contexts. Fix this by also making inherit use
pmu_ctx->pmu, ensuring all inherited counters end up in the same pmu context.

Similarly, __perf_event_read() should use equally use pmu_ctx->pmu for the
group case.

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Reported-by: Oliver Rosenberg <olrose55@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://patch.msgid.link/20260309133713.GB606826@noisy.programming.kicks-ass.net
---
 kernel/events/core.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1f5699b339ec..89b40e439717 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4813,7 +4813,7 @@ static void __perf_event_read(void *info)
 	struct perf_event *sub, *event = data->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
-	struct pmu *pmu = event->pmu;
+	struct pmu *pmu;
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -4825,7 +4825,7 @@ static void __perf_event_read(void *info)
 	if (ctx->task && cpuctx->task_ctx != ctx)
 		return;
 
-	raw_spin_lock(&ctx->lock);
+	guard(raw_spinlock)(&ctx->lock);
 	ctx_time_update_event(ctx, event);
 
 	perf_event_update_time(event);
@@ -4833,25 +4833,22 @@ static void __perf_event_read(void *info)
 		perf_event_update_sibling_time(event);
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
-		goto unlock;
+		return;
 
 	if (!data->group) {
-		pmu->read(event);
+		perf_pmu_read(event);
 		data->ret = 0;
-		goto unlock;
+		return;
 	}
 
+	pmu = event->pmu_ctx->pmu;
 	pmu->start_txn(pmu, PERF_PMU_TXN_READ);
 
-	pmu->read(event);
-
+	perf_pmu_read(event);
 	for_each_sibling_event(sub, event)
 		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
-
-unlock:
-	raw_spin_unlock(&ctx->lock);
 }
 
 static inline u64 perf_event_count(struct perf_event *event, bool self)
@@ -14744,7 +14741,7 @@ inherit_event(struct perf_event *parent_event,
 	get_ctx(child_ctx);
 	child_event->ctx = child_ctx;
 
-	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
+	pmu_ctx = find_get_pmu_context(parent_event->pmu_ctx->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
 		return ERR_CAST(pmu_ctx);
-- 
cgit v1.2.3


From 1d07bbd7ea36ea0b8dfa8068dbe67eb3a32d9590 Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Sat, 28 Feb 2026 13:33:20 +0800
Subject: perf/x86/intel: Add missing branch counters constraint apply

When running the command:
'perf record -e "{instructions,instructions:p}" -j any,counter sleep 1',
a "shift-out-of-bounds" warning is reported on CWF.

  UBSAN: shift-out-of-bounds in /kbuild/src/consumer/arch/x86/events/intel/lbr.c:970:15
  shift exponent 64 is too large for 64-bit type 'long long unsigned int'
  ......
  intel_pmu_lbr_counters_reorder.isra.0.cold+0x2a/0xa7
  intel_pmu_lbr_save_brstack+0xc0/0x4c0
  setup_arch_pebs_sample_data+0x114b/0x2400

The warning occurs because the second "instructions:p" event, which
involves branch counters sampling, is incorrectly programmed to fixed
counter 0 instead of the general-purpose (GP) counters 0-3 that support
branch counters sampling. Currently only GP counters 0-3 support branch
counters sampling on CWF, any event involving branch counters sampling
should be programed on GP counters 0-3. Since the counter index of fixed
counter 0 is 32, it leads to the "src" value in below code is right
shifted 64 bits and trigger the "shift-out-of-bounds" warning.

cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK;

The root cause is the loss of the branch counters constraint for the
new event in the branch counters sampling event group. Since it isn't
yet part of the sibling list. This results in the second
"instructions:p" event being programmed on fixed counter 0 incorrectly
instead of the appropriate GP counters 0-3.

To address this, we apply the missing branch counters constraint for
the last event in the group. Additionally, we introduce a new function,
`intel_set_branch_counter_constr()`, to apply the branch counters
constraint and avoid code duplication.

Fixes: 33744916196b ("perf/x86/intel: Support branch counters logging")
Reported-by: Xudong Hao <xudong.hao@intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260228053320.140406-2-dapeng1.mi@linux.intel.com
Cc: stable@vger.kernel.org
---
 arch/x86/events/intel/core.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cf3a4fe06ff2..36c68210d4d2 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4628,6 +4628,19 @@ static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event,
 		event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64);
 }
 
+static inline int intel_set_branch_counter_constr(struct perf_event *event,
+						  int *num)
+{
+	if (branch_sample_call_stack(event))
+		return -EINVAL;
+	if (branch_sample_counters(event)) {
+		(*num)++;
+		event->hw.dyn_constraint &= x86_pmu.lbr_counters;
+	}
+
+	return 0;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -4698,21 +4711,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 * group, which requires the extra space to store the counters.
 		 */
 		leader = event->group_leader;
-		if (branch_sample_call_stack(leader))
+		if (intel_set_branch_counter_constr(leader, &num))
 			return -EINVAL;
-		if (branch_sample_counters(leader)) {
-			num++;
-			leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
-		}
 		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
 
 		for_each_sibling_event(sibling, leader) {
-			if (branch_sample_call_stack(sibling))
+			if (intel_set_branch_counter_constr(sibling, &num))
+				return -EINVAL;
+		}
+
+		/* event isn't installed as a sibling yet. */
+		if (event != leader) {
+			if (intel_set_branch_counter_constr(event, &num))
 				return -EINVAL;
-			if (branch_sample_counters(sibling)) {
-				num++;
-				sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
-			}
 		}
 
 		if (num > fls(x86_pmu.lbr_counters))
-- 
cgit v1.2.3


From e7fcc54524f04e42641de99028edd9c69dc19f8c Mon Sep 17 00:00:00 2001
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
Date: Wed, 11 Mar 2026 15:52:00 +0800
Subject: perf/x86/intel: Fix OMR snoop information parsing issues

When omr_source is 0x2, the omr_snoop (bit[6]) and omr_promoted (bit[7])
fields are combined to represent the snoop information. However, the
omr_promoted field was not left-shifted by 1 bit, resulting in incorrect
snoop information.

Besides, the snoop information parsing is not accurate for some OMR
sources, like the snoop information should be SNOOP_NONE for these memory
access (omr_source >= 7) instead of SNOOP_HIT.

Fix these issues.

Closes: https://lore.kernel.org/all/CAP-5=fW4zLWFw1v38zCzB9-cseNSTTCtup=p2SDxZq7dPayVww@mail.gmail.com/
Fixes: d2bdcde9626c ("perf/x86/intel: Add support for PEBS memory auxiliary info field in DMR")
Reported-by: Ian Rogers <irogers@google.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://patch.msgid.link/20260311075201.2951073-1-dapeng1.mi@linux.intel.com
---
 arch/x86/events/intel/ds.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 5027afc97b65..7f0d515c07c5 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -345,12 +345,12 @@ static u64 parse_omr_data_source(u8 dse)
 	if (omr.omr_remote)
 		val |= REM;
 
-	val |= omr.omr_hitm ? P(SNOOP, HITM) : P(SNOOP, HIT);
-
 	if (omr.omr_source == 0x2) {
-		u8 snoop = omr.omr_snoop | omr.omr_promoted;
+		u8 snoop = omr.omr_snoop | (omr.omr_promoted << 1);
 
-		if (snoop == 0x0)
+		if (omr.omr_hitm)
+			val |= P(SNOOP, HITM);
+		else if (snoop == 0x0)
 			val |= P(SNOOP, NA);
 		else if (snoop == 0x1)
 			val |= P(SNOOP, MISS);
@@ -359,7 +359,10 @@ static u64 parse_omr_data_source(u8 dse)
 		else if (snoop == 0x3)
 			val |= P(SNOOP, NONE);
 	} else if (omr.omr_source > 0x2 && omr.omr_source < 0x7) {
+		val |= omr.omr_hitm ? P(SNOOP, HITM) : P(SNOOP, HIT);
 		val |= omr.omr_snoop ? P(SNOOPX, FWD) : 0;
+	} else {
+		val |= P(SNOOP, NONE);
 	}
 
 	return val;
-- 
cgit v1.2.3


From 70031e70ca15ede6a39db4d978e53a6cc720d454 Mon Sep 17 00:00:00 2001
From: Adrian Freund <adrian@freund.io>
Date: Wed, 11 Mar 2026 20:19:33 +0100
Subject: HID: logitech-hidpp: Enable MX Master 4 over bluetooth

The Logitech MX Master 4 can be connected over bluetooth or through a
Logitech Bolt receiver. This change adds support for non-standard HID
features, such as high resolution scrolling when the mouse is connected
over bluetooth.
Because no Logitech Bolt receiver driver exists yet those features
won't be available when the mouse is connected through the receiver.

Signed-off-by: Adrian Freund <adrian@freund.io>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-logitech-hidpp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 02d83c3bd73d..c3d53250a760 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4668,6 +4668,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb038) },
 	{ /* Slim Solar+ K980 Keyboard over Bluetooth */
 	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb391) },
+	{ /* MX Master 4 mouse over Bluetooth */
+	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb042) },
 	{}
 };
 
-- 
cgit v1.2.3


From 1965445e13c09b79932ca8154977b4408cb9610c Mon Sep 17 00:00:00 2001
From: Aditya Garg <gargaditya08@live.com>
Date: Tue, 17 Feb 2026 02:54:46 +0530
Subject: HID: appletb-kbd: add .resume method in PM

Upon resuming from suspend, the Touch Bar driver was missing a resume
method in order to restore the original mode the Touch Bar was on before
suspending. It is the same as the reset_resume method.

[jkosina@suse.com: rebased on top of the pm_ptr() conversion]
Cc: stable@vger.kernel.org
Signed-off-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appletb-kbd.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c
index a1db3b3d0667..0fdc0968b9ef 100644
--- a/drivers/hid/hid-appletb-kbd.c
+++ b/drivers/hid/hid-appletb-kbd.c
@@ -476,7 +476,7 @@ static int appletb_kbd_suspend(struct hid_device *hdev, pm_message_t msg)
 	return 0;
 }
 
-static int appletb_kbd_reset_resume(struct hid_device *hdev)
+static int appletb_kbd_resume(struct hid_device *hdev)
 {
 	struct appletb_kbd *kbd = hid_get_drvdata(hdev);
 
@@ -500,7 +500,8 @@ static struct hid_driver appletb_kbd_hid_driver = {
 	.event = appletb_kbd_hid_event,
 	.input_configured = appletb_kbd_input_configured,
 	.suspend = pm_ptr(appletb_kbd_suspend),
-	.reset_resume = pm_ptr(appletb_kbd_reset_resume),
+	.resume = pm_ptr(appletb_kbd_resume),
+	.reset_resume = pm_ptr(appletb_kbd_resume),
 	.driver.dev_groups = appletb_kbd_groups,
 };
 module_hid_driver(appletb_kbd_hid_driver);
-- 
cgit v1.2.3


From b22c526569e6af84008b674e66378e771bfbdd94 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Mon, 9 Feb 2026 23:37:01 -0600
Subject: pmdomain: mediatek: Fix power domain count

The wrong value of the number of domains is wrong which leads to
failures when trying to enumerate nested power domains.

 PM: genpd_xlate_onecell: invalid domain index 0
 PM: genpd_xlate_onecell: invalid domain index 1
 PM: genpd_xlate_onecell: invalid domain index 3
 PM: genpd_xlate_onecell: invalid domain index 4
 PM: genpd_xlate_onecell: invalid domain index 5
 PM: genpd_xlate_onecell: invalid domain index 13
 PM: genpd_xlate_onecell: invalid domain index 14

Attempts to use these power domains fail, so fix this by
using the correct value of calculated power domains.

Signed-off-by: Adam Ford <aford173@gmail.com>
Fixes: 88914db077b6 ("pmdomain: mediatek: Add support for Hardware Voter power domains")
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/mediatek/mtk-pm-domains.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pmdomain/mediatek/mtk-pm-domains.c b/drivers/pmdomain/mediatek/mtk-pm-domains.c
index f64f24d520dd..e2800aa1bc59 100644
--- a/drivers/pmdomain/mediatek/mtk-pm-domains.c
+++ b/drivers/pmdomain/mediatek/mtk-pm-domains.c
@@ -1203,7 +1203,7 @@ static int scpsys_probe(struct platform_device *pdev)
 	scpsys->soc_data = soc;
 
 	scpsys->pd_data.domains = scpsys->domains;
-	scpsys->pd_data.num_domains = soc->num_domains;
+	scpsys->pd_data.num_domains = num_domains;
 
 	parent = dev->parent;
 	if (!parent) {
-- 
cgit v1.2.3


From 592c61f3bfceaa29f8275696bd67c3dfad7ef72e Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Thu, 12 Mar 2026 12:10:14 +0100
Subject: rust: kbuild: allow `unused_features`

Starting with the upcoming Rust 1.96.0 (to be released 2026-05-28),
`rustc` introduces the new lint `unused_features` [1], which warns [2]:

    warning: feature `used_with_arg` is declared but not used
     --> <crate attribute>:1:93
      |
    1 | #![feature(asm_const,asm_goto,arbitrary_self_types,lint_reasons,offset_of_nested,raw_ref_op,used_with_arg)]
      |                                                                                             ^^^^^^^^^^^^^
      |
      = note: `#[warn(unused_features)]` (part of `#[warn(unused)]`) on by default

The original goal of using `-Zcrate-attr` automatically was that there
is a consistent set of features enabled and managed globally for all
Rust kernel code (modulo exceptions like the `rust/` crated).

While we could require crates to enable features manually (even if we
still keep the `-Zallow-features=` list, i.e. removing the `-Zcrate-attr`
list), it is not really worth making all developers worry about it just
for a new lint.

The features are expected to eventually become stable anyway (most already
did), and thus having to remove features in every file that may use them
is not worth it either.

Thus just allow the new lint globally.

The lint actually existed for a long time, which is why `rustc` does
not complain about an unknown lint in the stable versions we support,
but it was "disabled" years ago [3], and now it was made to work again.

For extra context, the new implementation of the lint has already been
improved to avoid linting about features that became stable thanks to
Benno's report and the ensuing discussion [4] [5], but while that helps,
it is still the case that we may have features enabled that are not used
for one reason or another in a particular crate.

Cc: stable@vger.kernel.org # Needed in 6.12.y and later (Rust is pinned in older LTSs).
Link: https://github.com/rust-lang/rust/pull/152164 [1]
Link: https://github.com/Rust-for-Linux/pin-init/pull/114 [2]
Link: https://github.com/rust-lang/rust/issues/44232 [3]
Link: https://github.com/rust-lang/rust/issues/153523 [4]
Link: https://github.com/rust-lang/rust/pull/153610 [5]
Reviewed-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260312111014.74198-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Makefile b/Makefile
index 73a39592f112..587345f16c97 100644
--- a/Makefile
+++ b/Makefile
@@ -476,6 +476,7 @@ KBUILD_USERLDFLAGS := $(USERLDFLAGS)
 export rust_common_flags := --edition=2021 \
 			    -Zbinary_dep_depinfo=y \
 			    -Astable_features \
+			    -Aunused_features \
 			    -Dnon_ascii_idents \
 			    -Dunsafe_op_in_unsafe_fn \
 			    -Wmissing_docs \
-- 
cgit v1.2.3


From a424a34b8faddf97b5af41689087e7a230f79ba7 Mon Sep 17 00:00:00 2001
From: Raul E Rangel <rrangel@chromium.org>
Date: Mon, 9 Feb 2026 13:58:18 -0700
Subject: serial: 8250: Fix TX deadlock when using DMA

`dmaengine_terminate_async` does not guarantee that the
`__dma_tx_complete` callback will run. The callback is currently the
only place where `dma->tx_running` gets cleared. If the transaction is
canceled and the callback never runs, then `dma->tx_running` will never
get cleared and we will never schedule new TX DMA transactions again.

This change makes it so we clear `dma->tx_running` after we terminate
the DMA transaction. This is "safe" because `serial8250_tx_dma_flush`
is holding the UART port lock. The first thing the callback does is also
grab the UART port lock, so access to `dma->tx_running` is serialized.

Fixes: 9e512eaaf8f4 ("serial: 8250: Fix fifo underflow on flush")
Cc: stable <stable@kernel.org>
Signed-off-by: Raul E Rangel <rrangel@google.com>
Link: https://patch.msgid.link/20260209135815.1.I16366ecb0f62f3c96fe3dd5763fcf6f3c2b4d8cd@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dma.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index bdd26c9f34bd..3b6452e759d5 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -162,7 +162,22 @@ void serial8250_tx_dma_flush(struct uart_8250_port *p)
 	 */
 	dma->tx_size = 0;
 
+	/*
+	 * We can't use `dmaengine_terminate_sync` because `uart_flush_buffer` is
+	 * holding the uart port spinlock.
+	 */
 	dmaengine_terminate_async(dma->txchan);
+
+	/*
+	 * The callback might or might not run. If it doesn't run, we need to ensure
+	 * that `tx_running` is cleared so that we can schedule new transactions.
+	 * If it does run, then the zombie callback will clear `tx_running` again
+	 * and perform a no-op since `tx_size` was cleared above.
+	 *
+	 * In either case, we ASSUME the DMA transaction will terminate before we
+	 * issue a new `serial8250_tx_dma`.
+	 */
+	dma->tx_running = 0;
 }
 
 int serial8250_rx_dma(struct uart_8250_port *p)
-- 
cgit v1.2.3


From 24b98e8664e157aff0814a0f49895ee8223f382f Mon Sep 17 00:00:00 2001
From: Peng Zhang <zhangpeng.00@bytedance.com>
Date: Tue, 24 Feb 2026 13:16:39 +0100
Subject: serial: 8250: always disable IRQ during THRE test

commit 039d4926379b ("serial: 8250: Toggle IER bits on only after irq
has been set up") moved IRQ setup before the THRE test, in combination
with commit 205d300aea75 ("serial: 8250: change lock order in
serial8250_do_startup()") the interrupt handler can run during the
test and race with its IIR reads. This can produce wrong THRE test
results and cause spurious registration of the
serial8250_backup_timeout timer. Unconditionally disable the IRQ for
the short duration of the test and re-enable it afterwards to avoid
the race.

Fixes: 039d4926379b ("serial: 8250: Toggle IER bits on only after irq has been set up")
Depends-on: 205d300aea75 ("serial: 8250: change lock order in serial8250_do_startup()")
Cc: stable <stable@kernel.org>
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Alban Bedel <alban.bedel@lht.dlh.de>
Tested-by: Maximilian Lueer <maximilian.lueer@lht.dlh.de>
Link: https://patch.msgid.link/20260224121639.579404-1-alban.bedel@lht.dlh.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index cc94af2d578a..a743964c9d22 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2147,8 +2147,7 @@ static void serial8250_THRE_test(struct uart_port *port)
 	if (up->port.flags & UPF_NO_THRE_TEST)
 		return;
 
-	if (port->irqflags & IRQF_SHARED)
-		disable_irq_nosync(port->irq);
+	disable_irq(port->irq);
 
 	/*
 	 * Test for UARTs that do not reassert THRE when the transmitter is idle and the interrupt
@@ -2170,8 +2169,7 @@ static void serial8250_THRE_test(struct uart_port *port)
 		serial_port_out(port, UART_IER, 0);
 	}
 
-	if (port->irqflags & IRQF_SHARED)
-		enable_irq(port->irq);
+	enable_irq(port->irq);
 
 	/*
 	 * If the interrupt is not reasserted, or we otherwise don't trust the iir, setup a timer to
-- 
cgit v1.2.3


From d54801cd509515f674a5aac1d3ea1401d2a05863 Mon Sep 17 00:00:00 2001
From: Maciej Andrzejewski ICEYE <maciej.andrzejewski@m-works.net>
Date: Thu, 5 Mar 2026 13:37:51 +0100
Subject: serial: uartlite: fix PM runtime usage count underflow on probe

ulite_probe() calls pm_runtime_put_autosuspend() at the end of probe
without holding a corresponding PM runtime reference for non-console
ports.

During ulite_assign(), uart_add_one_port() triggers uart_configure_port()
which calls ulite_pm() via uart_change_pm(). For non-console ports, the
UART core performs a balanced get/put cycle:

  uart_change_pm(ON)  -> ulite_pm() -> pm_runtime_get_sync()        +1
  uart_change_pm(OFF) -> ulite_pm() -> pm_runtime_put_autosuspend() -1

This leaves no spare reference for the pm_runtime_put_autosuspend() at
the end of probe. The PM runtime core prevents the count from actually
going below zero, and instead triggers a
"Runtime PM usage count underflow!" warning.

For console ports the bug is masked: the UART core skips the
uart_change_pm(OFF) call, so the UART core's unbalanced get happens to
pair with probe's trailing put.

Add pm_runtime_get_noresume() before pm_runtime_enable() to take an
explicit probe-owned reference that the trailing
pm_runtime_put_autosuspend() can release. This ensures a correct usage
count regardless of whether the port is a console.

Fixes: 5bbe10a6942d ("tty: serial: uartlite: Add runtime pm support")
Cc: stable <stable@kernel.org>
Signed-off-by: Maciej Andrzejewski ICEYE <maciej.andrzejewski@m-works.net>
Link: https://patch.msgid.link/20260305123746.4152800-1-maciej.andrzejewski@m-works.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/uartlite.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index 39c1fd1ff9ce..6240c3d4dfd7 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -878,6 +878,7 @@ of_err:
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
 	ret = ulite_assign(&pdev->dev, id, res->start, irq, pdata);
-- 
cgit v1.2.3


From 455ce986fa356ff43a43c0d363ba95fa152f21d5 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 4 Feb 2026 15:43:20 +0800
Subject: serial: core: fix infinite loop in handle_tx() for PORT_UNKNOWN

uart_write_room() and uart_write() behave inconsistently when
xmit_buf is NULL (which happens for PORT_UNKNOWN ports that were
never properly initialized):

- uart_write_room() returns kfifo_avail() which can be > 0
- uart_write() checks xmit_buf and returns 0 if NULL

This inconsistency causes an infinite loop in drivers that rely on
tty_write_room() to determine if they can write:

  while (tty_write_room(tty) > 0) {
      written = tty->ops->write(...);
      // written is always 0, loop never exits
  }

For example, caif_serial's handle_tx() enters an infinite loop when
used with PORT_UNKNOWN serial ports, causing system hangs.

Fix by making uart_write_room() also check xmit_buf and return 0 if
it's NULL, consistent with uart_write().

Reproducer: https://gist.github.com/mrpre/d9a694cc0e19828ee3bc3b37983fde13

Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260204074327.226165-1-jiayuan.chen@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 487756947a96..89cebdd27841 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -643,7 +643,10 @@ static unsigned int uart_write_room(struct tty_struct *tty)
 	unsigned int ret;
 
 	port = uart_port_ref_lock(state, &flags);
-	ret = kfifo_avail(&state->port.xmit_fifo);
+	if (!state->port.xmit_buf)
+		ret = 0;
+	else
+		ret = kfifo_avail(&state->port.xmit_fifo);
 	uart_port_unlock_deref(port, flags);
 	return ret;
 }
-- 
cgit v1.2.3


From 9c0072bc33d349c83d223e64be30794e11938a6b Mon Sep 17 00:00:00 2001
From: "Martin Roukala (né Peres)" <martin.roukala@mupuf.org>
Date: Mon, 9 Mar 2026 15:53:10 +0200
Subject: serial: 8250_pci: add support for the AX99100
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is found in popular brands such as StarTech.com or Delock, and has
been a source of frustration to quite a few people, if I can trust
Amazon comments complaining about Linux support via the official
out-of-the-tree driver.

Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260309-8250_pci_ax99100-v1-1-3328bdfd8e94@mupuf.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_pci.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index aa1ab4da9ff1..6cfd1b2af5b7 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -137,6 +137,8 @@ struct serial_private {
 };
 
 #define PCI_DEVICE_ID_HPE_PCI_SERIAL	0x37e
+#define PCIE_VENDOR_ID_ASIX		0x125B
+#define PCIE_DEVICE_ID_AX99100		0x9100
 
 static const struct pci_device_id pci_use_msi[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9900,
@@ -149,6 +151,8 @@ static const struct pci_device_id pci_use_msi[] = {
 			 0xA000, 0x1000) },
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_HP_3PAR, PCI_DEVICE_ID_HPE_PCI_SERIAL,
 			 PCI_ANY_ID, PCI_ANY_ID) },
+	{ PCI_DEVICE_SUB(PCIE_VENDOR_ID_ASIX, PCIE_DEVICE_ID_AX99100,
+			 0xA000, 0x1000) },
 	{ }
 };
 
@@ -920,6 +924,7 @@ static int pci_netmos_init(struct pci_dev *dev)
 	case PCI_DEVICE_ID_NETMOS_9912:
 	case PCI_DEVICE_ID_NETMOS_9922:
 	case PCI_DEVICE_ID_NETMOS_9900:
+	case PCIE_DEVICE_ID_AX99100:
 		num_serial = pci_netmos_9900_numports(dev);
 		break;
 
@@ -2544,6 +2549,14 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.init		= pci_netmos_init,
 		.setup		= pci_netmos_9900_setup,
 	},
+	{
+		.vendor		= PCIE_VENDOR_ID_ASIX,
+		.device		= PCI_ANY_ID,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.init		= pci_netmos_init,
+		.setup		= pci_netmos_9900_setup,
+	},
 	/*
 	 * EndRun Technologies
 	*/
@@ -6065,6 +6078,10 @@ static const struct pci_device_id serial_pci_tbl[] = {
 		0xA000, 0x3002,
 		0, 0, pbn_NETMOS9900_2s_115200 },
 
+	{	PCIE_VENDOR_ID_ASIX, PCIE_DEVICE_ID_AX99100,
+		0xA000, 0x1000,
+		0, 0, pbn_b0_1_115200 },
+
 	/*
 	 * Best Connectivity and Rosewill PCI Multi I/O cards
 	 */
-- 
cgit v1.2.3


From 59a33d83bbe6d73d2071d7ae21590b29faed0503 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:43 +0200
Subject: serial: 8250: Protect LCR write in shutdown
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 8250_dw driver needs to potentially perform very complex operations
during LCR writes because its BUSY handling prevents updates to LCR
while UART is BUSY (which is not fully under our control without those
complex operations). Thus, LCR writes should occur under port's lock.

Move LCR write under port's lock in serial8250_do_shutdown(). Also
split the LCR RMW so that the logic is on a separate line for clarity.

Reported-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Cc: stable <stable@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-2-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index a743964c9d22..20cf123a0540 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2348,6 +2348,7 @@ static int serial8250_startup(struct uart_port *port)
 void serial8250_do_shutdown(struct uart_port *port)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
+	u32 lcr;
 
 	serial8250_rpm_get(up);
 	/*
@@ -2374,13 +2375,13 @@ void serial8250_do_shutdown(struct uart_port *port)
 			port->mctrl &= ~TIOCM_OUT2;
 
 		serial8250_set_mctrl(port, port->mctrl);
+
+		/* Disable break condition */
+		lcr = serial_port_in(port, UART_LCR);
+		lcr &= ~UART_LCR_SBC;
+		serial_port_out(port, UART_LCR, lcr);
 	}
 
-	/*
-	 * Disable break condition and FIFOs
-	 */
-	serial_port_out(port, UART_LCR,
-			serial_port_in(port, UART_LCR) & ~UART_LCR_SBC);
 	serial8250_clear_fifos(up);
 
 	rsa_disable(up);
-- 
cgit v1.2.3


From 8002d6d6d0d8a36a7d6ca523b17a51cb0fa7c3c3 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:44 +0200
Subject: serial: 8250_dw: Avoid unnecessary LCR writes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When DW UART is configured with BUSY flag, LCR writes may not always
succeed which can make any LCR write complex and very expensive.
Performing write directly can trigger IRQ and the driver has to perform
complex and distruptive sequence while retrying the write.

Therefore, it's better to avoid doing LCR write that would not change
the value of the LCR register. Add LCR write avoidance code into the
8250_dw driver's .serial_out() functions.

Reported-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Cc: stable <stable@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-3-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dw.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index db73b2ae17fa..f47ede4d1968 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -181,6 +181,22 @@ static void dw8250_check_lcr(struct uart_port *p, unsigned int offset, u32 value
 	 */
 }
 
+/*
+ * With BUSY, LCR writes can be very expensive (IRQ + complex retry logic).
+ * If the write does not change the value of the LCR register, skip it entirely.
+ */
+static bool dw8250_can_skip_reg_write(struct uart_port *p, unsigned int offset, u32 value)
+{
+	struct dw8250_data *d = to_dw8250_data(p->private_data);
+	u32 lcr;
+
+	if (offset != UART_LCR || d->uart_16550_compatible)
+		return false;
+
+	lcr = serial_port_in(p, offset);
+	return lcr == value;
+}
+
 /* Returns once the transmitter is empty or we run out of retries */
 static void dw8250_tx_wait_empty(struct uart_port *p)
 {
@@ -207,12 +223,18 @@ static void dw8250_tx_wait_empty(struct uart_port *p)
 
 static void dw8250_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
+	if (dw8250_can_skip_reg_write(p, offset, value))
+		return;
+
 	writeb(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
 
 static void dw8250_serial_out38x(struct uart_port *p, unsigned int offset, u32 value)
 {
+	if (dw8250_can_skip_reg_write(p, offset, value))
+		return;
+
 	/* Allow the TX to drain before we reconfigure */
 	if (offset == UART_LCR)
 		dw8250_tx_wait_empty(p);
@@ -237,6 +259,9 @@ static u32 dw8250_serial_inq(struct uart_port *p, unsigned int offset)
 
 static void dw8250_serial_outq(struct uart_port *p, unsigned int offset, u32 value)
 {
+	if (dw8250_can_skip_reg_write(p, offset, value))
+		return;
+
 	value &= 0xff;
 	__raw_writeq(value, p->membase + (offset << p->regshift));
 	/* Read back to ensure register write ordering. */
@@ -248,6 +273,9 @@ static void dw8250_serial_outq(struct uart_port *p, unsigned int offset, u32 val
 
 static void dw8250_serial_out32(struct uart_port *p, unsigned int offset, u32 value)
 {
+	if (dw8250_can_skip_reg_write(p, offset, value))
+		return;
+
 	writel(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
@@ -261,6 +289,9 @@ static u32 dw8250_serial_in32(struct uart_port *p, unsigned int offset)
 
 static void dw8250_serial_out32be(struct uart_port *p, unsigned int offset, u32 value)
 {
+	if (dw8250_can_skip_reg_write(p, offset, value))
+		return;
+
 	iowrite32be(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
-- 
cgit v1.2.3


From 8324a54f604da18f21070702a8ad82ab2062787b Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:45 +0200
Subject: serial: 8250: Add serial8250_handle_irq_locked()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

8250_port exports serial8250_handle_irq() to HW specific 8250 drivers.
It takes port's lock within but a HW specific 8250 driver may want to
take port's lock itself, do something, and then call the generic
handler in 8250_port but to do that, the caller has to release port's
lock for no good reason.

Introduce serial8250_handle_irq_locked() which a HW specific driver can
call while already holding port's lock.

As this is new export, put it straight into a namespace (where all 8250
exports should eventually be moved).

Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Cc: stable <stable@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-4-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 24 ++++++++++++++++--------
 include/linux/serial_8250.h         |  1 +
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 20cf123a0540..14d6aca44551 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -18,6 +18,7 @@
 #include <linux/irq.h>
 #include <linux/console.h>
 #include <linux/gpio/consumer.h>
+#include <linux/lockdep.h>
 #include <linux/sysrq.h>
 #include <linux/delay.h>
 #include <linux/platform_device.h>
@@ -1782,20 +1783,16 @@ static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir)
 }
 
 /*
- * This handles the interrupt from one port.
+ * Context: port's lock must be held by the caller.
  */
-int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
+void serial8250_handle_irq_locked(struct uart_port *port, unsigned int iir)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 	struct tty_port *tport = &port->state->port;
 	bool skip_rx = false;
-	unsigned long flags;
 	u16 status;
 
-	if (iir & UART_IIR_NO_INT)
-		return 0;
-
-	uart_port_lock_irqsave(port, &flags);
+	lockdep_assert_held_once(&port->lock);
 
 	status = serial_lsr_in(up);
 
@@ -1828,8 +1825,19 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 		else if (!up->dma->tx_running)
 			__stop_tx(up);
 	}
+}
+EXPORT_SYMBOL_NS_GPL(serial8250_handle_irq_locked, "SERIAL_8250");
 
-	uart_unlock_and_check_sysrq_irqrestore(port, flags);
+/*
+ * This handles the interrupt from one port.
+ */
+int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
+{
+	if (iir & UART_IIR_NO_INT)
+		return 0;
+
+	guard(uart_port_lock_irqsave)(port);
+	serial8250_handle_irq_locked(port, iir);
 
 	return 1;
 }
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 01efdce0fda0..a95b2d143d24 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -195,6 +195,7 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl);
 void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud,
 			       unsigned int quot);
 int fsl8250_handle_irq(struct uart_port *port);
+void serial8250_handle_irq_locked(struct uart_port *port, unsigned int iir);
 int serial8250_handle_irq(struct uart_port *port, unsigned int iir);
 u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr);
 void serial8250_read_char(struct uart_8250_port *up, u16 lsr);
-- 
cgit v1.2.3


From 883c5a2bc934c165c4491d1ef7da0ac4e9765077 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:46 +0200
Subject: serial: 8250_dw: Rework dw8250_handle_irq() locking and IIR handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dw8250_handle_irq() takes port's lock multiple times with no good
reason to release it in between and calls serial8250_handle_irq()
that also takes port's lock.

Take port's lock only once in dw8250_handle_irq() and use
serial8250_handle_irq_locked() to avoid releasing port's lock in
between.

As IIR_NO_INT check in serial8250_handle_irq() was outside of port's
lock, it has to be done already in dw8250_handle_irq().

DW UART can, in addition to IIR_NO_INT, report BUSY_DETECT (0x7) which
collided with the IIR_NO_INT (0x1) check in serial8250_handle_irq()
(because & is used instead of ==) meaning that no other work is done by
serial8250_handle_irq() during an BUSY_DETECT interrupt.

This allows reorganizing code in dw8250_handle_irq() to do both
IIR_NO_INT and BUSY_DETECT handling right at the start simplifying
the logic.

Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Cc: stable <stable@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-5-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dw.c | 37 +++++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index f47ede4d1968..abf0814086a5 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -9,6 +9,9 @@
  * LCR is written whilst busy.  If it is, then a busy detect interrupt is
  * raised, the LCR needs to be rewritten and the uart status register read.
  */
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -40,6 +43,8 @@
 #define RZN1_UART_RDMACR 0x110 /* DMA Control Register Receive Mode */
 
 /* DesignWare specific register fields */
+#define DW_UART_IIR_IID			GENMASK(3, 0)
+
 #define DW_UART_MCR_SIRE		BIT(6)
 
 /* Renesas specific register fields */
@@ -312,7 +317,19 @@ static int dw8250_handle_irq(struct uart_port *p)
 	bool rx_timeout = (iir & 0x3f) == UART_IIR_RX_TIMEOUT;
 	unsigned int quirks = d->pdata->quirks;
 	unsigned int status;
-	unsigned long flags;
+
+	switch (FIELD_GET(DW_UART_IIR_IID, iir)) {
+	case UART_IIR_NO_INT:
+		return 0;
+
+	case UART_IIR_BUSY:
+		/* Clear the USR */
+		serial_port_in(p, d->pdata->usr_reg);
+
+		return 1;
+	}
+
+	guard(uart_port_lock_irqsave)(p);
 
 	/*
 	 * There are ways to get Designware-based UARTs into a state where
@@ -325,20 +342,15 @@ static int dw8250_handle_irq(struct uart_port *p)
 	 * so we limit the workaround only to non-DMA mode.
 	 */
 	if (!up->dma && rx_timeout) {
-		uart_port_lock_irqsave(p, &flags);
 		status = serial_lsr_in(up);
 
 		if (!(status & (UART_LSR_DR | UART_LSR_BI)))
 			serial_port_in(p, UART_RX);
-
-		uart_port_unlock_irqrestore(p, flags);
 	}
 
 	/* Manually stop the Rx DMA transfer when acting as flow controller */
 	if (quirks & DW_UART_QUIRK_IS_DMA_FC && up->dma && up->dma->rx_running && rx_timeout) {
-		uart_port_lock_irqsave(p, &flags);
 		status = serial_lsr_in(up);
-		uart_port_unlock_irqrestore(p, flags);
 
 		if (status & (UART_LSR_DR | UART_LSR_BI)) {
 			dw8250_writel_ext(p, RZN1_UART_RDMACR, 0);
@@ -346,17 +358,9 @@ static int dw8250_handle_irq(struct uart_port *p)
 		}
 	}
 
-	if (serial8250_handle_irq(p, iir))
-		return 1;
-
-	if ((iir & UART_IIR_BUSY) == UART_IIR_BUSY) {
-		/* Clear the USR */
-		serial_port_in(p, d->pdata->usr_reg);
+	serial8250_handle_irq_locked(p, iir);
 
-		return 1;
-	}
-
-	return 0;
+	return 1;
 }
 
 static void dw8250_clk_work_cb(struct work_struct *work)
@@ -867,6 +871,7 @@ static struct platform_driver dw8250_platform_driver = {
 
 module_platform_driver(dw8250_platform_driver);
 
+MODULE_IMPORT_NS("SERIAL_8250");
 MODULE_AUTHOR("Jamie Iles");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Synopsys DesignWare 8250 serial port driver");
-- 
cgit v1.2.3


From 73a4ed8f9efaaaf8207614ccc1c9d5ca1888f23a Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:47 +0200
Subject: serial: 8250_dw: Rework IIR_NO_INT handling to stop interrupt storm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

INTC10EE UART can end up into an interrupt storm where it reports
IIR_NO_INT (0x1). If the storm happens during active UART operation, it
is promptly stopped by IIR value change due to Rx or Tx events.
However, when there is no activity, either due to idle serial line or
due to specific circumstances such as during shutdown that writes
IER=0, there is nothing to stop the storm.

During shutdown the storm is particularly problematic because
serial8250_do_shutdown() calls synchronize_irq() that will hang in
waiting for the storm to finish which never happens.

This problem can also result in triggering a warning:

  irq 45: nobody cared (try booting with the "irqpoll" option)
  [...snip...]
  handlers:
    serial8250_interrupt
  Disabling IRQ #45

Normal means to reset interrupt status by reading LSR, MSR, USR, or RX
register do not result in the UART deasserting the IRQ.

Add a quirk to INTC10EE UARTs to enable Tx interrupts if UART's Tx is
currently empty and inactive. Rework IIR_NO_INT to keep track of the
number of consecutive IIR_NO_INT, and on fourth one perform the quirk.
Enabling Tx interrupts should change IIR value from IIR_NO_INT to
IIR_THRI which has been observed to stop the storm.

Fixes: e92fad024929 ("serial: 8250_dw: Add ACPI ID for Granite Rapids-D UART")
Cc: stable <stable@kernel.org>
Reported-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-6-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_dw.c | 67 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 63 insertions(+), 4 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index abf0814086a5..3d8032f752b8 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -61,6 +61,13 @@
 #define DW_UART_QUIRK_IS_DMA_FC		BIT(3)
 #define DW_UART_QUIRK_APMC0D08		BIT(4)
 #define DW_UART_QUIRK_CPR_VALUE		BIT(5)
+#define DW_UART_QUIRK_IER_KICK		BIT(6)
+
+/*
+ * Number of consecutive IIR_NO_INT interrupts required to trigger interrupt
+ * storm prevention code.
+ */
+#define DW_UART_QUIRK_IER_KICK_THRES	4
 
 struct dw8250_platform_data {
 	u8 usr_reg;
@@ -82,6 +89,8 @@ struct dw8250_data {
 
 	unsigned int		skip_autocfg:1;
 	unsigned int		uart_16550_compatible:1;
+
+	u8			no_int_count;
 };
 
 static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data)
@@ -308,6 +317,29 @@ static u32 dw8250_serial_in32be(struct uart_port *p, unsigned int offset)
        return dw8250_modify_msr(p, offset, value);
 }
 
+/*
+ * INTC10EE UART can IRQ storm while reporting IIR_NO_INT. Inducing IIR value
+ * change has been observed to break the storm.
+ *
+ * If Tx is empty (THRE asserted), we use here IER_THRI to cause IIR_NO_INT ->
+ * IIR_THRI transition.
+ */
+static void dw8250_quirk_ier_kick(struct uart_port *p)
+{
+	struct uart_8250_port *up = up_to_u8250p(p);
+	u32 lsr;
+
+	if (up->ier & UART_IER_THRI)
+		return;
+
+	lsr = serial_lsr_in(up);
+	if (!(lsr & UART_LSR_THRE))
+		return;
+
+	serial_port_out(p, UART_IER, up->ier | UART_IER_THRI);
+	serial_port_in(p, UART_LCR);		/* safe, no side-effects */
+	serial_port_out(p, UART_IER, up->ier);
+}
 
 static int dw8250_handle_irq(struct uart_port *p)
 {
@@ -318,18 +350,30 @@ static int dw8250_handle_irq(struct uart_port *p)
 	unsigned int quirks = d->pdata->quirks;
 	unsigned int status;
 
+	guard(uart_port_lock_irqsave)(p);
+
 	switch (FIELD_GET(DW_UART_IIR_IID, iir)) {
 	case UART_IIR_NO_INT:
+		if (d->uart_16550_compatible || up->dma)
+			return 0;
+
+		if (quirks & DW_UART_QUIRK_IER_KICK &&
+		    d->no_int_count == (DW_UART_QUIRK_IER_KICK_THRES - 1))
+			dw8250_quirk_ier_kick(p);
+		d->no_int_count = (d->no_int_count + 1) % DW_UART_QUIRK_IER_KICK_THRES;
+
 		return 0;
 
 	case UART_IIR_BUSY:
 		/* Clear the USR */
 		serial_port_in(p, d->pdata->usr_reg);
 
+		d->no_int_count = 0;
+
 		return 1;
 	}
 
-	guard(uart_port_lock_irqsave)(p);
+	d->no_int_count = 0;
 
 	/*
 	 * There are ways to get Designware-based UARTs into a state where
@@ -562,6 +606,14 @@ static void dw8250_reset_control_assert(void *data)
 	reset_control_assert(data);
 }
 
+static void dw8250_shutdown(struct uart_port *port)
+{
+	struct dw8250_data *d = to_dw8250_data(port->private_data);
+
+	serial8250_do_shutdown(port);
+	d->no_int_count = 0;
+}
+
 static int dw8250_probe(struct platform_device *pdev)
 {
 	struct uart_8250_port uart = {}, *up = &uart;
@@ -689,10 +741,12 @@ static int dw8250_probe(struct platform_device *pdev)
 		dw8250_quirks(p, data);
 
 	/* If the Busy Functionality is not implemented, don't handle it */
-	if (data->uart_16550_compatible)
+	if (data->uart_16550_compatible) {
 		p->handle_irq = NULL;
-	else if (data->pdata)
+	} else if (data->pdata) {
 		p->handle_irq = dw8250_handle_irq;
+		p->shutdown = dw8250_shutdown;
+	}
 
 	dw8250_setup_dma_filter(p, data);
 
@@ -824,6 +878,11 @@ static const struct dw8250_platform_data dw8250_skip_set_rate_data = {
 	.quirks = DW_UART_QUIRK_SKIP_SET_RATE,
 };
 
+static const struct dw8250_platform_data dw8250_intc10ee = {
+	.usr_reg = DW_UART_USR,
+	.quirks = DW_UART_QUIRK_IER_KICK,
+};
+
 static const struct of_device_id dw8250_of_match[] = {
 	{ .compatible = "snps,dw-apb-uart", .data = &dw8250_dw_apb },
 	{ .compatible = "cavium,octeon-3860-uart", .data = &dw8250_octeon_3860_data },
@@ -853,7 +912,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = {
 	{ "INT33C5", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3434", (kernel_ulong_t)&dw8250_dw_apb },
 	{ "INT3435", (kernel_ulong_t)&dw8250_dw_apb },
-	{ "INTC10EE", (kernel_ulong_t)&dw8250_dw_apb },
+	{ "INTC10EE", (kernel_ulong_t)&dw8250_intc10ee },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match);
-- 
cgit v1.2.3


From e0a368ae79531ff92105a2692f10d83052055856 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:48 +0200
Subject: serial: 8250: Add late synchronize_irq() to shutdown to handle DW
 UART BUSY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When DW UART is !uart_16550_compatible, it can indicate BUSY at any
point (when under constant Rx pressure) unless a complex sequence of
steps is performed. Any LCR write can run a foul with the condition
that prevents writing LCR while the UART is BUSY, which triggers
BUSY_DETECT interrupt that seems unmaskable using IER bits.

Normal flow is that dw8250_handle_irq() handles BUSY_DETECT condition
by reading USR register. This BUSY feature, however, breaks the
assumptions made in serial8250_do_shutdown(), which runs
synchronize_irq() after clearing IER and assumes no interrupts can
occur after that point but then proceeds to update LCR, which on DW
UART can trigger an interrupt.

If serial8250_do_shutdown() releases the interrupt handler before the
handler has run and processed the BUSY_DETECT condition by read the USR
register, the IRQ is not deasserted resulting in interrupt storm that
triggers "irq x: nobody cared" warning leading to disabling the IRQ.

Add late synchronize_irq() into serial8250_do_shutdown() to ensure
BUSY_DETECT from DW UART is handled before port's interrupt handler is
released. Alternative would be to add DW UART specific shutdown
function but it would mostly duplicate the generic code and the extra
synchronize_irq() seems pretty harmless in serial8250_do_shutdown().

Fixes: 7d4008ebb1c9 ("tty: add a DesignWare 8250 driver")
Cc: stable <stable@kernel.org>
Reported-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-7-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_port.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 14d6aca44551..94a64b3dd1f7 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2399,6 +2399,12 @@ void serial8250_do_shutdown(struct uart_port *port)
 	 * the IRQ chain.
 	 */
 	serial_port_in(port, UART_RX);
+	/*
+	 * LCR writes on DW UART can trigger late (unmaskable) IRQs.
+	 * Handle them before releasing the handler.
+	 */
+	synchronize_irq(port->irq);
+
 	serial8250_rpm_put(up);
 
 	up->ops->release_irq(up);
-- 
cgit v1.2.3


From a7b9ce39fbe4ae2919fe4f7ac16c293cb6632d30 Mon Sep 17 00:00:00 2001
From: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Feb 2026 19:10:49 +0200
Subject: serial: 8250_dw: Ensure BUSY is deasserted
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DW UART cannot write to LCR, DLL, and DLH while BUSY is asserted.
Existance of BUSY depends on uart_16550_compatible, if UART HW is
configured with it those registers can always be written.

There currently is dw8250_force_idle() which attempts to achieve
non-BUSY state by disabling FIFO, however, the solution is unreliable
when Rx keeps getting more and more characters.

Create a sequence of operations that ensures UART cannot keep BUSY
asserted indefinitely. The new sequence relies on enabling loopback mode
temporarily to prevent incoming Rx characters keeping UART BUSY.

Ensure no Tx in ongoing while the UART is switches into the loopback
mode (requires exporting serial8250_fifo_wait_for_lsr_thre() and adding
DMA Tx pause/resume functions).

According to tests performed by Adriana Nicolae <adriana@arista.com>,
simply disabling FIFO or clearing FIFOs only once does not always
ensure BUSY is deasserted but up to two tries may be needed. This could
be related to ongoing Rx of a character (a guess, not known for sure).
Therefore, retry FIFO clearing a few times (retry limit 4 is arbitrary
number but using, e.g., p->fifosize seems overly large). Tests
performed by others did not exhibit similar challenge but it does not
seem harmful to leave the FIFO clearing loop in place for all DW UARTs
with BUSY functionality.

Use the new dw8250_idle_enter/exit() to do divisor writes and LCR
writes. In case of plain LCR writes, opportunistically try to update
LCR first and only invoke dw8250_idle_enter() if the write did not
succeed (it has been observed that in practice most LCR writes do
succeed without complications).

This issue was first reported by qianfan Zhao who put lots of debugging
effort into understanding the solution space.

Fixes: c49436b657d0 ("serial: 8250_dw: Improve unwritable LCR workaround")
Fixes: 7d4008ebb1c9 ("tty: add a DesignWare 8250 driver")
Cc: stable <stable@kernel.org>
Reported-by: qianfan Zhao <qianfanguijin@163.com>
Link: https://lore.kernel.org/linux-serial/289bb78a-7509-1c5c-2923-a04ed3b6487d@163.com/
Reported-by: Adriana Nicolae <adriana@arista.com>
Link: https://lore.kernel.org/linux-serial/20250819182322.3451959-1-adriana@arista.com/
Reported-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Bandal, Shankar <shankar.bandal@intel.com>
Tested-by: Murthy, Shanth <shanth.murthy@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20260203171049.4353-8-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250.h      |  25 ++++++
 drivers/tty/serial/8250/8250_dw.c   | 163 ++++++++++++++++++++++++++----------
 drivers/tty/serial/8250/8250_port.c |  28 ++++---
 3 files changed, 161 insertions(+), 55 deletions(-)

diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 8caecfc85d93..77fe0588fd6b 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -175,7 +175,9 @@ static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up,
 	return value;
 }
 
+void serial8250_clear_fifos(struct uart_8250_port *p);
 void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p);
+void serial8250_fifo_wait_for_lsr_thre(struct uart_8250_port *up, unsigned int count);
 
 void serial8250_rpm_get(struct uart_8250_port *p);
 void serial8250_rpm_put(struct uart_8250_port *p);
@@ -400,6 +402,26 @@ static inline bool serial8250_tx_dma_running(struct uart_8250_port *p)
 
 	return dma && dma->tx_running;
 }
+
+static inline void serial8250_tx_dma_pause(struct uart_8250_port *p)
+{
+	struct uart_8250_dma *dma = p->dma;
+
+	if (!dma->tx_running)
+		return;
+
+	dmaengine_pause(dma->txchan);
+}
+
+static inline void serial8250_tx_dma_resume(struct uart_8250_port *p)
+{
+	struct uart_8250_dma *dma = p->dma;
+
+	if (!dma->tx_running)
+		return;
+
+	dmaengine_resume(dma->txchan);
+}
 #else
 static inline int serial8250_tx_dma(struct uart_8250_port *p)
 {
@@ -421,6 +443,9 @@ static inline bool serial8250_tx_dma_running(struct uart_8250_port *p)
 {
 	return false;
 }
+
+static inline void serial8250_tx_dma_pause(struct uart_8250_port *p) { }
+static inline void serial8250_tx_dma_resume(struct uart_8250_port *p) { }
 #endif
 
 static inline int ns16550a_goto_highspeed(struct uart_8250_port *up)
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 3d8032f752b8..94beadb4024d 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/lockdep.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
@@ -47,6 +48,8 @@
 
 #define DW_UART_MCR_SIRE		BIT(6)
 
+#define DW_UART_USR_BUSY		BIT(0)
+
 /* Renesas specific register fields */
 #define RZN1_UART_xDMACR_DMA_EN		BIT(0)
 #define RZN1_UART_xDMACR_1_WORD_BURST	(0 << 1)
@@ -89,6 +92,7 @@ struct dw8250_data {
 
 	unsigned int		skip_autocfg:1;
 	unsigned int		uart_16550_compatible:1;
+	unsigned int		in_idle:1;
 
 	u8			no_int_count;
 };
@@ -121,78 +125,151 @@ static inline u32 dw8250_modify_msr(struct uart_port *p, unsigned int offset, u3
 	return value;
 }
 
+static void dw8250_idle_exit(struct uart_port *p)
+{
+	struct dw8250_data *d = to_dw8250_data(p->private_data);
+	struct uart_8250_port *up = up_to_u8250p(p);
+
+	if (d->uart_16550_compatible)
+		return;
+
+	if (up->capabilities & UART_CAP_FIFO)
+		serial_port_out(p, UART_FCR, up->fcr);
+	serial_port_out(p, UART_MCR, up->mcr);
+	serial_port_out(p, UART_IER, up->ier);
+
+	/* DMA Rx is restarted by IRQ handler as needed. */
+	if (up->dma)
+		serial8250_tx_dma_resume(up);
+
+	d->in_idle = 0;
+}
+
 /*
- * This function is being called as part of the uart_port::serial_out()
- * routine. Hence, it must not call serial_port_out() or serial_out()
- * against the modified registers here, i.e. LCR.
+ * Ensure BUSY is not asserted. If DW UART is configured with
+ * !uart_16550_compatible, the writes to LCR, DLL, and DLH fail while
+ * BUSY is asserted.
+ *
+ * Context: port's lock must be held
  */
-static void dw8250_force_idle(struct uart_port *p)
+static int dw8250_idle_enter(struct uart_port *p)
 {
+	struct dw8250_data *d = to_dw8250_data(p->private_data);
+	unsigned int usr_reg = d->pdata ? d->pdata->usr_reg : DW_UART_USR;
 	struct uart_8250_port *up = up_to_u8250p(p);
-	unsigned int lsr;
+	int retries;
+	u32 lsr;
 
-	/*
-	 * The following call currently performs serial_out()
-	 * against the FCR register. Because it differs to LCR
-	 * there will be no infinite loop, but if it ever gets
-	 * modified, we might need a new custom version of it
-	 * that avoids infinite recursion.
-	 */
-	serial8250_clear_and_reinit_fifos(up);
+	lockdep_assert_held_once(&p->lock);
+
+	if (d->uart_16550_compatible)
+		return 0;
+
+	d->in_idle = 1;
+
+	/* Prevent triggering interrupt from RBR filling */
+	serial_port_out(p, UART_IER, 0);
+
+	if (up->dma) {
+		serial8250_rx_dma_flush(up);
+		if (serial8250_tx_dma_running(up))
+			serial8250_tx_dma_pause(up);
+	}
 
 	/*
-	 * With PSLVERR_RESP_EN parameter set to 1, the device generates an
-	 * error response when an attempt to read an empty RBR with FIFO
-	 * enabled.
+	 * Wait until Tx becomes empty + one extra frame time to ensure all bits
+	 * have been sent on the wire.
+	 *
+	 * FIXME: frame_time delay is too long with very low baudrates.
 	 */
-	if (up->fcr & UART_FCR_ENABLE_FIFO) {
-		lsr = serial_port_in(p, UART_LSR);
-		if (!(lsr & UART_LSR_DR))
-			return;
+	serial8250_fifo_wait_for_lsr_thre(up, p->fifosize);
+	ndelay(p->frame_time);
+
+	serial_port_out(p, UART_MCR, up->mcr | UART_MCR_LOOP);
+
+	retries = 4;	/* Arbitrary limit, 2 was always enough in tests */
+	do {
+		serial8250_clear_fifos(up);
+		if (!(serial_port_in(p, usr_reg) & DW_UART_USR_BUSY))
+			break;
+		/* FIXME: frame_time delay is too long with very low baudrates. */
+		ndelay(p->frame_time);
+	} while (--retries);
+
+	lsr = serial_lsr_in(up);
+	if (lsr & UART_LSR_DR) {
+		serial_port_in(p, UART_RX);
+		up->lsr_saved_flags = 0;
 	}
 
-	serial_port_in(p, UART_RX);
+	/* Now guaranteed to have BUSY deasserted? Just sanity check */
+	if (serial_port_in(p, usr_reg) & DW_UART_USR_BUSY) {
+		dw8250_idle_exit(p);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void dw8250_set_divisor(struct uart_port *p, unsigned int baud,
+			       unsigned int quot, unsigned int quot_frac)
+{
+	struct uart_8250_port *up = up_to_u8250p(p);
+	int ret;
+
+	ret = dw8250_idle_enter(p);
+	if (ret < 0)
+		return;
+
+	serial_port_out(p, UART_LCR, up->lcr | UART_LCR_DLAB);
+	if (!(serial_port_in(p, UART_LCR) & UART_LCR_DLAB))
+		goto idle_failed;
+
+	serial_dl_write(up, quot);
+	serial_port_out(p, UART_LCR, up->lcr);
+
+idle_failed:
+	dw8250_idle_exit(p);
 }
 
 /*
  * This function is being called as part of the uart_port::serial_out()
- * routine. Hence, it must not call serial_port_out() or serial_out()
- * against the modified registers here, i.e. LCR.
+ * routine. Hence, special care must be taken when serial_port_out() or
+ * serial_out() against the modified registers here, i.e. LCR (d->in_idle is
+ * used to break recursion loop).
  */
 static void dw8250_check_lcr(struct uart_port *p, unsigned int offset, u32 value)
 {
 	struct dw8250_data *d = to_dw8250_data(p->private_data);
-	void __iomem *addr = p->membase + (offset << p->regshift);
-	int tries = 1000;
+	u32 lcr;
+	int ret;
 
 	if (offset != UART_LCR || d->uart_16550_compatible)
 		return;
 
+	lcr = serial_port_in(p, UART_LCR);
+
 	/* Make sure LCR write wasn't ignored */
-	while (tries--) {
-		u32 lcr = serial_port_in(p, offset);
+	if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
+		return;
 
-		if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
-			return;
+	if (d->in_idle)
+		goto write_err;
 
-		dw8250_force_idle(p);
+	ret = dw8250_idle_enter(p);
+	if (ret < 0)
+		goto write_err;
 
-#ifdef CONFIG_64BIT
-		if (p->type == PORT_OCTEON)
-			__raw_writeq(value & 0xff, addr);
-		else
-#endif
-		if (p->iotype == UPIO_MEM32)
-			writel(value, addr);
-		else if (p->iotype == UPIO_MEM32BE)
-			iowrite32be(value, addr);
-		else
-			writeb(value, addr);
-	}
+	serial_port_out(p, UART_LCR, value);
+	dw8250_idle_exit(p);
+	return;
+
+write_err:
 	/*
 	 * FIXME: this deadlocks if port->lock is already held
 	 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
 	 */
+	return;		/* Silences "label at the end of compound statement" */
 }
 
 /*
@@ -632,8 +709,10 @@ static int dw8250_probe(struct platform_device *pdev)
 	p->type		= PORT_8250;
 	p->flags	= UPF_FIXED_PORT;
 	p->dev		= dev;
+
 	p->set_ldisc	= dw8250_set_ldisc;
 	p->set_termios	= dw8250_set_termios;
+	p->set_divisor	= dw8250_set_divisor;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 94a64b3dd1f7..328711b5df1a 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -489,7 +489,7 @@ serial_port_out_sync(struct uart_port *p, int offset, int value)
 /*
  * FIFO support.
  */
-static void serial8250_clear_fifos(struct uart_8250_port *p)
+void serial8250_clear_fifos(struct uart_8250_port *p)
 {
 	if (p->capabilities & UART_CAP_FIFO) {
 		serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO);
@@ -498,6 +498,7 @@ static void serial8250_clear_fifos(struct uart_8250_port *p)
 		serial_out(p, UART_FCR, 0);
 	}
 }
+EXPORT_SYMBOL_NS_GPL(serial8250_clear_fifos, "SERIAL_8250");
 
 static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t);
 static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t);
@@ -3198,6 +3199,17 @@ void serial8250_set_defaults(struct uart_8250_port *up)
 }
 EXPORT_SYMBOL_GPL(serial8250_set_defaults);
 
+void serial8250_fifo_wait_for_lsr_thre(struct uart_8250_port *up, unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		if (wait_for_lsr(up, UART_LSR_THRE))
+			return;
+	}
+}
+EXPORT_SYMBOL_NS_GPL(serial8250_fifo_wait_for_lsr_thre, "SERIAL_8250");
+
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 
 static void serial8250_console_putchar(struct uart_port *port, unsigned char ch)
@@ -3239,16 +3251,6 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 	serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
 }
 
-static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count)
-{
-	unsigned int i;
-
-	for (i = 0; i < count; i++) {
-		if (wait_for_lsr(up, UART_LSR_THRE))
-			return;
-	}
-}
-
 /*
  * Print a string to the serial port using the device FIFO
  *
@@ -3267,7 +3269,7 @@ static void serial8250_console_fifo_write(struct uart_8250_port *up,
 
 	while (s != end) {
 		/* Allow timeout for each byte of a possibly full FIFO */
-		fifo_wait_for_lsr(up, fifosize);
+		serial8250_fifo_wait_for_lsr_thre(up, fifosize);
 
 		for (i = 0; i < fifosize && s != end; ++i) {
 			if (*s == '\n' && !cr_sent) {
@@ -3285,7 +3287,7 @@ static void serial8250_console_fifo_write(struct uart_8250_port *up,
 	 * Allow timeout for each byte written since the caller will only wait
 	 * for UART_LSR_BOTH_EMPTY using the timeout of a single character
 	 */
-	fifo_wait_for_lsr(up, tx_count);
+	serial8250_fifo_wait_for_lsr_thre(up, tx_count);
 }
 
 /*
-- 
cgit v1.2.3


From c2c185be5c85d37215397c8e8781abf0a69bec1f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 12 Mar 2026 08:59:25 -0600
Subject: io_uring/kbuf: check if target buffer list is still legacy on recycle

There's a gap between when the buffer was grabbed and when it
potentially gets recycled, where if the list is empty, someone could've
upgraded it to a ring provided type. This can happen if the request
is forced via io-wq. The legacy recycling is missing checking if the
buffer_list still exists, and if it's of the correct type. Add those
checks.

Cc: stable@vger.kernel.org
Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index dae5b4ab3819..e7f444953dfb 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -111,9 +111,18 @@ bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags)
 
 	buf = req->kbuf;
 	bl = io_buffer_get_list(ctx, buf->bgid);
-	list_add(&buf->list, &bl->buf_list);
-	bl->nbufs++;
+	/*
+	 * If the buffer list was upgraded to a ring-based one, or removed,
+	 * while the request was in-flight in io-wq, drop it.
+	 */
+	if (bl && !(bl->flags & IOBL_BUF_RING)) {
+		list_add(&buf->list, &bl->buf_list);
+		bl->nbufs++;
+	} else {
+		kfree(buf);
+	}
 	req->flags &= ~REQ_F_BUFFER_SELECTED;
+	req->kbuf = NULL;
 
 	io_ring_submit_unlock(ctx, issue_flags);
 	return true;
-- 
cgit v1.2.3


From c38b8f5f791ecce13ab77e2257f8fd2444ba80f6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 12 Mar 2026 04:39:08 +0000
Subject: net: prevent NULL deref in ip[6]tunnel_xmit()

Blamed commit missed that both functions can be called with dev == NULL.

Also add unlikely() hints for these conditions that only fuzzers can hit.

Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions")
Signed-off-by: Eric Dumazet <edumazet@google.com>
CC: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260312043908.2790803-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip6_tunnel.h  | 10 ++++++----
 net/ipv4/ip_tunnel_core.c | 10 ++++++----
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 1253cbb4b0a4..359b595f1df9 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -156,10 +156,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
 {
 	int pkt_len, err;
 
-	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
-		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
-				     dev->name);
-		DEV_STATS_INC(dev, tx_errors);
+	if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
+		if (dev) {
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
+			DEV_STATS_INC(dev, tx_errors);
+		}
 		kfree_skb(skb);
 		return;
 	}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index b1b6bf949f65..5683c328990f 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -58,10 +58,12 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	struct iphdr *iph;
 	int err;
 
-	if (dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT) {
-		net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
-				     dev->name);
-		DEV_STATS_INC(dev, tx_errors);
+	if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
+		if (dev) {
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
+			DEV_STATS_INC(dev, tx_errors);
+		}
 		ip_rt_put(rt);
 		kfree_skb(skb);
 		return;
-- 
cgit v1.2.3


From d2ea4ff1ce50787a98a3900b3fb1636f3620b7cf Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 10 Mar 2026 14:18:41 -0700
Subject: KVM: selftests: Verify SEV+ guests can read and write EFER, CR0, CR4,
 and CR8

Add "do no harm" testing of EFER, CR0, CR4, and CR8 for SEV+ guests to
verify that the guest can read and write the registers, without hitting
e.g. a #VC on SEV-ES guests due to KVM incorrectly trying to intercept a
register.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260310211841.2552361-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/include/x86/processor.h  | 23 +++++++++++++++++
 tools/testing/selftests/kvm/x86/sev_smoke_test.c   | 30 ++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 4ebae4269e68..469a22122157 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -557,6 +557,11 @@ static inline uint64_t get_cr0(void)
 	return cr0;
 }
 
+static inline void set_cr0(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr0" : : "r" (val) : "memory");
+}
+
 static inline uint64_t get_cr3(void)
 {
 	uint64_t cr3;
@@ -566,6 +571,11 @@ static inline uint64_t get_cr3(void)
 	return cr3;
 }
 
+static inline void set_cr3(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr3" : : "r" (val) : "memory");
+}
+
 static inline uint64_t get_cr4(void)
 {
 	uint64_t cr4;
@@ -580,6 +590,19 @@ static inline void set_cr4(uint64_t val)
 	__asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
 }
 
+static inline uint64_t get_cr8(void)
+{
+	uint64_t cr8;
+
+	__asm__ __volatile__("mov %%cr8, %[cr8]" : [cr8]"=r"(cr8));
+	return cr8;
+}
+
+static inline void set_cr8(uint64_t val)
+{
+	__asm__ __volatile__("mov %0, %%cr8" : : "r" (val) : "memory");
+}
+
 static inline void set_idt(const struct desc_ptr *idt_desc)
 {
 	__asm__ __volatile__("lidt %0"::"m"(*idt_desc));
diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index 86ad1c7d068f..8bd37a476f15 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -13,6 +13,30 @@
 #include "linux/psp-sev.h"
 #include "sev.h"
 
+static void guest_sev_test_msr(uint32_t msr)
+{
+	uint64_t val = rdmsr(msr);
+
+	wrmsr(msr, val);
+	GUEST_ASSERT(val == rdmsr(msr));
+}
+
+#define guest_sev_test_reg(reg)			\
+do {						\
+	uint64_t val = get_##reg();		\
+						\
+	set_##reg(val);				\
+	GUEST_ASSERT(val == get_##reg());	\
+} while (0)
+
+static void guest_sev_test_regs(void)
+{
+	guest_sev_test_msr(MSR_EFER);
+	guest_sev_test_reg(cr0);
+	guest_sev_test_reg(cr3);
+	guest_sev_test_reg(cr4);
+	guest_sev_test_reg(cr8);
+}
 
 #define XFEATURE_MASK_X87_AVX (XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)
 
@@ -24,6 +48,8 @@ static void guest_snp_code(void)
 	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_ES_ENABLED);
 	GUEST_ASSERT(sev_msr & MSR_AMD64_SEV_SNP_ENABLED);
 
+	guest_sev_test_regs();
+
 	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
 	vmgexit();
 }
@@ -34,6 +60,8 @@ static void guest_sev_es_code(void)
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED);
 
+	guest_sev_test_regs();
+
 	/*
 	 * TODO: Add GHCB and ucall support for SEV-ES guests.  For now, simply
 	 * force "termination" to signal "done" via the GHCB MSR protocol.
@@ -47,6 +75,8 @@ static void guest_sev_code(void)
 	GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV));
 	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
 
+	guest_sev_test_regs();
+
 	GUEST_DONE();
 }
 
-- 
cgit v1.2.3


From 2619da73bb2f10d88f7e1087125c40144fdf0987 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Thu, 5 Mar 2026 20:49:55 +0100
Subject: KVM: x86: Use __DECLARE_FLEX_ARRAY() for UAPI structures with VLAs

Commit 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with
flexible-array members") broke the userspace API for C++.

These structures ending in VLAs are typically a *header*, which can be
followed by an arbitrary number of entries. Userspace typically creates
a larger structure with some non-zero number of entries, for example in
QEMU's kvm_arch_get_supported_msr_feature():

    struct {
        struct kvm_msrs info;
        struct kvm_msr_entry entries[1];
    } msr_data = {};

While that works in C, it fails in C++ with an error like:
 flexible array member 'kvm_msrs::entries' not at end of 'struct msr_data'

Fix this by using __DECLARE_FLEX_ARRAY() for the VLA, which uses [0]
for C++ compilation.

Fixes: 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members")
Cc: stable@vger.kernel.org
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://patch.msgid.link/3abaf6aefd6e5efeff3b860ac38421d9dec908db.camel@infradead.org
[sean: tag for stable@]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/uapi/asm/kvm.h | 12 ++++++------
 include/uapi/linux/kvm.h        | 11 ++++++-----
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 0d4538fa6c31..5f2b30d0405c 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -197,13 +197,13 @@ struct kvm_msrs {
 	__u32 nmsrs; /* number of msrs in entries */
 	__u32 pad;
 
-	struct kvm_msr_entry entries[];
+	__DECLARE_FLEX_ARRAY(struct kvm_msr_entry, entries);
 };
 
 /* for KVM_GET_MSR_INDEX_LIST */
 struct kvm_msr_list {
 	__u32 nmsrs; /* number of msrs in entries */
-	__u32 indices[];
+	__DECLARE_FLEX_ARRAY(__u32, indices);
 };
 
 /* Maximum size of any access bitmap in bytes */
@@ -245,7 +245,7 @@ struct kvm_cpuid_entry {
 struct kvm_cpuid {
 	__u32 nent;
 	__u32 padding;
-	struct kvm_cpuid_entry entries[];
+	__DECLARE_FLEX_ARRAY(struct kvm_cpuid_entry, entries);
 };
 
 struct kvm_cpuid_entry2 {
@@ -267,7 +267,7 @@ struct kvm_cpuid_entry2 {
 struct kvm_cpuid2 {
 	__u32 nent;
 	__u32 padding;
-	struct kvm_cpuid_entry2 entries[];
+	__DECLARE_FLEX_ARRAY(struct kvm_cpuid_entry2, entries);
 };
 
 /* for KVM_GET_PIT and KVM_SET_PIT */
@@ -398,7 +398,7 @@ struct kvm_xsave {
 	 * the contents of CPUID leaf 0xD on the host.
 	 */
 	__u32 region[1024];
-	__u32 extra[];
+	__DECLARE_FLEX_ARRAY(__u32, extra);
 };
 
 #define KVM_MAX_XCRS	16
@@ -566,7 +566,7 @@ struct kvm_pmu_event_filter {
 	__u32 fixed_counter_bitmap;
 	__u32 flags;
 	__u32 pad[4];
-	__u64 events[];
+	__DECLARE_FLEX_ARRAY(__u64, events);
 };
 
 #define KVM_PMU_EVENT_ALLOW 0
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 80364d4dbebb..3f0d8d3c3daf 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -11,6 +11,7 @@
 #include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/stddef.h>
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
@@ -542,7 +543,7 @@ struct kvm_coalesced_mmio {
 
 struct kvm_coalesced_mmio_ring {
 	__u32 first, last;
-	struct kvm_coalesced_mmio coalesced_mmio[];
+	__DECLARE_FLEX_ARRAY(struct kvm_coalesced_mmio, coalesced_mmio);
 };
 
 #define KVM_COALESCED_MMIO_MAX \
@@ -592,7 +593,7 @@ struct kvm_clear_dirty_log {
 /* for KVM_SET_SIGNAL_MASK */
 struct kvm_signal_mask {
 	__u32 len;
-	__u8  sigset[];
+	__DECLARE_FLEX_ARRAY(__u8, sigset);
 };
 
 /* for KVM_TPR_ACCESS_REPORTING */
@@ -1051,7 +1052,7 @@ struct kvm_irq_routing_entry {
 struct kvm_irq_routing {
 	__u32 nr;
 	__u32 flags;
-	struct kvm_irq_routing_entry entries[];
+	__DECLARE_FLEX_ARRAY(struct kvm_irq_routing_entry, entries);
 };
 
 #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
@@ -1142,7 +1143,7 @@ struct kvm_dirty_tlb {
 
 struct kvm_reg_list {
 	__u64 n; /* number of regs */
-	__u64 reg[];
+	__DECLARE_FLEX_ARRAY(__u64, reg);
 };
 
 struct kvm_one_reg {
@@ -1608,7 +1609,7 @@ struct kvm_stats_desc {
 #ifdef __KERNEL__
 	char name[KVM_STATS_NAME_SIZE];
 #else
-	char name[];
+	__DECLARE_FLEX_ARRAY(char, name);
 #endif
 };
 
-- 
cgit v1.2.3


From e1d9a66889867c232657a9b6f25d451d7c3ab96f Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Feb 2026 18:07:25 +0100
Subject: Bluetooth: LE L2CAP: Disconnect if received packet's SDU exceeds IMTU

Core 6.0, Vol 3, Part A, 3.4.3:
"If the SDU length field value exceeds the receiver's MTU, the receiver
shall disconnect the channel..."

This fixes L2CAP/LE/CFC/BV-26-C (running together with 'l2test -r -P
0x0027 -V le_public -I 100').

Fixes: aac23bf63659 ("Bluetooth: Implement LE L2CAP reassembly")
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ad98db9632fd..3056dcd5fa2f 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6662,8 +6662,10 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		return -ENOBUFS;
 	}
 
-	if (chan->imtu < skb->len) {
-		BT_ERR("Too big LE L2CAP PDU");
+	if (skb->len > chan->imtu) {
+		BT_ERR("Too big LE L2CAP PDU: len %u > %u", skb->len,
+		       chan->imtu);
+		l2cap_send_disconn_req(chan, ECONNRESET);
 		return -ENOBUFS;
 	}
 
@@ -6689,7 +6691,9 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		       sdu_len, skb->len, chan->imtu);
 
 		if (sdu_len > chan->imtu) {
-			BT_ERR("Too big LE L2CAP SDU length received");
+			BT_ERR("Too big LE L2CAP SDU length: len %u > %u",
+			       skb->len, sdu_len);
+			l2cap_send_disconn_req(chan, ECONNRESET);
 			err = -EMSGSIZE;
 			goto failed;
 		}
-- 
cgit v1.2.3


From b6a2bf43aa37670432843bc73ae2a6288ba4d6f8 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Feb 2026 18:07:27 +0100
Subject: Bluetooth: LE L2CAP: Disconnect if sum of payload sizes exceed SDU

Core 6.0, Vol 3, Part A, 3.4.3:
"... If the sum of the payload sizes for the K-frames exceeds the
specified SDU length, the receiver shall disconnect the channel."

This fixes L2CAP/LE/CFC/BV-27-C (running together with 'l2test -r -P
0x0027 -V le_public').

Fixes: aac23bf63659 ("Bluetooth: Implement LE L2CAP reassembly")
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 3056dcd5fa2f..0f400051f093 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6729,6 +6729,7 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 
 	if (chan->sdu->len + skb->len > chan->sdu_len) {
 		BT_ERR("Too much LE L2CAP data received");
+		l2cap_send_disconn_req(chan, ECONNRESET);
 		err = -EINVAL;
 		goto failed;
 	}
-- 
cgit v1.2.3


From 0e4d4dcc1a6e82cc6f9abf32193558efa7e1613d Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Feb 2026 18:07:28 +0100
Subject: Bluetooth: SMP: make SM/PER/KDU/BI-04-C happy

The last test step ("Test with Invalid public key X and Y, all set to
0") expects to get an "DHKEY check failed" instead of "unspecified".

Fixes: 6d19628f539f ("Bluetooth: SMP: Fail if remote and local public keys are identical")
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/smp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index e67bf7b34ea7..485e3468bd26 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2743,7 +2743,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (!test_bit(SMP_FLAG_DEBUG_KEY, &smp->flags) &&
 	    !crypto_memneq(key, smp->local_pk, 64)) {
 		bt_dev_err(hdev, "Remote and local public keys are identical");
-		return SMP_UNSPECIFIED;
+		return SMP_DHKEY_CHECK_FAILED;
 	}
 
 	memcpy(smp->remote_pk, key, 64);
-- 
cgit v1.2.3


From 62bcaa6b351b6dc400f6c6b83762001fd9f5c12d Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 27 Feb 2026 15:23:01 -0500
Subject: Bluetooth: ISO: Fix defer tests being unstable

iso-tester defer tests seem to fail with hci_conn_hash_lookup_cig
being unable to resolve a cig in set_cig_params_sync due a race
where it is run immediatelly before hci_bind_cis is able to set
the QoS settings into the hci_conn object.

So this moves the assigning of the QoS settings to be done directly
by hci_le_set_cig_params to prevent that from happening again.

Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 4719dac07190..6eb59e9f2aa8 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1944,6 +1944,8 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos)
 		return false;
 
 done:
+	conn->iso_qos = *qos;
+
 	if (hci_cmd_sync_queue(hdev, set_cig_params_sync,
 			       UINT_PTR(qos->ucast.cig), NULL) < 0)
 		return false;
@@ -2013,8 +2015,6 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 	}
 
 	hci_conn_hold(cis);
-
-	cis->iso_qos = *qos;
 	cis->state = BT_BOUND;
 
 	return cis;
-- 
cgit v1.2.3


From 2cabe7ff1001b7a197009cf50ba71701f9cbd354 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Thu, 5 Mar 2026 14:50:52 +0100
Subject: Bluetooth: hci_sync: Fix hci_le_create_conn_sync

While introducing hci_le_create_conn_sync the functionality
of hci_connect_le was ported to hci_le_create_conn_sync including
the disable of the scan before starting the connection.

When this code was run non synchronously the immediate call that was
setting the flag HCI_LE_SCAN_INTERRUPTED had an impact. Since the
completion handler for the LE_SCAN_DISABLE was not immediately called.
In the completion handler of the LE_SCAN_DISABLE event, this flag is
checked to set the state of the hdev to DISCOVERY_STOPPED.

With the synchronised approach the later setting of the
HCI_LE_SCAN_INTERRUPTED flag has not the same effect. The completion
handler would immediately fire in the LE_SCAN_DISABLE call, check for
the flag, which is then not yet set and do nothing.

To fix this issue and make the function call work as before, we move the
setting of the flag HCI_LE_SCAN_INTERRUPTED before disabling the scan.

Fixes: 8e8b92ee60de ("Bluetooth: hci_sync: Add hci_le_create_conn_sync")
Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 121dbc8208ec..3166914b0d6c 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -6627,8 +6627,8 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data)
 	 * state.
 	 */
 	if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
-		hci_scan_disable_sync(hdev);
 		hci_dev_set_flag(hdev, HCI_LE_SCAN_INTERRUPTED);
+		hci_scan_disable_sync(hdev);
 	}
 
 	/* Update random address, but set require_privacy to false so
-- 
cgit v1.2.3


From 17f89341cb4281d1da0e2fb0de5406ab7c4e25ef Mon Sep 17 00:00:00 2001
From: Wang Tao <wangtao554@huawei.com>
Date: Fri, 27 Feb 2026 11:03:39 +0000
Subject: Bluetooth: MGMT: Fix list corruption and UAF in command complete
 handlers

Commit 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs") introduced
mgmt_pending_valid(), which not only validates the pending command but
also unlinks it from the pending list if it is valid. This change in
semantics requires updates to several completion handlers to avoid list
corruption and memory safety issues.

This patch addresses two left-over issues from the aforementioned rework:

1. In mgmt_add_adv_patterns_monitor_complete(), mgmt_pending_remove()
is replaced with mgmt_pending_free() in the success path. Since
mgmt_pending_valid() already unlinks the command at the beginning of
the function, calling mgmt_pending_remove() leads to a double list_del()
and subsequent list corruption/kernel panic.

2. In set_mesh_complete(), the use of mgmt_pending_foreach() in the error
path is removed. Since the current command is already unlinked by
mgmt_pending_valid(), this foreach loop would incorrectly target other
pending mesh commands, potentially freeing them while they are still being
processed concurrently (leading to UAFs). The redundant mgmt_cmd_status()
is also simplified to use cmd->opcode directly.

Fixes: 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs")
Signed-off-by: Wang Tao <wangtao554@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index a7238fd3b03b..d52238ce6a9a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2195,10 +2195,7 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err)
 	sk = cmd->sk;
 
 	if (status) {
-		mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER,
-				status);
-		mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true,
-				     cmd_status_rsp, &status);
+		mgmt_cmd_status(cmd->sk, hdev->id, cmd->opcode, status);
 		goto done;
 	}
 
@@ -5377,7 +5374,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev,
 
 	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 			  mgmt_status(status), &rp, sizeof(rp));
-	mgmt_pending_remove(cmd);
+	mgmt_pending_free(cmd);
 
 	hci_dev_unlock(hdev);
 	bt_dev_dbg(hdev, "add monitor %d complete, status %d",
-- 
cgit v1.2.3


From dbf666e4fc9bdd975a61bf682b3f75cb0145eedd Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 5 Mar 2026 10:17:47 -0500
Subject: Bluetooth: HIDP: Fix possible UAF

This fixes the following trace caused by not dropping l2cap_conn
reference when user->remove callback is called:

[   97.809249] l2cap_conn_free: freeing conn ffff88810a171c00
[   97.809907] CPU: 1 UID: 0 PID: 1419 Comm: repro_standalon Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy)
[   97.809935] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[   97.809947] Call Trace:
[   97.809954]  <TASK>
[   97.809961]  dump_stack_lvl (lib/dump_stack.c:122)
[   97.809990]  l2cap_conn_free (net/bluetooth/l2cap_core.c:1808)
[   97.810017]  l2cap_conn_del (./include/linux/kref.h:66 net/bluetooth/l2cap_core.c:1821 net/bluetooth/l2cap_core.c:1798)
[   97.810055]  l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7347 (discriminator 1) net/bluetooth/l2cap_core.c:7340 (discriminator 1))
[   97.810086]  ? __pfx_l2cap_disconn_cfm (net/bluetooth/l2cap_core.c:7341)
[   97.810117]  hci_conn_hash_flush (./include/net/bluetooth/hci_core.h:2152 (discriminator 2) net/bluetooth/hci_conn.c:2644 (discriminator 2))
[   97.810148]  hci_dev_close_sync (net/bluetooth/hci_sync.c:5360)
[   97.810180]  ? __pfx_hci_dev_close_sync (net/bluetooth/hci_sync.c:5285)
[   97.810212]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810242]  ? up_write (./arch/x86/include/asm/atomic64_64.h:87 (discriminator 5) ./include/linux/atomic/atomic-arch-fallback.h:2852 (discriminator 5) ./include/linux/atomic/atomic-long.h:268 (discriminator 5) ./include/linux/atomic/atomic-instrumented.h:3391 (discriminator 5) kernel/locking/rwsem.c:1385 (discriminator 5) kernel/locking/rwsem.c:1643 (discriminator 5))
[   97.810267]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810290]  ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752)
[   97.810320]  hci_unregister_dev (net/bluetooth/hci_core.c:504 net/bluetooth/hci_core.c:2716)
[   97.810346]  vhci_release (drivers/bluetooth/hci_vhci.c:691)
[   97.810375]  ? __pfx_vhci_release (drivers/bluetooth/hci_vhci.c:678)
[   97.810404]  __fput (fs/file_table.c:470)
[   97.810430]  task_work_run (kernel/task_work.c:235)
[   97.810451]  ? __pfx_task_work_run (kernel/task_work.c:201)
[   97.810472]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810495]  ? do_raw_spin_unlock (./include/asm-generic/qspinlock.h:128 (discriminator 5) kernel/locking/spinlock_debug.c:142 (discriminator 5))
[   97.810527]  do_exit (kernel/exit.c:972)
[   97.810547]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810574]  ? __pfx_do_exit (kernel/exit.c:897)
[   97.810594]  ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6))
[   97.810616]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810639]  ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4))
[   97.810664]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810688]  ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1))
[   97.810721]  do_group_exit (kernel/exit.c:1093)
[   97.810745]  get_signal (kernel/signal.c:3007 (discriminator 1))
[   97.810772]  ? security_file_permission (./arch/x86/include/asm/jump_label.h:37 security/security.c:2366)
[   97.810803]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810826]  ? vfs_read (fs/read_write.c:555)
[   97.810854]  ? __pfx_get_signal (kernel/signal.c:2800)
[   97.810880]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810905]  ? __pfx_vfs_read (fs/read_write.c:555)
[   97.810932]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.810960]  arch_do_signal_or_restart (arch/x86/kernel/signal.c:337 (discriminator 1))
[   97.810990]  ? __pfx_arch_do_signal_or_restart (arch/x86/kernel/signal.c:334)
[   97.811021]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.811055]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.811078]  ? ksys_read (fs/read_write.c:707)
[   97.811106]  ? __pfx_ksys_read (fs/read_write.c:707)
[   97.811137]  exit_to_user_mode_loop (kernel/entry/common.c:66 kernel/entry/common.c:98)
[   97.811169]  ? rcu_is_watching (./arch/x86/include/asm/atomic.h:23 ./include/linux/atomic/atomic-arch-fallback.h:457 ./include/linux/context_tracking.h:128 kernel/rcu/tree.c:752)
[   97.811192]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.811215]  ? trace_hardirqs_off (./include/trace/events/preemptirq.h:36 (discriminator 33) kernel/trace/trace_preemptirq.c:95 (discriminator 33) kernel/trace/trace_preemptirq.c:90 (discriminator 33))
[   97.811240]  do_syscall_64 (./include/linux/irq-entry-common.h:226 ./include/linux/irq-entry-common.h:256 ./include/linux/entry-common.h:325 arch/x86/entry/syscall_64.c:100)
[   97.811268]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   97.811292]  ? exc_page_fault (arch/x86/mm/fault.c:1480 (discriminator 3) arch/x86/mm/fault.c:1527 (discriminator 3))
[   97.811318]  entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
[   97.811338] RIP: 0033:0x445cfe
[   97.811352] Code: Unable to access opcode bytes at 0x445cd4.

Code starting with the faulting instruction
===========================================
[   97.811360] RSP: 002b:00007f65c41c6dc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[   97.811378] RAX: fffffffffffffe00 RBX: 00007f65c41c76c0 RCX: 0000000000445cfe
[   97.811391] RDX: 0000000000000400 RSI: 00007f65c41c6e40 RDI: 0000000000000004
[   97.811403] RBP: 00007f65c41c7250 R08: 0000000000000000 R09: 0000000000000000
[   97.811415] R10: 0000000000000000 R11: 0000000000000246 R12: ffffffffffffffe8
[   97.811428] R13: 0000000000000000 R14: 00007fff780a8c00 R15: 00007f65c41c76c0
[   97.811453]  </TASK>
[   98.402453] ==================================================================
[   98.403560] BUG: KASAN: use-after-free in __mutex_lock (kernel/locking/mutex.c:199 kernel/locking/mutex.c:694 kernel/locking/mutex.c:776)
[   98.404541] Read of size 8 at addr ffff888113ee40a8 by task khidpd_00050004/1430
[   98.405361]
[   98.405563] CPU: 1 UID: 0 PID: 1430 Comm: khidpd_00050004 Not tainted 7.0.0-rc1-dirty #14 PREEMPT(lazy)
[   98.405588] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[   98.405600] Call Trace:
[   98.405607]  <TASK>
[   98.405614]  dump_stack_lvl (lib/dump_stack.c:122)
[   98.405641]  print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
[   98.405667]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.405691]  ? __virt_addr_valid (arch/x86/mm/physaddr.c:55)
[   98.405724]  ? __mutex_lock (kernel/locking/mutex.c:199 kernel/locking/mutex.c:694 kernel/locking/mutex.c:776)
[   98.405748]  kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597)
[   98.405778]  ? __mutex_lock (kernel/locking/mutex.c:199 kernel/locking/mutex.c:694 kernel/locking/mutex.c:776)
[   98.405807]  __mutex_lock (kernel/locking/mutex.c:199 kernel/locking/mutex.c:694 kernel/locking/mutex.c:776)
[   98.405832]  ? do_raw_spin_lock (kernel/locking/spinlock_debug.c:95 (discriminator 4) kernel/locking/spinlock_debug.c:118 (discriminator 4))
[   98.405859]  ? l2cap_unregister_user (./include/linux/list.h:381 (discriminator 2) net/bluetooth/l2cap_core.c:1723 (discriminator 2))
[   98.405888]  ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114)
[   98.405915]  ? __pfx___mutex_lock (kernel/locking/mutex.c:775)
[   98.405939]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.405963]  ? lock_acquire (kernel/locking/lockdep.c:470 (discriminator 6) kernel/locking/lockdep.c:5870 (discriminator 6) kernel/locking/lockdep.c:5825 (discriminator 6))
[   98.405984]  ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1))
[   98.406015]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406038]  ? lock_release (kernel/locking/lockdep.c:5536 kernel/locking/lockdep.c:5889 kernel/locking/lockdep.c:5875)
[   98.406061]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406085]  ? _raw_spin_unlock_irqrestore (./arch/x86/include/asm/irqflags.h:42 ./arch/x86/include/asm/irqflags.h:119 ./arch/x86/include/asm/irqflags.h:159 ./include/linux/spinlock_api_smp.h:178 kernel/locking/spinlock.c:194)
[   98.406107]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406130]  ? __timer_delete_sync (kernel/time/timer.c:1592)
[   98.406158]  ? l2cap_unregister_user (./include/linux/list.h:381 (discriminator 2) net/bluetooth/l2cap_core.c:1723 (discriminator 2))
[   98.406186]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406210]  l2cap_unregister_user (./include/linux/list.h:381 (discriminator 2) net/bluetooth/l2cap_core.c:1723 (discriminator 2))
[   98.406263]  hidp_session_thread (./include/linux/instrumented.h:112 ./include/linux/atomic/atomic-instrumented.h:400 ./include/linux/refcount.h:389 ./include/linux/refcount.h:432 ./include/linux/refcount.h:450 ./include/linux/kref.h:64 net/bluetooth/hidp/core.c:996 net/bluetooth/hidp/core.c:1305)
[   98.406293]  ? __pfx_hidp_session_thread (net/bluetooth/hidp/core.c:1264)
[   98.406323]  ? kthread (kernel/kthread.c:433)
[   98.406340]  ? __pfx_hidp_session_wake_function (net/bluetooth/hidp/core.c:1251)
[   98.406370]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406393]  ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1))
[   98.406424]  ? __pfx_hidp_session_wake_function (net/bluetooth/hidp/core.c:1251)
[   98.406453]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406476]  ? trace_hardirqs_on (kernel/trace/trace_preemptirq.c:79 (discriminator 1))
[   98.406499]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406523]  ? kthread (kernel/kthread.c:433)
[   98.406539]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406565]  ? kthread (kernel/kthread.c:433)
[   98.406581]  ? __pfx_hidp_session_thread (net/bluetooth/hidp/core.c:1264)
[   98.406610]  kthread (kernel/kthread.c:467)
[   98.406627]  ? __pfx_kthread (kernel/kthread.c:412)
[   98.406645]  ret_from_fork (arch/x86/kernel/process.c:164)
[   98.406674]  ? __pfx_ret_from_fork (arch/x86/kernel/process.c:153)
[   98.406704]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.406728]  ? __pfx_kthread (kernel/kthread.c:412)
[   98.406747]  ret_from_fork_asm (arch/x86/entry/entry_64.S:258)
[   98.406774]  </TASK>
[   98.406780]
[   98.433693] The buggy address belongs to the physical page:
[   98.434405] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888113ee7c40 pfn:0x113ee4
[   98.435557] flags: 0x200000000000000(node=0|zone=2)
[   98.436198] raw: 0200000000000000 ffffea0004244308 ffff8881f6f3ebc0 0000000000000000
[   98.437195] raw: ffff888113ee7c40 0000000000000000 00000000ffffffff 0000000000000000
[   98.438115] page dumped because: kasan: bad access detected
[   98.438951]
[   98.439211] Memory state around the buggy address:
[   98.439871]  ffff888113ee3f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   98.440714]  ffff888113ee4000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[   98.441580] >ffff888113ee4080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[   98.442458]                                   ^
[   98.443011]  ffff888113ee4100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[   98.443889]  ffff888113ee4180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
[   98.444768] ==================================================================
[   98.445719] Disabling lock debugging due to kernel taint
[   98.448074] l2cap_conn_free: freeing conn ffff88810c22b400
[   98.450012] CPU: 1 UID: 0 PID: 1430 Comm: khidpd_00050004 Tainted: G    B               7.0.0-rc1-dirty #14 PREEMPT(lazy)
[   98.450040] Tainted: [B]=BAD_PAGE
[   98.450047] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
[   98.450059] Call Trace:
[   98.450065]  <TASK>
[   98.450071]  dump_stack_lvl (lib/dump_stack.c:122)
[   98.450099]  l2cap_conn_free (net/bluetooth/l2cap_core.c:1808)
[   98.450125]  l2cap_conn_put (net/bluetooth/l2cap_core.c:1822)
[   98.450154]  session_free (net/bluetooth/hidp/core.c:990)
[   98.450181]  hidp_session_thread (net/bluetooth/hidp/core.c:1307)
[   98.450213]  ? __pfx_hidp_session_thread (net/bluetooth/hidp/core.c:1264)
[   98.450271]  ? kthread (kernel/kthread.c:433)
[   98.450293]  ? __pfx_hidp_session_wake_function (net/bluetooth/hidp/core.c:1251)
[   98.450339]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.450368]  ? find_held_lock (kernel/locking/lockdep.c:5350 (discriminator 1))
[   98.450406]  ? __pfx_hidp_session_wake_function (net/bluetooth/hidp/core.c:1251)
[   98.450442]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.450471]  ? trace_hardirqs_on (kernel/trace/trace_preemptirq.c:79 (discriminator 1))
[   98.450499]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.450528]  ? kthread (kernel/kthread.c:433)
[   98.450547]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.450578]  ? kthread (kernel/kthread.c:433)
[   98.450598]  ? __pfx_hidp_session_thread (net/bluetooth/hidp/core.c:1264)
[   98.450637]  kthread (kernel/kthread.c:467)
[   98.450657]  ? __pfx_kthread (kernel/kthread.c:412)
[   98.450680]  ret_from_fork (arch/x86/kernel/process.c:164)
[   98.450715]  ? __pfx_ret_from_fork (arch/x86/kernel/process.c:153)
[   98.450752]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[   98.450782]  ? __pfx_kthread (kernel/kthread.c:412)
[   98.450804]  ret_from_fork_asm (arch/x86/entry/entry_64.S:258)
[   98.450836]  </TASK>

Fixes: b4f34d8d9d26 ("Bluetooth: hidp: add new session-management helpers")
Reported-by: soufiane el hachmi <kilwa10@gmail.com>
Tested-by: soufiane el hachmi <kilwa10@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hidp/core.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 6fe815241b01..7bcf8c5ceaee 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -986,7 +986,8 @@ static void session_free(struct kref *ref)
 	skb_queue_purge(&session->intr_transmit);
 	fput(session->intr_sock->file);
 	fput(session->ctrl_sock->file);
-	l2cap_conn_put(session->conn);
+	if (session->conn)
+		l2cap_conn_put(session->conn);
 	kfree(session);
 }
 
@@ -1164,6 +1165,15 @@ static void hidp_session_remove(struct l2cap_conn *conn,
 
 	down_write(&hidp_session_sem);
 
+	/* Drop L2CAP reference immediately to indicate that
+	 * l2cap_unregister_user() shall not be called as it is already
+	 * considered removed.
+	 */
+	if (session->conn) {
+		l2cap_conn_put(session->conn);
+		session->conn = NULL;
+	}
+
 	hidp_session_terminate(session);
 
 	cancel_work_sync(&session->dev_init);
@@ -1301,7 +1311,9 @@ static int hidp_session_thread(void *arg)
 	 * Instead, this call has the same semantics as if user-space tried to
 	 * delete the session.
 	 */
-	l2cap_unregister_user(session->conn, &session->user);
+	if (session->conn)
+		l2cap_unregister_user(session->conn, &session->user);
+
 	hidp_session_put(session);
 
 	module_put_and_kthread_exit(0);
-- 
cgit v1.2.3


From 752a6c9596dd25efd6978a73ff21f3b592668f4a Mon Sep 17 00:00:00 2001
From: Shaurya Rane <ssrane_b23@ee.vjti.ac.in>
Date: Thu, 6 Nov 2025 23:50:16 +0530
Subject: Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user

After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in
hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to
conn->users. However, l2cap_register_user() and l2cap_unregister_user()
don't use conn->lock, creating a race condition where these functions can
access conn->users and conn->hchan concurrently with l2cap_conn_del().

This can lead to use-after-free and list corruption bugs, as reported
by syzbot.

Fix this by changing l2cap_register_user() and l2cap_unregister_user()
to use conn->lock instead of hci_dev_lock(), ensuring consistent locking
for the l2cap_conn structure.

Reported-by: syzbot+14b6d57fb728e27ce23c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=14b6d57fb728e27ce23c
Fixes: ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del")
Signed-off-by: Shaurya Rane <ssrane_b23@ee.vjti.ac.in>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 0f400051f093..780136e18aae 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1678,17 +1678,15 @@ static void l2cap_info_timeout(struct work_struct *work)
 
 int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user)
 {
-	struct hci_dev *hdev = conn->hcon->hdev;
 	int ret;
 
 	/* We need to check whether l2cap_conn is registered. If it is not, we
-	 * must not register the l2cap_user. l2cap_conn_del() is unregisters
-	 * l2cap_conn objects, but doesn't provide its own locking. Instead, it
-	 * relies on the parent hci_conn object to be locked. This itself relies
-	 * on the hci_dev object to be locked. So we must lock the hci device
-	 * here, too. */
+	 * must not register the l2cap_user. l2cap_conn_del() unregisters
+	 * l2cap_conn objects under conn->lock, and we use the same lock here
+	 * to protect access to conn->users and conn->hchan.
+	 */
 
-	hci_dev_lock(hdev);
+	mutex_lock(&conn->lock);
 
 	if (!list_empty(&user->list)) {
 		ret = -EINVAL;
@@ -1709,16 +1707,14 @@ int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user)
 	ret = 0;
 
 out_unlock:
-	hci_dev_unlock(hdev);
+	mutex_unlock(&conn->lock);
 	return ret;
 }
 EXPORT_SYMBOL(l2cap_register_user);
 
 void l2cap_unregister_user(struct l2cap_conn *conn, struct l2cap_user *user)
 {
-	struct hci_dev *hdev = conn->hcon->hdev;
-
-	hci_dev_lock(hdev);
+	mutex_lock(&conn->lock);
 
 	if (list_empty(&user->list))
 		goto out_unlock;
@@ -1727,7 +1723,7 @@ void l2cap_unregister_user(struct l2cap_conn *conn, struct l2cap_user *user)
 	user->remove(conn, user);
 
 out_unlock:
-	hci_dev_unlock(hdev);
+	mutex_unlock(&conn->lock);
 }
 EXPORT_SYMBOL(l2cap_unregister_user);
 
-- 
cgit v1.2.3


From 5b3e2052334f2ff6d5200e952f4aa66994d09899 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 3 Mar 2026 13:29:53 -0500
Subject: Bluetooth: L2CAP: Fix accepting multiple L2CAP_ECRED_CONN_REQ

Currently the code attempts to accept requests regardless of the
command identifier which may cause multiple requests to be marked
as pending (FLAG_DEFER_SETUP) which can cause more than
L2CAP_ECRED_MAX_CID(5) to be allocated in l2cap_ecred_rsp_defer
causing an overflow.

The spec is quite clear that the same identifier shall not be used on
subsequent requests:

'Within each signaling channel a different Identifier shall be used
for each successive request or indication.'
https://www.bluetooth.com/wp-content/uploads/Files/Specification/HTML/Core-62/out/en/host/logical-link-control-and-adaptation-protocol-specification.html#UUID-32a25a06-4aa4-c6c7-77c5-dcfe3682355d

So this attempts to check if there are any channels pending with the
same identifier and rejects if any are found.

Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 780136e18aae..9d5b8d4d375a 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5055,7 +5055,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	u16 mtu, mps;
 	__le16 psm;
 	u8 result, rsp_len = 0;
-	int i, num_scid;
+	int i, num_scid = 0;
 	bool defer = false;
 
 	if (!enable_ecred)
@@ -5068,6 +5068,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 		goto response;
 	}
 
+	/* Check if there are no pending channels with the same ident */
+	__l2cap_chan_list_id(conn, cmd->ident, l2cap_ecred_list_defer,
+			     &num_scid);
+	if (num_scid) {
+		result = L2CAP_CR_LE_INVALID_PARAMS;
+		goto response;
+	}
+
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
 
-- 
cgit v1.2.3


From 15145675690cab2de1056e7ed68e59cbd0452529 Mon Sep 17 00:00:00 2001
From: Lukas Johannes Möller <research@johannes-moeller.dev>
Date: Tue, 10 Mar 2026 21:59:46 +0000
Subject: Bluetooth: L2CAP: Fix type confusion in l2cap_ecred_reconf_rsp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

l2cap_ecred_reconf_rsp() casts the incoming data to struct
l2cap_ecred_conn_rsp (the ECRED *connection* response, 8 bytes with
result at offset 6) instead of struct l2cap_ecred_reconf_rsp (2 bytes
with result at offset 0).

This causes two problems:

 - The sizeof(*rsp) length check requires 8 bytes instead of the
   correct 2, so valid L2CAP_ECRED_RECONF_RSP packets are rejected
   with -EPROTO.

 - rsp->result reads from offset 6 instead of offset 0, returning
   wrong data when the packet is large enough to pass the check.

Fix by using the correct type.  Also pass the already byte-swapped
result variable to BT_DBG instead of the raw __le16 field.

Fixes: 15f02b910562 ("Bluetooth: L2CAP: Add initial code for Enhanced Credit Based Mode")
Cc: stable@vger.kernel.org
Signed-off-by: Lukas Johannes Möller <research@johannes-moeller.dev>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 9d5b8d4d375a..08a12515bfed 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5428,7 +5428,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn,
 					 u8 *data)
 {
 	struct l2cap_chan *chan, *tmp;
-	struct l2cap_ecred_conn_rsp *rsp = (void *) data;
+	struct l2cap_ecred_reconf_rsp *rsp = (void *)data;
 	u16 result;
 
 	if (cmd_len < sizeof(*rsp))
@@ -5436,7 +5436,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn,
 
 	result = __le16_to_cpu(rsp->result);
 
-	BT_DBG("result 0x%4.4x", rsp->result);
+	BT_DBG("result 0x%4.4x", result);
 
 	if (!result)
 		return 0;
-- 
cgit v1.2.3


From dd815e6e3918dc75a49aaabac36e4f024d675101 Mon Sep 17 00:00:00 2001
From: Lukas Johannes Möller <research@johannes-moeller.dev>
Date: Tue, 10 Mar 2026 21:59:47 +0000
Subject: Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before
 access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

l2cap_information_rsp() checks that cmd_len covers the fixed
l2cap_info_rsp header (type + result, 4 bytes) but then reads
rsp->data without verifying that the payload is present:

 - L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads
   4 bytes past the header (needs cmd_len >= 8).

 - L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header
   (needs cmd_len >= 5).

A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an
out-of-bounds read of adjacent skb data.

Guard each data access with the required payload length check.  If the
payload is too short, skip the read and let the state machine complete
with safe defaults (feat_mask and remote_fixed_chan remain zero from
kzalloc), so the info timer cleanup and l2cap_conn_start() still run
and the connection is not stalled.

Fixes: 4e8402a3f884 ("[Bluetooth] Retrieve L2CAP features mask on connection setup")
Cc: stable@vger.kernel.org
Signed-off-by: Lukas Johannes Möller <research@johannes-moeller.dev>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 08a12515bfed..5deb6c4f1e41 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4612,7 +4612,8 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn,
 
 	switch (type) {
 	case L2CAP_IT_FEAT_MASK:
-		conn->feat_mask = get_unaligned_le32(rsp->data);
+		if (cmd_len >= sizeof(*rsp) + sizeof(u32))
+			conn->feat_mask = get_unaligned_le32(rsp->data);
 
 		if (conn->feat_mask & L2CAP_FEAT_FIXED_CHAN) {
 			struct l2cap_info_req req;
@@ -4631,7 +4632,8 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn,
 		break;
 
 	case L2CAP_IT_FIXED_CHAN:
-		conn->remote_fixed_chan = rsp->data[0];
+		if (cmd_len >= sizeof(*rsp) + sizeof(rsp->data[0]))
+			conn->remote_fixed_chan = rsp->data[0];
 		conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE;
 		conn->info_ident = 0;
 
-- 
cgit v1.2.3


From 99b2c531e0e797119ae1b9195a8764ee98b00e65 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Wed, 11 Mar 2026 01:02:57 +0200
Subject: Bluetooth: qca: fix ROM version reading on WCN3998 chips

WCN3998 uses a bit different format for rom version:

[    5.479978] Bluetooth: hci0: setting up wcn399x
[    5.633763] Bluetooth: hci0: QCA Product ID   :0x0000000a
[    5.645350] Bluetooth: hci0: QCA SOC Version  :0x40010224
[    5.650906] Bluetooth: hci0: QCA ROM Version  :0x00001001
[    5.665173] Bluetooth: hci0: QCA Patch Version:0x00006699
[    5.679356] Bluetooth: hci0: QCA controller version 0x02241001
[    5.691109] Bluetooth: hci0: QCA Downloading qca/crbtfw21.tlv
[    6.680102] Bluetooth: hci0: QCA Downloading qca/crnv21.bin
[    6.842948] Bluetooth: hci0: QCA setup on UART is completed

Fixes: 523760b7ff88 ("Bluetooth: hci_qca: Added support for WCN3998")
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 74f820e89655..3b0626920193 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -787,6 +787,8 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	 */
 	if (soc_type == QCA_WCN3988)
 		rom_ver = ((soc_ver & 0x00000f00) >> 0x05) | (soc_ver & 0x0000000f);
+	else if (soc_type == QCA_WCN3998)
+		rom_ver = ((soc_ver & 0x0000f000) >> 0x07) | (soc_ver & 0x0000000f);
 	else
 		rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f);
 
-- 
cgit v1.2.3


From e5b31d988a41549037b8d8721a3c3cae893d8670 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 11 Mar 2026 05:40:40 +0000
Subject: af_unix: Give up GC if MSG_PEEK intervened.

Igor Ushakov reported that GC purged the receive queue of
an alive socket due to a race with MSG_PEEK with a nice repro.

This is the exact same issue previously fixed by commit
cbcf01128d0a ("af_unix: fix garbage collect vs MSG_PEEK").

After GC was replaced with the current algorithm, the cited
commit removed the locking dance in unix_peek_fds() and
reintroduced the same issue.

The problem is that MSG_PEEK bumps a file refcount without
interacting with GC.

Consider an SCC containing sk-A and sk-B, where sk-A is
close()d but can be recv()ed via sk-B.

The bad thing happens if sk-A is recv()ed with MSG_PEEK from
sk-B and sk-B is close()d while GC is checking unix_vertex_dead()
for sk-A and sk-B.

  GC thread                    User thread
  ---------                    -----------
  unix_vertex_dead(sk-A)
  -> true   <------.
                    \
                     `------   recv(sk-B, MSG_PEEK)
              invalidate !!    -> sk-A's file refcount : 1 -> 2

                               close(sk-B)
                               -> sk-B's file refcount : 2 -> 1
  unix_vertex_dead(sk-B)
  -> true

Initially, sk-A's file refcount is 1 by the inflight fd in sk-B
recvq.  GC thinks sk-A is dead because the file refcount is the
same as the number of its inflight fds.

However, sk-A's file refcount is bumped silently by MSG_PEEK,
which invalidates the previous evaluation.

At this moment, sk-B's file refcount is 2; one by the open fd,
and one by the inflight fd in sk-A.  The subsequent close()
releases one refcount by the former.

Finally, GC incorrectly concludes that both sk-A and sk-B are dead.

One option is to restore the locking dance in unix_peek_fds(),
but we can resolve this more elegantly thanks to the new algorithm.

The point is that the issue does not occur without the subsequent
close() and we actually do not need to synchronise MSG_PEEK with
the dead SCC detection.

When the issue occurs, close() and GC touch the same file refcount.
If GC sees the refcount being decremented by close(), it can just
give up garbage-collecting the SCC.

Therefore, we only need to signal the race during MSG_PEEK with
a proper memory barrier to make it visible to the GC.

Let's use seqcount_t to notify GC when MSG_PEEK occurs and let
it defer the SCC to the next run.

This way no locking is needed on the MSG_PEEK side, and we can
avoid imposing a penalty on every MSG_PEEK unnecessarily.

Note that we can retry within unix_scc_dead() if MSG_PEEK is
detected, but we do not do so to avoid hung task splat from
abusive MSG_PEEK calls.

Fixes: 118f457da9ed ("af_unix: Remove lock dance in unix_peek_fds().")
Reported-by: Igor Ushakov <sysroot314@gmail.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260311054043.1231316-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c |  2 ++
 net/unix/af_unix.h |  1 +
 net/unix/garbage.c | 79 +++++++++++++++++++++++++++++++++++-------------------
 3 files changed, 54 insertions(+), 28 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7eaa5b187fef..b23c33df8b46 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1958,6 +1958,8 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
 static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
 	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+
+	unix_peek_fpl(scm->fp);
 }
 
 static void unix_destruct_scm(struct sk_buff *skb)
diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h
index c4f1b2da363d..8119dbeef3a3 100644
--- a/net/unix/af_unix.h
+++ b/net/unix/af_unix.h
@@ -29,6 +29,7 @@ void unix_del_edges(struct scm_fp_list *fpl);
 void unix_update_edges(struct unix_sock *receiver);
 int unix_prepare_fpl(struct scm_fp_list *fpl);
 void unix_destroy_fpl(struct scm_fp_list *fpl);
+void unix_peek_fpl(struct scm_fp_list *fpl);
 void unix_schedule_gc(struct user_struct *user);
 
 /* SOCK_DIAG */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 816e8fa2b062..a7967a345827 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -318,6 +318,25 @@ void unix_destroy_fpl(struct scm_fp_list *fpl)
 	unix_free_vertices(fpl);
 }
 
+static bool gc_in_progress;
+static seqcount_t unix_peek_seq = SEQCNT_ZERO(unix_peek_seq);
+
+void unix_peek_fpl(struct scm_fp_list *fpl)
+{
+	static DEFINE_SPINLOCK(unix_peek_lock);
+
+	if (!fpl || !fpl->count_unix)
+		return;
+
+	if (!READ_ONCE(gc_in_progress))
+		return;
+
+	/* Invalidate the final refcnt check in unix_vertex_dead(). */
+	spin_lock(&unix_peek_lock);
+	raw_write_seqcount_barrier(&unix_peek_seq);
+	spin_unlock(&unix_peek_lock);
+}
+
 static bool unix_vertex_dead(struct unix_vertex *vertex)
 {
 	struct unix_edge *edge;
@@ -351,6 +370,36 @@ static bool unix_vertex_dead(struct unix_vertex *vertex)
 	return true;
 }
 
+static LIST_HEAD(unix_visited_vertices);
+static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2;
+
+static bool unix_scc_dead(struct list_head *scc, bool fast)
+{
+	struct unix_vertex *vertex;
+	bool scc_dead = true;
+	unsigned int seq;
+
+	seq = read_seqcount_begin(&unix_peek_seq);
+
+	list_for_each_entry_reverse(vertex, scc, scc_entry) {
+		/* Don't restart DFS from this vertex. */
+		list_move_tail(&vertex->entry, &unix_visited_vertices);
+
+		/* Mark vertex as off-stack for __unix_walk_scc(). */
+		if (!fast)
+			vertex->index = unix_vertex_grouped_index;
+
+		if (scc_dead)
+			scc_dead = unix_vertex_dead(vertex);
+	}
+
+	/* If MSG_PEEK intervened, defer this SCC to the next round. */
+	if (read_seqcount_retry(&unix_peek_seq, seq))
+		return false;
+
+	return scc_dead;
+}
+
 static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist)
 {
 	struct unix_vertex *vertex;
@@ -404,9 +453,6 @@ static bool unix_scc_cyclic(struct list_head *scc)
 	return false;
 }
 
-static LIST_HEAD(unix_visited_vertices);
-static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2;
-
 static unsigned long __unix_walk_scc(struct unix_vertex *vertex,
 				     unsigned long *last_index,
 				     struct sk_buff_head *hitlist)
@@ -474,9 +520,7 @@ prev_vertex:
 	}
 
 	if (vertex->index == vertex->scc_index) {
-		struct unix_vertex *v;
 		struct list_head scc;
-		bool scc_dead = true;
 
 		/* SCC finalised.
 		 *
@@ -485,18 +529,7 @@ prev_vertex:
 		 */
 		__list_cut_position(&scc, &vertex_stack, &vertex->scc_entry);
 
-		list_for_each_entry_reverse(v, &scc, scc_entry) {
-			/* Don't restart DFS from this vertex in unix_walk_scc(). */
-			list_move_tail(&v->entry, &unix_visited_vertices);
-
-			/* Mark vertex as off-stack. */
-			v->index = unix_vertex_grouped_index;
-
-			if (scc_dead)
-				scc_dead = unix_vertex_dead(v);
-		}
-
-		if (scc_dead) {
+		if (unix_scc_dead(&scc, false)) {
 			unix_collect_skb(&scc, hitlist);
 		} else {
 			if (unix_vertex_max_scc_index < vertex->scc_index)
@@ -550,19 +583,11 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist)
 	while (!list_empty(&unix_unvisited_vertices)) {
 		struct unix_vertex *vertex;
 		struct list_head scc;
-		bool scc_dead = true;
 
 		vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry);
 		list_add(&scc, &vertex->scc_entry);
 
-		list_for_each_entry_reverse(vertex, &scc, scc_entry) {
-			list_move_tail(&vertex->entry, &unix_visited_vertices);
-
-			if (scc_dead)
-				scc_dead = unix_vertex_dead(vertex);
-		}
-
-		if (scc_dead) {
+		if (unix_scc_dead(&scc, true)) {
 			cyclic_sccs--;
 			unix_collect_skb(&scc, hitlist);
 		}
@@ -577,8 +602,6 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist)
 		   cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC);
 }
 
-static bool gc_in_progress;
-
 static void unix_gc(struct work_struct *work)
 {
 	struct sk_buff_head hitlist;
-- 
cgit v1.2.3


From 39ebc8d7f561e1b64eca87353ef9b18e2825e591 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:41 +0000
Subject: lib/bootconfig: fix off-by-one in xbc_verify_tree() unclosed brace
 error

__xbc_open_brace() pushes entries with post-increment
(open_brace[brace_index++]), so brace_index always points one past
the last valid entry.  xbc_verify_tree() reads open_brace[brace_index]
to report which brace is unclosed, but this is one past the last
pushed entry and contains stale/zero data, causing the error message
to reference the wrong node.

Use open_brace[brace_index - 1] to correctly identify the unclosed
brace.  brace_index is known to be > 0 here since we are inside the
if (brace_index) guard.

Link: https://lore.kernel.org/all/20260312191143.28719-2-objecting@objecting.org/

Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 449369a60846..ce25714351d5 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -802,7 +802,7 @@ static int __init xbc_verify_tree(void)
 
 	/* Brace closing */
 	if (brace_index) {
-		n = &xbc_nodes[open_brace[brace_index]];
+		n = &xbc_nodes[open_brace[brace_index - 1]];
 		return xbc_parse_error("Brace is not closed",
 					xbc_node_get_data(n));
 	}
-- 
cgit v1.2.3


From 3715a00855316066cdda69d43648336367422127 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Wed, 11 Mar 2026 03:18:09 +0900
Subject: bridge: cfm: Fix race condition in peer_mep deletion

When a peer MEP is being deleted, cancel_delayed_work_sync() is called
on ccm_rx_dwork before freeing. However, br_cfm_frame_rx() runs in
softirq context under rcu_read_lock (without RTNL) and can re-schedule
ccm_rx_dwork via ccm_rx_timer_start() between cancel_delayed_work_sync()
returning and kfree_rcu() being called.

The following is a simple race scenario:

           cpu0                                     cpu1

mep_delete_implementation()
  cancel_delayed_work_sync(ccm_rx_dwork);
                                           br_cfm_frame_rx()
                                             // peer_mep still in hlist
                                             if (peer_mep->ccm_defect)
                                               ccm_rx_timer_start()
                                                 queue_delayed_work(ccm_rx_dwork)
  hlist_del_rcu(&peer_mep->head);
  kfree_rcu(peer_mep, rcu);
                                           ccm_rx_work_expired()
                                             // on freed peer_mep

To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync() in both peer MEP deletion paths, so
that subsequent queue_delayed_work() calls from br_cfm_frame_rx()
are silently rejected.

The cc_peer_disable() helper retains cancel_delayed_work_sync()
because it is also used for the CC enable/disable toggle path where
the work must remain re-schedulable.

Fixes: dc32cbb3dbd7 ("bridge: cfm: Kernel space implementation of CFM. CCM frame RX added.")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/abBgYT5K_FI9rD1a@v4bel
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_cfm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c
index 2c70fe47de38..118c7ea48c35 100644
--- a/net/bridge/br_cfm.c
+++ b/net/bridge/br_cfm.c
@@ -576,7 +576,7 @@ static void mep_delete_implementation(struct net_bridge *br,
 
 	/* Empty and free peer MEP list */
 	hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) {
-		cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+		disable_delayed_work_sync(&peer_mep->ccm_rx_dwork);
 		hlist_del_rcu(&peer_mep->head);
 		kfree_rcu(peer_mep, rcu);
 	}
@@ -732,7 +732,7 @@ int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
 		return -ENOENT;
 	}
 
-	cc_peer_disable(peer_mep);
+	disable_delayed_work_sync(&peer_mep->ccm_rx_dwork);
 
 	hlist_del_rcu(&peer_mep->head);
 	kfree_rcu(peer_mep, rcu);
-- 
cgit v1.2.3


From e1f0a18c9564cdb16523c802e2c6fe5874e3d944 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Wed, 11 Mar 2026 15:06:02 +0800
Subject: net/rose: fix NULL pointer dereference in rose_transmit_link on
 reconnect

syzkaller reported a bug [1], and the reproducer is available at [2].

ROSE sockets use four sk->sk_state values: TCP_CLOSE, TCP_LISTEN,
TCP_SYN_SENT, and TCP_ESTABLISHED. rose_connect() already rejects
calls for TCP_ESTABLISHED (-EISCONN) and TCP_CLOSE with SS_CONNECTING
(-ECONNREFUSED), but lacks a check for TCP_SYN_SENT.

When rose_connect() is called a second time while the first connection
attempt is still in progress (TCP_SYN_SENT), it overwrites
rose->neighbour via rose_get_neigh(). If that returns NULL, the socket
is left with rose->state == ROSE_STATE_1 but rose->neighbour == NULL.
When the socket is subsequently closed, rose_release() sees
ROSE_STATE_1 and calls rose_write_internal() ->
rose_transmit_link(skb, NULL), causing a NULL pointer dereference.

Per connect(2), a second connect() while a connection is already in
progress should return -EALREADY. Add this missing check for
TCP_SYN_SENT to complete the state validation in rose_connect().

[1] https://syzkaller.appspot.com/bug?extid=d00f90e0af54102fb271
[2] https://gist.github.com/mrpre/9e6779e0d13e2c66779b1653fef80516

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+d00f90e0af54102fb271@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69694d6f.050a0220.58bed.0027.GAE@google.com/T/
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260311070611.76913-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rose/af_rose.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 841d62481048..ba56213e0a2a 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -811,6 +811,11 @@ static int rose_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int
 		goto out_release;
 	}
 
+	if (sk->sk_state == TCP_SYN_SENT) {
+		err = -EALREADY;
+		goto out_release;
+	}
+
 	sk->sk_state   = TCP_CLOSE;
 	sock->state = SS_UNCONNECTED;
 
-- 
cgit v1.2.3


From 8431c602f551549f082bbfa67f3003f2d8e3e132 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Mar 2026 12:31:10 +0000
Subject: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS

Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which
call iptunnel_xmit_stats().

iptunnel_xmit_stats() was assuming tunnels were only using
NETDEV_PCPU_STAT_TSTATS.

@syncp offset in pcpu_sw_netstats and pcpu_dstats is different.

32bit kernels would either have corruptions or freezes if the syncp
sequence was overwritten.

This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid
a potential cache line miss since iptunnel_xmit_stats() needs to read it.

Fixes: 6fa6de302246 ("geneve: Handle stats using NETDEV_PCPU_STAT_DSTATS.")
Fixes: be226352e8dc ("vxlan: Handle stats using NETDEV_PCPU_STAT_DSTATS.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20260311123110.1471930-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  3 +--
 include/net/ip_tunnels.h  | 30 +++++++++++++++++++++++-------
 2 files changed, 24 insertions(+), 9 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ae269a2e7f4d..d7aac6f185bc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2155,6 +2155,7 @@ struct net_device {
 	unsigned long		state;
 	unsigned int		flags;
 	unsigned short		hard_header_len;
+	enum netdev_stat_type	pcpu_stat_type:8;
 	netdev_features_t	features;
 	struct inet6_dev __rcu	*ip6_ptr;
 	__cacheline_group_end(net_device_read_txrx);
@@ -2404,8 +2405,6 @@ struct net_device {
 	void				*ml_priv;
 	enum netdev_ml_priv_type	ml_priv_type;
 
-	enum netdev_stat_type		pcpu_stat_type:8;
-
 #if IS_ENABLED(CONFIG_GARP)
 	struct garp_port __rcu	*garp_port;
 #endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 80662f812080..1f577a4f8ce9 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -665,13 +665,29 @@ static inline int iptunnel_pull_offloads(struct sk_buff *skb)
 static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 {
 	if (pkt_len > 0) {
-		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
-
-		u64_stats_update_begin(&tstats->syncp);
-		u64_stats_add(&tstats->tx_bytes, pkt_len);
-		u64_stats_inc(&tstats->tx_packets);
-		u64_stats_update_end(&tstats->syncp);
-		put_cpu_ptr(tstats);
+		if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) {
+			struct pcpu_dstats *dstats = get_cpu_ptr(dev->dstats);
+
+			u64_stats_update_begin(&dstats->syncp);
+			u64_stats_add(&dstats->tx_bytes, pkt_len);
+			u64_stats_inc(&dstats->tx_packets);
+			u64_stats_update_end(&dstats->syncp);
+			put_cpu_ptr(dstats);
+			return;
+		}
+		if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) {
+			struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
+
+			u64_stats_update_begin(&tstats->syncp);
+			u64_stats_add(&tstats->tx_bytes, pkt_len);
+			u64_stats_inc(&tstats->tx_packets);
+			u64_stats_update_end(&tstats->syncp);
+			put_cpu_ptr(tstats);
+			return;
+		}
+		pr_err_once("iptunnel_xmit_stats pcpu_stat_type=%d\n",
+			    dev->pcpu_stat_type);
+		WARN_ON_ONCE(1);
 		return;
 	}
 
-- 
cgit v1.2.3


From 99600f79b28c83c68bae199a3d8e95049a758308 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Wed, 11 Mar 2026 23:35:09 +0100
Subject: mpls: add missing unregister_netdevice_notifier to mpls_init

If mpls_init() fails after registering mpls_dev_notifier, it never
gets removed. Add the missing unregister_netdevice_notifier() call to
the error handling path.

Fixes: 5be2062e3080 ("mpls: Handle error of rtnl_register_module().")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/7c55363c4f743d19e2306204a134407c90a69bbb.1773228081.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mpls/af_mpls.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index ef9e749d5e08..d5417688f69e 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -2854,6 +2854,7 @@ out_unregister_rtnl_af:
 	rtnl_af_unregister(&mpls_af_ops);
 out_unregister_dev_type:
 	dev_remove_pack(&mpls_packet_type);
+	unregister_netdevice_notifier(&mpls_dev_notifier);
 out_unregister_pernet:
 	unregister_pernet_subsys(&mpls_net_ops);
 	goto out;
-- 
cgit v1.2.3


From 82f73ef9c41e0623e0a8bdce4fa44a7237709f0c Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Tue, 10 Mar 2026 13:51:24 +0530
Subject: powerpc/iommu: fix lockdep warning during PCI enumeration

Commit a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev()
helper") introduced iommu_driver_get_domain_for_dev() for driver
code paths that hold iommu_group->mutex while attaching a device
to an IOMMU domain.

The same commit also added a lockdep assertion in
iommu_get_domain_for_dev() to ensure that callers do not hold
iommu_group->mutex when invoking it.

On powerpc platforms, when PCI device ownership is switched from
BLOCKED to the PLATFORM domain, the attach callback
spapr_tce_platform_iommu_attach_dev() still calls
iommu_get_domain_for_dev(). This happens while iommu_group->mutex
is held during domain switching, which triggers the lockdep warning
below during PCI enumeration:

WARNING: drivers/iommu/iommu.c:2252 at iommu_get_domain_for_dev+0x38/0x80, CPU#2: swapper/0/1
Modules linked in:
CPU: 2 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc2+ #35 PREEMPT
Hardware name: IBM,9105-22A Power11 (architected) 0x820200 0xf000007 of:IBM,FW1120.00 (RB1120_115) hv:phyp pSeries
NIP:  c000000000c244c4 LR: c00000000005b5a4 CTR: c00000000005b578
REGS: c00000000a7bf280 TRAP: 0700   Not tainted  (7.0.0-rc2+)
MSR:  8000000002029033 <SF,VEC,EE,ME,IR,DR,RI,LE>  CR: 22004422  XER: 0000000a
CFAR: c000000000c24508 IRQMASK: 0
GPR00: c00000000005b5a4 c00000000a7bf520 c000000001dc8100 0000000000000001
GPR04: c00000000f972f10 0000000000000000 0000000000000000 0000000000000001
GPR08: 0000001ffbc60000 0000000000000001 0000000000000000 0000000000000000
GPR12: c00000000005b578 c000001fffffe480 c000000000011618 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
GPR20: ffffffffffffefff 0000000000000000 c000000002d30eb0 0000000000000001
GPR24: c0000000017881f8 0000000000000000 0000000000000001 c00000000f972e00
GPR28: c00000000bbba0d0 0000000000000000 c00000000bbba0d0 c00000000f972e00
NIP [c000000000c244c4] iommu_get_domain_for_dev+0x38/0x80
LR [c00000000005b5a4] spapr_tce_platform_iommu_attach_dev+0x2c/0x98
Call Trace:
 iommu_get_domain_for_dev+0x68/0x80 (unreliable)
 spapr_tce_platform_iommu_attach_dev+0x2c/0x98
 __iommu_attach_device+0x44/0x220
 __iommu_device_set_domain+0xf4/0x194
 __iommu_group_set_domain_internal+0xec/0x228
 iommu_setup_default_domain+0x5f4/0x6a4
 __iommu_probe_device+0x674/0x724
 iommu_probe_device+0x50/0xb4
 iommu_add_device+0x48/0x198
 pci_dma_dev_setup_pSeriesLP+0x198/0x4f0
 pcibios_bus_add_device+0x80/0x464
 pci_bus_add_device+0x40/0x100
 pci_bus_add_devices+0x54/0xb0
 pcibios_init+0xd8/0x140
 do_one_initcall+0x8c/0x598
 kernel_init_freeable+0x3ec/0x850
 kernel_init+0x34/0x270
 ret_from_kernel_user_thread+0x14/0x1c

Fix this by using iommu_driver_get_domain_for_dev() instead of
iommu_get_domain_for_dev() in spapr_tce_platform_iommu_attach_dev(),
which is the appropriate helper for callers holding the group mutex.

Cc: stable@vger.kernel.org
Fixes: a75b2be249d6 ("iommu: Add iommu_driver_get_domain_for_dev() helper")
Closes: https://patchwork.ozlabs.org/project/linuxppc-dev/patch/d5c834ff-4c95-44dd-8bef-57242d63aeee@linux.ibm.com/
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
[Maddy: Added Closes, tested and reviewed by tags]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260310082129.3630996-1-nilay@linux.ibm.com
---
 arch/powerpc/kernel/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0ce71310b7d9..d122e8447831 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1159,7 +1159,7 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 				    struct device *dev,
 				    struct iommu_domain *old)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_driver_get_domain_for_dev(dev);
 	struct iommu_table_group *table_group;
 	struct iommu_group *grp;
 
-- 
cgit v1.2.3


From 5eb608319bb56464674a71b4a66ea65c6c435d64 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <npitre@baylibre.com>
Date: Tue, 27 Jan 2026 17:56:01 -0500
Subject: vt: save/restore unicode screen buffer for alternate screen

The alternate screen support added by commit 23743ba64709 ("vt: add
support for smput/rmput escape codes") only saves and restores the
regular screen buffer (vc_origin), but completely ignores the corresponding
unicode screen buffer (vc_uni_lines) creating a messed-up display.

Add vc_saved_uni_lines to save the unicode screen buffer when entering
the alternate screen, and restore it when leaving. Also ensure proper
cleanup in reset_terminal() and vc_deallocate().

Fixes: 23743ba64709 ("vt: add support for smput/rmput escape codes")
Cc: stable <stable@kernel.org>
Signed-off-by: Nicolas Pitre <npitre@baylibre.com>
Link: https://patch.msgid.link/5o2p6qp3-91pq-0p17-or02-1oors4417ns7@onlyvoer.pbz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c            | 8 ++++++++
 include/linux/console_struct.h | 1 +
 2 files changed, 9 insertions(+)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index c1f152d8b03b..e2df99e3d458 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1339,6 +1339,8 @@ struct vc_data *vc_deallocate(unsigned int currcons)
 			kfree(vc->vc_saved_screen);
 			vc->vc_saved_screen = NULL;
 		}
+		vc_uniscr_free(vc->vc_saved_uni_lines);
+		vc->vc_saved_uni_lines = NULL;
 	}
 	return vc;
 }
@@ -1884,6 +1886,8 @@ static void enter_alt_screen(struct vc_data *vc)
 	vc->vc_saved_screen = kmemdup((u16 *)vc->vc_origin, size, GFP_KERNEL);
 	if (vc->vc_saved_screen == NULL)
 		return;
+	vc->vc_saved_uni_lines = vc->vc_uni_lines;
+	vc->vc_uni_lines = NULL;
 	vc->vc_saved_rows = vc->vc_rows;
 	vc->vc_saved_cols = vc->vc_cols;
 	save_cur(vc);
@@ -1905,6 +1909,8 @@ static void leave_alt_screen(struct vc_data *vc)
 		dest = ((u16 *)vc->vc_origin) + r * vc->vc_cols;
 		memcpy(dest, src, 2 * cols);
 	}
+	vc_uniscr_set(vc, vc->vc_saved_uni_lines);
+	vc->vc_saved_uni_lines = NULL;
 	restore_cur(vc);
 	/* Update the entire screen */
 	if (con_should_update(vc))
@@ -2227,6 +2233,8 @@ static void reset_terminal(struct vc_data *vc, int do_clear)
 	if (vc->vc_saved_screen != NULL) {
 		kfree(vc->vc_saved_screen);
 		vc->vc_saved_screen = NULL;
+		vc_uniscr_free(vc->vc_saved_uni_lines);
+		vc->vc_saved_uni_lines = NULL;
 		vc->vc_saved_rows = 0;
 		vc->vc_saved_cols = 0;
 	}
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 13b35637bd5a..d5ca855116df 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -160,6 +160,7 @@ struct vc_data {
 	struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */
 	u32 **vc_uni_lines;			/* unicode screen content */
 	u16		*vc_saved_screen;
+	u32		**vc_saved_uni_lines;
 	unsigned int	vc_saved_cols;
 	unsigned int	vc_saved_rows;
 	/* additional information is in vt_kern.h */
-- 
cgit v1.2.3


From 560f763baa0f2c9a44da4294c06af071405ac46f Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:42 +0000
Subject: lib/bootconfig: check bounds before writing in __xbc_open_brace()

The bounds check for brace_index happens after the array write.
While the current call pattern prevents an actual out-of-bounds
access (the previous call would have returned an error), the
write-before-check pattern is fragile and would become a real
out-of-bounds write if the error return were ever not propagated.

Move the bounds check before the array write so the function is
self-contained and safe regardless of caller behavior.

Link: https://lore.kernel.org/all/20260312191143.28719-3-objecting@objecting.org/

Fixes: ead1e19ad905 ("lib/bootconfig: Fix a bug of breaking existing tree nodes")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index ce25714351d5..9c3d59fb96ed 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -532,9 +532,9 @@ static char *skip_spaces_until_newline(char *p)
 static int __init __xbc_open_brace(char *p)
 {
 	/* Push the last key as open brace */
-	open_brace[brace_index++] = xbc_node_index(last_parent);
 	if (brace_index >= XBC_DEPTH_MAX)
 		return xbc_parse_error("Exceed max depth of braces", p);
+	open_brace[brace_index++] = xbc_node_index(last_parent);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 1120a36bb1e9b9e22de75ecb4ef0b998f73a97f1 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 12 Mar 2026 19:11:43 +0000
Subject: lib/bootconfig: fix snprintf truncation check in
 xbc_node_compose_key_after()

snprintf() returns the number of characters that would have been
written excluding the NUL terminator.  Output is truncated when the
return value is >= the buffer size, not just > the buffer size.

When ret == size, the current code takes the non-truncated path,
advancing buf by ret and reducing size to 0.  This is wrong because
the output was actually truncated (the last character was replaced by
NUL).  Fix by using >= so the truncation path is taken correctly.

Link: https://lore.kernel.org/all/20260312191143.28719-4-objecting@objecting.org/

Fixes: 76db5a27a827 ("bootconfig: Add Extra Boot Config support")
Cc: stable@vger.kernel.org
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 9c3d59fb96ed..2da049216fe0 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -316,7 +316,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root,
 			       depth ? "." : "");
 		if (ret < 0)
 			return ret;
-		if (ret > size) {
+		if (ret >= size) {
 			size = 0;
 		} else {
 			size -= ret;
-- 
cgit v1.2.3


From e2715ea5fb352cd43fce437b91aa0fd50aaaf384 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 13:18:55 +0900
Subject: bootconfig: Add bootconfig tests about braces

Add more bootconfig tests for checking the error message of
non closing brace and max number of nested braces.

Link: https://lore.kernel.org/all/177337553551.416919.11217619471547711262.stgit@devnote2/

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 tools/bootconfig/samples/bad-non-closed-brace.bconf  |  4 ++++
 tools/bootconfig/samples/bad-over-max-brace.bconf    | 19 +++++++++++++++++++
 tools/bootconfig/samples/exp-good-nested-brace.bconf |  1 +
 tools/bootconfig/samples/good-nested-brace.bconf     | 18 ++++++++++++++++++
 tools/bootconfig/test-bootconfig.sh                  |  9 +++++++++
 5 files changed, 51 insertions(+)
 create mode 100644 tools/bootconfig/samples/bad-non-closed-brace.bconf
 create mode 100644 tools/bootconfig/samples/bad-over-max-brace.bconf
 create mode 100644 tools/bootconfig/samples/exp-good-nested-brace.bconf
 create mode 100644 tools/bootconfig/samples/good-nested-brace.bconf

diff --git a/tools/bootconfig/samples/bad-non-closed-brace.bconf b/tools/bootconfig/samples/bad-non-closed-brace.bconf
new file mode 100644
index 000000000000..6ed9f3363dde
--- /dev/null
+++ b/tools/bootconfig/samples/bad-non-closed-brace.bconf
@@ -0,0 +1,4 @@
+foo {
+ bar {
+   buz
+ }
diff --git a/tools/bootconfig/samples/bad-over-max-brace.bconf b/tools/bootconfig/samples/bad-over-max-brace.bconf
new file mode 100644
index 000000000000..74b5dc9e21dc
--- /dev/null
+++ b/tools/bootconfig/samples/bad-over-max-brace.bconf
@@ -0,0 +1,19 @@
+key1 {
+key2 {
+key3 {
+key4 {
+key5 {
+key6 {
+key7 {
+key8 {
+key9 {
+key10 {
+key11 {
+key12 {
+key13 {
+key14 {
+key15 {
+key16 {
+key17 {
+}}}}}}}}}}}}}}}}}
+
diff --git a/tools/bootconfig/samples/exp-good-nested-brace.bconf b/tools/bootconfig/samples/exp-good-nested-brace.bconf
new file mode 100644
index 000000000000..19e0f51b4553
--- /dev/null
+++ b/tools/bootconfig/samples/exp-good-nested-brace.bconf
@@ -0,0 +1 @@
+key1.key2.key3.key4.key5.key6.key7.key8.key9.key10.key11.key12.key13.key14.key15.key16;
diff --git a/tools/bootconfig/samples/good-nested-brace.bconf b/tools/bootconfig/samples/good-nested-brace.bconf
new file mode 100644
index 000000000000..980d094f296e
--- /dev/null
+++ b/tools/bootconfig/samples/good-nested-brace.bconf
@@ -0,0 +1,18 @@
+key1 {
+key2 {
+key3 {
+key4 {
+key5 {
+key6 {
+key7 {
+key8 {
+key9 {
+key10 {
+key11 {
+key12 {
+key13 {
+key14 {
+key15 {
+key16 {
+}}}}}}}}}}}}}}}}
+
diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index be9bd18b1d56..fc69f815ce4a 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -171,6 +171,15 @@ $BOOTCONF $INITRD > $OUTFILE
 xfail grep -q 'val[[:space:]]' $OUTFILE
 xpass grep -q 'val2[[:space:]]' $OUTFILE
 
+echo "Showing correct line:column of no closing brace"
+cat > $TEMPCONF << EOF
+foo {
+bar {
+}
+EOF
+$BOOTCONF -a $TEMPCONF $INITRD 2> $OUTFILE
+xpass grep -q "1:1" $OUTFILE
+
 echo "=== expected failure cases ==="
 for i in samples/bad-* ; do
   xfail $BOOTCONF -a $i $INITRD
-- 
cgit v1.2.3


From 995a418a6ca33e466e5e1527663ae3d5eee18304 Mon Sep 17 00:00:00 2001
From: Wang Jun <1742789905@qq.com>
Date: Thu, 12 Mar 2026 22:51:36 +0800
Subject: auxdisplay: lcd2s: add error handling for i2c transfers

The lcd2s_print() and lcd2s_gotoxy() functions currently ignore the
return value of lcd2s_i2c_master_send(), which can fail. This can lead
to silent data loss or incorrect cursor positioning.

Add proper error checking: if the number of bytes sent does not match
the expected length, return -EIO; otherwise propagate any error code
from the I2C transfer.

Signed-off-by: Wang Jun <1742789905@qq.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/auxdisplay/lcd2s.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c
index defb0573e43c..c7a962728752 100644
--- a/drivers/auxdisplay/lcd2s.c
+++ b/drivers/auxdisplay/lcd2s.c
@@ -99,8 +99,13 @@ static int lcd2s_print(struct charlcd *lcd, int c)
 {
 	struct lcd2s_data *lcd2s = lcd->drvdata;
 	u8 buf[2] = { LCD2S_CMD_WRITE, c };
+	int ret;
 
-	lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(buf))
+		return -EIO;
 	return 0;
 }
 
@@ -108,9 +113,13 @@ static int lcd2s_gotoxy(struct charlcd *lcd, unsigned int x, unsigned int y)
 {
 	struct lcd2s_data *lcd2s = lcd->drvdata;
 	u8 buf[3] = { LCD2S_CMD_CUR_POS, y + 1, x + 1 };
+	int ret;
 
-	lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
-
+	ret = lcd2s_i2c_master_send(lcd2s->i2c, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(buf))
+		return -EIO;
 	return 0;
 }
 
-- 
cgit v1.2.3


From daf8e3b253aa760ff9e96c7768a464bc1d6b3c90 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Wed, 11 Mar 2026 03:16:29 +0900
Subject: xfrm: Fix work re-schedule after cancel in
 xfrm_nat_keepalive_net_fini()

After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.

The following is a simple race scenario:

           cpu0                             cpu1

cleanup_net() [Round 1]
  ops_undo_list()
    xfrm_net_exit()
      xfrm_nat_keepalive_net_fini()
        cancel_delayed_work_sync(nat_keepalive_work);
      xfrm_state_fini()
        xfrm_state_flush()
          xfrm_state_delete(x)
            __xfrm_state_delete(x)
              xfrm_nat_keepalive_state_updated(x)
                schedule_delayed_work(nat_keepalive_work);
  rcu_barrier();
  net_complete_free();
  net_passive_dec(net);
    llist_add(&net->defer_free_list, &defer_free_list);

cleanup_net() [Round 2]
  rcu_barrier();
  net_complete_free()
    kmem_cache_free(net_cachep, net);
                                     nat_keepalive_work()
                                       // on freed net

To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync().

Fixes: f531d13bdfe3 ("xfrm: support sending NAT keepalives in ESP in UDP states")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_nat_keepalive.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c
index ebf95d48e86c..1856beee0149 100644
--- a/net/xfrm/xfrm_nat_keepalive.c
+++ b/net/xfrm/xfrm_nat_keepalive.c
@@ -261,7 +261,7 @@ int __net_init xfrm_nat_keepalive_net_init(struct net *net)
 
 int xfrm_nat_keepalive_net_fini(struct net *net)
 {
-	cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work);
+	disable_delayed_work_sync(&net->xfrm.nat_keepalive_work);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4f6abe9c743eaf9a473b06ebc01bec81163b3343 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Fri, 27 Feb 2026 14:12:24 +0100
Subject: btrfs: pass 'verbose' parameter to btrfs_relocate_block_group

Function `btrfs_relocate_chunk()` always passes verbose=true to
`btrfs_relocate_block_group()` instead of the `verbose` parameter passed
into it by it's callers.

While user initiated rebalancing should be logged in the Kernel's log
buffer. This causes excessive log spamming from automatic rebalancing,
e.g. on zoned filesystems running low on usable space.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3c37c5d2267b..7efc2f7a9bb2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3587,7 +3587,7 @@ int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset, bool v
 
 	/* step one, relocate all the extents inside this chunk */
 	btrfs_scrub_pause(fs_info);
-	ret = btrfs_relocate_block_group(fs_info, chunk_offset, true);
+	ret = btrfs_relocate_block_group(fs_info, chunk_offset, verbose);
 	btrfs_scrub_continue(fs_info);
 	if (ret) {
 		/*
-- 
cgit v1.2.3


From 77603ab10429fe713a03345553ca8dbbfb1d91c6 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Tue, 3 Mar 2026 11:53:46 +0100
Subject: btrfs: don't take device_list_mutex when querying zone info

Shin'ichiro reported sporadic hangs when running generic/013 in our CI
system. When enabling lockdep, there is a lockdep splat when calling
btrfs_get_dev_zone_info_all_devices() in the mount path that can be
triggered by i.e. generic/013:

  ======================================================
  WARNING: possible circular locking dependency detected
  7.0.0-rc1+ #355 Not tainted
  ------------------------------------------------------
  mount/1043 is trying to acquire lock:
  ffff8881020b5470 (&vblk->vdev_mutex){+.+.}-{4:4}, at: virtblk_report_zones+0xda/0x430

  but task is already holding lock:
  ffff888102a738e0 (&fs_devs->device_list_mutex){+.+.}-{4:4}, at: btrfs_get_dev_zone_info_all_devices+0x45/0x90

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

  -> #4 (&fs_devs->device_list_mutex){+.+.}-{4:4}:
	 __mutex_lock+0xa3/0x1360
	 btrfs_create_pending_block_groups+0x1f4/0x9d0
	 __btrfs_end_transaction+0x3e/0x2e0
	 btrfs_zoned_reserve_data_reloc_bg+0x2f8/0x390
	 open_ctree+0x1934/0x23db
	 btrfs_get_tree.cold+0x105/0x26c
	 vfs_get_tree+0x28/0xb0
	 __do_sys_fsconfig+0x324/0x680
	 do_syscall_64+0x92/0x4f0
	 entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #3 (btrfs_trans_num_extwriters){++++}-{0:0}:
	 join_transaction+0xc2/0x5c0
	 start_transaction+0x17c/0xbc0
	 btrfs_zoned_reserve_data_reloc_bg+0x2b4/0x390
	 open_ctree+0x1934/0x23db
	 btrfs_get_tree.cold+0x105/0x26c
	 vfs_get_tree+0x28/0xb0
	 __do_sys_fsconfig+0x324/0x680
	 do_syscall_64+0x92/0x4f0
	 entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #2 (btrfs_trans_num_writers){++++}-{0:0}:
	 lock_release+0x163/0x4b0
	 __btrfs_end_transaction+0x1c7/0x2e0
	 btrfs_dirty_inode+0x6f/0xd0
	 touch_atime+0xe5/0x2c0
	 btrfs_file_mmap_prepare+0x65/0x90
	 __mmap_region+0x4b9/0xf00
	 mmap_region+0xf7/0x120
	 do_mmap+0x43d/0x610
	 vm_mmap_pgoff+0xd6/0x190
	 ksys_mmap_pgoff+0x7e/0xc0
	 do_syscall_64+0x92/0x4f0
	 entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #1 (&mm->mmap_lock){++++}-{4:4}:
	 __might_fault+0x68/0xa0
	 _copy_to_user+0x22/0x70
	 blkdev_copy_zone_to_user+0x22/0x40
	 virtblk_report_zones+0x282/0x430
	 blkdev_report_zones_ioctl+0xfd/0x130
	 blkdev_ioctl+0x20f/0x2c0
	 __x64_sys_ioctl+0x86/0xd0
	 do_syscall_64+0x92/0x4f0
	 entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #0 (&vblk->vdev_mutex){+.+.}-{4:4}:
	 __lock_acquire+0x1522/0x2680
	 lock_acquire+0xd5/0x2f0
	 __mutex_lock+0xa3/0x1360
	 virtblk_report_zones+0xda/0x430
	 blkdev_report_zones_cached+0x162/0x190
	 btrfs_get_dev_zones+0xdc/0x2e0
	 btrfs_get_dev_zone_info+0x219/0xe80
	 btrfs_get_dev_zone_info_all_devices+0x62/0x90
	 open_ctree+0x1200/0x23db
	 btrfs_get_tree.cold+0x105/0x26c
	 vfs_get_tree+0x28/0xb0
	 __do_sys_fsconfig+0x324/0x680
	 do_syscall_64+0x92/0x4f0
	 entry_SYSCALL_64_after_hwframe+0x76/0x7e

  other info that might help us debug this:

  Chain exists of:
    &vblk->vdev_mutex --> btrfs_trans_num_extwriters --> &fs_devs->device_list_mutex

   Possible unsafe locking scenario:

	 CPU0                    CPU1
	 ----                    ----
    lock(&fs_devs->device_list_mutex);
				 lock(btrfs_trans_num_extwriters);
				 lock(&fs_devs->device_list_mutex);
    lock(&vblk->vdev_mutex);

   *** DEADLOCK ***

  3 locks held by mount/1043:
   #0: ffff88811063e878 (&fc->uapi_mutex){+.+.}-{4:4}, at: __do_sys_fsconfig+0x2ae/0x680
   #1: ffff88810cb9f0e8 (&type->s_umount_key#31/1){+.+.}-{4:4}, at: alloc_super+0xc0/0x3e0
   #2: ffff888102a738e0 (&fs_devs->device_list_mutex){+.+.}-{4:4}, at: btrfs_get_dev_zone_info_all_devices+0x45/0x90

  stack backtrace:
  CPU: 2 UID: 0 PID: 1043 Comm: mount Not tainted 7.0.0-rc1+ #355 PREEMPT(full)
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-9.fc43 06/10/2025
  Call Trace:
   <TASK>
   dump_stack_lvl+0x5b/0x80
   print_circular_bug.cold+0x18d/0x1d8
   check_noncircular+0x10d/0x130
   __lock_acquire+0x1522/0x2680
   ? vmap_small_pages_range_noflush+0x3ef/0x820
   lock_acquire+0xd5/0x2f0
   ? virtblk_report_zones+0xda/0x430
   ? lock_is_held_type+0xcd/0x130
   __mutex_lock+0xa3/0x1360
   ? virtblk_report_zones+0xda/0x430
   ? virtblk_report_zones+0xda/0x430
   ? __pfx_copy_zone_info_cb+0x10/0x10
   ? virtblk_report_zones+0xda/0x430
   virtblk_report_zones+0xda/0x430
   ? __pfx_copy_zone_info_cb+0x10/0x10
   blkdev_report_zones_cached+0x162/0x190
   ? __pfx_copy_zone_info_cb+0x10/0x10
   btrfs_get_dev_zones+0xdc/0x2e0
   btrfs_get_dev_zone_info+0x219/0xe80
   btrfs_get_dev_zone_info_all_devices+0x62/0x90
   open_ctree+0x1200/0x23db
   btrfs_get_tree.cold+0x105/0x26c
   ? rcu_is_watching+0x18/0x50
   vfs_get_tree+0x28/0xb0
   __do_sys_fsconfig+0x324/0x680
   do_syscall_64+0x92/0x4f0
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7f615e27a40e
  RSP: 002b:00007fff11b18fb8 EFLAGS: 00000246 ORIG_RAX: 00000000000001af
  RAX: ffffffffffffffda RBX: 000055572e92ab10 RCX: 00007f615e27a40e
  RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000003
  RBP: 00007fff11b19100 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 000055572e92bc40 R14: 00007f615e3faa60 R15: 000055572e92bd08
   </TASK>

Don't hold the device_list_mutex while calling into
btrfs_get_dev_zone_info() in btrfs_get_dev_zone_info_all_devices() to
mitigate the issue. This is safe, as no other thread can touch the device
list at the moment of execution.

Reported-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index ad8621587fd2..92b5ac8fac37 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -337,7 +337,10 @@ int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
 	if (!btrfs_fs_incompat(fs_info, ZONED))
 		return 0;
 
-	mutex_lock(&fs_devices->device_list_mutex);
+	/*
+	 * No need to take the device_list mutex here, we're still in the mount
+	 * path and devices cannot be added to or removed from the list yet.
+	 */
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		/* We can skip reading of zone info for missing devices */
 		if (!device->bdev)
@@ -347,7 +350,6 @@ int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
 		if (ret)
 			break;
 	}
-	mutex_unlock(&fs_devices->device_list_mutex);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 9573a365ff9ff45da9222d3fe63695ce562beb24 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 3 Mar 2026 16:57:43 +0000
Subject: btrfs: log new dentries when logging parent dir of a conflicting
 inode

If we log the parent directory of a conflicting inode, we are not logging
the new dentries of the directory, so when we finish we have the parent
directory's inode marked as logged but we did not log its new dentries.
As a consequence if the parent directory is explicitly fsynced later and
it does not have any new changes since we logged it, the fsync is a no-op
and after a power failure the new dentries are missing.

Example scenario:

  $ mkdir foo

  $ sync

  $rmdir foo

  $ mkdir dir1
  $ mkdir dir2

  # A file with the same name and parent as the directory we just deleted
  # and was persisted in a past transaction. So the deleted directory's
  # inode is a conflicting inode of this new file's inode.
  $ touch foo

  $ ln foo dir2/link

  # The fsync on dir2 will log the parent directory (".") because the
  # conflicting inode (deleted directory) does not exists anymore, but it
  # it does not log its new dentries (dir1).
  $ xfs_io -c "fsync" dir2

  # This fsync on the parent directory is no-op, since the previous fsync
  # logged it (but without logging its new dentries).
  $ xfs_io -c "fsync" .

  <power failure>

  # After log replay dir1 is missing.

Fix this by ensuring we log new dir dentries whenever we log the parent
directory of a no longer existing conflicting inode.

A test case for fstests will follow soon.

Reported-by: Vyacheslav Kovalevsky <slava.kovalevskiy.2014@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/182055fa-e9ce-4089-9f5f-4b8a23e8dd91@gmail.com/
Fixes: a3baaf0d786e ("Btrfs: fix fsync after succession of renames and unlink/rmdir")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index e1bd03ebfd98..37c272df52b0 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -6195,6 +6195,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root,
 				  struct btrfs_log_ctx *ctx)
 {
+	const bool orig_log_new_dentries = ctx->log_new_dentries;
 	int ret = 0;
 
 	/*
@@ -6256,7 +6257,11 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 			 * dir index key range logged for the directory. So we
 			 * must make sure the deletion is recorded.
 			 */
+			ctx->log_new_dentries = false;
 			ret = btrfs_log_inode(trans, inode, LOG_INODE_ALL, ctx);
+			if (!ret && ctx->log_new_dentries)
+				ret = log_new_dir_dentries(trans, inode, ctx);
+
 			btrfs_add_delayed_iput(inode);
 			if (ret)
 				break;
@@ -6291,6 +6296,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
 			break;
 	}
 
+	ctx->log_new_dentries = orig_log_new_dentries;
 	ctx->logging_conflict_inodes = false;
 	if (ret)
 		free_conflicting_inodes(ctx);
-- 
cgit v1.2.3


From fc1cd1f18c34f91e78362f9629ab9fd43b9dcab9 Mon Sep 17 00:00:00 2001
From: ZhengYuan Huang <gality369@gmail.com>
Date: Thu, 12 Mar 2026 08:33:21 +0800
Subject: btrfs: tree-checker: fix misleading root drop_level error message

Fix tree-checker error message to report "invalid root drop_level"
instead of the misleading "invalid root level".

Fixes: 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: ZhengYuan Huang <gality369@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index ac4c4573ee39..516ef62c8f43 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1284,7 +1284,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
 	}
 	if (unlikely(btrfs_root_drop_level(&ri) >= BTRFS_MAX_LEVEL)) {
 		generic_err(leaf, slot,
-			    "invalid root level, have %u expect [0, %u]",
+			    "invalid root drop_level, have %u expect [0, %u]",
 			    btrfs_root_drop_level(&ri), BTRFS_MAX_LEVEL - 1);
 		return -EUCLEAN;
 	}
-- 
cgit v1.2.3


From 7d73872d949c488a1d7c308031d6a9d89b5e0a8b Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Fri, 13 Mar 2026 14:54:17 +0530
Subject: wifi: mac80211: check tdls flag in ieee80211_tdls_oper

When NL80211_TDLS_ENABLE_LINK is called, the code only checks if the
station exists but not whether it is actually a TDLS station. This
allows the operation to proceed for non-TDLS stations, causing
unintended side effects like modifying channel context and HT
protection before failing.

Add a check for sta->sta.tdls early in the ENABLE_LINK case, before
any side effects occur, to ensure the operation is only allowed for
actual TDLS peers.

Reported-by: syzbot+56b6a844a4ea74487b7b@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=56b6a844a4ea74487b7b
Tested-by: syzbot+56b6a844a4ea74487b7b@syzkaller.appspotmail.com
Suggested-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Link: https://patch.msgid.link/20260313092417.520807-1-kartikey406@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tdls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index dbbfe2d6842f..1dca2fae05a5 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -1449,7 +1449,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 		}
 
 		sta = sta_info_get(sdata, peer);
-		if (!sta)
+		if (!sta || !sta->sta.tdls)
 			return -ENOLINK;
 
 		iee80211_tdls_recalc_chanctx(sdata, sta);
-- 
cgit v1.2.3


From e113f0b46d19626ec15388bcb91432c9a4fd6261 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 23:14:14 +0900
Subject: kprobes: avoid crash when rmmod/insmod after ftrace killed

After we hit ftrace is killed by some errors, the kernel crash if
we remove modules in which kprobe probes.

BUG: unable to handle page fault for address: fffffbfff805000d
PGD 817fcc067 P4D 817fcc067 PUD 817fc8067 PMD 101555067 PTE 0
Oops: Oops: 0000 [#1] SMP KASAN PTI
CPU: 4 UID: 0 PID: 2012 Comm: rmmod Tainted: G        W  OE
Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
RIP: 0010:kprobes_module_callback+0x89/0x790
RSP: 0018:ffff88812e157d30 EFLAGS: 00010a02
RAX: 1ffffffff805000d RBX: dffffc0000000000 RCX: ffffffff86a8de90
RDX: ffffed1025c2af9b RSI: 0000000000000008 RDI: ffffffffc0280068
RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed1025c2af9a
R10: ffff88812e157cd7 R11: 205d323130325420 R12: 0000000000000002
R13: ffffffffc0290488 R14: 0000000000000002 R15: ffffffffc0280040
FS:  00007fbc450dd740(0000) GS:ffff888420331000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffffbfff805000d CR3: 000000010f624000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 notifier_call_chain+0xc6/0x280
 blocking_notifier_call_chain+0x60/0x90
 __do_sys_delete_module.constprop.0+0x32a/0x4e0
 do_syscall_64+0x5d/0xfa0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

This is because the kprobe on ftrace does not correctly handles
the kprobe_ftrace_disabled flag set by ftrace_kill().

To prevent this error, check kprobe_ftrace_disabled in
__disarm_kprobe_ftrace() and skip all ftrace related operations.

Link: https://lore.kernel.org/all/176473947565.1727781.13110060700668331950.stgit@mhiramat.tok.corp.google.com/

Reported-by: Ye Bin <yebin10@huawei.com>
Closes: https://lore.kernel.org/all/20251125020536.2484381-1-yebin@huaweicloud.com/
Fixes: ae6aa16fdc16 ("kprobes: introduce ftrace based optimization")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/kprobes.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab25b4aa9095..025af57ad3ed 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1178,6 +1178,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	int ret;
 
 	lockdep_assert_held(&kprobe_mutex);
+	if (unlikely(kprobe_ftrace_disabled)) {
+		/* Now ftrace is disabled forever, disarm is already done. */
+		return 0;
+	}
 
 	if (*cnt == 1) {
 		ret = unregister_ftrace_function(ops);
-- 
cgit v1.2.3


From 5ef268cb7a0aac55521fd9881f1939fa94a8988e Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 13 Mar 2026 23:04:11 +0900
Subject: kprobes: Remove unneeded warnings from __arm_kprobe_ftrace()

Remove unneeded warnings for handled errors from __arm_kprobe_ftrace()
because all caller handled the error correctly.

Link: https://lore.kernel.org/all/177261531182.1312989.8737778408503961141.stgit@mhiramat.tok.corp.google.com/

Reported-by: Zw Tang <shicenci@gmail.com>
Closes: https://lore.kernel.org/all/CAPHJ_V+J6YDb_wX2nhXU6kh466Dt_nyDSas-1i_Y8s7tqY-Mzw@mail.gmail.com/
Fixes: 9c89bb8e3272 ("kprobes: treewide: Cleanup the error messages for kprobes")
Cc: stable@vger.kernel.org
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/kprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 025af57ad3ed..bfc89083daa9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1144,12 +1144,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
 	lockdep_assert_held(&kprobe_mutex);
 
 	ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0);
-	if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret))
+	if (ret < 0)
 		return ret;
 
 	if (*cnt == 0) {
 		ret = register_ftrace_function(ops);
-		if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) {
+		if (ret < 0) {
 			/*
 			 * At this point, sinec ops is not registered, we should be sefe from
 			 * registering empty filter.
-- 
cgit v1.2.3


From d499e9627d70b1269020d59b95ed3e18bee6b8cd Mon Sep 17 00:00:00 2001
From: Pepper Gray <hello@peppergray.xyz>
Date: Tue, 10 Mar 2026 14:44:28 +0100
Subject: arm64/scs: Fix handling of advance_loc4

DW_CFA_advance_loc4 is defined but no handler is implemented. Its
CFA opcode defaults to EDYNSCS_INVALID_CFA_OPCODE triggering an
error which wrongfully prevents modules from loading.

Link: https://bugs.gentoo.org/971060
Signed-off-by: Pepper Gray <hello@peppergray.xyz>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/pi/patch-scs.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c
index bbe7d30ed12b..dac568e4a54f 100644
--- a/arch/arm64/kernel/pi/patch-scs.c
+++ b/arch/arm64/kernel/pi/patch-scs.c
@@ -192,6 +192,14 @@ static int scs_handle_fde_frame(const struct eh_frame *frame,
 			size -= 2;
 			break;
 
+		case DW_CFA_advance_loc4:
+			loc += *opcode++ * code_alignment_factor;
+			loc += (*opcode++ << 8) * code_alignment_factor;
+			loc += (*opcode++ << 16) * code_alignment_factor;
+			loc += (*opcode++ << 24) * code_alignment_factor;
+			size -= 4;
+		break;
+
 		case DW_CFA_def_cfa:
 		case DW_CFA_offset_extended:
 			size = skip_xleb128(&opcode, size);
-- 
cgit v1.2.3


From 4ad79c874e53ebb7fe3b8ae7ac6c858a2121f415 Mon Sep 17 00:00:00 2001
From: Ben Horgan <ben.horgan@arm.com>
Date: Fri, 6 Mar 2026 18:27:16 +0000
Subject: arm_mpam: Fix null pointer dereference when restoring bandwidth
 counters

When an MSC supporting memory bandwidth monitoring is brought offline and
then online, mpam_restore_mbwu_state() calls __ris_msmon_read() via ipi to
restore the configuration of the bandwidth counters. It doesn't care about
the value read, mbwu_arg.val, and doesn't set it leading to a null pointer
dereference when __ris_msmon_read() adds to it. This results in a kernel
oops with a call trace such as:

Call trace:
__ris_msmon_read+0x19c/0x64c (P)
mpam_restore_mbwu_state+0xa0/0xe8
smp_call_on_cpu_callback+0x1c/0x38
process_one_work+0x154/0x4b4
worker_thread+0x188/0x310
kthread+0x11c/0x130
ret_from_fork+0x10/0x20

Provide a local variable for val to avoid __ris_msmon_read() dereferencing
a null pointer when adding to val.

Fixes: 41e8a14950e1 ("arm_mpam: Track bandwidth counter state for power management")
Signed-off-by: Ben Horgan <ben.horgan@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/resctrl/mpam_devices.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/resctrl/mpam_devices.c b/drivers/resctrl/mpam_devices.c
index 1eebc2602187..0666be6b0e88 100644
--- a/drivers/resctrl/mpam_devices.c
+++ b/drivers/resctrl/mpam_devices.c
@@ -1428,6 +1428,7 @@ static void mpam_reprogram_ris_partid(struct mpam_msc_ris *ris, u16 partid,
 static int mpam_restore_mbwu_state(void *_ris)
 {
 	int i;
+	u64 val;
 	struct mon_read mwbu_arg;
 	struct mpam_msc_ris *ris = _ris;
 	struct mpam_class *class = ris->vmsc->comp->class;
@@ -1437,6 +1438,7 @@ static int mpam_restore_mbwu_state(void *_ris)
 			mwbu_arg.ris = ris;
 			mwbu_arg.ctx = &ris->mbwu_state[i].cfg;
 			mwbu_arg.type = mpam_msmon_choose_counter(class);
+			mwbu_arg.val = &val;
 
 			__ris_msmon_read(&mwbu_arg);
 		}
-- 
cgit v1.2.3


From c1376f1ff3f016a4b84e8030ed69df82e018d231 Mon Sep 17 00:00:00 2001
From: Ben Horgan <ben.horgan@arm.com>
Date: Fri, 6 Mar 2026 18:27:17 +0000
Subject: arm_mpam: Disable preemption when making accesses to fake MSC in
 kunit test

Accesses to MSC must be made from a cpu that is affine to that MSC and the
driver checks this in __mpam_write_reg() using smp_processor_id(). A fake
in-memory MSC is used for testing. When using that, it doesn't matter which
cpu we access it from but calling smp_processor_id() from a preemptible
context gives warnings when running with CONFIG_DEBUG_PREEMPT.

Add a test helper that wraps mpam_reset_msc_bitmap() with preemption
disabled to ensure all (fake) MSC accesses are made with preemption
disabled.

Signed-off-by: Ben Horgan <ben.horgan@arm.com>
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/resctrl/test_mpam_devices.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/resctrl/test_mpam_devices.c b/drivers/resctrl/test_mpam_devices.c
index 3e8d564a0c64..75bd41bcc395 100644
--- a/drivers/resctrl/test_mpam_devices.c
+++ b/drivers/resctrl/test_mpam_devices.c
@@ -322,6 +322,14 @@ static void test_mpam_enable_merge_features(struct kunit *test)
 	mutex_unlock(&mpam_list_lock);
 }
 
+static void __test_mpam_reset_msc_bitmap(struct mpam_msc *msc, u16 reg, u16 wd)
+{
+	/* Avoid warnings when running with CONFIG_DEBUG_PREEMPT */
+	guard(preempt)();
+
+	mpam_reset_msc_bitmap(msc, reg, wd);
+}
+
 static void test_mpam_reset_msc_bitmap(struct kunit *test)
 {
 	char __iomem *buf = kunit_kzalloc(test, SZ_16K, GFP_KERNEL);
@@ -341,31 +349,31 @@ static void test_mpam_reset_msc_bitmap(struct kunit *test)
 
 	test_result = (u32 *)(buf + MPAMCFG_CPBM);
 
-	mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 0);
+	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 0);
 	KUNIT_EXPECT_EQ(test, test_result[0], 0);
 	KUNIT_EXPECT_EQ(test, test_result[1], 0);
 	test_result[0] = 0;
 	test_result[1] = 0;
 
-	mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 1);
+	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 1);
 	KUNIT_EXPECT_EQ(test, test_result[0], 1);
 	KUNIT_EXPECT_EQ(test, test_result[1], 0);
 	test_result[0] = 0;
 	test_result[1] = 0;
 
-	mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 16);
+	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 16);
 	KUNIT_EXPECT_EQ(test, test_result[0], 0xffff);
 	KUNIT_EXPECT_EQ(test, test_result[1], 0);
 	test_result[0] = 0;
 	test_result[1] = 0;
 
-	mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 32);
+	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 32);
 	KUNIT_EXPECT_EQ(test, test_result[0], 0xffffffff);
 	KUNIT_EXPECT_EQ(test, test_result[1], 0);
 	test_result[0] = 0;
 	test_result[1] = 0;
 
-	mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 33);
+	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 33);
 	KUNIT_EXPECT_EQ(test, test_result[0], 0xffffffff);
 	KUNIT_EXPECT_EQ(test, test_result[1], 1);
 	test_result[0] = 0;
-- 
cgit v1.2.3


From fb75437b447875ae97ea3a173e734dbd553a3881 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Fri, 6 Mar 2026 18:27:18 +0000
Subject: arm_mpam: Force __iomem casts

Code allocates standard kernel memory to pass to the MPAM, which expects
__iomem.  The code is safe, because __iomem accessors should work fine
on kernel mapped memory, however leads to sparse warnings:

  test_mpam_devices.c:327:42: warning: incorrect type in initializer (different address spaces)
  test_mpam_devices.c:327:42:    expected char [noderef] __iomem *buf
  test_mpam_devices.c:327:42:    got void *
  test_mpam_devices.c:342:24: warning: cast removes address space '__iomem' of expression

Cast the pointer to memory via __force to silence them.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202512160133.eAzPdJv2-lkp@intel.com/
Acked-by: Ben Horgan <ben.horgan@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/resctrl/test_mpam_devices.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/resctrl/test_mpam_devices.c b/drivers/resctrl/test_mpam_devices.c
index 75bd41bcc395..31871f519729 100644
--- a/drivers/resctrl/test_mpam_devices.c
+++ b/drivers/resctrl/test_mpam_devices.c
@@ -332,7 +332,7 @@ static void __test_mpam_reset_msc_bitmap(struct mpam_msc *msc, u16 reg, u16 wd)
 
 static void test_mpam_reset_msc_bitmap(struct kunit *test)
 {
-	char __iomem *buf = kunit_kzalloc(test, SZ_16K, GFP_KERNEL);
+	char __iomem *buf = (__force char __iomem *)kunit_kzalloc(test, SZ_16K, GFP_KERNEL);
 	struct mpam_msc fake_msc = {};
 	u32 *test_result;
 
@@ -347,7 +347,7 @@ static void test_mpam_reset_msc_bitmap(struct kunit *test)
 	mutex_init(&fake_msc.part_sel_lock);
 	mutex_lock(&fake_msc.part_sel_lock);
 
-	test_result = (u32 *)(buf + MPAMCFG_CPBM);
+	test_result = (__force u32 *)(buf + MPAMCFG_CPBM);
 
 	__test_mpam_reset_msc_bitmap(&fake_msc, MPAMCFG_CPBM, 0);
 	KUNIT_EXPECT_EQ(test, test_result[0], 0);
-- 
cgit v1.2.3


From 5cb81eeda909dbb2def209dd10636b51549a3f8a Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Sun, 8 Mar 2026 02:21:37 +0900
Subject: netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct()

ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the
netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the
conntrack reference immediately after netlink_dump_start().  When the
dump spans multiple rounds, the second recvmsg() triggers the dump
callback which dereferences the now-freed conntrack via nfct_help(ct),
leading to a use-after-free on ct->ext.

The bug is that the netlink_dump_control has no .start or .done
callbacks to manage the conntrack reference across dump rounds.  Other
dump functions in the same file (e.g. ctnetlink_get_conntrack) properly
use .start/.done callbacks for this purpose.

Fix this by adding .start and .done callbacks that hold and release the
conntrack reference for the duration of the dump, and move the
nfct_help() call after the cb->args[0] early-return check in the dump
callback to avoid dereferencing ct->ext unnecessarily.

 BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0
 Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133

 CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY
 Call Trace:
  <TASK>
  ctnetlink_exp_ct_dump_table+0x4f/0x2e0
  netlink_dump+0x333/0x880
  netlink_recvmsg+0x3e2/0x4b0
  ? aa_sk_perm+0x184/0x450
  sock_recvmsg+0xde/0xf0

 Allocated by task 133:
  kmem_cache_alloc_noprof+0x134/0x440
  __nf_conntrack_alloc+0xa8/0x2b0
  ctnetlink_create_conntrack+0xa1/0x900
  ctnetlink_new_conntrack+0x3cf/0x7d0
  nfnetlink_rcv_msg+0x48e/0x510
  netlink_rcv_skb+0xc9/0x1f0
  nfnetlink_rcv+0xdb/0x220
  netlink_unicast+0x3ec/0x590
  netlink_sendmsg+0x397/0x690
  __sys_sendmsg+0xf4/0x180

 Freed by task 0:
  slab_free_after_rcu_debug+0xad/0x1e0
  rcu_core+0x5c3/0x9c0

Fixes: e844a928431f ("netfilter: ctnetlink: allow to dump expectation per master conntrack")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_netlink.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c9d725fc2d71..65aa44a12d01 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3212,7 +3212,7 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	struct nf_conn *ct = cb->data;
-	struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help;
 	u_int8_t l3proto = nfmsg->nfgen_family;
 	unsigned long last_id = cb->args[1];
 	struct nf_conntrack_expect *exp;
@@ -3220,6 +3220,10 @@ ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	if (cb->args[0])
 		return 0;
 
+	help = nfct_help(ct);
+	if (!help)
+		return 0;
+
 	rcu_read_lock();
 
 restart:
@@ -3249,6 +3253,24 @@ out:
 	return skb->len;
 }
 
+static int ctnetlink_dump_exp_ct_start(struct netlink_callback *cb)
+{
+	struct nf_conn *ct = cb->data;
+
+	if (!refcount_inc_not_zero(&ct->ct_general.use))
+		return -ENOENT;
+	return 0;
+}
+
+static int ctnetlink_dump_exp_ct_done(struct netlink_callback *cb)
+{
+	struct nf_conn *ct = cb->data;
+
+	if (ct)
+		nf_ct_put(ct);
+	return 0;
+}
+
 static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl,
 				 struct sk_buff *skb,
 				 const struct nlmsghdr *nlh,
@@ -3264,6 +3286,8 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl,
 	struct nf_conntrack_zone zone;
 	struct netlink_dump_control c = {
 		.dump = ctnetlink_exp_ct_dump_table,
+		.start = ctnetlink_dump_exp_ct_start,
+		.done = ctnetlink_dump_exp_ct_done,
 	};
 
 	err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER,
-- 
cgit v1.2.3


From f900e1d77ee0ef87bfb5ab3fe60f0b3d8ad5ba05 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 10 Mar 2026 00:28:29 +0100
Subject: netfilter: conntrack: add missing netlink policy validations

Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink.

These attributes are used by the kernel without any validation.
Extend the netlink policies accordingly.

Quoting the reporter:
  nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE
  value directly to ct->proto.sctp.state without checking that it is
  within the valid range. [..]

  and: ... with exp->dir = 100, the access at
  ct->master->tuplehash[100] reads 5600 bytes past the start of a
  320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by
  UBSAN.

Fixes: 076a0ca02644 ("netfilter: ctnetlink: add NAT support for expectations")
Fixes: a258860e01b8 ("netfilter: ctnetlink: add full support for SCTP to ctnetlink")
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_netlink.c    | 2 +-
 net/netfilter/nf_conntrack_proto_sctp.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 65aa44a12d01..c156574e1273 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3489,7 +3489,7 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x,
 
 #if IS_ENABLED(CONFIG_NF_NAT)
 static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = {
-	[CTA_EXPECT_NAT_DIR]	= { .type = NLA_U32 },
+	[CTA_EXPECT_NAT_DIR]	= NLA_POLICY_MAX(NLA_BE32, IP_CT_DIR_REPLY),
 	[CTA_EXPECT_NAT_TUPLE]	= { .type = NLA_NESTED },
 };
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 7c6f7c9f7332..645d2c43ebf7 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -582,7 +582,8 @@ nla_put_failure:
 }
 
 static const struct nla_policy sctp_nla_policy[CTA_PROTOINFO_SCTP_MAX+1] = {
-	[CTA_PROTOINFO_SCTP_STATE]	    = { .type = NLA_U8 },
+	[CTA_PROTOINFO_SCTP_STATE]	    = NLA_POLICY_MAX(NLA_U8,
+							 SCTP_CONNTRACK_HEARTBEAT_SENT),
 	[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL]  = { .type = NLA_U32 },
 	[CTA_PROTOINFO_SCTP_VTAG_REPLY]     = { .type = NLA_U32 },
 };
-- 
cgit v1.2.3


From fbce58e719a17aa215c724473fd5baaa4a8dc57c Mon Sep 17 00:00:00 2001
From: Lukas Johannes Möller <research@johannes-moeller.dev>
Date: Tue, 10 Mar 2026 21:49:01 +0000
Subject: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in
 sip_help_tcp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sip_help_tcp() parses the SIP Content-Length header with
simple_strtoul(), which returns unsigned long, but stores the result in
unsigned int clen.  On 64-bit systems, values exceeding UINT_MAX are
silently truncated before computing the SIP message boundary.

For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32,
causing the parser to miscalculate where the current message ends.  The
loop then treats trailing data in the TCP segment as a second SIP
message and processes it through the SDP parser.

Fix this by changing clen to unsigned long to match the return type of
simple_strtoul(), and reject Content-Length values that exceed the
remaining TCP payload length.

Fixes: f5b321bd37fb ("netfilter: nf_conntrack_sip: add TCP support")
Signed-off-by: Lukas Johannes Möller <research@johannes-moeller.dev>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_sip.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index ca748f8dbff1..4ab5ef71d96d 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1534,11 +1534,12 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 {
 	struct tcphdr *th, _tcph;
 	unsigned int dataoff, datalen;
-	unsigned int matchoff, matchlen, clen;
+	unsigned int matchoff, matchlen;
 	unsigned int msglen, origlen;
 	const char *dptr, *end;
 	s16 diff, tdiff = 0;
 	int ret = NF_ACCEPT;
+	unsigned long clen;
 	bool term;
 
 	if (ctinfo != IP_CT_ESTABLISHED &&
@@ -1573,6 +1574,9 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff,
 		if (dptr + matchoff == end)
 			break;
 
+		if (clen > datalen)
+			break;
+
 		term = false;
 		for (; end + strlen("\r\n\r\n") <= dptr + datalen; end++) {
 			if (end[0] == '\r' && end[1] == '\n' &&
-- 
cgit v1.2.3


From 598adea720b97572c7028635cb1c59b3684e128c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Mar 2026 16:24:02 +0100
Subject: netfilter: revert nft_set_rbtree: validate open interval overlap

This reverts commit 648946966a08 ("netfilter: nft_set_rbtree: validate
open interval overlap").

There have been reports of nft failing to laod valid rulesets after this
patch was merged into -stable.

I can reproduce several such problem with recent nft versions, including
nft 1.1.6 which is widely shipped by distributions.

We currently have little choice here.
This commit can be resurrected at some point once the nftables fix that
triggers the false overlap positive has appeared in common distros
(see e83e32c8d1cd ("mnl: restore create element command with large batches" in
 nftables.git).

Fixes: 648946966a08 ("netfilter: nft_set_rbtree: validate open interval overlap")
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  4 ---
 net/netfilter/nf_tables_api.c     | 21 +++---------
 net/netfilter/nft_set_rbtree.c    | 71 ++++++---------------------------------
 3 files changed, 14 insertions(+), 82 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e2d2bfc1f989..6299af4ef423 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -277,8 +277,6 @@ struct nft_userdata {
 	unsigned char		data[];
 };
 
-#define NFT_SET_ELEM_INTERNAL_LAST	0x1
-
 /* placeholder structure for opaque set element backend representation. */
 struct nft_elem_priv { };
 
@@ -288,7 +286,6 @@ struct nft_elem_priv { };
  *	@key: element key
  *	@key_end: closing element key
  *	@data: element data
- * 	@flags: flags
  *	@priv: element private data and extensions
  */
 struct nft_set_elem {
@@ -304,7 +301,6 @@ struct nft_set_elem {
 		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
 		struct nft_data val;
 	} data;
-	u32			flags;
 	struct nft_elem_priv	*priv;
 };
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index dacec5f8a11c..4ccdd33cf133 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7156,8 +7156,7 @@ static u32 nft_set_maxsize(const struct nft_set *set)
 }
 
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
-			    const struct nlattr *attr, u32 nlmsg_flags,
-			    bool last)
+			    const struct nlattr *attr, u32 nlmsg_flags)
 {
 	struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {};
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
@@ -7444,11 +7443,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (flags)
 		*nft_set_ext_flags(ext) = flags;
 
-	if (last)
-		elem.flags = NFT_SET_ELEM_INTERNAL_LAST;
-	else
-		elem.flags = 0;
-
 	if (obj)
 		*nft_set_ext_obj(ext) = obj;
 
@@ -7613,8 +7607,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags,
-				       nla_is_last(attr, rem));
+		err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags);
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
 			return err;
@@ -7738,7 +7731,7 @@ static void nft_trans_elems_destroy_abort(const struct nft_ctx *ctx,
 }
 
 static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
-			   const struct nlattr *attr, bool last)
+			   const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_set_ext_tmpl tmpl;
@@ -7806,11 +7799,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (flags)
 		*nft_set_ext_flags(ext) = flags;
 
-	if (last)
-		elem.flags = NFT_SET_ELEM_INTERNAL_LAST;
-	else
-		elem.flags = 0;
-
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
 	if (trans == NULL)
 		goto fail_trans;
@@ -7961,8 +7949,7 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 		return nft_set_flush(&ctx, set, genmask);
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		err = nft_del_setelem(&ctx, set, attr,
-				      nla_is_last(attr, rem));
+		err = nft_del_setelem(&ctx, set, attr);
 		if (err == -ENOENT &&
 		    NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM)
 			continue;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index ee3d4f5b9ff7..fe8bd497d74a 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -304,19 +304,10 @@ static void nft_rbtree_set_start_cookie(struct nft_rbtree *priv,
 	priv->start_rbe_cookie = (unsigned long)rbe;
 }
 
-static void nft_rbtree_set_start_cookie_open(struct nft_rbtree *priv,
-					     const struct nft_rbtree_elem *rbe,
-					     unsigned long open_interval)
-{
-	priv->start_rbe_cookie = (unsigned long)rbe | open_interval;
-}
-
-#define NFT_RBTREE_OPEN_INTERVAL	1UL
-
 static bool nft_rbtree_cmp_start_cookie(struct nft_rbtree *priv,
 					const struct nft_rbtree_elem *rbe)
 {
-	return (priv->start_rbe_cookie & ~NFT_RBTREE_OPEN_INTERVAL) == (unsigned long)rbe;
+	return priv->start_rbe_cookie == (unsigned long)rbe;
 }
 
 static bool nft_rbtree_insert_same_interval(const struct net *net,
@@ -346,14 +337,13 @@ static bool nft_rbtree_insert_same_interval(const struct net *net,
 
 static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			       struct nft_rbtree_elem *new,
-			       struct nft_elem_priv **elem_priv, u64 tstamp, bool last)
+			       struct nft_elem_priv **elem_priv, u64 tstamp)
 {
 	struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL, *rbe_prev;
 	struct rb_node *node, *next, *parent, **p, *first = NULL;
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u8 cur_genmask = nft_genmask_cur(net);
 	u8 genmask = nft_genmask_next(net);
-	unsigned long open_interval = 0;
 	int d;
 
 	/* Descend the tree to search for an existing element greater than the
@@ -459,18 +449,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		}
 	}
 
-	if (nft_rbtree_interval_null(set, new)) {
+	if (nft_rbtree_interval_null(set, new))
+		priv->start_rbe_cookie = 0;
+	else if (nft_rbtree_interval_start(new) && priv->start_rbe_cookie)
 		priv->start_rbe_cookie = 0;
-	} else if (nft_rbtree_interval_start(new) && priv->start_rbe_cookie) {
-		if (nft_set_is_anonymous(set)) {
-			priv->start_rbe_cookie = 0;
-		} else if (priv->start_rbe_cookie & NFT_RBTREE_OPEN_INTERVAL) {
-			/* Previous element is an open interval that partially
-			 * overlaps with an existing non-open interval.
-			 */
-			return -ENOTEMPTY;
-		}
-	}
 
 	/* - new start element matching existing start element: full overlap
 	 *   reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
@@ -478,27 +460,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) &&
 	    nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) {
 		*elem_priv = &rbe_ge->priv;
-
-		/* - Corner case: new start element of open interval (which
-		 *   comes as last element in the batch) overlaps the start of
-		 *   an existing interval with an end element: partial overlap.
-		 */
-		node = rb_first(&priv->root);
-		rbe = __nft_rbtree_next_active(node, genmask);
-		if (rbe && nft_rbtree_interval_end(rbe)) {
-			rbe = nft_rbtree_next_active(rbe, genmask);
-			if (rbe &&
-			    nft_rbtree_interval_start(rbe) &&
-			    !nft_rbtree_cmp(set, new, rbe)) {
-				if (last)
-					return -ENOTEMPTY;
-
-				/* Maybe open interval? */
-				open_interval = NFT_RBTREE_OPEN_INTERVAL;
-			}
-		}
-		nft_rbtree_set_start_cookie_open(priv, rbe_ge, open_interval);
-
+		nft_rbtree_set_start_cookie(priv, rbe_ge);
 		return -EEXIST;
 	}
 
@@ -553,12 +515,6 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	    nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new))
 		return -ENOTEMPTY;
 
-	/* - start element overlaps an open interval but end element is new:
-	 *   partial overlap, reported as -ENOEMPTY.
-	 */
-	if (!rbe_ge && priv->start_rbe_cookie && nft_rbtree_interval_end(new))
-		return -ENOTEMPTY;
-
 	/* Accepted element: pick insertion point depending on key value */
 	parent = NULL;
 	p = &priv->root.rb_node;
@@ -668,7 +624,6 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			     struct nft_elem_priv **elem_priv)
 {
 	struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv);
-	bool last = !!(elem->flags & NFT_SET_ELEM_INTERNAL_LAST);
 	struct nft_rbtree *priv = nft_set_priv(set);
 	u64 tstamp = nft_net_tstamp(net);
 	int err;
@@ -685,12 +640,8 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		cond_resched();
 
 		write_lock_bh(&priv->lock);
-		err = __nft_rbtree_insert(net, set, rbe, elem_priv, tstamp, last);
+		err = __nft_rbtree_insert(net, set, rbe, elem_priv, tstamp);
 		write_unlock_bh(&priv->lock);
-
-		if (nft_rbtree_interval_end(rbe))
-			priv->start_rbe_cookie = 0;
-
 	} while (err == -EAGAIN);
 
 	return err;
@@ -778,7 +729,6 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 		      const struct nft_set_elem *elem)
 {
 	struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv);
-	bool last = !!(elem->flags & NFT_SET_ELEM_INTERNAL_LAST);
 	struct nft_rbtree *priv = nft_set_priv(set);
 	const struct rb_node *parent = priv->root.rb_node;
 	u8 genmask = nft_genmask_next(net);
@@ -819,10 +769,9 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 				continue;
 			}
 
-			if (nft_rbtree_interval_start(rbe)) {
-				if (!last)
-					nft_rbtree_set_start_cookie(priv, rbe);
-			} else if (!nft_rbtree_deactivate_same_interval(net, priv, rbe))
+			if (nft_rbtree_interval_start(rbe))
+				nft_rbtree_set_start_cookie(priv, rbe);
+			else if (!nft_rbtree_deactivate_same_interval(net, priv, rbe))
 				return NULL;
 
 			nft_rbtree_flush(net, set, &rbe->priv);
-- 
cgit v1.2.3


From a3aca98aec9a278ee56da4f8013bfa1dd1a1c298 Mon Sep 17 00:00:00 2001
From: Eric Woudstra <ericwouds@gmail.com>
Date: Tue, 10 Mar 2026 15:39:33 +0100
Subject: netfilter: nf_flow_table_ip: reset mac header before vlan push

With double vlan tagged packets in the fastpath, getting the error:

skb_vlan_push got skb with skb->data not at mac header (offset 18)

Call skb_reset_mac_header() before calling skb_vlan_push().

Fixes: c653d5a78f34 ("netfilter: flowtable: inline vlan encapsulation in xmit path")
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_flow_table_ip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 3fdb10d9bf7f..fd56d663cb5b 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -738,6 +738,7 @@ static int nf_flow_encap_push(struct sk_buff *skb,
 		switch (tuple->encap[i].proto) {
 		case htons(ETH_P_8021Q):
 		case htons(ETH_P_8021AD):
+			skb_reset_mac_header(skb);
 			if (skb_vlan_push(skb, tuple->encap[i].proto,
 					  tuple->encap[i].id) < 0)
 				return -1;
-- 
cgit v1.2.3


From 1e3a3593162c96e8a8de48b1e14f60c3b57fca8a Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Thu, 12 Mar 2026 02:29:32 +0000
Subject: netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In decode_int(), the CONS case calls get_bits(bs, 2) to read a length
value, then calls get_uint(bs, len) without checking that len bytes
remain in the buffer. The existing boundary check only validates the
2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint()
reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte
slab-out-of-bounds read.

Add a boundary check for len bytes after get_bits() and before
get_uint().

Fixes: 5e35941d9901 ("[NETFILTER]: Add H.323 conntrack/NAT helper")
Reported-by: Klaudia Kloc <klaudia@vidocsecurity.com>
Reported-by: Dawid Moczadło <dawid@vidocsecurity.com>
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_h323_asn1.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index 62aa22a07876..c972e9488e16 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -331,6 +331,8 @@ static int decode_int(struct bitstr *bs, const struct field_t *f,
 		if (nf_h323_error_boundary(bs, 0, 2))
 			return H323_ERROR_BOUND;
 		len = get_bits(bs, 2) + 1;
+		if (nf_h323_error_boundary(bs, len, 0))
+			return H323_ERROR_BOUND;
 		BYTE_ALIGN(bs);
 		if (base && (f->attr & DECODE)) {	/* timeToLive */
 			unsigned int v = get_uint(bs, len) + f->lb;
-- 
cgit v1.2.3


From 0548a13b5a145b16e4da0628b5936baf35f51b43 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 12 Mar 2026 12:38:59 +0100
Subject: nf_tables: nft_dynset: fix possible stateful expression memleak in
 error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If cloning the second stateful expression in the element via GFP_ATOMIC
fails, then the first stateful expression remains in place without being
released.

   unreferenced object (percpu) 0x607b97e9cab8 (size 16):
     comm "softirq", pid 0, jiffies 4294931867
     hex dump (first 16 bytes on cpu 3):
       00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
     backtrace (crc 0):
       pcpu_alloc_noprof+0x453/0xd80
       nft_counter_clone+0x9c/0x190 [nf_tables]
       nft_expr_clone+0x8f/0x1b0 [nf_tables]
       nft_dynset_new+0x2cb/0x5f0 [nf_tables]
       nft_rhash_update+0x236/0x11c0 [nf_tables]
       nft_dynset_eval+0x11f/0x670 [nf_tables]
       nft_do_chain+0x253/0x1700 [nf_tables]
       nft_do_chain_ipv4+0x18d/0x270 [nf_tables]
       nf_hook_slow+0xaa/0x1e0
       ip_local_deliver+0x209/0x330

Fixes: 563125a73ac3 ("netfilter: nftables: generalize set extension to support for several expressions")
Reported-by: Gurpreet Shergill <giki.shergill@proton.me>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     |  4 ++--
 net/netfilter/nft_dynset.c        | 10 +++++++++-
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 6299af4ef423..ec8a8ec9c0aa 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -874,6 +874,8 @@ struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set,
 					u64 timeout, u64 expiration, gfp_t gfp);
 int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
 			    struct nft_expr *expr_array[]);
+void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
+			       struct nft_set_elem_expr *elem_expr);
 void nft_set_elem_destroy(const struct nft_set *set,
 			  const struct nft_elem_priv *elem_priv,
 			  bool destroy_expr);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4ccdd33cf133..9b1c8d0a35fb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6744,8 +6744,8 @@ static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
 	}
 }
 
-static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
-				      struct nft_set_elem_expr *elem_expr)
+void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
+			       struct nft_set_elem_expr *elem_expr)
 {
 	struct nft_expr *expr;
 	u32 size;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 7807d8129664..9123277be03c 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -30,18 +30,26 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv,
 				 const struct nft_set_ext *ext)
 {
 	struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
+	struct nft_ctx ctx = {
+		.net	= read_pnet(&priv->set->net),
+		.family	= priv->set->table->family,
+	};
 	struct nft_expr *expr;
 	int i;
 
 	for (i = 0; i < priv->num_exprs; i++) {
 		expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
 		if (nft_expr_clone(expr, priv->expr_array[i], GFP_ATOMIC) < 0)
-			return -1;
+			goto err_out;
 
 		elem_expr->size += priv->expr_array[i]->ops->size;
 	}
 
 	return 0;
+err_out:
+	nft_set_elem_expr_destroy(&ctx, elem_expr);
+
+	return -1;
 }
 
 struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
-- 
cgit v1.2.3


From 36eae0956f659e48d5366d9b083d9417f3263ddc Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 12 Mar 2026 13:48:47 +0100
Subject: netfilter: nft_ct: drop pending enqueued packets on removal

Packets sitting in nfqueue might hold a reference to:

- templates that specify the conntrack zone, because a percpu area is
  used and module removal is possible.
- conntrack timeout policies and helper, where object removal leave
  a stale reference.

Since these objects can just go away, drop enqueued packets to avoid
stale reference to them.

If there is a need for finer grain removal, this logic can be revisited
to make selective packet drop upon dependencies.

Fixes: 7e0b2b57f01d ("netfilter: nft_ct: add ct timeout support")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_ct.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 47d3ef109a99..128ff8155b5d 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
+#include "nf_internals.h"
 
 struct nft_ct_helper_obj  {
 	struct nf_conntrack_helper *helper4;
@@ -543,6 +544,7 @@ static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv)
 #endif
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	case NFT_CT_ZONE:
+		nf_queue_nf_hook_drop(ctx->net);
 		mutex_lock(&nft_ct_pcpu_mutex);
 		if (--nft_ct_pcpu_template_refcnt == 0)
 			nft_ct_tmpl_put_pcpu();
@@ -1015,6 +1017,7 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx,
 	struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
 	struct nf_ct_timeout *timeout = priv->timeout;
 
+	nf_queue_nf_hook_drop(ctx->net);
 	nf_ct_untimeout(ctx->net, timeout);
 	nf_ct_netns_put(ctx->net, ctx->family);
 	kfree(priv->timeout);
@@ -1147,6 +1150,7 @@ static void nft_ct_helper_obj_destroy(const struct nft_ctx *ctx,
 {
 	struct nft_ct_helper_obj *priv = nft_obj_data(obj);
 
+	nf_queue_nf_hook_drop(ctx->net);
 	if (priv->helper4)
 		nf_conntrack_helper_put(priv->helper4);
 	if (priv->helper6)
-- 
cgit v1.2.3


From f62a218a946b19bb59abdd5361da85fa4606b96b Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 12 Mar 2026 13:48:48 +0100
Subject: netfilter: xt_CT: drop pending enqueued packets on template removal

Templates refer to objects that can go away while packets are sitting in
nfqueue refer to:

- helper, this can be an issue on module removal.
- timeout policy, nfnetlink_cttimeout might remove it.

The use of templates with zone and event cache filter are safe, since
this just copies values.

Flush these enqueued packets in case the template rule gets removed.

Fixes: 24de58f46516 ("netfilter: xt_CT: allow to attach timeout policy + glue code")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_CT.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 3ba94c34297c..498f5871c84a 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -16,6 +16,7 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
+#include "nf_internals.h"
 
 static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct)
 {
@@ -283,6 +284,9 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
 	struct nf_conn_help *help;
 
 	if (ct) {
+		if (info->helper[0] || info->timeout[0])
+			nf_queue_nf_hook_drop(par->net);
+
 		help = nfct_help(ct);
 		xt_ct_put_helper(help);
 
-- 
cgit v1.2.3


From 00050ec08cecfda447e1209b388086d76addda3a Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Thu, 12 Mar 2026 14:59:49 +0000
Subject: netfilter: xt_time: use unsigned int for monthday bit shift
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The monthday field can be up to 31, and shifting a signed integer 1
by 31 positions (1 << 31) is undefined behavior in C, as the result
overflows a 32-bit signed int. Use 1U to ensure well-defined behavior
for all valid monthday values.

Change the weekday shift to 1U as well for consistency.

Fixes: ee4411a1b1e0 ("[NETFILTER]: x_tables: add xt_time match")
Reported-by: Klaudia Kloc <klaudia@vidocsecurity.com>
Reported-by: Dawid Moczadło <dawid@vidocsecurity.com>
Tested-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_time.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c
index 00319d2a54da..d9d74011bb64 100644
--- a/net/netfilter/xt_time.c
+++ b/net/netfilter/xt_time.c
@@ -223,13 +223,13 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	localtime_2(&current_time, stamp);
 
-	if (!(info->weekdays_match & (1 << current_time.weekday)))
+	if (!(info->weekdays_match & (1U << current_time.weekday)))
 		return false;
 
 	/* Do not spend time computing monthday if all days match anyway */
 	if (info->monthdays_match != XT_TIME_ALL_MONTHDAYS) {
 		localtime_3(&current_time, stamp);
-		if (!(info->monthdays_match & (1 << current_time.monthday)))
+		if (!(info->monthdays_match & (1U << current_time.monthday)))
 			return false;
 	}
 
-- 
cgit v1.2.3


From f173d0f4c0f689173f8cdac79991043a4a89bf66 Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Thu, 12 Mar 2026 14:49:50 +0000
Subject: netfilter: nf_conntrack_h323: check for zero length in DecodeQ931()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In DecodeQ931(), the UserUserIE code path reads a 16-bit length from
the packet, then decrements it by 1 to skip the protocol discriminator
byte before passing it to DecodeH323_UserInformation(). If the encoded
length is 0, the decrement wraps to -1, which is then passed as a
large value to the decoder, leading to an out-of-bounds read.

Add a check to ensure len is positive after the decrement.

Fixes: 5e35941d9901 ("[NETFILTER]: Add H.323 conntrack/NAT helper")
Reported-by: Klaudia Kloc <klaudia@vidocsecurity.com>
Reported-by: Dawid Moczadło <dawid@vidocsecurity.com>
Tested-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_h323_asn1.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c
index c972e9488e16..7b1497ed97d2 100644
--- a/net/netfilter/nf_conntrack_h323_asn1.c
+++ b/net/netfilter/nf_conntrack_h323_asn1.c
@@ -924,6 +924,8 @@ int DecodeQ931(unsigned char *buf, size_t sz, Q931 *q931)
 				break;
 			p++;
 			len--;
+			if (len <= 0)
+				break;
 			return DecodeH323_UserInformation(buf, p, len,
 							  &q931->UUIE);
 		}
-- 
cgit v1.2.3


From d0d9b1f4f5391e6a00cee81d73ed2e8f98446d5f Mon Sep 17 00:00:00 2001
From: Vyacheslav Vahnenko <vahnenko2003@gmail.com>
Date: Fri, 13 Mar 2026 15:36:38 +0300
Subject: USB: ezcap401 needs USB_QUIRK_NO_BOS to function on 10gbs usb speed

Add USB_QUIRK_NO_BOS for ezcap401 capture card, without it dmesg will show
"unable to get BOS descriptor or descriptor too short" and "unable to
read config index 0 descriptor/start: -71" errors and device will not
able to work at full speed at 10gbs

Signed-off-by: Vyacheslav Vahnenko <vahnenko2003@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260313123638.20481-1-vahnenko2003@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index e3f402e0c351..5523a8e29021 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -589,6 +589,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */
 	{ USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* ezcap401 - BOS descriptor fetch hangs at SuperSpeed Plus */
+	{ USB_DEVICE(0x32ed, 0x0401), .driver_info = USB_QUIRK_NO_BOS },
+
 	/* DELL USB GEN2 */
 	{ USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME },
 
-- 
cgit v1.2.3


From 6922db250422a0dfee34de322f86b7a73d713d33 Mon Sep 17 00:00:00 2001
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Date: Thu, 12 Mar 2026 16:02:53 +0000
Subject: mshv: Fix use-after-free in mshv_map_user_memory error path

In the error path of mshv_map_user_memory(), calling vfree() directly on
the region leaves the MMU notifier registered. When userspace later unmaps
the memory, the notifier fires and accesses the freed region, causing a
use-after-free and potential kernel panic.

Replace vfree() with mshv_partition_put() to properly unregister
the MMU notifier before freeing the region.

Fixes: b9a66cd5ccbb9 ("mshv: Add support for movable memory regions")
Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_root_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index e281311b6a9d..6f42423f7faa 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -1347,7 +1347,7 @@ mshv_map_user_memory(struct mshv_partition *partition,
 	return 0;
 
 errout:
-	vfree(region);
+	mshv_region_put(region);
 	return ret;
 }
 
-- 
cgit v1.2.3


From b2ae73d954f71c7dd605eecfd817ed018dce7cc7 Mon Sep 17 00:00:00 2001
From: Saurabh Sengar <ssengar@linux.microsoft.com>
Date: Thu, 12 Mar 2026 21:21:48 -0700
Subject: MAINTAINERS: Update maintainers for Hyper-V DRM driver

Add myself, Dexuan, and Long as maintainers. Deepak is stepping down
from these responsibilities.

Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 MAINTAINERS | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..2bb7eae97d2e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8002,7 +8002,9 @@ F:	Documentation/devicetree/bindings/display/himax,hx8357.yaml
 F:	drivers/gpu/drm/tiny/hx8357d.c
 
 DRM DRIVER FOR HYPERV SYNTHETIC VIDEO DEVICE
-M:	Deepak Rawat <drawat.floss@gmail.com>
+M:	Dexuan Cui <decui@microsoft.com>
+M:	Long Li <longli@microsoft.com>
+M:	Saurabh Sengar <ssengar@linux.microsoft.com>
 L:	linux-hyperv@vger.kernel.org
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
-- 
cgit v1.2.3


From 5c52607c43c397b79a9852ce33fc61de58c3645c Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 4 Mar 2026 12:39:34 -0800
Subject: crypto: ccp - Fix leaking the same page twice

Commit 551120148b67 ("crypto: ccp - Fix a case where SNP_SHUTDOWN is
missed") fixed a case where SNP is left in INIT state if page reclaim
fails. It removes the transition to the INIT state for this command and
adjusts the page state management.

While doing this, it added a call to snp_leak_pages() after a call to
snp_reclaim_pages() failed. Since snp_reclaim_pages() already calls
snp_leak_pages() internally on the pages it fails to reclaim, calling
it again leaks the exact same page twice.

Fix by removing the extra call to snp_leak_pages().

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Assisted-by: Gemini:gemini-3.1-pro
Fixes: 551120148b67 ("crypto: ccp - Fix a case where SNP_SHUTDOWN is missed")
Cc: Tycho Andersen (AMD) <tycho@kernel.org>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Tycho Andersen (AMD) <tycho@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sev-dev.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index 8b2dfc11289b..aebf4dad545e 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -2408,10 +2408,8 @@ static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp)
 		 * in Firmware state on failure. Use snp_reclaim_pages() to
 		 * transition either case back to Hypervisor-owned state.
 		 */
-		if (snp_reclaim_pages(__pa(data), 1, true)) {
-			snp_leak_pages(__page_to_pfn(status_page), 1);
+		if (snp_reclaim_pages(__pa(data), 1, true))
 			return -EFAULT;
-		}
 	}
 
 	if (ret)
-- 
cgit v1.2.3


From 0d4aef630be9d5f9c1227d07669c26c4383b5ad0 Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Sat, 14 Mar 2026 07:11:27 +0000
Subject: batman-adv: avoid OGM aggregation when skb tailroom is insufficient

When OGM aggregation state is toggled at runtime, an existing forwarded
packet may have been allocated with only packet_len bytes, while a later
packet can still be selected for aggregation. Appending in this case can
hit skb_put overflow conditions.

Reject aggregation when the target skb tailroom cannot accommodate the new
packet. The caller then falls back to creating a new forward packet
instead of appending.

Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol")
Cc: stable@vger.kernel.org
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Ao Zhou <n05ec@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index b75c2228e69a..f28e9cbf8ad5 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -473,6 +473,9 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	if (aggregated_bytes > max_bytes)
 		return false;
 
+	if (skb_tailroom(forw_packet->skb) < packet_len)
+		return false;
+
 	if (packet_num >= BATADV_MAX_AGGREGATION_PACKETS)
 		return false;
 
-- 
cgit v1.2.3


From dbbd550d7c8d90d3af9fe8a12a9caff077ddb8e3 Mon Sep 17 00:00:00 2001
From: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Date: Sat, 14 Mar 2026 03:29:33 +0200
Subject: interconnect: qcom: sm8450: Fix NULL pointer dereference in
 icc_link_nodes()

The change to dynamic IDs for SM8450 platform interconnects left two links
unconverted, fix it to avoid the NULL pointer dereference in runtime,
when a pointer to a destination interconnect is not valid:

    Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
    <...>
    Call trace:
      icc_link_nodes+0x3c/0x100 (P)
      qcom_icc_rpmh_probe+0x1b4/0x528
      platform_probe+0x64/0xc0
      really_probe+0xc4/0x2a8
      __driver_probe_device+0x80/0x140
      driver_probe_device+0x48/0x170
      __device_attach_driver+0xc0/0x148
      bus_for_each_drv+0x88/0xf0
      __device_attach+0xb0/0x1c0
      device_initial_probe+0x58/0x68
      bus_probe_device+0x40/0xb8
      deferred_probe_work_func+0x90/0xd0
      process_one_work+0x15c/0x3c0
      worker_thread+0x2e8/0x400
      kthread+0x150/0x208
      ret_from_fork+0x10/0x20
     Code: 900310f4 911d6294 91008280 94176078 (f94002a0)
     ---[ end trace 0000000000000000 ]---
     Kernel panic - not syncing: Oops: Fatal exception

Fixes: 51513bec806f ("interconnect: qcom: sm8450: convert to dynamic IDs")
Signed-off-by: Vladimir Zapolskiy <vladimir.zapolskiy@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://msgid.link/20260314012933.350644-1-vladimir.zapolskiy@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/qcom/sm8450.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/interconnect/qcom/sm8450.c b/drivers/interconnect/qcom/sm8450.c
index 669a638bf3ef..c88327d200ac 100644
--- a/drivers/interconnect/qcom/sm8450.c
+++ b/drivers/interconnect/qcom/sm8450.c
@@ -800,7 +800,7 @@ static struct qcom_icc_node qhs_compute_cfg = {
 	.channels = 1,
 	.buswidth = 4,
 	.num_links = 1,
-	.link_nodes = { MASTER_CDSP_NOC_CFG },
+	.link_nodes = { &qhm_nsp_noc_config },
 };
 
 static struct qcom_icc_node qhs_cpr_cx = {
@@ -874,7 +874,7 @@ static struct qcom_icc_node qhs_lpass_cfg = {
 	.channels = 1,
 	.buswidth = 4,
 	.num_links = 1,
-	.link_nodes = { MASTER_CNOC_LPASS_AG_NOC },
+	.link_nodes = { &qhm_config_noc },
 };
 
 static struct qcom_icc_node qhs_mss_cfg = {
-- 
cgit v1.2.3


From 9978d74031f25fde575bef3e4e3e35c5009091ce Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Wed, 4 Mar 2026 22:14:32 +0800
Subject: iio: proximity: rfd77402: Fix completion race condition in IRQ mode

In IRQ mode, the completion was being reinitialized after the
measurement command had already been sent to the hardware. This
created a race condition where the IRQ handler could call complete()
before reinit_completion() was executed. Consequently,
wait_for_completion_timeout() would fail to see the signal and wait
until it timed out.

Move reinit_completion() to occur before the measurement command is
triggered to ensure the synchronization primitive is ready to
capture the interrupt.

Fixes: dc81be96a73a ("iio: proximity: rfd77402: Add interrupt handling support")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Shrikant Raskar <raskar.shree97@gmail.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/rfd77402.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/proximity/rfd77402.c b/drivers/iio/proximity/rfd77402.c
index 6afdbfca3e5a..81b8daf17a54 100644
--- a/drivers/iio/proximity/rfd77402.c
+++ b/drivers/iio/proximity/rfd77402.c
@@ -173,10 +173,8 @@ static int rfd77402_wait_for_result(struct rfd77402_data *data)
 	struct i2c_client *client = data->client;
 	int val, ret;
 
-	if (data->irq_en) {
-		reinit_completion(&data->completion);
+	if (data->irq_en)
 		return rfd77402_wait_for_irq(data);
-	}
 
 	/*
 	 * As per RFD77402 datasheet section '3.1.1 Single Measure', the
@@ -204,6 +202,9 @@ static int rfd77402_measure(struct rfd77402_data *data)
 	if (ret < 0)
 		return ret;
 
+	if (data->irq_en)
+		reinit_completion(&data->completion);
+
 	ret = i2c_smbus_write_byte_data(client, RFD77402_CMD_R,
 					RFD77402_CMD_SINGLE |
 					RFD77402_CMD_VALID);
-- 
cgit v1.2.3


From 9e22e9c4a5bd208a2d17f0b1a8414c170b4e5939 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 5 Mar 2026 15:25:18 -0700
Subject: ARM: multi_v7_defconfig: Drop duplicate CONFIG_TI_PRUSS=m

Commit ee1ab82ee032 ("ARM: defconfig: move entries") added a duplicate
instance of CONFIG_TI_PRUSS=m, causing a Kconfig warning:

  arch/arm/configs/multi_v7_defconfig:1152:warning: override: reassigning to symbol TI_PRUSS

Drop the first instance, as the second instance added by the
aforementioned change is where savedefconfig puts it.

Fixes: ee1ab82ee032 ("ARM: defconfig: move entries")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20260305-arm-defconfig-drop-duplicate-ti-pruss-v1-1-2839e3b42a8b@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/configs/multi_v7_defconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index f75d75cf91c8..70d05f74049e 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -279,7 +279,6 @@ CONFIG_TI_CPSW_SWITCHDEV=y
 CONFIG_TI_CPTS=y
 CONFIG_TI_KEYSTONE_NETCP=y
 CONFIG_TI_KEYSTONE_NETCP_ETHSS=y
-CONFIG_TI_PRUSS=m
 CONFIG_TI_PRUETH=m
 CONFIG_XILINX_EMACLITE=y
 CONFIG_SFP=m
-- 
cgit v1.2.3


From 79a86a6cc3669416a21fef32d0767d39ba84b3aa Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 7 Mar 2026 19:44:09 -0600
Subject: iio: orientation: hid-sensor-rotation: add timestamp hack to not
 break userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a hack to push two timestamps in the hid-sensor-rotation scan data
to avoid breaking userspace applications that depend on the timestamp
being at the incorrect location in the scan data due to unintentional
misalignment in older kernels.

When this driver was written, the timestamp was in the correct location
because of the way iio_compute_scan_bytes() was implemented at the time.
(Samples were 24 bytes each.) Then commit 883f61653069 ("iio: buffer:
align the size of scan bytes to size of the largest element") changed
the computed scan_bytes to be a different size (32 bytes), which caused
iio_push_to_buffers_with_timestamp() to place the timestamp at an
incorrect offset.

There have been long periods of time (6 years each) where the timestamp
was in either location, so to not break either case, we open-code the
timestamps to be pushed to both locations in the scan data.

Reported-by: Jonathan Cameron <jic23@kernel.org>
Closes: https://lore.kernel.org/linux-iio/20260215162351.79f40b32@jic23-huawei/
Fixes: 883f61653069 ("iio: buffer: align the size of scan bytes to size of the largest element")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/orientation/hid-sensor-rotation.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/orientation/hid-sensor-rotation.c b/drivers/iio/orientation/hid-sensor-rotation.c
index 6806481873be..5a5e6e4fbe34 100644
--- a/drivers/iio/orientation/hid-sensor-rotation.c
+++ b/drivers/iio/orientation/hid-sensor-rotation.c
@@ -20,7 +20,12 @@ struct dev_rot_state {
 	struct hid_sensor_hub_attribute_info quaternion;
 	struct {
 		IIO_DECLARE_QUATERNION(s32, sampled_vals);
-		aligned_s64 timestamp;
+		/*
+		 * ABI regression avoidance: There are two copies of the same
+		 * timestamp in case of userspace depending on broken alignment
+		 * from older kernels.
+		 */
+		aligned_s64 timestamp[2];
 	} scan;
 	int scale_pre_decml;
 	int scale_post_decml;
@@ -154,8 +159,19 @@ static int dev_rot_proc_event(struct hid_sensor_hub_device *hsdev,
 		if (!rot_state->timestamp)
 			rot_state->timestamp = iio_get_time_ns(indio_dev);
 
-		iio_push_to_buffers_with_timestamp(indio_dev, &rot_state->scan,
-						   rot_state->timestamp);
+		/*
+		 * ABI regression avoidance: IIO previously had an incorrect
+		 * implementation of iio_push_to_buffers_with_timestamp() that
+		 * put the timestamp in the last 8 bytes of the buffer, which
+		 * was incorrect according to the IIO ABI. To avoid breaking
+		 * userspace that may be depending on this broken behavior, we
+		 * put the timestamp in both the correct place [0] and the old
+		 * incorrect place [1].
+		 */
+		rot_state->scan.timestamp[0] = rot_state->timestamp;
+		rot_state->scan.timestamp[1] = rot_state->timestamp;
+
+		iio_push_to_buffers(indio_dev, &rot_state->scan);
 
 		rot_state->timestamp = 0;
 	}
-- 
cgit v1.2.3


From 7bae956cac0433c4d41aac9f1d04e42694e0b706 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 13 Mar 2026 16:06:24 +0800
Subject: ALSA: hda/realtek: add quirk for Lenovo Yoga 7 2-in-1 16AKP10

This machine is equipped with ALC287 and requires the quirk
ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN to fix the issue
where the bass speakers are not configured and the speaker
volume cannot be controlled.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221210
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260313080624.1395362-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index ab4b22fcb72e..8d0767db9802 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7575,6 +7575,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
 	SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	HDA_CODEC_QUIRK(0x17aa, 0x391c, "Lenovo Yoga 7 2-in-1 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+	HDA_CODEC_QUIRK(0x17aa, 0x391d, "Lenovo Yoga 7 2-in-1 16AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38b7, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
-- 
cgit v1.2.3


From 59f68dc1d8df3142cb58fd2568966a9bb7b0ed8a Mon Sep 17 00:00:00 2001
From: Matthew Schwartz <matthew.schwartz@linux.dev>
Date: Fri, 13 Mar 2026 10:25:03 -0700
Subject: ALSA: hda/realtek: Add quirk for ASUS ROG Flow Z13-KJP GZ302EAC

Fixes lack of audio output on the ASUS ROG Flow Z13-KJP GZ302EAC model,
similar to the ASUS ROG Flow Z13 GZ302EA.

Signed-off-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Link: https://patch.msgid.link/20260313172503.285846-1-matthew.schwartz@linux.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 8d0767db9802..b8aba01ef261 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7206,6 +7206,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x14f2, "ASUS VivoBook X515JA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1514, "ASUS ROG Flow Z13 GZ302EAC", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
-- 
cgit v1.2.3


From 922814879542c2e397b0e9641fd36b8202a8e555 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Mon, 9 Mar 2026 21:29:08 +0530
Subject: atm: lec: fix use-after-free in sock_def_readable()

A race condition exists between lec_atm_close() setting priv->lecd
to NULL and concurrent access to priv->lecd in send_to_lecd(),
lec_handle_bridge(), and lec_atm_send(). When the socket is freed
via RCU while another thread is still using it, a use-after-free
occurs in sock_def_readable() when accessing the socket's wait queue.

The root cause is that lec_atm_close() clears priv->lecd without
any synchronization, while callers dereference priv->lecd without
any protection against concurrent teardown.

Fix this by converting priv->lecd to an RCU-protected pointer:
- Mark priv->lecd as __rcu in lec.h
- Use rcu_assign_pointer() in lec_atm_close() and lecd_attach()
  for safe pointer assignment
- Use rcu_access_pointer() for NULL checks that do not dereference
  the pointer in lec_start_xmit(), lec_push(), send_to_lecd() and
  lecd_attach()
- Use rcu_read_lock/rcu_dereference/rcu_read_unlock in send_to_lecd(),
  lec_handle_bridge() and lec_atm_send() to safely access lecd
- Use rcu_assign_pointer() followed by synchronize_rcu() in
  lec_atm_close() to ensure all readers have completed before
  proceeding. This is safe since lec_atm_close() is called from
  vcc_release() which holds lock_sock(), a sleeping lock.
- Remove the manual sk_receive_queue drain from lec_atm_close()
  since vcc_destroy_socket() already drains it after lec_atm_close()
  returns.

v2: Switch from spinlock + sock_hold/put approach to RCU to properly
    fix the race. The v1 spinlock approach had two issues pointed out
    by Eric Dumazet:
    1. priv->lecd was still accessed directly after releasing the
       lock instead of using a local copy.
    2. The spinlock did not prevent packets being queued after
       lec_atm_close() drains sk_receive_queue since timer and
       workqueue paths bypass netif_stop_queue().

Note: Syzbot patch testing was attempted but the test VM terminated
    unexpectedly with "Connection to localhost closed by remote host",
    likely due to a QEMU AHCI emulation issue unrelated to this fix.
    Compile testing with "make W=1 net/atm/lec.o" passes cleanly.

Reported-by: syzbot+f50072212ab792c86925@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f50072212ab792c86925
Link: https://lore.kernel.org/all/20260309093614.502094-1-kartikey406@gmail.com/T/ [v1]
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260309155908.508768-1-kartikey406@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/lec.c | 72 ++++++++++++++++++++++++++++++++++++++---------------------
 net/atm/lec.h |  2 +-
 2 files changed, 48 insertions(+), 26 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index fb93c6e1c329..10e260acf602 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -154,10 +154,19 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
 					/* 0x01 is topology change */
 
 		priv = netdev_priv(dev);
-		atm_force_charge(priv->lecd, skb2->truesize);
-		sk = sk_atm(priv->lecd);
-		skb_queue_tail(&sk->sk_receive_queue, skb2);
-		sk->sk_data_ready(sk);
+		struct atm_vcc *vcc;
+
+		rcu_read_lock();
+		vcc = rcu_dereference(priv->lecd);
+		if (vcc) {
+			atm_force_charge(vcc, skb2->truesize);
+			sk = sk_atm(vcc);
+			skb_queue_tail(&sk->sk_receive_queue, skb2);
+			sk->sk_data_ready(sk);
+		} else {
+			dev_kfree_skb(skb2);
+		}
+		rcu_read_unlock();
 	}
 }
 #endif /* IS_ENABLED(CONFIG_BRIDGE) */
@@ -216,7 +225,7 @@ static netdev_tx_t lec_start_xmit(struct sk_buff *skb,
 	int is_rdesc;
 
 	pr_debug("called\n");
-	if (!priv->lecd) {
+	if (!rcu_access_pointer(priv->lecd)) {
 		pr_info("%s:No lecd attached\n", dev->name);
 		dev->stats.tx_errors++;
 		netif_stop_queue(dev);
@@ -449,10 +458,19 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
 				break;
 			skb2->len = sizeof(struct atmlec_msg);
 			skb_copy_to_linear_data(skb2, mesg, sizeof(*mesg));
-			atm_force_charge(priv->lecd, skb2->truesize);
-			sk = sk_atm(priv->lecd);
-			skb_queue_tail(&sk->sk_receive_queue, skb2);
-			sk->sk_data_ready(sk);
+			struct atm_vcc *vcc;
+
+			rcu_read_lock();
+			vcc = rcu_dereference(priv->lecd);
+			if (vcc) {
+				atm_force_charge(vcc, skb2->truesize);
+				sk = sk_atm(vcc);
+				skb_queue_tail(&sk->sk_receive_queue, skb2);
+				sk->sk_data_ready(sk);
+			} else {
+				dev_kfree_skb(skb2);
+			}
+			rcu_read_unlock();
 		}
 	}
 #endif /* IS_ENABLED(CONFIG_BRIDGE) */
@@ -468,23 +486,16 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
 
 static void lec_atm_close(struct atm_vcc *vcc)
 {
-	struct sk_buff *skb;
 	struct net_device *dev = (struct net_device *)vcc->proto_data;
 	struct lec_priv *priv = netdev_priv(dev);
 
-	priv->lecd = NULL;
+	rcu_assign_pointer(priv->lecd, NULL);
+	synchronize_rcu();
 	/* Do something needful? */
 
 	netif_stop_queue(dev);
 	lec_arp_destroy(priv);
 
-	if (skb_peek(&sk_atm(vcc)->sk_receive_queue))
-		pr_info("%s closing with messages pending\n", dev->name);
-	while ((skb = skb_dequeue(&sk_atm(vcc)->sk_receive_queue))) {
-		atm_return(vcc, skb->truesize);
-		dev_kfree_skb(skb);
-	}
-
 	pr_info("%s: Shut down!\n", dev->name);
 	module_put(THIS_MODULE);
 }
@@ -510,12 +521,14 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type,
 	     const unsigned char *mac_addr, const unsigned char *atm_addr,
 	     struct sk_buff *data)
 {
+	struct atm_vcc *vcc;
 	struct sock *sk;
 	struct sk_buff *skb;
 	struct atmlec_msg *mesg;
 
-	if (!priv || !priv->lecd)
+	if (!priv || !rcu_access_pointer(priv->lecd))
 		return -1;
+
 	skb = alloc_skb(sizeof(struct atmlec_msg), GFP_ATOMIC);
 	if (!skb)
 		return -1;
@@ -532,18 +545,27 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type,
 	if (atm_addr)
 		memcpy(&mesg->content.normal.atm_addr, atm_addr, ATM_ESA_LEN);
 
-	atm_force_charge(priv->lecd, skb->truesize);
-	sk = sk_atm(priv->lecd);
+	rcu_read_lock();
+	vcc = rcu_dereference(priv->lecd);
+	if (!vcc) {
+		rcu_read_unlock();
+		kfree_skb(skb);
+		return -1;
+	}
+
+	atm_force_charge(vcc, skb->truesize);
+	sk = sk_atm(vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk);
 
 	if (data != NULL) {
 		pr_debug("about to send %d bytes of data\n", data->len);
-		atm_force_charge(priv->lecd, data->truesize);
+		atm_force_charge(vcc, data->truesize);
 		skb_queue_tail(&sk->sk_receive_queue, data);
 		sk->sk_data_ready(sk);
 	}
 
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -618,7 +640,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb)
 
 		atm_return(vcc, skb->truesize);
 		if (*(__be16 *) skb->data == htons(priv->lecid) ||
-		    !priv->lecd || !(dev->flags & IFF_UP)) {
+		    !rcu_access_pointer(priv->lecd) || !(dev->flags & IFF_UP)) {
 			/*
 			 * Probably looping back, or if lecd is missing,
 			 * lecd has gone down
@@ -753,12 +775,12 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 		priv = netdev_priv(dev_lec[i]);
 	} else {
 		priv = netdev_priv(dev_lec[i]);
-		if (priv->lecd)
+		if (rcu_access_pointer(priv->lecd))
 			return -EADDRINUSE;
 	}
 	lec_arp_init(priv);
 	priv->itfnum = i;	/* LANE2 addition */
-	priv->lecd = vcc;
+	rcu_assign_pointer(priv->lecd, vcc);
 	vcc->dev = &lecatm_dev;
 	vcc_insert_socket(sk_atm(vcc));
 
diff --git a/net/atm/lec.h b/net/atm/lec.h
index be0e2667bd8c..ec85709bf818 100644
--- a/net/atm/lec.h
+++ b/net/atm/lec.h
@@ -91,7 +91,7 @@ struct lec_priv {
 						 */
 	spinlock_t lec_arp_lock;
 	struct atm_vcc *mcast_vcc;		/* Default Multicast Send VCC */
-	struct atm_vcc *lecd;
+	struct atm_vcc __rcu *lecd;
 	struct delayed_work lec_arp_work;	/* C10 */
 	unsigned int maximum_unknown_frame_count;
 						/*
-- 
cgit v1.2.3


From 48db892356d6cb80f6942885545de4a6dd8d2a29 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 19 Feb 2026 16:50:16 -0500
Subject: NFSD: Defer sub-object cleanup in export put callbacks

svc_export_put() calls path_put() and auth_domain_put() immediately
when the last reference drops, before the RCU grace period. RCU
readers in e_show() and c_show() access both ex_path (via
seq_path/d_path) and ex_client->name (via seq_escape) without
holding a reference. If cache_clean removes the entry and drops the
last reference concurrently, the sub-objects are freed while still
in use, producing a NULL pointer dereference in d_path.

Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or
ex_stats") moved kfree of ex_uuid and ex_stats into the
call_rcu callback, but left path_put() and auth_domain_put() running
before the grace period because both may sleep and call_rcu
callbacks execute in softirq context.

Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the
callback until after the RCU grace period and executes it in process
context where sleeping is permitted. This allows path_put() and
auth_domain_put() to be moved into the deferred callback alongside
the other resource releases. Apply the same fix to expkey_put(),
which has the identical pattern with ek_path and ek_client.

A dedicated workqueue scopes the shutdown drain to only NFSD
export release work items; flushing the shared
system_unbound_wq would stall on unrelated work from other
subsystems. nfsd_export_shutdown() uses rcu_barrier() followed
by flush_workqueue() to ensure all deferred release callbacks
complete before the export caches are destroyed.

Reported-by: Misbah Anjum N <misanjum@linux.ibm.com>
Closes: https://lore.kernel.org/linux-nfs/dcd371d3a95815a84ba7de52cef447b8@linux.ibm.com/
Fixes: c224edca7af0 ("nfsd: no need get cache ref when protected by rcu")
Fixes: 1b10f0b603c0 ("SUNRPC: no need get cache ref when protected by rcu")
Cc: stable@vger.kernel.org
Reviwed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Tested-by: Olga Kornievskaia <okorniev@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/export.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++--------
 fs/nfsd/export.h |  7 +++++--
 fs/nfsd/nfsctl.c |  8 ++++++-
 3 files changed, 66 insertions(+), 12 deletions(-)

diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 2a1499f2ad19..18933ca407be 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -36,19 +36,30 @@
  * second map contains a reference to the entry in the first map.
  */
 
+static struct workqueue_struct *nfsd_export_wq;
+
 #define	EXPKEY_HASHBITS		8
 #define	EXPKEY_HASHMAX		(1 << EXPKEY_HASHBITS)
 #define	EXPKEY_HASHMASK		(EXPKEY_HASHMAX -1)
 
-static void expkey_put(struct kref *ref)
+static void expkey_release(struct work_struct *work)
 {
-	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+	struct svc_expkey *key = container_of(to_rcu_work(work),
+					      struct svc_expkey, ek_rwork);
 
 	if (test_bit(CACHE_VALID, &key->h.flags) &&
 	    !test_bit(CACHE_NEGATIVE, &key->h.flags))
 		path_put(&key->ek_path);
 	auth_domain_put(key->ek_client);
-	kfree_rcu(key, ek_rcu);
+	kfree(key);
+}
+
+static void expkey_put(struct kref *ref)
+{
+	struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref);
+
+	INIT_RCU_WORK(&key->ek_rwork, expkey_release);
+	queue_rcu_work(nfsd_export_wq, &key->ek_rwork);
 }
 
 static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -353,11 +364,13 @@ static void export_stats_destroy(struct export_stats *stats)
 					    EXP_STATS_COUNTERS_NUM);
 }
 
-static void svc_export_release(struct rcu_head *rcu_head)
+static void svc_export_release(struct work_struct *work)
 {
-	struct svc_export *exp = container_of(rcu_head, struct svc_export,
-			ex_rcu);
+	struct svc_export *exp = container_of(to_rcu_work(work),
+					      struct svc_export, ex_rwork);
 
+	path_put(&exp->ex_path);
+	auth_domain_put(exp->ex_client);
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	export_stats_destroy(exp->ex_stats);
 	kfree(exp->ex_stats);
@@ -369,9 +382,8 @@ static void svc_export_put(struct kref *ref)
 {
 	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
 
-	path_put(&exp->ex_path);
-	auth_domain_put(exp->ex_client);
-	call_rcu(&exp->ex_rcu, svc_export_release);
+	INIT_RCU_WORK(&exp->ex_rwork, svc_export_release);
+	queue_rcu_work(nfsd_export_wq, &exp->ex_rwork);
 }
 
 static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -1478,6 +1490,36 @@ const struct seq_operations nfs_exports_op = {
 	.show	= e_show,
 };
 
+/**
+ * nfsd_export_wq_init - allocate the export release workqueue
+ *
+ * Called once at module load. The workqueue runs deferred svc_export and
+ * svc_expkey release work scheduled by queue_rcu_work() in the cache put
+ * callbacks.
+ *
+ * Return values:
+ *   %0: workqueue allocated
+ *   %-ENOMEM: allocation failed
+ */
+int nfsd_export_wq_init(void)
+{
+	nfsd_export_wq = alloc_workqueue("nfsd_export", WQ_UNBOUND, 0);
+	if (!nfsd_export_wq)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * nfsd_export_wq_shutdown - drain and free the export release workqueue
+ *
+ * Called once at module unload. Per-namespace teardown in
+ * nfsd_export_shutdown() has already drained all deferred work.
+ */
+void nfsd_export_wq_shutdown(void)
+{
+	destroy_workqueue(nfsd_export_wq);
+}
+
 /*
  * Initialize the exports module.
  */
@@ -1539,6 +1581,9 @@ nfsd_export_shutdown(struct net *net)
 
 	cache_unregister_net(nn->svc_expkey_cache, net);
 	cache_unregister_net(nn->svc_export_cache, net);
+	/* Drain deferred export and expkey release work. */
+	rcu_barrier();
+	flush_workqueue(nfsd_export_wq);
 	cache_destroy_net(nn->svc_expkey_cache, net);
 	cache_destroy_net(nn->svc_export_cache, net);
 	svcauth_unix_purge(net);
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index d2b09cd76145..b05399374574 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -7,6 +7,7 @@
 
 #include <linux/sunrpc/cache.h>
 #include <linux/percpu_counter.h>
+#include <linux/workqueue.h>
 #include <uapi/linux/nfsd/export.h>
 #include <linux/nfs4.h>
 
@@ -75,7 +76,7 @@ struct svc_export {
 	u32			ex_layout_types;
 	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
-	struct rcu_head		ex_rcu;
+	struct rcu_work		ex_rwork;
 	unsigned long		ex_xprtsec_modes;
 	struct export_stats	*ex_stats;
 };
@@ -92,7 +93,7 @@ struct svc_expkey {
 	u32			ek_fsid[6];
 
 	struct path		ek_path;
-	struct rcu_head		ek_rcu;
+	struct rcu_work		ek_rwork;
 };
 
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
@@ -110,6 +111,8 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
 /*
  * Function declarations
  */
+int			nfsd_export_wq_init(void);
+void			nfsd_export_wq_shutdown(void);
 int			nfsd_export_init(struct net *);
 void			nfsd_export_shutdown(struct net *);
 void			nfsd_export_flush(struct net *);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 369da69d5efe..fe3b3f206aa9 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2259,9 +2259,12 @@ static int __init init_nfsd(void)
 	if (retval)
 		goto out_free_pnfs;
 	nfsd_lockd_init();	/* lockd->nfsd callbacks */
+	retval = nfsd_export_wq_init();
+	if (retval)
+		goto out_free_lockd;
 	retval = register_pernet_subsys(&nfsd_net_ops);
 	if (retval < 0)
-		goto out_free_lockd;
+		goto out_free_export_wq;
 	retval = register_cld_notifier();
 	if (retval)
 		goto out_free_subsys;
@@ -2290,6 +2293,8 @@ out_free_cld:
 	unregister_cld_notifier();
 out_free_subsys:
 	unregister_pernet_subsys(&nfsd_net_ops);
+out_free_export_wq:
+	nfsd_export_wq_shutdown();
 out_free_lockd:
 	nfsd_lockd_shutdown();
 	nfsd_drc_slab_free();
@@ -2310,6 +2315,7 @@ static void __exit exit_nfsd(void)
 	nfsd4_destroy_laundry_wq();
 	unregister_cld_notifier();
 	unregister_pernet_subsys(&nfsd_net_ops);
+	nfsd_export_wq_shutdown();
 	nfsd_drc_slab_free();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
-- 
cgit v1.2.3


From e7fcf179b82d3a3730fd8615da01b087cc654d0b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 19 Feb 2026 16:50:17 -0500
Subject: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd

The /proc/fs/nfs/exports proc entry is created at module init
and persists for the module's lifetime. exports_proc_open()
captures the caller's current network namespace and stores
its svc_export_cache in seq->private, but takes no reference
on the namespace. If the namespace is subsequently torn down
(e.g. container destruction after the opener does setns() to a
different namespace), nfsd_net_exit() calls nfsd_export_shutdown()
which frees the cache. Subsequent reads on the still-open fd
dereference the freed cache_detail, walking a freed hash table.

Hold a reference on the struct net for the lifetime of the open
file descriptor. This prevents nfsd_net_exit() from running --
and thus prevents nfsd_export_shutdown() from freeing the cache
-- while any exports fd is open. cache_detail already stores
its net pointer (cd->net, set by cache_create_net()), so
exports_release() can retrieve it without additional per-file
storage.

Reported-by: Misbah Anjum N <misanjum@linux.ibm.com>
Closes: https://lore.kernel.org/linux-nfs/dcd371d3a95815a84ba7de52cef447b8@linux.ibm.com/
Fixes: 96d851c4d28d ("nfsd: use proper net while reading "exports" file")
Cc: stable@vger.kernel.org
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Tested-by: Olga Kornievskaia <okorniev@redhat.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index fe3b3f206aa9..d67c169526d0 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -149,9 +149,19 @@ static int exports_net_open(struct net *net, struct file *file)
 
 	seq = file->private_data;
 	seq->private = nn->svc_export_cache;
+	get_net(net);
 	return 0;
 }
 
+static int exports_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct cache_detail *cd = seq->private;
+
+	put_net(cd->net);
+	return seq_release(inode, file);
+}
+
 static int exports_nfsd_open(struct inode *inode, struct file *file)
 {
 	return exports_net_open(inode->i_sb->s_fs_info, file);
@@ -161,7 +171,7 @@ static const struct file_operations exports_nfsd_operations = {
 	.open		= exports_nfsd_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= exports_release,
 };
 
 static int export_features_show(struct seq_file *m, void *v)
@@ -1376,7 +1386,7 @@ static const struct proc_ops exports_proc_ops = {
 	.proc_open	= exports_proc_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
-	.proc_release	= seq_release,
+	.proc_release	= exports_release,
 };
 
 static int create_proc_exports_entry(void)
-- 
cgit v1.2.3


From 17ad31b3a43b72aec3a3d83605891e1397d0d065 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 23 Feb 2026 12:09:58 -0500
Subject: sunrpc: fix cache_request leak in cache_release

When a reader's file descriptor is closed while in the middle of reading
a cache_request (rp->offset != 0), cache_release() decrements the
request's readers count but never checks whether it should free the
request.

In cache_read(), when readers drops to 0 and CACHE_PENDING is clear, the
cache_request is removed from the queue and freed along with its buffer
and cache_head reference. cache_release() lacks this cleanup.

The only other path that frees requests with readers == 0 is
cache_dequeue(), but it runs only when CACHE_PENDING transitions from
set to clear. If that transition already happened while readers was
still non-zero, cache_dequeue() will have skipped the request, and no
subsequent call will clean it up.

Add the same cleanup logic from cache_read() to cache_release(): after
decrementing readers, check if it reached 0 with CACHE_PENDING clear,
and if so, dequeue and free the cache_request.

Reported-by: NeilBrown <neilb@ownmail.net>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/cache.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 131090f31e6a..6f6e0d4928af 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1061,14 +1061,25 @@ static int cache_release(struct inode *inode, struct file *filp,
 	struct cache_reader *rp = filp->private_data;
 
 	if (rp) {
+		struct cache_request *rq = NULL;
+
 		spin_lock(&queue_lock);
 		if (rp->offset) {
 			struct cache_queue *cq;
-			for (cq= &rp->q; &cq->list != &cd->queue;
-			     cq = list_entry(cq->list.next, struct cache_queue, list))
+			for (cq = &rp->q; &cq->list != &cd->queue;
+			     cq = list_entry(cq->list.next,
+					     struct cache_queue, list))
 				if (!cq->reader) {
-					container_of(cq, struct cache_request, q)
-						->readers--;
+					struct cache_request *cr =
+						container_of(cq,
+						struct cache_request, q);
+					cr->readers--;
+					if (cr->readers == 0 &&
+					    !test_bit(CACHE_PENDING,
+						      &cr->item->flags)) {
+						list_del(&cr->q.list);
+						rq = cr;
+					}
 					break;
 				}
 			rp->offset = 0;
@@ -1076,9 +1087,14 @@ static int cache_release(struct inode *inode, struct file *filp,
 		list_del(&rp->q.list);
 		spin_unlock(&queue_lock);
 
+		if (rq) {
+			cache_put(rq->item, cd);
+			kfree(rq->buf);
+			kfree(rq);
+		}
+
 		filp->private_data = NULL;
 		kfree(rp);
-
 	}
 	if (filp->f_mode & FMODE_WRITE) {
 		atomic_dec(&cd->writers);
-- 
cgit v1.2.3


From 6cfc3bc02b977f2fba5f7268e6504d1931a774f7 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 12 Mar 2026 12:18:52 -0700
Subject: net: bcmgenet: increase WoL poll timeout

Some systems require more than 5ms to get into WoL mode. Increase the
timeout value to 50ms.

Fixes: c51de7f3976b ("net: bcmgenet: add Wake-on-LAN support code")
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260312191852.3904571-1-justin.chen@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 8fb551288298..96d5d4f7f51f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -123,7 +123,7 @@ static int bcmgenet_poll_wol_status(struct bcmgenet_priv *priv)
 	while (!(bcmgenet_rbuf_readl(priv, RBUF_STATUS)
 		& RBUF_STATUS_WOL)) {
 		retries++;
-		if (retries > 5) {
+		if (retries > 50) {
 			netdev_crit(dev, "polling wol mode timeout\n");
 			return -ETIMEDOUT;
 		}
-- 
cgit v1.2.3


From fa103fc8f56954a60699a29215cb713448a39e87 Mon Sep 17 00:00:00 2001
From: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Date: Wed, 11 Mar 2026 12:22:04 -0700
Subject: net: mana: fix use-after-free in mana_hwc_destroy_channel() by
 reordering teardown

A potential race condition exists in mana_hwc_destroy_channel() where
hwc->caller_ctx is freed before the HWC's Completion Queue (CQ) and
Event Queue (EQ) are destroyed. This allows an in-flight CQ interrupt
handler to dereference freed memory, leading to a use-after-free or
NULL pointer dereference in mana_hwc_handle_resp().

mana_smc_teardown_hwc() signals the hardware to stop but does not
synchronize against IRQ handlers already executing on other CPUs. The
IRQ synchronization only happens in mana_hwc_destroy_cq() via
mana_gd_destroy_eq() -> mana_gd_deregister_irq(). Since this runs
after kfree(hwc->caller_ctx), a concurrent mana_hwc_rx_event_handler()
can dereference freed caller_ctx (and rxq->msg_buf) in
mana_hwc_handle_resp().

Fix this by reordering teardown to reverse-of-creation order: destroy
the TX/RX work queues and CQ/EQ before freeing hwc->caller_ctx. This
ensures all in-flight interrupt handlers complete before the memory they
access is freed.

Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)")
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/abHA3AjNtqa1nx9k@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/hw_channel.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index ba3467f1e2ea..48a9acea4ab6 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -814,9 +814,6 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
 		gc->max_num_cqs = 0;
 	}
 
-	kfree(hwc->caller_ctx);
-	hwc->caller_ctx = NULL;
-
 	if (hwc->txq)
 		mana_hwc_destroy_wq(hwc, hwc->txq);
 
@@ -826,6 +823,9 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
 	if (hwc->cq)
 		mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
 
+	kfree(hwc->caller_ctx);
+	hwc->caller_ctx = NULL;
+
 	mana_gd_free_res_map(&hwc->inflight_msg_res);
 
 	hwc->num_inflight_msg = 0;
-- 
cgit v1.2.3


From ebba09f198078b7a2565004104ef762d1148e7f0 Mon Sep 17 00:00:00 2001
From: AlanSong-oc <AlanSong-oc@zhaoxin.com>
Date: Fri, 13 Mar 2026 16:01:49 +0800
Subject: crypto: padlock-sha - Disable for Zhaoxin processor

For Zhaoxin processors, the XSHA1 instruction requires the total memory
allocated at %rdi register must be 32 bytes, while the XSHA1 and
XSHA256 instruction doesn't perform any operation when %ecx is zero.

Due to these requirements, the current padlock-sha driver does not work
correctly with Zhaoxin processors. It cannot pass the self-tests and
therefore does not activate the driver on Zhaoxin processors. This issue
has been reported in Debian [1]. The self-tests fail with the
following messages [2]:

alg: shash: sha1-padlock-nano test failed (wrong result) on test vector 0, cfg="init+update+final aligned buffer"
alg: self-tests for sha1 using sha1-padlock-nano failed (rc=-22)

alg: shash: sha256-padlock-nano test failed (wrong result) on test vector 0, cfg="init+update+final aligned buffer"
alg: self-tests for sha256 using sha256-padlock-nano failed (rc=-22)

Disable the padlock-sha driver on Zhaoxin processors with the CPU family
0x07 and newer. Following the suggestion in [3], support for PHE will be
added to lib/crypto/ instead.

[1] https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1113996
[2] https://linux-hardware.org/?probe=271fabb7a4&log=dmesg
[3] https://lore.kernel.org/linux-crypto/aUI4CGp6kK7mxgEr@gondor.apana.org.au/

Fixes: 63dc06cd12f9 ("crypto: padlock-sha - Use API partial block handling")
Cc: stable@vger.kernel.org
Signed-off-by: AlanSong-oc <AlanSong-oc@zhaoxin.com>
Link: https://lore.kernel.org/r/20260313080150.9393-2-AlanSong-oc@zhaoxin.com
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 drivers/crypto/padlock-sha.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 329f60ad422e..9214bbfc868f 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -332,6 +332,13 @@ static int __init padlock_init(void)
 	if (!x86_match_cpu(padlock_sha_ids) || !boot_cpu_has(X86_FEATURE_PHE_EN))
 		return -ENODEV;
 
+	/*
+	 * Skip family 0x07 and newer used by Zhaoxin processors,
+	 * as the driver's self-tests fail on these CPUs.
+	 */
+	if (c->x86 >= 0x07)
+		return -ENODEV;
+
 	/* Register the newly added algorithm module if on *
 	* VIA Nano processor, or else just do as before */
 	if (c->x86_model < 0x0f) {
-- 
cgit v1.2.3


From 719d3e71691db7c4f1658ba5a6d1472928121594 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Wed, 11 Mar 2026 15:24:41 +0530
Subject: net: ti: icssg-prueth: Fix memory leak in XDP_DROP for non-zero-copy
 mode

Page recycling was removed from the XDP_DROP path in emac_run_xdp() to
avoid conflicts with AF_XDP zero-copy mode, which uses xsk_buff_free()
instead.

However, this causes a memory leak when running XDP programs that drop
packets in non-zero-copy mode (standard page pool mode). The pages are
never returned to the page pool, leading to OOM conditions.

Fix this by handling cleanup in the caller, emac_rx_packet().
When emac_run_xdp() returns ICSSG_XDP_CONSUMED for XDP_DROP, the
caller now recycles the page back to the page pool. The zero-copy
path, emac_rx_packet_zc() already handles cleanup correctly with
xsk_buff_free().

Fixes: 7a64bb388df3 ("net: ti: icssg-prueth: Add AF_XDP zero copy for RX")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260311095441.1691636-1-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 0cf9dfe0fa36..0a3cf2f848a5 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -1075,6 +1075,11 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state)
 		xdp_prepare_buff(&xdp, pa, PRUETH_HEADROOM, pkt_len, false);
 
 		*xdp_state = emac_run_xdp(emac, &xdp, &pkt_len);
+		if (*xdp_state == ICSSG_XDP_CONSUMED) {
+			page_pool_recycle_direct(pool, page);
+			goto requeue;
+		}
+
 		if (*xdp_state != ICSSG_XDP_PASS)
 			goto requeue;
 		headroom = xdp.data - xdp.data_hard_start;
-- 
cgit v1.2.3


From 1a7124ecd655bcaf1845197fe416aa25cff4c3ea Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Thu, 12 Mar 2026 16:13:58 +0800
Subject: net: macb: Introduce gem_init_rx_ring()

Extract the initialization code for the GEM RX ring into a new function.
This change will be utilized in a subsequent patch. No functional changes
are introduced.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260312-macb-versal-v1-1-467647173fa4@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f290d608b409..4bdc7ccab730 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2669,6 +2669,14 @@ static void macb_init_tieoff(struct macb *bp)
 	desc->ctrl = 0;
 }
 
+static void gem_init_rx_ring(struct macb_queue *queue)
+{
+	queue->rx_tail = 0;
+	queue->rx_prepared_head = 0;
+
+	gem_rx_refill(queue);
+}
+
 static void gem_init_rings(struct macb *bp)
 {
 	struct macb_queue *queue;
@@ -2686,10 +2694,7 @@ static void gem_init_rings(struct macb *bp)
 		queue->tx_head = 0;
 		queue->tx_tail = 0;
 
-		queue->rx_tail = 0;
-		queue->rx_prepared_head = 0;
-
-		gem_rx_refill(queue);
+		gem_init_rx_ring(queue);
 	}
 
 	macb_init_tieoff(bp);
-- 
cgit v1.2.3


From 718d0766ce4c7634ce62fa78b526ea7263487edd Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Thu, 12 Mar 2026 16:13:59 +0800
Subject: net: macb: Reinitialize tx/rx queue pointer registers and rx ring
 during resume

On certain platforms, such as AMD Versal boards, the tx/rx queue pointer
registers are cleared after suspend, and the rx queue pointer register
is also disabled during suspend if WOL is enabled. Previously, we assumed
that these registers would be restored by macb_mac_link_up(). However,
in commit bf9cf80cab81, macb_init_buffers() was moved from
macb_mac_link_up() to macb_open(). Therefore, we should call
macb_init_buffers() to reinitialize the tx/rx queue pointer registers
during resume.

Due to the reset of these two registers, we also need to adjust the
tx/rx rings accordingly. The tx ring will be handled by
gem_shuffle_tx_rings() in macb_mac_link_up(), so we only need to
initialize the rx ring here.

Fixes: bf9cf80cab81 ("net: macb: Fix tx/rx malfunction after phy link down and up")
Reported-by: Quanyang Wang <quanyang.wang@windriver.com>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Tested-by: Quanyang Wang <quanyang.wang@windriver.com>
Cc: stable@vger.kernel.org
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260312-macb-versal-v1-2-467647173fa4@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4bdc7ccab730..033cff571904 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5952,8 +5952,18 @@ static int __maybe_unused macb_resume(struct device *dev)
 		rtnl_unlock();
 	}
 
+	if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+		macb_init_buffers(bp);
+
 	for (q = 0, queue = bp->queues; q < bp->num_queues;
 	     ++q, ++queue) {
+		if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) {
+			if (macb_is_gem(bp))
+				gem_init_rx_ring(queue);
+			else
+				macb_init_rx_ring(queue);
+		}
+
 		napi_enable(&queue->napi_rx);
 		napi_enable(&queue->napi_tx);
 	}
-- 
cgit v1.2.3


From 2c98a8fbd6aa647414c6248dacf254ebe91c79ad Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Mon, 9 Mar 2026 15:16:37 +0100
Subject: parisc: Flush correct cache in cacheflush() syscall

The assembly flush instructions were swapped for I- and D-cache flags:

SYSCALL_DEFINE3(cacheflush, ...)
{
	if (cache & DCACHE) {
			"fic ...\n"
	}
	if (cache & ICACHE && error == 0) {
			"fdc ...\n"
	}

Fix it by using fdc for DCACHE, and fic for ICACHE flushing.

Reported-by: Felix Lechner <felix.lechner@lease-up.com>
Fixes: c6d96328fecd ("parisc: Add cacheflush() syscall")
Cc: <stable@vger.kernel.org> # v6.5+
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 4c5240d3a3c7..b189265785dc 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -953,7 +953,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #else
 			"1: cmpb,<<,n	%0,%2,1b\n"
 #endif
-			"   fic,m	%3(%4,%0)\n"
+			"   fdc,m	%3(%4,%0)\n"
 			"2: sync\n"
 			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
@@ -968,7 +968,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 #else
 			"1: cmpb,<<,n	%0,%2,1b\n"
 #endif
-			"   fdc,m	%3(%4,%0)\n"
+			"   fic,m	%3(%4,%0)\n"
 			"2: sync\n"
 			ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 2b, "%1")
 			: "+r" (start), "+r" (error)
-- 
cgit v1.2.3


From 793b008cd39516385791a1d1d223d817e947a471 Mon Sep 17 00:00:00 2001
From: Andrii Kovalchuk <coderpy4@proton.me>
Date: Sun, 15 Mar 2026 01:08:51 +0000
Subject: ALSA: hda/realtek: Add HP ENVY Laptop 13-ba0xxx quirk

Add a PCI quirk for HP ENVY Laptop 13-ba0xxx (PCI device ID 0x8756)
to enable proper mute LED and mic mute behavior using the
ALC245_FIXUP_HP_X360_MUTE_LEDS fixup.

Signed-off-by: Andrii Kovalchuk <coderpy4@proton.me>
Link: https://patch.msgid.link/u0s-uRVegF9BN0t-4JnOUwsIAR-mVc4U4FJfJHdEHX7ro_laErHD9y35NebWybcN16gVaVHPJo1ap3AoJ1a2gqJImPvThgeNt_SYVY1KaDw=@proton.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index b8aba01ef261..7294298fce4a 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6854,6 +6854,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x8756, "HP ENVY Laptop 13-ba0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP EliteBook 8{4,5}5 G7", ALC285_FIXUP_HP_BEEP_MICMUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x876e, "HP ENVY x360 Convertible 13-ay0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
-- 
cgit v1.2.3


From c05a87d9ec3bf8727a5d746ce855003c6f2f8bb4 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Mon, 9 Mar 2026 20:45:45 -0700
Subject: iio: imu: bmi160: Remove potential undefined behavior in
 bmi160_config_pin()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If 'pin' is not one of its expected values, the value of
'int_out_ctrl_shift' is undefined.  With UBSAN enabled, this causes
Clang to generate undefined behavior, resulting in the following
warning:

  drivers/iio/imu/bmi160/bmi160_core.o: warning: objtool: bmi160_setup_irq() falls through to next function __cfi_bmi160_core_runtime_resume()

Prevent the UB and improve error handling by returning an error if 'pin'
has an unexpected value.

While at it, simplify the code a bit by moving the 'pin_name' assignment
to the first switch statement.

Fixes: 895bf81e6bbf ("iio:bmi160: add drdy interrupt support")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/a426d669-58bb-4be1-9eaa-6f3d83109e2d@app.fastmail.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/bmi160/bmi160_core.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c
index 5f47708b4c5d..4abb83b75e2e 100644
--- a/drivers/iio/imu/bmi160/bmi160_core.c
+++ b/drivers/iio/imu/bmi160/bmi160_core.c
@@ -573,12 +573,16 @@ static int bmi160_config_pin(struct regmap *regmap, enum bmi160_int_pin pin,
 		int_out_ctrl_shift = BMI160_INT1_OUT_CTRL_SHIFT;
 		int_latch_mask = BMI160_INT1_LATCH_MASK;
 		int_map_mask = BMI160_INT1_MAP_DRDY_EN;
+		pin_name = "INT1";
 		break;
 	case BMI160_PIN_INT2:
 		int_out_ctrl_shift = BMI160_INT2_OUT_CTRL_SHIFT;
 		int_latch_mask = BMI160_INT2_LATCH_MASK;
 		int_map_mask = BMI160_INT2_MAP_DRDY_EN;
+		pin_name = "INT2";
 		break;
+	default:
+		return -EINVAL;
 	}
 	int_out_ctrl_mask = BMI160_INT_OUT_CTRL_MASK << int_out_ctrl_shift;
 
@@ -612,17 +616,8 @@ static int bmi160_config_pin(struct regmap *regmap, enum bmi160_int_pin pin,
 	ret = bmi160_write_conf_reg(regmap, BMI160_REG_INT_MAP,
 				    int_map_mask, int_map_mask,
 				    write_usleep);
-	if (ret) {
-		switch (pin) {
-		case BMI160_PIN_INT1:
-			pin_name = "INT1";
-			break;
-		case BMI160_PIN_INT2:
-			pin_name = "INT2";
-			break;
-		}
+	if (ret)
 		dev_err(dev, "Failed to configure %s IRQ pin", pin_name);
-	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From dd154646d292cce7de952f216760c58c35cfecde Mon Sep 17 00:00:00 2001
From: Ariana Lazar <ariana.lazar@microchip.com>
Date: Tue, 10 Mar 2026 13:56:44 +0200
Subject: iio: dac: mcp47feb02: Fix Vref validation [1-999] case

Store reference voltages in uV instead of mV to avoid invalid error code
in dev_err_probe() call. Vref variables store the actual value returned by
devm_regulator_get_enable_read_voltage() function instead of the results of
dividing it by MILLI. The corner case [1-999] divided by MILLI of the
voltage reference variable value would become 0 is covered too.

Fixes: bf394cc80369 ("iio: dac: adding support for Microchip MCP47FEB02")
Link: https://lore.kernel.org/all/aYXvP5FLA5BvkoVX@stanley.mountain/
Signed-off-by: Ariana Lazar <ariana.lazar@microchip.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/mcp47feb02.c | 49 ++++++++++++++++++++------------------------
 1 file changed, 22 insertions(+), 27 deletions(-)

diff --git a/drivers/iio/dac/mcp47feb02.c b/drivers/iio/dac/mcp47feb02.c
index 08fb85359697..faccb804a5ed 100644
--- a/drivers/iio/dac/mcp47feb02.c
+++ b/drivers/iio/dac/mcp47feb02.c
@@ -65,7 +65,7 @@
 #define MCP47FEB02_MAX_SCALES_CH			3
 #define MCP47FEB02_DAC_WIPER_UNLOCKED			0
 #define MCP47FEB02_NORMAL_OPERATION			0
-#define MCP47FEB02_INTERNAL_BAND_GAP_mV			2440
+#define MCP47FEB02_INTERNAL_BAND_GAP_uV			2440000
 #define NV_DAC_ADDR_OFFSET				0x10
 
 enum mcp47feb02_vref_mode {
@@ -697,44 +697,40 @@ static const struct iio_chan_spec mcp47febxx_ch_template = {
 };
 
 static void mcp47feb02_init_scale(struct mcp47feb02_data *data, enum mcp47feb02_scale scale,
-				  int vref_mV, int scale_avail[])
+				  int vref_uV, int scale_avail[])
 {
 	u32 value_micro, value_int;
 	u64 tmp;
 
-	/* vref_mV should not be negative */
-	tmp = (u64)vref_mV * MICRO >> data->chip_features->resolution;
+	/* vref_uV should not be negative */
+	tmp = (u64)vref_uV * MILLI >> data->chip_features->resolution;
 	value_int = div_u64_rem(tmp, MICRO, &value_micro);
 	scale_avail[scale * 2] = value_int;
 	scale_avail[scale * 2 + 1] = value_micro;
 }
 
-static int mcp47feb02_init_scales_avail(struct mcp47feb02_data *data, int vdd_mV,
-					int vref_mV, int vref1_mV)
+static int mcp47feb02_init_scales_avail(struct mcp47feb02_data *data, int vdd_uV,
+					int vref_uV, int vref1_uV)
 {
-	struct device *dev = regmap_get_device(data->regmap);
 	int tmp_vref;
 
-	mcp47feb02_init_scale(data, MCP47FEB02_SCALE_VDD, vdd_mV, data->scale);
+	mcp47feb02_init_scale(data, MCP47FEB02_SCALE_VDD, vdd_uV, data->scale);
 
 	if (data->use_vref)
-		tmp_vref = vref_mV;
+		tmp_vref = vref_uV;
 	else
-		tmp_vref = MCP47FEB02_INTERNAL_BAND_GAP_mV;
+		tmp_vref = MCP47FEB02_INTERNAL_BAND_GAP_uV;
 
 	mcp47feb02_init_scale(data, MCP47FEB02_SCALE_GAIN_X1, tmp_vref, data->scale);
 	mcp47feb02_init_scale(data, MCP47FEB02_SCALE_GAIN_X2, tmp_vref * 2, data->scale);
 
 	if (data->phys_channels >= 4) {
-		mcp47feb02_init_scale(data, MCP47FEB02_SCALE_VDD, vdd_mV, data->scale_1);
-
-		if (data->use_vref1 && vref1_mV <= 0)
-			return dev_err_probe(dev, vref1_mV, "Invalid voltage for Vref1\n");
+		mcp47feb02_init_scale(data, MCP47FEB02_SCALE_VDD, vdd_uV, data->scale_1);
 
 		if (data->use_vref1)
-			tmp_vref = vref1_mV;
+			tmp_vref = vref1_uV;
 		else
-			tmp_vref = MCP47FEB02_INTERNAL_BAND_GAP_mV;
+			tmp_vref = MCP47FEB02_INTERNAL_BAND_GAP_uV;
 
 		mcp47feb02_init_scale(data, MCP47FEB02_SCALE_GAIN_X1,
 				      tmp_vref, data->scale_1);
@@ -1078,8 +1074,8 @@ static int mcp47feb02_init_ctrl_regs(struct mcp47feb02_data *data)
 	return 0;
 }
 
-static int mcp47feb02_init_ch_scales(struct mcp47feb02_data *data, int vdd_mV,
-				     int vref_mV, int vref1_mV)
+static int mcp47feb02_init_ch_scales(struct mcp47feb02_data *data, int vdd_uV,
+				     int vref_uV, int vref1_uV)
 {
 	unsigned int i;
 
@@ -1087,7 +1083,7 @@ static int mcp47feb02_init_ch_scales(struct mcp47feb02_data *data, int vdd_mV,
 		struct device *dev = regmap_get_device(data->regmap);
 		int ret;
 
-		ret = mcp47feb02_init_scales_avail(data, vdd_mV, vref_mV, vref1_mV);
+		ret = mcp47feb02_init_scales_avail(data, vdd_uV, vref_uV, vref1_uV);
 		if (ret)
 			return dev_err_probe(dev, ret, "failed to init scales for ch %u\n", i);
 	}
@@ -1101,10 +1097,7 @@ static int mcp47feb02_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	struct mcp47feb02_data *data;
 	struct iio_dev *indio_dev;
-	int vref1_mV = 0;
-	int vref_mV = 0;
-	int vdd_mV;
-	int ret;
+	int vref1_uV, vref_uV, vdd_uV, ret;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
 	if (!indio_dev)
@@ -1141,13 +1134,14 @@ static int mcp47feb02_probe(struct i2c_client *client)
 	if (ret < 0)
 		return ret;
 
-	vdd_mV = ret / MILLI;
+	vdd_uV = ret;
 
 	ret = devm_regulator_get_enable_read_voltage(dev, "vref");
 	if (ret > 0) {
-		vref_mV = ret / MILLI;
+		vref_uV = ret;
 		data->use_vref = true;
 	} else {
+		vref_uV = 0;
 		dev_dbg(dev, "using internal band gap as voltage reference.\n");
 		dev_dbg(dev, "Vref is unavailable.\n");
 	}
@@ -1155,9 +1149,10 @@ static int mcp47feb02_probe(struct i2c_client *client)
 	if (chip_features->have_ext_vref1) {
 		ret = devm_regulator_get_enable_read_voltage(dev, "vref1");
 		if (ret > 0) {
-			vref1_mV = ret / MILLI;
+			vref1_uV = ret;
 			data->use_vref1 = true;
 		} else {
+			vref1_uV = 0;
 			dev_dbg(dev, "using internal band gap as voltage reference 1.\n");
 			dev_dbg(dev, "Vref1 is unavailable.\n");
 		}
@@ -1167,7 +1162,7 @@ static int mcp47feb02_probe(struct i2c_client *client)
 	if (ret)
 		return dev_err_probe(dev, ret, "Error initialising vref register\n");
 
-	ret = mcp47feb02_init_ch_scales(data, vdd_mV, vref_mV, vref1_mV);
+	ret = mcp47feb02_init_ch_scales(data, vdd_uV, vref_uV, vref1_uV);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 1744a6ef48b9a48f017e3e1a0d05de0a6978396e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 12 Mar 2026 14:08:50 +0000
Subject: KVM: arm64: Discard PC update state on vcpu reset

Our vcpu reset suffers from a particularly interesting flaw, as it
does not correctly deal with state that will have an effect on the
execution flow out of reset.

Take the following completely random example, never seen in the wild
and that never resulted in a couple of sleepless nights: /s

- vcpu-A issues a PSCI_CPU_OFF using the SMC conduit

- SMC being a trapped instruction (as opposed to HVC which is always
  normally executed), we annotate the vcpu as needing to skip the
  next instruction, which is the SMC itself

- vcpu-A is now safely off

- vcpu-B issues a PSCI_CPU_ON for vcpu-A, providing a starting PC

- vcpu-A gets reset, get the new PC, and is sent on its merry way

- right at the point of entering the guest, we notice that a PC
  increment is pending (remember the earlier SMC?)

- vcpu-A skips its first instruction...

What could possibly go wrong?

Well, I'm glad you asked. For pKVM as a NV guest, that first instruction
is extremely significant, as it indicates whether the CPU is booting
or resuming. Having skipped that instruction, nothing makes any sense
anymore, and CPU hotplugging fails.

This is all caused by the decoupling of PC update from the handling
of an exception that triggers such update, making it non-obvious
what affects what when.

Fix this train wreck by discarding all the PC-affecting state on
vcpu reset.

Fixes: f5e30680616ab ("KVM: arm64: Move __adjust_pc out of line")
Cc: stable@vger.kernel.org
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Link: https://patch.msgid.link/20260312140850.822968-1-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/reset.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 959532422d3a..b963fd975aac 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -247,6 +247,20 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			kvm_vcpu_set_be(vcpu);
 
 		*vcpu_pc(vcpu) = target_pc;
+
+		/*
+		 * We may come from a state where either a PC update was
+		 * pending (SMC call resulting in PC being increpented to
+		 * skip the SMC) or a pending exception. Make sure we get
+		 * rid of all that, as this cannot be valid out of reset.
+		 *
+		 * Note that clearing the exception mask also clears PC
+		 * updates, but that's an implementation detail, and we
+		 * really want to make it explicit.
+		 */
+		vcpu_clear_flag(vcpu, PENDING_EXCEPTION);
+		vcpu_clear_flag(vcpu, EXCEPT_MASK);
+		vcpu_clear_flag(vcpu, INCREMENT_PC);
 		vcpu_set_reg(vcpu, 0, reset_state.r0);
 	}
 
-- 
cgit v1.2.3


From f338e77383789c0cae23ca3d48adcc5e9e137e3c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 15 Mar 2026 13:52:05 -0700
Subject: Linux 7.0-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index ec0f2d8466ea..c9b7bee102e8 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From a00da54d06f435dbbeacb84f9121dbbe6d6eda74 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 8 Mar 2026 21:34:55 +0800
Subject: spi: amlogic: spifc-a4: Remove redundant clock cleanup

The driver uses devm_clk_get_enabled() which enables the clock and
registers a callback to automatically disable it when the device
is unbound.

Remove the redundant aml_sfc_disable_clk() call in the error paths
and remove callback.

Fixes: 4670db6f32e9 ("spi: amlogic: add driver for Amlogic SPI Flash Controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260308-spifc-a4-1-v1-1-77e286c26832@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-amlogic-spifc-a4.c | 46 ++++++--------------------------------
 1 file changed, 7 insertions(+), 39 deletions(-)

diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c
index 3956869cfec1..1aabafa36e48 100644
--- a/drivers/spi/spi-amlogic-spifc-a4.c
+++ b/drivers/spi/spi-amlogic-spifc-a4.c
@@ -1083,14 +1083,6 @@ static int aml_sfc_clk_init(struct aml_sfc *sfc)
 	return clk_set_rate(sfc->core_clk, SFC_BUS_DEFAULT_CLK);
 }
 
-static int aml_sfc_disable_clk(struct aml_sfc *sfc)
-{
-	clk_disable_unprepare(sfc->core_clk);
-	clk_disable_unprepare(sfc->gate_clk);
-
-	return 0;
-}
-
 static int aml_sfc_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -1141,16 +1133,12 @@ static int aml_sfc_probe(struct platform_device *pdev)
 
 	/* Enable Amlogic flash controller spi mode */
 	ret = regmap_write(sfc->regmap_base, SFC_SPI_CFG, SPI_MODE_EN);
-	if (ret) {
-		dev_err(dev, "failed to enable SPI mode\n");
-		goto err_out;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to enable SPI mode\n");
 
 	ret = dma_set_mask(sfc->dev, DMA_BIT_MASK(32));
-	if (ret) {
-		dev_err(sfc->dev, "failed to set dma mask\n");
-		goto err_out;
-	}
+	if (ret)
+		return dev_err_probe(sfc->dev, ret, "failed to set dma mask\n");
 
 	sfc->ecc_eng.dev = &pdev->dev;
 	sfc->ecc_eng.integration = NAND_ECC_ENGINE_INTEGRATION_PIPELINED;
@@ -1158,10 +1146,8 @@ static int aml_sfc_probe(struct platform_device *pdev)
 	sfc->ecc_eng.priv = sfc;
 
 	ret = nand_ecc_register_on_host_hw_engine(&sfc->ecc_eng);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register Aml host ecc engine.\n");
-		goto err_out;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "failed to register Aml host ecc engine.\n");
 
 	ret = of_property_read_u32(np, "amlogic,rx-adj", &val);
 	if (!ret)
@@ -1177,24 +1163,7 @@ static int aml_sfc_probe(struct platform_device *pdev)
 	ctrl->min_speed_hz = SFC_MIN_FREQUENCY;
 	ctrl->num_chipselect = SFC_MAX_CS_NUM;
 
-	ret = devm_spi_register_controller(dev, ctrl);
-	if (ret)
-		goto err_out;
-
-	return 0;
-
-err_out:
-	aml_sfc_disable_clk(sfc);
-
-	return ret;
-}
-
-static void aml_sfc_remove(struct platform_device *pdev)
-{
-	struct spi_controller *ctlr = platform_get_drvdata(pdev);
-	struct aml_sfc *sfc = spi_controller_get_devdata(ctlr);
-
-	aml_sfc_disable_clk(sfc);
+	return devm_spi_register_controller(dev, ctrl);
 }
 
 static const struct of_device_id aml_sfc_of_match[] = {
@@ -1212,7 +1181,6 @@ static struct platform_driver aml_sfc_driver = {
 		.of_match_table = aml_sfc_of_match,
 	},
 	.probe = aml_sfc_probe,
-	.remove = aml_sfc_remove,
 };
 module_platform_driver(aml_sfc_driver);
 
-- 
cgit v1.2.3


From b8db9552997924b750e727a625a30eaa4603bbb9 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 8 Mar 2026 14:49:21 +0800
Subject: spi: amlogic-spisg: Fix memory leak in aml_spisg_probe()

In aml_spisg_probe(), ctlr is allocated by
spi_alloc_target()/spi_alloc_host(), but fails to call
spi_controller_put() in several error paths. This leads
to a memory leak whenever the driver fails to probe after
the initial allocation.

Convert to use devm_spi_alloc_host()/devm_spi_alloc_target()
to fix the memory leak.

Fixes: cef9991e04ae ("spi: Add Amlogic SPISG driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260308-spisg-v1-1-2cace5cafc24@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-amlogic-spisg.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/spi/spi-amlogic-spisg.c b/drivers/spi/spi-amlogic-spisg.c
index 1509df2b17ae..9d568e385f05 100644
--- a/drivers/spi/spi-amlogic-spisg.c
+++ b/drivers/spi/spi-amlogic-spisg.c
@@ -729,9 +729,9 @@ static int aml_spisg_probe(struct platform_device *pdev)
 	};
 
 	if (of_property_read_bool(dev->of_node, "spi-slave"))
-		ctlr = spi_alloc_target(dev, sizeof(*spisg));
+		ctlr = devm_spi_alloc_target(dev, sizeof(*spisg));
 	else
-		ctlr = spi_alloc_host(dev, sizeof(*spisg));
+		ctlr = devm_spi_alloc_host(dev, sizeof(*spisg));
 	if (!ctlr)
 		return -ENOMEM;
 
@@ -750,10 +750,8 @@ static int aml_spisg_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(spisg->map), "regmap init failed\n");
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = irq;
-		goto out_controller;
-	}
+	if (irq < 0)
+		return irq;
 
 	ret = device_reset_optional(dev);
 	if (ret)
@@ -817,8 +815,6 @@ out_clk:
 	if (spisg->core)
 		clk_disable_unprepare(spisg->core);
 	clk_disable_unprepare(spisg->pclk);
-out_controller:
-	spi_controller_put(ctlr);
 
 	return ret;
 }
-- 
cgit v1.2.3


From fe757092d2329c397ecb32f2bf68a5b1c4bd9193 Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Fri, 13 Mar 2026 12:06:11 +0800
Subject: ASoC: sma1307: fix double free of devm_kzalloc() memory

A previous change added NULL checks and cleanup for allocation
failures in sma1307_setting_loaded().

However, the cleanup for mode_set entries is wrong. Those entries are
allocated with devm_kzalloc(), so they are device-managed resources and
must not be freed with kfree(). Manually freeing them in the error path
can lead to a double free when devres later releases the same memory.

Drop the manual kfree() loop and let devres handle the cleanup.

Fixes: 0ec6bd16705fe ("ASoC: sma1307: Add NULL check in sma1307_setting_loaded()")
Cc: stable@vger.kernel.org
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Link: https://patch.msgid.link/20260313040611.391479-1-lgs201920130244@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/sma1307.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c
index 4bb59e5c0891..5850bf6e71ca 100644
--- a/sound/soc/codecs/sma1307.c
+++ b/sound/soc/codecs/sma1307.c
@@ -1759,8 +1759,10 @@ static void sma1307_setting_loaded(struct sma1307_priv *sma1307, const char *fil
 				   sma1307->set.mode_size * 2 * sizeof(int),
 				   GFP_KERNEL);
 		if (!sma1307->set.mode_set[i]) {
-			for (int j = 0; j < i; j++)
-				kfree(sma1307->set.mode_set[j]);
+			for (int j = 0; j < i; j++) {
+				devm_kfree(sma1307->dev, sma1307->set.mode_set[j]);
+				sma1307->set.mode_set[j] = NULL;
+			}
 			sma1307->set.status = false;
 			return;
 		}
-- 
cgit v1.2.3


From d0426510a9e1fabf074e274ceff26ffc6500980a Mon Sep 17 00:00:00 2001
From: Hasun Park <hasunpark@gmail.com>
Date: Mon, 9 Mar 2026 00:16:52 +0900
Subject: ASoC: amd: acp: add DMI override for ACP70 flag

Some ASUS ProArt PX13 systems expose ACP ACPI config flags that can
select a non-working fallback path.

Add a DMI override in snd_amd_acp_find_config() for ACP70+ boards and
return 0 so ACP ACPI flag-based selection is skipped on this platform.

This keeps machine driver selection on the intended SoundWire path.

Signed-off-by: Hasun Park <hasunpark@gmail.com>
Link: https://patch.msgid.link/20260308151654.29059-2-hasunpark@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-config.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/sound/soc/amd/acp-config.c b/sound/soc/amd/acp-config.c
index 365209ea53f3..1604ed679224 100644
--- a/sound/soc/amd/acp-config.c
+++ b/sound/soc/amd/acp-config.c
@@ -23,6 +23,16 @@
 
 static int acp_quirk_data;
 
+static const struct dmi_system_id acp70_acpi_flag_override_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"),
+		},
+	},
+	{}
+};
+
 static const struct config_entry config_table[] = {
 	{
 		.flags = FLAG_AMD_SOF,
@@ -186,8 +196,11 @@ int snd_amd_acp_find_config(struct pci_dev *pci)
 	 */
 	if (!pci->revision)
 		return 0;
-	else if (pci->revision >= ACP_7_0_REV)
+	else if (pci->revision >= ACP_7_0_REV) {
+		if (dmi_check_system(acp70_acpi_flag_override_table))
+			return 0;
 		return snd_amd_acp_acpi_find_config(pci);
+	}
 
 	for (i = 0; i < ARRAY_SIZE(config_table); i++, table++) {
 		if (table->device != device)
-- 
cgit v1.2.3


From 399b6fd37a102c73cefa32a0ec945d76d80fa35f Mon Sep 17 00:00:00 2001
From: Hasun Park <hasunpark@gmail.com>
Date: Mon, 9 Mar 2026 00:16:53 +0900
Subject: ASoC: amd: acp: add PX13 SoundWire machine link for rt721+tas2783x2

Add an ACP70 SoundWire machine entry for ASUS PX13
(HN7306EA/HN7306EAC) with rt721 and two TAS2783 amps on link1.

Describe rt721 with jack/DMIC endpoints on this platform and add
explicit left/right TAS2783 speaker endpoint mapping via name prefixes.

Signed-off-by: Hasun Park <hasunpark@gmail.com>
Link: https://patch.msgid.link/20260308151654.29059-3-hasunpark@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/amd-acp70-acpi-match.c | 61 ++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/sound/soc/amd/acp/amd-acp70-acpi-match.c b/sound/soc/amd/acp/amd-acp70-acpi-match.c
index 7a567ba02292..1ae43df5da6c 100644
--- a/sound/soc/amd/acp/amd-acp70-acpi-match.c
+++ b/sound/soc/amd/acp/amd-acp70-acpi-match.c
@@ -69,6 +69,28 @@ static const struct snd_soc_acpi_endpoint jack_amp_g1_dmic_endpoints[] = {
 	},
 };
 
+static const struct snd_soc_acpi_endpoint jack_dmic_endpoints[] = {
+	/* Jack Endpoint */
+	{
+		.num = 0,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+	/* DMIC Endpoint */
+	{
+		/*
+		 * rt721 endpoint #2 maps to AIF3 (internal DMIC capture).
+		 * Endpoint #1 is AIF2 amp path and is handled by external amps
+		 * on this platform.
+		 */
+		.num = 2,
+		.aggregated = 0,
+		.group_position = 0,
+		.group_id = 0,
+	},
+};
+
 static const struct snd_soc_acpi_adr_device rt712_vb_1_group1_adr[] = {
 	{
 		.adr = 0x000130025D071201ull,
@@ -563,6 +585,40 @@ static const struct snd_soc_acpi_link_adr acp70_rt1320_l0_rt722_l1[] = {
 	{}
 };
 
+static const struct snd_soc_acpi_adr_device rt721_l1u0_tas2783x2_l1u8b_adr[] = {
+	{
+		.adr = 0x000130025D072101ull,
+		/*
+		 * On this platform speakers are provided by two TAS2783 amps.
+		 * Keep rt721 as UAJ + DMIC only.
+		 */
+		.num_endpoints = ARRAY_SIZE(jack_dmic_endpoints),
+		.endpoints = jack_dmic_endpoints,
+		.name_prefix = "rt721",
+	},
+	{
+		.adr = 0x0001380102000001ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "tas2783-1",
+	},
+	{
+		.adr = 0x00013B0102000001ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "tas2783-2",
+	},
+};
+
+static const struct snd_soc_acpi_link_adr acp70_rt721_l1u0_tas2783x2_l1u8b[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(rt721_l1u0_tas2783x2_l1u8b_adr),
+		.adr_d = rt721_l1u0_tas2783x2_l1u8b_adr,
+	},
+	{}
+};
+
 struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = {
 	{
 		.link_mask = BIT(0) | BIT(1),
@@ -650,6 +706,11 @@ struct snd_soc_acpi_mach snd_soc_acpi_amd_acp70_sdw_machines[] = {
 		.machine_check = snd_soc_acpi_amd_sdca_is_device_rt712_vb,
 		.drv_name = "amd_sdw",
 	},
+	{
+		.link_mask = BIT(1),
+		.links = acp70_rt721_l1u0_tas2783x2_l1u8b,
+		.drv_name = "amd_sdw",
+	},
 	{},
 };
 EXPORT_SYMBOL(snd_soc_acpi_amd_acp70_sdw_machines);
-- 
cgit v1.2.3


From 7fc5e2f5603cfb305d0a8071f56b5bdb55161aeb Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 2 Mar 2026 01:08:40 +0800
Subject: spi: axiado: Fix double-free in ax_spi_probe()

ctlr is allocated using devm_spi_alloc_host(), which automatically
handles reference counting via the devm framework.

Calling spi_controller_put() manually in the probe error path is
redundant and results in a double-free.

Fixes: e75a6b00ad79 ("spi: axiado: Add driver for Axiado SPI DB controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260302-axiado-v1-1-1132819f1cb7@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-axiado.c | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/drivers/spi/spi-axiado.c b/drivers/spi/spi-axiado.c
index 8cea81432c5b..8ddcd27def22 100644
--- a/drivers/spi/spi-axiado.c
+++ b/drivers/spi/spi-axiado.c
@@ -765,30 +765,22 @@ static int ax_spi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ctlr);
 
 	xspi->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(xspi->regs)) {
-		ret = PTR_ERR(xspi->regs);
-		goto remove_ctlr;
-	}
+	if (IS_ERR(xspi->regs))
+		return PTR_ERR(xspi->regs);
 
 	xspi->pclk = devm_clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(xspi->pclk)) {
-		dev_err(&pdev->dev, "pclk clock not found.\n");
-		ret = PTR_ERR(xspi->pclk);
-		goto remove_ctlr;
-	}
+	if (IS_ERR(xspi->pclk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(xspi->pclk),
+				     "pclk clock not found.\n");
 
 	xspi->ref_clk = devm_clk_get(&pdev->dev, "ref");
-	if (IS_ERR(xspi->ref_clk)) {
-		dev_err(&pdev->dev, "ref clock not found.\n");
-		ret = PTR_ERR(xspi->ref_clk);
-		goto remove_ctlr;
-	}
+	if (IS_ERR(xspi->ref_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(xspi->ref_clk),
+				     "ref clock not found.\n");
 
 	ret = clk_prepare_enable(xspi->pclk);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to enable APB clock.\n");
-		goto remove_ctlr;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Unable to enable APB clock.\n");
 
 	ret = clk_prepare_enable(xspi->ref_clk);
 	if (ret) {
@@ -869,8 +861,7 @@ clk_dis_all:
 	clk_disable_unprepare(xspi->ref_clk);
 clk_dis_apb:
 	clk_disable_unprepare(xspi->pclk);
-remove_ctlr:
-	spi_controller_put(ctlr);
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From 641f6fda143b879da1515f821ee475073678cf2a Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com>
Date: Thu, 29 Jan 2026 20:53:20 +0530
Subject: soc: qcom: pd-mapper: Fix element length in servreg_loc_pfr_req_ei

It looks element length declared in servreg_loc_pfr_req_ei for reason
not matching servreg_loc_pfr_req's reason field due which we could
observe decoding error on PD crash.

  qmi_decode_string_elem: String len 81 >= Max Len 65

Fix this by matching with servreg_loc_pfr_req's reason field.

Fixes: 1ebcde047c54 ("soc: qcom: add pd-mapper implementation")
Signed-off-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Tested-by: Nikita Travkin <nikita@trvn.ru>
Link: https://lore.kernel.org/r/20260129152320.3658053-2-mukesh.ojha@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/pdr_internal.h | 2 +-
 drivers/soc/qcom/qcom_pdr_msg.c | 2 +-
 include/linux/soc/qcom/pdr.h    | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/pdr_internal.h b/drivers/soc/qcom/pdr_internal.h
index 039508c1bbf7..047c0160b617 100644
--- a/drivers/soc/qcom/pdr_internal.h
+++ b/drivers/soc/qcom/pdr_internal.h
@@ -84,7 +84,7 @@ struct servreg_set_ack_resp {
 
 struct servreg_loc_pfr_req {
 	char service[SERVREG_NAME_LENGTH + 1];
-	char reason[257];
+	char reason[SERVREG_PFR_LENGTH + 1];
 };
 
 struct servreg_loc_pfr_resp {
diff --git a/drivers/soc/qcom/qcom_pdr_msg.c b/drivers/soc/qcom/qcom_pdr_msg.c
index ca98932140d8..02022b11ecf0 100644
--- a/drivers/soc/qcom/qcom_pdr_msg.c
+++ b/drivers/soc/qcom/qcom_pdr_msg.c
@@ -325,7 +325,7 @@ const struct qmi_elem_info servreg_loc_pfr_req_ei[] = {
 	},
 	{
 		.data_type = QMI_STRING,
-		.elem_len = SERVREG_NAME_LENGTH + 1,
+		.elem_len = SERVREG_PFR_LENGTH + 1,
 		.elem_size = sizeof(char),
 		.array_type = VAR_LEN_ARRAY,
 		.tlv_type = 0x02,
diff --git a/include/linux/soc/qcom/pdr.h b/include/linux/soc/qcom/pdr.h
index 83a8ea612e69..2b7691e47c2a 100644
--- a/include/linux/soc/qcom/pdr.h
+++ b/include/linux/soc/qcom/pdr.h
@@ -5,6 +5,7 @@
 #include <linux/soc/qcom/qmi.h>
 
 #define SERVREG_NAME_LENGTH	64
+#define SERVREG_PFR_LENGTH	256
 
 struct pdr_service;
 struct pdr_handle;
-- 
cgit v1.2.3


From d487085006109e5981e059476818243759d2e925 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Fri, 6 Mar 2026 12:20:14 +0100
Subject: soc: qcom: pmic_glink_altmode: Fix SVID=DP && unconnected edge case

The commit referenced in Fixes started evaluating the value of
alt_port->mux_ctrl before checking the active SVID. This led to
drm_aux_hpd_bridge_notify() no longer being called for the 'DP unplug'
case.

Perhaps somewhat interestingly, the firmware sends a notification with
SVID=DP, mux_ctrl=MUX_CTRL_STATE_NO_CONN and pin_assignment=0 on
unplug. 'pin_assignment' was previously interpreted as a bitfield
excerpt from the second byte of the DP pg_altmode payload (and stored
as an u8).

That value is used in pmic_glink_altmode_sc8280xp_notify(), decremented
by 1 (DPAM_HPD_A). Previously, this would result in an u8 underflow
that would rollover to 0xff (which prior to the Fixes patch would have
caused a pmic_glink_altmode_safe() and 'disconnected' bridge
notification). That check was removed, without a replacement.

Resolve this issue by making sure the SID=DP && mux_ctrl=NO_CONN combo
once again results in a HPD bridge notification.

Fixes: 0539c5a6fdef ("soc: qcom: pmic_glink_altmode: Consume TBT3/USB4 mode notifications")
Reported-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Tested-by: Abel Vesa <abel.vesa@oss.qualcomm.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260306-topic-pgaltmode_fixup-v1-1-ec154b2d8e89@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/pmic_glink_altmode.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index d0afdcb96ee1..b496b88842a2 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -350,15 +350,17 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 
 	typec_switch_set(alt_port->typec_switch, alt_port->orientation);
 
-	if (alt_port->mux_ctrl == MUX_CTRL_STATE_NO_CONN) {
-		pmic_glink_altmode_safe(altmode, alt_port);
-	} else if (alt_port->svid == USB_TYPEC_TBT_SID) {
+	if (alt_port->svid == USB_TYPEC_TBT_SID) {
 		pmic_glink_altmode_enable_tbt(altmode, alt_port);
 	} else if (alt_port->svid == USB_TYPEC_DP_SID) {
-		pmic_glink_altmode_enable_dp(altmode, alt_port,
-					     alt_port->mode,
-					     alt_port->hpd_state,
-					     alt_port->hpd_irq);
+		if (alt_port->mux_ctrl == MUX_CTRL_STATE_NO_CONN) {
+			pmic_glink_altmode_safe(altmode, alt_port);
+		} else {
+			pmic_glink_altmode_enable_dp(altmode, alt_port,
+						     alt_port->mode,
+						     alt_port->hpd_state,
+						     alt_port->hpd_irq);
+		}
 
 		if (alt_port->hpd_state)
 			conn_status = connector_status_connected;
@@ -368,6 +370,8 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 		drm_aux_hpd_bridge_notify(&alt_port->bridge->dev, conn_status);
 	} else if (alt_port->mux_ctrl == MUX_CTRL_STATE_TUNNELING) {
 		pmic_glink_altmode_enable_usb4(altmode, alt_port);
+	} else if (alt_port->mux_ctrl == MUX_CTRL_STATE_NO_CONN) {
+		pmic_glink_altmode_safe(altmode, alt_port);
 	} else {
 		pmic_glink_altmode_enable_usb(altmode, alt_port);
 	}
-- 
cgit v1.2.3


From 12b4c5d98cd7ca46d5035a57bcd995df614c14e1 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Fri, 13 Mar 2026 00:03:38 -0300
Subject: smb: client: fix krb5 mount with username option

Customer reported that some of their krb5 mounts were failing against
a single server as the client was trying to mount the shares with
wrong credentials.  It turned out the client was reusing SMB session
from first mount to try mounting the other shares, even though a
different username= option had been specified to the other mounts.

By using username mount option along with sec=krb5 to search for
principals from keytab is supported by cifs.upcall(8) since
cifs-utils-4.8.  So fix this by matching username mount option in
match_session() even with Kerberos.

For example, the second mount below should fail with -ENOKEY as there
is no 'foobar' principal in keytab (/etc/krb5.keytab).  The client
ends up reusing SMB session from first mount to perform the second
one, which is wrong.

```
$ ktutil
ktutil:  add_entry -password -p testuser -k 1 -e aes256-cts
Password for testuser@ZELDA.TEST:
ktutil:  write_kt /etc/krb5.keytab
ktutil:  quit
$ klist -ke
Keytab name: FILE:/etc/krb5.keytab
KVNO Principal
 ---- ----------------------------------------------------------------
   1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96)
$ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser
$ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar
$ mount -t cifs | grep -Po 'username=\K\w+'
testuser
testuser
```

Reported-by: Oscar Santos <ossantos@redhat.com>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 3bad2c5c523d..69b38f0ccf2b 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -1955,6 +1955,10 @@ static int match_session(struct cifs_ses *ses,
 	case Kerberos:
 		if (!uid_eq(ctx->cred_uid, ses->cred_uid))
 			return 0;
+		if (strncmp(ses->user_name ?: "",
+			    ctx->username ?: "",
+			    CIFS_MAX_USERNAME_LEN))
+			return 0;
 		break;
 	case NTLMv2:
 	case RawNTLMSSP:
-- 
cgit v1.2.3


From c8b8f3c50f487b145433a6c3f95efd8790079a06 Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Mon, 16 Mar 2026 10:36:00 +0800
Subject: LoongArch: Only use SC.Q when supported by the assembler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 128-bit atomic cmpxchg implementation uses the SC.Q instruction.
Older versions of GNU AS do not support that instruction, erroring out:

ERROR:root:{standard input}: Assembler messages:
{standard input}:4831: Error: no match insn: sc.q	$t0,$t1,$r14
{standard input}:6407: Error: no match insn: sc.q	$t0,$t1,$r23
{standard input}:10856: Error: no match insn: sc.q	$t0,$t1,$r14

make[4]: *** [../scripts/Makefile.build:289: mm/slub.o] Error 1

(Binutils 2.41)

So test support for SC.Q in Kconfig and disable the atomics if the
instruction is not available.

Fixes: f0e4b1b6e295 ("LoongArch: Add 128-bit atomic cmpxchg support")
Closes: https://lore.kernel.org/lkml/20260216082834-edc51c46-7b7a-4295-8ea5-4d9a3ca2224f@linutronix.de/
Reviewed-by: Xi Ruoyao <xry111@xry111.site>
Acked-by: Hengqi Chen <hengqi.chen@gmail.com>
Tested-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Kconfig               | 3 +++
 arch/loongarch/include/asm/cmpxchg.h | 5 +++++
 2 files changed, 8 insertions(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index d211c6572b0a..92068ff38685 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -304,6 +304,9 @@ config AS_HAS_LBT_EXTENSION
 config AS_HAS_LVZ_EXTENSION
 	def_bool $(as-instr,hvcl 0)
 
+config AS_HAS_SCQ_EXTENSION
+	def_bool $(as-instr,sc.q \$t0$(comma)\$t1$(comma)\$t2)
+
 config CC_HAS_ANNOTATE_TABLEJUMP
 	def_bool $(cc-option,-mannotate-tablejump)
 
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 58cabab6d90d..909f9274fe71 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -238,6 +238,8 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, unsigned int
 	arch_cmpxchg((ptr), (o), (n));					\
   })
 
+#ifdef CONFIG_AS_HAS_SCQ_EXTENSION
+
 union __u128_halves {
 	u128 full;
 	struct {
@@ -290,6 +292,9 @@ union __u128_halves {
 	BUILD_BUG_ON(sizeof(*(ptr)) != 16);				\
 	__arch_cmpxchg128(ptr, o, n, "");				\
 })
+
+#endif /* CONFIG_AS_HAS_SCQ_EXTENSION */
+
 #else
 #include <asm-generic/cmpxchg-local.h>
 #define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n))
-- 
cgit v1.2.3


From 8a69d02481ff97683952e94b9d1eae29b45f88fd Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Mon, 16 Mar 2026 10:36:01 +0800
Subject: LoongArch: Fix calling smp_processor_id() in preemptible code

Fix the warning:

  BUG: using smp_processor_id() in preemptible [00000000] code: systemd/1
  caller is larch_insn_text_copy+0x40/0xf0

Simply changing it to raw_smp_processor_id() is not enough: if preempt
and CPU hotplug happens after raw_smp_processor_id() but before calling
stop_machine(), the CPU where raw_smp_processor_id() has run may become
offline when stop_machine() and no CPU will run copy_to_kernel_nofault()
in text_copy_cb().  Thus guard the larch_insn_text_copy() calls with
cpus_read_lock() and change stop_machine() to stop_machine_cpuslocked()
to prevent this.

I've considered moving the locks inside larch_insn_text_copy() but
doing so seems not an easy hack. In bpf_arch_text_poke() obviously the
memcpy() call must be guarded by text_mutex, so we have to leave the
acquire of text_mutex out of larch_insn_text_copy(). But in the entire
kernel the acquire of mutexes is always after cpus_read_lock(), so we
cannot put cpus_read_lock() into larch_insn_text_copy() while leaving
the text_mutex acquire out (or we risk a deadlock due to inconsistent
lock acquire order). So let's fix the bug first and leave the posssible
refactor as future work.

Fixes: 9fbd18cf4c69 ("LoongArch: BPF: Add dynamic code modification support")
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/inst.c | 10 ++++++++--
 arch/loongarch/net/bpf_jit.c |  6 ++++++
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index bf037f0c6b26..25fdb933119d 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -263,14 +263,20 @@ int larch_insn_text_copy(void *dst, void *src, size_t len)
 		.dst = dst,
 		.src = src,
 		.len = len,
-		.cpu = smp_processor_id(),
+		.cpu = raw_smp_processor_id(),
 	};
 
+	/*
+	 * Ensure copy.cpu won't be hot removed before stop_machine.
+	 * If it is removed nobody will really update the text.
+	 */
+	lockdep_assert_cpus_held();
+
 	start = round_down((size_t)dst, PAGE_SIZE);
 	end   = round_up((size_t)dst + len, PAGE_SIZE);
 
 	set_memory_rw(start, (end - start) / PAGE_SIZE);
-	ret = stop_machine(text_copy_cb, &copy, cpu_online_mask);
+	ret = stop_machine_cpuslocked(text_copy_cb, &copy, cpu_online_mask);
 	set_memory_rox(start, (end - start) / PAGE_SIZE);
 
 	return ret;
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 3bd89f55960d..e8e0ad34928c 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1379,9 +1379,11 @@ void *bpf_arch_text_copy(void *dst, void *src, size_t len)
 {
 	int ret;
 
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	ret = larch_insn_text_copy(dst, src, len);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 
 	return ret ? ERR_PTR(-EINVAL) : dst;
 }
@@ -1429,10 +1431,12 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
 	if (ret)
 		return ret;
 
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	if (memcmp(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES))
 		ret = larch_insn_text_copy(ip, new_insns, LOONGARCH_LONG_JUMP_NBYTES);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -1450,10 +1454,12 @@ int bpf_arch_text_invalidate(void *dst, size_t len)
 	for (i = 0; i < (len / sizeof(u32)); i++)
 		inst[i] = INSN_BREAK;
 
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	if (larch_insn_text_copy(dst, inst, len))
 		ret = -EINVAL;
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 
 	kvfree(inst);
 
-- 
cgit v1.2.3


From a47f0754bdd01f971c9715acdbdd3a07515c8f83 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 16 Mar 2026 10:36:01 +0800
Subject: LoongArch: Give more information if kmem access failed

If memory access such as copy_{from, to}_kernel_nofault() failed, its
users do not know what happened, so it is very useful to print the
exception code for such cases. Furthermore, it is better to print the
caller function to know where is the entry.

Here are the low level call chains:

  copy_from_kernel_nofault()
    copy_from_kernel_nofault_loop()
      __get_kernel_nofault()

  copy_to_kernel_nofault()
    copy_to_kernel_nofault_loop()
      __put_kernel_nofault()

Cc: stable@vger.kernel.org
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/uaccess.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h
index 4e259d490e45..438269313e78 100644
--- a/arch/loongarch/include/asm/uaccess.h
+++ b/arch/loongarch/include/asm/uaccess.h
@@ -253,8 +253,13 @@ do {									\
 									\
 	__get_kernel_common(*((type *)(dst)), sizeof(type),		\
 			    (__force type *)(src));			\
-	if (unlikely(__gu_err))						\
+	if (unlikely(__gu_err))	{					\
+		pr_info("%s: memory access failed, ecode 0x%x\n",	\
+			__func__, read_csr_excode());			\
+		pr_info("%s: the caller is %pS\n",			\
+			__func__, __builtin_return_address(0));		\
 		goto err_label;						\
+	}								\
 } while (0)
 
 #define __put_kernel_nofault(dst, src, type, err_label)			\
@@ -264,8 +269,13 @@ do {									\
 									\
 	__pu_val = *(__force type *)(src);				\
 	__put_kernel_common(((type *)(dst)), sizeof(type));		\
-	if (unlikely(__pu_err))						\
+	if (unlikely(__pu_err))	{					\
+		pr_info("%s: memory access failed, ecode 0x%x\n",	\
+			__func__, read_csr_excode());			\
+		pr_info("%s: the caller is %pS\n",			\
+			__func__, __builtin_return_address(0));		\
 		goto err_label;						\
+	}								\
 } while (0)
 
 extern unsigned long __copy_user(void *to, const void *from, __kernel_size_t n);
-- 
cgit v1.2.3


From 431ce839dad66d0d56fb604785452c6a57409f35 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 16 Mar 2026 10:36:01 +0800
Subject: LoongArch: Check return values for set_memory_{rw,rox}

set_memory_rw() and set_memory_rox() may fail, so we should check the
return values and return immediately in larch_insn_text_copy().

Cc: stable@vger.kernel.org
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/inst.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index 25fdb933119d..6c4ce6892276 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -258,6 +258,7 @@ static int text_copy_cb(void *data)
 int larch_insn_text_copy(void *dst, void *src, size_t len)
 {
 	int ret = 0;
+	int err = 0;
 	size_t start, end;
 	struct insn_copy copy = {
 		.dst = dst,
@@ -275,9 +276,19 @@ int larch_insn_text_copy(void *dst, void *src, size_t len)
 	start = round_down((size_t)dst, PAGE_SIZE);
 	end   = round_up((size_t)dst + len, PAGE_SIZE);
 
-	set_memory_rw(start, (end - start) / PAGE_SIZE);
+	err = set_memory_rw(start, (end - start) / PAGE_SIZE);
+	if (err) {
+		pr_info("%s: set_memory_rw() failed\n", __func__);
+		return err;
+	}
+
 	ret = stop_machine_cpuslocked(text_copy_cb, &copy, cpu_online_mask);
-	set_memory_rox(start, (end - start) / PAGE_SIZE);
+
+	err = set_memory_rox(start, (end - start) / PAGE_SIZE);
+	if (err) {
+		pr_info("%s: set_memory_rox() failed\n", __func__);
+		return err;
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From d3b8491961207ac967795c34375890407fd51a45 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 16 Mar 2026 10:36:01 +0800
Subject: LoongArch: No need to flush icache if text copy failed

If copy_to_kernel_nofault() failed, no need to flush icache and just
return immediately.

Cc: stable@vger.kernel.org
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/inst.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index 6c4ce6892276..1a728082944c 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -246,13 +246,15 @@ static int text_copy_cb(void *data)
 
 	if (smp_processor_id() == copy->cpu) {
 		ret = copy_to_kernel_nofault(copy->dst, copy->src, copy->len);
-		if (ret)
+		if (ret) {
 			pr_err("%s: operation failed\n", __func__);
+			return ret;
+		}
 	}
 
 	flush_icache_range((unsigned long)copy->dst, (unsigned long)copy->dst + copy->len);
 
-	return ret;
+	return 0;
 }
 
 int larch_insn_text_copy(void *dst, void *src, size_t len)
-- 
cgit v1.2.3


From b254c629a963f0b9d635902f3f979bddbc65f90f Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Mon, 16 Mar 2026 10:36:01 +0800
Subject: LoongArch: BPF: Make arch_protect_bpf_trampoline() return 0

Occasionally there exist "text_copy_cb: operation failed" when executing
the bpf selftests, the reason is copy_to_kernel_nofault() failed and the
ecode of ESTAT register is 0x4 (PME: Page Modification Exception) due to
the pte is not writeable. The root cause is that there is another place
to set the pte entry as readonly which is in the generic weak version of
arch_protect_bpf_trampoline().

There are two ways to fix this race condition issue: the direct way is
to modify the generic weak arch_protect_bpf_trampoline() to add a mutex
lock for set_memory_rox(), but the other simple and proper way is to
just make arch_protect_bpf_trampoline() return 0 in the arch-specific
code because LoongArch has already use the BPF prog pack allocator for
trampoline.

Here are the trimmed kernel log messages:

  copy_to_kernel_nofault: memory access failed, ecode 0x4
  copy_to_kernel_nofault: the caller is text_copy_cb+0x50/0xa0
  text_copy_cb: operation failed
  ------------[ cut here ]------------
  bpf_prog_pack bug: missing bpf_arch_text_invalidate?
  WARNING: kernel/bpf/core.c:1008 at bpf_prog_pack_free+0x200/0x228
  ...
  Call Trace:
  [<9000000000248914>] show_stack+0x64/0x188
  [<9000000000241308>] dump_stack_lvl+0x6c/0x9c
  [<90000000002705bc>] __warn+0x9c/0x200
  [<9000000001c428c0>] __report_bug+0xa8/0x1c0
  [<9000000001c42b5c>] report_bug+0x64/0x120
  [<9000000001c7dcd0>] do_bp+0x270/0x3c0
  [<9000000000246f40>] handle_bp+0x120/0x1c0
  [<900000000047b030>] bpf_prog_pack_free+0x200/0x228
  [<900000000047b2ec>] bpf_jit_binary_pack_free+0x24/0x60
  [<900000000026989c>] bpf_jit_free+0x54/0xb0
  [<900000000029e10c>] process_one_work+0x184/0x610
  [<900000000029ef8c>] worker_thread+0x24c/0x388
  [<90000000002a902c>] kthread+0x13c/0x170
  [<9000000001c7dfe8>] ret_from_kernel_thread+0x28/0x1c0
  [<9000000000246624>] ret_from_kernel_thread_asm+0xc/0x88

  ---[ end trace 0000000000000000 ]---

Here is a simple shell script to reproduce:

  #!/bin/bash

  for ((i=1; i<=1000; i++))
  do
    echo "Under testing $i ..."
    dmesg -c > /dev/null
    ./test_progs -t fentry_attach_stress > /dev/null
    dmesg -t | grep "text_copy_cb: operation failed"
    if [ $? -eq 0 ]; then
      break
    fi
  done

Cc: stable@vger.kernel.org
Fixes: 4ab17e762b34 ("LoongArch: BPF: Use BPF prog pack allocator")
Acked-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/net/bpf_jit.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index e8e0ad34928c..9cb796e16379 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1574,6 +1574,11 @@ void arch_free_bpf_trampoline(void *image, unsigned int size)
 	bpf_prog_pack_free(image, size);
 }
 
+int arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+	return 0;
+}
+
 /*
  * Sign-extend the register if necessary
  */
-- 
cgit v1.2.3


From c252c12d1f55bd5737e3b8e7839914ccdc7a701c Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Mon, 16 Mar 2026 10:36:02 +0800
Subject: LoongArch: KVM: Fix typo issue in kvm_vm_init_features()

Most of VM feature detections are integer OR operations, and integer
assignment operation will clear previous integer OR operation. So here
change all integer assignment operations to integer OR operations.

Fixes: 82db90bf461b ("LoongArch: KVM: Move feature detection in kvm_vm_init_features()")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/vm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 17b3d5b36cfc..8cc5ee1c53ef 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -49,8 +49,8 @@ static void kvm_vm_init_features(struct kvm *kvm)
 		kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PMU);
 
 	/* Enable all PV features by default */
-	kvm->arch.pv_features = BIT(KVM_FEATURE_IPI);
-	kvm->arch.kvm_features = BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI);
+	kvm->arch.pv_features |= BIT(KVM_FEATURE_IPI);
+	kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI);
 	if (kvm_pvtime_supported()) {
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_PREEMPT);
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
-- 
cgit v1.2.3


From ac57eb3b7d2ad649025b5a0fa207315f755ac4f6 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 9 Mar 2026 18:48:03 +0200
Subject: drm/i915/dmc: Fix an unlikely NULL pointer deference at probe

intel_dmc_update_dc6_allowed_count() oopses when DMC hasn't been
initialized, and dmc is thus NULL.

That would be the case when the call path is
intel_power_domains_init_hw() -> {skl,bxt,icl}_display_core_init() ->
gen9_set_dc_state() -> intel_dmc_update_dc6_allowed_count(), as
intel_power_domains_init_hw() is called *before* intel_dmc_init().

However, gen9_set_dc_state() calls intel_dmc_update_dc6_allowed_count()
conditionally, depending on the current and target DC states. At probe,
the target is disabled, but if DC6 is enabled, the function is called,
and an oops follows. Apparently it's quite unlikely that DC6 is enabled
at probe, as we haven't seen this failure mode before.

It is also strange to have DC6 enabled at boot, since that would require
the DMC firmware (loaded by BIOS); the BIOS loading the DMC firmware and
the driver stopping / reprogramming the firmware is a poorly specified
sequence and as such unlikely an intentional BIOS behaviour. It's more
likely that BIOS is leaving an unintentionally enabled DC6 HW state
behind (without actually loading the required DMC firmware for this).

The tracking of the DC6 allowed counter only works if starting /
stopping the counter depends on the _SW_ DC6 state vs. the current _HW_
DC6 state (since stopping the counter requires the DC5 counter captured
when the counter was started). Thus, using the HW DC6 state is incorrect
and it also leads to the above oops. Fix both issues by using the SW DC6
state for the tracking.

This is v2 of the fix originally sent by Jani, updated based on the
first Link: discussion below.

Link: https://lore.kernel.org/all/3626411dc9e556452c432d0919821b76d9991217@intel.com
Link: https://lore.kernel.org/all/20260228130946.50919-2-ltao@redhat.com
Fixes: 88c1f9a4d36d ("drm/i915/dmc: Create debugfs entry for dc6 counter")
Cc: Mohammed Thasleem <mohammed.thasleem@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Tao Liu <ltao@redhat.com>
Cc: <stable@vger.kernel.org> # v6.16+
Tested-by: Tao Liu <ltao@redhat.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patch.msgid.link/20260309164803.1918158-1-imre.deak@intel.com
(cherry picked from commit 2344b93af8eb5da5d496b4e0529d35f0f559eaf0)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power_well.c | 2 +-
 drivers/gpu/drm/i915/display/intel_dmc.c                | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index db185a859133..fba9fa41f827 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -806,7 +806,7 @@ void gen9_set_dc_state(struct intel_display *display, u32 state)
 			power_domains->dc_state, val & mask);
 
 	enable_dc6 = state & DC_STATE_EN_UPTO_DC6;
-	dc6_was_enabled = val & DC_STATE_EN_UPTO_DC6;
+	dc6_was_enabled = power_domains->dc_state & DC_STATE_EN_UPTO_DC6;
 	if (!dc6_was_enabled && enable_dc6)
 		intel_dmc_update_dc6_allowed_count(display, true);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 1006b060c3f3..0b15cb764b1d 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -1599,8 +1599,7 @@ static bool intel_dmc_get_dc6_allowed_count(struct intel_display *display, u32 *
 		return false;
 
 	mutex_lock(&power_domains->lock);
-	dc6_enabled = intel_de_read(display, DC_STATE_EN) &
-		      DC_STATE_EN_UPTO_DC6;
+	dc6_enabled = power_domains->dc_state & DC_STATE_EN_UPTO_DC6;
 	if (dc6_enabled)
 		intel_dmc_update_dc6_allowed_count(display, false);
 
-- 
cgit v1.2.3


From ce5ae93d1a216680460040c7c0465a6e3b629dec Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sun, 15 Mar 2026 07:24:15 +0900
Subject: ata: libata-core: disable LPM on ADATA SU680 SSD

ADATA SU680 SSDs suffer from NCQ read and write commands timeouts or bus
errors when link power management (LPM) is enabled. Flag these devices
with the ATA_QUIRK_NOLPM quirk to prevent the use of LPM and avoid these
command failures.

Reported-by: Mohammad Khaled Bayan <mhd.khaled.bayan@gmail.com>
Closes: https://bugs.launchpad.net/ubuntu/+source/linux-hwe-6.17/+bug/2144060
Cc: stable@vger.kernel.org
Tested-by: Mohammad-Khaled Bayan <mhd.khaled.bayan@gmail.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6c4e567b6582..374993031895 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4188,6 +4188,9 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	{ "ST3320[68]13AS",	"SD1[5-9]",	ATA_QUIRK_NONCQ |
 						ATA_QUIRK_FIRMWARE_WARN },
 
+	/* ADATA devices with LPM issues. */
+	{ "ADATA SU680",	NULL,		ATA_QUIRK_NOLPM },
+
 	/* Seagate disks with LPM issues */
 	{ "ST1000DM010-2EP102",	NULL,		ATA_QUIRK_NOLPM },
 	{ "ST2000DM008-2FR102",	NULL,		ATA_QUIRK_NOLPM },
-- 
cgit v1.2.3


From 29fe3a61bcdce398ee3955101c39f89c01a8a77e Mon Sep 17 00:00:00 2001
From: Minwoo Ra <raminwo0202@gmail.com>
Date: Sat, 14 Mar 2026 00:58:44 +0900
Subject: xfrm: prevent policy_hthresh.work from racing with netns teardown

A XFRM_MSG_NEWSPDINFO request can queue the per-net work item
policy_hthresh.work onto the system workqueue.

The queued callback, xfrm_hash_rebuild(), retrieves the enclosing
struct net via container_of(). If the net namespace is torn down
before that work runs, the associated struct net may already have
been freed, and xfrm_hash_rebuild() may then dereference stale memory.

xfrm_policy_fini() already flushes policy_hash_work during teardown,
but it does not synchronize policy_hthresh.work.

Synchronize policy_hthresh.work in xfrm_policy_fini() as well, so the
queued work cannot outlive the net namespace teardown and access a
freed struct net.

Fixes: 880a6fab8f6b ("xfrm: configure policy hash table thresholds by netlink")
Signed-off-by: Minwoo Ra <raminwo0202@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 66ac93e65264..2140ee7b102d 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4282,6 +4282,8 @@ static void xfrm_policy_fini(struct net *net)
 	unsigned int sz;
 	int dir;
 
+	disable_work_sync(&net->xfrm.policy_hthresh.work);
+
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
-- 
cgit v1.2.3


From eb2d16a7d599dc9d4df391b5e660df9949963786 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 14 Mar 2026 17:02:10 +0000
Subject: af_key: validate families in pfkey_send_migrate()

syzbot was able to trigger a crash in skb_put() [1]

Issue is that pfkey_send_migrate() does not check old/new families,
and that set_ipsecrequest() @family argument was truncated,
thus possibly overfilling the skb.

Validate families early, do not wait set_ipsecrequest().

[1]

skbuff: skb_over_panic: text:ffffffff8a752120 len:392 put:16 head:ffff88802a4ad040 data:ffff88802a4ad040 tail:0x188 end:0x180 dev:<NULL>
 kernel BUG at net/core/skbuff.c:214 !
Call Trace:
 <TASK>
  skb_over_panic net/core/skbuff.c:219 [inline]
  skb_put+0x159/0x210 net/core/skbuff.c:2655
  skb_put_zero include/linux/skbuff.h:2788 [inline]
  set_ipsecrequest net/key/af_key.c:3532 [inline]
  pfkey_send_migrate+0x1270/0x2e50 net/key/af_key.c:3636
  km_migrate+0x155/0x260 net/xfrm/xfrm_state.c:2848
  xfrm_migrate+0x2140/0x2450 net/xfrm/xfrm_policy.c:4705
  xfrm_do_migrate+0x8ff/0xaa0 net/xfrm/xfrm_user.c:3150

Fixes: 08de61beab8a ("[PFKEYV2]: Extension for dynamic update of endpoint address(es)")
Reported-by: syzbot+b518dfc8e021988fbd55@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69b5933c.050a0220.248e02.00f2.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/key/af_key.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 571200433aa9..bc91aeeb74bb 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3518,7 +3518,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *
 
 static int set_ipsecrequest(struct sk_buff *skb,
 			    uint8_t proto, uint8_t mode, int level,
-			    uint32_t reqid, uint8_t family,
+			    uint32_t reqid, sa_family_t family,
 			    const xfrm_address_t *src, const xfrm_address_t *dst)
 {
 	struct sadb_x_ipsecrequest *rq;
@@ -3583,12 +3583,17 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 
 	/* ipsecrequests */
 	for (i = 0, mp = m; i < num_bundles; i++, mp++) {
-		/* old locator pair */
-		size_pol += sizeof(struct sadb_x_ipsecrequest) +
-			    pfkey_sockaddr_pair_size(mp->old_family);
-		/* new locator pair */
-		size_pol += sizeof(struct sadb_x_ipsecrequest) +
-			    pfkey_sockaddr_pair_size(mp->new_family);
+		int pair_size;
+
+		pair_size = pfkey_sockaddr_pair_size(mp->old_family);
+		if (!pair_size)
+			return -EINVAL;
+		size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size;
+
+		pair_size = pfkey_sockaddr_pair_size(mp->new_family);
+		if (!pair_size)
+			return -EINVAL;
+		size_pol += sizeof(struct sadb_x_ipsecrequest) + pair_size;
 	}
 
 	size += sizeof(struct sadb_msg) + size_pol;
-- 
cgit v1.2.3


From 4bc7bc457922742d38915458e630195e761c1efd Mon Sep 17 00:00:00 2001
From: Daniel Schaefer <git@danielschaefer.me>
Date: Fri, 13 Mar 2026 21:39:25 +0800
Subject: HID: intel-thc-hid: Set HID_PHYS with PCI BDF

Currently HID_PHYS is empty, which means userspace tools (e.g. fwupd)
that depend on it for distinguishing the devices, are unable to do so.
Other drivers like i2c-hid, usbhid, surface-hid, all populate it.

With this change it's set to, for example: HID_PHYS=0000:00:10.0

Each function has just a single HID device, as far as I can tell, so
there is no need to add a suffix.

Tested with fwupd 2.1.1, can avoid https://github.com/fwupd/fwupd/pull/9995

Cc: Even Xu <even.xu@intel.com>
Cc: Xinpeng Sun <xinpeng.sun@intel.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Daniel Schaefer <git@danielschaefer.me>
Reviewed-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c | 1 +
 drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c
index f9fcb398673b..8075992e8732 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-hid.c
@@ -127,6 +127,7 @@ int quicki2c_hid_probe(struct quicki2c_device *qcdev)
 	hid->product = le16_to_cpu(qcdev->dev_desc.product_id);
 	snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quicki2c-hid",
 		 hid->vendor, hid->product);
+	strscpy(hid->phys, dev_name(qcdev->dev), sizeof(hid->phys));
 
 	ret = hid_add_device(hid);
 	if (ret) {
diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c
index 82c72bfa2795..91d5807b4a83 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-hid.c
@@ -118,6 +118,7 @@ int quickspi_hid_probe(struct quickspi_device *qsdev)
 	hid->product = le16_to_cpu(qsdev->dev_desc.product_id);
 	snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "quickspi-hid",
 		 hid->vendor, hid->product);
+	strscpy(hid->phys, dev_name(qsdev->dev), sizeof(hid->phys));
 
 	ret = hid_add_device(hid);
 	if (ret) {
-- 
cgit v1.2.3


From 6f770b73d0311a5b099277653199bb6421c4fed2 Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <syoshida@redhat.com>
Date: Sun, 15 Mar 2026 17:27:49 +0900
Subject: dma: swiotlb: add KMSAN annotations to swiotlb_bounce()

When a device performs DMA to a bounce buffer, KMSAN is unaware of
the write and does not mark the data as initialized.  When
swiotlb_bounce() later copies the bounce buffer back to the original
buffer, memcpy propagates the uninitialized shadow to the original
buffer, causing false positive uninit-value reports.

Fix this by calling kmsan_unpoison_memory() on the bounce buffer
before copying it back in the DMA_FROM_DEVICE path, so that memcpy
naturally propagates initialized shadow to the destination.

Suggested-by: Alexander Potapenko <glider@google.com>
Link: https://lore.kernel.org/CAG_fn=WUGta-paG1BgsGRoAR+fmuCgh3xo=R3XdzOt_-DqSdHw@mail.gmail.com/
Fixes: 7ade4f10779c ("dma: kmsan: unpoison DMA mappings")
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260315082750.2375581-1-syoshida@redhat.com
---
 kernel/dma/swiotlb.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index d8e6f1d889d5..9fd73700ddcf 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/kmsan-checks.h>
 #include <linux/iommu-helper.h>
 #include <linux/init.h>
 #include <linux/memblock.h>
@@ -901,10 +902,19 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 
 			local_irq_save(flags);
 			page = pfn_to_page(pfn);
-			if (dir == DMA_TO_DEVICE)
+			if (dir == DMA_TO_DEVICE) {
+				/*
+				 * Ideally, kmsan_check_highmem_page()
+				 * could be used here to detect infoleaks,
+				 * but callers may map uninitialized buffers
+				 * that will be written by the device,
+				 * causing false positives.
+				 */
 				memcpy_from_page(vaddr, page, offset, sz);
-			else
+			} else {
+				kmsan_unpoison_memory(vaddr, sz);
 				memcpy_to_page(page, offset, vaddr, sz);
+			}
 			local_irq_restore(flags);
 
 			size -= sz;
@@ -913,8 +923,15 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size
 			offset = 0;
 		}
 	} else if (dir == DMA_TO_DEVICE) {
+		/*
+		 * Ideally, kmsan_check_memory() could be used here to detect
+		 * infoleaks (uninitialized data being sent to device), but
+		 * callers may map uninitialized buffers that will be written
+		 * by the device, causing false positives.
+		 */
 		memcpy(vaddr, phys_to_virt(orig_addr), size);
 	} else {
+		kmsan_unpoison_memory(vaddr, size);
 		memcpy(phys_to_virt(orig_addr), vaddr, size);
 	}
 }
-- 
cgit v1.2.3


From 81f86728a9804c7ff99df8f2cb7a7a081a270400 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Mon, 16 Mar 2026 11:11:57 +0000
Subject: tools headers: Skip arm64 cputype.h check

Some definitions in the arm64 kernel's cputype.h are kernel specific and
cause perf build failures when the header is synced into tools.

Stop checking arm64's cputype.h.  In the future, the header in tools
will be updated manually when teaching tools about new CPUs.

Signed-off-by: Leo Yan <leo.yan@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/check-headers.sh | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index da3aca87457f..31826621eebd 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -187,7 +187,6 @@ done
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
 check arch/x86/include/asm/amd/ibs.h  '-I "^#include .*/msr-index.h"'
-check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
 check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
-- 
cgit v1.2.3


From 09e70e4f119ff650d24c96161fd2f62ac7e424b0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 2 Mar 2026 19:43:31 +0100
Subject: regmap: Synchronize cache for the page selector

If the selector register is represented in each page, its value
according to the debugfs is stale because it gets synchronized
only after the real page switch happens. Hence the regmap cache
initialisation from the HW inherits outdated data in the selector
register.

Synchronize cache for the page selector just in time.

Before (offset followed by hexdump, the first byte is selector):

    // Real registers
    18: 05 ff 00 00 ff 0f 00 00 f0 00 00 00
    ...
    // Virtual (per port)
    40: 05 ff 00 00 e0 e0 00 00 00 00 00 1f
    50: 00 ff 00 00 e0 e0 00 00 00 00 00 1f
    60: 01 ff 00 00 ff ff 00 00 00 00 00 00
    70: 02 ff 00 00 cf f3 00 00 00 00 00 0c
    80: 03 ff 00 00 00 00 00 00 00 00 00 ff
    90: 04 ff 00 00 ff 0f 00 00 f0 00 00 00

After:

    // Real registers
    18: 05 ff 00 00 ff 0f 00 00 f0 00 00 00
    ...
    // Virtual (per port)
    40: 00 ff 00 00 e0 e0 00 00 00 00 00 1f
    50: 01 ff 00 00 e0 e0 00 00 00 00 00 1f
    60: 02 ff 00 00 ff ff 00 00 00 00 00 00
    70: 03 ff 00 00 cf f3 00 00 00 00 00 0c
    80: 04 ff 00 00 00 00 00 00 00 00 00 ff
    90: 05 ff 00 00 ff 0f 00 00 f0 00 00 00

Fixes: 6863ca622759 ("regmap: Add support for register indirect addressing.")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20260302184753.2693803-1-andriy.shevchenko@linux.intel.com
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap.c | 30 ++++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 607c1246d994..e388b19850e3 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1545,6 +1545,7 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg,
 			       unsigned int val_num)
 {
 	void *orig_work_buf;
+	unsigned int selector_reg;
 	unsigned int win_offset;
 	unsigned int win_page;
 	bool page_chg;
@@ -1563,10 +1564,31 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg,
 			return -EINVAL;
 	}
 
-	/* It is possible to have selector register inside data window.
-	   In that case, selector register is located on every page and
-	   it needs no page switching, when accessed alone. */
+	/*
+	 * Calculate the address of the selector register in the corresponding
+	 * data window if it is located on every page.
+	 */
+	page_chg = in_range(range->selector_reg, range->window_start, range->window_len);
+	if (page_chg)
+		selector_reg = range->range_min + win_page * range->window_len +
+			       range->selector_reg - range->window_start;
+
+	/*
+	 * It is possible to have selector register inside data window.
+	 * In that case, selector register is located on every page and it
+	 * needs no page switching, when accessed alone.
+	 *
+	 * Nevertheless we should synchronize the cache values for it.
+	 * This can't be properly achieved if the selector register is
+	 * the first and the only one to be read inside the data window.
+	 * That's why we update it in that case as well.
+	 *
+	 * However, we specifically avoid updating it for the default page,
+	 * when it's overlapped with the real data window, to prevent from
+	 * infinite looping.
+	 */
 	if (val_num > 1 ||
+	    (page_chg && selector_reg != range->selector_reg) ||
 	    range->window_start + win_offset != range->selector_reg) {
 		/* Use separate work_buf during page switching */
 		orig_work_buf = map->work_buf;
@@ -1575,7 +1597,7 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg,
 		ret = _regmap_update_bits(map, range->selector_reg,
 					  range->selector_mask,
 					  win_page << range->selector_shift,
-					  &page_chg, false);
+					  NULL, false);
 
 		map->work_buf = orig_work_buf;
 
-- 
cgit v1.2.3


From ba3402f6c85bbeee5c11732c3aa4050a717e8f8f Mon Sep 17 00:00:00 2001
From: Maramaina Naresh <naresh.maramaina@oss.qualcomm.com>
Date: Mon, 16 Mar 2026 18:53:31 +0530
Subject: spi: geni-qcom: Fix CPHA and CPOL mode change detection

setup_fifo_params computes mode_changed from spi->mode flags but tests
it against SE_SPI_CPHA and SE_SPI_CPOL, which are register offsets,
not SPI mode bits. This causes CPHA and CPOL updates to be skipped
on mode switches, leaving the controller with stale clock phase
and polarity settings.

Fix this by using SPI_CPHA and SPI_CPOL to detect mode changes before
updating the corresponding registers.

Fixes: 781c3e71c94c ("spi: spi-geni-qcom: rework setup_fifo_params")
Signed-off-by: Maramaina Naresh <naresh.maramaina@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://patch.msgid.link/20260316-spi-geni-cpha-cpol-fix-v1-1-4cb44c176b79@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-geni-qcom.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 43ce47f2454c..772b7148ba5f 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -359,9 +359,9 @@ static int setup_fifo_params(struct spi_device *spi_slv,
 		writel((spi_slv->mode & SPI_LOOP) ? LOOPBACK_ENABLE : 0, se->base + SE_SPI_LOOPBACK);
 	if (cs_changed)
 		writel(chipselect, se->base + SE_SPI_DEMUX_SEL);
-	if (mode_changed & SE_SPI_CPHA)
+	if (mode_changed & SPI_CPHA)
 		writel((spi_slv->mode & SPI_CPHA) ? CPHA : 0, se->base + SE_SPI_CPHA);
-	if (mode_changed & SE_SPI_CPOL)
+	if (mode_changed & SPI_CPOL)
 		writel((spi_slv->mode & SPI_CPOL) ? CPOL : 0, se->base + SE_SPI_CPOL);
 	if ((mode_changed & SPI_CS_HIGH) || (cs_changed && (spi_slv->mode & SPI_CS_HIGH)))
 		writel((spi_slv->mode & SPI_CS_HIGH) ? BIT(chipselect) : 0, se->base + SE_SPI_DEMUX_OUTPUT_INV);
-- 
cgit v1.2.3


From 5e3486e64094c28a526543f1e8aa0d5964b7f02d Mon Sep 17 00:00:00 2001
From: Luke Wang <ziniu.wang_1@nxp.com>
Date: Wed, 11 Mar 2026 17:50:06 +0800
Subject: mmc: sdhci: fix timing selection for 1-bit bus width

When 1-bit bus width is used with HS200/HS400 capabilities set,
mmc_select_hs200() returns 0 without actually switching. This
causes mmc_select_timing() to skip mmc_select_hs(), leaving eMMC
in legacy mode (26MHz) instead of High Speed SDR (52MHz).

Per JEDEC eMMC spec section 5.3.2, 1-bit mode supports High Speed
SDR. Drop incompatible HS200/HS400/UHS/DDR caps early so timing
selection falls through to mmc_select_hs() correctly.

Fixes: f2119df6b764 ("mmc: sd: add support for signal voltage switch procedure")
Signed-off-by: Luke Wang <ziniu.wang_1@nxp.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index ac7e11f37af7..fec9329e1edb 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -4532,8 +4532,15 @@ int sdhci_setup_host(struct sdhci_host *host)
 	 * their platform code before calling sdhci_add_host(), and we
 	 * won't assume 8-bit width for hosts without that CAP.
 	 */
-	if (!(host->quirks & SDHCI_QUIRK_FORCE_1_BIT_DATA))
+	if (host->quirks & SDHCI_QUIRK_FORCE_1_BIT_DATA) {
+		host->caps1 &= ~(SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50);
+		if (host->quirks2 & SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400)
+			host->caps1 &= ~SDHCI_SUPPORT_HS400;
+		mmc->caps2 &= ~(MMC_CAP2_HS200 | MMC_CAP2_HS400 | MMC_CAP2_HS400_ES);
+		mmc->caps &= ~(MMC_CAP_DDR | MMC_CAP_UHS);
+	} else {
 		mmc->caps |= MMC_CAP_4_BIT_DATA;
+	}
 
 	if (host->quirks2 & SDHCI_QUIRK2_HOST_NO_CMD23)
 		mmc->caps &= ~MMC_CAP_CMD23;
-- 
cgit v1.2.3


From 0a3fe972a7cb1404f693d6f1711f32bc1d244b1c Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Mon, 9 Mar 2026 14:59:29 +0000
Subject: HID: core: Mitigate potential OOB by removing bogus memset()

The memset() in hid_report_raw_event() has the good intention of
clearing out bogus data by zeroing the area from the end of the incoming
data string to the assumed end of the buffer.  However, as we have
previously seen, doing so can easily result in OOB reads and writes in
the subsequent thread of execution.

The current suggestion from one of the HID maintainers is to remove the
memset() and simply return if the incoming event buffer size is not
large enough to fill the associated report.

Suggested-by Benjamin Tissoires <bentiss@kernel.org>

Signed-off-by: Lee Jones <lee@kernel.org>
[bentiss: changed the return value]
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index a5b3a8ca2fcb..f5587b786f87 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2057,9 +2057,10 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 		rsize = max_buffer_size;
 
 	if (csize < rsize) {
-		dbg_hid("report %d is too short, (%d < %d)\n", report->id,
-				csize, rsize);
-		memset(cdata + csize, 0, rsize - csize);
+		hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %d)\n",
+				     report->id, rsize, csize);
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if ((hid->claimed & HID_CLAIMED_HIDDEV) && hid->hiddev_report_event)
-- 
cgit v1.2.3


From 5d4c6c132ea9a967d48890dd03e6a786c060e968 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <bentiss@kernel.org>
Date: Fri, 13 Mar 2026 08:40:24 +0100
Subject: selftests/hid: fix compilation when bpf_wq and hid_device are not
 exported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This can happen in situations when CONFIG_HID_SUPPORT is set to no, or
some complex situations where struct bpf_wq is not exported.

So do the usual dance of hiding them before including vmlinux.h, and
then redefining them and make use of CO-RE to have the correct offsets.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603111558.KLCIxsZB-lkp@intel.com/
Fixes: fe8d561db3e8 ("selftests/hid: add wq test for hid_bpf_input_report()")
Cc: stable@vger.kernel.org
Acked-by: Jiri Kosina <jkosina@suse.com>
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 tools/testing/selftests/hid/progs/hid_bpf_helpers.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
index 80ab60905865..cdca912f3afd 100644
--- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
+++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
@@ -6,8 +6,10 @@
 #define __HID_BPF_HELPERS_H
 
 /* "undefine" structs and enums in vmlinux.h, because we "override" them below */
+#define bpf_wq bpf_wq___not_used
 #define hid_bpf_ctx hid_bpf_ctx___not_used
 #define hid_bpf_ops hid_bpf_ops___not_used
+#define hid_device hid_device___not_used
 #define hid_report_type hid_report_type___not_used
 #define hid_class_request hid_class_request___not_used
 #define hid_bpf_attach_flags hid_bpf_attach_flags___not_used
@@ -27,8 +29,10 @@
 
 #include "vmlinux.h"
 
+#undef bpf_wq
 #undef hid_bpf_ctx
 #undef hid_bpf_ops
+#undef hid_device
 #undef hid_report_type
 #undef hid_class_request
 #undef hid_bpf_attach_flags
@@ -55,6 +59,14 @@ enum hid_report_type {
 	HID_REPORT_TYPES,
 };
 
+struct hid_device {
+	unsigned int id;
+} __attribute__((preserve_access_index));
+
+struct bpf_wq {
+	__u64 __opaque[2];
+};
+
 struct hid_bpf_ctx {
 	struct hid_device *hid;
 	__u32 allocated_size;
-- 
cgit v1.2.3


From 2b658c1c442ec1cd9eec5ead98d68662c40fe645 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <bentiss@kernel.org>
Date: Fri, 13 Mar 2026 08:40:25 +0100
Subject: HID: bpf: prevent buffer overflow in hid_hw_request

right now the returned value is considered to be always valid. However,
when playing with HID-BPF, the return value can be arbitrary big,
because it's the return value of dispatch_hid_bpf_raw_requests(), which
calls the struct_ops and we have no guarantees that the value makes
sense.

Fixes: 8bd0488b5ea5 ("HID: bpf: add HID-BPF hooks for hid_hw_raw_requests")
Cc: stable@vger.kernel.org
Acked-by: Jiri Kosina <jkosina@suse.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/bpf/hid_bpf_dispatch.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c
index 892aca026ffa..33af17fdc729 100644
--- a/drivers/hid/bpf/hid_bpf_dispatch.c
+++ b/drivers/hid/bpf/hid_bpf_dispatch.c
@@ -444,6 +444,8 @@ hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
 					      (u64)(long)ctx,
 					      true); /* prevent infinite recursions */
 
+	if (ret > size)
+		ret = size;
 	if (ret > 0)
 		memcpy(buf, dma_data, ret);
 
-- 
cgit v1.2.3


From f7a4c78bfeb320299c1b641500fe7761eadbd101 Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Fri, 27 Feb 2026 10:09:38 +0000
Subject: HID: logitech-hidpp: Prevent use-after-free on force feedback
 initialisation failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Presently, if the force feedback initialisation fails when probing the
Logitech G920 Driving Force Racing Wheel for Xbox One, an error number
will be returned and propagated before the userspace infrastructure
(sysfs and /dev/input) has been torn down.  If userspace ignores the
errors and continues to use its references to these dangling entities, a
UAF will promptly follow.

We have 2 options; continue to return the error, but ensure that all of
the infrastructure is torn down accordingly or continue to treat this
condition as a warning by emitting the message but returning success.
It is thought that the original author's intention was to emit the
warning but keep the device functional, less the force feedback feature,
so let's go with that.

Signed-off-by: Lee Jones <lee@kernel.org>
Reviewed-by: Günther Noack <gnoack@google.com>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-logitech-hidpp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index c3d53250a760..65bfad405ac5 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4487,10 +4487,12 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		if (!ret)
 			ret = hidpp_ff_init(hidpp, &data);
 
-		if (ret)
+		if (ret) {
 			hid_warn(hidpp->hid_dev,
 		     "Unable to initialize force feedback support, errno %d\n",
 				 ret);
+			ret = 0;
+		}
 	}
 
 	/*
-- 
cgit v1.2.3


From b00be77302d7ec4ad0367bb236494fce7172b730 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Wed, 4 Mar 2026 10:18:37 +0000
Subject: s390/mm: Add missing secure storage access fixups for donated memory

There are special cases where secure storage access exceptions happen
in a kernel context for pages that don't have the PG_arch_1 bit
set. That bit is set for non-exported guest secure storage (memory)
but is absent on storage donated to the Ultravisor since the kernel
isn't allowed to export donated pages.

Prior to this patch we would try to export the page by calling
arch_make_folio_accessible() which would instantly return since the
arch bit is absent signifying that the page was already exported and
no further action is necessary. This leads to secure storage access
exception loops which can never be resolved.

With this patch we unconditionally try to export and if that fails we
fixup.

Fixes: 084ea4d611a3 ("s390/mm: add (non)secure page access exceptions handlers")
Reported-by: Heiko Carstens <hca@linux.ibm.com>
Suggested-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
---
 arch/s390/mm/fault.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a52aa7a99b6b..191cc53caead 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -441,10 +441,17 @@ void do_secure_storage_access(struct pt_regs *regs)
 		folio = phys_to_folio(addr);
 		if (unlikely(!folio_try_get(folio)))
 			return;
-		rc = arch_make_folio_accessible(folio);
+		rc = uv_convert_from_secure(folio_to_phys(folio));
+		if (!rc)
+			clear_bit(PG_arch_1, &folio->flags.f);
 		folio_put(folio);
+		/*
+		 * There are some valid fixup types for kernel
+		 * accesses to donated secure memory. zeropad is one
+		 * of them.
+		 */
 		if (rc)
-			BUG();
+			return handle_fault_error_nolock(regs, 0);
 	} else {
 		if (faulthandler_disabled())
 			return handle_fault_error_nolock(regs, 0);
-- 
cgit v1.2.3


From dcf96f7ad556d84d460e5f5cf06061eb1a13c272 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Tue, 3 Mar 2026 13:46:34 +0000
Subject: KVM: s390: Limit adapter indicator access to mapped page

While we check the address for errors, we don't seem to check the bit
offsets and since they are 32 and 64 bits a lot of memory can be
reached indirectly via those offsets.

Fixes: 84223598778b ("KVM: s390: irq routing for adapter interrupts.")
Suggested-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
---
 arch/s390/kvm/interrupt.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 18932a65ca68..1a702e8ef574 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2724,6 +2724,9 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
 
 	bit = bit_nr + (addr % PAGE_SIZE) * 8;
 
+	/* kvm_set_routing_entry() should never allow this to happen */
+	WARN_ON_ONCE(bit > (PAGE_SIZE * BITS_PER_BYTE - 1));
+
 	return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
 }
 
@@ -2852,6 +2855,7 @@ int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
+	const struct kvm_irq_routing_s390_adapter *adapter;
 	u64 uaddr_s, uaddr_i;
 	int idx;
 
@@ -2862,6 +2866,14 @@ int kvm_set_routing_entry(struct kvm *kvm,
 			return -EINVAL;
 		e->set = set_adapter_int;
 
+		adapter = &ue->u.adapter;
+		if (adapter->summary_addr + (adapter->summary_offset / 8) >=
+		    (adapter->summary_addr & PAGE_MASK) + PAGE_SIZE)
+			return -EINVAL;
+		if (adapter->ind_addr + (adapter->ind_offset / 8) >=
+		    (adapter->ind_addr & PAGE_MASK) + PAGE_SIZE)
+			return -EINVAL;
+
 		idx = srcu_read_lock(&kvm->srcu);
 		uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr);
 		uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr);
-- 
cgit v1.2.3


From 0c6294d98a6dfadd53296d762f4a396c2f04c7c1 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Tue, 3 Mar 2026 13:46:35 +0000
Subject: KVM: s390: selftests: Add IRQ routing address offset tests

This test tries to setup routes which have address + offset
combinations which cross a page.

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
---
 tools/testing/selftests/kvm/Makefile.kvm       |  1 +
 tools/testing/selftests/kvm/s390/irq_routing.c | 75 ++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/s390/irq_routing.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index fdec90e85467..271cbb63af36 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -205,6 +205,7 @@ TEST_GEN_PROGS_s390 += s390/ucontrol_test
 TEST_GEN_PROGS_s390 += s390/user_operexec
 TEST_GEN_PROGS_s390 += s390/keyop
 TEST_GEN_PROGS_s390 += rseq_test
+TEST_GEN_PROGS_s390 += s390/irq_routing
 
 TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON)
 TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
diff --git a/tools/testing/selftests/kvm/s390/irq_routing.c b/tools/testing/selftests/kvm/s390/irq_routing.c
new file mode 100644
index 000000000000..7819a0af19a8
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390/irq_routing.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * IRQ routing offset tests.
+ *
+ * Copyright IBM Corp. 2026
+ *
+ * Authors:
+ *  Janosch Frank <frankja@linux.ibm.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kselftest.h"
+#include "ucall_common.h"
+
+extern char guest_code[];
+asm("guest_code:\n"
+    "diag %r0,%r0,0\n"
+    "j .\n");
+
+static void test(void)
+{
+	struct kvm_irq_routing *routing;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	vm_paddr_t mem;
+	int ret;
+
+	struct kvm_irq_routing_entry ue = {
+		.type = KVM_IRQ_ROUTING_S390_ADAPTER,
+		.gsi = 1,
+	};
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+	mem = vm_phy_pages_alloc(vm, 2, 4096 * 42, 0);
+
+	routing = kvm_gsi_routing_create();
+	routing->nr = 1;
+	routing->entries[0] = ue;
+	routing->entries[0].u.adapter.summary_addr = (uintptr_t)mem;
+	routing->entries[0].u.adapter.ind_addr = (uintptr_t)mem;
+
+	routing->entries[0].u.adapter.summary_offset = 4096 * 8;
+	ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing);
+	ksft_test_result(ret == -1 && errno == EINVAL, "summary offset outside of page\n");
+
+	routing->entries[0].u.adapter.summary_offset -= 4;
+	ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing);
+	ksft_test_result(ret == 0, "summary offset inside of page\n");
+
+	routing->entries[0].u.adapter.ind_offset = 4096 * 8;
+	ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing);
+	ksft_test_result(ret == -1 && errno == EINVAL, "ind offset outside of page\n");
+
+	routing->entries[0].u.adapter.ind_offset -= 4;
+	ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing);
+	ksft_test_result(ret == 0, "ind offset inside of page\n");
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_IRQ_ROUTING));
+
+	ksft_print_header();
+	ksft_set_plan(4);
+	test();
+
+	ksft_finished();	/* Print results and exit() accordingly */
+}
-- 
cgit v1.2.3


From 1ca90f4ae554034d96764577196d8dd0c3bcd05e Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@linux.ibm.com>
Date: Fri, 6 Mar 2026 11:25:40 +0100
Subject: KVM: s390: log machine checks more aggressively

KVM will reinject machine checks that happen during guest activity.
From a host perspective this machine check is no longer visible
and even for the guest, the guest might decide to only kill a
userspace program or even ignore the machine check.
As this can be a disruptive event nevertheless, we should log this
not only in the VM debug event (that gets lost after guest shutdown)
but also on the global KVM event as well as syslog.
Consolidate the logging and log with loglevel 2 and higher.

Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: Janosch Frank <frankja@linux.ibm.com>
Acked-by: Hendrik Brueckner <brueckner@linux.ibm.com>
---
 arch/s390/kvm/interrupt.c | 6 ++++++
 arch/s390/kvm/kvm-s390.c  | 1 -
 arch/s390/kvm/vsie.c      | 1 -
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1a702e8ef574..7cb8ce833b62 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2827,6 +2827,12 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 	int rc;
 
 	mci.val = mcck_info->mcic;
+
+	/* log machine checks being reinjected on all debugs */
+	VCPU_EVENT(vcpu, 2, "guest machine check %lx", mci.val);
+	KVM_EVENT(2, "guest machine check %lx", mci.val);
+	pr_info("guest machine check pid %d: %lx", current->pid, mci.val);
+
 	if (mci.sr)
 		cr14 |= CR14_RECOVERY_SUBMASK;
 	if (mci.dg)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index bc7d6fa66eaf..1668580008c6 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4634,7 +4634,6 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
 
 	if (exit_reason == -EINTR) {
-		VCPU_EVENT(vcpu, 3, "%s", "machine check");
 		sie_page = container_of(vcpu->arch.sie_block,
 					struct sie_page, sie_block);
 		mcck_info = &sie_page->mcck_info;
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index d249b10044eb..c0d36afd4023 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1179,7 +1179,6 @@ skip_sie:
 	kvm_vcpu_srcu_read_lock(vcpu);
 
 	if (rc == -EINTR) {
-		VCPU_EVENT(vcpu, 3, "%s", "machine check");
 		kvm_s390_reinject_machine_check(vcpu, &vsie_page->mcck_info);
 		return 0;
 	}
-- 
cgit v1.2.3


From ab5119735e984f6b724ef1b699c01479949ed1de Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@linux.ibm.com>
Date: Mon, 16 Mar 2026 13:13:17 +0100
Subject: KVM: s390: vsie: Avoid injecting machine check on signal

The recent XFER_TO_GUEST_WORK change resulted in a situation, where the
vsie code would interpret a signal during work as a machine check during
SIE as both use the EINTR return code.
The exit_reason of the sie64a function has nothing to do with the
kvm_run exit_reason. Rename it and define a specific code for machine
checks instead of abusing -EINTR.
rename exit_reason into sie_return to avoid the naming conflict
and change the code flow in vsie.c to have a separate variable for rc
and sie_return.

Fixes: 2bd1337a1295e ("KVM: s390: Use generic VIRT_XFER_TO_GUEST_WORK functions")
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/include/asm/kvm_host.h   |  3 +++
 arch/s390/include/asm/stacktrace.h |  2 +-
 arch/s390/kernel/asm-offsets.c     |  2 +-
 arch/s390/kernel/entry.S           |  4 ++--
 arch/s390/kernel/nmi.c             |  4 ++--
 arch/s390/kvm/kvm-s390.c           | 15 ++++++++-------
 arch/s390/kvm/vsie.c               |  7 +++++--
 7 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 64a50f0862aa..3039c88daa63 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -710,6 +710,9 @@ void kvm_arch_crypto_clear_masks(struct kvm *kvm);
 void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm,
 			       unsigned long *aqm, unsigned long *adm);
 
+#define SIE64_RETURN_NORMAL	0
+#define SIE64_RETURN_MCCK	1
+
 int __sie64a(phys_addr_t sie_block_phys, struct kvm_s390_sie_block *sie_block, u64 *rsa,
 	     unsigned long gasce);
 
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
index c9ae680a28af..ac3606c3babe 100644
--- a/arch/s390/include/asm/stacktrace.h
+++ b/arch/s390/include/asm/stacktrace.h
@@ -62,7 +62,7 @@ struct stack_frame {
 		struct {
 			unsigned long sie_control_block;
 			unsigned long sie_savearea;
-			unsigned long sie_reason;
+			unsigned long sie_return;
 			unsigned long sie_flags;
 			unsigned long sie_control_block_phys;
 			unsigned long sie_guest_asce;
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index e1a5b5b54e4f..fbd26f3e9f96 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -63,7 +63,7 @@ int main(void)
 	OFFSET(__SF_EMPTY, stack_frame, empty[0]);
 	OFFSET(__SF_SIE_CONTROL, stack_frame, sie_control_block);
 	OFFSET(__SF_SIE_SAVEAREA, stack_frame, sie_savearea);
-	OFFSET(__SF_SIE_REASON, stack_frame, sie_reason);
+	OFFSET(__SF_SIE_RETURN, stack_frame, sie_return);
 	OFFSET(__SF_SIE_FLAGS, stack_frame, sie_flags);
 	OFFSET(__SF_SIE_CONTROL_PHYS, stack_frame, sie_control_block_phys);
 	OFFSET(__SF_SIE_GUEST_ASCE, stack_frame, sie_guest_asce);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 4873fe9d891b..5817cb47b2d0 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -200,7 +200,7 @@ SYM_FUNC_START(__sie64a)
 	stg	%r3,__SF_SIE_CONTROL(%r15)	# ...and virtual addresses
 	stg	%r4,__SF_SIE_SAVEAREA(%r15)	# save guest register save area
 	stg	%r5,__SF_SIE_GUEST_ASCE(%r15)	# save guest asce
-	xc	__SF_SIE_REASON(8,%r15),__SF_SIE_REASON(%r15) # reason code = 0
+	xc	__SF_SIE_RETURN(8,%r15),__SF_SIE_RETURN(%r15) # return code = 0
 	mvc	__SF_SIE_FLAGS(8,%r15),__TI_flags(%r14) # copy thread flags
 	lmg	%r0,%r13,0(%r4)			# load guest gprs 0-13
 	mvi	__TI_sie(%r14),1
@@ -237,7 +237,7 @@ SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL)
 	xgr	%r4,%r4
 	xgr	%r5,%r5
 	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
-	lg	%r2,__SF_SIE_REASON(%r15)	# return exit reason code
+	lg	%r2,__SF_SIE_RETURN(%r15)	# return sie return code
 	BR_EX	%r14
 SYM_FUNC_END(__sie64a)
 EXPORT_SYMBOL(__sie64a)
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index a55abbf65333..94fbfad49f62 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -487,8 +487,8 @@ void notrace s390_do_machine_check(struct pt_regs *regs)
 	mcck_dam_code = (mci.val & MCIC_SUBCLASS_MASK);
 	if (test_cpu_flag(CIF_MCCK_GUEST) &&
 	(mcck_dam_code & MCCK_CODE_NO_GUEST) != mcck_dam_code) {
-		/* Set exit reason code for host's later handling */
-		*((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR;
+		/* Set sie return code for host's later handling */
+		((struct stack_frame *)regs->gprs[15])->sie_return = SIE64_RETURN_MCCK;
 	}
 	clear_cpu_flag(CIF_MCCK_GUEST);
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1668580008c6..ebcb0ef8835e 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -4617,7 +4617,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
+static int vcpu_post_run(struct kvm_vcpu *vcpu, int sie_return)
 {
 	struct mcck_volatile_info *mcck_info;
 	struct sie_page *sie_page;
@@ -4633,13 +4633,14 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
 	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
 
-	if (exit_reason == -EINTR) {
+	if (sie_return == SIE64_RETURN_MCCK) {
 		sie_page = container_of(vcpu->arch.sie_block,
 					struct sie_page, sie_block);
 		mcck_info = &sie_page->mcck_info;
 		kvm_s390_reinject_machine_check(vcpu, mcck_info);
 		return 0;
 	}
+	WARN_ON_ONCE(sie_return != SIE64_RETURN_NORMAL);
 
 	if (vcpu->arch.sie_block->icptcode > 0) {
 		rc = kvm_handle_sie_intercept(vcpu);
@@ -4678,7 +4679,7 @@ int noinstr kvm_s390_enter_exit_sie(struct kvm_s390_sie_block *scb,
 #define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK)
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
-	int rc, exit_reason;
+	int rc, sie_return;
 	struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block;
 
 	/*
@@ -4718,9 +4719,9 @@ xfer_to_guest_mode_check:
 		guest_timing_enter_irqoff();
 		__disable_cpu_timer_accounting(vcpu);
 
-		exit_reason = kvm_s390_enter_exit_sie(vcpu->arch.sie_block,
-						      vcpu->run->s.regs.gprs,
-						      vcpu->arch.gmap->asce.val);
+		sie_return = kvm_s390_enter_exit_sie(vcpu->arch.sie_block,
+						     vcpu->run->s.regs.gprs,
+						     vcpu->arch.gmap->asce.val);
 
 		__enable_cpu_timer_accounting(vcpu);
 		guest_timing_exit_irqoff();
@@ -4743,7 +4744,7 @@ xfer_to_guest_mode_check:
 		}
 		kvm_vcpu_srcu_read_lock(vcpu);
 
-		rc = vcpu_post_run(vcpu, exit_reason);
+		rc = vcpu_post_run(vcpu, sie_return);
 		if (rc || guestdbg_exit_pending(vcpu)) {
 			kvm_vcpu_srcu_read_unlock(vcpu);
 			break;
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index c0d36afd4023..0330829b4046 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1122,6 +1122,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, struc
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	unsigned long sie_return = SIE64_RETURN_NORMAL;
 	int guest_bp_isolation;
 	int rc = 0;
 
@@ -1163,7 +1164,7 @@ xfer_to_guest_mode_check:
 			goto xfer_to_guest_mode_check;
 		}
 		guest_timing_enter_irqoff();
-		rc = kvm_s390_enter_exit_sie(scb_s, vcpu->run->s.regs.gprs, sg->asce.val);
+		sie_return = kvm_s390_enter_exit_sie(scb_s, vcpu->run->s.regs.gprs, sg->asce.val);
 		guest_timing_exit_irqoff();
 		local_irq_enable();
 	}
@@ -1178,11 +1179,13 @@ skip_sie:
 
 	kvm_vcpu_srcu_read_lock(vcpu);
 
-	if (rc == -EINTR) {
+	if (sie_return == SIE64_RETURN_MCCK) {
 		kvm_s390_reinject_machine_check(vcpu, &vsie_page->mcck_info);
 		return 0;
 	}
 
+	WARN_ON_ONCE(sie_return != SIE64_RETURN_NORMAL);
+
 	if (rc > 0)
 		rc = 0; /* we could still have an icpt */
 	else if (current->thread.gmap_int_code)
-- 
cgit v1.2.3


From a6919f2a01f8fbf807b015e5b26aecae7db8117b Mon Sep 17 00:00:00 2001
From: Sean Rhodes <sean@starlabs.systems>
Date: Sun, 15 Mar 2026 20:11:27 +0000
Subject: ALSA: hda/realtek: Sequence GPIO2 on Star Labs StarFighter

The initial StarFighter quirk fixed the runtime suspend pop by muting
speakers in the shutup callback before power-down. Further hardware
validation showed that the speaker path is controlled directly by LINE2
EAPD on NID 0x1b together with GPIO2 for the external amplifier.

Replace the shutup-delay workaround with explicit sequencing of those
controls at playback start and stop:
- assert LINE2 EAPD and drive GPIO2 high on PREPARE
- deassert LINE2 EAPD and drive GPIO2 low on CLEANUP

This avoids the runtime suspend pop without a sleep, and also fixes pops
around G3 entry and display-manager start that the original workaround
did not cover.

Fixes: 1cb3c20688fc ("ALSA: hda/realtek: Fix speaker pop on Star Labs StarFighter")
Tested-by: Sean Rhodes <sean@starlabs.systems>
Signed-off-by: Sean Rhodes <sean@starlabs.systems>
Link: https://patch.msgid.link/20260315201127.33744-1-sean@starlabs.systems
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 38 ++++++++++++++++++++++++++++++++------
 1 file changed, 32 insertions(+), 6 deletions(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 7294298fce4a..190c1dd11bee 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -1017,12 +1017,30 @@ static int alc269_resume(struct hda_codec *codec)
 	return 0;
 }
 
-#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS	30
+#define ALC233_STARFIGHTER_SPK_PIN	0x1b
+#define ALC233_STARFIGHTER_GPIO2	0x04
 
-static void starlabs_starfighter_shutup(struct hda_codec *codec)
+static void alc233_starfighter_update_amp(struct hda_codec *codec, bool on)
 {
-	if (snd_hda_gen_shutup_speakers(codec))
-		msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS);
+	snd_hda_codec_write(codec, ALC233_STARFIGHTER_SPK_PIN, 0,
+			    AC_VERB_SET_EAPD_BTLENABLE,
+			    on ? AC_EAPDBTL_EAPD : 0);
+	alc_update_gpio_data(codec, ALC233_STARFIGHTER_GPIO2, on);
+}
+
+static void alc233_starfighter_pcm_hook(struct hda_pcm_stream *hinfo,
+					struct hda_codec *codec,
+					struct snd_pcm_substream *substream,
+					int action)
+{
+	switch (action) {
+	case HDA_GEN_PCM_ACT_PREPARE:
+		alc233_starfighter_update_amp(codec, true);
+		break;
+	case HDA_GEN_PCM_ACT_CLEANUP:
+		alc233_starfighter_update_amp(codec, false);
+		break;
+	}
 }
 
 static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec,
@@ -1031,8 +1049,16 @@ static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec,
 {
 	struct alc_spec *spec = codec->spec;
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE)
-		spec->shutup = starlabs_starfighter_shutup;
+	switch (action) {
+	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->gpio_mask |= ALC233_STARFIGHTER_GPIO2;
+		spec->gpio_dir |= ALC233_STARFIGHTER_GPIO2;
+		spec->gpio_data &= ~ALC233_STARFIGHTER_GPIO2;
+		break;
+	case HDA_FIXUP_ACT_PROBE:
+		spec->gen.pcm_playback_hook = alc233_starfighter_pcm_hook;
+		break;
+	}
 }
 
 static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec,
-- 
cgit v1.2.3


From 0bdf27abaf8940592207be939142451436afe39f Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 16 Mar 2026 10:28:43 +0800
Subject: ALSA: hda/realtek: add quirk for ASUS Strix G16 G615JMR

The machine is equipped with ALC294 and requires the
ALC287_FIXUP_TXNW2781_I2C_ASUS quirk for the amplifier to work properly.
Since the machine's PCI SSID is also 1043:1204, HDA_CODEC_QUIRK is
used to retain the previous quirk.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221173
Cc: <stable@vger.kernel.org>
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260316022843.2809968-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 190c1dd11bee..327f4dc1b09f 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7204,6 +7204,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1194, "ASUS UM3406KA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	HDA_CODEC_QUIRK(0x1043, 0x1204, "ASUS Strix G16 G615JMR", ALC287_FIXUP_TXNW2781_I2C_ASUS),
 	SND_PCI_QUIRK(0x1043, 0x1204, "ASUS Strix G615JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1214, "ASUS Strix G615LH_LM_LP", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
-- 
cgit v1.2.3


From 8634e05b08ead636e926022f4a98416e13440df9 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 12 Mar 2026 16:18:13 +0100
Subject: spi: fix use-after-free on controller registration failure

Make sure to deregister from driver core also in the unlikely event that
per-cpu statistics allocation fails during controller registration to
avoid use-after-free (of driver resources) and unclocked register
accesses.

Fixes: 6598b91b5ac3 ("spi: spi.c: Convert statistics to per-cpu u64_stats_t")
Cc: stable@vger.kernel.org	# 6.0
Cc: David Jander <david@protonic.nl>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260312151817.32100-2-johan@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 61f7bde8c7fb..9b2e307dc30a 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3480,10 +3480,8 @@ int spi_register_controller(struct spi_controller *ctlr)
 		dev_info(dev, "controller is unqueued, this is deprecated\n");
 	} else if (ctlr->transfer_one || ctlr->transfer_one_message) {
 		status = spi_controller_initialize_queue(ctlr);
-		if (status) {
-			device_del(&ctlr->dev);
-			goto free_bus_id;
-		}
+		if (status)
+			goto del_ctrl;
 	}
 	/* Add statistics */
 	ctlr->pcpu_statistics = spi_alloc_pcpu_stats(dev);
@@ -3506,6 +3504,8 @@ int spi_register_controller(struct spi_controller *ctlr)
 
 destroy_queue:
 	spi_destroy_queue(ctlr);
+del_ctrl:
+	device_del(&ctlr->dev);
 free_bus_id:
 	mutex_lock(&board_lock);
 	idr_remove(&spi_controller_idr, ctlr->bus_num);
-- 
cgit v1.2.3


From dee0774bbb2abb172e9069ce5ffef579b12b3ae9 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 12 Mar 2026 16:18:14 +0100
Subject: spi: fix statistics allocation

The controller per-cpu statistics is not allocated until after the
controller has been registered with driver core, which leaves a window
where accessing the sysfs attributes can trigger a NULL-pointer
dereference.

Fix this by moving the statistics allocation to controller allocation
while tying its lifetime to that of the controller (rather than using
implicit devres).

Fixes: 6598b91b5ac3 ("spi: spi.c: Convert statistics to per-cpu u64_stats_t")
Cc: stable@vger.kernel.org	# 6.0
Cc: David Jander <david@protonic.nl>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260312151817.32100-3-johan@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 9b2e307dc30a..53dee314d76a 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3049,6 +3049,8 @@ static void spi_controller_release(struct device *dev)
 	struct spi_controller *ctlr;
 
 	ctlr = container_of(dev, struct spi_controller, dev);
+
+	free_percpu(ctlr->pcpu_statistics);
 	kfree(ctlr);
 }
 
@@ -3192,6 +3194,12 @@ struct spi_controller *__spi_alloc_controller(struct device *dev,
 	if (!ctlr)
 		return NULL;
 
+	ctlr->pcpu_statistics = spi_alloc_pcpu_stats(NULL);
+	if (!ctlr->pcpu_statistics) {
+		kfree(ctlr);
+		return NULL;
+	}
+
 	device_initialize(&ctlr->dev);
 	INIT_LIST_HEAD(&ctlr->queue);
 	spin_lock_init(&ctlr->queue_lock);
@@ -3483,13 +3491,6 @@ int spi_register_controller(struct spi_controller *ctlr)
 		if (status)
 			goto del_ctrl;
 	}
-	/* Add statistics */
-	ctlr->pcpu_statistics = spi_alloc_pcpu_stats(dev);
-	if (!ctlr->pcpu_statistics) {
-		dev_err(dev, "Error allocating per-cpu statistics\n");
-		status = -ENOMEM;
-		goto destroy_queue;
-	}
 
 	mutex_lock(&board_lock);
 	list_add_tail(&ctlr->list, &spi_controller_list);
@@ -3502,8 +3503,6 @@ int spi_register_controller(struct spi_controller *ctlr)
 	acpi_register_spi_devices(ctlr);
 	return status;
 
-destroy_queue:
-	spi_destroy_queue(ctlr);
 del_ctrl:
 	device_del(&ctlr->dev);
 free_bus_id:
-- 
cgit v1.2.3


From f4c31b07b136839e0fb3026f8a5b6543e3b14d2f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 13 Mar 2026 13:25:41 +0100
Subject: sched: idle: Consolidate the handling of two special cases

There are two special cases in the idle loop that are handled
inconsistently even though they are analogous.

The first one is when a cpuidle driver is absent and the default CPU
idle time power management implemented by the architecture code is used.
In that case, the scheduler tick is stopped every time before invoking
default_idle_call().

The second one is when a cpuidle driver is present, but there is only
one idle state in its table.  In that case, the scheduler tick is never
stopped at all.

Since each of these approaches has its drawbacks, reconcile them with
the help of one simple heuristic.  Namely, stop the tick if the CPU has
been woken up by it in the previous iteration of the idle loop, or let
it tick otherwise.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Qais Yousef <qyousef@layalina.io>
Reviewed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Fixes: ed98c3491998 ("sched: idle: Do not stop the tick before cpuidle_idle_call()")
[ rjw: Added Fixes tag, changelog edits ]
Link: https://patch.msgid.link/4741364.LvFx2qVVIh@rafael.j.wysocki
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/sched/idle.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index b95449165122..a83be0c834dd 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -161,6 +161,14 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	return cpuidle_enter(drv, dev, next_state);
 }
 
+static void idle_call_stop_or_retain_tick(bool stop_tick)
+{
+	if (stop_tick || tick_nohz_tick_stopped())
+		tick_nohz_idle_stop_tick();
+	else
+		tick_nohz_idle_retain_tick();
+}
+
 /**
  * cpuidle_idle_call - the main idle function
  *
@@ -170,7 +178,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  * set, and it returns with polling set.  If it ever stops polling, it
  * must clear the polling bit.
  */
-static void cpuidle_idle_call(void)
+static void cpuidle_idle_call(bool stop_tick)
 {
 	struct cpuidle_device *dev = cpuidle_get_device();
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
@@ -186,7 +194,7 @@ static void cpuidle_idle_call(void)
 	}
 
 	if (cpuidle_not_available(drv, dev)) {
-		tick_nohz_idle_stop_tick();
+		idle_call_stop_or_retain_tick(stop_tick);
 
 		default_idle_call();
 		goto exit_idle;
@@ -222,17 +230,19 @@ static void cpuidle_idle_call(void)
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
 	} else if (drv->state_count > 1) {
-		bool stop_tick = true;
+		/*
+		 * stop_tick is expected to be true by default by cpuidle
+		 * governors, which allows them to select idle states with
+		 * target residency above the tick period length.
+		 */
+		stop_tick = true;
 
 		/*
 		 * Ask the cpuidle framework to choose a convenient idle state.
 		 */
 		next_state = cpuidle_select(drv, dev, &stop_tick);
 
-		if (stop_tick || tick_nohz_tick_stopped())
-			tick_nohz_idle_stop_tick();
-		else
-			tick_nohz_idle_retain_tick();
+		idle_call_stop_or_retain_tick(stop_tick);
 
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
@@ -240,7 +250,7 @@ static void cpuidle_idle_call(void)
 		 */
 		cpuidle_reflect(dev, entered_state);
 	} else {
-		tick_nohz_idle_retain_tick();
+		idle_call_stop_or_retain_tick(stop_tick);
 
 		/*
 		 * If there is only a single idle state (or none), there is
@@ -268,6 +278,7 @@ exit_idle:
 static void do_idle(void)
 {
 	int cpu = smp_processor_id();
+	bool got_tick = false;
 
 	/*
 	 * Check if we need to update blocked load
@@ -338,8 +349,9 @@ static void do_idle(void)
 			tick_nohz_idle_restart_tick();
 			cpu_idle_poll();
 		} else {
-			cpuidle_idle_call();
+			cpuidle_idle_call(got_tick);
 		}
+		got_tick = tick_nohz_idle_got_tick();
 		arch_cpu_idle_exit();
 	}
 
-- 
cgit v1.2.3


From 29ab768277617452d88c0607c9299cdc63b6e9ff Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 12 Mar 2026 11:27:20 -0700
Subject: PM: runtime: Fix a race condition related to device removal

The following code in pm_runtime_work() may dereference the dev->parent
pointer after the parent device has been freed:

	/* Maybe the parent is now able to suspend. */
	if (parent && !parent->power.ignore_children) {
		spin_unlock(&dev->power.lock);

		spin_lock(&parent->power.lock);
		rpm_idle(parent, RPM_ASYNC);
		spin_unlock(&parent->power.lock);

		spin_lock(&dev->power.lock);
	}

Fix this by inserting a flush_work() call in pm_runtime_remove().

Without this patch blktest block/001 triggers the following complaint
sporadically:

BUG: KASAN: slab-use-after-free in lock_acquire+0x70/0x160
Read of size 1 at addr ffff88812bef7198 by task kworker/u553:1/3081
Workqueue: pm pm_runtime_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x61/0x80
 print_address_description.constprop.0+0x8b/0x310
 print_report+0xfd/0x1d7
 kasan_report+0xd8/0x1d0
 __kasan_check_byte+0x42/0x60
 lock_acquire.part.0+0x38/0x230
 lock_acquire+0x70/0x160
 _raw_spin_lock+0x36/0x50
 rpm_suspend+0xc6a/0xfe0
 rpm_idle+0x578/0x770
 pm_runtime_work+0xee/0x120
 process_one_work+0xde3/0x1410
 worker_thread+0x5eb/0xfe0
 kthread+0x37b/0x480
 ret_from_fork+0x6cb/0x920
 ret_from_fork_asm+0x11/0x20
 </TASK>

Allocated by task 4314:
 kasan_save_stack+0x2a/0x50
 kasan_save_track+0x18/0x40
 kasan_save_alloc_info+0x3d/0x50
 __kasan_kmalloc+0xa0/0xb0
 __kmalloc_noprof+0x311/0x990
 scsi_alloc_target+0x122/0xb60 [scsi_mod]
 __scsi_scan_target+0x101/0x460 [scsi_mod]
 scsi_scan_channel+0x179/0x1c0 [scsi_mod]
 scsi_scan_host_selected+0x259/0x2d0 [scsi_mod]
 store_scan+0x2d2/0x390 [scsi_mod]
 dev_attr_store+0x43/0x80
 sysfs_kf_write+0xde/0x140
 kernfs_fop_write_iter+0x3ef/0x670
 vfs_write+0x506/0x1470
 ksys_write+0xfd/0x230
 __x64_sys_write+0x76/0xc0
 x64_sys_call+0x213/0x1810
 do_syscall_64+0xee/0xfc0
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Freed by task 4314:
 kasan_save_stack+0x2a/0x50
 kasan_save_track+0x18/0x40
 kasan_save_free_info+0x3f/0x50
 __kasan_slab_free+0x67/0x80
 kfree+0x225/0x6c0
 scsi_target_dev_release+0x3d/0x60 [scsi_mod]
 device_release+0xa3/0x220
 kobject_cleanup+0x105/0x3a0
 kobject_put+0x72/0xd0
 put_device+0x17/0x20
 scsi_device_dev_release+0xacf/0x12c0 [scsi_mod]
 device_release+0xa3/0x220
 kobject_cleanup+0x105/0x3a0
 kobject_put+0x72/0xd0
 put_device+0x17/0x20
 scsi_device_put+0x7f/0xc0 [scsi_mod]
 sdev_store_delete+0xa5/0x120 [scsi_mod]
 dev_attr_store+0x43/0x80
 sysfs_kf_write+0xde/0x140
 kernfs_fop_write_iter+0x3ef/0x670
 vfs_write+0x506/0x1470
 ksys_write+0xfd/0x230
 __x64_sys_write+0x76/0xc0
 x64_sys_call+0x213/0x1810

Reported-by: Ming Lei <ming.lei@redhat.com>
Closes: https://lore.kernel.org/all/ZxdNvLNI8QaOfD2d@fedora/
Reported-by: syzbot+6c905ab800f20cf4086c@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68c13942.050a0220.2ff435.000b.GAE@google.com/
Fixes: 5e928f77a09a ("PM: Introduce core framework for run-time PM of I/O devices (rev. 17)")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://patch.msgid.link/20260312182720.2776083-1-bvanassche@acm.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/runtime.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 0ee8ea971aa4..335288e8b5b3 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1895,6 +1895,7 @@ void pm_runtime_reinit(struct device *dev)
 void pm_runtime_remove(struct device *dev)
 {
 	__pm_runtime_disable(dev, false);
+	flush_work(&dev->power.work);
 	pm_runtime_reinit(dev);
 }
 
-- 
cgit v1.2.3


From 2f2600decb3004938762a3f2d0eba3ea9e01045b Mon Sep 17 00:00:00 2001
From: Joe Lawrence <joe.lawrence@redhat.com>
Date: Tue, 10 Mar 2026 16:37:40 -0400
Subject: objtool/klp: fix data alignment in __clone_symbol()

Commit 356e4b2f5b80 ("objtool: Fix data alignment in elf_add_data()")
corrected the alignment of data within a section (honoring the section's
sh_addralign).  Apply the same alignment when klp-diff mode clones a
symbol, adjusting the new symbol's offset for the output section's
sh_addralign.

Fixes: dd590d4d57eb ("objtool/klp: Introduce klp diff subcommand for diffing object files")
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Link: https://patch.msgid.link/20260310203751.1479229-2-joe.lawrence@redhat.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/klp-diff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/objtool/klp-diff.c b/tools/objtool/klp-diff.c
index a3198a63c2f0..c2c4e4968bc2 100644
--- a/tools/objtool/klp-diff.c
+++ b/tools/objtool/klp-diff.c
@@ -14,6 +14,7 @@
 #include <objtool/util.h>
 #include <arch/special.h>
 
+#include <linux/align.h>
 #include <linux/objtool_types.h>
 #include <linux/livepatch_external.h>
 #include <linux/stringify.h>
@@ -560,7 +561,7 @@ static struct symbol *__clone_symbol(struct elf *elf, struct symbol *patched_sym
 		}
 
 		if (!is_sec_sym(patched_sym))
-			offset = sec_size(out_sec);
+			offset = ALIGN(sec_size(out_sec), out_sec->sh.sh_addralign);
 
 		if (patched_sym->len || is_sec_sym(patched_sym)) {
 			void *data = NULL;
-- 
cgit v1.2.3


From 28e367a969b0c54c87ca655ec180715fe469fd14 Mon Sep 17 00:00:00 2001
From: Joe Lawrence <joe.lawrence@redhat.com>
Date: Tue, 10 Mar 2026 16:37:41 -0400
Subject: objtool/klp: fix mkstemp() failure with long paths

The elf_create_file() function fails with EINVAL when the build directory
path is long enough to truncate the "XXXXXX" suffix in the 256-byte
tmp_name buffer.

Simplify the code to remove the unnecessary dirname()/basename() split
and concatenation.  Instead, allocate the exact number of bytes needed for
the path.

Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Link: https://patch.msgid.link/20260310203751.1479229-3-joe.lawrence@redhat.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/elf.c | 23 +++--------------------
 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 3da90686350d..2ffe3ebfbe37 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -16,7 +16,6 @@
 #include <string.h>
 #include <unistd.h>
 #include <errno.h>
-#include <libgen.h>
 #include <ctype.h>
 #include <linux/align.h>
 #include <linux/kernel.h>
@@ -1189,7 +1188,7 @@ err:
 struct elf *elf_create_file(GElf_Ehdr *ehdr, const char *name)
 {
 	struct section *null, *symtab, *strtab, *shstrtab;
-	char *dir, *base, *tmp_name;
+	char *tmp_name;
 	struct symbol *sym;
 	struct elf *elf;
 
@@ -1203,29 +1202,13 @@ struct elf *elf_create_file(GElf_Ehdr *ehdr, const char *name)
 
 	INIT_LIST_HEAD(&elf->sections);
 
-	dir = strdup(name);
-	if (!dir) {
-		ERROR_GLIBC("strdup");
-		return NULL;
-	}
-
-	dir = dirname(dir);
-
-	base = strdup(name);
-	if (!base) {
-		ERROR_GLIBC("strdup");
-		return NULL;
-	}
-
-	base = basename(base);
-
-	tmp_name = malloc(256);
+	tmp_name = malloc(strlen(name) + 8);
 	if (!tmp_name) {
 		ERROR_GLIBC("malloc");
 		return NULL;
 	}
 
-	snprintf(tmp_name, 256, "%s/%s.XXXXXX", dir, base);
+	sprintf(tmp_name, "%s.XXXXXX", name);
 
 	elf->fd = mkstemp(tmp_name);
 	if (elf->fd == -1) {
-- 
cgit v1.2.3


From 6f93f7b06810d04acc6b106a7d5ecd6000f80545 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 10 Mar 2026 16:37:48 -0400
Subject: livepatch/klp-build: Fix inconsistent kernel version

If .config hasn't been synced with auto.conf, any recent changes to
CONFIG_LOCALVERSION* may not get reflected in the kernel version name.

Use "make syncconfig" to force them to sync, and "make -s kernelrelease"
to get the version instead of having to construct it manually.

Fixes: 24ebfcd65a87 ("livepatch/klp-build: Introduce klp-build script for generating livepatch modules")
Closes: https://lore.kernel.org/20260217160645.3434685-10-joe.lawrence@redhat.com
Reported-by: Joe Lawrence <joe.lawrence@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Acked-by: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/20260310203751.1479229-10-joe.lawrence@redhat.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 scripts/livepatch/klp-build | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/scripts/livepatch/klp-build b/scripts/livepatch/klp-build
index 809e198a561d..7b82c7503c2b 100755
--- a/scripts/livepatch/klp-build
+++ b/scripts/livepatch/klp-build
@@ -285,15 +285,14 @@ set_module_name() {
 # application from appending it with '+' due to a dirty git working tree.
 set_kernelversion() {
 	local file="$SRC/scripts/setlocalversion"
-	local localversion
+	local kernelrelease
 
 	stash_file "$file"
 
-	localversion="$(cd "$SRC" && make --no-print-directory kernelversion)"
-	localversion="$(cd "$SRC" && KERNELVERSION="$localversion" ./scripts/setlocalversion)"
-	[[ -z "$localversion" ]] && die "setlocalversion failed"
+	kernelrelease="$(cd "$SRC" && make syncconfig &>/dev/null && make -s kernelrelease)"
+	[[ -z "$kernelrelease" ]] && die "failed to get kernel version"
 
-	sed -i "2i echo $localversion; exit 0" scripts/setlocalversion
+	sed -i "2i echo $kernelrelease; exit 0" scripts/setlocalversion
 }
 
 get_patch_files() {
-- 
cgit v1.2.3


From 5133b61aaf437e5f25b1b396b14242a6bb0508e2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 24 Feb 2026 11:33:35 -0500
Subject: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache

The NFSv4.0 replay cache uses a fixed 112-byte inline buffer
(rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses.
This size was calculated based on OPEN responses and does not account
for LOCK denied responses, which include the conflicting lock owner as
a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT).

When a LOCK operation is denied due to a conflict with an existing lock
that has a large owner, nfsd4_encode_operation() copies the full encoded
response into the undersized replay buffer via read_bytes_from_xdr_buf()
with no bounds check. This results in a slab-out-of-bounds write of up
to 944 bytes past the end of the buffer, corrupting adjacent heap memory.

This can be triggered remotely by an unauthenticated attacker with two
cooperating NFSv4.0 clients: one sets a lock with a large owner string,
then the other requests a conflicting lock to provoke the denial.

We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full
opaque, but that would increase the size of every stateowner, when most
lockowners are not that large.

Instead, fix this by checking the encoded response length against
NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the
response is too large, set rp_buflen to 0 to skip caching the replay
payload. The status is still cached, and the client already received the
correct response on the original request.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@kernel.org
Reported-by: Nicholas Carlini <npc@anthropic.com>
Tested-by: Nicholas Carlini <npc@anthropic.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4xdr.c |  9 +++++++--
 fs/nfsd/state.h   | 17 ++++++++++++-----
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5172dbd0cb05..fa16b34fae50 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -6281,9 +6281,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 		int len = xdr->buf->len - (op_status_offset + XDR_UNIT);
 
 		so->so_replay.rp_status = op->status;
-		so->so_replay.rp_buflen = len;
-		read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT,
+		if (len <= NFSD4_REPLAY_ISIZE) {
+			so->so_replay.rp_buflen = len;
+			read_bytes_from_xdr_buf(xdr->buf,
+						op_status_offset + XDR_UNIT,
 						so->so_replay.rp_buf, len);
+		} else {
+			so->so_replay.rp_buflen = 0;
+		}
 	}
 status:
 	op->status = nfsd4_map_status(op->status,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 6fcbf1e427d4..c0ca115c3b74 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -541,11 +541,18 @@ struct nfs4_client_reclaim {
 	struct xdr_netobj	cr_princhash;
 };
 
-/* A reasonable value for REPLAY_ISIZE was estimated as follows:  
- * The OPEN response, typically the largest, requires 
- *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +  8(verifier) + 
- *   4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) + 
- *   20(deleg. space limit) + ~32(deleg. ace) = 112 bytes 
+/*
+ * REPLAY_ISIZE is sized for an OPEN response with delegation:
+ *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +
+ *   8(verifier) + 4(deleg. type) + 8(deleg. stateid) +
+ *   4(deleg. recall flag) + 20(deleg. space limit) +
+ *   ~32(deleg. ace) = 112 bytes
+ *
+ * Some responses can exceed this. A LOCK denial includes the conflicting
+ * lock owner, which can be up to 1024 bytes (NFS4_OPAQUE_LIMIT). Responses
+ * larger than REPLAY_ISIZE are not cached in rp_ibuf; only rp_status is
+ * saved. Enlarging this constant increases the size of every
+ * nfs4_stateowner.
  */
 
 #define NFSD4_REPLAY_ISIZE       112 
-- 
cgit v1.2.3


From cf3287fb2c1ff74cb16e4348c6914acf140ebe30 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@oss.qualcomm.com>
Date: Mon, 23 Feb 2026 20:15:59 +0530
Subject: PCI/pwrctrl: Ensure that remote endpoint node parent has supply
 requirement

If OF graph is used in the PCI device node, the pwrctrl core creates a
pwrctrl device even if the remote endpoint doesn't have power supply
requirements. Since the device doesn't have any power supply requirements,
there was no pwrctrl driver to probe, leading to PCI controller driver
probe deferral as it waits for all pwrctrl drivers to probe before starting
bus scan.

This issue happens with Qcom ath12k devices with WSI interface attached to
the Qcom IPQ platforms.

Fix this issue by checking for the existence of at least one power supply
property in the remote endpoint parent node. To consolidate all the checks,
create a new helper pci_pwrctrl_is_required() and move all the checks
there.

Fixes: 9db826206f9b ("PCI/pwrctrl: Create pwrctrl device if graph port is found")
Reported-by: Raj Kumar Bhagat <raj.bhagat@oss.qualcomm.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@oss.qualcomm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Raj Kumar Bhagat <raj.bhagat@oss.qualcomm.com>
Reviewed-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260223-pwrctrl-fixes-7-0-v2-1-97566dfb1809@oss.qualcomm.com
---
 drivers/pci/pwrctrl/core.c | 47 +++++++++++++++++++++++++++++++++-------------
 1 file changed, 34 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c
index 6f7dea6746e0..8325858cc379 100644
--- a/drivers/pci/pwrctrl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -268,6 +268,39 @@ err_power_off:
 }
 EXPORT_SYMBOL_GPL(pci_pwrctrl_power_on_devices);
 
+/*
+ * Check whether the pwrctrl device really needs to be created or not. The
+ * pwrctrl device will only be created if the node satisfies below requirements:
+ *
+ * 1. Presence of compatible property to match against the pwrctrl driver (AND)
+ * 2. At least one of the power supplies defined in the devicetree node of the
+ *    device (OR) in the remote endpoint parent node to indicate pwrctrl
+ *    requirement.
+ */
+static bool pci_pwrctrl_is_required(struct device_node *np)
+{
+	struct device_node *endpoint;
+
+	if (!of_property_present(np, "compatible"))
+		return false;
+
+	if (of_pci_supply_present(np))
+		return true;
+
+	if (of_graph_is_present(np)) {
+		for_each_endpoint_of_node(np, endpoint) {
+			struct device_node *remote __free(device_node) =
+				of_graph_get_remote_port_parent(endpoint);
+			if (remote) {
+				if (of_pci_supply_present(remote))
+					return true;
+			}
+		}
+	}
+
+	return false;
+}
+
 static int pci_pwrctrl_create_device(struct device_node *np,
 				     struct device *parent)
 {
@@ -287,19 +320,7 @@ static int pci_pwrctrl_create_device(struct device_node *np,
 		return 0;
 	}
 
-	/*
-	 * Sanity check to make sure that the node has the compatible property
-	 * to allow driver binding.
-	 */
-	if (!of_property_present(np, "compatible"))
-		return 0;
-
-	/*
-	 * Check whether the pwrctrl device really needs to be created or not.
-	 * This is decided based on at least one of the power supplies defined
-	 * in the devicetree node of the device or the graph property.
-	 */
-	if (!of_pci_supply_present(np) && !of_graph_is_present(np)) {
+	if (!pci_pwrctrl_is_required(np)) {
 		dev_dbg(parent, "Skipping OF node: %s\n", np->name);
 		return 0;
 	}
-- 
cgit v1.2.3


From ee226656cd64c1d781e6f91a38a5131106e9e094 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@oss.qualcomm.com>
Date: Mon, 23 Feb 2026 20:16:00 +0530
Subject: PCI/pwrctrl: Create pwrctrl devices only for PCI device nodes

A PCI host bridge node can have non-PCI child nodes (OPP tables, USB
hub, etc.) as well as PCI device child nodes.

Ensure that pwrctrl devices are only created for PCI device nodes by
checking for the 'pci' prefix in the compatible property.

Fixes: 4c4132489201 ("PCI/pwrctrl: Add APIs to create, destroy pwrctrl devices")
Reported-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Closes: https://lore.kernel.org/all/20260212-rb3gen2-upd-gl3590-v1-1-18fb04bb32b0@oss.qualcomm.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@oss.qualcomm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20260223-pwrctrl-fixes-7-0-v2-2-97566dfb1809@oss.qualcomm.com
---
 drivers/pci/pwrctrl/core.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c
index 8325858cc379..7754baed67f2 100644
--- a/drivers/pci/pwrctrl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -272,7 +272,8 @@ EXPORT_SYMBOL_GPL(pci_pwrctrl_power_on_devices);
  * Check whether the pwrctrl device really needs to be created or not. The
  * pwrctrl device will only be created if the node satisfies below requirements:
  *
- * 1. Presence of compatible property to match against the pwrctrl driver (AND)
+ * 1. Presence of compatible property with "pci" prefix to match against the
+ *    pwrctrl driver (AND)
  * 2. At least one of the power supplies defined in the devicetree node of the
  *    device (OR) in the remote endpoint parent node to indicate pwrctrl
  *    requirement.
@@ -280,8 +281,14 @@ EXPORT_SYMBOL_GPL(pci_pwrctrl_power_on_devices);
 static bool pci_pwrctrl_is_required(struct device_node *np)
 {
 	struct device_node *endpoint;
+	const char *compat;
+	int ret;
+
+	ret = of_property_read_string(np, "compatible", &compat);
+	if (ret < 0)
+		return false;
 
-	if (!of_property_present(np, "compatible"))
+	if (!strstarts(compat, "pci"))
 		return false;
 
 	if (of_pci_supply_present(np))
-- 
cgit v1.2.3


From 4e5019216402ad0b4a84cff457b662d26803f103 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Mon, 9 Mar 2026 09:03:05 -0700
Subject: objtool: Fix Clang jump table detection

With Clang, there can be a conditional forward jump between the load of
the jump table address and the indirect branch.

Fixes the following warning:

  vmlinux.o: warning: objtool: ___bpf_prog_run+0x1c5: sibling call from callable instruction with modified stack frame

Reported-by: Arnd Bergmann <arnd@arndb.de>
Closes: https://lore.kernel.org/a426d669-58bb-4be1-9eaa-6f3d83109e2d@app.fastmail.com
Link: https://patch.msgid.link/7d8600caed08901b6679767488acd639f6df9688.1773071992.git.jpoimboe@kernel.org
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/check.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 91b3ff4803cf..b6765e876507 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2184,12 +2184,11 @@ static void mark_func_jump_tables(struct objtool_file *file,
 			last = insn;
 
 		/*
-		 * Store back-pointers for unconditional forward jumps such
+		 * Store back-pointers for forward jumps such
 		 * that find_jump_table() can back-track using those and
 		 * avoid some potentially confusing code.
 		 */
-		if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest &&
-		    insn->offset > last->offset &&
+		if (insn->jump_dest &&
 		    insn->jump_dest->offset > insn->offset &&
 		    !insn->jump_dest->first_jump_src) {
 
-- 
cgit v1.2.3


From 75cea0776de502f2a1be5ca02d37c586dc81887e Mon Sep 17 00:00:00 2001
From: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Date: Mon, 16 Mar 2026 20:19:49 +0000
Subject: cxl/hdm: Avoid incorrect DVSEC fallback when HDM decoders are enabled

Check the global CXL_HDM_DECODER_ENABLE bit instead of looping over
per-decoder COMMITTED bits to determine whether to fall back to DVSEC
range emulation. When the HDM decoder capability is globally enabled,
ignore DVSEC range registers regardless of individual decoder commit
state.

should_emulate_decoders() currently loops over per-decoder COMMITTED
bits, which leads to an incorrect DVSEC fallback when those bits are
zero. One way to trigger this is to destroy a region and bounce the
memdev:

  cxl disable-region region0
  cxl destroy-region region0
  cxl disable-memdev mem0
  cxl enable-memdev mem0

Region teardown zeroes the HDM decoder registers including the committed
bits. The subsequent memdev re-probe finds uncommitted decoders and falls
back to DVSEC emulation, even though HDM remains globally enabled.

Observed failures:

  should_emulate_decoders: cxl_port endpoint6: decoder6.0: committed: 0 base: 0x0_00000000 size: 0x0_00000000
  devm_cxl_setup_hdm: cxl_port endpoint6: Fallback map 1 range register
  ..
  devm_cxl_add_region: cxl_acpi ACPI0017:00: decoder0.0: created region0
  __construct_region: cxl_pci 0000:e1:00.0: mem1:decoder6.0:
  __construct_region region0 res: [mem 0x850000000-0x284fffffff flags 0x200] iw: 1 ig: 4096
  cxl region0: pci0000:e0:port1 cxl_port_setup_targets expected iw: 1 ig: 4096 ..
  cxl region0: pci0000:e0:port1 cxl_port_setup_targets got iw: 1 ig: 256 state: disabled ..
  cxl_port endpoint6: failed to attach decoder6.0 to region0: -6
  ..
  devm_cxl_add_region: cxl_acpi ACPI0017:00: decoder0.0: created region4
  alloc_hpa: cxl region4: HPA allocation error (-34) ..

Fixes: 52cc48ad2a76 ("cxl/hdm: Limit emulation to the number of range registers")
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260316201950.224567-1-Smita.KoralahalliChannabasappa@amd.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/hdm.c | 25 +++++++++----------------
 1 file changed, 9 insertions(+), 16 deletions(-)

diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index c222e98ae736..cb5d5a047a9d 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -94,7 +94,6 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info)
 	struct cxl_hdm *cxlhdm;
 	void __iomem *hdm;
 	u32 ctrl;
-	int i;
 
 	if (!info)
 		return false;
@@ -113,22 +112,16 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info)
 		return false;
 
 	/*
-	 * If any decoders are committed already, there should not be any
-	 * emulated DVSEC decoders.
+	 * If HDM decoders are globally enabled, do not fall back to DVSEC
+	 * range emulation. Zeroed decoder registers after region teardown
+	 * do not imply absence of HDM capability.
+	 *
+	 * Falling back to DVSEC here would treat the decoder as AUTO and
+	 * may incorrectly latch default interleave settings.
 	 */
-	for (i = 0; i < cxlhdm->decoder_count; i++) {
-		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
-		dev_dbg(&info->port->dev,
-			"decoder%d.%d: committed: %ld base: %#x_%.8x size: %#x_%.8x\n",
-			info->port->id, i,
-			FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl),
-			readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i)),
-			readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i)),
-			readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i)),
-			readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i)));
-		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
-			return false;
-	}
+	ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
+	if (ctrl & CXL_HDM_DECODER_ENABLE)
+		return false;
 
 	return true;
 }
-- 
cgit v1.2.3


From 50bfd2a22b75a904d5900d64530ae1b69a69907c Mon Sep 17 00:00:00 2001
From: Joseph Salisbury <joseph.salisbury@oracle.com>
Date: Mon, 16 Mar 2026 21:13:49 -0400
Subject: cifs: smb1: fix comment typo

The file contains a spelling error in a source comment (resposne).

Typos in comments reduce readability and make text searches less reliable
for developers and maintainers.

Replace 'resposne' with 'response' in the affected comment. This is a
comment-only cleanup and does not change behavior.

[v2: Removed Fixes: and Cc: to stable tags.]

Signed-off-by: Joseph Salisbury <joseph.salisbury@oracle.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb1transport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb1transport.c b/fs/smb/client/smb1transport.c
index 38d6d5538b96..53abb29fe71b 100644
--- a/fs/smb/client/smb1transport.c
+++ b/fs/smb/client/smb1transport.c
@@ -460,7 +460,7 @@ check_smb_hdr(struct smb_hdr *smb)
 		return 0;
 
 	/*
-	 * Windows NT server returns error resposne (e.g. STATUS_DELETE_PENDING
+	 * Windows NT server returns error response (e.g. STATUS_DELETE_PENDING
 	 * or STATUS_OBJECT_NAME_NOT_FOUND or ERRDOS/ERRbadfile or any other)
 	 * for some TRANS2 requests without the RESPONSE flag set in header.
 	 */
-- 
cgit v1.2.3


From eade54040384f54b7fb330e4b0975c5734850b3c Mon Sep 17 00:00:00 2001
From: Sheng Yong <shengyong1@xiaomi.com>
Date: Fri, 27 Feb 2026 10:30:08 +0800
Subject: erofs: set fileio bio failed in short read case

For file-backed mount, IO requests are handled by vfs_iocb_iter_read().
However, it can be interrupted by SIGKILL, returning the number of
bytes actually copied. Unused folios in bio are unexpectedly marked
as uptodate.

  vfs_read
    filemap_read
      filemap_get_pages
        filemap_readahead
          erofs_fileio_readahead
            erofs_fileio_rq_submit
              vfs_iocb_iter_read
                filemap_read
                  filemap_get_pages  <= detect signal
              erofs_fileio_ki_complete  <= set all folios uptodate

This patch addresses this by setting short read bio with an error
directly.

Fixes: bc804a8d7e86 ("erofs: handle end of filesystem properly for file-backed mounts")
Reported-by: chenguanyou <chenguanyou@xiaomi.com>
Signed-off-by: Yunlei He <heyunlei@xiaomi.com>
Signed-off-by: Sheng Yong <shengyong1@xiaomi.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/fileio.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index abe873f01297..98cdaa1cd1a7 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -25,10 +25,8 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
 			container_of(iocb, struct erofs_fileio_rq, iocb);
 	struct folio_iter fi;
 
-	if (ret >= 0 && ret != rq->bio.bi_iter.bi_size) {
-		bio_advance(&rq->bio, ret);
-		zero_fill_bio(&rq->bio);
-	}
+	if (ret >= 0 && ret != rq->bio.bi_iter.bi_size)
+		ret = -EIO;
 	if (!rq->bio.bi_end_io) {
 		bio_for_each_folio_all(fi, &rq->bio) {
 			DBG_BUGON(folio_test_uptodate(fi.folio));
-- 
cgit v1.2.3


From b7405dcf7385445e10821777143f18c3ce20fa04 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 15 Mar 2026 10:41:52 +0000
Subject: bonding: prevent potential infinite loop in bond_header_parse()

bond_header_parse() can loop if a stack of two bonding devices is setup,
because skb->dev always points to the hierarchy top.

Add new "const struct net_device *dev" parameter to
(struct header_ops)->parse() method to make sure the recursion
is bounded, and that the final leaf parse method is called.

Fixes: 950803f72547 ("bonding: fix type confusion in bond_setup_by_slave()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Tested-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Cc: Jay Vosburgh <jv@jvosburgh.net>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Link: https://patch.msgid.link/20260315104152.1436867-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/firewire/net.c          | 5 +++--
 drivers/net/bonding/bond_main.c | 8 +++++---
 include/linux/etherdevice.h     | 3 ++-
 include/linux/if_ether.h        | 3 ++-
 include/linux/netdevice.h       | 6 ++++--
 net/ethernet/eth.c              | 9 +++------
 net/ipv4/ip_gre.c               | 3 ++-
 net/mac802154/iface.c           | 4 +++-
 net/phonet/af_phonet.c          | 5 ++++-
 9 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index f1a2bee39bf1..82b3b6d9ed2d 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -257,9 +257,10 @@ static void fwnet_header_cache_update(struct hh_cache *hh,
 	memcpy((u8 *)hh->hh_data + HH_DATA_OFF(FWNET_HLEN), haddr, net->addr_len);
 }
 
-static int fwnet_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+static int fwnet_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+			      unsigned char *haddr)
 {
-	memcpy(haddr, skb->dev->dev_addr, FWNET_ALEN);
+	memcpy(haddr, dev->dev_addr, FWNET_ALEN);
 
 	return FWNET_ALEN;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 707419270ebf..33f414d03ab9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1530,9 +1530,11 @@ static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev,
 	return ret;
 }
 
-static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+static int bond_header_parse(const struct sk_buff *skb,
+			     const struct net_device *dev,
+			     unsigned char *haddr)
 {
-	struct bonding *bond = netdev_priv(skb->dev);
+	struct bonding *bond = netdev_priv(dev);
 	const struct header_ops *slave_ops;
 	struct slave *slave;
 	int ret = 0;
@@ -1542,7 +1544,7 @@ static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr)
 	if (slave) {
 		slave_ops = READ_ONCE(slave->dev->header_ops);
 		if (slave_ops && slave_ops->parse)
-			ret = slave_ops->parse(skb, haddr);
+			ret = slave_ops->parse(skb, slave->dev, haddr);
 	}
 	rcu_read_unlock();
 	return ret;
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 9a1eacf35d37..df8f88f63a70 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -42,7 +42,8 @@ extern const struct header_ops eth_header_ops;
 
 int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
 	       const void *daddr, const void *saddr, unsigned len);
-int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
+int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+		     unsigned char *haddr);
 int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh,
 		     __be16 type);
 void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev,
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 61b7335aa037..ca9afa824aa4 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -40,7 +40,8 @@ static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb)
 	return (struct ethhdr *)skb_inner_mac_header(skb);
 }
 
-int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr);
+int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+		     unsigned char *haddr);
 
 extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d7aac6f185bc..7ca01eb3f7d2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -311,7 +311,9 @@ struct header_ops {
 	int	(*create) (struct sk_buff *skb, struct net_device *dev,
 			   unsigned short type, const void *daddr,
 			   const void *saddr, unsigned int len);
-	int	(*parse)(const struct sk_buff *skb, unsigned char *haddr);
+	int	(*parse)(const struct sk_buff *skb,
+			 const struct net_device *dev,
+			 unsigned char *haddr);
 	int	(*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type);
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
@@ -3445,7 +3447,7 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 
 	if (!dev->header_ops || !dev->header_ops->parse)
 		return 0;
-	return dev->header_ops->parse(skb, haddr);
+	return dev->header_ops->parse(skb, dev, haddr);
 }
 
 static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb)
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 13a63b48b7ee..d9faadbe9b6c 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -193,14 +193,11 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 }
 EXPORT_SYMBOL(eth_type_trans);
 
-/**
- * eth_header_parse - extract hardware address from packet
- * @skb: packet to extract header from
- * @haddr: destination buffer
- */
-int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+		     unsigned char *haddr)
 {
 	const struct ethhdr *eth = eth_hdr(skb);
+
 	memcpy(haddr, eth->h_source, ETH_ALEN);
 	return ETH_ALEN;
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e13244729ad8..35f0baa99d40 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -919,7 +919,8 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
 	return -(t->hlen + sizeof(*iph));
 }
 
-static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+static int ipgre_header_parse(const struct sk_buff *skb, const struct net_device *dev,
+			      unsigned char *haddr)
 {
 	const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb);
 	memcpy(haddr, &iph->saddr, 4);
diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c
index 9e4631fade90..000be60d9580 100644
--- a/net/mac802154/iface.c
+++ b/net/mac802154/iface.c
@@ -469,7 +469,9 @@ static int mac802154_header_create(struct sk_buff *skb,
 }
 
 static int
-mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+mac802154_header_parse(const struct sk_buff *skb,
+		       const struct net_device *dev,
+		       unsigned char *haddr)
 {
 	struct ieee802154_hdr hdr;
 
diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c
index 238a9638d2b0..d89225d6bfd3 100644
--- a/net/phonet/af_phonet.c
+++ b/net/phonet/af_phonet.c
@@ -129,9 +129,12 @@ static int pn_header_create(struct sk_buff *skb, struct net_device *dev,
 	return 1;
 }
 
-static int pn_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+static int pn_header_parse(const struct sk_buff *skb,
+			   const struct net_device *dev,
+			   unsigned char *haddr)
 {
 	const u8 *media = skb_mac_header(skb);
+
 	*haddr = *media;
 	return 1;
 }
-- 
cgit v1.2.3


From 6d5e4538364b9ceb1ac2941a4deb86650afb3538 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 12 Mar 2026 17:29:07 +0800
Subject: net/smc: fix NULL dereference and UAF in smc_tcp_syn_recv_sock()

Syzkaller reported a panic in smc_tcp_syn_recv_sock() [1].

smc_tcp_syn_recv_sock() is called in the TCP receive path
(softirq) via icsk_af_ops->syn_recv_sock on the clcsock (TCP
listening socket). It reads sk_user_data to get the smc_sock
pointer. However, when the SMC listen socket is being closed
concurrently, smc_close_active() sets clcsock->sk_user_data
to NULL under sk_callback_lock, and then the smc_sock itself
can be freed via sock_put() in smc_release().

This leads to two issues:

1) NULL pointer dereference: sk_user_data is NULL when
   accessed.
2) Use-after-free: sk_user_data is read as non-NULL, but the
   smc_sock is freed before its fields (e.g., queued_smc_hs,
   ori_af_ops) are accessed.

The race window looks like this (the syzkaller crash [1]
triggers via the SYN cookie path: tcp_get_cookie_sock() ->
smc_tcp_syn_recv_sock(), but the normal tcp_check_req() path
has the same race):

  CPU A (softirq)              CPU B (process ctx)

  tcp_v4_rcv()
    TCP_NEW_SYN_RECV:
    sk = req->rsk_listener
    sock_hold(sk)
    /* No lock on listener */
                               smc_close_active():
                                 write_lock_bh(cb_lock)
                                 sk_user_data = NULL
                                 write_unlock_bh(cb_lock)
                                 ...
                                 smc_clcsock_release()
                                 sock_put(smc->sk) x2
                                   -> smc_sock freed!
    tcp_check_req()
      smc_tcp_syn_recv_sock():
        smc = user_data(sk)
          -> NULL or dangling
        smc->queued_smc_hs
          -> crash!

Note that the clcsock and smc_sock are two independent objects
with separate refcounts. TCP stack holds a reference on the
clcsock, which keeps it alive, but this does NOT prevent the
smc_sock from being freed.

Fix this by using RCU and refcount_inc_not_zero() to safely
access smc_sock. Since smc_tcp_syn_recv_sock() is called in
the TCP three-way handshake path, taking read_lock_bh on
sk_callback_lock is too heavy and would not survive a SYN
flood attack. Using rcu_read_lock() is much more lightweight.

- Set SOCK_RCU_FREE on the SMC listen socket so that
  smc_sock freeing is deferred until after the RCU grace
  period. This guarantees the memory is still valid when
  accessed inside rcu_read_lock().
- Use rcu_read_lock() to protect reading sk_user_data.
- Use refcount_inc_not_zero(&smc->sk.sk_refcnt) to pin the
  smc_sock. If the refcount has already reached zero (close
  path completed), it returns false and we bail out safely.

Note: smc_hs_congested() has a similar lockless read of
sk_user_data without rcu_read_lock(), but it only checks for
NULL and accesses the global smc_hs_wq, never dereferencing
any smc_sock field, so it is not affected.

Reproducer was verified with mdelay injection and smc_run,
the issue no longer occurs with this patch applied.

[1] https://syzkaller.appspot.com/bug?extid=827ae2bfb3a3529333e9

Fixes: 8270d9c21041 ("net/smc: Limit backlog connections")
Reported-by: syzbot+827ae2bfb3a3529333e9@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/67eaf9b8.050a0220.3c3d88.004a.GAE@google.com/T/
Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260312092909.48325-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/af_smc.c    | 23 +++++++++++++++++------
 net/smc/smc.h       |  5 +++++
 net/smc/smc_close.c |  2 +-
 3 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d0119afcc6a1..1a565095376a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -131,7 +131,14 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 	struct smc_sock *smc;
 	struct sock *child;
 
-	smc = smc_clcsock_user_data(sk);
+	rcu_read_lock();
+	smc = smc_clcsock_user_data_rcu(sk);
+	if (!smc || !refcount_inc_not_zero(&smc->sk.sk_refcnt)) {
+		rcu_read_unlock();
+		smc = NULL;
+		goto drop;
+	}
+	rcu_read_unlock();
 
 	if (READ_ONCE(sk->sk_ack_backlog) + atomic_read(&smc->queued_smc_hs) >
 				sk->sk_max_ack_backlog)
@@ -153,11 +160,14 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 		if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops)
 			inet_csk(child)->icsk_af_ops = smc->ori_af_ops;
 	}
+	sock_put(&smc->sk);
 	return child;
 
 drop:
 	dst_release(dst);
 	tcp_listendrop(sk);
+	if (smc)
+		sock_put(&smc->sk);
 	return NULL;
 }
 
@@ -254,7 +264,7 @@ static void smc_fback_restore_callbacks(struct smc_sock *smc)
 	struct sock *clcsk = smc->clcsock->sk;
 
 	write_lock_bh(&clcsk->sk_callback_lock);
-	clcsk->sk_user_data = NULL;
+	rcu_assign_sk_user_data(clcsk, NULL);
 
 	smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change);
 	smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready);
@@ -902,7 +912,7 @@ static void smc_fback_replace_callbacks(struct smc_sock *smc)
 	struct sock *clcsk = smc->clcsock->sk;
 
 	write_lock_bh(&clcsk->sk_callback_lock);
-	clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
+	__rcu_assign_sk_user_data_with_flags(clcsk, smc, SK_USER_DATA_NOCOPY);
 
 	smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change,
 			       &smc->clcsk_state_change);
@@ -2665,8 +2675,8 @@ int smc_listen(struct socket *sock, int backlog)
 	 * smc-specific sk_data_ready function
 	 */
 	write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
-	smc->clcsock->sk->sk_user_data =
-		(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
+	__rcu_assign_sk_user_data_with_flags(smc->clcsock->sk, smc,
+					     SK_USER_DATA_NOCOPY);
 	smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready,
 			       smc_clcsock_data_ready, &smc->clcsk_data_ready);
 	write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
@@ -2687,10 +2697,11 @@ int smc_listen(struct socket *sock, int backlog)
 		write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
 		smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready,
 				       &smc->clcsk_data_ready);
-		smc->clcsock->sk->sk_user_data = NULL;
+		rcu_assign_sk_user_data(smc->clcsock->sk, NULL);
 		write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
 		goto out;
 	}
+	sock_set_flag(sk, SOCK_RCU_FREE);
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	sk->sk_state = SMC_LISTEN;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 9e6af72784ba..52145df83f6e 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -346,6 +346,11 @@ static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk)
 	       ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY);
 }
 
+static inline struct smc_sock *smc_clcsock_user_data_rcu(const struct sock *clcsk)
+{
+	return (struct smc_sock *)rcu_dereference_sk_user_data(clcsk);
+}
+
 /* save target_cb in saved_cb, and replace target_cb with new_cb */
 static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *),
 					  void (*new_cb)(struct sock *),
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 10219f55aad1..bb0313ef5f7c 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -218,7 +218,7 @@ again:
 			write_lock_bh(&smc->clcsock->sk->sk_callback_lock);
 			smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready,
 					       &smc->clcsk_data_ready);
-			smc->clcsock->sk->sk_user_data = NULL;
+			rcu_assign_sk_user_data(smc->clcsock->sk, NULL);
 			write_unlock_bh(&smc->clcsock->sk->sk_callback_lock);
 			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
 		}
-- 
cgit v1.2.3


From 66360460cab63c248ca5b1070a01c0c29133b960 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 15 Mar 2026 11:54:22 -0400
Subject: net/sched: teql: Fix double-free in teql_master_xmit

Whenever a TEQL devices has a lockless Qdisc as root, qdisc_reset should
be called using the seq_lock to avoid racing with the datapath. Failure
to do so may cause crashes like the following:

[  238.028993][  T318] BUG: KASAN: double-free in skb_release_data (net/core/skbuff.c:1139)
[  238.029328][  T318] Free of addr ffff88810c67ec00 by task poc_teql_uaf_ke/318
[  238.029749][  T318]
[  238.029900][  T318] CPU: 3 UID: 0 PID: 318 Comm: poc_teql_ke Not tainted 7.0.0-rc3-00149-ge5b31d988a41 #704 PREEMPT(full)
[  238.029906][  T318] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[  238.029910][  T318] Call Trace:
[  238.029913][  T318]  <TASK>
[  238.029916][  T318]  dump_stack_lvl (lib/dump_stack.c:122)
[  238.029928][  T318]  print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
[  238.029940][  T318]  ? skb_release_data (net/core/skbuff.c:1139)
[  238.029944][  T318]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
...
[  238.029957][  T318]  ? skb_release_data (net/core/skbuff.c:1139)
[  238.029969][  T318]  kasan_report_invalid_free (mm/kasan/report.c:221 mm/kasan/report.c:563)
[  238.029979][  T318]  ? skb_release_data (net/core/skbuff.c:1139)
[  238.029989][  T318]  check_slab_allocation (mm/kasan/common.c:231)
[  238.029995][  T318]  kmem_cache_free (mm/slub.c:2637 (discriminator 1) mm/slub.c:6168 (discriminator 1) mm/slub.c:6298 (discriminator 1))
[  238.030004][  T318]  skb_release_data (net/core/skbuff.c:1139)
...
[  238.030025][  T318]  sk_skb_reason_drop (net/core/skbuff.c:1256)
[  238.030032][  T318]  pfifo_fast_reset (./include/linux/ptr_ring.h:171 ./include/linux/ptr_ring.h:309 ./include/linux/skb_array.h:98 net/sched/sch_generic.c:827)
[  238.030039][  T318]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
...
[  238.030054][  T318]  qdisc_reset (net/sched/sch_generic.c:1034)
[  238.030062][  T318]  teql_destroy (./include/linux/spinlock.h:395 net/sched/sch_teql.c:157)
[  238.030071][  T318]  __qdisc_destroy (./include/net/pkt_sched.h:328 net/sched/sch_generic.c:1077)
[  238.030077][  T318]  qdisc_graft (net/sched/sch_api.c:1062 net/sched/sch_api.c:1053 net/sched/sch_api.c:1159)
[  238.030089][  T318]  ? __pfx_qdisc_graft (net/sched/sch_api.c:1091)
[  238.030095][  T318]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  238.030102][  T318]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  238.030106][  T318]  ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221)
[  238.030114][  T318]  tc_get_qdisc (net/sched/sch_api.c:1529 net/sched/sch_api.c:1556)
...
[  238.072958][  T318] Allocated by task 303 on cpu 5 at 238.026275s:
[  238.073392][  T318]  kasan_save_stack (mm/kasan/common.c:58)
[  238.073884][  T318]  kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5))
[  238.074230][  T318]  __kasan_slab_alloc (mm/kasan/common.c:369)
[  238.074578][  T318]  kmem_cache_alloc_node_noprof (./include/linux/kasan.h:253 mm/slub.c:4542 mm/slub.c:4869 mm/slub.c:4921)
[  238.076091][  T318]  kmalloc_reserve (net/core/skbuff.c:616 (discriminator 107))
[  238.076450][  T318]  __alloc_skb (net/core/skbuff.c:713)
[  238.076834][  T318]  alloc_skb_with_frags (./include/linux/skbuff.h:1383 net/core/skbuff.c:6763)
[  238.077178][  T318]  sock_alloc_send_pskb (net/core/sock.c:2997)
[  238.077520][  T318]  packet_sendmsg (net/packet/af_packet.c:2926 net/packet/af_packet.c:3019 net/packet/af_packet.c:3108)
[  238.081469][  T318]
[  238.081870][  T318] Freed by task 299 on cpu 1 at 238.028496s:
[  238.082761][  T318]  kasan_save_stack (mm/kasan/common.c:58)
[  238.083481][  T318]  kasan_save_track (mm/kasan/common.c:64 (discriminator 5) mm/kasan/common.c:79 (discriminator 5))
[  238.085348][  T318]  kasan_save_free_info (mm/kasan/generic.c:587 (discriminator 1))
[  238.085900][  T318]  __kasan_slab_free (mm/kasan/common.c:287)
[  238.086439][  T318]  kmem_cache_free (mm/slub.c:6168 (discriminator 3) mm/slub.c:6298 (discriminator 3))
[  238.087007][  T318]  skb_release_data (net/core/skbuff.c:1139)
[  238.087491][  T318]  consume_skb (net/core/skbuff.c:1451)
[  238.087757][  T318]  teql_master_xmit (net/sched/sch_teql.c:358)
[  238.088116][  T318]  dev_hard_start_xmit (./include/linux/netdevice.h:5324 ./include/linux/netdevice.h:5333 net/core/dev.c:3871 net/core/dev.c:3887)
[  238.088468][  T318]  sch_direct_xmit (net/sched/sch_generic.c:347)
[  238.088820][  T318]  __qdisc_run (net/sched/sch_generic.c:420 (discriminator 1))
[  238.089166][  T318]  __dev_queue_xmit (./include/net/sch_generic.h:229 ./include/net/pkt_sched.h:121 ./include/net/pkt_sched.h:117 net/core/dev.c:4196 net/core/dev.c:4802)

Workflow to reproduce:
1. Initialize a TEQL topology (dummy0 and ifb0 as slaves, teql0 up).
2. Start multiple sender workers continuously transmitting packets
   through teql0 to drive teql_master_xmit().
3. In parallel, repeatedly delete and re-add the root qdisc on
   dummy0 and ifb0 via RTNETLINK, forcing frequent teardown and reset activity
   (teql_destroy() / qdisc_reset()).
4. After running both workloads concurrently for several iterations,
   KASAN reports slab-use-after-free or double-free in the skb free path.

Fix this by moving dev_reset_queue to sch_generic.h and calling it, instead
of qdisc_reset, in teql_destroy since it handles both the lock and lockless
cases correctly for root qdiscs.

Fixes: 96009c7d500e ("sched: replace __QDISC_STATE_RUNNING bit with a spin lock")
Reported-by: Xianrui Dong <keenanat2000@gmail.com>
Tested-by: Xianrui Dong <keenanat2000@gmail.com>
Co-developed-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260315155422.147256-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sch_generic.h | 28 ++++++++++++++++++++++++++++
 net/sched/sch_generic.c   | 27 ---------------------------
 net/sched/sch_teql.c      |  7 ++-----
 3 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d5d55cb21686..cafb266a0b80 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -716,6 +716,34 @@ void qdisc_destroy(struct Qdisc *qdisc);
 void qdisc_put(struct Qdisc *qdisc);
 void qdisc_put_unlocked(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len);
+
+static inline void dev_reset_queue(struct net_device *dev,
+				   struct netdev_queue *dev_queue,
+				   void *_unused)
+{
+	struct Qdisc *qdisc;
+	bool nolock;
+
+	qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
+	if (!qdisc)
+		return;
+
+	nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+	if (nolock)
+		spin_lock_bh(&qdisc->seqlock);
+	spin_lock_bh(qdisc_lock(qdisc));
+
+	qdisc_reset(qdisc);
+
+	spin_unlock_bh(qdisc_lock(qdisc));
+	if (nolock) {
+		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
+		clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
+		spin_unlock_bh(&qdisc->seqlock);
+	}
+}
+
 #ifdef CONFIG_NET_SCHED
 int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
 			      void *type_data);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 98ffe64de51f..9e726c3bd86b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1288,33 +1288,6 @@ static void dev_deactivate_queue(struct net_device *dev,
 	}
 }
 
-static void dev_reset_queue(struct net_device *dev,
-			    struct netdev_queue *dev_queue,
-			    void *_unused)
-{
-	struct Qdisc *qdisc;
-	bool nolock;
-
-	qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
-	if (!qdisc)
-		return;
-
-	nolock = qdisc->flags & TCQ_F_NOLOCK;
-
-	if (nolock)
-		spin_lock_bh(&qdisc->seqlock);
-	spin_lock_bh(qdisc_lock(qdisc));
-
-	qdisc_reset(qdisc);
-
-	spin_unlock_bh(qdisc_lock(qdisc));
-	if (nolock) {
-		clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
-		clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
-		spin_unlock_bh(&qdisc->seqlock);
-	}
-}
-
 static bool some_qdisc_is_busy(struct net_device *dev)
 {
 	unsigned int i;
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 783300d8b019..ec4039a201a2 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -146,15 +146,12 @@ teql_destroy(struct Qdisc *sch)
 					master->slaves = NEXT_SLAVE(q);
 					if (q == master->slaves) {
 						struct netdev_queue *txq;
-						spinlock_t *root_lock;
 
 						txq = netdev_get_tx_queue(master->dev, 0);
 						master->slaves = NULL;
 
-						root_lock = qdisc_root_sleeping_lock(rtnl_dereference(txq->qdisc));
-						spin_lock_bh(root_lock);
-						qdisc_reset(rtnl_dereference(txq->qdisc));
-						spin_unlock_bh(root_lock);
+						dev_reset_queue(master->dev,
+								txq, NULL);
 					}
 				}
 				skb_queue_purge(&dat->q);
-- 
cgit v1.2.3


From d4a533ad249e9fbdc2d0633f2ddd60a5b3a9a4ca Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 13 Mar 2026 12:27:00 +0100
Subject: net: airoha: Remove airoha_dev_stop() in airoha_remove()

Do not run airoha_dev_stop routine explicitly in airoha_remove()
since ndo_stop() callback is already executed by unregister_netdev() in
__dev_close_many routine if necessary and, doing so, we will end up causing
an underflow in the qdma users atomic counters. Rely on networking subsystem
to stop the device removing the airoha_eth module.

Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260313-airoha-remove-ndo_stop-remove-net-v2-1-67542c3ceeca@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 62bcbbbe2a95..56cf9a926a83 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -3083,7 +3083,6 @@ static void airoha_remove(struct platform_device *pdev)
 		if (!port)
 			continue;
 
-		airoha_dev_stop(port->dev);
 		unregister_netdev(port->dev);
 		airoha_metadata_dst_free(port);
 	}
-- 
cgit v1.2.3


From 2aa8a4fa8d5b7d0e1ebcec100e1a4d80a1f4b21a Mon Sep 17 00:00:00 2001
From: Tobi Gaertner <tob.gaertner@me.com>
Date: Fri, 13 Mar 2026 22:46:39 -0700
Subject: net: usb: cdc_ncm: add ndpoffset to NDP16 nframes bounds check

cdc_ncm_rx_verify_ndp16() validates that the NDP header and its DPE
entries fit within the skb. The first check correctly accounts for
ndpoffset:

  if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len)

but the second check omits it:

  if ((sizeof(struct usb_cdc_ncm_ndp16) +
       ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len)

This validates the DPE array size against the total skb length as if
the NDP were at offset 0, rather than at ndpoffset. When the NDP is
placed near the end of the NTB (large wNdpIndex), the DPE entries can
extend past the skb data buffer even though the check passes.
cdc_ncm_rx_fixup() then reads out-of-bounds memory when iterating
the DPE array.

Add ndpoffset to the nframes bounds check and use struct_size_t() to
express the NDP-plus-DPE-array size more clearly.

Fixes: ff06ab13a4cc ("net: cdc_ncm: splitting rx_fixup for code reuse")
Signed-off-by: Tobi Gaertner <tob.gaertner@me.com>
Link: https://patch.msgid.link/20260314054640.2895026-2-tob.gaertner@me.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ncm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 7057c6c0cfc6..21e53b20e239 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1656,6 +1656,7 @@ int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset)
 	struct usbnet *dev = netdev_priv(skb_in->dev);
 	struct usb_cdc_ncm_ndp16 *ndp16;
 	int ret = -EINVAL;
+	size_t ndp_len;
 
 	if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp16)) > skb_in->len) {
 		netif_dbg(dev, rx_err, dev->net, "invalid NDP offset  <%u>\n",
@@ -1675,8 +1676,8 @@ int cdc_ncm_rx_verify_ndp16(struct sk_buff *skb_in, int ndpoffset)
 					sizeof(struct usb_cdc_ncm_dpe16));
 	ret--; /* we process NDP entries except for the last one */
 
-	if ((sizeof(struct usb_cdc_ncm_ndp16) +
-	     ret * (sizeof(struct usb_cdc_ncm_dpe16))) > skb_in->len) {
+	ndp_len = struct_size_t(struct usb_cdc_ncm_ndp16, dpe16, ret);
+	if (ndpoffset + ndp_len > skb_in->len) {
 		netif_dbg(dev, rx_err, dev->net, "Invalid nframes = %d\n", ret);
 		ret = -EINVAL;
 	}
-- 
cgit v1.2.3


From 77914255155e68a20aa41175edeecf8121dac391 Mon Sep 17 00:00:00 2001
From: Tobi Gaertner <tob.gaertner@me.com>
Date: Fri, 13 Mar 2026 22:46:40 -0700
Subject: net: usb: cdc_ncm: add ndpoffset to NDP32 nframes bounds check

The same bounds-check bug fixed for NDP16 in the previous patch also
exists in cdc_ncm_rx_verify_ndp32(). The DPE array size is validated
against the total skb length without accounting for ndpoffset, allowing
out-of-bounds reads when the NDP32 is placed near the end of the NTB.

Add ndpoffset to the nframes bounds check and use struct_size_t() to
express the NDP-plus-DPE-array size more clearly.

Compile-tested only.

Fixes: 0fa81b304a79 ("cdc_ncm: Implement the 32-bit version of NCM Transfer Block")
Signed-off-by: Tobi Gaertner <tob.gaertner@me.com>
Link: https://patch.msgid.link/20260314054640.2895026-3-tob.gaertner@me.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ncm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 21e53b20e239..bb9929727eb9 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1693,6 +1693,7 @@ int cdc_ncm_rx_verify_ndp32(struct sk_buff *skb_in, int ndpoffset)
 	struct usbnet *dev = netdev_priv(skb_in->dev);
 	struct usb_cdc_ncm_ndp32 *ndp32;
 	int ret = -EINVAL;
+	size_t ndp_len;
 
 	if ((ndpoffset + sizeof(struct usb_cdc_ncm_ndp32)) > skb_in->len) {
 		netif_dbg(dev, rx_err, dev->net, "invalid NDP offset  <%u>\n",
@@ -1712,8 +1713,8 @@ int cdc_ncm_rx_verify_ndp32(struct sk_buff *skb_in, int ndpoffset)
 					sizeof(struct usb_cdc_ncm_dpe32));
 	ret--; /* we process NDP entries except for the last one */
 
-	if ((sizeof(struct usb_cdc_ncm_ndp32) +
-	     ret * (sizeof(struct usb_cdc_ncm_dpe32))) > skb_in->len) {
+	ndp_len = struct_size_t(struct usb_cdc_ncm_ndp32, dpe32, ret);
+	if (ndpoffset + ndp_len > skb_in->len) {
 		netif_dbg(dev, rx_err, dev->net, "Invalid nframes = %d\n", ret);
 		ret = -EINVAL;
 	}
-- 
cgit v1.2.3


From e4c00ba7274b613e3ab19e27eb009f0ec2e28379 Mon Sep 17 00:00:00 2001
From: Paul SAGE <paul.sage@42.fr>
Date: Sun, 15 Mar 2026 03:24:30 +0530
Subject: tg3: replace placeholder MAC address with device property

On some systems (e.g. iMac 20,1 with BCM57766), the tg3 driver reads
a default placeholder mac address (00:10:18:00:00:00) from the
mailbox. The correct value on those systems are stored in the
'local-mac-address' property.

This patch, detect the default value and tries to retrieve
the correct address from the device_get_mac_address
function instead.

The patch has been tested on two different systems:
- iMac 20,1 (BCM57766) model which use the local-mac-address property
- iMac 13,2 (BCM57766) model which can use the mailbox,
    NVRAM or MAC control registers

Tested-by: Rishon Jonathan R <mithicalaviator85@gmail.com>

Co-developed-by: Vincent MORVAN <vinc@42.fr>
Signed-off-by: Vincent MORVAN <vinc@42.fr>
Signed-off-by: Paul SAGE <paul.sage@42.fr>
Signed-off-by: Atharva Tiwari <atharvatiwarilinuxdev@gmail.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260314215432.3589-1-atharvatiwarilinuxdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/tg3.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 2328fce33644..21a5dd342724 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -17029,6 +17029,13 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 	return err;
 }
 
+static int tg3_is_default_mac_address(u8 *addr)
+{
+	static const u8 default_mac_address[ETH_ALEN] = { 0x00, 0x10, 0x18, 0x00, 0x00, 0x00 };
+
+	return ether_addr_equal(default_mac_address, addr);
+}
+
 static int tg3_get_device_address(struct tg3 *tp, u8 *addr)
 {
 	u32 hi, lo, mac_offset;
@@ -17102,6 +17109,10 @@ static int tg3_get_device_address(struct tg3 *tp, u8 *addr)
 
 	if (!is_valid_ether_addr(addr))
 		return -EINVAL;
+
+	if (tg3_is_default_mac_address(addr))
+		return device_get_mac_address(&tp->pdev->dev, addr);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From bb120ad57def62e3f23e3d999c5fbed11f610993 Mon Sep 17 00:00:00 2001
From: Alexey Nepomnyashih <sdl@nppct.ru>
Date: Mon, 16 Mar 2026 19:18:22 +0000
Subject: ALSA: firewire-lib: fix uninitialized local variable

Similar to commit d8dc8720468a ("ALSA: firewire-lib: fix uninitialized
local variable"), the local variable `curr_cycle_time` in
process_rx_packets() is declared without initialization.

When the tracepoint event is not probed, the variable may appear to be
used without being initialized. In practice the value is only relevant
when the tracepoint is enabled, however initializing it avoids potential
use of an uninitialized value and improves code safety.

Initialize `curr_cycle_time` to zero.

Fixes: fef4e61b0b76 ("ALSA: firewire-lib: extend tracepoints event including CYCLE_TIME of 1394 OHCI")
Cc: stable@vger.kernel.org
Signed-off-by: Alexey Nepomnyashih <sdl@nppct.ru>
Link: https://patch.msgid.link/20260316191824.83249-1-sdl@nppct.ru
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/amdtp-stream.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
index e97721f80f65..8e70da850fac 100644
--- a/sound/firewire/amdtp-stream.c
+++ b/sound/firewire/amdtp-stream.c
@@ -1164,7 +1164,7 @@ static void process_rx_packets(struct fw_iso_context *context, u32 tstamp, size_
 	struct pkt_desc *desc = s->packet_descs_cursor;
 	unsigned int pkt_header_length;
 	unsigned int packets;
-	u32 curr_cycle_time;
+	u32 curr_cycle_time = 0;
 	bool need_hw_irq;
 	int i;
 
-- 
cgit v1.2.3


From b0a4dba7b623aa7cbc9efcc56b4af2ec8b274f3e Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Thu, 12 Mar 2026 10:37:09 +0200
Subject: drm/i915/psr: Disable PSR on update_m_n and update_lrr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR/PR parameters might change based on update_m_n or update_lrr. Disable
on update_m_n and update_lrr to ensure proper parameters are taken into use
on next PSR enable in intel_psr_post_plane_update.

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15771
Fixes: 2bc98c6f97af ("drm/i915/alpm: Compute ALPM parameters into crtc_state->alpm_state")
Cc: <stable@vger.kernel.org> # v6.19+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://patch.msgid.link/20260312083710.1593781-2-jouni.hogander@intel.com
(cherry picked from commit 65852b56bfa929f99e28c96fd98b02058959da7f)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index b7302a32ded4..426c23319269 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3109,6 +3109,8 @@ void intel_psr_pre_plane_update(struct intel_atomic_state *state,
 			 * - Display WA #1136: skl, bxt
 			 */
 			if (intel_crtc_needs_modeset(new_crtc_state) ||
+			    new_crtc_state->update_m_n ||
+			    new_crtc_state->update_lrr ||
 			    !new_crtc_state->has_psr ||
 			    !new_crtc_state->active_planes ||
 			    new_crtc_state->has_sel_update != psr->sel_update_enabled ||
-- 
cgit v1.2.3


From 7caac659a837af9fd4cad85be851982b88859484 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Thu, 12 Mar 2026 10:37:10 +0200
Subject: drm/i915/psr: Compute PSR entry_setup_frames into intel_crtc_state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR entry_setup_frames is currently computed directly into struct
intel_dp:intel_psr:entry_setup_frames. This causes a problem if mode change
gets rejected after PSR compute config: Psr_entry_setup_frames computed for
this rejected state is in intel_dp:intel_psr:entry_setup_frame. Fix this by
computing it into intel_crtc_state and copy the value into
intel_dp:intel_psr:entry_setup_frames on PSR enable.

Fixes: 2b981d57e480 ("drm/i915/display: Support PSR entry VSC packet to be transmitted one frame earlier")
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://patch.msgid.link/20260312083710.1593781-3-jouni.hogander@intel.com
(cherry picked from commit 8c229b4aa00262c13787982e998c61c0783285e0)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_types.h | 1 +
 drivers/gpu/drm/i915/display/intel_psr.c           | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 6b92f333e18b..ced0e5a5989b 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1186,6 +1186,7 @@ struct intel_crtc_state {
 	u32 dc3co_exitline;
 	u16 su_y_granularity;
 	u8 active_non_psr_pipes;
+	u8 entry_setup_frames;
 	const char *no_psr_reason;
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 426c23319269..3791944389db 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1717,7 +1717,7 @@ static bool _psr_compute_config(struct intel_dp *intel_dp,
 	entry_setup_frames = intel_psr_entry_setup_frames(intel_dp, conn_state, adjusted_mode);
 
 	if (entry_setup_frames >= 0) {
-		intel_dp->psr.entry_setup_frames = entry_setup_frames;
+		crtc_state->entry_setup_frames = entry_setup_frames;
 	} else {
 		crtc_state->no_psr_reason = "PSR setup timing not met";
 		drm_dbg_kms(display->drm,
@@ -1815,7 +1815,7 @@ static bool intel_psr_needs_wa_18037818876(struct intel_dp *intel_dp,
 {
 	struct intel_display *display = to_intel_display(intel_dp);
 
-	return (DISPLAY_VER(display) == 20 && intel_dp->psr.entry_setup_frames > 0 &&
+	return (DISPLAY_VER(display) == 20 && crtc_state->entry_setup_frames > 0 &&
 		!crtc_state->has_sel_update);
 }
 
@@ -2189,6 +2189,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 	intel_dp->psr.pkg_c_latency_used = crtc_state->pkg_c_latency_used;
 	intel_dp->psr.io_wake_lines = crtc_state->alpm_state.io_wake_lines;
 	intel_dp->psr.fast_wake_lines = crtc_state->alpm_state.fast_wake_lines;
+	intel_dp->psr.entry_setup_frames = crtc_state->entry_setup_frames;
 
 	if (!psr_interrupt_error_check(intel_dp))
 		return;
-- 
cgit v1.2.3


From 76f0930d6e809234904cf9f0f5f42ee6c1dc694e Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 15 Mar 2026 15:17:54 +0800
Subject: irqchip/riscv-rpmi-sysmsi: Fix mailbox channel leak in
 rpmi_sysmsi_probe()

When riscv_acpi_get_gsi_info() fails, the mailbox channel previously
requested via mbox_request_channel() is not freed. Add the missing
mbox_free_channel() call to prevent the resource leak.

Fixes: 4752b0cfbc37 ("irqchip/riscv-rpmi-sysmsi: Add ACPI support")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: stable@vger.kernel.org
Reviewed-by: Rahul Pathak <rahul@summations.net>
Link: https://patch.msgid.link/20260315-sysmsi-v1-1-5f090c86c2ca@gmail.com
---
 drivers/irqchip/irq-riscv-rpmi-sysmsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/irqchip/irq-riscv-rpmi-sysmsi.c b/drivers/irqchip/irq-riscv-rpmi-sysmsi.c
index 5c74c561ce31..612f3972f7af 100644
--- a/drivers/irqchip/irq-riscv-rpmi-sysmsi.c
+++ b/drivers/irqchip/irq-riscv-rpmi-sysmsi.c
@@ -250,6 +250,7 @@ static int rpmi_sysmsi_probe(struct platform_device *pdev)
 		rc = riscv_acpi_get_gsi_info(fwnode, &priv->gsi_base, &id,
 					     &nr_irqs, NULL);
 		if (rc) {
+			mbox_free_channel(priv->chan);
 			dev_err(dev, "failed to find GSI mapping\n");
 			return rc;
 		}
-- 
cgit v1.2.3


From 50242828700f06edfa8d563f9e0acc23a59424ee Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sun, 8 Feb 2026 19:24:16 +0000
Subject: btrfs: check for NULL root after calls to btrfs_extent_root()

btrfs_extent_root() can return a NULL pointer in case the root we are
looking for is not in the rb tree that tracks roots. So add checks to
every caller that is missing such check to log a message and return
an error. The same applies to callers of btrfs_block_group_root(),
since it calls btrfs_extent_root().

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208161657.3972997-1-clm@meta.com/
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/backref.c         | 28 +++++++++++++++++
 fs/btrfs/block-group.c     | 36 +++++++++++++++++++++
 fs/btrfs/disk-io.c         | 16 ++++++++--
 fs/btrfs/extent-tree.c     | 78 ++++++++++++++++++++++++++++++++++++++++++++--
 fs/btrfs/free-space-tree.c |  9 +++++-
 fs/btrfs/qgroup.c          |  8 +++++
 fs/btrfs/relocation.c      | 22 +++++++++++--
 fs/btrfs/zoned.c           |  7 +++++
 8 files changed, 195 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 9bb406f7dd30..7921a926f676 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1393,6 +1393,13 @@ static int find_parent_nodes(struct btrfs_backref_walk_ctx *ctx,
 		.indirect_missing_keys = PREFTREE_INIT
 	};
 
+	if (unlikely(!root)) {
+		btrfs_err(ctx->fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  ctx->bytenr);
+		return -EUCLEAN;
+	}
+
 	/* Roots ulist is not needed when using a sharedness check context. */
 	if (sc)
 		ASSERT(ctx->roots == NULL);
@@ -2204,6 +2211,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	struct btrfs_extent_item *ei;
 	struct btrfs_key key;
 
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  logical);
+		return -EUCLEAN;
+	}
+
 	key.objectid = logical;
 	if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
 		key.type = BTRFS_METADATA_ITEM_KEY;
@@ -2851,6 +2865,13 @@ int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr)
 	struct btrfs_key key;
 	int ret;
 
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	key.type = BTRFS_METADATA_ITEM_KEY;
 	key.offset = (u64)-1;
@@ -2987,6 +3008,13 @@ int btrfs_backref_iter_next(struct btrfs_backref_iter *iter)
 
 	/* We're at keyed items, there is no inline item, go to the next one */
 	extent_root = btrfs_extent_root(iter->fs_info, iter->bytenr);
+	if (unlikely(!extent_root)) {
+		btrfs_err(iter->fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  iter->bytenr);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_next_item(extent_root, iter->path);
 	if (ret)
 		return ret;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 77285ade3a0e..fa55d868ecd8 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -739,6 +739,12 @@ static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
 
 	last = max_t(u64, block_group->start, BTRFS_SUPER_INFO_OFFSET);
 	extent_root = btrfs_extent_root(fs_info, last);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for block group at offset %llu",
+			  block_group->start);
+		return -EUCLEAN;
+	}
 
 #ifdef CONFIG_BTRFS_DEBUG
 	/*
@@ -1061,6 +1067,11 @@ static int remove_block_group_item(struct btrfs_trans_handle *trans,
 	int ret;
 
 	root = btrfs_block_group_root(fs_info);
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return -EUCLEAN;
+	}
+
 	key.objectid = block_group->start;
 	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
 	key.offset = block_group->length;
@@ -1349,6 +1360,11 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 	struct btrfs_chunk_map *map;
 	unsigned int num_items;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return ERR_PTR(-EUCLEAN);
+	}
+
 	map = btrfs_find_chunk_map(fs_info, chunk_offset, 1);
 	ASSERT(map != NULL);
 	ASSERT(map->start == chunk_offset);
@@ -2140,6 +2156,11 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 	int ret;
 	struct btrfs_key found_key;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return -EUCLEAN;
+	}
+
 	btrfs_for_each_slot(root, key, &found_key, path, ret) {
 		if (found_key.objectid >= key->objectid &&
 		    found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
@@ -2714,6 +2735,11 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans,
 	size_t size;
 	int ret;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return -EUCLEAN;
+	}
+
 	spin_lock(&block_group->lock);
 	btrfs_set_stack_block_group_v2_used(&bgi, block_group->used);
 	btrfs_set_stack_block_group_v2_chunk_objectid(&bgi, block_group->global_root_id);
@@ -3049,6 +3075,11 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
 	int ret;
 	bool dirty_bg_running;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return -EUCLEAN;
+	}
+
 	/*
 	 * This can only happen when we are doing read-only scrub on read-only
 	 * mount.
@@ -3193,6 +3224,11 @@ static int update_block_group_item(struct btrfs_trans_handle *trans,
 	u64 used, remap_bytes;
 	u32 identity_remap_count;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info, "missing block group root");
+		return -EUCLEAN;
+	}
+
 	/*
 	 * Block group items update can be triggered out of commit transaction
 	 * critical section, thus we need a consistent view of used bytes.
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2aeb85e3ece9..08368247668e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1591,7 +1591,7 @@ static int find_newest_super_backup(struct btrfs_fs_info *info)
  * this will bump the backup pointer by one when it is
  * done
  */
-static void backup_super_roots(struct btrfs_fs_info *info)
+static int backup_super_roots(struct btrfs_fs_info *info)
 {
 	const int next_backup = info->backup_root_index;
 	struct btrfs_root_backup *root_backup;
@@ -1623,6 +1623,11 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 		struct btrfs_root *extent_root = btrfs_extent_root(info, 0);
 		struct btrfs_root *csum_root = btrfs_csum_root(info, 0);
 
+		if (unlikely(!extent_root)) {
+			btrfs_err(info, "missing extent root for extent at bytenr 0");
+			return -EUCLEAN;
+		}
+
 		btrfs_set_backup_extent_root(root_backup,
 					     extent_root->node->start);
 		btrfs_set_backup_extent_root_gen(root_backup,
@@ -1670,6 +1675,8 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 	memcpy(&info->super_copy->super_roots,
 	       &info->super_for_commit->super_roots,
 	       sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
+
+	return 0;
 }
 
 /*
@@ -4051,8 +4058,11 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 	 * not from fsync where the tree roots in fs_info have not
 	 * been consistent on disk.
 	 */
-	if (max_mirrors == 0)
-		backup_super_roots(fs_info);
+	if (max_mirrors == 0) {
+		ret = backup_super_roots(fs_info);
+		if (ret < 0)
+			return ret;
+	}
 
 	sb = fs_info->super_for_commit;
 	dev_item = &sb->dev_item;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b0d9baf5b412..7fcd83f32014 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -75,6 +75,12 @@ int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
 	struct btrfs_key key;
 	BTRFS_PATH_AUTO_FREE(path);
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu", start);
+		return -EUCLEAN;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -131,6 +137,12 @@ search_again:
 	key.offset = offset;
 
 	extent_root = btrfs_extent_root(fs_info, bytenr);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
@@ -436,6 +448,12 @@ static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
 	int recow;
 	int ret;
 
+	if (unlikely(!root)) {
+		btrfs_err(trans->fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	if (parent) {
 		key.type = BTRFS_SHARED_DATA_REF_KEY;
@@ -510,6 +528,12 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
 	u32 num_refs;
 	int ret;
 
+	if (unlikely(!root)) {
+		btrfs_err(trans->fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	if (node->parent) {
 		key.type = BTRFS_SHARED_DATA_REF_KEY;
@@ -668,6 +692,12 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 
+	if (unlikely(!root)) {
+		btrfs_err(trans->fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	if (parent) {
 		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
@@ -692,6 +722,12 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 
+	if (unlikely(!root)) {
+		btrfs_err(trans->fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	if (node->parent) {
 		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
@@ -782,6 +818,12 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
 	int needed;
 
+	if (unlikely(!root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	key.offset = num_bytes;
@@ -1680,6 +1722,12 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
 	}
 
 	root = btrfs_extent_root(fs_info, key.objectid);
+	if (unlikely(!root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  key.objectid);
+		return -EUCLEAN;
+	}
 again:
 	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
 	if (ret < 0) {
@@ -2379,6 +2427,12 @@ static noinline int check_committed_ref(struct btrfs_inode *inode,
 	int type;
 	int ret;
 
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
+
 	key.objectid = bytenr;
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	key.offset = (u64)-1;
@@ -3222,7 +3276,11 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	u64 delayed_ref_root = href->owning_root;
 
 	extent_root = btrfs_extent_root(info, bytenr);
-	ASSERT(extent_root);
+	if (unlikely(!extent_root)) {
+		btrfs_err(info,
+			  "missing extent root for extent at bytenr %llu", bytenr);
+		return -EUCLEAN;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4939,11 +4997,18 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 		size += btrfs_extent_inline_ref_size(BTRFS_EXTENT_OWNER_REF_KEY);
 	size += btrfs_extent_inline_ref_size(type);
 
+	extent_root = btrfs_extent_root(fs_info, ins->objectid);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  ins->objectid);
+		return -EUCLEAN;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	extent_root = btrfs_extent_root(fs_info, ins->objectid);
 	ret = btrfs_insert_empty_item(trans, extent_root, path, ins, size);
 	if (ret) {
 		btrfs_free_path(path);
@@ -5019,11 +5084,18 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 		size += sizeof(*block_info);
 	}
 
+	extent_root = btrfs_extent_root(fs_info, extent_key.objectid);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  extent_key.objectid);
+		return -EUCLEAN;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	extent_root = btrfs_extent_root(fs_info, extent_key.objectid);
 	ret = btrfs_insert_empty_item(trans, extent_root, path, &extent_key,
 				      size);
 	if (ret) {
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index ecddfca92b2b..9efd1ec90f03 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1073,6 +1073,14 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
+	extent_root = btrfs_extent_root(trans->fs_info, block_group->start);
+	if (unlikely(!extent_root)) {
+		btrfs_err(trans->fs_info,
+			  "missing extent root for block group at offset %llu",
+			  block_group->start);
+		return -EUCLEAN;
+	}
+
 	mutex_lock(&block_group->free_space_lock);
 
 	/*
@@ -1086,7 +1094,6 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	key.offset = 0;
 
-	extent_root = btrfs_extent_root(trans->fs_info, key.objectid);
 	ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0);
 	if (ret < 0)
 		goto out_locked;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 19edd25ff5d1..0fa66fe4fbb0 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3740,6 +3740,14 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	extent_root = btrfs_extent_root(fs_info,
 				fs_info->qgroup_rescan_progress.objectid);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  fs_info->qgroup_rescan_progress.objectid);
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_search_slot_for_read(extent_root,
 					 &fs_info->qgroup_rescan_progress,
 					 path, 1, 0);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fcfbe1b1dab4..93a5ae23406d 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4954,6 +4954,12 @@ static int do_remap_reloc_trans(struct btrfs_fs_info *fs_info,
 	struct btrfs_space_info *sinfo = src_bg->space_info;
 
 	extent_root = btrfs_extent_root(fs_info, src_bg->start);
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for block group at offset %llu",
+			  src_bg->start);
+		return -EUCLEAN;
+	}
 
 	trans = btrfs_start_transaction(extent_root, 0);
 	if (IS_ERR(trans))
@@ -5306,6 +5312,13 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start,
 	int ret;
 	bool bg_is_ro = false;
 
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for block group at offset %llu",
+			  group_start);
+		return -EUCLEAN;
+	}
+
 	/*
 	 * This only gets set if we had a half-deleted snapshot on mount.  We
 	 * cannot allow relocation to start while we're still trying to clean up
@@ -5536,12 +5549,17 @@ int btrfs_recover_relocation(struct btrfs_fs_info *fs_info)
 		goto out;
 	}
 
+	rc->extent_root = btrfs_extent_root(fs_info, 0);
+	if (unlikely(!rc->extent_root)) {
+		btrfs_err(fs_info, "missing extent root for extent at bytenr 0");
+		ret = -EUCLEAN;
+		goto out;
+	}
+
 	ret = reloc_chunk_start(fs_info);
 	if (ret < 0)
 		goto out_end;
 
-	rc->extent_root = btrfs_extent_root(fs_info, 0);
-
 	set_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 92b5ac8fac37..afb5924018ac 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1261,6 +1261,13 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache,
 	key.offset = 0;
 
 	root = btrfs_extent_root(fs_info, key.objectid);
+	if (unlikely(!root)) {
+		btrfs_err(fs_info,
+			  "missing extent root for extent at bytenr %llu",
+			  key.objectid);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	/* We should not find the exact match */
 	if (unlikely(!ret))
-- 
cgit v1.2.3


From 2b4cb4e58f3463d142fcece5a19e0405fb82c794 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sun, 8 Feb 2026 19:43:01 +0000
Subject: btrfs: check for NULL root after calls to btrfs_csum_root()

btrfs_csum_root() can return a NULL pointer in case the root we are
looking for is not in the rb tree that tracks roots. So add checks to
every caller that is missing such check to log a message and return
an error.

Reported-by: Chris Mason <clm@meta.com>
Link: https://lore.kernel.org/linux-btrfs/20260208161657.3972997-1-clm@meta.com/
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c     |  4 ++++
 fs/btrfs/extent-tree.c | 20 ++++++++++++++++++--
 fs/btrfs/file-item.c   |  7 +++++++
 fs/btrfs/inode.c       | 18 ++++++++++++++++--
 fs/btrfs/raid56.c      | 12 ++++++++++--
 fs/btrfs/relocation.c  |  8 ++++++++
 fs/btrfs/tree-log.c    | 21 +++++++++++++++++++++
 7 files changed, 84 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08368247668e..b1b53d713ee9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1627,6 +1627,10 @@ static int backup_super_roots(struct btrfs_fs_info *info)
 			btrfs_err(info, "missing extent root for extent at bytenr 0");
 			return -EUCLEAN;
 		}
+		if (unlikely(!csum_root)) {
+			btrfs_err(info, "missing csum root for extent at bytenr 0");
+			return -EUCLEAN;
+		}
 
 		btrfs_set_backup_extent_root(root_backup,
 					     extent_root->node->start);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7fcd83f32014..85ee5c79759d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1974,8 +1974,15 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 			struct btrfs_root *csum_root;
 
 			csum_root = btrfs_csum_root(fs_info, head->bytenr);
-			ret = btrfs_del_csums(trans, csum_root, head->bytenr,
-					      head->num_bytes);
+			if (unlikely(!csum_root)) {
+				btrfs_err(fs_info,
+					  "missing csum root for extent at bytenr %llu",
+					  head->bytenr);
+				ret = -EUCLEAN;
+			} else {
+				ret = btrfs_del_csums(trans, csum_root, head->bytenr,
+						      head->num_bytes);
+			}
 		}
 	}
 
@@ -3147,6 +3154,15 @@ static int do_free_extent_accounting(struct btrfs_trans_handle *trans,
 		struct btrfs_root *csum_root;
 
 		csum_root = btrfs_csum_root(trans->fs_info, bytenr);
+		if (unlikely(!csum_root)) {
+			ret = -EUCLEAN;
+			btrfs_abort_transaction(trans, ret);
+			btrfs_err(trans->fs_info,
+				  "missing csum root for extent at bytenr %llu",
+				  bytenr);
+			return ret;
+		}
+
 		ret = btrfs_del_csums(trans, csum_root, bytenr, num_bytes);
 		if (unlikely(ret)) {
 			btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 7bd715442f3e..f585ddfa8440 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -308,6 +308,13 @@ static int search_csum_tree(struct btrfs_fs_info *fs_info,
 	/* Current item doesn't contain the desired range, search again */
 	btrfs_release_path(path);
 	csum_root = btrfs_csum_root(fs_info, disk_bytenr);
+	if (unlikely(!csum_root)) {
+		btrfs_err(fs_info,
+			  "missing csum root for extent at bytenr %llu",
+			  disk_bytenr);
+		return -EUCLEAN;
+	}
+
 	item = btrfs_lookup_csum(NULL, csum_root, path, disk_bytenr, 0);
 	if (IS_ERR(item)) {
 		ret = PTR_ERR(item);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b409efe1857e..ed4d19780f22 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2012,6 +2012,13 @@ static int can_nocow_file_extent(struct btrfs_path *path,
 	 */
 
 	csum_root = btrfs_csum_root(root->fs_info, io_start);
+	if (unlikely(!csum_root)) {
+		btrfs_err(root->fs_info,
+			  "missing csum root for extent at bytenr %llu", io_start);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
 	ret = btrfs_lookup_csums_list(csum_root, io_start,
 				      io_start + args->file_extent.num_bytes - 1,
 				      NULL, nowait);
@@ -2749,10 +2756,17 @@ static int add_pending_csums(struct btrfs_trans_handle *trans,
 	int ret;
 
 	list_for_each_entry(sum, list, list) {
-		trans->adding_csums = true;
-		if (!csum_root)
+		if (!csum_root) {
 			csum_root = btrfs_csum_root(trans->fs_info,
 						    sum->logical);
+			if (unlikely(!csum_root)) {
+				btrfs_err(trans->fs_info,
+				  "missing csum root for extent at bytenr %llu",
+					  sum->logical);
+				return -EUCLEAN;
+			}
+		}
+		trans->adding_csums = true;
 		ret = btrfs_csum_file_blocks(trans, csum_root, sum);
 		trans->adding_csums = false;
 		if (ret)
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index baadaaa189c0..230dd93dad6e 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2295,8 +2295,7 @@ void raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc,
 static void fill_data_csums(struct btrfs_raid_bio *rbio)
 {
 	struct btrfs_fs_info *fs_info = rbio->bioc->fs_info;
-	struct btrfs_root *csum_root = btrfs_csum_root(fs_info,
-						       rbio->bioc->full_stripe_logical);
+	struct btrfs_root *csum_root;
 	const u64 start = rbio->bioc->full_stripe_logical;
 	const u32 len = (rbio->nr_data * rbio->stripe_nsectors) <<
 			fs_info->sectorsize_bits;
@@ -2329,6 +2328,15 @@ static void fill_data_csums(struct btrfs_raid_bio *rbio)
 		goto error;
 	}
 
+	csum_root = btrfs_csum_root(fs_info, rbio->bioc->full_stripe_logical);
+	if (unlikely(!csum_root)) {
+		btrfs_err(fs_info,
+			  "missing csum root for extent at bytenr %llu",
+			  rbio->bioc->full_stripe_logical);
+		ret = -EUCLEAN;
+		goto error;
+	}
+
 	ret = btrfs_lookup_csums_bitmap(csum_root, NULL, start, start + len - 1,
 					rbio->csum_buf, rbio->csum_bitmap);
 	if (ret < 0)
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 93a5ae23406d..2625a66054d0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -5654,6 +5654,14 @@ int btrfs_reloc_clone_csums(struct btrfs_ordered_extent *ordered)
 	LIST_HEAD(list);
 	int ret;
 
+	if (unlikely(!csum_root)) {
+		btrfs_mark_ordered_extent_error(ordered);
+		btrfs_err(fs_info,
+			  "missing csum root for extent at bytenr %llu",
+			  disk_bytenr);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_lookup_csums_list(csum_root, disk_bytenr,
 				      disk_bytenr + ordered->num_bytes - 1,
 				      &list, false);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 37c272df52b0..9ff3933bc382 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -984,6 +984,13 @@ static noinline int replay_one_extent(struct walk_control *wc)
 
 		sums = list_first_entry(&ordered_sums, struct btrfs_ordered_sum, list);
 		csum_root = btrfs_csum_root(fs_info, sums->logical);
+		if (unlikely(!csum_root)) {
+			btrfs_err(fs_info,
+				  "missing csum root for extent at bytenr %llu",
+				  sums->logical);
+			ret = -EUCLEAN;
+		}
+
 		if (!ret) {
 			ret = btrfs_del_csums(trans, csum_root, sums->logical,
 					      sums->len);
@@ -4890,6 +4897,13 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 		}
 
 		csum_root = btrfs_csum_root(trans->fs_info, disk_bytenr);
+		if (unlikely(!csum_root)) {
+			btrfs_err(trans->fs_info,
+				  "missing csum root for extent at bytenr %llu",
+				  disk_bytenr);
+			return -EUCLEAN;
+		}
+
 		disk_bytenr += extent_offset;
 		ret = btrfs_lookup_csums_list(csum_root, disk_bytenr,
 					      disk_bytenr + extent_num_bytes - 1,
@@ -5086,6 +5100,13 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	/* block start is already adjusted for the file extent offset. */
 	block_start = btrfs_extent_map_block_start(em);
 	csum_root = btrfs_csum_root(trans->fs_info, block_start);
+	if (unlikely(!csum_root)) {
+		btrfs_err(trans->fs_info,
+			  "missing csum root for extent at bytenr %llu",
+			  block_start);
+		return -EUCLEAN;
+	}
+
 	ret = btrfs_lookup_csums_list(csum_root, block_start + csum_offset,
 				      block_start + csum_offset + csum_len - 1,
 				      &ordered_sums, false);
-- 
cgit v1.2.3


From e716edafedad4952fe3a4a273d2e039a84e8681a Mon Sep 17 00:00:00 2001
From: Lee Jones <lee@kernel.org>
Date: Fri, 27 Feb 2026 16:30:25 +0000
Subject: HID: multitouch: Check to ensure report responses match the request

It is possible for a malicious (or clumsy) device to respond to a
specific report's feature request using a completely different report
ID.  This can cause confusion in the HID core resulting in nasty
side-effects such as OOB writes.

Add a check to ensure that the report ID in the response, matches the
one that was requested.  If it doesn't, omit reporting the raw event and
return early.

Signed-off-by: Lee Jones <lee@kernel.org>
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-multitouch.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index b8a748bbf0fd..e82a3c4e5b44 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -526,12 +526,19 @@ static void mt_get_feature(struct hid_device *hdev, struct hid_report *report)
 		dev_warn(&hdev->dev, "failed to fetch feature %d\n",
 			 report->id);
 	} else {
+		/* The report ID in the request and the response should match */
+		if (report->id != buf[0]) {
+			hid_err(hdev, "Returned feature report did not match the request\n");
+			goto free;
+		}
+
 		ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf,
 					   size, 0);
 		if (ret)
 			dev_warn(&hdev->dev, "failed to report feature\n");
 	}
 
+free:
 	kfree(buf);
 }
 
-- 
cgit v1.2.3


From abb863e6213dc41a58ef8bb3289b7e77460dabf3 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Date: Mon, 16 Mar 2026 15:32:45 +0200
Subject: dmaengine: sh: rz-dmac: Protect the driver specific lists

The driver lists (ld_free, ld_queue) are used in
rz_dmac_free_chan_resources(), rz_dmac_terminate_all(),
rz_dmac_issue_pending(), and rz_dmac_irq_handler_thread(), all under
the virtual channel lock. Take the same lock in rz_dmac_prep_slave_sg()
and rz_dmac_prep_dma_memcpy() as well to avoid concurrency issues, since
these functions also check whether the lists are empty and update or
remove list entries.

Fixes: 5000d37042a6 ("dmaengine: sh: Add DMAC driver for RZ/G2L SoC")
Cc: stable@vger.kernel.org
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://patch.msgid.link/20260316133252.240348-2-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/rz-dmac.c | 57 +++++++++++++++++++++++++++---------------------
 1 file changed, 32 insertions(+), 25 deletions(-)

diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index d84ca551b2bf..089e1ab29159 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
@@ -447,6 +448,7 @@ static int rz_dmac_alloc_chan_resources(struct dma_chan *chan)
 		if (!desc)
 			break;
 
+		/* No need to lock. This is called only for the 1st client. */
 		list_add_tail(&desc->node, &channel->ld_free);
 		channel->descs_allocated++;
 	}
@@ -502,18 +504,21 @@ rz_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	dev_dbg(dmac->dev, "%s channel: %d src=0x%pad dst=0x%pad len=%zu\n",
 		__func__, channel->index, &src, &dest, len);
 
-	if (list_empty(&channel->ld_free))
-		return NULL;
+	scoped_guard(spinlock_irqsave, &channel->vc.lock) {
+		if (list_empty(&channel->ld_free))
+			return NULL;
+
+		desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
 
-	desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
+		desc->type = RZ_DMAC_DESC_MEMCPY;
+		desc->src = src;
+		desc->dest = dest;
+		desc->len = len;
+		desc->direction = DMA_MEM_TO_MEM;
 
-	desc->type = RZ_DMAC_DESC_MEMCPY;
-	desc->src = src;
-	desc->dest = dest;
-	desc->len = len;
-	desc->direction = DMA_MEM_TO_MEM;
+		list_move_tail(channel->ld_free.next, &channel->ld_queue);
+	}
 
-	list_move_tail(channel->ld_free.next, &channel->ld_queue);
 	return vchan_tx_prep(&channel->vc, &desc->vd, flags);
 }
 
@@ -529,27 +534,29 @@ rz_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	int dma_length = 0;
 	int i = 0;
 
-	if (list_empty(&channel->ld_free))
-		return NULL;
+	scoped_guard(spinlock_irqsave, &channel->vc.lock) {
+		if (list_empty(&channel->ld_free))
+			return NULL;
 
-	desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
+		desc = list_first_entry(&channel->ld_free, struct rz_dmac_desc, node);
 
-	for_each_sg(sgl, sg, sg_len, i) {
-		dma_length += sg_dma_len(sg);
-	}
+		for_each_sg(sgl, sg, sg_len, i)
+			dma_length += sg_dma_len(sg);
 
-	desc->type = RZ_DMAC_DESC_SLAVE_SG;
-	desc->sg = sgl;
-	desc->sgcount = sg_len;
-	desc->len = dma_length;
-	desc->direction = direction;
+		desc->type = RZ_DMAC_DESC_SLAVE_SG;
+		desc->sg = sgl;
+		desc->sgcount = sg_len;
+		desc->len = dma_length;
+		desc->direction = direction;
 
-	if (direction == DMA_DEV_TO_MEM)
-		desc->src = channel->src_per_address;
-	else
-		desc->dest = channel->dst_per_address;
+		if (direction == DMA_DEV_TO_MEM)
+			desc->src = channel->src_per_address;
+		else
+			desc->dest = channel->dst_per_address;
+
+		list_move_tail(channel->ld_free.next, &channel->ld_queue);
+	}
 
-	list_move_tail(channel->ld_free.next, &channel->ld_queue);
 	return vchan_tx_prep(&channel->vc, &desc->vd, flags);
 }
 
-- 
cgit v1.2.3


From 89a8567d84bde88cb7cdbbac2ab2299c4f991490 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Date: Mon, 16 Mar 2026 15:32:46 +0200
Subject: dmaengine: sh: rz-dmac: Move CHCTRL updates under spinlock

Both rz_dmac_disable_hw() and rz_dmac_irq_handle_channel() update the
CHCTRL register. To avoid concurrency issues when configuring
functionalities exposed by this registers, take the virtual channel lock.
All other CHCTRL updates were already protected by the same lock.

Previously, rz_dmac_disable_hw() disabled and re-enabled local IRQs, before
accessing CHCTRL registers but this does not ensure race-free access.
Remove the local IRQ disable/enable code as well.

Fixes: 5000d37042a6 ("dmaengine: sh: Add DMAC driver for RZ/G2L SoC")
Cc: stable@vger.kernel.org
Reviewed-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://patch.msgid.link/20260316133252.240348-3-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/sh/rz-dmac.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 089e1ab29159..f30bdf69c740 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -297,13 +297,10 @@ static void rz_dmac_disable_hw(struct rz_dmac_chan *channel)
 {
 	struct dma_chan *chan = &channel->vc.chan;
 	struct rz_dmac *dmac = to_rz_dmac(chan->device);
-	unsigned long flags;
 
 	dev_dbg(dmac->dev, "%s channel %d\n", __func__, channel->index);
 
-	local_irq_save(flags);
 	rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
-	local_irq_restore(flags);
 }
 
 static void rz_dmac_set_dmars_register(struct rz_dmac *dmac, int nr, u32 dmars)
@@ -568,8 +565,8 @@ static int rz_dmac_terminate_all(struct dma_chan *chan)
 	unsigned int i;
 	LIST_HEAD(head);
 
-	rz_dmac_disable_hw(channel);
 	spin_lock_irqsave(&channel->vc.lock, flags);
+	rz_dmac_disable_hw(channel);
 	for (i = 0; i < DMAC_NR_LMDESC; i++)
 		lmdesc[i].header = 0;
 
@@ -706,7 +703,9 @@ static void rz_dmac_irq_handle_channel(struct rz_dmac_chan *channel)
 	if (chstat & CHSTAT_ER) {
 		dev_err(dmac->dev, "DMAC err CHSTAT_%d = %08X\n",
 			channel->index, chstat);
-		rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
+
+		scoped_guard(spinlock_irqsave, &channel->vc.lock)
+			rz_dmac_ch_writel(channel, CHCTRL_DEFAULT, CHCTRL, 1);
 		goto done;
 	}
 
-- 
cgit v1.2.3


From f9a4e3015db1aeafbef407650eb8555445ca943e Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 13 Feb 2026 16:08:53 +0000
Subject: btrfs: reserve enough transaction items for qgroup ioctls

Currently our qgroup ioctls don't reserve any space, they just do a
transaction join, which does not reserve any space, neither for the quota
tree updates nor for the delayed refs generated when updating the quota
tree. The quota root uses the global block reserve, which is fine most of
the time since we don't expect a lot of updates to the quota root, or to
be too close to -ENOSPC such that other critical metadata updates need to
resort to the global reserve.

However this is not optimal, as not reserving proper space may result in a
transaction abort due to not reserving space for delayed refs and then
abusing the use of the global block reserve.

For example, the following reproducer (which is unlikely to model any
real world use case, but just to illustrate the problem), triggers such a
transaction abort due to -ENOSPC when running delayed refs:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/nullb0
  MNT=/mnt/nullb0

  umount $DEV &> /dev/null
  # Limit device to 1G so that it's much faster to reproduce the issue.
  mkfs.btrfs -f -b 1G $DEV
  mount -o commit=600 $DEV $MNT

  fallocate -l 800M $MNT/filler
  btrfs quota enable $MNT

  for ((i = 1; i <= 400000; i++)); do
      btrfs qgroup create 1/$i $MNT
  done

  umount $MNT

When running this, we can see in dmesg/syslog that a transaction abort
happened:

  [436.490] BTRFS error (device nullb0): failed to run delayed ref for logical 30408704 num_bytes 16384 type 176 action 1 ref_mod 1: -28
  [436.493] ------------[ cut here ]------------
  [436.494] BTRFS: Transaction aborted (error -28)
  [436.495] WARNING: fs/btrfs/extent-tree.c:2247 at btrfs_run_delayed_refs+0xd9/0x110 [btrfs], CPU#4: umount/2495372
  [436.497] Modules linked in: btrfs loop (...)
  [436.508] CPU: 4 UID: 0 PID: 2495372 Comm: umount Tainted: G        W           6.19.0-rc8-btrfs-next-225+ #1 PREEMPT(full)
  [436.510] Tainted: [W]=WARN
  [436.511] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-0-gea1b7a073390-prebuilt.qemu.org 04/01/2014
  [436.513] RIP: 0010:btrfs_run_delayed_refs+0xdf/0x110 [btrfs]
  [436.514] Code: 0f 82 ea (...)
  [436.518] RSP: 0018:ffffd511850b7d78 EFLAGS: 00010292
  [436.519] RAX: 00000000ffffffe4 RBX: ffff8f120dad37e0 RCX: 0000000002040001
  [436.520] RDX: 0000000000000002 RSI: 00000000ffffffe4 RDI: ffffffffc090fd80
  [436.522] RBP: 0000000000000000 R08: 0000000000000001 R09: ffffffffc04d1867
  [436.523] R10: ffff8f18dc1fffa8 R11: 0000000000000003 R12: ffff8f173aa89400
  [436.524] R13: 0000000000000000 R14: ffff8f173aa89400 R15: 0000000000000000
  [436.526] FS:  00007fe59045d840(0000) GS:ffff8f192e22e000(0000) knlGS:0000000000000000
  [436.527] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [436.528] CR2: 00007fe5905ff2b0 CR3: 000000060710a002 CR4: 0000000000370ef0
  [436.530] Call Trace:
  [436.530]  <TASK>
  [436.530]  btrfs_commit_transaction+0x73/0xc00 [btrfs]
  [436.531]  ? btrfs_attach_transaction_barrier+0x1e/0x70 [btrfs]
  [436.532]  sync_filesystem+0x7a/0x90
  [436.533]  generic_shutdown_super+0x28/0x180
  [436.533]  kill_anon_super+0x12/0x40
  [436.534]  btrfs_kill_super+0x12/0x20 [btrfs]
  [436.534]  deactivate_locked_super+0x2f/0xb0
  [436.534]  cleanup_mnt+0xea/0x180
  [436.535]  task_work_run+0x58/0xa0
  [436.535]  exit_to_user_mode_loop+0xed/0x480
  [436.536]  ? __x64_sys_umount+0x68/0x80
  [436.536]  do_syscall_64+0x2a5/0xf20
  [436.537]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [436.537] RIP: 0033:0x7fe5906b6217
  [436.538] Code: 0d 00 f7 (...)
  [436.540] RSP: 002b:00007ffcd87a61f8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
  [436.541] RAX: 0000000000000000 RBX: 00005618b9ecadc8 RCX: 00007fe5906b6217
  [436.541] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00005618b9ecb100
  [436.542] RBP: 0000000000000000 R08: 00007ffcd87a4fe0 R09: 00000000ffffffff
  [436.544] R10: 0000000000000103 R11: 0000000000000246 R12: 00007fe59081626c
  [436.544] R13: 00005618b9ecb100 R14: 0000000000000000 R15: 00005618b9ecacc0
  [436.545]  </TASK>
  [436.545] ---[ end trace 0000000000000000 ]---

Fix this by changing the qgroup ioctls to use start transaction instead of
joining so that proper space is reserved for the delayed refs generated
for the updates to the quota root. This way we don't get any transaction
abort.

Reviewed-by: Boris Burkov <boris@bur.io>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7d86e9c8909e..7d1e3f41dc7d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3687,7 +3687,8 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 		}
 	}
 
-	trans = btrfs_join_transaction(root);
+	/* 2 BTRFS_QGROUP_RELATION_KEY items. */
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out;
@@ -3759,7 +3760,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	trans = btrfs_join_transaction(root);
+	/*
+	 * 1 BTRFS_QGROUP_INFO_KEY item.
+	 * 1 BTRFS_QGROUP_LIMIT_KEY item.
+	 */
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out;
@@ -3808,7 +3813,8 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		goto drop_write;
 	}
 
-	trans = btrfs_join_transaction(root);
+	/* 1 BTRFS_QGROUP_LIMIT_KEY item. */
+	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto out;
-- 
cgit v1.2.3


From 65ee6061388b334c341fd37c22ec9149417f6ccf Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 19 Feb 2026 18:51:11 +1030
Subject: btrfs: fix a bug that makes encoded write bio larger than expected

[BUG]
When running btrfs/284 with 64K page size and 4K fs block size, the
following ASSERT() can be triggered:

  assertion failed: cb->bbio.bio.bi_iter.bi_size == disk_num_bytes :: 0, in inode.c:9991
  ------------[ cut here ]------------
  kernel BUG at inode.c:9991!
  Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
  CPU: 5 UID: 0 PID: 6787 Comm: btrfs Tainted: G           OE       6.19.0-rc8-custom+ #1 PREEMPT(voluntary)
  Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
  pc : btrfs_do_encoded_write+0x9b0/0x9c0 [btrfs]
  lr : btrfs_do_encoded_write+0x9b0/0x9c0 [btrfs]
  Call trace:
   btrfs_do_encoded_write+0x9b0/0x9c0 [btrfs] (P)
   btrfs_do_write_iter+0x1d8/0x208 [btrfs]
   btrfs_ioctl_encoded_write+0x3c8/0x6d0 [btrfs]
   btrfs_ioctl+0xeb0/0x2b60 [btrfs]
   __arm64_sys_ioctl+0xac/0x110
   invoke_syscall.constprop.0+0x64/0xe8
   el0_svc_common.constprop.0+0x40/0xe8
   do_el0_svc+0x24/0x38
   el0_svc+0x3c/0x1b8
   el0t_64_sync_handler+0xa0/0xe8
   el0t_64_sync+0x1a4/0x1a8
  Code: 91180021 90001080 9111a000 94039d54 (d4210000)
  ---[ end trace 0000000000000000 ]---

[CAUSE]
After commit e1bc83f8b157 ("btrfs: get rid of compressed_folios[] usage
for encoded writes"), the encoded write is changed to copy the content
from the iov into a folio, and queue the folio into the compressed bio.

However we always queue the full folio into the compressed bio, which
can make the compressed bio larger than the on-disk extent, if the folio
size is larger than the fs block size.

Although we have an ASSERT() to catch such problem, for kernels without
CONFIG_BTRFS_ASSERT, such larger than expected bio will just be
submitted, possibly overwrite the next data extent, causing data
corruption.

[FIX]
Instead of blindly queuing the full folio into the compressed bio, only
queue the rounded up range, which is the old behavior before that
offending commit.
This also means we no longer need to zero the tailing range until the
folio end (but still to the block boundary), as such range will not be
submitted anyway.

And since we're here, add a final ASSERT() into
btrfs_submit_compressed_write() as the last safety net for kernels with
btrfs assertions enabled

Fixes: e1bc83f8b157 ("btrfs: get rid of compressed_folios[] usage for encoded writes")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 1 +
 fs/btrfs/inode.c       | 7 ++++---
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1e7174ad32e2..ac995ec78e05 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -324,6 +324,7 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
 
 	cb->start = ordered->file_offset;
 	cb->len = ordered->num_bytes;
+	ASSERT(cb->bbio.bio.bi_iter.bi_size == ordered->disk_num_bytes);
 	cb->compressed_len = ordered->disk_num_bytes;
 	cb->bbio.bio.bi_iter.bi_sector = ordered->disk_bytenr >> SECTOR_SHIFT;
 	cb->bbio.ordered = ordered;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ed4d19780f22..8abfe8f0f2d4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9889,6 +9889,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	int compression;
 	size_t orig_count;
 	const u32 min_folio_size = btrfs_min_folio_size(fs_info);
+	const u32 blocksize = fs_info->sectorsize;
 	u64 start, end;
 	u64 num_bytes, ram_bytes, disk_num_bytes;
 	struct btrfs_key ins;
@@ -9999,9 +10000,9 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 			ret = -EFAULT;
 			goto out_cb;
 		}
-		if (bytes < min_folio_size)
-			folio_zero_range(folio, bytes, min_folio_size - bytes);
-		ret = bio_add_folio(&cb->bbio.bio, folio, folio_size(folio), 0);
+		if (!IS_ALIGNED(bytes, blocksize))
+			folio_zero_range(folio, bytes, round_up(bytes, blocksize) - bytes);
+		ret = bio_add_folio(&cb->bbio.bio, folio, round_up(bytes, blocksize), 0);
 		if (unlikely(!ret)) {
 			folio_put(folio);
 			ret = -EINVAL;
-- 
cgit v1.2.3


From 3adf8f14152fba1cae51f9b0d3570a1da2153b16 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 19 Feb 2026 18:51:12 +1030
Subject: btrfs: do not touch page cache for encoded writes

[BUG]
When running btrfs/284, the following ASSERT() will be triggered with
64K page size and 4K fs block size:

  assertion failed: folio_test_writeback(folio) :: 0, in subpage.c:476
  ------------[ cut here ]------------
  kernel BUG at subpage.c:476!
  Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
  CPU: 4 UID: 0 PID: 2313 Comm: kworker/u37:2 Tainted: G           OE       6.19.0-rc8-custom+ #185 PREEMPT(voluntary)
  Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
  Workqueue: btrfs-endio simple_end_io_work [btrfs]
  pc : btrfs_subpage_clear_writeback+0x148/0x160 [btrfs]
  lr : btrfs_subpage_clear_writeback+0x148/0x160 [btrfs]
  Call trace:
   btrfs_subpage_clear_writeback+0x148/0x160 [btrfs] (P)
   btrfs_folio_clamp_clear_writeback+0xb4/0xd0 [btrfs]
   end_compressed_writeback+0xe0/0x1e0 [btrfs]
   end_bbio_compressed_write+0x1e8/0x218 [btrfs]
   btrfs_bio_end_io+0x108/0x258 [btrfs]
   simple_end_io_work+0x68/0xa8 [btrfs]
   process_one_work+0x168/0x3f0
   worker_thread+0x25c/0x398
   kthread+0x154/0x250
   ret_from_fork+0x10/0x20
  ---[ end trace 0000000000000000 ]---

[CAUSE]
The offending bio is from an encoded write, where the compressed data is
directly written as a data extent, without touching the page cache.

However the encoded write still utilizes the regular buffered write path
for compressed data, by setting the compressed_bio::writeback flag.

When that flag is set, at end_bbio_compressed_write() btrfs will go
clearing the writeback flag of the folios in the page cache.

However for bs < ps cases, the subpage helper has one extra check to make
sure the folio has a writeback flag set in the first place.

But since it's an encoded write, we never go through page
cache, thus the folio has no writeback flag and triggers the ASSERT().

[FIX]
Do not set compressed_bio::writeback flag for encoded writes, and change
the ASSERT() in btrfs_submit_compressed_write() to make sure that flag
is not set.

Fixes: e1bc83f8b157 ("btrfs: get rid of compressed_folios[] usage for encoded writes")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ac995ec78e05..dc61f7e3cbbf 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -320,7 +320,12 @@ void btrfs_submit_compressed_write(struct btrfs_ordered_extent *ordered,
 
 	ASSERT(IS_ALIGNED(ordered->file_offset, fs_info->sectorsize));
 	ASSERT(IS_ALIGNED(ordered->num_bytes, fs_info->sectorsize));
-	ASSERT(cb->writeback);
+	/*
+	 * This flag determines if we should clear the writeback flag from the
+	 * page cache. But this function is only utilized by encoded writes, it
+	 * never goes through the page cache.
+	 */
+	ASSERT(!cb->writeback);
 
 	cb->start = ordered->file_offset;
 	cb->len = ordered->num_bytes;
@@ -346,8 +351,7 @@ struct compressed_bio *btrfs_alloc_compressed_write(struct btrfs_inode *inode,
 	cb = alloc_compressed_bio(inode, start, REQ_OP_WRITE, end_bbio_compressed_write);
 	cb->start = start;
 	cb->len = len;
-	cb->writeback = true;
-
+	cb->writeback = false;
 	return cb;
 }
 
-- 
cgit v1.2.3


From 96a2d235896b53291efc6d5c3de030e570f77070 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 19 Feb 2026 18:51:13 +1030
Subject: btrfs: fix an incorrect ASSERT() condition inside
 zstd_decompress_bio()

[BUG]
When running btrfs/284 with 64K page size and 4K fs block size, it
crashes with the following ASSERT() triggered:

  assertion failed: folio_size(fi.folio) == blocksize :: 0, in fs/btrfs/zstd.c:603
  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/zstd.c:603!
  Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
  CPU: 2 UID: 0 PID: 1183 Comm: kworker/u35:4 Not tainted 6.19.0-rc8-custom+ #185 PREEMPT(voluntary)
  Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
  Workqueue: btrfs-endio simple_end_io_work [btrfs]
  pc : zstd_decompress_bio+0x4f0/0x508 [btrfs]
  lr : zstd_decompress_bio+0x4f0/0x508 [btrfs]
  Call trace:
   zstd_decompress_bio+0x4f0/0x508 [btrfs] (P)
   end_bbio_compressed_read+0x260/0x2c0 [btrfs]
   btrfs_bio_end_io+0xc4/0x258 [btrfs]
   btrfs_check_read_bio+0x424/0x7e0 [btrfs]
   simple_end_io_work+0x40/0xa8 [btrfs]
   process_one_work+0x168/0x3f0
   worker_thread+0x25c/0x398
   kthread+0x154/0x250
   ret_from_fork+0x10/0x20
  ---[ end trace 0000000000000000 ]---

[CAUSE]
Commit 1914b94231e9 ("btrfs: zstd: use folio_iter to handle
zstd_decompress_bio()") added the ASSERT() to make sure the folio size
matches the fs block size.

But the check is completely wrong, the original intention is to make
sure for bs > ps cases, we always got a large folio that covers a full fs
block.

However for bs < ps cases, a folio can never be smaller than page size,
and the ASSERT() gets triggered immediately.

[FIX]
Check the folio size against @min_folio_size instead, which will never
be smaller than PAGE_SIZE, and still cover bs > ps cases.

Fixes: 1914b94231e9 ("btrfs: zstd: use folio_iter to handle zstd_decompress_bio()")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zstd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 32fd7f5454d3..c002d18666b7 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -600,7 +600,7 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	bio_first_folio(&fi, &cb->bbio.bio, 0);
 	if (unlikely(!fi.folio))
 		return -EINVAL;
-	ASSERT(folio_size(fi.folio) == blocksize);
+	ASSERT(folio_size(fi.folio) == min_folio_size);
 
 	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
-- 
cgit v1.2.3


From 5118130e722b1261a2e92b2fb0b067463c39ecc7 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 19 Feb 2026 18:51:14 +1030
Subject: btrfs: fix an incorrect ASSERT() condition inside
 lzo_decompress_bio()

[BUG]
When running btrfs/284 with 64K page size and 4K fs block size, it
crashes with the following ASSERT() triggered:

  BTRFS info (device dm-3): use lzo compression, level 1
  assertion failed: folio_size(fi.folio) == sectorsize :: 0, in lzo.c:450
  ------------[ cut here ]------------
  kernel BUG at lzo.c:450!
  Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
  CPU: 4 UID: 0 PID: 329 Comm: kworker/u37:2 Tainted: G           OE       6.19.0-rc8-custom+ #185 PREEMPT(voluntary)
  Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
  Workqueue: btrfs-endio simple_end_io_work [btrfs]
  pc : lzo_decompress_bio+0x61c/0x630 [btrfs]
  lr : lzo_decompress_bio+0x61c/0x630 [btrfs]
  Call trace:
   lzo_decompress_bio+0x61c/0x630 [btrfs] (P)
   end_bbio_compressed_read+0x2a8/0x2c0 [btrfs]
   btrfs_bio_end_io+0xc4/0x258 [btrfs]
   btrfs_check_read_bio+0x424/0x7e0 [btrfs]
   simple_end_io_work+0x40/0xa8 [btrfs]
   process_one_work+0x168/0x3f0
   worker_thread+0x25c/0x398
   kthread+0x154/0x250
   ret_from_fork+0x10/0x20
  Code: 912a2021 b0000e00 91246000 940244e9 (d4210000)
  ---[ end trace 0000000000000000 ]---

[CAUSE]
Commit 37cc07cab7dc ("btrfs: lzo: use folio_iter to handle
lzo_decompress_bio()") added the ASSERT() to make sure the folio size
matches the fs block size.

But the check is completely wrong, the original intention is to make
sure for bs > ps cases, we always got a large folio that covers a full fs
block.

However for bs < ps cases, a folio can never be smaller than page size,
and the ASSERT() gets triggered immediately.

[FIX]
Check the folio size against @min_folio_size instead, which will never
be smaller than PAGE_SIZE, and still cover bs > ps cases.

Fixes: 37cc07cab7dc ("btrfs: lzo: use folio_iter to handle lzo_decompress_bio()")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/lzo.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 8e20497afffe..971c2ea98e18 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -429,7 +429,7 @@ static void copy_compressed_segment(struct compressed_bio *cb,
 int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	const struct btrfs_fs_info *fs_info = cb->bbio.inode->root->fs_info;
+	struct btrfs_fs_info *fs_info = cb->bbio.inode->root->fs_info;
 	const u32 sectorsize = fs_info->sectorsize;
 	struct folio_iter fi;
 	char *kaddr;
@@ -447,7 +447,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	/* There must be a compressed folio and matches the sectorsize. */
 	if (unlikely(!fi.folio))
 		return -EINVAL;
-	ASSERT(folio_size(fi.folio) == sectorsize);
+	ASSERT(folio_size(fi.folio) == btrfs_min_folio_size(fs_info));
 	kaddr = kmap_local_folio(fi.folio, 0);
 	len_in = read_compress_length(kaddr);
 	kunmap_local(kaddr);
-- 
cgit v1.2.3


From 057495ccc0ad381015b45d3edf995c2b6b982474 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 17:03:53 +0000
Subject: btrfs: hold block group reference during entire move_existing_remap()

There is a potential use-after-free in move_existing_remap(): we're calling
btrfs_put_block_group() on dest_bg, then passing it to
btrfs_add_block_group_free_space() a few lines later.

Fix this by getting the BG at the start of the function and putting it
near the end. This also means we're not doing a lookup twice for the
same thing.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125123908.2096548-1-clm@meta.com/
Fixes: bbea42dfb91f ("btrfs: move existing remaps before relocating block group")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 2625a66054d0..0f61bdf7f5d1 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4185,6 +4185,8 @@ static int move_existing_remap(struct btrfs_fs_info *fs_info,
 	dest_addr = ins.objectid;
 	dest_length = ins.offset;
 
+	dest_bg = btrfs_lookup_block_group(fs_info, dest_addr);
+
 	if (!is_data && !IS_ALIGNED(dest_length, fs_info->nodesize)) {
 		u64 new_length = ALIGN_DOWN(dest_length, fs_info->nodesize);
 
@@ -4295,15 +4297,12 @@ static int move_existing_remap(struct btrfs_fs_info *fs_info,
 	if (unlikely(ret))
 		goto end;
 
-	dest_bg = btrfs_lookup_block_group(fs_info, dest_addr);
-
 	adjust_block_group_remap_bytes(trans, dest_bg, dest_length);
 
 	mutex_lock(&dest_bg->free_space_lock);
 	bg_needs_free_space = test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE,
 				       &dest_bg->runtime_flags);
 	mutex_unlock(&dest_bg->free_space_lock);
-	btrfs_put_block_group(dest_bg);
 
 	if (bg_needs_free_space) {
 		ret = btrfs_add_block_group_free_space(trans, dest_bg);
@@ -4333,13 +4332,13 @@ end:
 			btrfs_end_transaction(trans);
 		}
 	} else {
-		dest_bg = btrfs_lookup_block_group(fs_info, dest_addr);
 		btrfs_free_reserved_bytes(dest_bg, dest_length, 0);
-		btrfs_put_block_group(dest_bg);
 
 		ret = btrfs_commit_transaction(trans);
 	}
 
+	btrfs_put_block_group(dest_bg);
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From adbb0ebacc3223a2dc2e58ef3d4c10f5e9653f09 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Thu, 19 Feb 2026 19:19:00 +0000
Subject: btrfs: check block group before marking it unused in
 balance_remap_chunks()

Fix a potential segfault in balance_remap_chunks(): if we quit early
because btrfs_inc_block_group_ro() fails, all the remaining items in the
chunks list will still have their bg value set to NULL. It's thus not
safe to dereference this pointer without checking first.

Reported-by: Chris Mason <clm@fb.com>
Link: https://lore.kernel.org/linux-btrfs/20260125120717.1578828-1-clm@meta.com/
Fixes: 81e5a4551c32 ("btrfs: allow balancing remap tree")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 7efc2f7a9bb2..8fbd736aad9f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4277,20 +4277,29 @@ static int balance_remap_chunks(struct btrfs_fs_info *fs_info, struct btrfs_path
 end:
 	while (!list_empty(chunks)) {
 		bool is_unused;
+		struct btrfs_block_group *bg;
 
 		rci = list_first_entry(chunks, struct remap_chunk_info, list);
 
-		spin_lock(&rci->bg->lock);
-		is_unused = !btrfs_is_block_group_used(rci->bg);
-		spin_unlock(&rci->bg->lock);
+		bg = rci->bg;
+		if (bg) {
+			/*
+			 * This is a bit racy and the 'used' status can change
+			 * but this is not a problem as later functions will
+			 * verify it again.
+			 */
+			spin_lock(&bg->lock);
+			is_unused = !btrfs_is_block_group_used(bg);
+			spin_unlock(&bg->lock);
 
-		if (is_unused)
-			btrfs_mark_bg_unused(rci->bg);
+			if (is_unused)
+				btrfs_mark_bg_unused(bg);
 
-		if (rci->made_ro)
-			btrfs_dec_block_group_ro(rci->bg);
+			if (rci->made_ro)
+				btrfs_dec_block_group_ro(bg);
 
-		btrfs_put_block_group(rci->bg);
+			btrfs_put_block_group(bg);
+		}
 
 		list_del(&rci->list);
 		kfree(rci);
-- 
cgit v1.2.3


From b17b79ff896305fd74980a5f72afec370ee88ca4 Mon Sep 17 00:00:00 2001
From: ZhengYuan Huang <gality369@gmail.com>
Date: Thu, 12 Mar 2026 08:14:43 +0800
Subject: btrfs: reject root items with drop_progress and zero drop_level

[BUG]
When recovering relocation at mount time, merge_reloc_root() and
btrfs_drop_snapshot() both use BUG_ON(level == 0) to guard against
an impossible state: a non-zero drop_progress combined with a zero
drop_level in a root_item, which can be triggered:

------------[ cut here ]------------
kernel BUG at fs/btrfs/relocation.c:1545!
Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
CPU: 1 UID: 0 PID: 283 ... Tainted: 6.18.0+ #16 PREEMPT(voluntary)
Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
Hardware name: QEMU Ubuntu 24.04 PC v2, BIOS 1.16.3-debian-1.16.3-2
RIP: 0010:merge_reloc_root+0x1266/0x1650 fs/btrfs/relocation.c:1545
Code: ffff0000 00004589 d7e9acfa ffffe8a1 79bafebe 02000000
Call Trace:
 merge_reloc_roots+0x295/0x890 fs/btrfs/relocation.c:1861
 btrfs_recover_relocation+0xd6e/0x11d0 fs/btrfs/relocation.c:4195
 btrfs_start_pre_rw_mount+0xa4d/0x1810 fs/btrfs/disk-io.c:3130
 open_ctree+0x5824/0x5fe0 fs/btrfs/disk-io.c:3640
 btrfs_fill_super fs/btrfs/super.c:987 [inline]
 btrfs_get_tree_super fs/btrfs/super.c:1951 [inline]
 btrfs_get_tree_subvol fs/btrfs/super.c:2094 [inline]
 btrfs_get_tree+0x111c/0x2190 fs/btrfs/super.c:2128
 vfs_get_tree+0x9a/0x370 fs/super.c:1758
 fc_mount fs/namespace.c:1199 [inline]
 do_new_mount_fc fs/namespace.c:3642 [inline]
 do_new_mount fs/namespace.c:3718 [inline]
 path_mount+0x5b8/0x1ea0 fs/namespace.c:4028
 do_mount fs/namespace.c:4041 [inline]
 __do_sys_mount fs/namespace.c:4229 [inline]
 __se_sys_mount fs/namespace.c:4206 [inline]
 __x64_sys_mount+0x282/0x320 fs/namespace.c:4206
 ...
RIP: 0033:0x7f969c9a8fde
Code: 0f1f4000 48c7c2b0 fffffff7 d8648902 b8ffffff ffc3660f
---[ end trace 0000000000000000 ]---

The bug is reproducible on 7.0.0-rc2-next-20260310 with our dynamic
metadata fuzzing tool that corrupts btrfs metadata at runtime.

[CAUSE]
A non-zero drop_progress.objectid means an interrupted
btrfs_drop_snapshot() left a resume point on disk, and in that case
drop_level must be greater than 0 because the checkpoint is only
saved at internal node levels.

Although this invariant is enforced when the kernel writes the root
item, it is not validated when the root item is read back from disk.
That allows on-disk corruption to provide an invalid state with
drop_progress.objectid != 0 and drop_level == 0.

When relocation recovery later processes such a root item,
merge_reloc_root() reads drop_level and hits BUG_ON(level == 0). The
same invalid metadata can also trigger the corresponding BUG_ON() in
btrfs_drop_snapshot().

[FIX]
Fix this by validating the root_item invariant in tree-checker when
reading root items from disk: if drop_progress.objectid is non-zero,
drop_level must also be non-zero. Reject such malformed metadata with
-EUCLEAN before it reaches merge_reloc_root() or btrfs_drop_snapshot()
and triggers the BUG_ON.

After the fix, the same corruption is correctly rejected by tree-checker
and the BUG_ON is no longer triggered.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: ZhengYuan Huang <gality369@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 516ef62c8f43..b4e114efff45 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1288,6 +1288,23 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
 			    btrfs_root_drop_level(&ri), BTRFS_MAX_LEVEL - 1);
 		return -EUCLEAN;
 	}
+	/*
+	 * If drop_progress.objectid is non-zero, a btrfs_drop_snapshot() was
+	 * interrupted and the resume point was recorded in drop_progress and
+	 * drop_level.  In that case drop_level must be >= 1: level 0 is the
+	 * leaf level and drop_snapshot never saves a checkpoint there (it
+	 * only records checkpoints at internal node levels in DROP_REFERENCE
+	 * stage).  A zero drop_level combined with a non-zero drop_progress
+	 * objectid indicates on-disk corruption and would cause a BUG_ON in
+	 * merge_reloc_root() and btrfs_drop_snapshot() at mount time.
+	 */
+	if (unlikely(btrfs_disk_key_objectid(&ri.drop_progress) != 0 &&
+		     btrfs_root_drop_level(&ri) == 0)) {
+		generic_err(leaf, slot,
+			    "invalid root drop_level 0 with non-zero drop_progress objectid %llu",
+			    btrfs_disk_key_objectid(&ri.drop_progress));
+		return -EUCLEAN;
+	}
 
 	/* Flags check */
 	if (unlikely(btrfs_root_flags(&ri) & ~valid_root_flags)) {
-- 
cgit v1.2.3


From d849a2f7309fc0616e79d13b008b0a47e0458b6e Mon Sep 17 00:00:00 2001
From: Paul Moses <p@1g4.org>
Date: Mon, 16 Mar 2026 14:56:51 +0000
Subject: xfrm: iptfs: only publish mode_data after clone setup

iptfs_clone_state() stores x->mode_data before allocating the reorder
window. If that allocation fails, the code frees the cloned state and
returns -ENOMEM, leaving x->mode_data pointing at freed memory.

The xfrm clone unwind later runs destroy_state() through x->mode_data,
so the failed clone path tears down IPTFS state that clone_state()
already freed.

Keep the cloned IPTFS state private until all allocations succeed so
failed clones leave x->mode_data unset. The destroy path already
handles a NULL mode_data pointer.

Fixes: 6be02e3e4f37 ("xfrm: iptfs: handle reordering of received packets")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Moses <p@1g4.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_iptfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c
index 2c87290fe06c..7cd97c1dcd11 100644
--- a/net/xfrm/xfrm_iptfs.c
+++ b/net/xfrm/xfrm_iptfs.c
@@ -2664,9 +2664,6 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig)
 	if (!xtfs)
 		return -ENOMEM;
 
-	x->mode_data = xtfs;
-	xtfs->x = x;
-
 	xtfs->ra_newskb = NULL;
 	if (xtfs->cfg.reorder_win_size) {
 		xtfs->w_saved = kcalloc(xtfs->cfg.reorder_win_size,
@@ -2677,6 +2674,9 @@ static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig)
 		}
 	}
 
+	x->mode_data = xtfs;
+	xtfs->x = x;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From e9cc95397bb7da13fe8a5b53a2f23cfaf9018ade Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@nabladev.com>
Date: Mon, 16 Mar 2026 23:16:54 +0100
Subject: dmaengine: xilinx: xilinx_dma: Fix dma_device directions

Unlike chan->direction , struct dma_device .directions field is a
bitfield. Turn chan->direction into a bitfield to make it compatible
with struct dma_device .directions .

Fixes: 7e01511443c3 ("dmaengine: xilinx_dma: Set dma_device directions")
Signed-off-by: Marek Vasut <marex@nabladev.com>
Link: https://patch.msgid.link/20260316221728.160139-1-marex@nabladev.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index b53292e02448..bbecf18b04ac 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -3024,7 +3024,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		return -EINVAL;
 	}
 
-	xdev->common.directions |= chan->direction;
+	xdev->common.directions |= BIT(chan->direction);
 
 	/* Request the interrupt */
 	chan->irq = of_irq_get(node, chan->tdest);
-- 
cgit v1.2.3


From f61d145999d61948a23cd436ebbfa4c3b9ab8987 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@nabladev.com>
Date: Mon, 16 Mar 2026 23:18:57 +0100
Subject: dmaengine: xilinx: xilinx_dma: Fix residue calculation for cyclic DMA

The cyclic DMA calculation is currently entirely broken and reports
residue only for the first segment. The problem is twofold.

First, when the first descriptor finishes, it is moved from active_list
to done_list, but it is never returned back into the active_list. The
xilinx_dma_tx_status() expects the descriptor to be in the active_list
to report any meaningful residue information, which never happens after
the first descriptor finishes. Fix this up in xilinx_dma_start_transfer()
and if the descriptor is cyclic, lift it from done_list and place it back
into active_list list.

Second, the segment .status fields of the descriptor remain dirty. Once
the DMA did one pass on the descriptor, the .status fields are populated
with data by the DMA, but the .status fields are not cleared before reuse
during the next cyclic DMA round. The xilinx_dma_get_residue() recognizes
that as if the descriptor was complete and had 0 residue, which is bogus.
Reinitialize the status field before placing the descriptor back into the
active_list.

Fixes: c0bba3a99f07 ("dmaengine: vdma: Add Support for Xilinx AXI Direct Memory Access Engine")
Signed-off-by: Marek Vasut <marex@nabladev.com>
Link: https://patch.msgid.link/20260316221943.160375-1-marex@nabladev.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dma.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index bbecf18b04ac..9dd5d7388e1d 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -1564,8 +1564,29 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 	if (chan->err)
 		return;
 
-	if (list_empty(&chan->pending_list))
+	if (list_empty(&chan->pending_list)) {
+		if (chan->cyclic) {
+			struct xilinx_dma_tx_descriptor *desc;
+			struct list_head *entry;
+
+			desc = list_last_entry(&chan->done_list,
+					       struct xilinx_dma_tx_descriptor, node);
+			list_for_each(entry, &desc->segments) {
+				struct xilinx_axidma_tx_segment *axidma_seg;
+				struct xilinx_axidma_desc_hw *axidma_hw;
+				axidma_seg = list_entry(entry,
+							struct xilinx_axidma_tx_segment,
+							node);
+				axidma_hw = &axidma_seg->hw;
+				axidma_hw->status = 0;
+			}
+
+			list_splice_tail_init(&chan->done_list, &chan->active_list);
+			chan->desc_pendingcount = 0;
+			chan->idle = false;
+		}
 		return;
+	}
 
 	if (!chan->idle)
 		return;
-- 
cgit v1.2.3


From c7d812e33f3e8ca0fa9eeabf71d1c7bc3acedc09 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@nabladev.com>
Date: Mon, 16 Mar 2026 23:25:24 +0100
Subject: dmaengine: xilinx: xilinx_dma: Fix unmasked residue subtraction

The segment .control and .status fields both contain top bits which are
not part of the buffer size, the buffer size is located only in the bottom
max_buffer_len bits. To avoid interference from those top bits, mask out
the size using max_buffer_len first, and only then subtract the values.

Fixes: a575d0b4e663 ("dmaengine: xilinx_dma: Introduce xilinx_dma_get_residue")
Signed-off-by: Marek Vasut <marex@nabladev.com>
Link: https://patch.msgid.link/20260316222530.163815-1-marex@nabladev.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dma.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 9dd5d7388e1d..969343342e86 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -997,16 +997,16 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan,
 					      struct xilinx_cdma_tx_segment,
 					      node);
 			cdma_hw = &cdma_seg->hw;
-			residue += (cdma_hw->control - cdma_hw->status) &
-				   chan->xdev->max_buffer_len;
+			residue += (cdma_hw->control & chan->xdev->max_buffer_len) -
+			           (cdma_hw->status & chan->xdev->max_buffer_len);
 		} else if (chan->xdev->dma_config->dmatype ==
 			   XDMA_TYPE_AXIDMA) {
 			axidma_seg = list_entry(entry,
 						struct xilinx_axidma_tx_segment,
 						node);
 			axidma_hw = &axidma_seg->hw;
-			residue += (axidma_hw->control - axidma_hw->status) &
-				   chan->xdev->max_buffer_len;
+			residue += (axidma_hw->control & chan->xdev->max_buffer_len) -
+			           (axidma_hw->status & chan->xdev->max_buffer_len);
 		} else {
 			aximcdma_seg =
 				list_entry(entry,
@@ -1014,8 +1014,8 @@ static u32 xilinx_dma_get_residue(struct xilinx_dma_chan *chan,
 					   node);
 			aximcdma_hw = &aximcdma_seg->hw;
 			residue +=
-				(aximcdma_hw->control - aximcdma_hw->status) &
-				chan->xdev->max_buffer_len;
+				(aximcdma_hw->control & chan->xdev->max_buffer_len) -
+				(aximcdma_hw->status & chan->xdev->max_buffer_len);
 		}
 	}
 
-- 
cgit v1.2.3


From a17ce4bc6f4f9acf77ba416c36791a15602e53aa Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Wed, 11 Mar 2026 07:34:46 +0200
Subject: dmaengine: xilinx_dma: Fix reset related timeout with two-channel
 AXIDMA

A single AXIDMA controller can have one or two channels. When it has two
channels, the reset for both are tied together: resetting one channel
resets the other as well. This creates a problem where resetting one
channel will reset the registers for both channels, including clearing
interrupt enable bits for the other channel, which can then lead  to
timeouts as the driver is waiting for an interrupt which never comes.

The driver currently has a probe-time work around for this: when a
channel is created, the driver also resets and enables the
interrupts. With two channels the reset for the second channel will
clear the interrupt enables for the first one. The work around in the
driver is just to manually enable the interrupts again in
xilinx_dma_alloc_chan_resources().

This workaround only addresses the probe-time issue. When channels are
reset at runtime (e.g., in xilinx_dma_terminate_all() or during error
recovery), there's no corresponding mechanism to restore the other
channel's interrupt enables. This leads to one channel having its
interrupts disabled while the driver expects them to work, causing
timeouts and DMA failures.

A proper fix is a complicated matter, as we should not reset the other
channel when it's operating normally. So, perhaps, there should be some
kind of synchronization for a common reset, which is not trivial to
implement. To add to the complexity, the driver also supports other DMA
types, like VDMA, CDMA and MCDMA, which don't have a shared reset.

However, when the two-channel AXIDMA is used in the (assumably) normal
use case, providing DMA for a single memory-to-memory device, the common
reset is a bit smaller issue: when something bad happens on one channel,
or when one channel is terminated, the assumption is that we also want
to terminate the other channel. And thus resetting both at the same time
is "ok".

With that line of thinking we can implement a bit better work around
than just the current probe time work around: let's enable the
AXIDMA interrupts at xilinx_dma_start_transfer() instead.
This ensures interrupts are enabled whenever a transfer starts,
regardless of any prior resets that may have cleared them.

This approach is also more logical: enable interrupts only when needed
for a transfer, rather than at resource allocation time, and, I think,
all the other DMA types should also use this model, but I'm reluctant to
do such changes as I cannot test them.

The reset function still enables interrupts even though it's not needed
for AXIDMA anymore, but it's common code for all DMA types (VDMA, CDMA,
MCDMA), so leave it unchanged to avoid affecting other variants.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Fixes: c0bba3a99f07 ("dmaengine: vdma: Add Support for Xilinx AXI Direct Memory Access Engine")
Link: https://patch.msgid.link/20260311-xilinx-dma-fix-v2-1-a725abb66e3c@ideasonboard.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/xilinx/xilinx_dma.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 969343342e86..e3a18ee42aa2 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -1235,14 +1235,6 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 
 	dma_cookie_init(dchan);
 
-	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		/* For AXI DMA resetting once channel will reset the
-		 * other channel as well so enable the interrupts here.
-		 */
-		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
-			      XILINX_DMA_DMAXR_ALL_IRQ_MASK);
-	}
-
 	if ((chan->xdev->dma_config->dmatype == XDMA_TYPE_CDMA) && chan->has_sg)
 		dma_ctrl_set(chan, XILINX_DMA_REG_DMACR,
 			     XILINX_CDMA_CR_SGMODE);
@@ -1612,6 +1604,7 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 			     head_desc->async_tx.phys);
 	reg  &= ~XILINX_DMA_CR_DELAY_MAX;
 	reg  |= chan->irq_delay << XILINX_DMA_CR_DELAY_SHIFT;
+	reg |= XILINX_DMA_DMAXR_ALL_IRQ_MASK;
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
 	xilinx_dma_start(chan);
-- 
cgit v1.2.3


From a0671125d4f55e1e98d9bde8a0b671941987e208 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 13 Mar 2026 07:55:31 +0100
Subject: clsact: Fix use-after-free in init/destroy rollback asymmetry

Fix a use-after-free in the clsact qdisc upon init/destroy rollback asymmetry.
The latter is achieved by first fully initializing a clsact instance, and
then in a second step having a replacement failure for the new clsact qdisc
instance. clsact_init() initializes ingress first and then takes care of the
egress part. This can fail midway, for example, via tcf_block_get_ext(). Upon
failure, the kernel will trigger the clsact_destroy() callback.

Commit 1cb6f0bae504 ("bpf: Fix too early release of tcx_entry") details the
way how the transition is happening. If tcf_block_get_ext on the q->ingress_block
ends up failing, we took the tcx_miniq_inc reference count on the ingress
side, but not yet on the egress side. clsact_destroy() tests whether the
{ingress,egress}_entry was non-NULL. However, even in midway failure on the
replacement, both are in fact non-NULL with a valid egress_entry from the
previous clsact instance.

What we really need to test for is whether the qdisc instance-specific ingress
or egress side previously got initialized. This adds a small helper for checking
the miniq initialization called mini_qdisc_pair_inited, and utilizes that upon
clsact_destroy() in order to fix the use-after-free scenario. Convert the
ingress_destroy() side as well so both are consistent to each other.

Fixes: 1cb6f0bae504 ("bpf: Fix too early release of tcx_entry")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20260313065531.98639-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/sch_generic.h |  5 +++++
 net/sched/sch_ingress.c   | 14 ++++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index cafb266a0b80..c3d657359a3d 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1457,6 +1457,11 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
 				struct tcf_block *block);
 
+static inline bool mini_qdisc_pair_inited(struct mini_Qdisc_pair *miniqp)
+{
+	return !!miniqp->p_miniq;
+}
+
 void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx);
 
 int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index cc6051d4f2ef..c3e18bae8fbf 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -113,14 +113,15 @@ static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
-	struct bpf_mprog_entry *entry = rtnl_dereference(dev->tcx_ingress);
+	struct bpf_mprog_entry *entry;
 
 	if (sch->parent != TC_H_INGRESS)
 		return;
 
 	tcf_block_put_ext(q->block, sch, &q->block_info);
 
-	if (entry) {
+	if (mini_qdisc_pair_inited(&q->miniqp)) {
+		entry = rtnl_dereference(dev->tcx_ingress);
 		tcx_miniq_dec(entry);
 		if (!tcx_entry_is_active(entry)) {
 			tcx_entry_update(dev, NULL, true);
@@ -290,10 +291,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 
 static void clsact_destroy(struct Qdisc *sch)
 {
+	struct bpf_mprog_entry *ingress_entry, *egress_entry;
 	struct clsact_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
-	struct bpf_mprog_entry *ingress_entry = rtnl_dereference(dev->tcx_ingress);
-	struct bpf_mprog_entry *egress_entry = rtnl_dereference(dev->tcx_egress);
 
 	if (sch->parent != TC_H_CLSACT)
 		return;
@@ -301,7 +301,8 @@ static void clsact_destroy(struct Qdisc *sch)
 	tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info);
 	tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
 
-	if (ingress_entry) {
+	if (mini_qdisc_pair_inited(&q->miniqp_ingress)) {
+		ingress_entry = rtnl_dereference(dev->tcx_ingress);
 		tcx_miniq_dec(ingress_entry);
 		if (!tcx_entry_is_active(ingress_entry)) {
 			tcx_entry_update(dev, NULL, true);
@@ -309,7 +310,8 @@ static void clsact_destroy(struct Qdisc *sch)
 		}
 	}
 
-	if (egress_entry) {
+	if (mini_qdisc_pair_inited(&q->miniqp_egress)) {
+		egress_entry = rtnl_dereference(dev->tcx_egress);
 		tcx_miniq_dec(egress_entry);
 		if (!tcx_entry_is_active(egress_entry)) {
 			tcx_entry_update(dev, NULL, false);
-- 
cgit v1.2.3


From fe89277c9ceb0d6af0aa665bcf24a41d8b1b79cd Mon Sep 17 00:00:00 2001
From: Guanghui Feng <guanghuifeng@linux.alibaba.com>
Date: Mon, 16 Mar 2026 15:16:39 +0800
Subject: iommu/vt-d: Fix intel iommu iotlb sync hardlockup and retry

During the qi_check_fault process after an IOMMU ITE event, requests at
odd-numbered positions in the queue are set to QI_ABORT, only satisfying
single-request submissions. However, qi_submit_sync now supports multiple
simultaneous submissions, and can't guarantee that the wait_desc will be
at an odd-numbered position. Therefore, if an item times out, IOMMU can't
re-initiate the request, resulting in an infinite polling wait.

This modifies the process by setting the status of all requests already
fetched by IOMMU and recorded as QI_IN_USE status (including wait_desc
requests) to QI_ABORT, thus enabling multiple requests to be resubmitted.

Fixes: 8a1d82462540 ("iommu/vt-d: Multiple descriptors per qi_submit_sync()")
Cc: stable@vger.kernel.org
Signed-off-by: Guanghui Feng <guanghuifeng@linux.alibaba.com>
Tested-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://lore.kernel.org/r/20260306101516.3885775-1-guanghuifeng@linux.alibaba.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Fixes: 8a1d82462540 ("iommu/vt-d: Multiple descriptors per  qi_submit_sync()")
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/intel/dmar.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index d68c06025cac..69222dbd2af0 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1314,7 +1314,6 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 	if (fault & DMA_FSTS_ITE) {
 		head = readl(iommu->reg + DMAR_IQH_REG);
 		head = ((head >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
-		head |= 1;
 		tail = readl(iommu->reg + DMAR_IQT_REG);
 		tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
 
@@ -1331,7 +1330,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 		do {
 			if (qi->desc_status[head] == QI_IN_USE)
 				qi->desc_status[head] = QI_ABORT;
-			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
+			head = (head - 1 + QI_LENGTH) % QI_LENGTH;
 		} while (head != tail);
 
 		/*
-- 
cgit v1.2.3


From 39c20c4e83b9f78988541d829aa34668904e54a0 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Mon, 16 Mar 2026 15:16:40 +0800
Subject: iommu/vt-d: Only handle IOPF for SVA when PRI is supported

In intel_svm_set_dev_pasid(), the driver unconditionally manages the IOPF
handling during a domain transition. However, commit a86fb7717320
("iommu/vt-d: Allow SVA with device-specific IOPF") introduced support for
SVA on devices that handle page faults internally without utilizing the
PCI PRI. On such devices, the IOMMU-side IOPF infrastructure is not
required. Calling iopf_for_domain_replace() on these devices is incorrect
and can lead to unexpected failures during PASID attachment or unwinding.

Add a check for info->pri_supported to ensure that the IOPF queue logic
is only invoked for devices that actually rely on the IOMMU's PRI-based
fault handling.

Fixes: 17fce9d2336d ("iommu/vt-d: Put iopf enablement in domain attach path")
Cc: stable@vger.kernel.org
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20260310075520.295104-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/intel/svm.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index fea10acd4f02..57cd1db7207a 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -164,9 +164,12 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 	if (IS_ERR(dev_pasid))
 		return PTR_ERR(dev_pasid);
 
-	ret = iopf_for_domain_replace(domain, old, dev);
-	if (ret)
-		goto out_remove_dev_pasid;
+	/* SVA with non-IOMMU/PRI IOPF handling is allowed. */
+	if (info->pri_supported) {
+		ret = iopf_for_domain_replace(domain, old, dev);
+		if (ret)
+			goto out_remove_dev_pasid;
+	}
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
@@ -181,7 +184,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 
 	return 0;
 out_unwind_iopf:
-	iopf_for_domain_replace(old, domain, dev);
+	if (info->pri_supported)
+		iopf_for_domain_replace(old, domain, dev);
 out_remove_dev_pasid:
 	domain_remove_dev_pasid(domain, dev, pasid);
 	return ret;
-- 
cgit v1.2.3


From 4eae391a8e4cb065b900afcb95a3b0f97c75184d Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Mon, 16 Mar 2026 19:23:00 +0100
Subject: ASoC: dt-bindings: rockchip: Add compatible for RK3576 SPDIF

Add a compatible string for SPDIF on RK3576, which is similar to the
one on RK3568.

Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://patch.msgid.link/20260316-rk3576-spdif-v1-1-acb75088b560@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rockchip-spdif.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml
index 56c755c22945..502907dd28b3 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml
+++ b/Documentation/devicetree/bindings/sound/rockchip-spdif.yaml
@@ -33,6 +33,7 @@ properties:
           - const: rockchip,rk3066-spdif
       - items:
           - enum:
+              - rockchip,rk3576-spdif
               - rockchip,rk3588-spdif
           - const: rockchip,rk3568-spdif
 
-- 
cgit v1.2.3


From 0a4d00e2e99a39a5698e4b63c394415dcbb39d90 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Fri, 27 Feb 2026 09:06:37 +0100
Subject: iommu: Fix mapping check for 0x0 to avoid re-mapping it

Commit 789a5913b29c ("iommu/amd: Use the generic iommu page table")
introduces the shared iommu page table for AMD IOMMU. Some bioses
contain an identity mapping for address 0x0, which is not parsed
properly (e.g., certain Strix Halo devices). This causes the DMA
components of the device to fail to initialize (e.g., the NVMe SSD
controller), leading to a failed post.

Specifically, on the GPD Win 5, the NVME and SSD GPU fail to mount,
making collecting errors difficult. While debugging, it was found that
a -EADDRINUSE error was emitted and its source was traced to
iommu_iova_to_phys(). After adding some debug prints, it was found that
phys_addr becomes 0, which causes the code to try to re-map the 0
address and fail, causing a cascade leading to a failed post. This is
because the GPD Win 5 contains a 0x0-0x1 identity mapping for DMA
devices, causing it to be repeated for each device.

The cause of this failure is the following check in
iommu_create_device_direct_mappings(), where address aliasing is handled
via the following check:

```
phys_addr = iommu_iova_to_phys(domain, addr);
if (!phys_addr) {
        map_size += pg_size;
        continue;
}
````

Obviously, the iommu_iova_to_phys() signature is faulty and aliases
unmapped and 0 together, causing the allocation code to try to
re-allocate the 0 address per device. However, it has too many
instantiations to fix. Therefore, use a ternary so that when addr
is 0, the check is done for address 1 instead.

Suggested-by: Robin Murphy <robin.murphy@arm.com>
Fixes: 789a5913b29c ("iommu/amd: Use the generic iommu page table")
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/iommu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 35db51780954..50718ab810a4 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1213,7 +1213,11 @@ static int iommu_create_device_direct_mappings(struct iommu_domain *domain,
 			if (addr == end)
 				goto map_end;
 
-			phys_addr = iommu_iova_to_phys(domain, addr);
+			/*
+			 * Return address by iommu_iova_to_phys for 0 is
+			 * ambiguous. Offset to address 1 if addr is 0.
+			 */
+			phys_addr = iommu_iova_to_phys(domain, addr ? addr : 1);
 			if (!phys_addr) {
 				map_size += pg_size;
 				continue;
-- 
cgit v1.2.3


From 069c8f5aebe4d5224cf62acc7d4b3486091c658a Mon Sep 17 00:00:00 2001
From: "Nikola Z. Ivanov" <zlatistiv@gmail.com>
Date: Fri, 13 Mar 2026 16:16:43 +0200
Subject: net: usb: aqc111: Do not perform PM inside suspend callback

syzbot reports "task hung in rpm_resume"

This is caused by aqc111_suspend calling
the PM variant of its write_cmd routine.

The simplified call trace looks like this:

rpm_suspend()
  usb_suspend_both() - here udev->dev.power.runtime_status == RPM_SUSPENDING
    aqc111_suspend() - called for the usb device interface
      aqc111_write32_cmd()
        usb_autopm_get_interface()
          pm_runtime_resume_and_get()
            rpm_resume() - here we call rpm_resume() on our parent
              rpm_resume() - Here we wait for a status change that will never happen.

At this point we block another task which holds
rtnl_lock and locks up the whole networking stack.

Fix this by replacing the write_cmd calls with their _nopm variants

Reported-by: syzbot+48dc1e8dfc92faf1124c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=48dc1e8dfc92faf1124c
Fixes: e58ba4544c77 ("net: usb: aqc111: Add support for wake on LAN by MAGIC packet")
Signed-off-by: Nikola Z. Ivanov <zlatistiv@gmail.com>
Link: https://patch.msgid.link/20260313141643.1181386-1-zlatistiv@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/aqc111.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index cbffa9ae1bb6..dd53f413c38f 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1395,14 +1395,14 @@ static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 		aqc111_write16_cmd_nopm(dev, AQ_ACCESS_MAC,
 					SFR_MEDIUM_STATUS_MODE, 2, &reg16);
 
-		aqc111_write_cmd(dev, AQ_WOL_CFG, 0, 0,
-				 WOL_CFG_SIZE, &wol_cfg);
-		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+		aqc111_write_cmd_nopm(dev, AQ_WOL_CFG, 0, 0,
+				      WOL_CFG_SIZE, &wol_cfg);
+		aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
+					&aqc111_data->phy_cfg);
 	} else {
 		aqc111_data->phy_cfg |= AQ_LOW_POWER;
-		aqc111_write32_cmd(dev, AQ_PHY_OPS, 0, 0,
-				   &aqc111_data->phy_cfg);
+		aqc111_write32_cmd_nopm(dev, AQ_PHY_OPS, 0, 0,
+					&aqc111_data->phy_cfg);
 
 		/* Disable RX path */
 		aqc111_read16_cmd_nopm(dev, AQ_ACCESS_MAC,
-- 
cgit v1.2.3


From 45c6a2dc7ec8339052666b06065c521a10cc29bb Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Mar 2026 16:52:14 -0800
Subject: iommu/io-pgtable: fix all kernel-doc warnings in io-pgtable.h

Avoid kernel-doc warnings in io-pgtable.h:
- use the correct struct member names or kernel-doc format
- add a missing struct member description
- add a missing function return comment section

Warning: include/linux/io-pgtable.h:187 struct member 'coherent_walk' not
 described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'arm_lpae_s1_cfg' not
 described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'arm_lpae_s2_cfg' not
 described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'arm_v7s_cfg' not
 described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'arm_mali_lpae_cfg'
 not described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'apple_dart_cfg' not
 described in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:187 struct member 'amd' not described
 in 'io_pgtable_cfg'
Warning: include/linux/io-pgtable.h:223 struct member
 'read_and_clear_dirty' not described in 'io_pgtable_ops'
Warning: include/linux/io-pgtable.h:237 No description found for return
 value of 'alloc_io_pgtable_ops'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 include/linux/io-pgtable.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 7a1516011ccf..e19872e37e06 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -53,7 +53,7 @@ struct iommu_flush_ops {
  *                 tables.
  * @ias:           Input address (iova) size, in bits.
  * @oas:           Output address (paddr) size, in bits.
- * @coherent_walk  A flag to indicate whether or not page table walks made
+ * @coherent_walk: A flag to indicate whether or not page table walks made
  *                 by the IOMMU are coherent with the CPU caches.
  * @tlb:           TLB management callbacks for this set of tables.
  * @iommu_dev:     The device representing the DMA configuration for the
@@ -136,6 +136,7 @@ struct io_pgtable_cfg {
 	void (*free)(void *cookie, void *pages, size_t size);
 
 	/* Low-level data specific to the table format */
+	/* private: */
 	union {
 		struct {
 			u64	ttbr;
@@ -203,6 +204,9 @@ struct arm_lpae_io_pgtable_walk_data {
  * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
  * @iova_to_phys: Translate iova to physical address.
  * @pgtable_walk: (optional) Perform a page table walk for a given iova.
+ * @read_and_clear_dirty: Record dirty info per IOVA. If an IOVA is dirty,
+ *			  clear its dirty state from the PTE unless the
+ *			  IOMMU_DIRTY_NO_CLEAR flag is passed in.
  *
  * These functions map directly onto the iommu_ops member functions with
  * the same names.
@@ -231,7 +235,9 @@ struct io_pgtable_ops {
  *          the configuration actually provided by the allocator (e.g. the
  *          pgsize_bitmap may be restricted).
  * @cookie: An opaque token provided by the IOMMU driver and passed back to
- *          the callback routines in cfg->tlb.
+ *          the callback routines.
+ *
+ * Returns: Pointer to the &struct io_pgtable_ops for this set of page tables.
  */
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
-- 
cgit v1.2.3


From 06e14c36e20b48171df13d51b89fe67c594ed07a Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 4 Mar 2026 22:18:42 -0800
Subject: iommu/sva: Fix crash in iommu_sva_unbind_device()

domain->mm->iommu_mm can be freed by iommu_domain_free():
  iommu_domain_free()
    mmdrop()
      __mmdrop()
        mm_pasid_drop()
After iommu_domain_free() returns, accessing domain->mm->iommu_mm may
dereference a freed mm structure, leading to a crash.

Fix this by moving the code that accesses domain->mm->iommu_mm to before
the call to iommu_domain_free().

Fixes: e37d5a2d60a3 ("iommu/sva: invalidate stale IOTLB entries for kernel address space")
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/iommu-sva.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 07d64908a05f..bc7c7232a43e 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -182,13 +182,13 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
 		list_del(&domain->next);
-		iommu_domain_free(domain);
-	}
+		if (list_empty(&iommu_mm->sva_domains)) {
+			list_del(&iommu_mm->mm_list_elm);
+			if (list_empty(&iommu_sva_mms))
+				iommu_sva_present = false;
+		}
 
-	if (list_empty(&iommu_mm->sva_domains)) {
-		list_del(&iommu_mm->mm_list_elm);
-		if (list_empty(&iommu_sva_mms))
-			iommu_sva_present = false;
+		iommu_domain_free(domain);
 	}
 
 	mutex_unlock(&iommu_sva_lock);
-- 
cgit v1.2.3


From ba17de98545d07285d15ce4fe2afe98283338fb0 Mon Sep 17 00:00:00 2001
From: Joe Damato <joe@dama.to>
Date: Mon, 9 Mar 2026 16:52:33 -0700
Subject: iommu/amd: Block identity domain when SNP enabled

Previously, commit 8388f7df936b ("iommu/amd: Do not support
IOMMU_DOMAIN_IDENTITY after SNP is enabled") prevented users from
changing the IOMMU domain to identity if SNP was enabled.

This resulted in an error when writing to sysfs:

  # echo "identity" > /sys/kernel/iommu_groups/50/type
  -bash: echo: write error: Cannot allocate memory

However, commit 4402f2627d30 ("iommu/amd: Implement global identity
domain") changed the flow of the code, skipping the SNP guard and
allowing users to change the IOMMU domain to identity after a machine
has booted.

Once the user does that, they will probably try to bind and the
device/driver will start to do DMA which will trigger errors:

  iommu ivhd3: AMD-Vi: Event logged [ILLEGAL_DEV_TABLE_ENTRY device=0000:43:00.0 pasid=0x00000 address=0x3737b01000 flags=0x0020]
  iommu ivhd3: AMD-Vi: Control Reg : 0xc22000142148d
  AMD-Vi: DTE[0]: 6000000000000003
  AMD-Vi: DTE[1]: 0000000000000001
  AMD-Vi: DTE[2]: 2000003088b3e013
  AMD-Vi: DTE[3]: 0000000000000000
  bnxt_en 0000:43:00.0 (unnamed net_device) (uninitialized): Error (timeout: 500015) msg {0x0 0x0} len:0
  iommu ivhd3: AMD-Vi: Event logged [ILLEGAL_DEV_TABLE_ENTRY device=0000:43:00.0 pasid=0x00000 address=0x3737b01000 flags=0x0020]
  iommu ivhd3: AMD-Vi: Control Reg : 0xc22000142148d
  AMD-Vi: DTE[0]: 6000000000000003
  AMD-Vi: DTE[1]: 0000000000000001
  AMD-Vi: DTE[2]: 2000003088b3e013
  AMD-Vi: DTE[3]: 0000000000000000
  bnxt_en 0000:43:00.0: probe with driver bnxt_en failed with error -16

To prevent this from happening, create an attach wrapper for
identity_domain_ops which returns EINVAL if amd_iommu_snp_en is true.

With this commit applied:

  # echo "identity" > /sys/kernel/iommu_groups/62/type
  -bash: echo: write error: Invalid argument

Fixes: 4402f2627d30 ("iommu/amd: Implement global identity domain")
Signed-off-by: Joe Damato <joe@dama.to>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/amd/iommu.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 81c4d7733872..760d5f4623b5 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2909,8 +2909,21 @@ static struct iommu_domain blocked_domain = {
 
 static struct protection_domain identity_domain;
 
+static int amd_iommu_identity_attach(struct iommu_domain *dom, struct device *dev,
+				     struct iommu_domain *old)
+{
+	/*
+	 * Don't allow attaching a device to the identity domain if SNP is
+	 * enabled.
+	 */
+	if (amd_iommu_snp_en)
+		return -EINVAL;
+
+	return amd_iommu_attach_device(dom, dev, old);
+}
+
 static const struct iommu_domain_ops identity_domain_ops = {
-	.attach_dev = amd_iommu_attach_device,
+	.attach_dev = amd_iommu_identity_attach,
 };
 
 void amd_iommu_init_identity_domain(void)
-- 
cgit v1.2.3


From 0496acc42fb51eee040b5170cec05cec41385540 Mon Sep 17 00:00:00 2001
From: "Zenghui Yu (Huawei)" <zenghui.yu@linux.dev>
Date: Tue, 17 Mar 2026 19:57:48 +0800
Subject: KVM: arm64: Fix the descriptor address in __kvm_at_swap_desc()

Using "(u64 __user *)hva + offset" to get the virtual addresses of S1/S2
descriptors looks really wrong, if offset is not zero. What we want to get
for swapping is hva + offset, not hva + offset*8. ;-)

Fix it.

Fixes: f6927b41d573 ("KVM: arm64: Add helper for swapping guest descriptor")
Signed-off-by: Zenghui Yu (Huawei) <zenghui.yu@linux.dev>
Link: https://patch.msgid.link/20260317115748.47332-1-zenghui.yu@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
---
 arch/arm64/kvm/at.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index c5c5644b1878..a024d9a770dc 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1753,7 +1753,7 @@ int __kvm_at_swap_desc(struct kvm *kvm, gpa_t ipa, u64 old, u64 new)
 	if (!writable)
 		return -EPERM;
 
-	ptep = (u64 __user *)hva + offset;
+	ptep = (void __user *)hva + offset;
 	if (cpus_have_final_cap(ARM64_HAS_LSE_ATOMICS))
 		r = __lse_swap_desc(ptep, old, new);
 	else
-- 
cgit v1.2.3


From 01e8d0f742222f1e68f48180d5480097adf7ae9f Mon Sep 17 00:00:00 2001
From: Wanquan Zhong <wanquan.zhong@fibocom.com>
Date: Mon, 16 Mar 2026 19:55:12 +0800
Subject: USB: serial: option: add support for Rolling Wireless RW135R-GL

Add VID/PID 33f8:1003 for the Rolling Wireless RW135R-GL M.2 module,
which is used in laptop debug cards with MBIM interface for
Linux/Chrome OS. The device supports mbim, pipe functionalities.

Here are the outputs of usb-devices:
T:  Bus=04 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#=  2 Spd=5000 MxCh= 0
D:  Ver= 3.20 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs=  1
P:  Vendor=33f8 ProdID=1003 Rev=05.15
S:  Manufacturer=Rolling Wireless S.a.r.l.
S:  Product=Rolling RW135R-GL Module
S:  SerialNumber=12345678
C:  #Ifs= 3 Cfg#= 1 Atr=a0 MxPwr=896mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=0f(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=40 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

Signed-off-by: Wanquan Zhong <wanquan.zhong@fibocom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index e349ed66d2ac..d222bf2c2539 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2461,6 +2461,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0302, 0xff) },			/* Rolling RW101R-GL (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0802, 0xff),			/* Rolling RW350-GL (laptop MBIM) */
 	  .driver_info = RSVD(5) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x1003, 0xff) },			/* Rolling RW135R-GL (laptop MBIM) */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x30) },	/* NetPrisma LCUK54-WWD for Global */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0x00, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x40) },
-- 
cgit v1.2.3


From f8b8820a4a16c4ef673e90ded41e8348514e53f0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Mar 2026 14:44:04 +0100
Subject: fs: clear I_DIRTY_TIME in sync_lazytime

For file systems implementing ->sync_lazytime, I_DIRTY_TIME fails to get
cleared in sync_lazytime, and might cause additional calls to
sync_lazytime during inode deactivation.  Use the same pattern as in
__mark_inode_dirty to clear the flag under the inode lock.

Fixes: 5cf06ea56ee6 ("fs: add a ->sync_lazytime method")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260317134409.1691317-1-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs-writeback.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 7c75ed7e8979..d8dac1931595 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1711,6 +1711,19 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 }
 
+static bool __sync_lazytime(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (!(inode_state_read(inode) & I_DIRTY_TIME)) {
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	inode_state_clear(inode, I_DIRTY_TIME);
+	spin_unlock(&inode->i_lock);
+	inode->i_op->sync_lazytime(inode);
+	return true;
+}
+
 bool sync_lazytime(struct inode *inode)
 {
 	if (!(inode_state_read_once(inode) & I_DIRTY_TIME))
@@ -1718,9 +1731,8 @@ bool sync_lazytime(struct inode *inode)
 
 	trace_writeback_lazytime(inode);
 	if (inode->i_op->sync_lazytime)
-		inode->i_op->sync_lazytime(inode);
-	else
-		mark_inode_dirty_sync(inode);
+		return __sync_lazytime(inode);
+	mark_inode_dirty_sync(inode);
 	return true;
 }
 
-- 
cgit v1.2.3


From 0e01c3416eb863ee7f156a9d7e7421ec0a9f68a0 Mon Sep 17 00:00:00 2001
From: Frej Drejhammar <frej@stacken.kth.se>
Date: Sun, 22 Feb 2026 18:00:42 +0100
Subject: USB: serial: io_edgeport: add support for Blackbox IC135A

The Blackbox 724-746-5500 USB Director USB-RS-232 HUB, part number
IC135A, is a rebadged Edgeport/4 with its own USB device id.

Signed-off-by: Frej Drejhammar <frej@stacken.kth.se>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/io_edgeport.c | 3 +++
 drivers/usb/serial/io_usbvend.h  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c
index 58694b8943d1..3f5889145e51 100644
--- a/drivers/usb/serial/io_edgeport.c
+++ b/drivers/usb/serial/io_edgeport.c
@@ -73,6 +73,7 @@ static const struct usb_device_id edgeport_4port_id_table[] = {
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_22I) },
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_412_4) },
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_COMPATIBLE) },
+	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_BLACKBOX_IC135A) },
 	{ }
 };
 
@@ -121,6 +122,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_8R) },
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_8RR) },
 	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_EDGEPORT_412_8) },
+	{ USB_DEVICE(USB_VENDOR_ID_ION, ION_DEVICE_ID_BLACKBOX_IC135A) },
 	{ USB_DEVICE(USB_VENDOR_ID_NCR, NCR_DEVICE_ID_EPIC_0202) },
 	{ USB_DEVICE(USB_VENDOR_ID_NCR, NCR_DEVICE_ID_EPIC_0203) },
 	{ USB_DEVICE(USB_VENDOR_ID_NCR, NCR_DEVICE_ID_EPIC_0310) },
@@ -470,6 +472,7 @@ static void get_product_info(struct edgeport_serial *edge_serial)
 	case ION_DEVICE_ID_EDGEPORT_2_DIN:
 	case ION_DEVICE_ID_EDGEPORT_4_DIN:
 	case ION_DEVICE_ID_EDGEPORT_16_DUAL_CPU:
+	case ION_DEVICE_ID_BLACKBOX_IC135A:
 		product_info->IsRS232 = 1;
 		break;
 
diff --git a/drivers/usb/serial/io_usbvend.h b/drivers/usb/serial/io_usbvend.h
index 9a6f742ad3ab..c82a275e8e76 100644
--- a/drivers/usb/serial/io_usbvend.h
+++ b/drivers/usb/serial/io_usbvend.h
@@ -211,6 +211,7 @@
 
 //
 // Definitions for other product IDs
+#define ION_DEVICE_ID_BLACKBOX_IC135A		0x0801	// OEM device (rebranded Edgeport/4)
 #define ION_DEVICE_ID_MT4X56USB			0x1403	// OEM device
 #define ION_DEVICE_ID_E5805A			0x1A01  // OEM device (rebranded Edgeport/4)
 
-- 
cgit v1.2.3


From f200b2f9a810c440c6750b56fc647b73337749a1 Mon Sep 17 00:00:00 2001
From: Vee Satayamas <vsatayamas@gmail.com>
Date: Sun, 15 Mar 2026 21:25:12 +0700
Subject: ASoC: amd: yc: Add DMI quirk for ASUS EXPERTBOOK BM1403CDA

Add a DMI quirk for the Asus Expertbook BM1403CDA to resolve the issue of the
internal microphone not being detected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221236
Signed-off-by: Vee Satayamas <vsatayamas@gmail.com>
Reviewed-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260315142511.66029-2-vsatayamas@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 1324543b42d7..c536de1bb94a 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -717,6 +717,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "PM1503CDA"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "BM1403CDA"),
+		}
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 21647677ba9af2cb6bc460e17d9f29a7132c40c3 Mon Sep 17 00:00:00 2001
From: Koichiro Den <den@valinux.co.jp>
Date: Mon, 16 Mar 2026 23:02:25 +0900
Subject: PCI: endpoint: pci-epf-test: Roll back BAR mapping when subrange
 setup fails

When the BAR subrange mapping test on DWC-based platforms fails due to
insufficient free inbound iATU regions, pci_epf_test_bar_subrange_setup()
returns an error (-ENOSPC) but does not restore the original BAR mapping.
This causes subsequent test runs to become confusing, since the failure may
leave room for the next subrange mapping test to pass.

Fix this by restoring the original BAR mapping when preparation of the
subrange mapping fails, so that no side effect remains regardless of the
test success or failure.

Fixes: 6c5e6101423b ("PCI: endpoint: pci-epf-test: Add BAR subrange mapping test support")
Reported-by: Christian Bruel <christian.bruel@foss.st.com>
Closes: https://lore.kernel.org/linux-pci/b2b03ebe-9482-4a13-b22f-7b44da096eed@foss.st.com/
Signed-off-by: Koichiro Den <den@valinux.co.jp>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Christian Bruel <christian.bruel@foss.st.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20260316140225.1481658-1-den@valinux.co.jp
---
 drivers/pci/endpoint/functions/pci-epf-test.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 582938b7b4f1..33548935765e 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -894,6 +894,11 @@ static void pci_epf_test_bar_subrange_setup(struct pci_epf_test *epf_test,
 		dev_err(&epf->dev, "pci_epc_set_bar() failed: %d\n", ret);
 		bar->submap = old_submap;
 		bar->num_submap = old_nsub;
+		ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, bar);
+		if (ret)
+			dev_warn(&epf->dev, "Failed to restore the original BAR mapping: %d\n",
+				 ret);
+
 		kfree(submap);
 		goto err;
 	}
-- 
cgit v1.2.3


From 4221f30e3e0a2507641b3397d21aff9e71e749f8 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Tue, 17 Mar 2026 11:23:39 -0400
Subject: regulator: dt-bindings: fix typos in regulator-uv-* descriptions

Remove word "over".

Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://patch.msgid.link/20260317152357.3473584-1-hugo@hugovil.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/regulator/regulator.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/regulator/regulator.yaml b/Documentation/devicetree/bindings/regulator/regulator.yaml
index 042e56396399..019aeb664cae 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/regulator.yaml
@@ -168,7 +168,7 @@ properties:
       offset from voltage set to regulator.
 
   regulator-uv-protection-microvolt:
-    description: Set over under voltage protection limit. This is a limit where
+    description: Set under voltage protection limit. This is a limit where
       hardware performs emergency shutdown. Zero can be passed to disable
       protection and value '1' indicates that protection should be enabled but
       limit setting can be omitted. Limit is given as microvolt offset from
@@ -182,7 +182,7 @@ properties:
       is given as microvolt offset from voltage set to regulator.
 
   regulator-uv-warn-microvolt:
-    description: Set over under voltage warning limit. This is a limit where
+    description: Set under voltage warning limit. This is a limit where
       hardware is assumed still to be functional but approaching limit where
       it gets damaged. Recovery actions should be initiated. Zero can be passed
       to disable detection and value '1' indicates that detection should
-- 
cgit v1.2.3


From c465f5591aa84a6f85d66d152e28b92844a45d4f Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 17 Mar 2026 16:59:45 +0100
Subject: selftests/mount_setattr: increase tmpfs size for idmapped mount tests

The mount_setattr_idmapped fixture mounts a 2 MB tmpfs at /mnt and then
creates a 2 GB sparse ext4 image at /mnt/C/ext4.img. While ftruncate()
succeeds (sparse file), mkfs.ext4 needs to write actual metadata blocks
(inode tables, journal, bitmaps) which easily exceeds the 2 MB tmpfs
limit, causing ENOSPC and failing the fixture setup for all
mount_setattr_idmapped tests.

This was introduced by commit d37d4720c3e7 ("selftests/mount_settattr:
ensure that ext4 filesystem can be created") which increased the image
size from 2 MB to 2 GB but didn't adjust the tmpfs size.

Bump the tmpfs size to 256 MB which is sufficient for the ext4 metadata.

Fixes: d37d4720c3e7 ("selftests/mount_settattr: ensure that ext4 filesystem can be created")
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 tools/testing/selftests/mount_setattr/mount_setattr_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index 7aec3ae82a44..c6dafb3cc116 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -1020,7 +1020,7 @@ FIXTURE_SETUP(mount_setattr_idmapped)
 			"size=100000,mode=700"), 0);
 
 	ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
-			"size=2m,mode=700"), 0);
+			"size=256m,mode=700"), 0);
 
 	ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
 
-- 
cgit v1.2.3


From b49814033cb5224c818cfb04dccb3260da10cc4f Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Wed, 11 Mar 2026 15:18:37 -0600
Subject: drm/amd/display: Fix gamma 2.2 colorop TFs

Use GAMMA22 for degamma/blend and GAMMA22_INV for shaper so
curves match the color pipeline.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5016
Tested-by: Xaver Hugl <xaver.hugl@kde.org>
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d8f9f42effd767ffa7bbcd7e05fbd6b20737e468)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
index d59ba82d3d7c..aa4658867e55 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_colorop.c
@@ -37,19 +37,19 @@ const u64 amdgpu_dm_supported_degam_tfs =
 	BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) |
-	BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV);
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22);
 
 const u64 amdgpu_dm_supported_shaper_tfs =
 	BIT(DRM_COLOROP_1D_CURVE_SRGB_INV_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_PQ_125_INV_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_BT2020_OETF) |
-	BIT(DRM_COLOROP_1D_CURVE_GAMMA22);
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV);
 
 const u64 amdgpu_dm_supported_blnd_tfs =
 	BIT(DRM_COLOROP_1D_CURVE_SRGB_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_PQ_125_EOTF) |
 	BIT(DRM_COLOROP_1D_CURVE_BT2020_INV_OETF) |
-	BIT(DRM_COLOROP_1D_CURVE_GAMMA22_INV);
+	BIT(DRM_COLOROP_1D_CURVE_GAMMA22);
 
 #define MAX_COLOR_PIPELINE_OPS 10
 
-- 
cgit v1.2.3


From 6270b1a5dab94665d7adce3dc78bc9066ed28bdd Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 12 Mar 2026 18:06:17 +0800
Subject: drm/amdgpu: Limit BO list entry count to prevent resource exhaustion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userspace can pass an arbitrary number of BO list entries via the
bo_number field. Although the previous multiplication overflow check
prevents out-of-bounds allocation, a large number of entries could still
cause excessive memory allocation (up to potentially gigabytes) and
unnecessarily long list processing times.

Introduce a hard limit of 128k entries per BO list, which is more than
sufficient for any realistic use case (e.g., a single list containing all
buffers in a large scene). This prevents memory exhaustion attacks and
ensures predictable performance.

Return -EINVAL if the requested entry count exceeds the limit

Reviewed-by: Christian König <christian.koenig@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 688b87d39e0aa8135105b40dc167d74b5ada5332)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 4662bfbe70b2..43864df8af04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -36,6 +36,7 @@
 
 #define AMDGPU_BO_LIST_MAX_PRIORITY	32u
 #define AMDGPU_BO_LIST_NUM_BUCKETS	(AMDGPU_BO_LIST_MAX_PRIORITY + 1)
+#define AMDGPU_BO_LIST_MAX_ENTRIES	(128 * 1024)
 
 static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu)
 {
@@ -188,6 +189,9 @@ int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 	const uint32_t bo_number = in->bo_number;
 	struct drm_amdgpu_bo_list_entry *info;
 
+	if (bo_number > AMDGPU_BO_LIST_MAX_ENTRIES)
+		return -EINVAL;
+
 	/* copy the handle array from userspace to a kernel buffer */
 	if (likely(info_size == bo_info_size)) {
 		info = vmemdup_array_user(uptr, bo_number, info_size);
-- 
cgit v1.2.3


From 10718159890bc99cbcc7b5a38dade05df335e797 Mon Sep 17 00:00:00 2001
From: Calvin Owens <calvin@wbinvd.org>
Date: Thu, 12 Mar 2026 10:13:34 -0700
Subject: drm/amd/display: Fix uninitialized variable use which breaks full LTO

Commit e1b385726f7f ("drm/amd/display: Add additional checks for PSP
footer size") introduced a use of an uninitialized stack variable
in dm_dmub_sw_init() (region_params.bss_data_size).

Interestingly, this seems to cause no issue on normal kernels. But when
full LTO is enabled, it causes the compiler to "optimize" out huge
swaths of amdgpu initialization code, and the driver is unusable:

    amdgpu 0000:03:00.0: [drm] Loading DMUB firmware via PSP: version=0x07002F00
    amdgpu 0000:03:00.0: sw_init of IP block <dm> failed 5
    amdgpu 0000:03:00.0: amdgpu_device_ip_init failed
    amdgpu 0000:03:00.0: Fatal error during GPU init

It surprises me that neither gcc nor clang emit a warning about this: I
only found it by bisecting the LTO breakage.

Fix by using the bss_data_size field from fw_meta_info_params, as was
presumably intended.

Fixes: e1b385726f7f ("drm/amd/display: Add additional checks for PSP footer size")
Signed-off-by: Calvin Owens <calvin@wbinvd.org>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b7f1402f6ad24cc6b9a01fa09ebd1c6559d787d0)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b3d6f2cd8ab6..0d1c772ef713 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2554,7 +2554,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 	fw_meta_info_params.fw_inst_const = adev->dm.dmub_fw->data +
 					    le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
 					    PSP_HEADER_BYTES_256;
-	fw_meta_info_params.fw_bss_data = region_params.bss_data_size ? adev->dm.dmub_fw->data +
+	fw_meta_info_params.fw_bss_data = fw_meta_info_params.bss_data_size ? adev->dm.dmub_fw->data +
 					  le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
 					  le32_to_cpu(hdr->inst_const_bytes) : NULL;
 	fw_meta_info_params.custom_psp_footer_size = 0;
-- 
cgit v1.2.3


From ebe82c6e75cfc547154d0fd843b0dd6cca3d548f Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Fri, 6 Mar 2026 14:28:03 +0800
Subject: drm/amd/display: Wrap dcn32_override_min_req_memclk() in
 DC_FP_{START, END}

[Why]
The dcn32_override_min_req_memclk function is in dcn32_fpu.c, which is
compiled with CC_FLAGS_FPU into FP instructions.  So when we call it we
must use DC_FP_{START,END} to save and restore the FP context, and
prepare the FP unit on architectures like LoongArch where the FP unit
isn't always on.

Reported-by: LiarOnce <liaronce@hotmail.com>
Fixes: ee7be8f3de1c ("drm/amd/display: Limit DCN32 8 channel or less parts to DPM1 for FPO")
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 25bb1d54ba3983c064361033a8ec15474fece37e)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 7ebb7d1193af..c7fd604024d6 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -1785,7 +1785,10 @@ static bool dml1_validate(struct dc *dc, struct dc_state *context, enum dc_valid
 
 	dc->res_pool->funcs->calculate_wm_and_dlg(dc, context, pipes, pipe_cnt, vlevel);
 
+	DC_FP_START();
 	dcn32_override_min_req_memclk(dc, context);
+	DC_FP_END();
+
 	dcn32_override_min_req_dcfclk(dc, context);
 
 	BW_VAL_TRACE_END_WATERMARKS();
-- 
cgit v1.2.3


From 2323b019651ad81c20a0f7f817c63392b3110652 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sun, 15 Mar 2026 18:30:26 +0530
Subject: drm/amd/display: Fix DisplayID not-found handling in
 parse_edid_displayid_vrr()

parse_edid_displayid_vrr() searches the EDID extension blocks for a
DisplayID extension before parsing the dynamic video timing range.

The code previously checked whether edid_ext was NULL after the search
loop. However, edid_ext is assigned during each iteration of the loop,
so it will never be NULL once the loop has executed. If no DisplayID
extension is found, edid_ext ends up pointing to the last extension
block, and the NULL check does not correctly detect the failure case.

Instead, check whether the loop completed without finding a matching
DisplayID block by testing "i == edid->extensions". This ensures the
function exits early when no DisplayID extension is present and avoids
parsing an unrelated EDID extension block.

Also simplify the EDID validation check using "!edid ||
!edid->extensions".

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:13079 parse_edid_displayid_vrr() warn: variable dereferenced before check 'edid_ext' (see line 13075)

Fixes: a638b837d0e6 ("drm/amd/display: Fix refresh rate range for some panel")
Cc: Roman Li <roman.li@amd.com>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Jerry Zuo <jerry.zuo@amd.com>
Cc: Sun peng Li <sunpeng.li@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 91c7e6342e98c846b259c57273436fdea4c043f2)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0d1c772ef713..085cc98bd875 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -13119,7 +13119,7 @@ static void parse_edid_displayid_vrr(struct drm_connector *connector,
 	u16 min_vfreq;
 	u16 max_vfreq;
 
-	if (edid == NULL || edid->extensions == 0)
+	if (!edid || !edid->extensions)
 		return;
 
 	/* Find DisplayID extension */
@@ -13129,7 +13129,7 @@ static void parse_edid_displayid_vrr(struct drm_connector *connector,
 			break;
 	}
 
-	if (edid_ext == NULL)
+	if (i == edid->extensions)
 		return;
 
 	while (j < EDID_LENGTH) {
-- 
cgit v1.2.3


From 39f44f54afa58661ecae9c27e15f5dbce2372892 Mon Sep 17 00:00:00 2001
From: Andy Nguyen <theofficialflow1996@gmail.com>
Date: Sun, 15 Mar 2026 17:51:47 +0100
Subject: drm/amd: fix dcn 2.01 check

The ASICREV_IS_BEIGE_GOBY_P check always took precedence, because it includes all chip revisions upto NV_UNKNOWN.

Fixes: 54b822b3eac3 ("drm/amd/display: Use dce_version instead of chip_id")
Signed-off-by: Andy Nguyen <theofficialflow1996@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9c7be0efa6f0daa949a5f3e3fdf9ea090b0713cb)
---
 drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 08d0e05a313e..d237d7b41dfd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -255,6 +255,10 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			BREAK_TO_DEBUGGER();
 			return NULL;
 		}
+		if (ctx->dce_version == DCN_VERSION_2_01) {
+			dcn201_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+			return &clk_mgr->base;
+		}
 		if (ASICREV_IS_SIENNA_CICHLID_P(asic_id.hw_internal_rev)) {
 			dcn3_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			return &clk_mgr->base;
@@ -267,10 +271,6 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			dcn3_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			return &clk_mgr->base;
 		}
-		if (ctx->dce_version == DCN_VERSION_2_01) {
-			dcn201_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
-			return &clk_mgr->base;
-		}
 		dcn20_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 		return &clk_mgr->base;
 	}
-- 
cgit v1.2.3


From 0b26edac4ac5535df1f63e6e8ab44c24fe1acad7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:22:43 -0500
Subject: drm/amdgpu/mmhub2.0: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e064cef4b53552602bb6ac90399c18f662f3cacd)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index a0cc8e218ca1..534cb4c544dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -154,14 +154,17 @@ mmhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(2, 0, 0):
 	case IP_VERSION(2, 0, 2):
-		mmhub_cid = mmhub_client_ids_navi1x[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_navi1x) ?
+			mmhub_client_ids_navi1x[cid][rw] : NULL;
 		break;
 	case IP_VERSION(2, 1, 0):
 	case IP_VERSION(2, 1, 1):
-		mmhub_cid = mmhub_client_ids_sienna_cichlid[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_sienna_cichlid) ?
+			mmhub_client_ids_sienna_cichlid[cid][rw] : NULL;
 		break;
 	case IP_VERSION(2, 1, 2):
-		mmhub_cid = mmhub_client_ids_beige_goby[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_beige_goby) ?
+			mmhub_client_ids_beige_goby[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From a54403a534972af5d9ba5aaa3bb6ead612500ec6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:24:10 -0500
Subject: drm/amdgpu/mmhub2.3: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 89cd90375c19fb45138990b70e9f4ba4806f05c4)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index 5eb8122e2746..ceb2f6b46de5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -94,7 +94,8 @@ mmhub_v2_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
 	case IP_VERSION(2, 3, 0):
 	case IP_VERSION(2, 4, 0):
 	case IP_VERSION(2, 4, 1):
-		mmhub_cid = mmhub_client_ids_vangogh[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_vangogh) ?
+			mmhub_client_ids_vangogh[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From 5d4e88bcfef29569a1db224ef15e28c603666c6d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:24:35 -0500
Subject: drm/amdgpu/mmhub3.0.1: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5f76083183363c4528a4aaa593f5d38c28fe7d7b)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
index 910337dc28d1..14a742d3a99d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
@@ -117,7 +117,8 @@ mmhub_v3_0_1_print_l2_protection_fault_status(struct amdgpu_device *adev,
 
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(3, 0, 1):
-		mmhub_cid = mmhub_client_ids_v3_0_1[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_0_1) ?
+			mmhub_client_ids_v3_0_1[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From e5e6d67b1ce9764e67aef2d0eef9911af53ad99a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:25:09 -0500
Subject: drm/amdgpu/mmhub3.0.2: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1441f52c7f6ae6553664aa9e3e4562f6fc2fe8ea)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c
index f0f182f033b9..e1f07f2a1852 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_2.c
@@ -108,7 +108,8 @@ mmhub_v3_0_2_print_l2_protection_fault_status(struct amdgpu_device *adev,
 		"MMVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
 		status);
 
-	mmhub_cid = mmhub_client_ids_v3_0_2[cid][rw];
+	mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_0_2) ?
+		mmhub_client_ids_v3_0_2[cid][rw] : NULL;
 	dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
 		mmhub_cid ? mmhub_cid : "unknown", cid);
 	dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
-- 
cgit v1.2.3


From cdb82ecbeccb55fae75a3c956b605f7801a30db1 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:25:30 -0500
Subject: drm/amdgpu/mmhub3.0: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f14f27bbe2a3ed7af32d5f6eaf3f417139f45253)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
index 7d5242df58a5..ab966e69a342 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0.c
@@ -110,7 +110,8 @@ mmhub_v3_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(3, 0, 0):
 	case IP_VERSION(3, 0, 1):
-		mmhub_cid = mmhub_client_ids_v3_0_0[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_0_0) ?
+			mmhub_client_ids_v3_0_0[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From 3cdd405831d8cc50a5eae086403402697bb98a4a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:25:56 -0500
Subject: drm/amdgpu/mmhub4.1.0: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 04f063d85090f5dd0c671010ce88ee49d9dcc8ed)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
index 951998454b25..88bfe321f83a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c
@@ -102,7 +102,8 @@ mmhub_v4_1_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
 		status);
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(4, 1, 0):
-		mmhub_cid = mmhub_client_ids_v4_1_0[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v4_1_0) ?
+			mmhub_client_ids_v4_1_0[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From 9c52f49545478aa47769378cd0b53c5005d6a846 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 4 Mar 2026 17:26:17 -0500
Subject: drm/amdgpu/mmhub4.2.0: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit dea5f235baf3786bfd4fd920b03c19285fdc3d9f)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v4_2_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_2_0.c
index a72770e3d0e9..2532ca80f735 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_2_0.c
@@ -688,7 +688,8 @@ mmhub_v4_2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
 		status);
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(4, 2, 0):
-		mmhub_cid = mmhub_client_ids_v4_2_0[cid][rw];
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v4_2_0) ?
+			mmhub_client_ids_v4_2_0[cid][rw] : NULL;
 		break;
 	default:
 		mmhub_cid = NULL;
-- 
cgit v1.2.3


From f39e1270277f4b06db0b2c6ec9405b6dd766fb13 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 16 Mar 2026 15:51:08 -0400
Subject: drm/amdgpu/gmc9.0: add bounds checking for cid

The value should never exceed the array size as those
are the only values the hardware is expected to return,
but add checks anyway.

Cc: Benjamin Cheng <benjamin.cheng@amd.com>
Reviewed-by: Benjamin Cheng <benjamin.cheng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e14d468304832bcc4a082d95849bc0a41b18ddea)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index e35ed0cc2ec6..8eba99aa0f8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -662,28 +662,35 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	} else {
 		switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 		case IP_VERSION(9, 0, 0):
-			mmhub_cid = mmhub_client_ids_vega10[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_vega10) ?
+				mmhub_client_ids_vega10[cid][rw] : NULL;
 			break;
 		case IP_VERSION(9, 3, 0):
-			mmhub_cid = mmhub_client_ids_vega12[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_vega12) ?
+				mmhub_client_ids_vega12[cid][rw] : NULL;
 			break;
 		case IP_VERSION(9, 4, 0):
-			mmhub_cid = mmhub_client_ids_vega20[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_vega20) ?
+				mmhub_client_ids_vega20[cid][rw] : NULL;
 			break;
 		case IP_VERSION(9, 4, 1):
-			mmhub_cid = mmhub_client_ids_arcturus[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_arcturus) ?
+				mmhub_client_ids_arcturus[cid][rw] : NULL;
 			break;
 		case IP_VERSION(9, 1, 0):
 		case IP_VERSION(9, 2, 0):
-			mmhub_cid = mmhub_client_ids_raven[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_raven) ?
+				mmhub_client_ids_raven[cid][rw] : NULL;
 			break;
 		case IP_VERSION(1, 5, 0):
 		case IP_VERSION(2, 4, 0):
-			mmhub_cid = mmhub_client_ids_renoir[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_renoir) ?
+				mmhub_client_ids_renoir[cid][rw] : NULL;
 			break;
 		case IP_VERSION(1, 8, 0):
 		case IP_VERSION(9, 4, 2):
-			mmhub_cid = mmhub_client_ids_aldebaran[cid][rw];
+			mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_aldebaran) ?
+				mmhub_client_ids_aldebaran[cid][rw] : NULL;
 			break;
 		default:
 			mmhub_cid = NULL;
-- 
cgit v1.2.3


From 3fc4648b53b7e393b91e63600e28e6f25c8ef0c5 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Wed, 11 Mar 2026 12:15:09 -0400
Subject: drm/amdgpu: Fix ISP segfault issue in kernel v7.0

Add NULL pointer checks for dev->type before accessing
dev->type->name in ISP genpd add/remove functions to
prevent kernel crashes.

This regression was introduced in v7.0 as the wakeup sources
are registered using physical device instead of ACPI device.
This led to adding wakeup source device as the first child of
AMDGPU device without initializing dev-type variable, and
resulted in segfault when accessed it in the amdgpu isp driver.

Fixes: 057edc58aa59 ("ACPI: PM: Register wakeup sources under physical devices")
Suggested-by: Bin Du <Bin.Du@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c51632d1ed7ac5aed2d40dbc0718d75342c12c6a)
---
 drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
index b3590b33cab9..485ecdec9618 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
@@ -129,7 +129,7 @@ static int isp_genpd_add_device(struct device *dev, void *data)
 	if (!pdev)
 		return -EINVAL;
 
-	if (!dev->type->name) {
+	if (!dev->type || !dev->type->name) {
 		drm_dbg(&adev->ddev, "Invalid device type to add\n");
 		goto exit;
 	}
@@ -165,7 +165,7 @@ static int isp_genpd_remove_device(struct device *dev, void *data)
 	if (!pdev)
 		return -EINVAL;
 
-	if (!dev->type->name) {
+	if (!dev->type || !dev->type->name) {
 		drm_dbg(&adev->ddev, "Invalid device type to remove\n");
 		goto exit;
 	}
-- 
cgit v1.2.3


From d5b66179b0e27c14a9033c4356937506577485e3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 16 Mar 2026 21:49:25 -0700
Subject: lib/crypto: powerpc: Add powerpc/aesp8-ppc.S to clean-files

Make the generated file powerpc/aesp8-ppc.S be removed by 'make clean'.

Fixes: 7cf2082e74ce ("lib/crypto: powerpc/aes: Migrate POWER8 optimized code into library")
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260317044925.104184-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/Makefile | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 725eef05b758..dc7a56f7287d 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -55,6 +55,9 @@ libaes-$(CONFIG_SPARC) += sparc/aes_asm.o
 libaes-$(CONFIG_X86) += x86/aes-aesni.o
 endif # CONFIG_CRYPTO_LIB_AES_ARCH
 
+# clean-files must be defined unconditionally
+clean-files += powerpc/aesp8-ppc.S
+
 ################################################################################
 
 obj-$(CONFIG_CRYPTO_LIB_AESCFB)			+= libaescfb.o
-- 
cgit v1.2.3


From 8c89a077ca796a2fe248c584e9d7e66cff0388c8 Mon Sep 17 00:00:00 2001
From: Praveen Talari <praveen.talari@oss.qualcomm.com>
Date: Fri, 13 Mar 2026 21:49:01 +0530
Subject: spi: geni-qcom: Check DMA interrupts early in ISR

The current interrupt handler only checks the GENI main IRQ status
(m_irq) before deciding to return IRQ_NONE. This can lead to spurious
IRQ_NONE returns when DMA interrupts are pending but m_irq is zero.

Move the DMA TX/RX status register reads to the beginning of the ISR,
right after reading m_irq. Update the early return condition to check
all three status registers (m_irq, dma_tx_status, dma_rx_status) before
returning IRQ_NONE.

Signed-off-by: Praveen Talari <praveen.talari@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://patch.msgid.link/20260313-spi-geni-qcom-fix-dma-irq-handling-v1-1-0bd122589e02@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-geni-qcom.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 772b7148ba5f..d5fb0edc8e0c 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -906,10 +906,13 @@ static irqreturn_t geni_spi_isr(int irq, void *data)
 	struct spi_controller *spi = data;
 	struct spi_geni_master *mas = spi_controller_get_devdata(spi);
 	struct geni_se *se = &mas->se;
-	u32 m_irq;
+	u32 m_irq, dma_tx_status, dma_rx_status;
 
 	m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
-	if (!m_irq)
+	dma_tx_status = readl_relaxed(se->base + SE_DMA_TX_IRQ_STAT);
+	dma_rx_status = readl_relaxed(se->base + SE_DMA_RX_IRQ_STAT);
+
+	if (!m_irq && !dma_tx_status && !dma_rx_status)
 		return IRQ_NONE;
 
 	if (m_irq & (M_CMD_OVERRUN_EN | M_ILLEGAL_CMD_EN | M_CMD_FAILURE_EN |
@@ -957,8 +960,6 @@ static irqreturn_t geni_spi_isr(int irq, void *data)
 		}
 	} else if (mas->cur_xfer_mode == GENI_SE_DMA) {
 		const struct spi_transfer *xfer = mas->cur_xfer;
-		u32 dma_tx_status = readl_relaxed(se->base + SE_DMA_TX_IRQ_STAT);
-		u32 dma_rx_status = readl_relaxed(se->base + SE_DMA_RX_IRQ_STAT);
 
 		if (dma_tx_status)
 			writel(dma_tx_status, se->base + SE_DMA_TX_IRQ_CLR);
-- 
cgit v1.2.3


From 1f182ec9d7084db7dfdb2372d453c28f0e5c3f0a Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 16 Mar 2026 16:02:18 +0800
Subject: ASoC: amd: yc: Add DMI quirk for Thin A15 B7VF

Add a DMI quirk for the Thin A15 B7VF fixing the issue where
the internal microphone was not detected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220833
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260316080218.2931304-1-zhangheng@kylinos.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index c536de1bb94a..6f1c105ca77e 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -724,6 +724,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "BM1403CDA"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"),
+		}
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 00da250c21b074ea9494c375d0117b69e5b1d0a4 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 13 Mar 2026 15:41:58 -0400
Subject: RDMA/rw: Fall back to direct SGE on MR pool exhaustion

When IOMMU passthrough mode is active, ib_dma_map_sgtable_attrs()
produces no coalescing: each scatterlist page maps 1:1 to a DMA
entry, so sgt.nents equals the raw page count. A 1 MB transfer
yields 256 DMA entries. If that count exceeds the device's
max_sgl_rd threshold (an optimization hint from mlx5 firmware),
rdma_rw_io_needs_mr() steers the operation into the MR
registration path. Each such operation consumes one or more MRs
from a pool sized at max_rdma_ctxs -- roughly one MR per
concurrent context. Under write-intensive workloads that issue
many concurrent RDMA READs, the pool is rapidly exhausted,
ib_mr_pool_get() returns NULL, and rdma_rw_init_one_mr() returns
-EAGAIN. Upper layer protocols treat this as a fatal DMA mapping
failure and tear down the connection.

The max_sgl_rd check is a performance optimization, not a
correctness requirement: the device can handle large SGE counts
via direct posting, just less efficiently than with MR
registration. When the MR pool cannot satisfy a request, falling
back to the direct SGE (map_wrs) path avoids the connection
reset while preserving the MR optimization for the common case
where pool resources are available.

Add a fallback in rdma_rw_ctx_init() so that -EAGAIN from
rdma_rw_init_mr_wrs() triggers direct SGE posting instead of
propagating the error. iWARP devices, which mandate MR
registration for RDMA READs, and force_mr debug mode continue
to treat -EAGAIN as terminal.

Fixes: 00bd1439f464 ("RDMA/rw: Support threshold for registration vs scattering to local pages")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260313194201.5818-2-cel@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/rw.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index fc45c384833f..c01d5e605053 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -608,14 +608,29 @@ int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u32 port_num,
 	if (rdma_rw_io_needs_mr(qp->device, port_num, dir, sg_cnt)) {
 		ret = rdma_rw_init_mr_wrs(ctx, qp, port_num, sg, sg_cnt,
 				sg_offset, remote_addr, rkey, dir);
-	} else if (sg_cnt > 1) {
+		/*
+		 * If MR init succeeded or failed for a reason other
+		 * than pool exhaustion, that result is final.
+		 *
+		 * Pool exhaustion (-EAGAIN) from the max_sgl_rd
+		 * optimization is recoverable: fall back to
+		 * direct SGE posting. iWARP and force_mr require
+		 * MRs unconditionally, so -EAGAIN is terminal.
+		 */
+		if (ret != -EAGAIN ||
+		    rdma_protocol_iwarp(qp->device, port_num) ||
+		    unlikely(rdma_rw_force_mr))
+			goto out;
+	}
+
+	if (sg_cnt > 1)
 		ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset,
 				remote_addr, rkey, dir);
-	} else {
+	else
 		ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset,
 				remote_addr, rkey, dir);
-	}
 
+out:
 	if (ret < 0)
 		goto out_unmap_sg;
 	return ret;
-- 
cgit v1.2.3


From f28599f3969d1d928276772f1306872344c967f0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 13 Mar 2026 15:41:59 -0400
Subject: RDMA/rw: Fix MR pool exhaustion in bvec RDMA READ path

When IOVA-based DMA mapping is unavailable (e.g., IOMMU
passthrough mode), rdma_rw_ctx_init_bvec() falls back to
checking rdma_rw_io_needs_mr() with the raw bvec count.
Unlike the scatterlist path in rdma_rw_ctx_init(), which
passes a post-DMA-mapping entry count that reflects
coalescing of physically contiguous pages, the bvec path
passes the pre-mapping page count. This overstates the
number of DMA entries, causing every multi-bvec RDMA READ
to consume an MR from the QP's pool.

Under NFS WRITE workloads the server performs RDMA READs
to pull data from the client. With the inflated MR demand,
the pool is rapidly exhausted, ib_mr_pool_get() returns
NULL, and rdma_rw_init_one_mr() returns -EAGAIN. svcrdma
treats this as a DMA mapping failure, closes the connection,
and the client reconnects -- producing a cycle of 71% RPC
retransmissions and ~100 reconnections per test run. RDMA
WRITEs (NFS READ direction) are unaffected because
DMA_TO_DEVICE never triggers the max_sgl_rd check.

Remove the rdma_rw_io_needs_mr() gate from the bvec path
entirely, so that bvec RDMA operations always use the
map_wrs path (direct WR posting without MR allocation).
The bvec caller has no post-DMA-coalescing segment count
available -- xdr_buf and svc_rqst hold pages as individual
pointers, and physical contiguity is discovered only during
DMA mapping -- so the raw page count cannot serve as a
reliable input to rdma_rw_io_needs_mr(). iWARP devices,
which require MRs unconditionally, are handled by an
earlier check in rdma_rw_ctx_init_bvec() and are unaffected.

Fixes: bea28ac14cab ("RDMA/core: add MR support for bvec-based RDMA operations")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260313194201.5818-3-cel@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/rw.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index c01d5e605053..4fafe393a48c 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -701,14 +701,16 @@ int rdma_rw_ctx_init_bvec(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
 		return ret;
 
 	/*
-	 * IOVA mapping not available. Check if MR registration provides
-	 * better performance than multiple SGE entries.
+	 * IOVA not available; fall back to the map_wrs path, which maps
+	 * each bvec as a direct SGE. This is always correct: the MR path
+	 * is a throughput optimization, not a correctness requirement.
+	 * (iWARP, which does require MRs, is handled by the check above.)
+	 *
+	 * The rdma_rw_io_needs_mr() gate is not used here because nr_bvec
+	 * is a raw page count that overstates DMA entry demand -- the bvec
+	 * caller has no post-DMA-coalescing segment count, and feeding the
+	 * inflated count into the MR path exhausts the pool on RDMA READs.
 	 */
-	if (rdma_rw_io_needs_mr(dev, port_num, dir, nr_bvec))
-		return rdma_rw_init_mr_wrs_bvec(ctx, qp, port_num, bvecs,
-						nr_bvec, &iter, remote_addr,
-						rkey, dir);
-
 	return rdma_rw_init_map_wrs_bvec(ctx, qp, bvecs, nr_bvec, &iter,
 			remote_addr, rkey, dir);
 }
-- 
cgit v1.2.3


From 0f2055db7b630559870afb40fc84490816ab8ec5 Mon Sep 17 00:00:00 2001
From: Ethan Tidmore <ethantidmore06@gmail.com>
Date: Fri, 13 Mar 2026 23:57:30 -0500
Subject: RDMA/efa: Fix possible deadlock

In the error path for efa_com_alloc_comp_ctx() the semaphore assigned to
&aq->avail_cmds is not released.

Detected by Smatch:
drivers/infiniband/hw/efa/efa_com.c:662 efa_com_cmd_exec() warn:
inconsistent returns '&aq->avail_cmds'

Add release for &aq->avail_cmds in efa_com_alloc_comp_ctx() error path.

Fixes: ef3b06742c8a2 ("RDMA/efa: Fix use of completion ctx after free")
Signed-off-by: Ethan Tidmore <ethantidmore06@gmail.com>
Link: https://patch.msgid.link/20260314045730.1143862-1-ethantidmore06@gmail.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/efa/efa_com.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c
index 56caba612139..e97b5f0d7003 100644
--- a/drivers/infiniband/hw/efa/efa_com.c
+++ b/drivers/infiniband/hw/efa/efa_com.c
@@ -629,6 +629,7 @@ int efa_com_cmd_exec(struct efa_com_admin_queue *aq,
 	comp_ctx = efa_com_alloc_comp_ctx(aq);
 	if (!comp_ctx) {
 		clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
+		up(&aq->avail_cmds);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From cb3d1049f4ea77d5ad93f17d8ac1f2ed4da70501 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 3 Mar 2026 12:53:18 +0100
Subject: driver core: generalize driver_override in struct device

Currently, there are 12 busses (including platform and PCI) that
duplicate the driver_override logic for their individual devices.

All of them seem to be prone to the bug described in [1].

While this could be solved for every bus individually using a separate
lock, solving this in the driver-core generically results in less (and
cleaner) changes overall.

Thus, move driver_override to struct device, provide corresponding
accessors for busses and handle locking with a separate lock internally.

In particular, add device_set_driver_override(),
device_has_driver_override(), device_match_driver_override() and
generalize the sysfs store() and show() callbacks via a driver_override
feature flag in struct bus_type.

Until all busses have migrated, keep driver_set_override() in place.

Note that we can't use the device lock for the reasons described in [2].

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220789 [1]
Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [2]
Tested-by: Gui-Dong Han <hanguidong02@gmail.com>
Co-developed-by: Gui-Dong Han <hanguidong02@gmail.com>
Signed-off-by: Gui-Dong Han <hanguidong02@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260303115720.48783-2-dakr@kernel.org
[ Use dev->bus instead of sp->bus for consistency; fix commit message to
  refer to the struct bus_type's driver_override feature flag. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/bus.c         | 43 ++++++++++++++++++++++++++++++++-
 drivers/base/core.c        |  2 ++
 drivers/base/dd.c          | 60 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/device.h     | 54 +++++++++++++++++++++++++++++++++++++++++
 include/linux/device/bus.h |  4 ++++
 5 files changed, 162 insertions(+), 1 deletion(-)

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index bb61d8adbab1..8b6722ff8590 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -504,6 +504,36 @@ int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
 }
 EXPORT_SYMBOL_GPL(bus_for_each_drv);
 
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	int ret;
+
+	ret = __device_set_driver_override(dev, buf, count);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	guard(spinlock)(&dev->driver_override.lock);
+	return sysfs_emit(buf, "%s\n", dev->driver_override.name);
+}
+static DEVICE_ATTR_RW(driver_override);
+
+static struct attribute *driver_override_dev_attrs[] = {
+	&dev_attr_driver_override.attr,
+	NULL,
+};
+
+static const struct attribute_group driver_override_dev_group = {
+	.attrs = driver_override_dev_attrs,
+};
+
 /**
  * bus_add_device - add device to bus
  * @dev: device being added
@@ -537,9 +567,15 @@ int bus_add_device(struct device *dev)
 	if (error)
 		goto out_put;
 
+	if (dev->bus->driver_override) {
+		error = device_add_group(dev, &driver_override_dev_group);
+		if (error)
+			goto out_groups;
+	}
+
 	error = sysfs_create_link(&sp->devices_kset->kobj, &dev->kobj, dev_name(dev));
 	if (error)
-		goto out_groups;
+		goto out_override;
 
 	error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem");
 	if (error)
@@ -550,6 +586,9 @@ int bus_add_device(struct device *dev)
 
 out_subsys:
 	sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev));
+out_override:
+	if (dev->bus->driver_override)
+		device_remove_group(dev, &driver_override_dev_group);
 out_groups:
 	device_remove_groups(dev, sp->bus->dev_groups);
 out_put:
@@ -607,6 +646,8 @@ void bus_remove_device(struct device *dev)
 
 	sysfs_remove_link(&dev->kobj, "subsystem");
 	sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev));
+	if (dev->bus->driver_override)
+		device_remove_group(dev, &driver_override_dev_group);
 	device_remove_groups(dev, dev->bus->dev_groups);
 	if (klist_node_attached(&dev->p->knode_bus))
 		klist_del(&dev->p->knode_bus);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 791f9e444df8..09b98f02f559 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2556,6 +2556,7 @@ static void device_release(struct kobject *kobj)
 	devres_release_all(dev);
 
 	kfree(dev->dma_range_map);
+	kfree(dev->driver_override.name);
 
 	if (dev->release)
 		dev->release(dev);
@@ -3159,6 +3160,7 @@ void device_initialize(struct device *dev)
 	kobject_init(&dev->kobj, &device_ktype);
 	INIT_LIST_HEAD(&dev->dma_pools);
 	mutex_init(&dev->mutex);
+	spin_lock_init(&dev->driver_override.lock);
 	lockdep_set_novalidate_class(&dev->mutex);
 	spin_lock_init(&dev->devres_lock);
 	INIT_LIST_HEAD(&dev->devres_head);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index bea8da5f8a3a..37c7e54e0e4c 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -381,6 +381,66 @@ static void __exit deferred_probe_exit(void)
 }
 __exitcall(deferred_probe_exit);
 
+int __device_set_driver_override(struct device *dev, const char *s, size_t len)
+{
+	const char *new, *old;
+	char *cp;
+
+	if (!s)
+		return -EINVAL;
+
+	/*
+	 * The stored value will be used in sysfs show callback (sysfs_emit()),
+	 * which has a length limit of PAGE_SIZE and adds a trailing newline.
+	 * Thus we can store one character less to avoid truncation during sysfs
+	 * show.
+	 */
+	if (len >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	/*
+	 * Compute the real length of the string in case userspace sends us a
+	 * bunch of \0 characters like python likes to do.
+	 */
+	len = strlen(s);
+
+	if (!len) {
+		/* Empty string passed - clear override */
+		spin_lock(&dev->driver_override.lock);
+		old = dev->driver_override.name;
+		dev->driver_override.name = NULL;
+		spin_unlock(&dev->driver_override.lock);
+		kfree(old);
+
+		return 0;
+	}
+
+	cp = strnchr(s, len, '\n');
+	if (cp)
+		len = cp - s;
+
+	new = kstrndup(s, len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	spin_lock(&dev->driver_override.lock);
+	old = dev->driver_override.name;
+	if (cp != s) {
+		dev->driver_override.name = new;
+		spin_unlock(&dev->driver_override.lock);
+	} else {
+		/* "\n" passed - clear override */
+		dev->driver_override.name = NULL;
+		spin_unlock(&dev->driver_override.lock);
+
+		kfree(new);
+	}
+	kfree(old);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__device_set_driver_override);
+
 /**
  * device_is_bound() - Check if device is bound to a driver
  * @dev: device to check
diff --git a/include/linux/device.h b/include/linux/device.h
index 0be95294b6e6..e65d564f01cd 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -483,6 +483,8 @@ struct device_physical_location {
  * 		on.  This shrinks the "Board Support Packages" (BSPs) and
  * 		minimizes board-specific #ifdefs in drivers.
  * @driver_data: Private pointer for driver specific info.
+ * @driver_override: Driver name to force a match.  Do not touch directly; use
+ *		     device_set_driver_override() instead.
  * @links:	Links to suppliers and consumers of this device.
  * @power:	For device power management.
  *		See Documentation/driver-api/pm/devices.rst for details.
@@ -576,6 +578,10 @@ struct device {
 					   core doesn't touch it */
 	void		*driver_data;	/* Driver data, set and get with
 					   dev_set_drvdata/dev_get_drvdata */
+	struct {
+		const char	*name;
+		spinlock_t	lock;
+	} driver_override;
 	struct mutex		mutex;	/* mutex to synchronize calls to
 					 * its driver.
 					 */
@@ -701,6 +707,54 @@ struct device_link {
 
 #define kobj_to_dev(__kobj)	container_of_const(__kobj, struct device, kobj)
 
+int __device_set_driver_override(struct device *dev, const char *s, size_t len);
+
+/**
+ * device_set_driver_override() - Helper to set or clear driver override.
+ * @dev: Device to change
+ * @s: NUL-terminated string, new driver name to force a match, pass empty
+ *     string to clear it ("" or "\n", where the latter is only for sysfs
+ *     interface).
+ *
+ * Helper to set or clear driver override of a device.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static inline int device_set_driver_override(struct device *dev, const char *s)
+{
+	return __device_set_driver_override(dev, s, s ? strlen(s) : 0);
+}
+
+/**
+ * device_has_driver_override() - Check if a driver override has been set.
+ * @dev: device to check
+ *
+ * Returns true if a driver override has been set for this device.
+ */
+static inline bool device_has_driver_override(struct device *dev)
+{
+	guard(spinlock)(&dev->driver_override.lock);
+	return !!dev->driver_override.name;
+}
+
+/**
+ * device_match_driver_override() - Match a driver against the device's driver_override.
+ * @dev: device to check
+ * @drv: driver to match against
+ *
+ * Returns > 0 if a driver override is set and matches the given driver, 0 if a
+ * driver override is set but does not match, or < 0 if a driver override is not
+ * set at all.
+ */
+static inline int device_match_driver_override(struct device *dev,
+					       const struct device_driver *drv)
+{
+	guard(spinlock)(&dev->driver_override.lock);
+	if (dev->driver_override.name)
+		return !strcmp(dev->driver_override.name, drv->name);
+	return -1;
+}
+
 /**
  * device_iommu_mapped - Returns true when the device DMA is translated
  *			 by an IOMMU
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index 63de5f053c33..c1b463cd6464 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -65,6 +65,9 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
+ * @driver_override:	Set to true if this bus supports the driver_override
+ *			mechanism, which allows userspace to force a specific
+ *			driver to bind to a device via a sysfs attribute.
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -106,6 +109,7 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
+	bool driver_override;
 	bool need_parent_lock;
 };
 
-- 
cgit v1.2.3


From bcd085d5c76f687f5b6df049f7c415ae63a9b857 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 3 Mar 2026 12:53:19 +0100
Subject: docs: driver-model: document driver_override

Now that we support driver_override as a driver-core feature through
struct device and struct bus_type, add some documentation in the context
of how a device / driver binding is established.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260303115720.48783-3-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 Documentation/driver-api/driver-model/binding.rst | 48 +++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/Documentation/driver-api/driver-model/binding.rst b/Documentation/driver-api/driver-model/binding.rst
index d1d311a4011f..fa0888c2b3b9 100644
--- a/Documentation/driver-api/driver-model/binding.rst
+++ b/Documentation/driver-api/driver-model/binding.rst
@@ -99,3 +99,51 @@ of the driver is decremented. All symlinks between the two are removed.
 When a driver is removed, the list of devices that it supports is
 iterated over, and the driver's remove callback is called for each
 one. The device is removed from that list and the symlinks removed.
+
+
+Driver Override
+~~~~~~~~~~~~~~~
+
+Userspace may override the standard matching by writing a driver name to
+a device's ``driver_override`` sysfs attribute.  When set, only a driver
+whose name matches the override will be considered during binding.  This
+bypasses all bus-specific matching (OF, ACPI, ID tables, etc.).
+
+The override may be cleared by writing an empty string, which returns
+the device to standard matching rules.  Writing to ``driver_override``
+does not automatically unbind the device from its current driver or
+make any attempt to load the specified driver.
+
+Buses opt into this mechanism by setting the ``driver_override`` flag in
+their ``struct bus_type``::
+
+  const struct bus_type example_bus_type = {
+      ...
+      .driver_override = true,
+  };
+
+When the flag is set, the driver core automatically creates the
+``driver_override`` sysfs attribute for every device on that bus.
+
+The bus's ``match()`` callback should check the override before performing
+its own matching, using ``device_match_driver_override()``::
+
+  static int example_match(struct device *dev, const struct device_driver *drv)
+  {
+      int ret;
+
+      ret = device_match_driver_override(dev, drv);
+      if (ret >= 0)
+          return ret;
+
+      /* Fall through to bus-specific matching... */
+  }
+
+``device_match_driver_override()`` returns > 0 if the override matches
+the given driver, 0 if the override is set but does not match, or < 0 if
+no override is set at all.
+
+Additional helpers are available:
+
+- ``device_set_driver_override()`` - set or clear the override from kernel code.
+- ``device_has_driver_override()`` - check whether an override is set.
-- 
cgit v1.2.3


From 813bbc4d33d2ca5b0da63e70ae13b60874f20d37 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 3 Mar 2026 12:53:20 +0100
Subject: hwmon: axi-fan: don't use driver_override as IRQ name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Do not use driver_override as IRQ name, as it is not guaranteed to point
to a valid string; use NULL instead (which makes the devm IRQ helpers
use dev_name()).

Fixes: 8412b410fa5e ("hwmon: Support ADI Fan Control IP")
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260303115720.48783-4-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/hwmon/axi-fan-control.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/axi-fan-control.c b/drivers/hwmon/axi-fan-control.c
index b7bb325c3ad9..01590dfa55e6 100644
--- a/drivers/hwmon/axi-fan-control.c
+++ b/drivers/hwmon/axi-fan-control.c
@@ -507,7 +507,7 @@ static int axi_fan_control_probe(struct platform_device *pdev)
 	ret = devm_request_threaded_irq(&pdev->dev, ctl->irq, NULL,
 					axi_fan_control_irq_handler,
 					IRQF_ONESHOT | IRQF_TRIGGER_HIGH,
-					pdev->driver_override, ctl);
+					NULL, ctl);
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret,
 				     "failed to request an irq\n");
-- 
cgit v1.2.3


From c5f60e3f07b6609562d21efda878e83ce8860728 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 17 Mar 2026 00:37:15 +0100
Subject: sh: platform_early: remove pdev->driver_override check

In commit 507fd01d5333 ("drivers: move the early platform device support to
arch/sh") platform_match() was copied over to the sh platform_early
code, accidentally including the driver_override check.

This check does not make sense for platform_early, as sysfs is not even
available in first place at this point in the boot process, hence remove
the check.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Fixes: 507fd01d5333 ("drivers: move the early platform device support to arch/sh")
Link: https://lore.kernel.org/all/DH4M3DJ4P58T.1BGVAVXN71Z09@kernel.org/
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 arch/sh/drivers/platform_early.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c
index 143747c45206..48ddbc547bd9 100644
--- a/arch/sh/drivers/platform_early.c
+++ b/arch/sh/drivers/platform_early.c
@@ -26,10 +26,6 @@ static int platform_match(struct device *dev, struct device_driver *drv)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct platform_driver *pdrv = to_platform_driver(drv);
 
-	/* When driver_override is set, only bind to the matching driver */
-	if (pdev->driver_override)
-		return !strcmp(pdev->driver_override, drv->name);
-
 	/* Then try to match against the id table */
 	if (pdrv->id_table)
 		return platform_match_id(pdrv->id_table, pdev) != NULL;
-- 
cgit v1.2.3


From 2b38efc05bf7a8568ec74bfffea0f5cfa62bc01d Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 3 Mar 2026 12:53:21 +0100
Subject: driver core: platform: use generic driver_override infrastructure

When a driver is probed through __driver_attach(), the bus' match()
callback is called without the device lock held, thus accessing the
driver_override field without a lock, which can cause a UAF.

Fix this by using the driver-core driver_override infrastructure taking
care of proper locking internally.

Note that calling match() from __driver_attach() without the device lock
held is intentional. [1]

Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1]
Reported-by: Gui-Dong Han <hanguidong02@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789
Fixes: 3d713e0e382e ("driver core: platform: add device binding path 'driver_override'")
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260303115720.48783-5-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/base/platform.c         | 37 +++++--------------------------------
 drivers/bus/simple-pm-bus.c     |  4 ++--
 drivers/clk/imx/clk-scu.c       |  3 +--
 drivers/slimbus/qcom-ngd-ctrl.c |  6 ++----
 include/linux/platform_device.h |  5 -----
 sound/soc/samsung/i2s.c         |  6 +++---
 6 files changed, 13 insertions(+), 48 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b45d41b018ca..d44591d52e36 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -603,7 +603,6 @@ static void platform_device_release(struct device *dev)
 	kfree(pa->pdev.dev.platform_data);
 	kfree(pa->pdev.mfd_cell);
 	kfree(pa->pdev.resource);
-	kfree(pa->pdev.driver_override);
 	kfree(pa);
 }
 
@@ -1306,38 +1305,9 @@ static ssize_t numa_node_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(numa_node);
 
-static ssize_t driver_override_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	ssize_t len;
-
-	device_lock(dev);
-	len = sysfs_emit(buf, "%s\n", pdev->driver_override);
-	device_unlock(dev);
-
-	return len;
-}
-
-static ssize_t driver_override_store(struct device *dev,
-				     struct device_attribute *attr,
-				     const char *buf, size_t count)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	int ret;
-
-	ret = driver_set_override(dev, &pdev->driver_override, buf, count);
-	if (ret)
-		return ret;
-
-	return count;
-}
-static DEVICE_ATTR_RW(driver_override);
-
 static struct attribute *platform_dev_attrs[] = {
 	&dev_attr_modalias.attr,
 	&dev_attr_numa_node.attr,
-	&dev_attr_driver_override.attr,
 	NULL,
 };
 
@@ -1377,10 +1347,12 @@ static int platform_match(struct device *dev, const struct device_driver *drv)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct platform_driver *pdrv = to_platform_driver(drv);
+	int ret;
 
 	/* When driver_override is set, only bind to the matching driver */
-	if (pdev->driver_override)
-		return !strcmp(pdev->driver_override, drv->name);
+	ret = device_match_driver_override(dev, drv);
+	if (ret >= 0)
+		return ret;
 
 	/* Attempt an OF style match first */
 	if (of_driver_match_device(dev, drv))
@@ -1516,6 +1488,7 @@ static const struct dev_pm_ops platform_dev_pm_ops = {
 const struct bus_type platform_bus_type = {
 	.name		= "platform",
 	.dev_groups	= platform_dev_groups,
+	.driver_override = true,
 	.match		= platform_match,
 	.uevent		= platform_uevent,
 	.probe		= platform_probe,
diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c
index 3f00d953fb9a..c920bd6fbaaf 100644
--- a/drivers/bus/simple-pm-bus.c
+++ b/drivers/bus/simple-pm-bus.c
@@ -36,7 +36,7 @@ static int simple_pm_bus_probe(struct platform_device *pdev)
 	 * that's not listed in simple_pm_bus_of_match. We don't want to do any
 	 * of the simple-pm-bus tasks for these devices, so return early.
 	 */
-	if (pdev->driver_override)
+	if (device_has_driver_override(&pdev->dev))
 		return 0;
 
 	match = of_match_device(dev->driver->of_match_table, dev);
@@ -78,7 +78,7 @@ static void simple_pm_bus_remove(struct platform_device *pdev)
 {
 	const void *data = of_device_get_match_data(&pdev->dev);
 
-	if (pdev->driver_override || data)
+	if (device_has_driver_override(&pdev->dev) || data)
 		return;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c
index a85ec48a798b..9b33df9967ec 100644
--- a/drivers/clk/imx/clk-scu.c
+++ b/drivers/clk/imx/clk-scu.c
@@ -706,8 +706,7 @@ struct clk_hw *imx_clk_scu_alloc_dev(const char *name,
 	if (ret)
 		goto put_device;
 
-	ret = driver_set_override(&pdev->dev, &pdev->driver_override,
-				  "imx-scu-clk", strlen("imx-scu-clk"));
+	ret = device_set_driver_override(&pdev->dev, "imx-scu-clk");
 	if (ret)
 		goto put_device;
 
diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c
index 9aa7218b4e8d..1ed6be6e85d2 100644
--- a/drivers/slimbus/qcom-ngd-ctrl.c
+++ b/drivers/slimbus/qcom-ngd-ctrl.c
@@ -1535,10 +1535,8 @@ static int of_qcom_slim_ngd_register(struct device *parent,
 		ngd->id = id;
 		ngd->pdev->dev.parent = parent;
 
-		ret = driver_set_override(&ngd->pdev->dev,
-					  &ngd->pdev->driver_override,
-					  QCOM_SLIM_NGD_DRV_NAME,
-					  strlen(QCOM_SLIM_NGD_DRV_NAME));
+		ret = device_set_driver_override(&ngd->pdev->dev,
+						 QCOM_SLIM_NGD_DRV_NAME);
 		if (ret) {
 			platform_device_put(ngd->pdev);
 			kfree(ngd);
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 813da101b5bf..ed1d50d1c3c1 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -31,11 +31,6 @@ struct platform_device {
 	struct resource	*resource;
 
 	const struct platform_device_id	*id_entry;
-	/*
-	 * Driver name to force a match.  Do not set directly, because core
-	 * frees it.  Use driver_set_override() to set or clear it.
-	 */
-	const char *driver_override;
 
 	/* MFD cell pointer */
 	struct mfd_cell *mfd_cell;
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index e9964f0e010a..140907a41a70 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1360,10 +1360,10 @@ static int i2s_create_secondary_device(struct samsung_i2s_priv *priv)
 	if (!pdev_sec)
 		return -ENOMEM;
 
-	pdev_sec->driver_override = kstrdup("samsung-i2s", GFP_KERNEL);
-	if (!pdev_sec->driver_override) {
+	ret = device_set_driver_override(&pdev_sec->dev, "samsung-i2s");
+	if (ret) {
 		platform_device_put(pdev_sec);
-		return -ENOMEM;
+		return ret;
 	}
 
 	ret = platform_device_add(pdev_sec);
-- 
cgit v1.2.3


From ab93d7eee94205430fc3b0532557cb0494bf2faf Mon Sep 17 00:00:00 2001
From: Saket Dumbre <saket.dumbre@intel.com>
Date: Tue, 17 Mar 2026 20:34:49 +0100
Subject: ACPICA: Update the format of Arg3 of _DSM

To get rid of type incompatibility warnings in Linux.

Fixes: 81f92cff6d42 ("ACPICA: ACPI_TYPE_ANY does not include the package type")
Link: https://github.com/acpica/acpica/commit/4fb74872dcec
Signed-off-by: Saket Dumbre <saket.dumbre@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/12856643.O9o76ZdvQC@rafael.j.wysocki
---
 drivers/acpi/acpica/acpredef.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 6c9b5bf7d392..07d5790d09f8 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -451,7 +451,7 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 
 	{{"_DSM",
 	  METHOD_4ARGS(ACPI_TYPE_BUFFER, ACPI_TYPE_INTEGER, ACPI_TYPE_INTEGER,
-		       ACPI_TYPE_ANY | ACPI_TYPE_PACKAGE) |
+		       ACPI_TYPE_PACKAGE | ACPI_TYPE_ANY) |
 		       ARG_COUNT_IS_MINIMUM,
 	  METHOD_RETURNS(ACPI_RTYPE_ALL)}},	/* Must return a value, but it can be of any type */
 
-- 
cgit v1.2.3


From a68ed2df72131447d131531a08fe4dfcf4fa4653 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 15 Mar 2026 09:03:03 -0600
Subject: io_uring/poll: fix multishot recv missing EOF on wakeup race

When a socket send and shutdown() happen back-to-back, both fire
wake-ups before the receiver's task_work has a chance to run. The first
wake gets poll ownership (poll_refs=1), and the second bumps it to 2.
When io_poll_check_events() runs, it calls io_poll_issue() which does a
recv that reads the data and returns IOU_RETRY. The loop then drains all
accumulated refs (atomic_sub_return(2) -> 0) and exits, even though only
the first event was consumed. Since the shutdown is a persistent state
change, no further wakeups will happen, and the multishot recv can hang
forever.

Check specifically for HUP in the poll loop, and ensure that another
loop is done to check for status if more than a single poll activation
is pending. This ensures we don't lose the shutdown event.

Cc: stable@vger.kernel.org
Fixes: dbc2564cfe0f ("io_uring: let fast poll support multishot")
Reported-by: Francis Brosseau <francis@malagauche.com>
Link: https://github.com/axboe/liburing/issues/1549
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/poll.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/io_uring/poll.c b/io_uring/poll.c
index aac4b3b881fb..488c08593b64 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -272,6 +272,7 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 				atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs);
 				v &= ~IO_POLL_RETRY_FLAG;
 			}
+			v &= IO_POLL_REF_MASK;
 		}
 
 		/* the mask was stashed in __io_poll_execute */
@@ -304,8 +305,13 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			}
 		} else {
-			int ret = io_poll_issue(req, tw);
+			int ret;
 
+			/* multiple refs and HUP, ensure we loop once more */
+			if ((req->cqe.res & (POLLHUP | POLLRDHUP)) && v != 1)
+				v--;
+
+			ret = io_poll_issue(req, tw);
 			if (ret == IOU_COMPLETE)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			else if (ret == IOU_REQUEUE)
@@ -321,7 +327,6 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 		 * Release all references, retry if someone tried to restart
 		 * task_work while we were executing it.
 		 */
-		v &= IO_POLL_REF_MASK;
 	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
 
 	io_napi_add(req);
-- 
cgit v1.2.3


From 8dd1d9a335321d0829aeb85d8e1a897248d0da29 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Feb 2026 16:49:56 -0800
Subject: perf metricgroup: Fix metricgroup__has_metric_or_groups()

Use metricgroup__for_each_metric() rather than
pmu_metrics_table__for_each_metric() that combines the
default metric table with, a potentially empty, CPUID table.

Fixes: cee275edcdb1acfd ("perf metricgroup: Don't early exit if no CPUID table exists")
Reviewed-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Leo Yan <leo.yan@arm.com>
Cc: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/metricgroup.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 46bf4dfeebc8..7e39d469111b 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1605,9 +1605,9 @@ bool metricgroup__has_metric_or_groups(const char *pmu, const char *metric_or_gr
 		.metric_or_groups = metric_or_groups,
 	};
 
-	return pmu_metrics_table__for_each_metric(table,
-						  metricgroup__has_metric_or_groups_callback,
-						  &data)
+	return metricgroup__for_each_metric(table,
+					    metricgroup__has_metric_or_groups_callback,
+					    &data)
 		? true : false;
 }
 
-- 
cgit v1.2.3


From 72a8b9c060d3188ff29e2a3f3ea47b1f2a67e005 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 17 Feb 2026 14:14:56 +0100
Subject: perf parse-events: Fix big-endian 'overwrite' by writing correct
 union member

The "Read backward ring buffer" test crashes on big-endian (e.g. s390x)
due to a NULL dereference when the backward mmap path isn't enabled.

Reproducer:
  # ./perf test -F 'Read backward ring buffer'
  Segmentation fault (core dumped)
  # uname -m
  s390x
  #

Root cause:
get_config_terms() stores into evsel_config_term::val.val (u64) while later
code reads boolean fields such as evsel_config_term::val.overwrite.
On big-endian the 1-byte boolean is left-aligned, so writing
evsel_config_term::val.val = 1 is read back as
evsel_config_term::val.overwrite = 0,
leaving backward mmap disabled and a NULL map being used.

Store values in the union member that matches the term type, e.g.:
  /* for OVERWRITE */
  new_term->val.overwrite = 1;  /* not new_term->val.val = 1 */
to fix this. Improve add_config_term() and add two more parameters for
string and value. Function add_config_term() now creates a complete node
element of type evsel_config_term and handles all evsel_config_term::val
union members.

Impact:
Enables backward mmap on big-endian and prevents the crash.
No change on little-endian.

Output after:
 # ./perf test -Fv 44
 --- start ---
 Using CPUID IBM,9175,705,ME1,3.8,002f
 mmap size 1052672B
 mmap size 8192B
 ---- end ----
 44: Read backward ring buffer                         : Ok
 #

Fixes: 159ca97cd97ce8cc ("perf parse-events: Refactor get_config_terms() to remove macros")
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Jan Polensky <japo@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 82 +++++++++++++++++++++++++++++++++---------
 1 file changed, 65 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index b9efb296bba5..7b4629625b1e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1117,7 +1117,7 @@ static int config_attr(struct perf_event_attr *attr,
 
 static struct evsel_config_term *add_config_term(enum evsel_term_type type,
 						 struct list_head *head_terms,
-						 bool weak)
+						 bool weak, char *str, u64 val)
 {
 	struct evsel_config_term *t;
 
@@ -1128,8 +1128,62 @@ static struct evsel_config_term *add_config_term(enum evsel_term_type type,
 	INIT_LIST_HEAD(&t->list);
 	t->type = type;
 	t->weak	= weak;
-	list_add_tail(&t->list, head_terms);
 
+	switch (type) {
+	case EVSEL__CONFIG_TERM_PERIOD:
+	case EVSEL__CONFIG_TERM_FREQ:
+	case EVSEL__CONFIG_TERM_STACK_USER:
+	case EVSEL__CONFIG_TERM_USR_CHG_CONFIG:
+	case EVSEL__CONFIG_TERM_USR_CHG_CONFIG1:
+	case EVSEL__CONFIG_TERM_USR_CHG_CONFIG2:
+	case EVSEL__CONFIG_TERM_USR_CHG_CONFIG3:
+	case EVSEL__CONFIG_TERM_USR_CHG_CONFIG4:
+		t->val.val = val;
+		break;
+	case EVSEL__CONFIG_TERM_TIME:
+		t->val.time = val;
+		break;
+	case EVSEL__CONFIG_TERM_INHERIT:
+		t->val.inherit = val;
+		break;
+	case EVSEL__CONFIG_TERM_OVERWRITE:
+		t->val.overwrite = val;
+		break;
+	case EVSEL__CONFIG_TERM_MAX_STACK:
+		t->val.max_stack = val;
+		break;
+	case EVSEL__CONFIG_TERM_MAX_EVENTS:
+		t->val.max_events = val;
+		break;
+	case EVSEL__CONFIG_TERM_PERCORE:
+		t->val.percore = val;
+		break;
+	case EVSEL__CONFIG_TERM_AUX_OUTPUT:
+		t->val.aux_output = val;
+		break;
+	case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE:
+		t->val.aux_sample_size = val;
+		break;
+	case EVSEL__CONFIG_TERM_CALLGRAPH:
+	case EVSEL__CONFIG_TERM_BRANCH:
+	case EVSEL__CONFIG_TERM_DRV_CFG:
+	case EVSEL__CONFIG_TERM_RATIO_TO_PREV:
+	case EVSEL__CONFIG_TERM_AUX_ACTION:
+		if (str) {
+			t->val.str = strdup(str);
+			if (!t->val.str) {
+				zfree(&t);
+				return NULL;
+			}
+			t->free_str = true;
+		}
+		break;
+	default:
+		t->val.val = val;
+		break;
+	}
+
+	list_add_tail(&t->list, head_terms);
 	return t;
 }
 
@@ -1142,7 +1196,7 @@ static int get_config_terms(const struct parse_events_terms *head_config,
 		struct evsel_config_term *new_term;
 		enum evsel_term_type new_type;
 		bool str_type = false;
-		u64 val;
+		u64 val = 0;
 
 		switch (term->type_term) {
 		case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
@@ -1234,20 +1288,15 @@ static int get_config_terms(const struct parse_events_terms *head_config,
 			continue;
 		}
 
-		new_term = add_config_term(new_type, head_terms, term->weak);
+		/*
+		 * Note: Members evsel_config_term::val and
+		 * parse_events_term::val are unions and endianness needs
+		 * to be taken into account when changing such union members.
+		 */
+		new_term = add_config_term(new_type, head_terms, term->weak,
+					   str_type ? term->val.str : NULL, val);
 		if (!new_term)
 			return -ENOMEM;
-
-		if (str_type) {
-			new_term->val.str = strdup(term->val.str);
-			if (!new_term->val.str) {
-				zfree(&new_term);
-				return -ENOMEM;
-			}
-			new_term->free_str = true;
-		} else {
-			new_term->val.val = val;
-		}
 	}
 	return 0;
 }
@@ -1277,10 +1326,9 @@ static int add_cfg_chg(const struct perf_pmu *pmu,
 	if (bits) {
 		struct evsel_config_term *new_term;
 
-		new_term = add_config_term(new_term_type, head_terms, false);
+		new_term = add_config_term(new_term_type, head_terms, false, NULL, bits);
 		if (!new_term)
 			return -ENOMEM;
-		new_term->val.cfg_chg = bits;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 563d39928db602c58d24301769e25e33a48a65ab Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Sun, 1 Mar 2026 17:43:25 +0000
Subject: perf kvm stat: Fix relative paths for including headers

Add an extra "../" to the relative paths so that the uAPI headers
provided by tools can be found correctly.

Fixes: a724a8fce5e25b45 ("perf kvm stat: Fix build error")
Reported-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Ian Rogers <irogers@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/kvm-stat-arch/kvm-stat-x86.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c
index 43275d25b6cb..0f626db3a439 100644
--- a/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c
+++ b/tools/perf/util/kvm-stat-arch/kvm-stat-x86.c
@@ -4,9 +4,9 @@
 #include "../kvm-stat.h"
 #include "../evsel.h"
 #include "../env.h"
-#include "../../arch/x86/include/uapi/asm/svm.h"
-#include "../../arch/x86/include/uapi/asm/vmx.h"
-#include "../../arch/x86/include/uapi/asm/kvm.h"
+#include "../../../arch/x86/include/uapi/asm/svm.h"
+#include "../../../arch/x86/include/uapi/asm/vmx.h"
+#include "../../../arch/x86/include/uapi/asm/kvm.h"
 #include <subcmd/parse-options.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
-- 
cgit v1.2.3


From 0ffba246652faf4a36aedc66059c2f94e4c83ea5 Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Sat, 14 Feb 2026 19:46:32 +0000
Subject: igc: fix missing update of skb->tail in igc_xmit_frame()

igc_xmit_frame() misses updating skb->tail when the packet size is
shorter than the minimum one.
Use skb_put_padto() in alignment with other Intel Ethernet drivers.

Fixes: 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers")
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index b2e8d0c0f827..1c5d7b23f225 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1730,11 +1730,8 @@ static netdev_tx_t igc_xmit_frame(struct sk_buff *skb,
 	/* The minimum packet size with TCTL.PSP set is 17 so pad the skb
 	 * in order to meet this minimum size requirement.
 	 */
-	if (skb->len < 17) {
-		if (skb_padto(skb, 17))
-			return NETDEV_TX_OK;
-		skb->len = 17;
-	}
+	if (skb_put_padto(skb, 17))
+		return NETDEV_TX_OK;
 
 	return igc_xmit_frame_ring(skb, igc_tx_queue_mapping(adapter, skb));
 }
-- 
cgit v1.2.3


From 45b33e805bd39f615d9353a7194b2da5281332df Mon Sep 17 00:00:00 2001
From: Zdenek Bouska <zdenek.bouska@siemens.com>
Date: Wed, 25 Feb 2026 10:58:29 +0100
Subject: igc: fix page fault in XDP TX timestamps handling

If an XDP application that requested TX timestamping is shutting down
while the link of the interface in use is still up the following kernel
splat is reported:

[  883.803618] [   T1554] BUG: unable to handle page fault for address: ffffcfb6200fd008
...
[  883.803650] [   T1554] Call Trace:
[  883.803652] [   T1554]  <TASK>
[  883.803654] [   T1554]  igc_ptp_tx_tstamp_event+0xdf/0x160 [igc]
[  883.803660] [   T1554]  igc_tsync_interrupt+0x2d5/0x300 [igc]
...

During shutdown of the TX ring the xsk_meta pointers are left behind, so
that the IRQ handler is trying to touch them.

This issue is now being fixed by cleaning up the stale xsk meta data on
TX shutdown. TX timestamps on other queues remain unaffected.

Fixes: 15fd021bc427 ("igc: Add Tx hardware timestamp request for AF_XDP zero-copy packet")
Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Florian Bezdeka <florian.bezdeka@siemens.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      |  2 ++
 drivers/net/ethernet/intel/igc/igc_main.c |  7 +++++++
 drivers/net/ethernet/intel/igc/igc_ptp.c  | 33 +++++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index a427f05814c1..17236813965d 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -781,6 +781,8 @@ int igc_ptp_hwtstamp_set(struct net_device *netdev,
 			 struct kernel_hwtstamp_config *config,
 			 struct netlink_ext_ack *extack);
 void igc_ptp_tx_hang(struct igc_adapter *adapter);
+void igc_ptp_clear_xsk_tx_tstamp_queue(struct igc_adapter *adapter,
+				       u16 queue_id);
 void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts);
 void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 1c5d7b23f225..72bc5128d8b8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -264,6 +264,13 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
 	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
+
+	/* Clear any lingering XSK TX timestamp requests */
+	if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) {
+		struct igc_adapter *adapter = netdev_priv(tx_ring->netdev);
+
+		igc_ptp_clear_xsk_tx_tstamp_queue(adapter, tx_ring->queue_index);
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 44ee19386766..3d6b2264164a 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -577,6 +577,39 @@ static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter)
 	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
 
+/**
+ * igc_ptp_clear_xsk_tx_tstamp_queue - Clear pending XSK TX timestamps for a queue
+ * @adapter: Board private structure
+ * @queue_id: TX queue index to clear timestamps for
+ *
+ * Iterates over all TX timestamp registers and releases any pending
+ * timestamp requests associated with the given TX queue. This is
+ * called when an XDP pool is being disabled to ensure no stale
+ * timestamp references remain.
+ */
+void igc_ptp_clear_xsk_tx_tstamp_queue(struct igc_adapter *adapter, u16 queue_id)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
+
+	for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+		struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i];
+
+		if (tstamp->buffer_type != IGC_TX_BUFFER_TYPE_XSK)
+			continue;
+		if (tstamp->xsk_queue_index != queue_id)
+			continue;
+		if (!tstamp->xsk_tx_buffer)
+			continue;
+
+		igc_ptp_free_tx_buffer(adapter, tstamp);
+	}
+
+	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
+}
+
 static void igc_ptp_disable_tx_timestamp(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-- 
cgit v1.2.3


From fc9c69be594756b81b54c6bc40803fa6052f35ae Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 25 Feb 2026 11:01:37 +0100
Subject: iavf: fix VLAN filter lost on add/delete race

When iavf_add_vlan() finds an existing filter in IAVF_VLAN_REMOVE
state, it transitions the filter to IAVF_VLAN_ACTIVE assuming the
pending delete can simply be cancelled. However, there is no guarantee
that iavf_del_vlans() has not already processed the delete AQ request
and removed the filter from the PF. In that case the filter remains in
the driver's list as IAVF_VLAN_ACTIVE but is no longer programmed on
the NIC. Since iavf_add_vlans() only picks up filters in
IAVF_VLAN_ADD state, the filter is never re-added, and spoof checking
drops all traffic for that VLAN.

  CPU0                       CPU1                     Workqueue
  ----                       ----                     ---------
  iavf_del_vlan(vlan 100)
    f->state = REMOVE
    schedule AQ_DEL_VLAN
                             iavf_add_vlan(vlan 100)
                               f->state = ACTIVE
                                                      iavf_del_vlans()
                                                        f is ACTIVE, skip
                                                      iavf_add_vlans()
                                                        f is ACTIVE, skip

  Filter is ACTIVE in driver but absent from NIC.

Transition to IAVF_VLAN_ADD instead and schedule
IAVF_FLAG_AQ_ADD_VLAN_FILTER so iavf_add_vlans() re-programs the
filter.  A duplicate add is idempotent on the PF.

Fixes: 0c0da0e95105 ("iavf: refactor VLAN filter states")
Signed-off-by: Petr Oros <poros@redhat.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 7925ee152c76..dad001abc908 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -757,10 +757,13 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		adapter->num_vlan_filters++;
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
 	} else if (f->state == IAVF_VLAN_REMOVE) {
-		/* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed.
-		 * We can safely only change the state here.
+		/* Re-add the filter since we cannot tell whether the
+		 * pending delete has already been processed by the PF.
+		 * A duplicate add is harmless.
 		 */
-		f->state = IAVF_VLAN_ACTIVE;
+		f->state = IAVF_VLAN_ADD;
+		iavf_schedule_aq_request(adapter,
+					 IAVF_FLAG_AQ_ADD_VLAN_FILTER);
 	}
 
 clearout:
-- 
cgit v1.2.3


From 6850deb61118345996f03b87817b4ae0f2f25c38 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 11 Feb 2026 10:10:08 +0100
Subject: libie: prevent memleak in fwlog code

All cmd_buf buffers are allocated and need to be freed after usage.
Add an error unwinding path that properly frees these buffers.

The memory leak happens whenever fwlog configuration is changed. For
example:

$echo 256K > /sys/kernel/debug/ixgbe/0000\:32\:00.0/fwlog/log_size

Fixes: 96a9a9341cda ("ice: configure FW logging")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/libie/fwlog.c | 49 +++++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c
index 4d0c8370386b..96bba57c8a5b 100644
--- a/drivers/net/ethernet/intel/libie/fwlog.c
+++ b/drivers/net/ethernet/intel/libie/fwlog.c
@@ -433,17 +433,21 @@ libie_debugfs_module_write(struct file *filp, const char __user *buf,
 	module = libie_find_module_by_dentry(fwlog->debugfs_modules, dentry);
 	if (module < 0) {
 		dev_info(dev, "unknown module\n");
-		return -EINVAL;
+		count = -EINVAL;
+		goto free_cmd_buf;
 	}
 
 	cnt = sscanf(cmd_buf, "%s", user_val);
-	if (cnt != 1)
-		return -EINVAL;
+	if (cnt != 1) {
+		count = -EINVAL;
+		goto free_cmd_buf;
+	}
 
 	log_level = sysfs_match_string(libie_fwlog_level_string, user_val);
 	if (log_level < 0) {
 		dev_info(dev, "unknown log level '%s'\n", user_val);
-		return -EINVAL;
+		count = -EINVAL;
+		goto free_cmd_buf;
 	}
 
 	if (module != LIBIE_AQC_FW_LOG_ID_MAX) {
@@ -458,6 +462,9 @@ libie_debugfs_module_write(struct file *filp, const char __user *buf,
 			fwlog->cfg.module_entries[i].log_level = log_level;
 	}
 
+free_cmd_buf:
+	kfree(cmd_buf);
+
 	return count;
 }
 
@@ -515,23 +522,31 @@ libie_debugfs_nr_messages_write(struct file *filp, const char __user *buf,
 		return PTR_ERR(cmd_buf);
 
 	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
+	if (ret != 1) {
+		count = -EINVAL;
+		goto free_cmd_buf;
+	}
 
 	ret = kstrtos16(user_val, 0, &nr_messages);
-	if (ret)
-		return ret;
+	if (ret) {
+		count = ret;
+		goto free_cmd_buf;
+	}
 
 	if (nr_messages < LIBIE_AQC_FW_LOG_MIN_RESOLUTION ||
 	    nr_messages > LIBIE_AQC_FW_LOG_MAX_RESOLUTION) {
 		dev_err(dev, "Invalid FW log number of messages %d, value must be between %d - %d\n",
 			nr_messages, LIBIE_AQC_FW_LOG_MIN_RESOLUTION,
 			LIBIE_AQC_FW_LOG_MAX_RESOLUTION);
-		return -EINVAL;
+		count = -EINVAL;
+		goto free_cmd_buf;
 	}
 
 	fwlog->cfg.log_resolution = nr_messages;
 
+free_cmd_buf:
+	kfree(cmd_buf);
+
 	return count;
 }
 
@@ -588,8 +603,10 @@ libie_debugfs_enable_write(struct file *filp, const char __user *buf,
 		return PTR_ERR(cmd_buf);
 
 	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
+	if (ret != 1) {
+		ret = -EINVAL;
+		goto free_cmd_buf;
+	}
 
 	ret = kstrtobool(user_val, &enable);
 	if (ret)
@@ -624,6 +641,8 @@ enable_write_error:
 	 */
 	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
 		ret = -EIO;
+free_cmd_buf:
+	kfree(cmd_buf);
 
 	return ret;
 }
@@ -682,8 +701,10 @@ libie_debugfs_log_size_write(struct file *filp, const char __user *buf,
 		return PTR_ERR(cmd_buf);
 
 	ret = sscanf(cmd_buf, "%s", user_val);
-	if (ret != 1)
-		return -EINVAL;
+	if (ret != 1) {
+		ret = -EINVAL;
+		goto free_cmd_buf;
+	}
 
 	index = sysfs_match_string(libie_fwlog_log_size, user_val);
 	if (index < 0) {
@@ -712,6 +733,8 @@ log_size_write_error:
 	 */
 	if (WARN_ON(ret != (ssize_t)count && ret >= 0))
 		ret = -EIO;
+free_cmd_buf:
+	kfree(cmd_buf);
 
 	return ret;
 }
-- 
cgit v1.2.3


From e9f58ff991dd4be13fd7a651bbf64329c090af09 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 16 Mar 2026 11:04:46 -0400
Subject: drm/amdgpu: rework how we handle TLB fences
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new VM flag to indicate whether or not we need
a TLB fence.  Userqs (KFD or KGD) require a TLB fence.
A TLB fence is not strictly required for kernel queues,
but it shouldn't hurt.  That said, enabling this
unconditionally should be fine, but it seems to tickle
some issues in KIQ/MES.  Only enable them for KFD,
or when KGD userq queues are enabled (currently via module
parameter).

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4798
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4749
Fixes: f3854e04b708 ("drm/amdgpu: attach tlb fence to the PTs update")
Cc: Christian König <christian.koenig@amd.com>
Cc: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 69c5fbd2b93b5ced77c6e79afe83371bca84c788)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 ++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index f2beb980e3c3..c60cbce356cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1069,7 +1069,10 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
 	}
 
 	/* Prepare a TLB flush fence to be attached to PTs */
-	if (!params->unlocked) {
+	/* The check for need_tlb_fence should be dropped once we
+	 * sort out the issues with KIQ/MES TLB invalidation timeouts.
+	 */
+	if (!params->unlocked && vm->need_tlb_fence) {
 		amdgpu_vm_tlb_fence_create(params->adev, vm, fence);
 
 		/* Makes sure no PD/PT is freed before the flush */
@@ -2602,6 +2605,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ttm_lru_bulk_move_init(&vm->lru_bulk_move);
 
 	vm->is_compute_context = false;
+	vm->need_tlb_fence = amdgpu_userq_enabled(&adev->ddev);
 
 	vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
 				    AMDGPU_VM_USE_CPU_FOR_GFX);
@@ -2739,6 +2743,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	dma_fence_put(vm->last_update);
 	vm->last_update = dma_fence_get_stub();
 	vm->is_compute_context = true;
+	vm->need_tlb_fence = true;
 
 unreserve_bo:
 	amdgpu_bo_unreserve(vm->root.bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 806d62ed61ef..bb276c0ad06d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -441,6 +441,8 @@ struct amdgpu_vm {
 	struct ttm_lru_bulk_move lru_bulk_move;
 	/* Flag to indicate if VM is used for compute */
 	bool			is_compute_context;
+	/* Flag to indicate if VM needs a TLB fence (KFD or KGD) */
+	bool			need_tlb_fence;
 
 	/* Memory partition number, -1 means any partition */
 	int8_t			mem_id;
-- 
cgit v1.2.3


From 9787f7da186ee8143b7b6d914cfa0b6e7fee2648 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Sep 2023 10:44:07 -0400
Subject: drm/amdgpu: apply state adjust rules to some additional HAINAN
 vairants

They need a similar workaround.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1839
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 0de31d92a173d3d94f28051b0b80a6c98913aed4)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 61b1c5aa74cb..36942467d4ad 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -3454,9 +3454,11 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 	if (adev->asic_type == CHIP_HAINAN) {
 		if ((adev->pdev->revision == 0x81) ||
 		    (adev->pdev->revision == 0xC3) ||
+		    (adev->pdev->device == 0x6660) ||
 		    (adev->pdev->device == 0x6664) ||
 		    (adev->pdev->device == 0x6665) ||
-		    (adev->pdev->device == 0x6667)) {
+		    (adev->pdev->device == 0x6667) ||
+		    (adev->pdev->device == 0x666F)) {
 			max_sclk = 75000;
 		}
 		if ((adev->pdev->revision == 0xC3) ||
-- 
cgit v1.2.3


From 86650ee2241ff84207eaa298ab318533f3c21a38 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Sep 2023 10:44:06 -0400
Subject: drm/radeon: apply state adjust rules to some additional HAINAN
 vairants

They need a similar workaround.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1839
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 87327658c848f56eac166cb382b57b83bf06c5ac)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/si_dpm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index b4aa49b1ac63..4b10715f951c 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2915,9 +2915,11 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 	if (rdev->family == CHIP_HAINAN) {
 		if ((rdev->pdev->revision == 0x81) ||
 		    (rdev->pdev->revision == 0xC3) ||
+		    (rdev->pdev->device == 0x6660) ||
 		    (rdev->pdev->device == 0x6664) ||
 		    (rdev->pdev->device == 0x6665) ||
-		    (rdev->pdev->device == 0x6667)) {
+		    (rdev->pdev->device == 0x6667) ||
+		    (rdev->pdev->device == 0x666F)) {
 			max_sclk = 75000;
 		}
 		if ((rdev->pdev->revision == 0xC3) ||
-- 
cgit v1.2.3


From c925fccc4f8fae4354d98b2af606bd4747d3738d Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Tue, 17 Mar 2026 17:36:53 +0000
Subject: hwmon: (pmbus/hac300s) Add error check for pmbus_read_word_data()
 return value

hac300s_read_word_data() passes the return value of pmbus_read_word_data()
directly to FIELD_GET() without checking for errors. If the I2C transaction
fails, a negative error code is sign-extended and passed to FIELD_GET(),
which silently produces garbage data instead of propagating the error.

Add the missing error check before using the return value in
the FIELD_GET() macro.

Fixes: 669cf162f7a1 ("hwmon: Add support for HiTRON HAC300S PSU")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260317173308.382545-2-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/hac300s.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/pmbus/hac300s.c b/drivers/hwmon/pmbus/hac300s.c
index 0a1d52cae91e..a073db1cfe2e 100644
--- a/drivers/hwmon/pmbus/hac300s.c
+++ b/drivers/hwmon/pmbus/hac300s.c
@@ -58,6 +58,8 @@ static int hac300s_read_word_data(struct i2c_client *client, int page,
 	case PMBUS_MFR_VOUT_MIN:
 	case PMBUS_READ_VOUT:
 		rv = pmbus_read_word_data(client, page, phase, reg);
+		if (rv < 0)
+			return rv;
 		return FIELD_GET(LINEAR11_MANTISSA_MASK, rv);
 	default:
 		return -ENODATA;
-- 
cgit v1.2.3


From 19d4b9c8a136704d5f2544e7ac550f27918a5004 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Tue, 17 Mar 2026 17:37:17 +0000
Subject: hwmon: (pmbus/mp2975) Add error check for pmbus_read_word_data()
 return value

mp2973_read_word_data() XORs the return value of pmbus_read_word_data()
with PB_STATUS_POWER_GOOD_N without first checking for errors. If the I2C
transaction fails, a negative error code is XORed with the constant,
producing a corrupted value that is returned as valid status data instead
of propagating the error.

Add the missing error check before modifying the return value.

Fixes: acda945afb465 ("hwmon: (pmbus/mp2975) Fix PGOOD in READ_STATUS_WORD")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260317173308.382545-3-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/mp2975.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c
index c31982d85196..d0bc47b12cb0 100644
--- a/drivers/hwmon/pmbus/mp2975.c
+++ b/drivers/hwmon/pmbus/mp2975.c
@@ -313,6 +313,8 @@ static int mp2973_read_word_data(struct i2c_client *client, int page,
 	case PMBUS_STATUS_WORD:
 		/* MP2973 & MP2971 return PGOOD instead of PB_STATUS_POWER_GOOD_N. */
 		ret = pmbus_read_word_data(client, page, phase, reg);
+		if (ret < 0)
+			return ret;
 		ret ^= PB_STATUS_POWER_GOOD_N;
 		break;
 	case PMBUS_OT_FAULT_LIMIT:
-- 
cgit v1.2.3


From c6f45ed26b6eb4766db06f21ff28a97ed485bcbb Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Tue, 17 Mar 2026 17:37:41 +0000
Subject: hwmon: (pmbus/mp2869) Check pmbus_read_byte_data() before using its
 return value

In mp2869_read_byte_data() and mp2869_read_word_data(), the return value
of pmbus_read_byte_data() for PMBUS_STATUS_MFR_SPECIFIC is used directly
inside FIELD_GET() macro arguments without error checking. If the I2C
transaction fails, a negative error code is passed to FIELD_GET() and
FIELD_PREP(), silently corrupting the status register bits being
constructed.

Extract the nested pmbus_read_byte_data() calls into a separate variable
and check for errors before use. This also eliminates a redundant duplicate
read of the same register in the PMBUS_STATUS_TEMPERATURE case.

Fixes: a3a2923aaf7f2 ("hwmon: add MP2869,MP29608,MP29612 and MP29816 series driver")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260317173308.382545-4-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/mp2869.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/drivers/hwmon/pmbus/mp2869.c b/drivers/hwmon/pmbus/mp2869.c
index cc69a1e91dfe..4647892e5112 100644
--- a/drivers/hwmon/pmbus/mp2869.c
+++ b/drivers/hwmon/pmbus/mp2869.c
@@ -165,7 +165,7 @@ static int mp2869_read_byte_data(struct i2c_client *client, int page, int reg)
 {
 	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
 	struct mp2869_data *data = to_mp2869_data(info);
-	int ret;
+	int ret, mfr;
 
 	switch (reg) {
 	case PMBUS_VOUT_MODE:
@@ -188,11 +188,14 @@ static int mp2869_read_byte_data(struct i2c_client *client, int page, int reg)
 		if (ret < 0)
 			return ret;
 
+		mfr = pmbus_read_byte_data(client, page,
+					   PMBUS_STATUS_MFR_SPECIFIC);
+		if (mfr < 0)
+			return mfr;
+
 		ret = (ret & ~GENMASK(2, 2)) |
 			FIELD_PREP(GENMASK(2, 2),
-				   FIELD_GET(GENMASK(1, 1),
-					     pmbus_read_byte_data(client, page,
-								  PMBUS_STATUS_MFR_SPECIFIC)));
+				   FIELD_GET(GENMASK(1, 1), mfr));
 		break;
 	case PMBUS_STATUS_TEMPERATURE:
 		/*
@@ -207,15 +210,16 @@ static int mp2869_read_byte_data(struct i2c_client *client, int page, int reg)
 		if (ret < 0)
 			return ret;
 
+		mfr = pmbus_read_byte_data(client, page,
+					   PMBUS_STATUS_MFR_SPECIFIC);
+		if (mfr < 0)
+			return mfr;
+
 		ret = (ret & ~GENMASK(7, 6)) |
 			FIELD_PREP(GENMASK(6, 6),
-				   FIELD_GET(GENMASK(1, 1),
-					     pmbus_read_byte_data(client, page,
-								  PMBUS_STATUS_MFR_SPECIFIC))) |
+				   FIELD_GET(GENMASK(1, 1), mfr)) |
 			 FIELD_PREP(GENMASK(7, 7),
-				    FIELD_GET(GENMASK(1, 1),
-					      pmbus_read_byte_data(client, page,
-								   PMBUS_STATUS_MFR_SPECIFIC)));
+				    FIELD_GET(GENMASK(1, 1), mfr));
 		break;
 	default:
 		ret = -ENODATA;
@@ -230,7 +234,7 @@ static int mp2869_read_word_data(struct i2c_client *client, int page, int phase,
 {
 	const struct pmbus_driver_info *info = pmbus_get_driver_info(client);
 	struct mp2869_data *data = to_mp2869_data(info);
-	int ret;
+	int ret, mfr;
 
 	switch (reg) {
 	case PMBUS_STATUS_WORD:
@@ -246,11 +250,14 @@ static int mp2869_read_word_data(struct i2c_client *client, int page, int phase,
 		if (ret < 0)
 			return ret;
 
+		mfr = pmbus_read_byte_data(client, page,
+					   PMBUS_STATUS_MFR_SPECIFIC);
+		if (mfr < 0)
+			return mfr;
+
 		ret = (ret & ~GENMASK(2, 2)) |
 			 FIELD_PREP(GENMASK(2, 2),
-				    FIELD_GET(GENMASK(1, 1),
-					      pmbus_read_byte_data(client, page,
-								   PMBUS_STATUS_MFR_SPECIFIC)));
+				    FIELD_GET(GENMASK(1, 1), mfr));
 		break;
 	case PMBUS_READ_VIN:
 		/*
-- 
cgit v1.2.3


From 32f59301b9898c0ab5e72908556d553e2d481945 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Tue, 17 Mar 2026 17:46:31 +0000
Subject: hwmon: (pmbus/ina233) Add error check for pmbus_read_word_data()
 return value

ina233_read_word_data() uses the return value of pmbus_read_word_data()
directly in a DIV_ROUND_CLOSEST() computation without first checking for
errors. If the underlying I2C transaction fails, a negative error code is
used in the arithmetic, producing a garbage sensor value instead of
propagating the error.

Add the missing error check before using the return value.

Fixes: b64b6cb163f16 ("hwmon: Add driver for TI INA233 Current and Power Monitor")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260317174553.385567-1-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/ina233.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/pmbus/ina233.c b/drivers/hwmon/pmbus/ina233.c
index dde1e1678394..2d8b5a5347ed 100644
--- a/drivers/hwmon/pmbus/ina233.c
+++ b/drivers/hwmon/pmbus/ina233.c
@@ -67,6 +67,8 @@ static int ina233_read_word_data(struct i2c_client *client, int page,
 	switch (reg) {
 	case PMBUS_VIRT_READ_VMON:
 		ret = pmbus_read_word_data(client, 0, 0xff, MFR_READ_VSHUNT);
+		if (ret < 0)
+			return ret;
 
 		/* Adjust returned value to match VIN coefficients */
 		/* VIN: 1.25 mV VSHUNT: 2.5 uV LSB */
-- 
cgit v1.2.3


From 64dcbde7f8f870a4f2d9daf24ffb06f9748b5dd3 Mon Sep 17 00:00:00 2001
From: Junrui Luo <moonafterrain@outlook.com>
Date: Sat, 14 Mar 2026 17:41:04 +0800
Subject: bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler

The ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER handler in
bnxt_async_event_process() uses a firmware-supplied 'type' field
directly as an index into bp->bs_trace[] without bounds validation.

The 'type' field is a 16-bit value extracted from DMA-mapped completion
ring memory that the NIC writes directly to host RAM. A malicious or
compromised NIC can supply any value from 0 to 65535, causing an
out-of-bounds access into kernel heap memory.

The bnxt_bs_trace_check_wrap() call then dereferences bs_trace->magic_byte
and writes to bs_trace->last_offset and bs_trace->wrapped, leading to
kernel memory corruption or a crash.

Fix by adding a bounds check and defining BNXT_TRACE_MAX as
DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE + 1 to cover all currently
defined firmware trace types (0x0 through 0xc).

Fixes: 84fcd9449fd7 ("bnxt_en: Manage the FW trace context memory")
Reported-by: Yuhao Jiang <danisjiang@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Junrui Luo <moonafterrain@outlook.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/SYBPR01MB7881A253A1C9775D277F30E9AF42A@SYBPR01MB7881.ausprd01.prod.outlook.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c426a41c3663..0751c0e4581a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2929,6 +2929,8 @@ static int bnxt_async_event_process(struct bnxt *bp,
 		u16 type = (u16)BNXT_EVENT_BUF_PRODUCER_TYPE(data1);
 		u32 offset =  BNXT_EVENT_BUF_PRODUCER_OFFSET(data2);
 
+		if (type >= ARRAY_SIZE(bp->bs_trace))
+			goto async_event_process_exit;
 		bnxt_bs_trace_check_wrap(&bp->bs_trace[type], offset);
 		goto async_event_process_exit;
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9a41b9e0423c..a97d651130df 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2146,7 +2146,7 @@ enum board_idx {
 };
 
 #define BNXT_TRACE_BUF_MAGIC_BYTE ((u8)0xbc)
-#define BNXT_TRACE_MAX 11
+#define BNXT_TRACE_MAX (DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE + 1)
 
 struct bnxt_bs_trace_info {
 	u8 *magic_byte;
-- 
cgit v1.2.3


From d56c9cca2e7f8f0ad91f37abd4e6357c2318b0db Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Tue, 17 Mar 2026 13:56:28 +0800
Subject: HID: Intel-thc-hid: Intel-quicki2c: Add NVL Device IDs

Add Nova Lake THC QuickI2C device IDs to support list.

Signed-off-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c | 7 +++++++
 drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h | 4 ++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
index f178017352ba..46d3e9a01999 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
@@ -26,6 +26,11 @@ static struct quicki2c_ddata ptl_ddata = {
 	.max_interrupt_delay = MAX_RX_INTERRUPT_DELAY,
 };
 
+static struct quicki2c_ddata nvl_ddata = {
+	.max_detect_size = MAX_RX_DETECT_SIZE_NVL,
+	.max_interrupt_delay = MAX_RX_INTERRUPT_DELAY,
+};
+
 /* THC QuickI2C ACPI method to get device properties */
 /* HIDI2C device method */
 static guid_t i2c_hid_guid =
@@ -1032,6 +1037,8 @@ static const struct pci_device_id quicki2c_pci_tbl[] = {
 	{ PCI_DEVICE_DATA(INTEL, THC_PTL_U_DEVICE_ID_I2C_PORT2, &ptl_ddata) },
 	{ PCI_DEVICE_DATA(INTEL, THC_WCL_DEVICE_ID_I2C_PORT1, &ptl_ddata) },
 	{ PCI_DEVICE_DATA(INTEL, THC_WCL_DEVICE_ID_I2C_PORT2, &ptl_ddata) },
+	{ PCI_DEVICE_DATA(INTEL, THC_NVL_H_DEVICE_ID_I2C_PORT1, &nvl_ddata) },
+	{ PCI_DEVICE_DATA(INTEL, THC_NVL_H_DEVICE_ID_I2C_PORT2, &nvl_ddata) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, quicki2c_pci_tbl);
diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
index 33a1e3db1cb2..61dbdece59a1 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
@@ -15,6 +15,8 @@
 #define PCI_DEVICE_ID_INTEL_THC_PTL_U_DEVICE_ID_I2C_PORT2	0xE44A
 #define PCI_DEVICE_ID_INTEL_THC_WCL_DEVICE_ID_I2C_PORT1 	0x4D48
 #define PCI_DEVICE_ID_INTEL_THC_WCL_DEVICE_ID_I2C_PORT2 	0x4D4A
+#define PCI_DEVICE_ID_INTEL_THC_NVL_H_DEVICE_ID_I2C_PORT1	0xD348
+#define PCI_DEVICE_ID_INTEL_THC_NVL_H_DEVICE_ID_I2C_PORT2	0xD34A
 
 /* Packet size value, the unit is 16 bytes */
 #define MAX_PACKET_SIZE_VALUE_LNL			256
@@ -40,6 +42,8 @@
 
 /* PTL Max packet size detection capability is 255 Bytes */
 #define MAX_RX_DETECT_SIZE_PTL			255
+/* NVL Max packet size detection capability is 64K Bytes */
+#define MAX_RX_DETECT_SIZE_NVL			65535
 /* Max interrupt delay capability is 2.56ms */
 #define MAX_RX_INTERRUPT_DELAY			256
 
-- 
cgit v1.2.3


From 48e91af0cbe942d50ef6257d850accdca1d01378 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Tue, 17 Mar 2026 13:56:29 +0800
Subject: HID: Intel-thc-hid: Intel-quickspi: Add NVL Device IDs

Add Nova Lake THC QuickSPI device IDs to support list.

Signed-off-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c | 6 ++++++
 drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
index ad6bd59963b2..b6a69995692c 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
@@ -37,6 +37,10 @@ struct quickspi_driver_data arl = {
 	.max_packet_size_value = MAX_PACKET_SIZE_VALUE_MTL,
 };
 
+struct quickspi_driver_data nvl = {
+	.max_packet_size_value = MAX_PACKET_SIZE_VALUE_LNL,
+};
+
 /* THC QuickSPI ACPI method to get device properties */
 /* HIDSPI Method: {6e2ac436-0fcf-41af-a265-b32a220dcfab} */
 static guid_t hidspi_guid =
@@ -982,6 +986,8 @@ static const struct pci_device_id quickspi_pci_tbl[] = {
 	{PCI_DEVICE_DATA(INTEL, THC_WCL_DEVICE_ID_SPI_PORT2, &ptl), },
 	{PCI_DEVICE_DATA(INTEL, THC_ARL_DEVICE_ID_SPI_PORT1, &arl), },
 	{PCI_DEVICE_DATA(INTEL, THC_ARL_DEVICE_ID_SPI_PORT2, &arl), },
+	{PCI_DEVICE_DATA(INTEL, THC_NVL_H_DEVICE_ID_SPI_PORT1, &nvl), },
+	{PCI_DEVICE_DATA(INTEL, THC_NVL_H_DEVICE_ID_SPI_PORT2, &nvl), },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, quickspi_pci_tbl);
diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
index c30e1a42eb09..bf5e18f5a5f4 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-dev.h
@@ -23,6 +23,8 @@
 #define PCI_DEVICE_ID_INTEL_THC_WCL_DEVICE_ID_SPI_PORT2 	0x4D4B
 #define PCI_DEVICE_ID_INTEL_THC_ARL_DEVICE_ID_SPI_PORT1 	0x7749
 #define PCI_DEVICE_ID_INTEL_THC_ARL_DEVICE_ID_SPI_PORT2 	0x774B
+#define PCI_DEVICE_ID_INTEL_THC_NVL_H_DEVICE_ID_SPI_PORT1	0xD349
+#define PCI_DEVICE_ID_INTEL_THC_NVL_H_DEVICE_ID_SPI_PORT2	0xD34B
 
 /* HIDSPI special ACPI parameters DSM methods */
 #define ACPI_QUICKSPI_REVISION_NUM			2
-- 
cgit v1.2.3


From 5258572aa5fd5a7ed01b123b28241e0281b6fb9b Mon Sep 17 00:00:00 2001
From: Nicholas Carlini <nicholas@carlini.com>
Date: Mon, 9 Mar 2026 08:29:49 +0900
Subject: ksmbd: fix share_conf UAF in tree_conn disconnect

__ksmbd_tree_conn_disconnect() drops the share_conf reference before
checking tree_conn->refcount. When someone uses SMB3 multichannel and
binds two connections to one session, a SESSION_LOGOFF on connection A
calls ksmbd_conn_wait_idle(conn) which only drains connection A's
request counter, not connection B's. This means there's a race condition:
requests already dispatched on connection B hold tree_conn references via
work->tcon. The disconnect path frees share_conf while those requests
are still walking work->tcon->share_conf, causing a use-after-free.

This fix combines the share_conf put with the tree_conn free so it
only happens when the last reference is dropped.

Fixes: b39a1833cc4a ("ksmbd: fix use-after-free in ksmbd_tree_connect_put under concurrency")
Signed-off-by: Nicholas Carlini <nicholas@carlini.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/mgmt/tree_connect.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c
index a72d7e42a6c2..58e5b8592da4 100644
--- a/fs/smb/server/mgmt/tree_connect.c
+++ b/fs/smb/server/mgmt/tree_connect.c
@@ -102,8 +102,10 @@ out_error:
 
 void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon)
 {
-	if (atomic_dec_and_test(&tcon->refcount))
+	if (atomic_dec_and_test(&tcon->refcount)) {
+		ksmbd_share_config_put(tcon->share_conf);
 		kfree(tcon);
+	}
 }
 
 static int __ksmbd_tree_conn_disconnect(struct ksmbd_session *sess,
@@ -113,10 +115,11 @@ static int __ksmbd_tree_conn_disconnect(struct ksmbd_session *sess,
 
 	ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id);
 	ksmbd_release_tree_conn_id(sess, tree_conn->id);
-	ksmbd_share_config_put(tree_conn->share_conf);
 	ksmbd_counter_dec(KSMBD_COUNTER_TREE_CONNS);
-	if (atomic_dec_and_test(&tree_conn->refcount))
+	if (atomic_dec_and_test(&tree_conn->refcount)) {
+		ksmbd_share_config_put(tree_conn->share_conf);
 		kfree(tree_conn);
+	}
 	return ret;
 }
 
-- 
cgit v1.2.3


From 282343cf8a4a5a3603b1cb0e17a7083e4a593b03 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 13 Mar 2026 10:00:58 +0900
Subject: ksmbd: unset conn->binding on failed binding request

When a multichannel SMB2_SESSION_SETUP request with
SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true
but never clears it on the error path. This leaves the connection in
a binding state where all subsequent ksmbd_session_lookup_all() calls
fall back to the global sessions table. This fix it by clearing
conn->binding = false in the error path.

Cc: stable@vger.kernel.org
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 9f7ff7491e9a..78d2d79d09b4 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1948,6 +1948,7 @@ out_err:
 			}
 		}
 		smb2_set_err_rsp(work);
+		conn->binding = false;
 	} else {
 		unsigned int iov_len;
 
-- 
cgit v1.2.3


From 3a64125730cabc34fccfbc230c2667c2e14f7308 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 13 Mar 2026 10:01:29 +0900
Subject: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION

Use sb->s_uuid for a proper volume identifier as the primary choice.
For filesystems that do not provide a UUID, fall back to stfs.f_fsid
obtained from vfs_statfs().

Cc: stable@vger.kernel.org
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 78d2d79d09b4..796cc2413817 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -5453,7 +5453,6 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 				    struct smb2_query_info_req *req,
 				    struct smb2_query_info_rsp *rsp)
 {
-	struct ksmbd_session *sess = work->sess;
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_share_config *share = work->tcon->share_conf;
 	int fsinfoclass = 0;
@@ -5590,10 +5589,11 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 
 		info = (struct object_id_info *)(rsp->Buffer);
 
-		if (!user_guest(sess->user))
-			memcpy(info->objid, user_passkey(sess->user), 16);
+		if (path.mnt->mnt_sb->s_uuid_len == 16)
+			memcpy(info->objid, path.mnt->mnt_sb->s_uuid.b,
+					path.mnt->mnt_sb->s_uuid_len);
 		else
-			memset(info->objid, 0, 16);
+			memcpy(info->objid, &stfs.f_fsid, sizeof(stfs.f_fsid));
 
 		info->extended_info.magic = cpu_to_le32(EXTENDED_INFO_MAGIC);
 		info->extended_info.version = cpu_to_le32(1);
-- 
cgit v1.2.3


From c33615f995aee80657b9fdfbc4ee7f49c2bd733d Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Thu, 12 Mar 2026 17:17:02 +0900
Subject: ksmbd: fix use-after-free of share_conf in compound request

smb2_get_ksmbd_tcon() reuses work->tcon in compound requests without
validating tcon->t_state. ksmbd_tree_conn_lookup() checks t_state ==
TREE_CONNECTED on the initial lookup path, but the compound reuse path
bypasses this check entirely.

If a prior command in the compound (SMB2_TREE_DISCONNECT) sets t_state
to TREE_DISCONNECTED and frees share_conf via ksmbd_share_config_put(),
subsequent commands dereference the freed share_conf through
work->tcon->share_conf.

KASAN report:

[    4.144653] ==================================================================
[    4.145059] BUG: KASAN: slab-use-after-free in smb2_write+0xc74/0xe70
[    4.145415] Read of size 4 at addr ffff88810430c194 by task kworker/1:1/44
[    4.145772]
[    4.145867] CPU: 1 UID: 0 PID: 44 Comm: kworker/1:1 Not tainted 7.0.0-rc3+ #60 PREEMPTLAZY
[    4.145871] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[    4.145875] Workqueue: ksmbd-io handle_ksmbd_work
[    4.145888] Call Trace:
[    4.145892]  <TASK>
[    4.145894]  dump_stack_lvl+0x64/0x80
[    4.145910]  print_report+0xce/0x660
[    4.145919]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[    4.145928]  ? smb2_write+0xc74/0xe70
[    4.145931]  kasan_report+0xce/0x100
[    4.145934]  ? smb2_write+0xc74/0xe70
[    4.145937]  smb2_write+0xc74/0xe70
[    4.145939]  ? __pfx_smb2_write+0x10/0x10
[    4.145942]  ? _raw_spin_unlock+0xe/0x30
[    4.145945]  ? ksmbd_smb2_check_message+0xeb2/0x24c0
[    4.145948]  ? smb2_tree_disconnect+0x31c/0x480
[    4.145951]  handle_ksmbd_work+0x40f/0x1080
[    4.145953]  process_one_work+0x5fa/0xef0
[    4.145962]  ? assign_work+0x122/0x3e0
[    4.145964]  worker_thread+0x54b/0xf70
[    4.145967]  ? __pfx_worker_thread+0x10/0x10
[    4.145970]  kthread+0x346/0x470
[    4.145976]  ? recalc_sigpending+0x19b/0x230
[    4.145980]  ? __pfx_kthread+0x10/0x10
[    4.145984]  ret_from_fork+0x4fb/0x6c0
[    4.145992]  ? __pfx_ret_from_fork+0x10/0x10
[    4.145995]  ? __switch_to+0x36c/0xbe0
[    4.145999]  ? __pfx_kthread+0x10/0x10
[    4.146003]  ret_from_fork_asm+0x1a/0x30
[    4.146013]  </TASK>
[    4.146014]
[    4.149858] Allocated by task 44:
[    4.149953]  kasan_save_stack+0x33/0x60
[    4.150061]  kasan_save_track+0x14/0x30
[    4.150169]  __kasan_kmalloc+0x8f/0xa0
[    4.150274]  ksmbd_share_config_get+0x1dd/0xdd0
[    4.150401]  ksmbd_tree_conn_connect+0x7e/0x600
[    4.150529]  smb2_tree_connect+0x2e6/0x1000
[    4.150645]  handle_ksmbd_work+0x40f/0x1080
[    4.150761]  process_one_work+0x5fa/0xef0
[    4.150873]  worker_thread+0x54b/0xf70
[    4.150978]  kthread+0x346/0x470
[    4.151071]  ret_from_fork+0x4fb/0x6c0
[    4.151176]  ret_from_fork_asm+0x1a/0x30
[    4.151286]
[    4.151332] Freed by task 44:
[    4.151418]  kasan_save_stack+0x33/0x60
[    4.151526]  kasan_save_track+0x14/0x30
[    4.151634]  kasan_save_free_info+0x3b/0x60
[    4.151751]  __kasan_slab_free+0x43/0x70
[    4.151861]  kfree+0x1ca/0x430
[    4.151952]  __ksmbd_tree_conn_disconnect+0xc8/0x190
[    4.152088]  smb2_tree_disconnect+0x1cd/0x480
[    4.152211]  handle_ksmbd_work+0x40f/0x1080
[    4.152326]  process_one_work+0x5fa/0xef0
[    4.152438]  worker_thread+0x54b/0xf70
[    4.152545]  kthread+0x346/0x470
[    4.152638]  ret_from_fork+0x4fb/0x6c0
[    4.152743]  ret_from_fork_asm+0x1a/0x30
[    4.152853]
[    4.152900] The buggy address belongs to the object at ffff88810430c180
[    4.152900]  which belongs to the cache kmalloc-96 of size 96
[    4.153226] The buggy address is located 20 bytes inside of
[    4.153226]  freed 96-byte region [ffff88810430c180, ffff88810430c1e0)
[    4.153549]
[    4.153596] The buggy address belongs to the physical page:
[    4.153750] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff88810430ce80 pfn:0x10430c
[    4.154000] flags: 0x100000000000200(workingset|node=0|zone=2)
[    4.154160] page_type: f5(slab)
[    4.154251] raw: 0100000000000200 ffff888100041280 ffff888100040110 ffff888100040110
[    4.154461] raw: ffff88810430ce80 0000000800200009 00000000f5000000 0000000000000000
[    4.154668] page dumped because: kasan: bad access detected
[    4.154820]
[    4.154866] Memory state around the buggy address:
[    4.155002]  ffff88810430c080: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    4.155196]  ffff88810430c100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    4.155391] >ffff88810430c180: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[    4.155587]                          ^
[    4.155693]  ffff88810430c200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    4.155891]  ffff88810430c280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    4.156087] ==================================================================

Add the same t_state validation to the compound reuse path, consistent
with ksmbd_tree_conn_lookup().

Fixes: 5005bcb42191 ("ksmbd: validate session id and tree id in the compound request")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 796cc2413817..0854f238b278 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -126,6 +126,8 @@ int smb2_get_ksmbd_tcon(struct ksmbd_work *work)
 			pr_err("The first operation in the compound does not have tcon\n");
 			return -EINVAL;
 		}
+		if (work->tcon->t_state != TREE_CONNECTED)
+			return -ENOENT;
 		if (tree_id != UINT_MAX && work->tcon->id != tree_id) {
 			pr_err("tree id(%u) is different with id(%u) in first operation\n",
 					tree_id, work->tcon->id);
-- 
cgit v1.2.3


From b425e4d0eb321a1116ddbf39636333181675d8f4 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Thu, 12 Mar 2026 17:15:51 +0900
Subject: ksmbd: fix use-after-free in durable v2 replay of active file handles

parse_durable_handle_context() unconditionally assigns dh_info->fp->conn
to the current connection when handling a DURABLE_REQ_V2 context with
SMB2_FLAGS_REPLAY_OPERATION. ksmbd_lookup_fd_cguid() does not filter by
fp->conn, so it returns file handles that are already actively connected.
The unconditional overwrite replaces fp->conn, and when the overwriting
connection is subsequently freed, __ksmbd_close_fd() dereferences the
stale fp->conn via spin_lock(&fp->conn->llist_lock), causing a
use-after-free.

KASAN report:

[    7.349357] ==================================================================
[    7.349607] BUG: KASAN: slab-use-after-free in _raw_spin_lock+0x75/0xe0
[    7.349811] Write of size 4 at addr ffff8881056ac18c by task kworker/1:2/108
[    7.350010]
[    7.350064] CPU: 1 UID: 0 PID: 108 Comm: kworker/1:2 Not tainted 7.0.0-rc3+ #58 PREEMPTLAZY
[    7.350068] Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[    7.350070] Workqueue: ksmbd-io handle_ksmbd_work
[    7.350083] Call Trace:
[    7.350087]  <TASK>
[    7.350087]  dump_stack_lvl+0x64/0x80
[    7.350094]  print_report+0xce/0x660
[    7.350100]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[    7.350101]  ? __pfx___mod_timer+0x10/0x10
[    7.350106]  ? _raw_spin_lock+0x75/0xe0
[    7.350108]  kasan_report+0xce/0x100
[    7.350109]  ? _raw_spin_lock+0x75/0xe0
[    7.350114]  kasan_check_range+0x105/0x1b0
[    7.350116]  _raw_spin_lock+0x75/0xe0
[    7.350118]  ? __pfx__raw_spin_lock+0x10/0x10
[    7.350119]  ? __call_rcu_common.constprop.0+0x25e/0x780
[    7.350125]  ? close_id_del_oplock+0x2cc/0x4e0
[    7.350128]  __ksmbd_close_fd+0x27f/0xaf0
[    7.350131]  ksmbd_close_fd+0x135/0x1b0
[    7.350133]  smb2_close+0xb19/0x15b0
[    7.350142]  ? __pfx_smb2_close+0x10/0x10
[    7.350143]  ? xas_load+0x18/0x270
[    7.350146]  ? _raw_spin_lock+0x84/0xe0
[    7.350148]  ? __pfx__raw_spin_lock+0x10/0x10
[    7.350150]  ? _raw_spin_unlock+0xe/0x30
[    7.350151]  ? ksmbd_smb2_check_message+0xeb2/0x24c0
[    7.350153]  ? ksmbd_tree_conn_lookup+0xcd/0xf0
[    7.350154]  handle_ksmbd_work+0x40f/0x1080
[    7.350156]  process_one_work+0x5fa/0xef0
[    7.350162]  ? assign_work+0x122/0x3e0
[    7.350163]  worker_thread+0x54b/0xf70
[    7.350165]  ? __pfx_worker_thread+0x10/0x10
[    7.350166]  kthread+0x346/0x470
[    7.350170]  ? recalc_sigpending+0x19b/0x230
[    7.350176]  ? __pfx_kthread+0x10/0x10
[    7.350178]  ret_from_fork+0x4fb/0x6c0
[    7.350183]  ? __pfx_ret_from_fork+0x10/0x10
[    7.350185]  ? __switch_to+0x36c/0xbe0
[    7.350188]  ? __pfx_kthread+0x10/0x10
[    7.350190]  ret_from_fork_asm+0x1a/0x30
[    7.350197]  </TASK>
[    7.350197]
[    7.355160] Allocated by task 123:
[    7.355261]  kasan_save_stack+0x33/0x60
[    7.355373]  kasan_save_track+0x14/0x30
[    7.355484]  __kasan_kmalloc+0x8f/0xa0
[    7.355593]  ksmbd_conn_alloc+0x44/0x6d0
[    7.355711]  ksmbd_kthread_fn+0x243/0xd70
[    7.355839]  kthread+0x346/0x470
[    7.355942]  ret_from_fork+0x4fb/0x6c0
[    7.356051]  ret_from_fork_asm+0x1a/0x30
[    7.356164]
[    7.356214] Freed by task 134:
[    7.356305]  kasan_save_stack+0x33/0x60
[    7.356416]  kasan_save_track+0x14/0x30
[    7.356527]  kasan_save_free_info+0x3b/0x60
[    7.356646]  __kasan_slab_free+0x43/0x70
[    7.356761]  kfree+0x1ca/0x430
[    7.356862]  ksmbd_tcp_disconnect+0x59/0xe0
[    7.356993]  ksmbd_conn_handler_loop+0x77e/0xd40
[    7.357138]  kthread+0x346/0x470
[    7.357240]  ret_from_fork+0x4fb/0x6c0
[    7.357350]  ret_from_fork_asm+0x1a/0x30
[    7.357463]
[    7.357513] The buggy address belongs to the object at ffff8881056ac000
[    7.357513]  which belongs to the cache kmalloc-1k of size 1024
[    7.357857] The buggy address is located 396 bytes inside of
[    7.357857]  freed 1024-byte region [ffff8881056ac000, ffff8881056ac400)

Fix by removing the unconditional fp->conn assignment and rejecting the
replay when fp->conn is non-NULL. This is consistent with
ksmbd_lookup_durable_fd(), which also rejects file handles with a
non-NULL fp->conn. For disconnected file handles (fp->conn == NULL),
ksmbd_reopen_durable_fd() handles setting fp->conn.

Fixes: c8efcc786146 ("ksmbd: add support for durable handles v1/v2")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 0854f238b278..9c44e71e3c3b 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -2831,7 +2831,11 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
 						goto out;
 					}
 
-					dh_info->fp->conn = conn;
+					if (dh_info->fp->conn) {
+						ksmbd_put_durable_fd(dh_info->fp);
+						err = -EBADF;
+						goto out;
+					}
 					dh_info->reconnected = true;
 					goto out;
 				}
-- 
cgit v1.2.3


From b8ead30e2b2c7f32c8d2782e805160b110766592 Mon Sep 17 00:00:00 2001
From: Len Brown <len.brown@intel.com>
Date: Sat, 7 Mar 2026 21:43:11 -0500
Subject: tools/power turbostat: Fix swidle header vs data display

I changed my mind about displaying swidle statistics,
which are "added counters".  Recently I reverted the
column headers to 8-columns, but kept print_decimal_value()
padding out to 16-columns for all 64-bit counters.

Simplify by keeping print_decimial_value() at %lld -- which
will often fit into 8-columns, and live with the fact
that it can overflow and shift the other columns,
which continue to tab-delimited.

This is a better compromise than inserting a bunch
of space characters that most users don't like.

Fixes: 1a23ba6a1ba2 ("tools/power turbostat: Print wide names only for RAW 64-bit columns")
Reported-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index ae827485950d..791b9154f662 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2852,10 +2852,9 @@ static inline int print_hex_value(int width, int *printed, char *delim, unsigned
 
 static inline int print_decimal_value(int width, int *printed, char *delim, unsigned long long value)
 {
-	if (width <= 32)
-		return (sprintf(outp, "%s%d", (*printed++ ? delim : ""), (unsigned int)value));
-	else
-		return (sprintf(outp, "%s%-8lld", (*printed++ ? delim : ""), value));
+	UNUSED(width);
+
+	return (sprintf(outp, "%s%lld", (*printed++ ? delim : ""), value));
 }
 
 static inline int print_float_value(int *printed, char *delim, double value)
-- 
cgit v1.2.3


From 99b38fa34342b227a863948460b7937a97dbce28 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Tue, 10 Mar 2026 14:02:01 +0800
Subject: tools/power turbostat: Eliminate unnecessary data structure
 allocation

Linux core_id's are a per-package namespace, not a per-node namespace.

Rename topo.cores_per_node to topo.cores_per_pkg to reflect this.

Eliminate topo.nodes_per_pkg from the sizing for core data structures,
since it has no role except to unnecessarily bloat the allocation.

Validated on multiple Intel platforms (ICX/SPR/SRF/EMR/GNR/CWF) with
various CPU online/offline configurations and SMT enabled/disabled
scenarios.

No functional changes.

[lenb: commit message]
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 791b9154f662..14021a6ed717 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2409,7 +2409,7 @@ struct topo_params {
 	int max_l3_id;
 	int max_node_num;
 	int nodes_per_pkg;
-	int cores_per_node;
+	int cores_per_pkg;
 	int threads_per_core;
 } topo;
 
@@ -9633,9 +9633,9 @@ void topology_probe(bool startup)
 	topo.max_core_id = max_core_id;	/* within a package */
 	topo.max_package_id = max_package_id;
 
-	topo.cores_per_node = max_core_id + 1;
+	topo.cores_per_pkg = max_core_id + 1;
 	if (debug > 1)
-		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_node);
+		fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_pkg);
 	if (!summary_only)
 		BIC_PRESENT(BIC_Core);
 
@@ -9700,7 +9700,7 @@ error:
 void allocate_counters(struct counters *counters)
 {
 	int i;
-	int num_cores = topo.cores_per_node * topo.nodes_per_pkg * topo.num_packages;
+	int num_cores = topo.cores_per_pkg * topo.num_packages;
 
 	counters->threads = calloc(topo.max_cpu_num + 1, sizeof(struct thread_data));
 	if (counters->threads == NULL)
-- 
cgit v1.2.3


From a444083286434ec1fd127c5da11a3091e6013008 Mon Sep 17 00:00:00 2001
From: Serhii Pievniev <spevnev16@gmail.com>
Date: Wed, 25 Feb 2026 18:16:03 -0500
Subject: tools/power/turbostat: Fix microcode patch level output for AMD/Hygon

turbostat always used the same logic to read the microcode patch level,
which is correct for Intel but not for AMD/Hygon.
While Intel stores the patch level in the upper 32 bits of MSR, AMD
stores it in the lower 32 bits, which causes turbostat to report the
microcode version as 0x0 on AMD/Hygon.

Fix by shifting right by 32 for non-AMD/Hygon, preserving the existing
behavior for Intel and unknown vendors.

Fixes: 3e4048466c39 ("tools/power turbostat: Add --no-msr option")
Signed-off-by: Serhii Pievniev <spevnev16@gmail.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 14021a6ed717..b985bce69142 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -9121,10 +9121,13 @@ void process_cpuid()
 	cpuid_has_hv = ecx_flags & (1 << 31);
 
 	if (!no_msr) {
-		if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
+		if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) {
 			warnx("get_msr(UCODE)");
-		else
+		} else {
 			ucode_patch_valid = true;
+			if (!authentic_amd && !hygon_genuine)
+				ucode_patch >>= 32;
+		}
 	}
 
 	/*
@@ -9138,7 +9141,7 @@ void process_cpuid()
 	if (!quiet) {
 		fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", family, model, stepping, family, model, stepping);
 		if (ucode_patch_valid)
-			fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+			fprintf(outf, " microcode 0x%x", (unsigned int)ucode_patch);
 		fputc('\n', outf);
 
 		fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level);
-- 
cgit v1.2.3


From bccaf98c1077f2216ecae12923e21ffaebd67d95 Mon Sep 17 00:00:00 2001
From: Max Krummenacher <max.krummenacher@toradex.com>
Date: Thu, 19 Feb 2026 16:11:49 +0100
Subject: Revert "ARM: dts: imx: move nand related property under nand@0"

This reverts commit 8124b4a4a96b57d6cc3705a9df9623c52baa047b.

The change introduced a regression: at least Colibri iMX6ULL and
Colibri iMX7 no longer boot with that commit applied, while they boot
again after reverting it.

Although this has only been verified on these two modules, the issue
is expected to affect all device trees using the gpmi-nand driver.

[    0.876938] Creating 5 MTD partitions on "gpmi-nand":
[    0.876974] 0x000000000000-0x000000080000 : "mx7-bcb"
[    0.879860] 0x000000080000-0x000000200000 : "u-boot1"
[    0.884761] 0x000000200000-0x000000380000 : "u-boot2"
[    0.886993] 0x000000380000-0x000000400000 : "u-boot-env"
[    0.894686] 0x000000400000-0x000020000000 : "ubi"
[    0.899054] gpmi-nand 33002000.nand-controller: driver registered.
...
[    0.960443] ubi0: default fastmap pool size: 200
[    0.960476] ubi0: default fastmap WL pool size: 100
[    0.960500] ubi0: attaching mtd4
[    1.636355] ubi0 error: scan_peb: bad image sequence number 1588722158 in PEB 4060, expected 1574791632
...
[    1.649889] ubi0 error: ubi_attach_mtd_dev: failed to attach mtd4, error -22
[    1.650029] UBI error: cannot attach mtd4
...
[    1.670262] Kernel panic - not syncing: VFS: Unable to mount root fs on unknown-block(0,253)

Fixes: 8124b4a4a96b ("ARM: dts: imx: move nand related property under nand@0")
Signed-off-by: Max Krummenacher <max.krummenacher@toradex.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm/boot/dts/nxp/imx/imx6-logicpd-som.dtsi           |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6qdl-icore.dtsi              |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi      |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi           |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6qdl-tx6.dtsi                |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts                 |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ul-isiot.dtsi               |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ul-phytec-phycore-som.dtsi  |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ul-tx6ul.dtsi               |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ull-colibri.dtsi            | 12 ++++--------
 arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea.dtsi   | 12 ++++--------
 arch/arm/boot/dts/nxp/imx/imx6ull-myir-mys-6ulx.dtsi      |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx6ulz-bsh-smm-m2.dts          |  6 +-----
 arch/arm/boot/dts/nxp/imx/imx7-colibri.dtsi               |  8 ++------
 15 files changed, 22 insertions(+), 82 deletions(-)

diff --git a/arch/arm/boot/dts/nxp/imx/imx6-logicpd-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6-logicpd-som.dtsi
index f452764fae00..547fb141ec0c 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6-logicpd-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6-logicpd-som.dtsi
@@ -36,12 +36,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c3 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-icore.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-icore.dtsi
index 58ecdb87c6d4..9975b6ee433d 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-icore.dtsi
@@ -172,12 +172,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
index 6f3becd33a5b..aa9a442852f4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-pfla02.dtsi
@@ -102,12 +102,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
index f2140dd8525f..85e278eb2016 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-phytec-phycore-som.dtsi
@@ -73,12 +73,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "disabled";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c3 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
index 131a3428ddb8..c93dbc595ef6 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-skov-cpu.dtsi
@@ -260,14 +260,10 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	#address-cells = <1>;
 	#size-cells = <0>;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c3 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-tx6.dtsi
index d29adfef5fdb..57297d6521cf 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-tx6.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-tx6.dtsi
@@ -252,13 +252,9 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	fsl,no-blockmark-swap;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
index 40d530c1dc29..2a6bb5ff808a 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
@@ -133,12 +133,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-isiot.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-isiot.dtsi
index 776f6f78ee46..e34c8cbe36ae 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-isiot.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-isiot.dtsi
@@ -101,12 +101,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "disabled";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-phytec-phycore-som.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-phytec-phycore-som.dtsi
index 27e4d2aec137..a3ea1b208462 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-phytec-phycore-som.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-phytec-phycore-som.dtsi
@@ -63,12 +63,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "disabled";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-tx6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-tx6ul.dtsi
index dc53f9286ffe..1992dfb53b45 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ul-tx6ul.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ul-tx6ul.dtsi
@@ -296,13 +296,9 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	fsl,no-blockmark-swap;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &i2c2 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-colibri.dtsi
index eaed2cbf0c82..ec3c1e7301f4 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-colibri.dtsi
@@ -160,15 +160,11 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
 	fsl,use-minimum-ecc;
+	nand-on-flash-bbt;
+	nand-ecc-mode = "hw";
+	nand-ecc-strength = <8>;
+	nand-ecc-step-size = <512>;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-		nand-ecc-mode = "hw";
-		nand-ecc-strength = <8>;
-		nand-ecc-step-size = <512>;
-	};
 };
 
 /* I2C3_SDA/SCL on SODIMM 194/196 (e.g. RTC on carrier board) */
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea.dtsi
index 3dfd43b32055..43518bf07602 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea.dtsi
@@ -43,15 +43,11 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-ecc-mode = "hw";
+	nand-ecc-strength = <0>;
+	nand-ecc-step-size = <0>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-ecc-mode = "hw";
-		nand-ecc-strength = <0>;
-		nand-ecc-step-size = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &iomuxc {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-myir-mys-6ulx.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-myir-mys-6ulx.dtsi
index fc298f57bfff..83b9de17cee2 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-myir-mys-6ulx.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-myir-mys-6ulx.dtsi
@@ -60,12 +60,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "disabled";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &uart1 {
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ulz-bsh-smm-m2.dts b/arch/arm/boot/dts/nxp/imx/imx6ulz-bsh-smm-m2.dts
index 8ec18eae98a4..2d9f495660c9 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ulz-bsh-smm-m2.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx6ulz-bsh-smm-m2.dts
@@ -25,12 +25,8 @@
 &gpmi {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
+	nand-on-flash-bbt;
 	status = "okay";
-
-	nand@0 {
-		reg = <0>;
-		nand-on-flash-bbt;
-	};
 };
 
 &snvs_poweroff {
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-colibri.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-colibri.dtsi
index a41dc4edfc0d..8666dcd7fe97 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-colibri.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-colibri.dtsi
@@ -375,14 +375,10 @@
 /* NAND on such SKUs */
 &gpmi {
 	fsl,use-minimum-ecc;
+	nand-ecc-mode = "hw";
+	nand-on-flash-bbt;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_gpmi_nand>;
-
-	nand@0 {
-		reg = <0>;
-		nand-ecc-mode = "hw";
-		nand-on-flash-bbt;
-	};
 };
 
 /* On-module Power I2C */
-- 
cgit v1.2.3


From 4cd46ea0eb4504f7f4fea92cb4601c5c9a3e545e Mon Sep 17 00:00:00 2001
From: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Date: Sat, 21 Feb 2026 19:15:18 +0100
Subject: Revert "arm64: dts: imx8mq-librem5: Set the DVS voltages lower"

This reverts commit c24a9b698fb02cd0723fa8375abab07f94b97b10.

It's been found that there's a significant per-unit variance in accepted
supply voltages and the current set still makes some units unstable.

Revert back to nominal values.

Cc: stable@vger.kernel.org
Fixes: c24a9b698fb0 ("arm64: dts: imx8mq-librem5: Set the DVS voltages lower")
Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 .../arm64/boot/dts/freescale/imx8mq-librem5-r3.dts |  2 +-
 arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi  | 22 ++++++----------------
 2 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts b/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts
index 077c5cd2586f..4533a84fb0b9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5-r3.dts
@@ -7,7 +7,7 @@
 
 &a53_opp_table {
 	opp-1000000000 {
-		opp-microvolt = <950000>;
+		opp-microvolt = <1000000>;
 	};
 };
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
index eee390c27210..7818d84f25a7 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
@@ -880,8 +880,8 @@
 				regulator-max-microvolt = <1300000>;
 				regulator-boot-on;
 				regulator-ramp-delay = <1250>;
-				rohm,dvs-run-voltage = <880000>;
-				rohm,dvs-idle-voltage = <820000>;
+				rohm,dvs-run-voltage = <900000>;
+				rohm,dvs-idle-voltage = <850000>;
 				rohm,dvs-suspend-voltage = <810000>;
 				regulator-always-on;
 			};
@@ -892,8 +892,8 @@
 				regulator-max-microvolt = <1300000>;
 				regulator-boot-on;
 				regulator-ramp-delay = <1250>;
-				rohm,dvs-run-voltage = <950000>;
-				rohm,dvs-idle-voltage = <850000>;
+				rohm,dvs-run-voltage = <1000000>;
+				rohm,dvs-idle-voltage = <900000>;
 				regulator-always-on;
 			};
 
@@ -902,14 +902,14 @@
 				regulator-min-microvolt = <700000>;
 				regulator-max-microvolt = <1300000>;
 				regulator-boot-on;
-				rohm,dvs-run-voltage = <850000>;
+				rohm,dvs-run-voltage = <900000>;
 			};
 
 			buck4_reg: BUCK4 {
 				regulator-name = "buck4";
 				regulator-min-microvolt = <700000>;
 				regulator-max-microvolt = <1300000>;
-				rohm,dvs-run-voltage = <930000>;
+				rohm,dvs-run-voltage = <1000000>;
 			};
 
 			buck5_reg: BUCK5 {
@@ -1448,13 +1448,3 @@
 	fsl,ext-reset-output;
 	status = "okay";
 };
-
-&a53_opp_table {
-	opp-1000000000 {
-		opp-microvolt = <850000>;
-	};
-
-	opp-1500000000 {
-		opp-microvolt = <950000>;
-	};
-};
-- 
cgit v1.2.3


From 511f76bf1dce5acf8907b65a7d1bc8f7e7c0d637 Mon Sep 17 00:00:00 2001
From: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Date: Sat, 21 Feb 2026 19:15:19 +0100
Subject: arm64: dts: imx8mq-librem5: Bump BUCK1 suspend voltage up to 0.85V
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The minimal voltage of VDD_SOC sourced from BUCK1 is 0.81V, which
is the currently set value. However, BD71837 only guarantees accuracy
of ±0.01V, and this still doesn't factor other reasons for actual
voltage to slightly drop in, resulting in the possibility of running
out of the operational range.

Bump the voltage up to 0.85V, which should give enough headroom.

Cc: stable@vger.kernel.org
Fixes: 8f0216b006e5 ("arm64: dts: Add a device tree for the Librem 5 phone")
Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
 arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
index 7818d84f25a7..f5d529c5baf3 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-librem5.dtsi
@@ -882,7 +882,7 @@
 				regulator-ramp-delay = <1250>;
 				rohm,dvs-run-voltage = <900000>;
 				rohm,dvs-idle-voltage = <850000>;
-				rohm,dvs-suspend-voltage = <810000>;
+				rohm,dvs-suspend-voltage = <850000>;
 				regulator-always-on;
 			};
 
-- 
cgit v1.2.3


From ed532d738a82269dfe490436b9b8def2274cfb6e Mon Sep 17 00:00:00 2001
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Wed, 11 Mar 2026 11:00:31 +0200
Subject: tools/power turbostat: Consistently use print_float_value()

Fix the PMT thread code to use print_float_value(),
to be consistent with the PMT core and package code.

[lenb: commit message]
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index b985bce69142..9744f9caac9a 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3489,12 +3489,12 @@ int format_counters(PER_THREAD_PARAMS)
 
 		case PMT_TYPE_XTAL_TIME:
 			value_converted = pct(value_raw / crystal_hz, interval_float);
-			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
+			outp += print_float_value(&printed, delim, value_converted);
 			break;
 
 		case PMT_TYPE_TCORE_CLOCK:
 			value_converted = pct(value_raw / tcore_clock_freq_hz, interval_float);
-			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
+			outp += print_float_value(&printed, delim, value_converted);
 		}
 	}
 
-- 
cgit v1.2.3


From 23cb4f5c81766e70e5f32ed0987ee8fb5ab2e00a Mon Sep 17 00:00:00 2001
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Wed, 11 Mar 2026 11:00:32 +0200
Subject: tools/power turbostat: Fix incorrect format variable

In the perf thread, core, and package counter loops, an incorrect
'mp->format' variable is used instead of 'pp->format'.

[lenb: edit commit message]
Fixes: 696d15cbd8c2 ("tools/power turbostat: Refactor floating point printout code")
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9744f9caac9a..4d954533c71d 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3468,7 +3468,7 @@ int format_counters(PER_THREAD_PARAMS)
 	for (i = 0, pp = sys.perf_tp; pp; ++i, pp = pp->next) {
 		if (pp->format == FORMAT_RAW)
 			outp += print_hex_value(pp->width, &printed, delim, t->perf_counter[i]);
-		else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
+		else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
 			outp += print_decimal_value(pp->width, &printed, delim, t->perf_counter[i]);
 		else if (pp->format == FORMAT_PERCENT) {
 			if (pp->type == COUNTER_USEC)
@@ -3538,7 +3538,7 @@ int format_counters(PER_THREAD_PARAMS)
 	for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) {
 		if (pp->format == FORMAT_RAW)
 			outp += print_hex_value(pp->width, &printed, delim, c->perf_counter[i]);
-		else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
+		else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
 			outp += print_decimal_value(pp->width, &printed, delim, c->perf_counter[i]);
 		else if (pp->format == FORMAT_PERCENT)
 			outp += print_float_value(&printed, delim, pct(c->perf_counter[i], tsc));
@@ -3694,7 +3694,7 @@ int format_counters(PER_THREAD_PARAMS)
 			outp += print_hex_value(pp->width, &printed, delim, p->perf_counter[i]);
 		else if (pp->type == COUNTER_K2M)
 			outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->perf_counter[i] / 1000);
-		else if (pp->format == FORMAT_DELTA || mp->format == FORMAT_AVERAGE)
+		else if (pp->format == FORMAT_DELTA || pp->format == FORMAT_AVERAGE)
 			outp += print_decimal_value(pp->width, &printed, delim, p->perf_counter[i]);
 		else if (pp->format == FORMAT_PERCENT)
 			outp += print_float_value(&printed, delim, pct(p->perf_counter[i], tsc));
-- 
cgit v1.2.3


From b6398bc2ef3a78f1be37ba01ae0a5eedaee47803 Mon Sep 17 00:00:00 2001
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Wed, 11 Mar 2026 11:00:33 +0200
Subject: tools/power turbostat: Fix --show/--hide for individual cpuidle
 counters

Problem: individual swidle counter names (C1, C1+, C1-, etc.) cannot be
selected via --show/--hide due to two bugs in probe_cpuidle_counts():
1. The function returns immediately when BIC_cpuidle is not enabled,
   without checking deferred_add_index.
2. The deferred name check runs against name_buf before the trailing
   newline is stripped, so is_deferred_add("C1\n") never matches "C1".

Fix:
1. Relax the early return to pass through when deferred names are
   queued.
2. Strip the trailing newline from name_buf before performing deferred
   name checks.
3. Check each suffixed variant (C1+, C1, C1-) individually so that
   e.g. "--show C1+" enables only the requested metric.

In addition, introduce a helper function to avoid repeating the
condition (readability cleanup).

Fixes: ec4acd3166d8 ("tools/power turbostat: disable "cpuidle" invocation counters, by default")
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 4d954533c71d..3487548841e1 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -11285,6 +11285,14 @@ void probe_cpuidle_residency(void)
 	}
 }
 
+static bool cpuidle_counter_wanted(char *name)
+{
+	if (is_deferred_skip(name))
+		return false;
+
+	return DO_BIC(BIC_cpuidle) || is_deferred_add(name);
+}
+
 void probe_cpuidle_counts(void)
 {
 	char path[64];
@@ -11294,7 +11302,7 @@ void probe_cpuidle_counts(void)
 	int min_state = 1024, max_state = 0;
 	char *sp;
 
-	if (!DO_BIC(BIC_cpuidle))
+	if (!DO_BIC(BIC_cpuidle) && !deferred_add_index)
 		return;
 
 	for (state = 10; state >= 0; --state) {
@@ -11309,12 +11317,6 @@ void probe_cpuidle_counts(void)
 
 		remove_underbar(name_buf);
 
-		if (!DO_BIC(BIC_cpuidle) && !is_deferred_add(name_buf))
-			continue;
-
-		if (is_deferred_skip(name_buf))
-			continue;
-
 		/* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
@@ -11329,16 +11331,19 @@ void probe_cpuidle_counts(void)
 			 * Add 'C1+' for C1, and so on. The 'below' sysfs file always contains 0 for
 			 * the last state, so do not add it.
 			 */
-
 			*sp = '+';
 			*(sp + 1) = '\0';
-			sprintf(path, "cpuidle/state%d/below", state);
-			add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+			if (cpuidle_counter_wanted(name_buf)) {
+				sprintf(path, "cpuidle/state%d/below", state);
+				add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+			}
 		}
 
 		*sp = '\0';
-		sprintf(path, "cpuidle/state%d/usage", state);
-		add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+		if (cpuidle_counter_wanted(name_buf)) {
+			sprintf(path, "cpuidle/state%d/usage", state);
+			add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+		}
 
 		/*
 		 * The 'above' sysfs file always contains 0 for the shallowest state (smallest
@@ -11347,8 +11352,10 @@ void probe_cpuidle_counts(void)
 		if (state != min_state) {
 			*sp = '-';
 			*(sp + 1) = '\0';
-			sprintf(path, "cpuidle/state%d/above", state);
-			add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+			if (cpuidle_counter_wanted(name_buf)) {
+				sprintf(path, "cpuidle/state%d/above", state);
+				add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, FORMAT_DELTA, SYSFS_PERCPU, 0);
+			}
 		}
 	}
 }
-- 
cgit v1.2.3


From 8780f561f6717dec52351251881bff79e960eb46 Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Wed, 18 Mar 2026 06:02:30 +1030
Subject: ALSA: usb-audio: Exclude Scarlett 2i2 1st Gen from SKIP_IFACE_SETUP

The Focusrite Scarlett 2i2 1st Gen (1235:8006) produces
distorted/silent audio when QUIRK_FLAG_SKIP_IFACE_SETUP is active, as
that flag causes the feedback format to be detected as 17.15 instead
of 16.16.

Add a DEVICE_FLG entry for this device before the Focusrite VENDOR_FLG
entry so that it gets no quirk flags, overriding the vendor-wide
SKIP_IFACE_SETUP. This device doesn't have the internal mixer, Air, or
Safe modes that the quirk was designed to protect.

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Reported-by: pairomaniac [https://github.com/geoffreybennett/linux-fcp/issues/54]
Tested-by: pairomaniac [https://github.com/geoffreybennett/linux-fcp/issues/54]
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://patch.msgid.link/abmsTjKmQMKbhYtK@m.b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 049a94079f9e..cd3a9fe8edf2 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2429,6 +2429,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY),
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
+	DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),
-- 
cgit v1.2.3


From c73bb9a2d33bf81f6eecaa0f474b6c6dbe9855bd Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Tue, 17 Mar 2026 20:42:44 -0700
Subject: wifi: mac80211: fix NULL deref in mesh_matches_local()

mesh_matches_local() unconditionally dereferences ie->mesh_config to
compare mesh configuration parameters. When called from
mesh_rx_csa_frame(), the parsed action-frame elements may not contain a
Mesh Configuration IE, leaving ie->mesh_config NULL and triggering a
kernel NULL pointer dereference.

The other two callers are already safe:
  - ieee80211_mesh_rx_bcn_presp() checks !elems->mesh_config before
    calling mesh_matches_local()
  - mesh_plink_get_event() is only reached through
    mesh_process_plink_frame(), which checks !elems->mesh_config, too

mesh_rx_csa_frame() is the only caller that passes raw parsed elements
to mesh_matches_local() without guarding mesh_config. An adjacent
attacker can exploit this by sending a crafted CSA action frame that
includes a valid Mesh ID IE but omits the Mesh Configuration IE,
crashing the kernel.

The captured crash log:

Oops: general protection fault, probably for non-canonical address ...
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
Workqueue: events_unbound cfg80211_wiphy_work
[...]
Call Trace:
 <TASK>
 ? __pfx_mesh_matches_local (net/mac80211/mesh.c:65)
 ieee80211_mesh_rx_queued_mgmt (net/mac80211/mesh.c:1686)
 [...]
 ieee80211_iface_work (net/mac80211/iface.c:1754 net/mac80211/iface.c:1802)
 [...]
 cfg80211_wiphy_work (net/wireless/core.c:426)
 process_one_work (net/kernel/workqueue.c:3280)
 ? assign_work (net/kernel/workqueue.c:1219)
 worker_thread (net/kernel/workqueue.c:3352)
 ? __pfx_worker_thread (net/kernel/workqueue.c:3385)
 kthread (net/kernel/kthread.c:436)
 [...]
 ret_from_fork_asm (net/arch/x86/entry/entry_64.S:255)
 </TASK>

This patch adds a NULL check for ie->mesh_config at the top of
mesh_matches_local() to return false early when the Mesh Configuration
IE is absent.

Fixes: 2e3c8736820b ("mac80211: support functions for mesh")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260318034244.2595020-1-xmei5@asu.edu
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 28624e57aa49..8fdbdf9ba2a9 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -79,6 +79,9 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata,
 	 *   - MDA enabled
 	 * - Power management control on fc
 	 */
+	if (!ie->mesh_config)
+		return false;
+
 	if (!(ifmsh->mesh_id_len == ie->mesh_id_len &&
 	     memcmp(ifmsh->mesh_id, ie->mesh_id, ie->mesh_id_len) == 0 &&
 	     (ifmsh->mesh_pp_id == ie->mesh_config->meshconf_psel) &&
-- 
cgit v1.2.3


From deb353d9bb009638b7762cae2d0b6e8fdbb41a69 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Tue, 17 Mar 2026 23:46:36 -0700
Subject: wifi: wlcore: Return -ENOMEM instead of -EAGAIN if there is not
 enough headroom

Since upstream commit e75665dd0968 ("wifi: wlcore: ensure skb headroom
before skb_push"), wl1271_tx_allocate() and with it
wl1271_prepare_tx_frame() returns -EAGAIN if pskb_expand_head() fails.
However, in wlcore_tx_work_locked(), a return value of -EAGAIN from
wl1271_prepare_tx_frame() is interpreted as the aggregation buffer being
full. This causes the code to flush the buffer, put the skb back at the
head of the queue, and immediately retry the same skb in a tight while
loop.

Because wlcore_tx_work_locked() holds wl->mutex, and the retry happens
immediately with GFP_ATOMIC, this will result in an infinite loop and a
CPU soft lockup. Return -ENOMEM instead so the packet is dropped and
the loop terminates.

The problem was found by an experimental code review agent based on
gemini-3.1-pro while reviewing backports into v6.18.y.

Assisted-by: Gemini:gemini-3.1-pro
Fixes: e75665dd0968 ("wifi: wlcore: ensure skb headroom before skb_push")
Cc: Peter Astrand <astrand@lysator.liu.se>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Link: https://patch.msgid.link/20260318064636.3065925-1-linux@roeck-us.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wlcore/tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c
index 6241866d39df..75cfbcfb7626 100644
--- a/drivers/net/wireless/ti/wlcore/tx.c
+++ b/drivers/net/wireless/ti/wlcore/tx.c
@@ -210,7 +210,7 @@ static int wl1271_tx_allocate(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 		if (skb_headroom(skb) < (total_len - skb->len) &&
 		    pskb_expand_head(skb, (total_len - skb->len), 0, GFP_ATOMIC)) {
 			wl1271_free_tx_id(wl, id);
-			return -EAGAIN;
+			return -ENOMEM;
 		}
 		desc = skb_push(skb, total_len - skb->len);
 
-- 
cgit v1.2.3


From d5ad6ab61cbd89afdb60881f6274f74328af3ee9 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sat, 14 Mar 2026 06:54:55 +0000
Subject: wifi: mac80211: always free skb on ieee80211_tx_prepare_skb() failure

ieee80211_tx_prepare_skb() has three error paths, but only two of them
free the skb. The first error path (ieee80211_tx_prepare() returning
TX_DROP) does not free it, while invoke_tx_handlers() failure and the
fragmentation check both do.

Add kfree_skb() to the first error path so all three are consistent,
and remove the now-redundant frees in callers (ath9k, mt76,
mac80211_hwsim) to avoid double-free.

Document the skb ownership guarantee in the function's kdoc.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://patch.msgid.link/20260314065455.2462900-1-nbd@nbd.name
Fixes: 06be6b149f7e ("mac80211: add ieee80211_tx_prepare_skb() helper function")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath9k/channel.c      | 6 ++----
 drivers/net/wireless/mediatek/mt76/scan.c     | 4 +---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 1 -
 include/net/mac80211.h                        | 4 +++-
 net/mac80211/tx.c                             | 4 +++-
 5 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/channel.c b/drivers/net/wireless/ath/ath9k/channel.c
index 121e51ce1bc0..8b27d8cc086a 100644
--- a/drivers/net/wireless/ath/ath9k/channel.c
+++ b/drivers/net/wireless/ath/ath9k/channel.c
@@ -1006,7 +1006,7 @@ static void ath_scan_send_probe(struct ath_softc *sc,
 	skb_set_queue_mapping(skb, IEEE80211_AC_VO);
 
 	if (!ieee80211_tx_prepare_skb(sc->hw, vif, skb, band, NULL))
-		goto error;
+		return;
 
 	txctl.txq = sc->tx.txq_map[IEEE80211_AC_VO];
 	if (ath_tx_start(sc->hw, skb, &txctl))
@@ -1119,10 +1119,8 @@ ath_chanctx_send_vif_ps_frame(struct ath_softc *sc, struct ath_vif *avp,
 
 		skb->priority = 7;
 		skb_set_queue_mapping(skb, IEEE80211_AC_VO);
-		if (!ieee80211_tx_prepare_skb(sc->hw, vif, skb, band, &sta)) {
-			dev_kfree_skb_any(skb);
+		if (!ieee80211_tx_prepare_skb(sc->hw, vif, skb, band, &sta))
 			return false;
-		}
 		break;
 	default:
 		return false;
diff --git a/drivers/net/wireless/mediatek/mt76/scan.c b/drivers/net/wireless/mediatek/mt76/scan.c
index ff9176cdee3d..63b0447e55c1 100644
--- a/drivers/net/wireless/mediatek/mt76/scan.c
+++ b/drivers/net/wireless/mediatek/mt76/scan.c
@@ -63,10 +63,8 @@ mt76_scan_send_probe(struct mt76_dev *dev, struct cfg80211_ssid *ssid)
 
 	rcu_read_lock();
 
-	if (!ieee80211_tx_prepare_skb(phy->hw, vif, skb, band, NULL)) {
-		ieee80211_free_txskb(phy->hw, skb);
+	if (!ieee80211_tx_prepare_skb(phy->hw, vif, skb, band, NULL))
 		goto out;
-	}
 
 	info = IEEE80211_SKB_CB(skb);
 	if (req->no_cck)
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index f6b890dea7e0..1b6e55eb81a2 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -3021,7 +3021,6 @@ static void hw_scan_work(struct work_struct *work)
 						      hwsim->tmp_chan->band,
 						      NULL)) {
 				rcu_read_unlock();
-				kfree_skb(probe);
 				continue;
 			}
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 7f9d96939a4e..adce2144a678 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -7407,7 +7407,9 @@ void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif,
  * @band: the band to transmit on
  * @sta: optional pointer to get the station to send the frame to
  *
- * Return: %true if the skb was prepared, %false otherwise
+ * Return: %true if the skb was prepared, %false otherwise.
+ * On failure, the skb is freed by this function; callers must not
+ * free it again.
  *
  * Note: must be called under RCU lock
  */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8cdbd417d7be..b7aedaab8483 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1899,8 +1899,10 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw,
 	struct ieee80211_tx_data tx;
 	struct sk_buff *skb2;
 
-	if (ieee80211_tx_prepare(sdata, &tx, NULL, skb) == TX_DROP)
+	if (ieee80211_tx_prepare(sdata, &tx, NULL, skb) == TX_DROP) {
+		kfree_skb(skb);
 		return false;
+	}
 
 	info->band = band;
 	info->control.vif = vif;
-- 
cgit v1.2.3


From 4f24a767e3d64a5f58c595b5c29b6063a201f1e3 Mon Sep 17 00:00:00 2001
From: Yuto Ohnuki <ytohnuki@amazon.com>
Date: Tue, 10 Mar 2026 18:38:37 +0000
Subject: xfs: stop reclaim before pushing AIL during unmount

The unmount sequence in xfs_unmount_flush_inodes() pushed the AIL while
background reclaim and inodegc are still running. This is broken
independently of any use-after-free issues - background reclaim and
inodegc should not be running while the AIL is being pushed during
unmount, as inodegc can dirty and insert inodes into the AIL during the
flush, and background reclaim can race to abort and free dirty inodes.

Reorder xfs_unmount_flush_inodes() to stop inodegc and cancel background
reclaim before pushing the AIL. Stop inodegc before cancelling
m_reclaim_work because the inodegc worker can re-queue m_reclaim_work
via xfs_inodegc_set_reclaimable.

Reported-by: syzbot+652af2b3c5569c4ab63c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=652af2b3c5569c4ab63c
Fixes: 90c60e164012 ("xfs: xfs_iflush() is no longer necessary")
Cc: stable@vger.kernel.org # v5.9
Signed-off-by: Yuto Ohnuki <ytohnuki@amazon.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_mount.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 9c295abd0a0a..ef1ea8a1238c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -608,8 +608,9 @@ xfs_unmount_check(
  * have been retrying in the background.  This will prevent never-ending
  * retries in AIL pushing from hanging the unmount.
  *
- * Finally, we can push the AIL to clean all the remaining dirty objects, then
- * reclaim the remaining inodes that are still in memory at this point in time.
+ * Stop inodegc and background reclaim before pushing the AIL so that they
+ * are not running while the AIL is being flushed. Then push the AIL to
+ * clean all the remaining dirty objects and reclaim the remaining inodes.
  */
 static void
 xfs_unmount_flush_inodes(
@@ -621,9 +622,9 @@ xfs_unmount_flush_inodes(
 
 	xfs_set_unmounting(mp);
 
-	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_inodegc_stop(mp);
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	xfs_ail_push_all_sync(mp->m_ail);
 	xfs_reclaim_inodes(mp);
 	xfs_health_unmount(mp);
 	xfs_healthmon_unmount(mp);
-- 
cgit v1.2.3


From 79ef34ec0554ec04bdbafafbc9836423734e1bd6 Mon Sep 17 00:00:00 2001
From: Yuto Ohnuki <ytohnuki@amazon.com>
Date: Tue, 10 Mar 2026 18:38:38 +0000
Subject: xfs: avoid dereferencing log items after push callbacks

After xfsaild_push_item() calls iop_push(), the log item may have been
freed if the AIL lock was dropped during the push. Background inode
reclaim or the dquot shrinker can free the log item while the AIL lock
is not held, and the tracepoints in the switch statement dereference
the log item after iop_push() returns.

Fix this by capturing the log item type, flags, and LSN before calling
xfsaild_push_item(), and introducing a new xfs_ail_push_class trace
event class that takes these pre-captured values and the ailp pointer
instead of the log item pointer.

Reported-by: syzbot+652af2b3c5569c4ab63c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=652af2b3c5569c4ab63c
Fixes: 90c60e164012 ("xfs: xfs_iflush() is no longer necessary")
Cc: stable@vger.kernel.org # v5.9
Signed-off-by: Yuto Ohnuki <ytohnuki@amazon.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_trace.h     | 36 ++++++++++++++++++++++++++++++++----
 fs/xfs/xfs_trans_ail.c | 26 +++++++++++++++++++-------
 2 files changed, 51 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 813e5a9f57eb..0e994b3f768f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -56,6 +56,7 @@
 #include <linux/tracepoint.h>
 
 struct xfs_agf;
+struct xfs_ail;
 struct xfs_alloc_arg;
 struct xfs_attr_list_context;
 struct xfs_buf_log_item;
@@ -1650,16 +1651,43 @@ TRACE_EVENT(xfs_log_force,
 DEFINE_EVENT(xfs_log_item_class, name, \
 	TP_PROTO(struct xfs_log_item *lip), \
 	TP_ARGS(lip))
-DEFINE_LOG_ITEM_EVENT(xfs_ail_push);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_locked);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin);
 DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort);
 DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort);
 
+DECLARE_EVENT_CLASS(xfs_ail_push_class,
+	TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn),
+	TP_ARGS(ailp, type, flags, lsn),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(uint, type)
+		__field(unsigned long, flags)
+		__field(xfs_lsn_t, lsn)
+	),
+	TP_fast_assign(
+		__entry->dev = ailp->ail_log->l_mp->m_super->s_dev;
+		__entry->type = type;
+		__entry->flags = flags;
+		__entry->lsn = lsn;
+	),
+	TP_printk("dev %d:%d lsn %d/%d type %s flags %s",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn),
+		  __print_symbolic(__entry->type, XFS_LI_TYPE_DESC),
+		  __print_flags(__entry->flags, "|", XFS_LI_FLAGS))
+)
+
+#define DEFINE_AIL_PUSH_EVENT(name) \
+DEFINE_EVENT(xfs_ail_push_class, name, \
+	TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), \
+	TP_ARGS(ailp, type, flags, lsn))
+DEFINE_AIL_PUSH_EVENT(xfs_ail_push);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_pinned);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_locked);
+DEFINE_AIL_PUSH_EVENT(xfs_ail_flushing);
+
 DECLARE_EVENT_CLASS(xfs_ail_class,
 	TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn),
 	TP_ARGS(lip, old_lsn, new_lsn),
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 923729af4206..63266d31b514 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -365,6 +365,12 @@ xfsaild_resubmit_item(
 	return XFS_ITEM_SUCCESS;
 }
 
+/*
+ * Push a single log item from the AIL.
+ *
+ * @lip may have been released and freed by the time this function returns,
+ * so callers must not dereference the log item afterwards.
+ */
 static inline uint
 xfsaild_push_item(
 	struct xfs_ail		*ailp,
@@ -505,7 +511,10 @@ xfsaild_push(
 
 	lsn = lip->li_lsn;
 	while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) {
-		int	lock_result;
+		int		lock_result;
+		uint		type = lip->li_type;
+		unsigned long	flags = lip->li_flags;
+		xfs_lsn_t	item_lsn = lip->li_lsn;
 
 		if (test_bit(XFS_LI_FLUSHING, &lip->li_flags))
 			goto next_item;
@@ -514,14 +523,17 @@ xfsaild_push(
 		 * Note that iop_push may unlock and reacquire the AIL lock.  We
 		 * rely on the AIL cursor implementation to be able to deal with
 		 * the dropped lock.
+		 *
+		 * The log item may have been freed by the push, so it must not
+		 * be accessed or dereferenced below this line.
 		 */
 		lock_result = xfsaild_push_item(ailp, lip);
 		switch (lock_result) {
 		case XFS_ITEM_SUCCESS:
 			XFS_STATS_INC(mp, xs_push_ail_success);
-			trace_xfs_ail_push(lip);
+			trace_xfs_ail_push(ailp, type, flags, item_lsn);
 
-			ailp->ail_last_pushed_lsn = lsn;
+			ailp->ail_last_pushed_lsn = item_lsn;
 			break;
 
 		case XFS_ITEM_FLUSHING:
@@ -537,22 +549,22 @@ xfsaild_push(
 			 * AIL is being flushed.
 			 */
 			XFS_STATS_INC(mp, xs_push_ail_flushing);
-			trace_xfs_ail_flushing(lip);
+			trace_xfs_ail_flushing(ailp, type, flags, item_lsn);
 
 			flushing++;
-			ailp->ail_last_pushed_lsn = lsn;
+			ailp->ail_last_pushed_lsn = item_lsn;
 			break;
 
 		case XFS_ITEM_PINNED:
 			XFS_STATS_INC(mp, xs_push_ail_pinned);
-			trace_xfs_ail_pinned(lip);
+			trace_xfs_ail_pinned(ailp, type, flags, item_lsn);
 
 			stuck++;
 			ailp->ail_log_flush++;
 			break;
 		case XFS_ITEM_LOCKED:
 			XFS_STATS_INC(mp, xs_push_ail_locked);
-			trace_xfs_ail_locked(lip);
+			trace_xfs_ail_locked(ailp, type, flags, item_lsn);
 
 			stuck++;
 			break;
-- 
cgit v1.2.3


From 394d70b86fae9fe865e7e6d9540b7696f73aa9b6 Mon Sep 17 00:00:00 2001
From: Yuto Ohnuki <ytohnuki@amazon.com>
Date: Tue, 10 Mar 2026 18:38:39 +0000
Subject: xfs: save ailp before dropping the AIL lock in push callbacks

In xfs_inode_item_push() and xfs_qm_dquot_logitem_push(), the AIL lock
is dropped to perform buffer IO. Once the cluster buffer no longer
protects the log item from reclaim, the log item may be freed by
background reclaim or the dquot shrinker. The subsequent spin_lock()
call dereferences lip->li_ailp, which is a use-after-free.

Fix this by saving the ailp pointer in a local variable while the AIL
lock is held and the log item is guaranteed to be valid.

Reported-by: syzbot+652af2b3c5569c4ab63c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=652af2b3c5569c4ab63c
Fixes: 90c60e164012 ("xfs: xfs_iflush() is no longer necessary")
Cc: stable@vger.kernel.org # v5.9
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Yuto Ohnuki <ytohnuki@amazon.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_dquot_item.c | 9 +++++++--
 fs/xfs/xfs_inode_item.c | 9 +++++++--
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 491e2a7053a3..65a0e69c3d08 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -125,6 +125,7 @@ xfs_qm_dquot_logitem_push(
 	struct xfs_dq_logitem	*qlip = DQUOT_ITEM(lip);
 	struct xfs_dquot	*dqp = qlip->qli_dquot;
 	struct xfs_buf		*bp;
+	struct xfs_ail		*ailp = lip->li_ailp;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
@@ -153,7 +154,7 @@ xfs_qm_dquot_logitem_push(
 		goto out_unlock;
 	}
 
-	spin_unlock(&lip->li_ailp->ail_lock);
+	spin_unlock(&ailp->ail_lock);
 
 	error = xfs_dquot_use_attached_buf(dqp, &bp);
 	if (error == -EAGAIN) {
@@ -172,9 +173,13 @@ xfs_qm_dquot_logitem_push(
 			rval = XFS_ITEM_FLUSHING;
 	}
 	xfs_buf_relse(bp);
+	/*
+	 * The buffer no longer protects the log item from reclaim, so
+	 * do not reference lip after this point.
+	 */
 
 out_relock_ail:
-	spin_lock(&lip->li_ailp->ail_lock);
+	spin_lock(&ailp->ail_lock);
 out_unlock:
 	mutex_unlock(&dqp->q_qlock);
 	return rval;
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 8913036b8024..4ae81eed0442 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -746,6 +746,7 @@ xfs_inode_item_push(
 	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
 	struct xfs_inode	*ip = iip->ili_inode;
 	struct xfs_buf		*bp = lip->li_buf;
+	struct xfs_ail		*ailp = lip->li_ailp;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
@@ -771,7 +772,7 @@ xfs_inode_item_push(
 	if (!xfs_buf_trylock(bp))
 		return XFS_ITEM_LOCKED;
 
-	spin_unlock(&lip->li_ailp->ail_lock);
+	spin_unlock(&ailp->ail_lock);
 
 	/*
 	 * We need to hold a reference for flushing the cluster buffer as it may
@@ -795,7 +796,11 @@ xfs_inode_item_push(
 		rval = XFS_ITEM_LOCKED;
 	}
 
-	spin_lock(&lip->li_ailp->ail_lock);
+	/*
+	 * The buffer no longer protects the log item from reclaim, so
+	 * do not reference lip after this point.
+	 */
+	spin_lock(&ailp->ail_lock);
 	return rval;
 }
 
-- 
cgit v1.2.3


From 7cac60947335f8d88a6390814840590a61134484 Mon Sep 17 00:00:00 2001
From: Yuto Ohnuki <ytohnuki@amazon.com>
Date: Tue, 10 Mar 2026 18:38:40 +0000
Subject: xfs: refactor xfsaild_push loop into helper

Factor the loop body of xfsaild_push() into a separate
xfsaild_process_logitem() helper to improve readability.

This is a pure code movement with no functional change.

Signed-off-by: Yuto Ohnuki <ytohnuki@amazon.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_trans_ail.c | 127 +++++++++++++++++++++++++++----------------------
 1 file changed, 69 insertions(+), 58 deletions(-)

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 63266d31b514..99a9bf3762b7 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -464,6 +464,74 @@ xfs_ail_calc_push_target(
 	return target_lsn;
 }
 
+static void
+xfsaild_process_logitem(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	*lip,
+	int			*stuck,
+	int			*flushing)
+{
+	struct xfs_mount	*mp = ailp->ail_log->l_mp;
+	uint			type = lip->li_type;
+	unsigned long		flags = lip->li_flags;
+	xfs_lsn_t		item_lsn = lip->li_lsn;
+	int			lock_result;
+
+	/*
+	 * Note that iop_push may unlock and reacquire the AIL lock. We
+	 * rely on the AIL cursor implementation to be able to deal with
+	 * the dropped lock.
+	 *
+	 * The log item may have been freed by the push, so it must not
+	 * be accessed or dereferenced below this line.
+	 */
+	lock_result = xfsaild_push_item(ailp, lip);
+	switch (lock_result) {
+	case XFS_ITEM_SUCCESS:
+		XFS_STATS_INC(mp, xs_push_ail_success);
+		trace_xfs_ail_push(ailp, type, flags, item_lsn);
+
+		ailp->ail_last_pushed_lsn = item_lsn;
+		break;
+
+	case XFS_ITEM_FLUSHING:
+		/*
+		 * The item or its backing buffer is already being
+		 * flushed.  The typical reason for that is that an
+		 * inode buffer is locked because we already pushed the
+		 * updates to it as part of inode clustering.
+		 *
+		 * We do not want to stop flushing just because lots
+		 * of items are already being flushed, but we need to
+		 * re-try the flushing relatively soon if most of the
+		 * AIL is being flushed.
+		 */
+		XFS_STATS_INC(mp, xs_push_ail_flushing);
+		trace_xfs_ail_flushing(ailp, type, flags, item_lsn);
+
+		(*flushing)++;
+		ailp->ail_last_pushed_lsn = item_lsn;
+		break;
+
+	case XFS_ITEM_PINNED:
+		XFS_STATS_INC(mp, xs_push_ail_pinned);
+		trace_xfs_ail_pinned(ailp, type, flags, item_lsn);
+
+		(*stuck)++;
+		ailp->ail_log_flush++;
+		break;
+	case XFS_ITEM_LOCKED:
+		XFS_STATS_INC(mp, xs_push_ail_locked);
+		trace_xfs_ail_locked(ailp, type, flags, item_lsn);
+
+		(*stuck)++;
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+}
+
 static long
 xfsaild_push(
 	struct xfs_ail		*ailp)
@@ -511,68 +579,11 @@ xfsaild_push(
 
 	lsn = lip->li_lsn;
 	while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) {
-		int		lock_result;
-		uint		type = lip->li_type;
-		unsigned long	flags = lip->li_flags;
-		xfs_lsn_t	item_lsn = lip->li_lsn;
 
 		if (test_bit(XFS_LI_FLUSHING, &lip->li_flags))
 			goto next_item;
 
-		/*
-		 * Note that iop_push may unlock and reacquire the AIL lock.  We
-		 * rely on the AIL cursor implementation to be able to deal with
-		 * the dropped lock.
-		 *
-		 * The log item may have been freed by the push, so it must not
-		 * be accessed or dereferenced below this line.
-		 */
-		lock_result = xfsaild_push_item(ailp, lip);
-		switch (lock_result) {
-		case XFS_ITEM_SUCCESS:
-			XFS_STATS_INC(mp, xs_push_ail_success);
-			trace_xfs_ail_push(ailp, type, flags, item_lsn);
-
-			ailp->ail_last_pushed_lsn = item_lsn;
-			break;
-
-		case XFS_ITEM_FLUSHING:
-			/*
-			 * The item or its backing buffer is already being
-			 * flushed.  The typical reason for that is that an
-			 * inode buffer is locked because we already pushed the
-			 * updates to it as part of inode clustering.
-			 *
-			 * We do not want to stop flushing just because lots
-			 * of items are already being flushed, but we need to
-			 * re-try the flushing relatively soon if most of the
-			 * AIL is being flushed.
-			 */
-			XFS_STATS_INC(mp, xs_push_ail_flushing);
-			trace_xfs_ail_flushing(ailp, type, flags, item_lsn);
-
-			flushing++;
-			ailp->ail_last_pushed_lsn = item_lsn;
-			break;
-
-		case XFS_ITEM_PINNED:
-			XFS_STATS_INC(mp, xs_push_ail_pinned);
-			trace_xfs_ail_pinned(ailp, type, flags, item_lsn);
-
-			stuck++;
-			ailp->ail_log_flush++;
-			break;
-		case XFS_ITEM_LOCKED:
-			XFS_STATS_INC(mp, xs_push_ail_locked);
-			trace_xfs_ail_locked(ailp, type, flags, item_lsn);
-
-			stuck++;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
-
+		xfsaild_process_logitem(ailp, lip, &stuck, &flushing);
 		count++;
 
 		/*
-- 
cgit v1.2.3


From 268378b6ad20569af0d1957992de1c8b16c6e900 Mon Sep 17 00:00:00 2001
From: hongao <hongao@uniontech.com>
Date: Thu, 12 Mar 2026 20:10:26 +0800
Subject: xfs: scrub: unlock dquot before early return in quota scrub

xchk_quota_item can return early after calling xchk_fblock_process_error.
When that helper returns false, the function returned immediately without
dropping dq->q_qlock, which can leave the dquot lock held and risk lock
leaks or deadlocks in later quota operations.

Fix this by unlocking dq->q_qlock before the early return.

Signed-off-by: hongao <hongao@uniontech.com>
Fixes: 7d1f0e167a067e ("xfs: check the ondisk space mapping behind a dquot")
Cc: <stable@vger.kernel.org> # v6.8
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/quota.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 1d25bd5b892e..222812fe202c 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -171,8 +171,10 @@ xchk_quota_item(
 
 	error = xchk_quota_item_bmap(sc, dq, offset);
 	xchk_iunlock(sc, XFS_ILOCK_SHARED);
-	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) {
+		mutex_unlock(&dq->q_qlock);
 		return error;
+	}
 
 	/*
 	 * Warn if the hard limits are larger than the fs.
-- 
cgit v1.2.3


From 0c98524ab20193d8772cff9c71b00ad004fb1349 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Mar 2026 16:35:29 +0100
Subject: xfs: cleanup buftarg handling in XFS_IOC_VERIFY_MEDIA

The newly added XFS_IOC_VERIFY_MEDIA is a bit unusual in how it handles
buftarg fields.  Update it to be more in line with other XFS code:

 - use btp->bt_dev instead of btp->bt_bdev->bd_dev to retrieve the device
   number for tracing
 - use btp->bt_logical_sectorsize instead of
   bdev_logical_block_size(btp->bt_bdev) to retrieve the logical sector
   size
 - compare the buftarg and not the bdev to see if there is a separate
   log buftarg

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_verify_media.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c
index 8bbd4ec567f8..5ead3976d511 100644
--- a/fs/xfs/xfs_verify_media.c
+++ b/fs/xfs/xfs_verify_media.c
@@ -183,10 +183,9 @@ xfs_verify_iosize(
 			min_not_zero(SZ_1M, me->me_max_io_size);
 
 	BUILD_BUG_ON(BBSHIFT != SECTOR_SHIFT);
-	ASSERT(BBTOB(bbcount) >= bdev_logical_block_size(btp->bt_bdev));
+	ASSERT(BBTOB(bbcount) >= btp->bt_logical_sectorsize);
 
-	return clamp(iosize, bdev_logical_block_size(btp->bt_bdev),
-			BBTOB(bbcount));
+	return clamp(iosize, btp->bt_logical_sectorsize, BBTOB(bbcount));
 }
 
 /* Allocate as much memory as we can get for verification buffer. */
@@ -218,8 +217,8 @@ xfs_verify_media_error(
 	unsigned int		bio_bbcount,
 	blk_status_t		bio_status)
 {
-	trace_xfs_verify_media_error(mp, me, btp->bt_bdev->bd_dev, daddr,
-			bio_bbcount, bio_status);
+	trace_xfs_verify_media_error(mp, me, btp->bt_dev, daddr, bio_bbcount,
+			bio_status);
 
 	/*
 	 * Pass any error, I/O or otherwise, up to the caller if we didn't
@@ -280,7 +279,7 @@ xfs_verify_media(
 		btp = mp->m_ddev_targp;
 		break;
 	case XFS_DEV_LOG:
-		if (mp->m_logdev_targp->bt_bdev != mp->m_ddev_targp->bt_bdev)
+		if (mp->m_logdev_targp != mp->m_ddev_targp)
 			btp = mp->m_logdev_targp;
 		break;
 	case XFS_DEV_RT:
@@ -299,7 +298,7 @@ xfs_verify_media(
 
 	/* start and end have to be aligned to the lba size */
 	if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr),
-			bdev_logical_block_size(btp->bt_bdev)))
+			btp->bt_logical_sectorsize))
 		return -EINVAL;
 
 	/*
@@ -331,8 +330,7 @@ xfs_verify_media(
 	if (!folio)
 		return -ENOMEM;
 
-	trace_xfs_verify_media(mp, me, btp->bt_bdev->bd_dev, daddr, bbcount,
-			folio);
+	trace_xfs_verify_media(mp, me, btp->bt_dev, daddr, bbcount, folio);
 
 	bio = bio_alloc(btp->bt_bdev, 1, REQ_OP_READ, GFP_KERNEL);
 	if (!bio) {
@@ -400,7 +398,7 @@ out_folio:
 	 * an operational error.
 	 */
 	me->me_start_daddr = daddr;
-	trace_xfs_verify_media_end(mp, me, btp->bt_bdev->bd_dev);
+	trace_xfs_verify_media_end(mp, me, btp->bt_dev);
 	return 0;
 }
 
-- 
cgit v1.2.3


From e5966096d0856d071269cb5928d6bc33342d2dfd Mon Sep 17 00:00:00 2001
From: Bill Wendling <morbo@google.com>
Date: Mon, 16 Mar 2026 18:41:58 +0000
Subject: xfs: annotate struct xfs_attr_list_context with __counted_by_ptr

Add the `__counted_by_ptr` attribute to the `buffer` field of `struct
xfs_attr_list_context`. This field is used to point to a buffer of
size `bufsize`.

The `buffer` field is assigned in:
1. `xfs_ioc_attr_list` in `fs/xfs/xfs_handle.c`
2. `xfs_xattr_list` in `fs/xfs/xfs_xattr.c`
3. `xfs_getparents` in `fs/xfs/xfs_handle.c` (implicitly initialized to NULL)

In `xfs_ioc_attr_list`, `buffer` was assigned before `bufsize`. Reorder
them to ensure `bufsize` is set before `buffer` is assigned, although
no access happens between them.

In `xfs_xattr_list`, `buffer` was assigned before `bufsize`. Reorder
them to ensure `bufsize` is set before `buffer` is assigned.

In `xfs_getparents`, `buffer` is NULL (from zero initialization) and
remains NULL. `bufsize` is set to a non-zero value, but since `buffer`
is NULL, no access occurs.

In all cases, the pointer `buffer` is not accessed before `bufsize` is set.

This patch was generated by CodeMender and reviewed by Bill Wendling.
Tested by running xfstests.

Signed-off-by: Bill Wendling <morbo@google.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_attr.h | 3 ++-
 fs/xfs/xfs_handle.c      | 2 +-
 fs/xfs/xfs_xattr.c       | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 8244305949de..67fd9c75ac3f 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -55,7 +55,8 @@ struct xfs_attr_list_context {
 	struct xfs_trans	*tp;
 	struct xfs_inode	*dp;		/* inode */
 	struct xfs_attrlist_cursor_kern cursor;	/* position in list */
-	void			*buffer;	/* output buffer */
+	/* output buffer */
+	void			*buffer __counted_by_ptr(bufsize);
 
 	/*
 	 * Abort attribute list iteration if non-zero.  Can be used to pass
diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c
index d1291ca15239..2b8617ae7ec2 100644
--- a/fs/xfs/xfs_handle.c
+++ b/fs/xfs/xfs_handle.c
@@ -443,8 +443,8 @@ xfs_ioc_attr_list(
 	context.dp = dp;
 	context.resynch = 1;
 	context.attr_filter = xfs_attr_filter(flags);
-	context.buffer = buffer;
 	context.bufsize = round_down(bufsize, sizeof(uint32_t));
+	context.buffer = buffer;
 	context.firstu = context.bufsize;
 	context.put_listent = xfs_ioc_attr_put_listent;
 
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index a735f16d9cd8..544213067d59 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -332,8 +332,8 @@ xfs_vn_listxattr(
 	memset(&context, 0, sizeof(context));
 	context.dp = XFS_I(inode);
 	context.resynch = 1;
-	context.buffer = size ? data : NULL;
 	context.bufsize = size;
+	context.buffer = size ? data : NULL;
 	context.firstu = context.bufsize;
 	context.put_listent = xfs_xattr_put_listent;
 
-- 
cgit v1.2.3


From bd71fb3fea9945987053968f028a948997cba8cc Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 17 Mar 2026 13:39:35 -0700
Subject: iomap: fix invalid folio access when i_blkbits differs from I/O
 granularity

Commit aa35dd5cbc06 ("iomap: fix invalid folio access after
folio_end_read()") partially addressed invalid folio access for folios
without an ifs attached, but it did not handle the case where
1 << inode->i_blkbits matches the folio size but is different from the
granularity used for the IO, which means IO can be submitted for less
than the full folio for the !ifs case.

In this case, the condition:

  if (*bytes_submitted == folio_len)
    ctx->cur_folio = NULL;

in iomap_read_folio_iter() will not invalidate ctx->cur_folio, and
iomap_read_end() will still be called on the folio even though the IO
helper owns it and will finish the read on it.

Fix this by unconditionally invalidating ctx->cur_folio for the !ifs
case.

Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/linux-fsdevel/b3dfe271-4e3d-4922-b618-e73731242bca@wdc.com/
Fixes: b2f35ac4146d ("iomap: add caller-provided callbacks for read and readahead")
Cc: stable@vger.kernel.org
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20260317203935.830549-1-joannelkoong@gmail.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 00f0efaf12b2..92a831cf4bf1 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -514,6 +514,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 	loff_t length = iomap_length(iter);
 	struct folio *folio = ctx->cur_folio;
 	size_t folio_len = folio_size(folio);
+	struct iomap_folio_state *ifs;
 	size_t poff, plen;
 	loff_t pos_diff;
 	int ret;
@@ -525,7 +526,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 		return iomap_iter_advance(iter, length);
 	}
 
-	ifs_alloc(iter->inode, folio, iter->flags);
+	ifs = ifs_alloc(iter->inode, folio, iter->flags);
 
 	length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos));
 	while (length) {
@@ -560,11 +561,15 @@ static int iomap_read_folio_iter(struct iomap_iter *iter,
 
 			*bytes_submitted += plen;
 			/*
-			 * If the entire folio has been read in by the IO
-			 * helper, then the helper owns the folio and will end
-			 * the read on it.
+			 * Hand off folio ownership to the IO helper when:
+			 * 1) The entire folio has been submitted for IO, or
+			 * 2) There is no ifs attached to the folio
+			 *
+			 * Case (2) occurs when 1 << i_blkbits matches the folio
+			 * size but the underlying filesystem or block device
+			 * uses a smaller granularity for IO.
 			 */
-			if (*bytes_submitted == folio_len)
+			if (*bytes_submitted == folio_len || !ifs)
 				ctx->cur_folio = NULL;
 		}
 
-- 
cgit v1.2.3


From 0162ab3220bac870e43e229e6e3024d1a21c3f26 Mon Sep 17 00:00:00 2001
From: Rahul Bukte <rahul.bukte@sony.com>
Date: Tue, 3 Feb 2026 10:18:39 +0530
Subject: drm/i915/gt: Check set_default_submission() before deferencing

When the i915 driver firmware binaries are not present, the
set_default_submission pointer is not set. This pointer is
dereferenced during suspend anyways.

Add a check to make sure it is set before dereferencing.

[   23.289926] PM: suspend entry (deep)
[   23.293558] Filesystems sync: 0.000 seconds
[   23.298010] Freezing user space processes
[   23.302771] Freezing user space processes completed (elapsed 0.000 seconds)
[   23.309766] OOM killer disabled.
[   23.313027] Freezing remaining freezable tasks
[   23.318540] Freezing remaining freezable tasks completed (elapsed 0.001 seconds)
[   23.342038] serial 00:05: disabled
[   23.345719] serial 00:02: disabled
[   23.349342] serial 00:01: disabled
[   23.353782] sd 0:0:0:0: [sda] Synchronizing SCSI cache
[   23.358993] sd 1:0:0:0: [sdb] Synchronizing SCSI cache
[   23.361635] ata1.00: Entering standby power mode
[   23.368863] ata2.00: Entering standby power mode
[   23.445187] BUG: kernel NULL pointer dereference, address: 0000000000000000
[   23.452194] #PF: supervisor instruction fetch in kernel mode
[   23.457896] #PF: error_code(0x0010) - not-present page
[   23.463065] PGD 0 P4D 0
[   23.465640] Oops: Oops: 0010 [#1] SMP NOPTI
[   23.469869] CPU: 8 UID: 0 PID: 211 Comm: kworker/u48:18 Tainted: G S      W           6.19.0-rc4-00020-gf0b9d8eb98df #10 PREEMPT(voluntary)
[   23.482512] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
[   23.496511] Workqueue: async async_run_entry_fn
[   23.501087] RIP: 0010:0x0
[   23.503755] Code: Unable to access opcode bytes at 0xffffffffffffffd6.
[   23.510324] RSP: 0018:ffffb4a60065fca8 EFLAGS: 00010246
[   23.515592] RAX: 0000000000000000 RBX: ffff9f428290e000 RCX: 000000000000000f
[   23.522765] RDX: 0000000000000000 RSI: 0000000000000282 RDI: ffff9f428290e000
[   23.529937] RBP: ffff9f4282907070 R08: ffff9f4281130428 R09: 00000000ffffffff
[   23.537111] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f42829070f8
[   23.544284] R13: ffff9f4282906028 R14: ffff9f4282900000 R15: ffff9f4282906b68
[   23.551457] FS:  0000000000000000(0000) GS:ffff9f466b2cf000(0000) knlGS:0000000000000000
[   23.559588] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   23.565365] CR2: ffffffffffffffd6 CR3: 000000031c230001 CR4: 0000000000f70ef0
[   23.572539] PKRU: 55555554
[   23.575281] Call Trace:
[   23.577770]  <TASK>
[   23.579905]  intel_engines_reset_default_submission+0x42/0x60
[   23.585695]  __intel_gt_unset_wedged+0x191/0x200
[   23.590360]  intel_gt_unset_wedged+0x20/0x40
[   23.594675]  gt_sanitize+0x15e/0x170
[   23.598290]  i915_gem_suspend_late+0x6b/0x180
[   23.602692]  i915_drm_suspend_late+0x35/0xf0
[   23.607008]  ? __pfx_pci_pm_suspend_late+0x10/0x10
[   23.611843]  dpm_run_callback+0x78/0x1c0
[   23.615817]  device_suspend_late+0xde/0x2e0
[   23.620037]  async_suspend_late+0x18/0x30
[   23.624082]  async_run_entry_fn+0x25/0xa0
[   23.628129]  process_one_work+0x15b/0x380
[   23.632182]  worker_thread+0x2a5/0x3c0
[   23.635973]  ? __pfx_worker_thread+0x10/0x10
[   23.640279]  kthread+0xf6/0x1f0
[   23.643464]  ? __pfx_kthread+0x10/0x10
[   23.647263]  ? __pfx_kthread+0x10/0x10
[   23.651045]  ret_from_fork+0x131/0x190
[   23.654837]  ? __pfx_kthread+0x10/0x10
[   23.658634]  ret_from_fork_asm+0x1a/0x30
[   23.662597]  </TASK>
[   23.664826] Modules linked in:
[   23.667914] CR2: 0000000000000000
[   23.671271] ------------[ cut here ]------------

Signed-off-by: Rahul Bukte <rahul.bukte@sony.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://patch.msgid.link/20260203044839.1555147-1-suraj.kandpal@intel.com
(cherry picked from commit daa199abc3d3d1740c9e3a2c3e9216ae5b447cad)
Fixes: ff44ad51ebf8 ("drm/i915: Move engine->submit_request selection to a vfunc")
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index d37966ec7a92..54c9571327e7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1967,7 +1967,8 @@ void intel_engines_reset_default_submission(struct intel_gt *gt)
 		if (engine->sanitize)
 			engine->sanitize(engine);
 
-		engine->set_default_submission(engine);
+		if (engine->set_default_submission)
+			engine->set_default_submission(engine);
 	}
 }
 
-- 
cgit v1.2.3


From 11a95521fb93c91e2d4ef9d53dc80ef0a755549b Mon Sep 17 00:00:00 2001
From: Jacob Moroni <jmoroni@google.com>
Date: Mon, 16 Mar 2026 13:39:38 -0500
Subject: RDMA/irdma: Initialize free_qp completion before using it

In irdma_create_qp, if ib_copy_to_udata fails, it will call
irdma_destroy_qp to clean up which will attempt to wait on
the free_qp completion, which is not initialized yet. Fix this
by initializing the completion before the ib_copy_to_udata call.

Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
Signed-off-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index a20d25585993..ce1050bdd191 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -1105,6 +1105,7 @@ static int irdma_create_qp(struct ib_qp *ibqp,
 	spin_lock_init(&iwqp->sc_qp.pfpdu.lock);
 	iwqp->sig_all = init_attr->sq_sig_type == IB_SIGNAL_ALL_WR;
 	rf->qp_table[qp_num] = iwqp;
+	init_completion(&iwqp->free_qp);
 
 	if (udata) {
 		/* GEN_1 legacy support with libi40iw does not have expanded uresp struct */
@@ -1129,7 +1130,6 @@ static int irdma_create_qp(struct ib_qp *ibqp,
 		}
 	}
 
-	init_completion(&iwqp->free_qp);
 	return 0;
 
 error:
-- 
cgit v1.2.3


From 8c1f19a2225cf37b3f8ab0b5a8a5322291cda620 Mon Sep 17 00:00:00 2001
From: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Date: Mon, 16 Mar 2026 13:39:41 -0500
Subject: RDMA/irdma: Update ibqp state to error if QP is already in error
 state

In irdma_modify_qp() update ibqp state to error if the irdma QP is already
in error state, otherwise the ibqp state which is visible to the consumer
app remains stale.

Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index ce1050bdd191..a13ed000fa19 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -1540,6 +1540,7 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
+				iwqp->ibqp_state = attr->qp_state;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
 					if (ib_copy_from_udata(&ureq, udata,
@@ -1745,6 +1746,7 @@ int irdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
 		case IB_QPS_ERR:
 		case IB_QPS_RESET:
 			if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) {
+				iwqp->ibqp_state = attr->qp_state;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
 				if (udata && udata->inlen) {
 					if (ib_copy_from_udata(&ureq, udata,
-- 
cgit v1.2.3


From 5e8f0239731a83753473b7aa91bda67bbdff5053 Mon Sep 17 00:00:00 2001
From: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Date: Mon, 16 Mar 2026 13:39:42 -0500
Subject: RDMA/irdma: Remove a NOP wait_event() in irdma_modify_qp_roce()

Remove a NOP wait_event() in irdma_modify_qp_roce() which is relevant
for iWARP and likely a copy and paste artifact for RoCEv2. The wait event
is for sending a reset on a TCP connection, after the reset has been
requested in irdma_modify_qp(), which occurs only in iWarp mode.

Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index a13ed000fa19..9920a3304be3 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -1462,8 +1462,6 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				ctx_info->remote_atomics_en = true;
 	}
 
-	wait_event(iwqp->mod_qp_waitq, !atomic_read(&iwqp->hw_mod_qp_pend));
-
 	ibdev_dbg(&iwdev->ibdev,
 		  "VERBS: caller: %pS qp_id=%d to_ibqpstate=%d ibqpstate=%d irdma_qpstate=%d attr_mask=0x%x\n",
 		  __builtin_return_address(0), ibqp->qp_num, attr->qp_state,
-- 
cgit v1.2.3


From b415399c9a024d574b65479636f0d4eb625b9abd Mon Sep 17 00:00:00 2001
From: Ivan Barrera <ivan.d.barrera@intel.com>
Date: Mon, 16 Mar 2026 13:39:43 -0500
Subject: RDMA/irdma: Clean up unnecessary dereference of event->cm_node

The cm_node is available and the usage of cm_node and event->cm_node
seems arbitrary. Clean up unnecessary dereference of event->cm_node.

Fixes: 146b9756f14c ("RDMA/irdma: Add connection manager")
Signed-off-by: Ivan Barrera <ivan.d.barrera@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/cm.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c
index 3d084d4ff577..13b24ffca265 100644
--- a/drivers/infiniband/hw/irdma/cm.c
+++ b/drivers/infiniband/hw/irdma/cm.c
@@ -4239,21 +4239,21 @@ static void irdma_cm_event_handler(struct work_struct *work)
 		irdma_cm_event_reset(event);
 		break;
 	case IRDMA_CM_EVENT_CONNECTED:
-		if (!event->cm_node->cm_id ||
-		    event->cm_node->state != IRDMA_CM_STATE_OFFLOADED)
+		if (!cm_node->cm_id ||
+		    cm_node->state != IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_cm_event_connected(event);
 		break;
 	case IRDMA_CM_EVENT_MPA_REJECT:
-		if (!event->cm_node->cm_id ||
+		if (!cm_node->cm_id ||
 		    cm_node->state == IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_send_cm_event(cm_node, cm_node->cm_id,
 				    IW_CM_EVENT_CONNECT_REPLY, -ECONNREFUSED);
 		break;
 	case IRDMA_CM_EVENT_ABORTED:
-		if (!event->cm_node->cm_id ||
-		    event->cm_node->state == IRDMA_CM_STATE_OFFLOADED)
+		if (!cm_node->cm_id ||
+		    cm_node->state == IRDMA_CM_STATE_OFFLOADED)
 			break;
 		irdma_event_connect_error(event);
 		break;
@@ -4263,7 +4263,7 @@ static void irdma_cm_event_handler(struct work_struct *work)
 		break;
 	}
 
-	irdma_rem_ref_cm_node(event->cm_node);
+	irdma_rem_ref_cm_node(cm_node);
 	kfree(event);
 }
 
-- 
cgit v1.2.3


From c45c6ebd693b944f1ffe429fdfb6cc1674c237be Mon Sep 17 00:00:00 2001
From: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Date: Mon, 16 Mar 2026 13:39:44 -0500
Subject: RDMA/irdma: Remove reset check from irdma_modify_qp_to_err()

During reset, irdma_modify_qp() to error should be called to disconnect
the QP. Without this fix, if not preceded by irdma_modify_qp() to error, the
API call irdma_destroy_qp() gets stuck waiting for the QP refcount to go
to zero, because the cm_node associated with this QP isn't disconnected.

Fixes: 915cc7ac0f8e ("RDMA/irdma: Add miscellaneous utility definitions")
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/utils.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c
index ab8c5284d4be..495e5daff4b4 100644
--- a/drivers/infiniband/hw/irdma/utils.c
+++ b/drivers/infiniband/hw/irdma/utils.c
@@ -2322,8 +2322,6 @@ void irdma_modify_qp_to_err(struct irdma_sc_qp *sc_qp)
 	struct irdma_qp *qp = sc_qp->qp_uk.back_qp;
 	struct ib_qp_attr attr;
 
-	if (qp->iwdev->rf->reset)
-		return;
 	attr.qp_state = IB_QPS_ERR;
 
 	if (rdma_protocol_roce(qp->ibqp.device, 1))
-- 
cgit v1.2.3


From 6f52370970ac07d352a7af4089e55e0e6425f827 Mon Sep 17 00:00:00 2001
From: Anil Samal <anil.samal@intel.com>
Date: Mon, 16 Mar 2026 13:39:45 -0500
Subject: RDMA/irdma: Fix deadlock during netdev reset with active connections

Resolve deadlock that occurs when user executes netdev reset while RDMA
applications (e.g., rping) are active. The netdev reset causes ice
driver to remove irdma auxiliary driver, triggering device_delete and
subsequent client removal. During client removal, uverbs_client waits
for QP reference count to reach zero while cma_client holds the final
reference, creating circular dependency and indefinite wait in iWARP
mode. Skip QP reference count wait during device reset to prevent
deadlock.

Fixes: c8f304d75f6c ("RDMA/irdma: Prevent QP use after free")
Signed-off-by: Anil Samal <anil.samal@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/verbs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 9920a3304be3..95f590c10c05 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -558,7 +558,8 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 	}
 
 	irdma_qp_rem_ref(&iwqp->ibqp);
-	wait_for_completion(&iwqp->free_qp);
+	if (!iwdev->rf->reset)
+		wait_for_completion(&iwqp->free_qp);
 	irdma_free_lsmm_rsrc(iwqp);
 	irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp);
 
-- 
cgit v1.2.3


From 7221f581eefa79ead06e171044f393fb7ee22f87 Mon Sep 17 00:00:00 2001
From: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Date: Mon, 16 Mar 2026 13:39:46 -0500
Subject: RDMA/irdma: Return EINVAL for invalid arp index error

When rdma_connect() fails due to an invalid arp index, user space rdma core
reports ENOMEM which is confusing. Modify irdma_make_cm_node() to return the
correct error code.

Fixes: 146b9756f14c ("RDMA/irdma: Add connection manager")
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/cm.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c
index 13b24ffca265..91c0e7298283 100644
--- a/drivers/infiniband/hw/irdma/cm.c
+++ b/drivers/infiniband/hw/irdma/cm.c
@@ -2241,11 +2241,12 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev,
 	int oldarpindex;
 	int arpindex;
 	struct net_device *netdev = iwdev->netdev;
+	int ret;
 
 	/* create an hte and cm_node for this instance */
 	cm_node = kzalloc_obj(*cm_node, GFP_ATOMIC);
 	if (!cm_node)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* set our node specific transport info */
 	cm_node->ipv4 = cm_info->ipv4;
@@ -2348,8 +2349,10 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev,
 			arpindex = -EINVAL;
 	}
 
-	if (arpindex < 0)
+	if (arpindex < 0) {
+		ret = -EINVAL;
 		goto err;
+	}
 
 	ether_addr_copy(cm_node->rem_mac,
 			iwdev->rf->arp_table[arpindex].mac_addr);
@@ -2360,7 +2363,7 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev,
 err:
 	kfree(cm_node);
 
-	return NULL;
+	return ERR_PTR(ret);
 }
 
 static void irdma_destroy_connection(struct irdma_cm_node *cm_node)
@@ -3021,8 +3024,8 @@ static int irdma_create_cm_node(struct irdma_cm_core *cm_core,
 
 	/* create a CM connection node */
 	cm_node = irdma_make_cm_node(cm_core, iwdev, cm_info, NULL);
-	if (!cm_node)
-		return -ENOMEM;
+	if (IS_ERR(cm_node))
+		return PTR_ERR(cm_node);
 
 	/* set our node side to client (active) side */
 	cm_node->tcp_cntxt.client = 1;
@@ -3219,9 +3222,9 @@ void irdma_receive_ilq(struct irdma_sc_vsi *vsi, struct irdma_puda_buf *rbuf)
 		cm_info.cm_id = listener->cm_id;
 		cm_node = irdma_make_cm_node(cm_core, iwdev, &cm_info,
 					     listener);
-		if (!cm_node) {
+		if (IS_ERR(cm_node)) {
 			ibdev_dbg(&cm_core->iwdev->ibdev,
-				  "CM: allocate node failed\n");
+				  "CM: allocate node failed ret=%ld\n", PTR_ERR(cm_node));
 			refcount_dec(&listener->refcnt);
 			return;
 		}
-- 
cgit v1.2.3


From e37afcb56ae070477741fe2d6e61fc0c542cce2d Mon Sep 17 00:00:00 2001
From: Shiraz Saleem <shiraz.saleem@intel.com>
Date: Mon, 16 Mar 2026 13:39:47 -0500
Subject: RDMA/irdma: Harden depth calculation functions

An issue was exposed where OS can pass in U32_MAX for SQ/RQ/SRQ size.
This can cause integer overflow and truncation of SQ/RQ/SRQ depth
returning a success when it should have failed.

Harden the functions to do all depth calculations and boundary
checking in u64 sizes.

Fixes: 563e1feb5f6e ("RDMA/irdma: Add SRQ support")
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/irdma/uk.c | 39 ++++++++++++++++++++++-----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index ac3721a5747a..4718acf6c6fd 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -1438,7 +1438,7 @@ exit:
  * irdma_round_up_wq - return round up qp wq depth
  * @wqdepth: wq depth in quanta to round up
  */
-static int irdma_round_up_wq(u32 wqdepth)
+static u64 irdma_round_up_wq(u64 wqdepth)
 {
 	int scount = 1;
 
@@ -1491,15 +1491,16 @@ void irdma_get_wqe_shift(struct irdma_uk_attrs *uk_attrs, u32 sge,
 int irdma_get_sqdepth(struct irdma_uk_attrs *uk_attrs, u32 sq_size, u8 shift,
 		      u32 *sqdepth)
 {
-	u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift;
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)sq_size << shift) + IRDMA_SQ_RSVD);
 
-	*sqdepth = irdma_round_up_wq((sq_size << shift) + IRDMA_SQ_RSVD);
-
-	if (*sqdepth < min_size)
-		*sqdepth = min_size;
-	else if (*sqdepth > uk_attrs->max_hw_wq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_wq_quanta)
 		return -EINVAL;
 
+	*sqdepth = hw_quanta;
 	return 0;
 }
 
@@ -1513,15 +1514,16 @@ int irdma_get_sqdepth(struct irdma_uk_attrs *uk_attrs, u32 sq_size, u8 shift,
 int irdma_get_rqdepth(struct irdma_uk_attrs *uk_attrs, u32 rq_size, u8 shift,
 		      u32 *rqdepth)
 {
-	u32 min_size = (u32)uk_attrs->min_hw_wq_size << shift;
-
-	*rqdepth = irdma_round_up_wq((rq_size << shift) + IRDMA_RQ_RSVD);
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)rq_size << shift) + IRDMA_RQ_RSVD);
 
-	if (*rqdepth < min_size)
-		*rqdepth = min_size;
-	else if (*rqdepth > uk_attrs->max_hw_rq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_rq_quanta)
 		return -EINVAL;
 
+	*rqdepth = hw_quanta;
 	return 0;
 }
 
@@ -1535,13 +1537,16 @@ int irdma_get_rqdepth(struct irdma_uk_attrs *uk_attrs, u32 rq_size, u8 shift,
 int irdma_get_srqdepth(struct irdma_uk_attrs *uk_attrs, u32 srq_size, u8 shift,
 		       u32 *srqdepth)
 {
-	*srqdepth = irdma_round_up_wq((srq_size << shift) + IRDMA_RQ_RSVD);
+	u32 min_hw_quanta = (u32)uk_attrs->min_hw_wq_size << shift;
+	u64 hw_quanta =
+		irdma_round_up_wq(((u64)srq_size << shift) + IRDMA_RQ_RSVD);
 
-	if (*srqdepth < ((u32)uk_attrs->min_hw_wq_size << shift))
-		*srqdepth = uk_attrs->min_hw_wq_size << shift;
-	else if (*srqdepth > uk_attrs->max_hw_srq_quanta)
+	if (hw_quanta < min_hw_quanta)
+		hw_quanta = min_hw_quanta;
+	else if (hw_quanta > uk_attrs->max_hw_srq_quanta)
 		return -EINVAL;
 
+	*srqdepth = hw_quanta;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 9232fa05921bc0ea0bc71947440ec9a50b3ad26e Mon Sep 17 00:00:00 2001
From: Michael Riesch <michael.riesch@collabora.com>
Date: Mon, 16 Feb 2026 13:28:47 +0100
Subject: media: synopsys: csi2rx: fix out-of-bounds check for formats array

The out-of-bounds check for the format array is off by one. Fix the
check.

Fixes: 355a11004066 ("media: synopsys: add driver for the designware mipi csi-2 receiver")
Cc: stable@kernel.org
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Michael Riesch <michael.riesch@collabora.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/synopsys/dw-mipi-csi2rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/synopsys/dw-mipi-csi2rx.c b/drivers/media/platform/synopsys/dw-mipi-csi2rx.c
index 170346ae1a59..4d96171a650b 100644
--- a/drivers/media/platform/synopsys/dw-mipi-csi2rx.c
+++ b/drivers/media/platform/synopsys/dw-mipi-csi2rx.c
@@ -301,7 +301,7 @@ dw_mipi_csi2rx_enum_mbus_code(struct v4l2_subdev *sd,
 
 		return 0;
 	case DW_MIPI_CSI2RX_PAD_SINK:
-		if (code->index > csi2->formats_num)
+		if (code->index >= csi2->formats_num)
 			return -EINVAL;
 
 		code->code = csi2->formats[code->index].code;
-- 
cgit v1.2.3


From ac62a20035ecc18e6d365c6c792f5965ce1da77c Mon Sep 17 00:00:00 2001
From: Michael Riesch <michael.riesch@collabora.com>
Date: Mon, 16 Feb 2026 13:28:48 +0100
Subject: media: synopsys: csi2rx: add missing kconfig dependency

Fix "ERROR: modpost: "phy_mipi_dphy_get_default_config_for_hsclk"
[drivers/media/platform/synopsys/dw-mipi-csi2rx.ko] undefined!" by
selecting GENERIC_PHY_MIPI_DPHY in the Kconfig entry.

Fixes: 355a11004066 ("media: synopsys: add driver for the designware mipi csi-2 receiver")
Cc: stable@kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202602130253.BZnVd4jh-lkp@intel.com/
Signed-off-by: Michael Riesch <michael.riesch@collabora.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/synopsys/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/synopsys/Kconfig b/drivers/media/platform/synopsys/Kconfig
index e798ec00b189..bf2ac092fbb3 100644
--- a/drivers/media/platform/synopsys/Kconfig
+++ b/drivers/media/platform/synopsys/Kconfig
@@ -7,6 +7,7 @@ config VIDEO_DW_MIPI_CSI2RX
 	depends on VIDEO_DEV
 	depends on V4L_PLATFORM_DRIVERS
 	depends on PM && COMMON_CLK
+	select GENERIC_PHY_MIPI_DPHY
 	select MEDIA_CONTROLLER
 	select V4L2_FWNODE
 	select VIDEO_V4L2_SUBDEV_API
-- 
cgit v1.2.3


From bef4f4a88b73e4cc550d25f665b8a9952af22773 Mon Sep 17 00:00:00 2001
From: Yuchan Nam <entropy1110@gmail.com>
Date: Fri, 6 Mar 2026 21:52:23 +0900
Subject: media: mc, v4l2: serialize REINIT and REQBUFS with req_queue_mutex

MEDIA_REQUEST_IOC_REINIT can run concurrently with VIDIOC_REQBUFS(0)
queue teardown paths. This can race request object cleanup against vb2
queue cancellation and lead to use-after-free reports.

We already serialize request queueing against STREAMON/OFF with
req_queue_mutex. Extend that serialization to REQBUFS, and also take
the same mutex in media_request_ioctl_reinit() so REINIT is in the
same exclusion domain.

This keeps request cleanup and queue cancellation from running in
parallel for request-capable devices.

Fixes: 6093d3002eab ("media: vb2: keep a reference to the request until dqbuf")
Cc: stable@vger.kernel.org
Signed-off-by: Yuchan Nam <entropy1110@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/mc/mc-request.c        | 5 +++++
 drivers/media/v4l2-core/v4l2-ioctl.c | 5 +++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/media/mc/mc-request.c b/drivers/media/mc/mc-request.c
index c7c7d4a86c6b..13e77648807c 100644
--- a/drivers/media/mc/mc-request.c
+++ b/drivers/media/mc/mc-request.c
@@ -192,6 +192,8 @@ static long media_request_ioctl_reinit(struct media_request *req)
 	struct media_device *mdev = req->mdev;
 	unsigned long flags;
 
+	mutex_lock(&mdev->req_queue_mutex);
+
 	spin_lock_irqsave(&req->lock, flags);
 	if (req->state != MEDIA_REQUEST_STATE_IDLE &&
 	    req->state != MEDIA_REQUEST_STATE_COMPLETE) {
@@ -199,6 +201,7 @@ static long media_request_ioctl_reinit(struct media_request *req)
 			"request: %s not in idle or complete state, cannot reinit\n",
 			req->debug_str);
 		spin_unlock_irqrestore(&req->lock, flags);
+		mutex_unlock(&mdev->req_queue_mutex);
 		return -EBUSY;
 	}
 	if (req->access_count) {
@@ -206,6 +209,7 @@ static long media_request_ioctl_reinit(struct media_request *req)
 			"request: %s is being accessed, cannot reinit\n",
 			req->debug_str);
 		spin_unlock_irqrestore(&req->lock, flags);
+		mutex_unlock(&mdev->req_queue_mutex);
 		return -EBUSY;
 	}
 	req->state = MEDIA_REQUEST_STATE_CLEANING;
@@ -216,6 +220,7 @@ static long media_request_ioctl_reinit(struct media_request *req)
 	spin_lock_irqsave(&req->lock, flags);
 	req->state = MEDIA_REQUEST_STATE_IDLE;
 	spin_unlock_irqrestore(&req->lock, flags);
+	mutex_unlock(&mdev->req_queue_mutex);
 
 	return 0;
 }
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 37d33d4a363d..a2b650f4ec3c 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -3082,13 +3082,14 @@ static long __video_do_ioctl(struct file *file,
 	}
 
 	/*
-	 * We need to serialize streamon/off with queueing new requests.
+	 * We need to serialize streamon/off/reqbufs with queueing new requests.
 	 * These ioctls may trigger the cancellation of a streaming
 	 * operation, and that should not be mixed with queueing a new
 	 * request at the same time.
 	 */
 	if (v4l2_device_supports_requests(vfd->v4l2_dev) &&
-	    (cmd == VIDIOC_STREAMON || cmd == VIDIOC_STREAMOFF)) {
+	    (cmd == VIDIOC_STREAMON || cmd == VIDIOC_STREAMOFF ||
+	     cmd == VIDIOC_REQBUFS)) {
 		req_queue_lock = &vfd->v4l2_dev->mdev->req_queue_mutex;
 
 		if (mutex_lock_interruptible(req_queue_lock))
-- 
cgit v1.2.3


From daa87ca42652af0d6791ef875e3c4d724b099f22 Mon Sep 17 00:00:00 2001
From: Detlev Casanova <detlev.casanova@collabora.com>
Date: Fri, 23 Jan 2026 14:22:44 -0500
Subject: media: rkvdec: Improve handling missing short/long term RPS

The values of ext_sps_st_rps and ext_sps_lt_rps in struct rkvdec_hevc_run
are not initialized when the respective controls are not set by userspace.

When this is the case, set them to NULL so the rkvdec_hevc_run_preamble
function that parses controls does not access garbage data which leads to
a panic on unaccessible memory.

Fixes: c9a59dc2acc7 ("media: rkvdec: Add HEVC support for the VDPU381 variant")
Reported-by: Christian Hewitt <christianshewitt@gmail.com>
Suggested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
Tested-by: Christian Hewitt <christianshewitt@gmail.com>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c
index 28267ee30190..3119f3bc9f98 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-hevc-common.c
@@ -500,11 +500,15 @@ void rkvdec_hevc_run_preamble(struct rkvdec_ctx *ctx,
 		ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl,
 				      V4L2_CID_STATELESS_HEVC_EXT_SPS_ST_RPS);
 		run->ext_sps_st_rps = ctrl ? ctrl->p_cur.p : NULL;
+	} else {
+		run->ext_sps_st_rps = NULL;
 	}
 	if (ctx->has_sps_lt_rps) {
 		ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl,
 				      V4L2_CID_STATELESS_HEVC_EXT_SPS_LT_RPS);
 		run->ext_sps_lt_rps = ctrl ? ctrl->p_cur.p : NULL;
+	} else {
+		run->ext_sps_lt_rps = NULL;
 	}
 
 	rkvdec_run_preamble(ctx, &run->base);
-- 
cgit v1.2.3


From 446c6a25a4494e137ec42e886da04e29efc2dc39 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Feb 2026 10:47:50 +0100
Subject: media: rkvdec: reduce excessive stack usage in assemble_hw_pps()

The rkvdec_pps had a large set of bitfields, all of which
as misaligned. This causes clang-21 and likely other versions to
produce absolutely awful object code and a warning about very
large stack usage, on targets without unaligned access:

drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c:966:12: error: stack frame size (1472) exceeds limit (1280) in 'rkvdec_vp9_start' [-Werror,-Wframe-larger-than]

Part of the problem here is how all the bitfield accesses are
inlined into a function that already has large structures on
the stack.

Mark set_field_order_cnt() as noinline_for_stack, and split out
the following accesses in assemble_hw_pps() into another noinline
function, both of which now using around 800 bytes of stack in the
same configuration.

There is clearly still something wrong with clang here, but
splitting it into multiple functions reduces the risk of stack
overflow.

Fixes: fde24907570d ("media: rkvdec: Add H264 support for the VDPU383 variant")
Link: https://godbolt.org/z/acP1eKeq9
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c | 50 ++++++++++++----------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c
index 97f1efde2e47..fb4f849d7366 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vdpu383-h264.c
@@ -130,7 +130,7 @@ struct rkvdec_h264_ctx {
 	struct vdpu383_regs_h26x regs;
 };
 
-static void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_dpb_entry *dpb)
+static noinline_for_stack void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_dpb_entry *dpb)
 {
 	pps->top_field_order_cnt0 = dpb[0].top_field_order_cnt;
 	pps->bot_field_order_cnt0 = dpb[0].bottom_field_order_cnt;
@@ -166,6 +166,31 @@ static void set_field_order_cnt(struct rkvdec_pps *pps, const struct v4l2_h264_d
 	pps->bot_field_order_cnt15 = dpb[15].bottom_field_order_cnt;
 }
 
+static noinline_for_stack void set_dec_params(struct rkvdec_pps *pps, const struct v4l2_ctrl_h264_decode_params *dec_params)
+{
+	const struct v4l2_h264_dpb_entry *dpb = dec_params->dpb;
+
+	for (int i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) {
+		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)
+			pps->is_longterm |= (1 << i);
+		pps->ref_field_flags |=
+		 (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD)) << i;
+		pps->ref_colmv_use_flag |=
+		 (!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) << i;
+		pps->ref_topfield_used |=
+		 (!!(dpb[i].fields & V4L2_H264_TOP_FIELD_REF)) << i;
+		pps->ref_botfield_used |=
+			(!!(dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)) << i;
+	}
+	pps->pic_field_flag =
+		!!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC);
+	pps->pic_associated_flag =
+		!!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD);
+
+	pps->cur_top_field = dec_params->top_field_order_cnt;
+	pps->cur_bot_field = dec_params->bottom_field_order_cnt;
+}
+
 static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 			    struct rkvdec_h264_run *run)
 {
@@ -177,7 +202,6 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 	struct rkvdec_h264_priv_tbl *priv_tbl = h264_ctx->priv_tbl.cpu;
 	struct rkvdec_sps_pps *hw_ps;
 	u32 pic_width, pic_height;
-	u32 i;
 
 	/*
 	 * HW read the SPS/PPS information from PPS packet index by PPS id.
@@ -261,28 +285,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 		!!(pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT);
 
 	set_field_order_cnt(&hw_ps->pps, dpb);
+	set_dec_params(&hw_ps->pps, dec_params);
 
-	for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) {
-		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM)
-			hw_ps->pps.is_longterm |= (1 << i);
-
-		hw_ps->pps.ref_field_flags |=
-			(!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD)) << i;
-		hw_ps->pps.ref_colmv_use_flag |=
-			(!!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) << i;
-		hw_ps->pps.ref_topfield_used |=
-			(!!(dpb[i].fields & V4L2_H264_TOP_FIELD_REF)) << i;
-		hw_ps->pps.ref_botfield_used |=
-			(!!(dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)) << i;
-	}
-
-	hw_ps->pps.pic_field_flag =
-		!!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC);
-	hw_ps->pps.pic_associated_flag =
-		!!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD);
-
-	hw_ps->pps.cur_top_field = dec_params->top_field_order_cnt;
-	hw_ps->pps.cur_bot_field = dec_params->bottom_field_order_cnt;
 }
 
 static void rkvdec_write_regs(struct rkvdec_ctx *ctx)
-- 
cgit v1.2.3


From c03b7dec3c4ddc97872fa12bfca75bae9cb46510 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 2 Feb 2026 10:47:51 +0100
Subject: media: rkvdec: reduce stack usage in rkvdec_init_v4l2_vp9_count_tbl()

The deeply nested loop in rkvdec_init_v4l2_vp9_count_tbl() needs a lot
of registers, so when the clang register allocator runs out, it ends up
spilling countless temporaries to the stack:

drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c:966:12: error: stack frame size (1472) exceeds limit (1280) in 'rkvdec_vp9_start' [-Werror,-Wframe-larger-than]

Marking this function as noinline_for_stack keeps it out of
rkvdec_vp9_start(), giving the compiler more room for optimization.

The resulting code is good enough that both the total stack usage
and the loop get enough better to stay under the warning limit,
though it's still slow, and would need a larger rework if this
function ends up being called in a fast path.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c b/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c
index e4cdd2122873..2751f5396ee8 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec-vp9.c
@@ -893,7 +893,8 @@ out_update_last:
 	update_ctx_last_info(vp9_ctx);
 }
 
-static void rkvdec_init_v4l2_vp9_count_tbl(struct rkvdec_ctx *ctx)
+static noinline_for_stack void
+rkvdec_init_v4l2_vp9_count_tbl(struct rkvdec_ctx *ctx)
 {
 	struct rkvdec_vp9_ctx *vp9_ctx = ctx->priv;
 	struct rkvdec_vp9_intra_frame_symbol_counts *intra_cnts = vp9_ctx->count_tbl.cpu;
-- 
cgit v1.2.3


From bf504b229cb8d534eccbaeaa23eba34c05131e25 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 17 Mar 2026 21:39:05 +0100
Subject: ACPI: processor: Fix previous acpi_processor_errata_piix4() fix

After commi f132e089fe89 ("ACPI: processor: Fix NULL-pointer dereference
in acpi_processor_errata_piix4()"), device pointers may be dereferenced
after dropping references to the device objects pointed to by them,
which may cause a use-after-free to occur.

Moreover, debug messages about enabling the errata may be printed
if the errata flags corresponding to them are unset.

Address all of these issues by moving message printing to the points
in the code where the errata flags are set.

Fixes: f132e089fe89 ("ACPI: processor: Fix NULL-pointer dereference in acpi_processor_errata_piix4()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/linux-acpi/938e2206-def5-4b7a-9b2c-d1fd37681d8a@roeck-us.net/
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://patch.msgid.link/5975693.DvuYhMxLoT@rafael.j.wysocki
---
 drivers/acpi/acpi_processor.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index b34a48068a8d..b1652cab631a 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -113,6 +113,10 @@ static int acpi_processor_errata_piix4(struct pci_dev *dev)
 				     PCI_ANY_ID, PCI_ANY_ID, NULL);
 		if (ide_dev) {
 			errata.piix4.bmisx = pci_resource_start(ide_dev, 4);
+			if (errata.piix4.bmisx)
+				dev_dbg(&ide_dev->dev,
+					"Bus master activity detection (BM-IDE) erratum enabled\n");
+
 			pci_dev_put(ide_dev);
 		}
 
@@ -131,20 +135,17 @@ static int acpi_processor_errata_piix4(struct pci_dev *dev)
 		if (isa_dev) {
 			pci_read_config_byte(isa_dev, 0x76, &value1);
 			pci_read_config_byte(isa_dev, 0x77, &value2);
-			if ((value1 & 0x80) || (value2 & 0x80))
+			if ((value1 & 0x80) || (value2 & 0x80)) {
 				errata.piix4.fdma = 1;
+				dev_dbg(&isa_dev->dev,
+					"Type-F DMA livelock erratum (C3 disabled)\n");
+			}
 			pci_dev_put(isa_dev);
 		}
 
 		break;
 	}
 
-	if (ide_dev)
-		dev_dbg(&ide_dev->dev, "Bus master activity detection (BM-IDE) erratum enabled\n");
-
-	if (isa_dev)
-		dev_dbg(&isa_dev->dev, "Type-F DMA livelock erratum (C3 disabled)\n");
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From e7648ffecb7fcb7400e123bb6ea989633a104fc3 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Tue, 17 Mar 2026 23:47:57 -0400
Subject: ACPI: bus: Fix MFD child automatic modprobe issue

MFD child devices sharing parent's ACPI Companion fails to probe as
acpi_companion_match() returns incompatible ACPI Companion handle for
binding with the check for pnp.type.backlight added recently. Remove this
pnp.type.backlight check in acpi_companion_match() to fix the automatic
modprobe issue.

Fixes: 7a7a7ed5f8bdb ("ACPI: scan: Register platform devices for backlight device objects")
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Link: https://patch.msgid.link/20260318034842.1216536-1-pratap.nirujogi@amd.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index f6707325f582..2ec095e2009e 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -818,9 +818,6 @@ const struct acpi_device *acpi_companion_match(const struct device *dev)
 	if (list_empty(&adev->pnp.ids))
 		return NULL;
 
-	if (adev->pnp.type.backlight)
-		return adev;
-
 	return acpi_primary_dev_companion(adev, dev);
 }
 
-- 
cgit v1.2.3


From b8bee48e38f2ddbdba5e58bc54ef54bb7d8d341b Mon Sep 17 00:00:00 2001
From: Frank Zhang <rmxpzlb@gmail.com>
Date: Tue, 17 Mar 2026 18:25:27 +0800
Subject: ALSA:usb:qcom: add AUXILIARY_BUS to Kconfig dependencies

The build can fail with:

ERROR: modpost: "__auxiliary_driver_register"
[sound/usb/qcom/snd-usb-audio-qmi.ko] undefined!
ERROR: modpost: "auxiliary_driver_unregister"
[sound/usb/qcom/snd-usb-audio-qmi.ko] undefined!

Select AUXILIARY_BUS when SND_USB_AUDIO_QMI is enabled.

Signed-off-by: Frank Zhang <rmxpzlb@gmail.com>
Link: https://patch.msgid.link/20260317102527.556248-1-rmxpzlb@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index 9b890abd96d3..b4588915efa1 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -192,6 +192,7 @@ config SND_USB_AUDIO_QMI
 	tristate "Qualcomm Audio Offload driver"
 	depends on QCOM_QMI_HELPERS && SND_USB_AUDIO && SND_SOC_USB
 	depends on USB_XHCI_HCD && USB_XHCI_SIDEBAND
+	select AUXILIARY_BUS
 	help
 	  Say Y here to enable the Qualcomm USB audio offloading feature.
 
-- 
cgit v1.2.3


From 8306a78a1c04cf87bfa9ae6451cc9d8f0f9dc0e0 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@oss.qualcomm.com>
Date: Tue, 17 Mar 2026 19:09:38 +0100
Subject: ALSA: usb-audio: qcom: Fix the license marking

The Copyright for Qualcomm changed its format and replaces the old
Qualcomm Innovative Center by Qualcomm Technology Inc.

Signed-off-by: Daniel Lezcano <daniel.lezcano@oss.qualcomm.com>
Link: https://patch.msgid.link/20260317180943.3062085-1-daniel.lezcano@oss.qualcomm.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/qcom/qc_audio_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 510b68cced33..f161eb29f911 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/auxiliary_bus.h>
-- 
cgit v1.2.3


From e8d97c270cb46a2a88739019d0f8547adc7d97da Mon Sep 17 00:00:00 2001
From: Ming Qian <ming.qian@oss.nxp.com>
Date: Fri, 6 Mar 2026 11:10:57 +0800
Subject: media: verisilicon: Fix kernel panic due to __initconst misuse

Fix a kernel panic when probing the driver as a module:

  Unable to handle kernel paging request at virtual address
  ffffd9c18eb05000
  of_find_matching_node_and_match+0x5c/0x1a0
  hantro_probe+0x2f4/0x7d0 [hantro_vpu]

The imx8mq_vpu_shared_resources array is referenced by variant
structures through their shared_devices field. When built as a
module, __initconst causes this data to be freed after module
init, but it's later accessed during probe, causing a page fault.

The imx8mq_vpu_shared_resources is referenced from non-init code,
so keeping __initconst or __initconst_or_module here is wrong.

Drop the __initconst annotation and let it live in the normal .rodata
section.

A bug of __initconst called from regular non-init probe code
leading to bugs during probe deferrals or during unbind-bind cycles.

Reported-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Closes: https://lore.kernel.org/all/68ef934f-baa0-4bf6-93d8-834bbc441e66@kernel.org/
Reported-by: Franz Schnyder <franz.schnyder@toradex.com>
Closes: https://lore.kernel.org/all/n3qmcb62tepxltoskpf7ws6yiirc2so62ia23b42rj3wlmpl67@rvkbuirx7kkp/
Fixes: e0203ddf9af7 ("media: verisilicon: Avoid G2 bus error while decoding H.264 and HEVC")
Suggested-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Suggested-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Ming Qian <ming.qian@oss.nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Cc: stable@kernel.org
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/platform/verisilicon/imx8m_vpu_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
index 6f8e43b7f157..fa4224de4b99 100644
--- a/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
+++ b/drivers/media/platform/verisilicon/imx8m_vpu_hw.c
@@ -343,7 +343,7 @@ const struct hantro_variant imx8mq_vpu_variant = {
 	.num_regs = ARRAY_SIZE(imx8mq_reg_names)
 };
 
-static const struct of_device_id imx8mq_vpu_shared_resources[] __initconst = {
+static const struct of_device_id imx8mq_vpu_shared_resources[] = {
 	{ .compatible = "nxp,imx8mq-vpu-g1", },
 	{ .compatible = "nxp,imx8mq-vpu-g2", },
 	{ /* sentinel */ }
-- 
cgit v1.2.3


From 0e9fc79132ce7ea1e48c388b864382aa38eb0ed4 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 18 Mar 2026 18:28:49 +0800
Subject: ASoC: simple-card-utils: Check value of is_playback_only and
 is_capture_only

The audio-graph-card2 gets the value of 'playback-only' and
'capture_only' property in below sequence, if there is 'playback_only' or
'capture_only' property in port_cpu and port_codec nodes, but no these
properties in ep_cpu and ep_codec nodes, the value of playback_only and
capture_only will be flushed to zero in the end.

graph_util_parse_link_direction(lnk,            &playback_only, &capture_only);
graph_util_parse_link_direction(ports_cpu,      &playback_only, &capture_only);
graph_util_parse_link_direction(ports_codec,    &playback_only, &capture_only);
graph_util_parse_link_direction(port_cpu,       &playback_only, &capture_only);
graph_util_parse_link_direction(port_codec,     &playback_only, &capture_only);
graph_util_parse_link_direction(ep_cpu,         &playback_only, &capture_only);
graph_util_parse_link_direction(ep_codec,       &playback_only, &capture_only);

So check the value of is_playback_only and is_capture_only in
graph_util_parse_link_direction() function, if they are true, then rewrite
the values, and no need to check the np variable as
of_property_read_bool() will ignore if it was NULL.

Fixes: 3cc393d2232e ("ASoC: simple-card-utils: Fix pointer check in graph_util_parse_link_direction")
Fixes: 22a507d7680f ("ASoC: simple-card-utils: Check device node before overwrite direction")
Suggested-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://patch.msgid.link/20260318102850.2794029-2-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-card-utils.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 9e5be0eaa77f..89d694c2cbdd 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1183,9 +1183,9 @@ void graph_util_parse_link_direction(struct device_node *np,
 	bool is_playback_only = of_property_read_bool(np, "playback-only");
 	bool is_capture_only  = of_property_read_bool(np, "capture-only");
 
-	if (np && playback_only)
+	if (playback_only && is_playback_only)
 		*playback_only = is_playback_only;
-	if (np && capture_only)
+	if (capture_only && is_capture_only)
 		*capture_only = is_capture_only;
 }
 EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);
-- 
cgit v1.2.3


From ca67bd564e94aaa898a2cbb90922ca3cccd0612b Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 18 Mar 2026 18:28:50 +0800
Subject: ASoC: fsl: imx-card: initialize playback_only and capture_only

Fix uninitialized variable playback_only and capture_only because
graph_util_parse_link_direction() may not write them.

Fixes: 1877c3e7937f ("ASoC: imx-card: Add playback_only or capture_only support")
Suggested-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://patch.msgid.link/20260318102850.2794029-3-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/imx-card.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/fsl/imx-card.c b/sound/soc/fsl/imx-card.c
index 05b4e971a366..a4518fefad69 100644
--- a/sound/soc/fsl/imx-card.c
+++ b/sound/soc/fsl/imx-card.c
@@ -710,6 +710,8 @@ static int imx_card_parse_of(struct imx_card_data *data)
 			link->ops = &imx_aif_ops;
 		}
 
+		playback_only = false;
+		capture_only  = false;
 		graph_util_parse_link_direction(np, &playback_only, &capture_only);
 		link->playback_only = playback_only;
 		link->capture_only = capture_only;
-- 
cgit v1.2.3


From 85d98669fa7f1d3041d962515e45ee6e392db6f8 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@oss.qualcomm.com>
Date: Mon, 2 Mar 2026 15:26:03 +0100
Subject: arm64: dts: qcom: monaco: Reserve full Gunyah metadata region
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We observe spurious "Synchronous External Abort" exceptions
(ESR=0x96000010) and kernel crashes on Monaco-based platforms.
These faults are caused by the kernel inadvertently accessing
hypervisor-owned memory that is not properly marked as reserved.

>From boot log, The Qualcomm hypervisor reports the memory range
at 0x91a80000 of size 0x80000 (512 KiB) as hypervisor-owned:
qhee_hyp_assign_remove_memory: 0x91a80000/0x80000 -> ret 0

However, the EFI memory map provided by firmware only reserves the
subrange 0x91a40000–0x91a87fff (288 KiB). The remaining portion
(0x91a88000–0x91afffff) is incorrectly reported as conventional
memory (from efi debug):
efi:   0x000091a40000-0x000091a87fff [Reserved...]
efi:   0x000091a88000-0x0000938fffff [Conventional...]

As a result, the allocator may hand out PFNs inside the hypervisor
owned region, causing fatal aborts when the kernel accesses those
addresses.

Add a reserved-memory carveout for the Gunyah hypervisor metadata
at 0x91a80000 (512 KiB) and mark it as no-map so Linux does not
map or allocate from this area.

For the record:
Hyp version: gunyah-e78adb36e debug (2025-11-17 05:38:05 UTC)
UEFI Ver: 6.0.260122.BOOT.MXF.1.0.c1-00449-KODIAKLA-1

Fixes: 7be190e4bdd2 ("arm64: dts: qcom: add QCS8300 platform")
Signed-off-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260302142603.1113355-1-loic.poulain@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/monaco.dtsi | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/boot/dts/qcom/monaco.dtsi b/arch/arm64/boot/dts/qcom/monaco.dtsi
index dbb2273b0ee8..0cb9fd154b68 100644
--- a/arch/arm64/boot/dts/qcom/monaco.dtsi
+++ b/arch/arm64/boot/dts/qcom/monaco.dtsi
@@ -765,6 +765,11 @@
 			hwlocks = <&tcsr_mutex 3>;
 		};
 
+		gunyah_md_mem: gunyah-md-region@91a80000 {
+			reg = <0x0 0x91a80000 0x0 0x80000>;
+			no-map;
+		};
+
 		lpass_machine_learning_mem: lpass-machine-learning-region@93b00000 {
 			reg = <0x0 0x93b00000 0x0 0xf00000>;
 			no-map;
-- 
cgit v1.2.3


From e1eabb072c75681f78312c484ccfffb7430f206e Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Wed, 11 Mar 2026 17:12:15 +0800
Subject: usb: gadget: u_ether: Fix race between gether_disconnect and eth_stop

A race condition between gether_disconnect() and eth_stop() leads to a
NULL pointer dereference. Specifically, if eth_stop() is triggered
concurrently while gether_disconnect() is tearing down the endpoints,
eth_stop() attempts to access the cleared endpoint descriptor, causing
the following NPE:

  Unable to handle kernel NULL pointer dereference
  Call trace:
   __dwc3_gadget_ep_enable+0x60/0x788
   dwc3_gadget_ep_enable+0x70/0xe4
   usb_ep_enable+0x60/0x15c
   eth_stop+0xb8/0x108

Because eth_stop() crashes while holding the dev->lock, the thread
running gether_disconnect() fails to acquire the same lock and spins
forever, resulting in a hardlockup:

  Core - Debugging Information for Hardlockup core(7)
  Call trace:
   queued_spin_lock_slowpath+0x94/0x488
   _raw_spin_lock+0x64/0x6c
   gether_disconnect+0x19c/0x1e8
   ncm_set_alt+0x68/0x1a0
   composite_setup+0x6a0/0xc50

The root cause is that the clearing of dev->port_usb in
gether_disconnect() is delayed until the end of the function.

Move the clearing of dev->port_usb to the very beginning of
gether_disconnect() while holding dev->lock. This cuts off the link
immediately, ensuring eth_stop() will see dev->port_usb as NULL and
safely bail out.

Fixes: 2b3d942c4878 ("usb ethernet gadget: split out network core")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260311-gether-disconnect-npe-v1-1-454966adf7c7@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 1a9e7c495e2e..23c7c0cdf202 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1223,6 +1223,11 @@ void gether_disconnect(struct gether *link)
 
 	DBG(dev, "%s\n", __func__);
 
+	spin_lock(&dev->lock);
+	dev->port_usb = NULL;
+	link->is_suspend = false;
+	spin_unlock(&dev->lock);
+
 	netif_stop_queue(dev->net);
 	netif_carrier_off(dev->net);
 
@@ -1260,11 +1265,6 @@ void gether_disconnect(struct gether *link)
 	dev->header_len = 0;
 	dev->unwrap = NULL;
 	dev->wrap = NULL;
-
-	spin_lock(&dev->lock);
-	dev->port_usb = NULL;
-	link->is_suspend = false;
-	spin_unlock(&dev->lock);
 }
 EXPORT_SYMBOL_GPL(gether_disconnect);
 
-- 
cgit v1.2.3


From 8a768552f7a8276fb9e01d49773d2094ace7c8f1 Mon Sep 17 00:00:00 2001
From: Heitor Alves de Siqueira <halves@igalia.com>
Date: Thu, 12 Mar 2026 09:27:28 -0300
Subject: usb: usbtmc: Flush anchored URBs in usbtmc_release

When calling usbtmc_release, pending anchored URBs must be flushed or
killed to prevent use-after-free errors (e.g. in the HCD giveback
path). Call usbtmc_draw_down() to allow anchored URBs to be completed.

Fixes: 4f3c8d6eddc2 ("usb: usbtmc: Support Read Status Byte with SRQ per file")
Reported-by: syzbot+9a3c54f52bd1edbd975f@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=9a3c54f52bd1edbd975f
Cc: stable <stable@kernel.org>
Signed-off-by: Heitor Alves de Siqueira <halves@igalia.com>
Link: https://patch.msgid.link/20260312-usbtmc-flush-release-v1-1-5755e9f4336f@igalia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/usbtmc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index d39bbfd7fd18..bd9347804dec 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -254,6 +254,9 @@ static int usbtmc_release(struct inode *inode, struct file *file)
 	list_del(&file_data->file_elem);
 
 	spin_unlock_irq(&file_data->data->dev_lock);
+
+	/* flush anchored URBs */
+	usbtmc_draw_down(file_data);
 	mutex_unlock(&file_data->data->io_mutex);
 
 	kref_put(&file_data->data->kref, usbtmc_delete);
-- 
cgit v1.2.3


From d2d8c17ac01a1b1f638ea5d340a884ccc5015186 Mon Sep 17 00:00:00 2001
From: Nathan Rebello <nathan.c.rebello@gmail.com>
Date: Fri, 13 Mar 2026 18:24:53 -0400
Subject: usb: typec: ucsi: validate connector number in ucsi_notify_common()

The connector number extracted from CCI via UCSI_CCI_CONNECTOR() is a
7-bit field (0-127) that is used to index into the connector array in
ucsi_connector_change(). However, the array is only allocated for the
number of connectors reported by the device (typically 2-4 entries).

A malicious or malfunctioning device could report an out-of-range
connector number in the CCI, causing an out-of-bounds array access in
ucsi_connector_change().

Add a bounds check in ucsi_notify_common(), the central point where CCI
is parsed after arriving from hardware, so that bogus connector numbers
are rejected before they propagate further.

Fixes: bdc62f2bae8f ("usb: typec: ucsi: Simplified registration and I/O API")
Cc: stable <stable@kernel.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Nathan Rebello <nathan.c.rebello@gmail.com>
Link: https://patch.msgid.link/20260313222453.123-1-nathan.c.rebello@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index f38a4d7ebc42..8333bdaf5566 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -43,8 +43,13 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci)
 	if (cci & UCSI_CCI_BUSY)
 		return;
 
-	if (UCSI_CCI_CONNECTOR(cci))
-		ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci));
+	if (UCSI_CCI_CONNECTOR(cci)) {
+		if (UCSI_CCI_CONNECTOR(cci) <= ucsi->cap.num_connectors)
+			ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci));
+		else
+			dev_err(ucsi->dev, "bogus connector number in CCI: %lu\n",
+				UCSI_CCI_CONNECTOR(cci));
+	}
 
 	if (cci & UCSI_CCI_ACK_COMPLETE &&
 	    test_and_clear_bit(ACK_PENDING, &ucsi->flags))
-- 
cgit v1.2.3


From 616a63ff495df12863692ab3f9f7b84e3fa7a66d Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Sun, 15 Mar 2026 14:30:43 -0400
Subject: USB: dummy-hcd: Fix locking/synchronization error

Syzbot testing was able to provoke an addressing exception and crash
in the usb_gadget_udc_reset() routine in
drivers/usb/gadgets/udc/core.c, resulting from the fact that the
routine was called with a second ("driver") argument of NULL.  The bad
caller was set_link_state() in dummy_hcd.c, and the problem arose
because of a race between a USB reset and driver unbind.

These sorts of races were not supposed to be possible; commit
7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change"),
along with a few followup commits, was written specifically to prevent
them.  As it turns out, there are (at least) two errors remaining in
the code.  Another patch will address the second error; this one is
concerned with the first.

The error responsible for the syzbot crash occurred because the
stop_activity() routine will sometimes drop and then re-acquire the
dum->lock spinlock.  A call to stop_activity() occurs in
set_link_state() when handling an emulated USB reset, after the test
of dum->ints_enabled and before the increment of dum->callback_usage.
This allowed another thread (doing a driver unbind) to sneak in and
grab the spinlock, and then clear dum->ints_enabled and dum->driver.
Normally this other thread would have to wait for dum->callback_usage
to go down to 0 before it would clear dum->driver, but in this case it
didn't have to wait since dum->callback_usage had not yet been
incremented.

The fix is to increment dum->callback_usage _before_ calling
stop_activity() instead of after.  Then the thread doing the unbind
will not clear dum->driver until after the call to
usb_gadget_udc_reset() safely returns and dum->callback_usage has been
decremented again.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-by: syzbot+19bed92c97bee999e5db@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-usb/68fc7c9c.050a0220.346f24.023c.GAE@google.com/
Tested-by: syzbot+19bed92c97bee999e5db@syzkaller.appspotmail.com
Fixes: 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous synchronization change")
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/46135f42-fdbe-46b5-aac0-6ca70492af15@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index c9eca90376e2..860ee7d3ef98 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -462,8 +462,13 @@ static void set_link_state(struct dummy_hcd *dum_hcd)
 
 		/* Report reset and disconnect events to the driver */
 		if (dum->ints_enabled && (disconnect || reset)) {
-			stop_activity(dum);
 			++dum->callback_usage;
+			/*
+			 * stop_activity() can drop dum->lock, so it must
+			 * not come between the dum->ints_enabled test
+			 * and the ++dum->callback_usage.
+			 */
+			stop_activity(dum);
 			spin_unlock(&dum->lock);
 			if (reset)
 				usb_gadget_udc_reset(&dum->gadget, dum->driver);
-- 
cgit v1.2.3


From 2ca9e46f8f1f5a297eb0ac83f79d35d5b3a02541 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Sun, 15 Mar 2026 14:31:00 -0400
Subject: USB: dummy-hcd: Fix interrupt synchronization error

This fixes an error in synchronization in the dummy-hcd driver.  The
error has a somewhat involved history.  The synchronization mechanism
was introduced by commit 7dbd8f4cabd9 ("USB: dummy-hcd: Fix erroneous
synchronization change"), which added an emulated "interrupts enabled"
flag together with code emulating synchronize_irq() (it waits until
all current handler callbacks have returned).

But the emulated interrupt-disable occurred too late, after the driver
containing the handler callback routines had been told that it was
unbound and no more callbacks would occur.  Commit 4a5d797a9f9c ("usb:
gadget: dummy_hcd: fix gpf in gadget_setup") tried to fix this by
moving the synchronize_irq() emulation code from dummy_stop() to
dummy_pullup(), which runs before the unbind callback.

There still were races, though, because the emulated interrupt-disable
still occurred too late.  It couldn't be moved to dummy_pullup(),
because that routine can be called for reasons other than an impending
unbind.  Therefore commits 7dc0c55e9f30 ("USB: UDC core: Add
udc_async_callbacks gadget op") and 04145a03db9d ("USB: UDC: Implement
udc_async_callbacks in dummy-hcd") added an API allowing the UDC core
to tell dummy-hcd exactly when emulated interrupts and their callbacks
should be disabled.

That brings us to the current state of things, which is still wrong
because the emulated synchronize_irq() occurs before the emulated
interrupt-disable!  That's no good, beause it means that more emulated
interrupts can occur after the synchronize_irq() emulation has run,
leading to the possibility that a callback handler may be running when
the gadget driver is unbound.

To fix this, we have to move the synchronize_irq() emulation code yet
again, to the dummy_udc_async_callbacks() routine, which takes care of
enabling and disabling emulated interrupt requests.  The
synchronization will now run immediately after emulated interrupts are
disabled, which is where it belongs.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Fixes: 04145a03db9d ("USB: UDC: Implement udc_async_callbacks in dummy-hcd")
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/c7bc93fe-4241-4d04-bd56-27c12ba35c97@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 860ee7d3ef98..e55701575857 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -913,21 +913,6 @@ static int dummy_pullup(struct usb_gadget *_gadget, int value)
 	spin_lock_irqsave(&dum->lock, flags);
 	dum->pullup = (value != 0);
 	set_link_state(dum_hcd);
-	if (value == 0) {
-		/*
-		 * Emulate synchronize_irq(): wait for callbacks to finish.
-		 * This seems to be the best place to emulate the call to
-		 * synchronize_irq() that's in usb_gadget_remove_driver().
-		 * Doing it in dummy_udc_stop() would be too late since it
-		 * is called after the unbind callback and unbind shouldn't
-		 * be invoked until all the other callbacks are finished.
-		 */
-		while (dum->callback_usage > 0) {
-			spin_unlock_irqrestore(&dum->lock, flags);
-			usleep_range(1000, 2000);
-			spin_lock_irqsave(&dum->lock, flags);
-		}
-	}
 	spin_unlock_irqrestore(&dum->lock, flags);
 
 	usb_hcd_poll_rh_status(dummy_hcd_to_hcd(dum_hcd));
@@ -950,6 +935,20 @@ static void dummy_udc_async_callbacks(struct usb_gadget *_gadget, bool enable)
 
 	spin_lock_irq(&dum->lock);
 	dum->ints_enabled = enable;
+	if (!enable) {
+		/*
+		 * Emulate synchronize_irq(): wait for callbacks to finish.
+		 * This has to happen after emulated interrupts are disabled
+		 * (dum->ints_enabled is clear) and before the unbind callback,
+		 * just like the call to synchronize_irq() in
+		 * gadget/udc/core:gadget_unbind_driver().
+		 */
+		while (dum->callback_usage > 0) {
+			spin_unlock_irq(&dum->lock);
+			usleep_range(1000, 2000);
+			spin_lock_irq(&dum->lock);
+		}
+	}
 	spin_unlock_irq(&dum->lock);
 }
 
-- 
cgit v1.2.3


From e002e92e88e12457373ed096b18716d97e7bbb20 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Mon, 16 Mar 2026 15:49:09 +0800
Subject: usb: gadget: u_ether: Fix NULL pointer deref in eth_get_drvinfo

Commit ec35c1969650 ("usb: gadget: f_ncm: Fix net_device lifecycle with
device_move") reparents the gadget device to /sys/devices/virtual during
unbind, clearing the gadget pointer. If the userspace tool queries on
the surviving interface during this detached window, this leads to a
NULL pointer dereference.

Unable to handle kernel NULL pointer dereference
Call trace:
 eth_get_drvinfo+0x50/0x90
 ethtool_get_drvinfo+0x5c/0x1f0
 __dev_ethtool+0xaec/0x1fe0
 dev_ethtool+0x134/0x2e0
 dev_ioctl+0x338/0x560

Add a NULL check for dev->gadget in eth_get_drvinfo(). When detached,
skip copying the fw_version and bus_info strings, which is natively
handled by ethtool_get_drvinfo for empty strings.

Suggested-by: Val Packett <val@packett.cool>
Reported-by: Val Packett <val@packett.cool>
Closes: https://lore.kernel.org/linux-usb/10890524-cf83-4a71-b879-93e2b2cc1fcc@packett.cool/
Fixes: ec35c1969650 ("usb: gadget: f_ncm: Fix net_device lifecycle with device_move")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260316-eth-null-deref-v1-1-07005f33be85@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 23c7c0cdf202..59d85d6a84a8 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -113,8 +113,10 @@ static void eth_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *p)
 
 	strscpy(p->driver, "g_ether", sizeof(p->driver));
 	strscpy(p->version, UETH__VERSION, sizeof(p->version));
-	strscpy(p->fw_version, dev->gadget->name, sizeof(p->fw_version));
-	strscpy(p->bus_info, dev_name(&dev->gadget->dev), sizeof(p->bus_info));
+	if (dev->gadget) {
+		strscpy(p->fw_version, dev->gadget->name, sizeof(p->fw_version));
+		strscpy(p->bus_info, dev_name(&dev->gadget->dev), sizeof(p->bus_info));
+	}
 }
 
 /* REVISIT can also support:
-- 
cgit v1.2.3


From b2f6648c735639d246dc5f98f377b69d5374c2bd Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 16 Mar 2026 17:48:11 +0800
Subject: usb: hcd: queue wakeup_work to system_freezable_wq workqueue

After commit 4fb352df14de ("PM: sleep: Do not flag runtime PM workqueue
as freezable"), pm_wq workqueue will be unfreezable during system pm. This
brings issue as below:

[  344.255749] ------------[ cut here ]------------
[  344.277740] URB 000000004aae4ad1 submitted while active
[  344.282996] WARNING: drivers/usb/core/urb.c:379 at usb_submit_urb+0x5a4/0x5e0, CPU#2: kworker/u16:14/964
[  344.292477] Modules linked in:
[  344.295532] CPU: 2 UID: 0 PID: 964 Comm: kworker/u16:14 Not tainted 7.0.0-rc2-next-20260303-00006-gf03fe0b53b39-dirty #100 PREEMPT
[  344.307341] Hardware name: NXP i.MX943 EVK board (DT)
[  344.312386] Workqueue: async async_run_entry_fn
[  344.316919] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[  344.323862] pc : usb_submit_urb+0x5a4/0x5e0
[  344.328046] lr : usb_submit_urb+0x5a4/0x5e0
[  344.332217] sp : ffff800083283b30
[  344.335528] x29: ffff800083283b30 x28: ffff000082631000 x27: 0000000000000000
[  344.342661] x26: 0000000000000003 x25: 0000000000000c00 x24: 0000000000000000
[  344.349793] x23: 0000000000000004 x22: 0000000000000010 x21: 0000000000000000
[  344.356917] x20: 0000000000000002 x19: ffff00008253ce40 x18: ffff000089e4eec0
[  344.364050] x17: 000000040044ffff x16: 000005d9d87f6289 x15: 0000000000000000
[  344.371174] x14: ffff000089e4eec0 x13: 6576697463612065 x12: 6c69687720646574
[  344.378298] x11: 0000000000000058 x10: 0000000000000001 x9 : 0000000000000001
[  344.385431] x8 : 0000000000000000 x7 : 0000005028dd0800 x6 : 0000000000000002
[  344.392563] x5 : ffffc48f74e9daf8 x4 : 0000000000000000 x3 : 0000000000000000
[  344.399696] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff000089e4ee40
[  344.406835] Call trace:
[  344.409280]  usb_submit_urb+0x5a4/0x5e0 (P)
[  344.413456]  hub_activate+0x268/0x878
[  344.417116]  hub_resume+0x5c/0x10c
[  344.420522]  usb_resume_interface.isra.0+0xa8/0x110
[  344.425393]  usb_resume_both+0x10c/0x1e0
[  344.429310]  usb_resume+0x1c/0x70
[  344.432621]  usb_dev_resume+0x14/0x20
[  344.436278]  dpm_run_callback.isra.0+0x38/0xf8
[  344.440715]  device_resume+0xec/0x1e8
[  344.444373]  async_resume+0x20/0x38
[  344.447848]  async_run_entry_fn+0x34/0xe0
[  344.451852]  process_one_work+0x150/0x290
[  344.455856]  worker_thread+0x18c/0x300
[  344.459600]  kthread+0x118/0x124
[  344.462824]  ret_from_fork+0x10/0x20

The reason is if the host controller resume routine xhci_resume() call
usb_hcd_resume_root_hub(), wakeup_work will be queued and run immediately.
Then usb_autoresume_device() will be called and usb device will exit
runtime suspended state (if it was suspended before). For a hub device,
hub_resume()/hub_reset_resume() will be called accordingly.

After the host controller device system resume is finished, the root hub
usb device "usb1" will do system resume too. Then hub_resume() will be
called again.

Above sequence will cause hub->urb to be submitted twice. To avoid this
issue, restore the previous behavior by queuing wakeup_work to
system_freezable_wq workqueue.

Acked-by: Alan Stern <stern@rowland.harvard.edu>
Fixes: 4fb352df14de ("PM: sleep: Do not flag runtime PM workqueue as freezable")
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://patch.msgid.link/20260316094811.1559471-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index dee842ea6931..89221f1ce769 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2403,7 +2403,7 @@ void usb_hcd_resume_root_hub (struct usb_hcd *hcd)
 	if (hcd->rh_registered) {
 		pm_wakeup_event(&hcd->self.root_hub->dev, 0);
 		set_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags);
-		queue_work(pm_wq, &hcd->wakeup_work);
+		queue_work(system_freezable_wq, &hcd->wakeup_work);
 	}
 	spin_unlock_irqrestore (&hcd_root_hub_lock, flags);
 }
-- 
cgit v1.2.3


From f97e96c303d689708f7f713d8f3afcc31f1237e9 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Tue, 17 Mar 2026 09:41:10 +0100
Subject: cdc-acm: new quirk for EPSON HMD

This device has a union descriptor that is just garbage
and needs a custom descriptor.
In principle this could be done with a (conditionally
activated) heuristic. That would match more devices
without a need for defining a new quirk. However,
this always carries the risk that the heuristics
does the wrong thing and leads to more breakage.
Defining the quirk and telling it exactly what to do
is the safe and conservative approach.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260317084139.1461008-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/cdc-acm.c | 9 +++++++++
 drivers/usb/class/cdc-acm.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 7ede29d4c7c1..cf3c3eede1a5 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1225,6 +1225,12 @@ static int acm_probe(struct usb_interface *intf,
 		if (!data_interface || !control_interface)
 			return -ENODEV;
 		goto skip_normal_probe;
+	} else if (quirks == NO_UNION_12) {
+		data_interface = usb_ifnum_to_if(usb_dev, 2);
+		control_interface = usb_ifnum_to_if(usb_dev, 1);
+		if (!data_interface || !control_interface)
+			 return -ENODEV;
+		goto skip_normal_probe;
 	}
 
 	/* normal probing*/
@@ -1748,6 +1754,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x045b, 0x024D),	/* Renesas R-Car E3 USB Download mode */
 	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
 	},
+	{ USB_DEVICE(0x04b8, 0x0d12),	/* EPSON HMD Com&Sens */
+	.driver_info = NO_UNION_12,	/* union descriptor is garbage */
+	},
 	{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 76f73853a60b..25fd5329a878 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -114,3 +114,4 @@ struct acm {
 #define SEND_ZERO_PACKET		BIT(6)
 #define DISABLE_ECHO			BIT(7)
 #define MISSING_CAP_BRK			BIT(8)
+#define NO_UNION_12			BIT(9)
-- 
cgit v1.2.3


From 1a122198ee26d2f328edae802b2ca4fa0518a20a Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 16 Mar 2026 23:30:06 +0800
Subject: dwc3: google: Fix PM domain leak in dwc3_google_probe()

When syscon_regmap_lookup_by_phandle_args() fails, the function was
returning directly without cleaning up the power domain initialized
earlier by dwc3_google_pm_domain_init().

Fix by jumping to err_deinit_pdom to properly clean up resources.

Fixes: 8995a37371bf4 ("usb: dwc3: Add Google Tensor SoC DWC3 glue driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260316-dwc3-google-v1-1-c9bde1b02f62@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-google.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/dwc3/dwc3-google.c b/drivers/usb/dwc3/dwc3-google.c
index 2105c72af753..4ca567ec01d0 100644
--- a/drivers/usb/dwc3/dwc3-google.c
+++ b/drivers/usb/dwc3/dwc3-google.c
@@ -385,8 +385,9 @@ static int dwc3_google_probe(struct platform_device *pdev)
 						     "google,usb-cfg-csr",
 						     ARRAY_SIZE(args), args);
 	if (IS_ERR(google->usb_cfg_regmap)) {
-		return dev_err_probe(dev, PTR_ERR(google->usb_cfg_regmap),
-				     "invalid usb cfg csr\n");
+		ret = dev_err_probe(dev, PTR_ERR(google->usb_cfg_regmap),
+				    "invalid usb cfg csr\n");
+		goto err_deinit_pdom;
 	}
 
 	google->host_cfg_offset = args[0];
-- 
cgit v1.2.3


From f50200dd44125e445a6164e88c217472fa79cdbc Mon Sep 17 00:00:00 2001
From: Sebastian Urban <surban@surban.net>
Date: Sun, 15 Mar 2026 16:10:45 +0100
Subject: usb: gadget: dummy_hcd: fix premature URB completion when ZLP follows
 partial transfer

When a gadget request is only partially transferred in transfer()
because the per-frame bandwidth budget is exhausted, the loop advances
to the next queued request. If that next request is a zero-length
packet (ZLP), len evaluates to zero and the code takes the
unlikely(len == 0) path, which sets is_short = 1. This bypasses the
bandwidth guard ("limit < ep->ep.maxpacket && limit < len") that
lives in the else branch and would otherwise break out of the loop for
non-zero requests. The is_short path then completes the URB before all
data from the first request has been transferred.

Reproducer (bulk IN, high speed):

  Device side (FunctionFS with Linux AIO):
    1. Queue a 65024-byte write via io_submit (127 * 512, i.e. a
       multiple of the HS bulk max packet size).
    2. Immediately queue a zero-length write (ZLP) via io_submit.

  Host side:
    3. Submit a 65536-byte bulk IN URB.

  Expected: URB completes with actual_length = 65024.
  Actual:   URB completes with actual_length = 53248, losing 11776
            bytes that leak into subsequent URBs.

At high speed the per-frame budget is 53248 bytes (512 * 13 * 8).
The 65024-byte request exhausts this budget after 53248 bytes, leaving
the request incomplete (req->req.actual < req->req.length). Neither
the request nor the URB is finished, and rescan is 0, so the loop
advances to the ZLP. For the ZLP, dev_len = 0, so len = min(12288, 0)
= 0, taking the unlikely(len == 0) path and setting is_short = 1.
The is_short handler then sets *status = 0, completing the URB with
only 53248 of the expected 65024 bytes.

Fix this by breaking out of the loop when the current request has
remaining data (req->req.actual < req->req.length). The request
resumes on the next timer tick, preserving correct data ordering.

Signed-off-by: Sebastian Urban <surban@surban.net>
Cc: stable <stable@kernel.org>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://patch.msgid.link/20260315151045.1155850-1-surban@surban.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index e55701575857..f094491b1041 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1538,6 +1538,12 @@ top:
 		/* rescan to continue with any other queued i/o */
 		if (rescan)
 			goto top;
+
+		/* request not fully transferred; stop iterating to
+		 * preserve data ordering across queued requests.
+		 */
+		if (req->req.actual < req->req.length)
+			break;
 	}
 	return sent;
 }
-- 
cgit v1.2.3


From 9a6a2091324ab6525951651b3700e3bea0fe9a89 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Sun, 1 Mar 2026 14:17:39 -0800
Subject: cxl/mbox: Use proper endpoint validity check upon sanitize

Fuzzying CXL triggered:

BUG: KASAN: null-ptr-deref in cxl_num_decoders_committed+0x3e/0x80 drivers/cxl/core/port.c:49
Read of size 4 at addr 0000000000000642 by task syz.0.97/2282

CPU: 2 UID: 0 PID: 2282 Comm: syz.0.97 Not tainted 7.0.0-rc1-gebd11be59f74-dirty #494 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.17.0-0-gb52ca86e094d-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 kasan_report+0xe0/0x110 mm/kasan/report.c:595
 cxl_num_decoders_committed+0x3e/0x80 drivers/cxl/core/port.c:49
 cxl_mem_sanitize+0x141/0x170 drivers/cxl/core/mbox.c:1304
 security_sanitize_store+0xb0/0x120 drivers/cxl/core/memdev.c:173
 dev_attr_store+0x46/0x70 drivers/base/core.c:2437
 sysfs_kf_write+0x95/0xb0 fs/sysfs/file.c:142
 kernfs_fop_write_iter+0x276/0x330 fs/kernfs/file.c:352
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x5df/0xaa0 fs/read_write.c:688
 ksys_write+0x103/0x1f0 fs/read_write.c:740
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x111/0x680 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f60a584ba79
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f60a42a7038 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f60a5ab5fa0 RCX: 00007f60a584ba79
RDX: 0000000000000002 RSI: 00002000000001c0 RDI: 0000000000000003
RBP: 00007f60a58a49df R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f60a5ab6038 R14: 00007f60a5ab5fa0 R15: 00007ffe58fad8b8
 </TASK>

This goes away using the correct check instead of abusing cxlmd->endpoint,
which is unusable (ENXIO) until the driver has probed. During that window
the memdev sysfs attributes are already visible, as soon as device_add()
completes.

Fixes: 29317f8dc6ed ("cxl/mem: Introduce cxl_memdev_attach for CXL-dependent operation")
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Link: https://patch.msgid.link/20260301221739.1726722-1-dave@stgolabs.net
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/mbox.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index e7a6452bf544..12386d912705 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1301,7 +1301,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
 	 * Require an endpoint to be safe otherwise the driver can not
 	 * be sure that the device is unmapped.
 	 */
-	if (endpoint && cxl_num_decoders_committed(endpoint) == 0)
+	if (cxlmd->dev.driver && cxl_num_decoders_committed(endpoint) == 0)
 		return __cxl_mem_sanitize(mds, cmd);
 
 	return -EBUSY;
-- 
cgit v1.2.3


From 591721223be9e28f83489a59289579493b8e3d83 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Mar 2026 13:40:07 +0100
Subject: ALSA: asihpi: avoid write overflow check warning

clang-22 rightfully warns that the memcpy() in adapter_prepare() copies
between different structures, crossing the boundary of nested
structures inside it:

In file included from sound/pci/asihpi/hpimsgx.c:13:
In file included from include/linux/string.h:386:
include/linux/fortify-string.h:569:4: error: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]
  569 |                         __write_overflow_field(p_size_field, size);

The two structures seem to refer to the same layout, despite the
separate definitions, so the code is in fact correct.

Avoid the warning by copying the two inner structures separately.
I see the same pattern happens in other functions in the same file,
so there is a chance that this may come back in the future, but
this instance is the only one that I saw in practice, hitting it
multiple times per day in randconfig build.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20260318124016.3488566-1-arnd@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/asihpi/hpimsgx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/sound/pci/asihpi/hpimsgx.c b/sound/pci/asihpi/hpimsgx.c
index b68e6bfbbfba..ed1c7b774436 100644
--- a/sound/pci/asihpi/hpimsgx.c
+++ b/sound/pci/asihpi/hpimsgx.c
@@ -581,8 +581,10 @@ static u16 adapter_prepare(u16 adapter)
 		HPI_ADAPTER_OPEN);
 	hm.adapter_index = adapter;
 	hw_entry_point(&hm, &hr);
-	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter], &hr,
-		sizeof(rESP_HPI_ADAPTER_OPEN[0]));
+	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].h, &hr,
+		sizeof(rESP_HPI_ADAPTER_OPEN[adapter].h));
+	memcpy(&rESP_HPI_ADAPTER_OPEN[adapter].a, &hr.u.ax.info,
+		sizeof(rESP_HPI_ADAPTER_OPEN[adapter].a));
 	if (hr.error)
 		return hr.error;
 
-- 
cgit v1.2.3


From c0e296f257671ba10249630fe58026f29e4804d9 Mon Sep 17 00:00:00 2001
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Date: Tue, 17 Mar 2026 15:04:55 +0000
Subject: mshv: Fix error handling in mshv_region_pin

The current error handling has two issues:

First, pin_user_pages_fast() can return a short pin count (less than
requested but greater than zero) when it cannot pin all requested pages.
This is treated as success, leading to partially pinned regions being
used, which causes memory corruption.

Second, when an error occurs mid-loop, already pinned pages from the
current batch are not properly accounted for before calling
mshv_region_invalidate_pages(), causing a page reference leak.

Treat short pins as errors and fix partial batch accounting before
cleanup.

Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_regions.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/mshv_regions.c b/drivers/hv/mshv_regions.c
index c28aac0726de..fdffd4f002f6 100644
--- a/drivers/hv/mshv_regions.c
+++ b/drivers/hv/mshv_regions.c
@@ -314,15 +314,17 @@ int mshv_region_pin(struct mshv_mem_region *region)
 		ret = pin_user_pages_fast(userspace_addr, nr_pages,
 					  FOLL_WRITE | FOLL_LONGTERM,
 					  pages);
-		if (ret < 0)
+		if (ret != nr_pages)
 			goto release_pages;
 	}
 
 	return 0;
 
 release_pages:
+	if (ret > 0)
+		done_count += ret;
 	mshv_region_invalidate_pages(region, 0, done_count);
-	return ret;
+	return ret < 0 ? ret : -ENOMEM;
 }
 
 static int mshv_region_chunk_unmap(struct mshv_mem_region *region,
-- 
cgit v1.2.3


From c23df30915f83e7257c8625b690a1cece94142a0 Mon Sep 17 00:00:00 2001
From: Jiucheng Xu <jiucheng.xu@amlogic.com>
Date: Wed, 11 Mar 2026 17:11:31 +0800
Subject: erofs: add GFP_NOIO in the bio completion if needed

The bio completion path in the process context (e.g. dm-verity)
will directly call into decompression rather than trigger another
workqueue context for minimal scheduling latencies, which can
then call vm_map_ram() with GFP_KERNEL.

Due to insufficient memory, vm_map_ram() may generate memory
swapping I/O, which can cause submit_bio_wait to deadlock
in some scenarios.

Trimmed down the call stack, as follows:

f2fs_submit_read_io
  submit_bio                      //bio_list is initialized.
    mmc_blk_mq_recovery
      z_erofs_endio
        vm_map_ram
          __pte_alloc_kernel
            __alloc_pages_direct_reclaim
              shrink_folio_list
                __swap_writepage
                  submit_bio_wait  //bio_list is non-NULL, hang!!!

Use memalloc_noio_{save,restore}() to wrap up this path.

Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Jiucheng Xu <jiucheng.xu@amlogic.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/zdata.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 3977e42b9516..fe8121df9ef2 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1445,6 +1445,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
 				       int bios)
 {
 	struct erofs_sb_info *const sbi = EROFS_SB(io->sb);
+	int gfp_flag;
 
 	/* wake up the caller thread for sync decompression */
 	if (io->sync) {
@@ -1477,7 +1478,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
 			sbi->sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON;
 		return;
 	}
+	gfp_flag = memalloc_noio_save();
 	z_erofs_decompressqueue_work(&io->u.work);
+	memalloc_noio_restore(gfp_flag);
 }
 
 static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
-- 
cgit v1.2.3


From ac512cd351f7e4ab4569f6a52c116f4ab3a239cc Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Tue, 17 Mar 2026 11:18:42 +0100
Subject: mtd: spi-nor: Fix RDCR controller capability core check

Commit 5008c3ec3f89 ("mtd: spi-nor: core: Check read CR support") adds a
controller check to make sure the core will not use CR reads on
controllers not supporting them. The approach is valid but the fix is
incorrect. Unfortunately, the author could not catch it, because the
expected behavior was met. The patch indeed drops the RDCR capability,
but it does it for all controllers!

The issue comes from the use of spi_nor_spimem_check_op() which is an
internal helper dedicated to check read/write operations only, despite
its generic name.

This helper looks for the biggest number of address bytes that can be
used for a page operation and tries 4 then 3. It then calls the usual
spi-mem helpers to do the checks. These will always fail because there
is now an inconsistency: the address cycles are forced to 4 (then 3)
bytes, but the bus width during the address cycles rightfully remains
0. There is a non-zero address length but a zero address bus width,
which is an invalid combination.

The correct check in this case is to directly call spi_mem_supports_op()
which doesn't messes up with the operation content.

Fixes: 5008c3ec3f89 ("mtd: spi-nor: core: Check read CR support")
Cc: stable@vger.kernel.org
Acked-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Acked-by: Takahiro Kuwano <takahiro.kuwano@infineon.com>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/spi-nor/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 8ffeb41c3e08..13201908a69f 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2466,7 +2466,7 @@ spi_nor_spimem_adjust_hwcaps(struct spi_nor *nor, u32 *hwcaps)
 
 		spi_nor_spimem_setup_op(nor, &op, nor->reg_proto);
 
-		if (spi_nor_spimem_check_op(nor, &op))
+		if (!spi_mem_supports_op(nor->spimem, &op))
 			nor->flags |= SNOR_F_NO_READ_CR;
 	}
 }
-- 
cgit v1.2.3


From 16dec014db0f4ac6f8090dea0bdfcb1ecebc12ca Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Tue, 17 Mar 2026 18:17:22 +0100
Subject: mtd: spi-nor: Rename spi_nor_spimem_check_op()

This helper really is just a little helper for internal purposes, and is
I/O operation oriented, despite its name. It has already been misused
in commit 5008c3ec3f89 ("mtd: spi-nor: core: Check read CR support"), so
rename it to clarify its purpose: it is only useful for reads and page
programs.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/spi-nor/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 13201908a69f..1eee519c01e5 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2345,15 +2345,15 @@ int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
 }
 
 /**
- * spi_nor_spimem_check_op - check if the operation is supported
- *                           by controller
+ * spi_nor_spimem_check_read_pp_op - check if a read or a page program operation is
+ *                                   supported by controller
  *@nor:        pointer to a 'struct spi_nor'
  *@op:         pointer to op template to be checked
  *
  * Returns 0 if operation is supported, -EOPNOTSUPP otherwise.
  */
-static int spi_nor_spimem_check_op(struct spi_nor *nor,
-				   struct spi_mem_op *op)
+static int spi_nor_spimem_check_read_pp_op(struct spi_nor *nor,
+					   struct spi_mem_op *op)
 {
 	/*
 	 * First test with 4 address bytes. The opcode itself might
@@ -2396,7 +2396,7 @@ static int spi_nor_spimem_check_readop(struct spi_nor *nor,
 	if (spi_nor_protocol_is_dtr(nor->read_proto))
 		op.dummy.nbytes *= 2;
 
-	return spi_nor_spimem_check_op(nor, &op);
+	return spi_nor_spimem_check_read_pp_op(nor, &op);
 }
 
 /**
@@ -2414,7 +2414,7 @@ static int spi_nor_spimem_check_pp(struct spi_nor *nor,
 
 	spi_nor_spimem_setup_op(nor, &op, pp->proto);
 
-	return spi_nor_spimem_check_op(nor, &op);
+	return spi_nor_spimem_check_read_pp_op(nor, &op);
 }
 
 /**
-- 
cgit v1.2.3


From b9465b04de4b90228de03db9a1e0d56b00814366 Mon Sep 17 00:00:00 2001
From: Olivier Sobrie <olivier@sobrie.be>
Date: Tue, 17 Mar 2026 18:18:07 +0100
Subject: mtd: rawnand: pl353: make sure optimal timings are applied

Timings of the nand are adjusted by pl35x_nfc_setup_interface() but
actually applied by the pl35x_nand_select_target() function.
If there is only one nand chip, the pl35x_nand_select_target() will only
apply the timings once since the test at its beginning will always be true
after the first call to this function. As a result, the hardware will
keep using the default timings set at boot to detect the nand chip, not
the optimal ones.

With this patch, we program directly the new timings when
pl35x_nfc_setup_interface() is called.

Fixes: 08d8c62164a3 ("mtd: rawnand: pl353: Add support for the ARM PL353 SMC NAND controller")
Signed-off-by: Olivier Sobrie <olivier@sobrie.be>
Cc: stable@vger.kernel.org
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/pl35x-nand-controller.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/mtd/nand/raw/pl35x-nand-controller.c b/drivers/mtd/nand/raw/pl35x-nand-controller.c
index 947fd86ac5fa..f2c65eb7a8d9 100644
--- a/drivers/mtd/nand/raw/pl35x-nand-controller.c
+++ b/drivers/mtd/nand/raw/pl35x-nand-controller.c
@@ -862,6 +862,9 @@ static int pl35x_nfc_setup_interface(struct nand_chip *chip, int cs,
 			  PL35X_SMC_NAND_TAR_CYCLES(tmgs.t_ar) |
 			  PL35X_SMC_NAND_TRR_CYCLES(tmgs.t_rr);
 
+	writel(plnand->timings, nfc->conf_regs + PL35X_SMC_CYCLES);
+	pl35x_smc_update_regs(nfc);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From b826d2c0b0ecb844c84431ba6b502e744f5d919a Mon Sep 17 00:00:00 2001
From: Maíra Canal <mcanal@igalia.com>
Date: Tue, 17 Mar 2026 19:41:49 -0300
Subject: pmdomain: bcm: bcm2835-power: Increase ASB control timeout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bcm2835_asb_control() function uses a tight polling loop to wait
for the ASB bridge to acknowledge a request. During intensive workloads,
this handshake intermittently fails for V3D's master ASB on BCM2711,
resulting in "Failed to disable ASB master for v3d" errors during
runtime PM suspend. As a consequence, the failed power-off leaves V3D in
a broken state, leading to bus faults or system hangs on later accesses.

As the timeout is insufficient in some scenarios, increase the polling
timeout from 1us to 5us, which is still negligible in the context of a
power domain transition. Also, replace the open-coded ktime_get_ns()/
cpu_relax() polling loop with readl_poll_timeout_atomic().

Cc: stable@vger.kernel.org
Fixes: 670c672608a1 ("soc: bcm: bcm2835-pm: Add support for power domains under a new binding.")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/bcm/bcm2835-power.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c
index 0450202bbee2..eee87a300532 100644
--- a/drivers/pmdomain/bcm/bcm2835-power.c
+++ b/drivers/pmdomain/bcm/bcm2835-power.c
@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/mfd/bcm2835-pm.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -153,7 +154,6 @@ struct bcm2835_power {
 static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable)
 {
 	void __iomem *base = power->asb;
-	u64 start;
 	u32 val;
 
 	switch (reg) {
@@ -166,8 +166,6 @@ static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable
 		break;
 	}
 
-	start = ktime_get_ns();
-
 	/* Enable the module's async AXI bridges. */
 	if (enable) {
 		val = readl(base + reg) & ~ASB_REQ_STOP;
@@ -176,11 +174,9 @@ static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable
 	}
 	writel(PM_PASSWORD | val, base + reg);
 
-	while (!!(readl(base + reg) & ASB_ACK) == enable) {
-		cpu_relax();
-		if (ktime_get_ns() - start >= 1000)
-			return -ETIMEDOUT;
-	}
+	if (readl_poll_timeout_atomic(base + reg, val,
+				      !!(val & ASB_ACK) != enable, 0, 5))
+		return -ETIMEDOUT;
 
 	return 0;
 }
-- 
cgit v1.2.3


From c4192754e836e0ffed95833509b6ada975b74418 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 18 Mar 2026 11:36:29 -0700
Subject: fs/tests: exec: Remove bad test vector

Drop an unusable test in the bprm stack limits.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Closes: https://lore.kernel.org/all/a3e9b1c2-40c1-45df-9fa2-14ee6a7b3fe2@roeck-us.net
Fixes: 60371f43e56b ("exec: Add KUnit test for bprm_stack_limits()")
Signed-off-by: Kees Cook <kees@kernel.org>
---
 fs/tests/exec_kunit.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/tests/exec_kunit.c b/fs/tests/exec_kunit.c
index f412d1a0f6bb..1c32cac098cf 100644
--- a/fs/tests/exec_kunit.c
+++ b/fs/tests/exec_kunit.c
@@ -94,9 +94,6 @@ static const struct bprm_stack_limits_result bprm_stack_limits_results[] = {
 	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 * 3 + sizeof(void *)),
 	    .argc = 0, .envc = 0 },
 	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
-	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 *  + sizeof(void *)),
-	    .argc = 0, .envc = 0 },
-	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
 	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * _STK_LIM,
 	    .argc = 0, .envc = 0 },
 	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
-- 
cgit v1.2.3


From cdbefe9d4029d4834d404f7ba13a960b38a69e88 Mon Sep 17 00:00:00 2001
From: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Date: Wed, 11 Mar 2026 11:00:34 +0200
Subject: tools/power turbostat: Fix delimiter bug in print functions

Commands that add counters, such as 'turbostat --show C1,C1+'
display merged columns without a delimiter.

This is caused by the bad syntax: '(*printed++ ? delim : "")', shared by
print_name()/print_hex_value()/print_decimal_value()/print_float_value()

Use '((*printed)++ ? delim : "")' to correctly increment the value at *printed.

[lenb: fix code and commit message typo, re-word]
Fixes: 56dbb878507b ("tools/power turbostat: Refactor added column header printing")
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 3487548841e1..34e2143cd4b3 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -2837,29 +2837,29 @@ static inline int print_name(int width, int *printed, char *delim, char *name, e
 	UNUSED(type);
 
 	if (format == FORMAT_RAW && width >= 64)
-		return (sprintf(outp, "%s%-8s", (*printed++ ? delim : ""), name));
+		return (sprintf(outp, "%s%-8s", ((*printed)++ ? delim : ""), name));
 	else
-		return (sprintf(outp, "%s%s", (*printed++ ? delim : ""), name));
+		return (sprintf(outp, "%s%s", ((*printed)++ ? delim : ""), name));
 }
 
 static inline int print_hex_value(int width, int *printed, char *delim, unsigned long long value)
 {
 	if (width <= 32)
-		return (sprintf(outp, "%s%08x", (*printed++ ? delim : ""), (unsigned int)value));
+		return (sprintf(outp, "%s%08x", ((*printed)++ ? delim : ""), (unsigned int)value));
 	else
-		return (sprintf(outp, "%s%016llx", (*printed++ ? delim : ""), value));
+		return (sprintf(outp, "%s%016llx", ((*printed)++ ? delim : ""), value));
 }
 
 static inline int print_decimal_value(int width, int *printed, char *delim, unsigned long long value)
 {
 	UNUSED(width);
 
-	return (sprintf(outp, "%s%lld", (*printed++ ? delim : ""), value));
+	return (sprintf(outp, "%s%lld", ((*printed)++ ? delim : ""), value));
 }
 
 static inline int print_float_value(int *printed, char *delim, double value)
 {
-	return (sprintf(outp, "%s%0.2f", (*printed++ ? delim : ""), value));
+	return (sprintf(outp, "%s%0.2f", ((*printed)++ ? delim : ""), value));
 }
 
 void print_header(char *delim)
-- 
cgit v1.2.3


From 86259558e422b250aa6aa57163a6d759074573f5 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Wed, 18 Mar 2026 19:40:19 +0000
Subject: hwmon: (pmbus/isl68137) Fix unchecked return value and use
 sysfs_emit()

isl68137_avs_enable_show_page() uses the return value of
pmbus_read_byte_data() without checking for errors. If the I2C transaction
fails, a negative error code is passed through bitwise operations,
producing incorrect output.

Add an error check to propagate the return value if it is negative.
Additionally, modernize the callback by replacing sprintf()
with sysfs_emit().

Fixes: 038a9c3d1e424 ("hwmon: (pmbus/isl68137) Add driver for Intersil ISL68137 PWM Controller")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260318193952.47908-2-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/isl68137.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c
index 97b61836f53a..e7dac26b5be6 100644
--- a/drivers/hwmon/pmbus/isl68137.c
+++ b/drivers/hwmon/pmbus/isl68137.c
@@ -98,8 +98,11 @@ static ssize_t isl68137_avs_enable_show_page(struct i2c_client *client,
 {
 	int val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
 
-	return sprintf(buf, "%d\n",
-		       (val & ISL68137_VOUT_AVS) == ISL68137_VOUT_AVS ? 1 : 0);
+	if (val < 0)
+		return val;
+
+	return sysfs_emit(buf, "%d\n",
+			   (val & ISL68137_VOUT_AVS) == ISL68137_VOUT_AVS);
 }
 
 static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client,
-- 
cgit v1.2.3


From 201bc182ad6333468013f1af0719ffe125826b6a Mon Sep 17 00:00:00 2001
From: William Roche <william.roche@oracle.com>
Date: Tue, 17 Mar 2026 10:38:10 +0000
Subject: x86/mce/amd: Check SMCA feature bit before accessing SMCA MSRs

People do effort to inject MCEs into guests in order to simulate/test
handling of hardware errors. The real use case behind it is testing the
handling of SIGBUS which the memory failure code sends to the process.

If that process is QEMU, instead of killing the whole guest, the MCE can
be injected into the guest kernel so that latter can attempt proper
handling and kill the user *process*  in the guest, instead, which
caused the MCE. The assumption being here that the whole injection flow
can supply enough information that the guest kernel can pinpoint the
right process. But that's a different topic...

Regardless of virtualization or not, access to SMCA-specific registers
like MCA_DESTAT should only be done after having checked the smca
feature bit. And there are AMD machines like Bulldozer (the one before
Zen1) which do support deferred errors but are not SMCA machines.

Therefore, properly check the feature bit before accessing related MSRs.

  [ bp: Rewrite commit message. ]

Fixes: 7cb735d7c0cb ("x86/mce: Unify AMD DFR handler with MCA Polling")
Signed-off-by: William Roche <william.roche@oracle.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20260218163025.1316501-1-william.roche@oracle.com
---
 arch/x86/kernel/cpu/mce/amd.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index da13c1e37f87..a030ee4cecc2 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -875,13 +875,18 @@ void amd_clear_bank(struct mce *m)
 {
 	amd_reset_thr_limit(m->bank);
 
-	/* Clear MCA_DESTAT for all deferred errors even those logged in MCA_STATUS. */
-	if (m->status & MCI_STATUS_DEFERRED)
-		mce_wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(m->bank), 0);
+	if (mce_flags.smca) {
+		/*
+		 * Clear MCA_DESTAT for all deferred errors even those
+		 * logged in MCA_STATUS.
+		 */
+		if (m->status & MCI_STATUS_DEFERRED)
+			mce_wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(m->bank), 0);
 
-	/* Don't clear MCA_STATUS if MCA_DESTAT was used exclusively. */
-	if (m->kflags & MCE_CHECK_DFR_REGS)
-		return;
+		/* Don't clear MCA_STATUS if MCA_DESTAT was used exclusively. */
+		if (m->kflags & MCE_CHECK_DFR_REGS)
+			return;
+	}
 
 	mce_wrmsrq(mca_msr_reg(m->bank, MCA_STATUS), 0);
 }
-- 
cgit v1.2.3


From bb288d7d869e86d382f35a0e26242c5ccb05ca82 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 19 Mar 2026 08:43:05 +0900
Subject: lib/bootconfig: check xbc_init_node() return in override path

The ':=' override path in xbc_parse_kv() calls xbc_init_node() to
re-initialize an existing value node but does not check the return
value. If xbc_init_node() fails (data offset out of range), parsing
silently continues with stale node data.

Add the missing error check to match the xbc_add_node() call path
which already checks for failure.

In practice, a bootconfig using ':=' to override a value near the
32KB data limit could silently retain the old value, meaning a
security-relevant boot parameter override (e.g., a trace filter or
debug setting) would not take effect as intended.

Link: https://lore.kernel.org/all/20260318155847.78065-2-objecting@objecting.org/

Fixes: e5efaeb8a8f5 ("bootconfig: Support mixing a value and subkeys under a key")
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 lib/bootconfig.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 2da049216fe0..e88d0221a826 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -723,7 +723,8 @@ static int __init xbc_parse_kv(char **k, char *v, int op)
 		if (op == ':') {
 			unsigned short nidx = child->next;
 
-			xbc_init_node(child, v, XBC_VALUE);
+			if (xbc_init_node(child, v, XBC_VALUE) < 0)
+				return xbc_parse_error("Failed to override value", v);
 			child->next = nidx;	/* keep subkeys */
 			goto array;
 		}
-- 
cgit v1.2.3


From 3b2c2ab4ceb82af484310c3087541eab00ea288b Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Thu, 19 Mar 2026 08:43:06 +0900
Subject: tools/bootconfig: fix fd leak in load_xbc_file() on fstat failure

If fstat() fails after open() succeeds, the function returns without
closing the file descriptor. Also preserve errno across close(), since
close() may overwrite it before the error is returned.

Link: https://lore.kernel.org/all/20260318155847.78065-3-objecting@objecting.org/

Fixes: 950313ebf79c ("tools: bootconfig: Add bootconfig command")
Signed-off-by: Josh Law <objecting@objecting.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 tools/bootconfig/main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 55d59ed507d5..643f707b8f1d 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -162,8 +162,11 @@ static int load_xbc_file(const char *path, char **buf)
 	if (fd < 0)
 		return -errno;
 	ret = fstat(fd, &stat);
-	if (ret < 0)
-		return -errno;
+	if (ret < 0) {
+		ret = -errno;
+		close(fd);
+		return ret;
+	}
 
 	ret = load_xbc_fd(fd, buf, stat.st_size);
 
-- 
cgit v1.2.3


From 7d9351435ebba08bbb60f42793175c9dc714d2fb Mon Sep 17 00:00:00 2001
From: Wesley Atwell <atwellwea@gmail.com>
Date: Tue, 17 Mar 2026 00:14:31 -0600
Subject: netdevsim: drop PSP ext ref on forward failure

nsim_do_psp() takes an extra reference to the PSP skb extension so the
extension survives __dev_forward_skb(). That forward path scrubs the skb
and drops attached skb extensions before nsim_psp_handle_ext() can
reattach the PSP metadata.

If __dev_forward_skb() fails in nsim_forward_skb(), the function returns
before nsim_psp_handle_ext() can attach that extension to the skb, leaving
the extra reference leaked.

Drop the saved PSP extension reference before returning from the
forward-failure path. Guard the put because plain or non-decapsulated
traffic can also fail forwarding without ever taking the extra PSP
reference.

Fixes: f857478d6206 ("netdevsim: a basic test PSP implementation")
Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
Reviewed-by: Daniel Zahka <daniel.zahka@gmail.com>
Link: https://patch.msgid.link/20260317061431.1482716-1-atwellwea@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 5ec028a00c62..3645ebde049a 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -109,8 +109,11 @@ static int nsim_forward_skb(struct net_device *tx_dev,
 	int ret;
 
 	ret = __dev_forward_skb(rx_dev, skb);
-	if (ret)
+	if (ret) {
+		if (psp_ext)
+			__skb_ext_put(psp_ext);
 		return ret;
+	}
 
 	nsim_psp_handle_ext(skb, psp_ext);
 
-- 
cgit v1.2.3


From 8da13e6d63c1a97f7302d342c89c4a56a55c7015 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 16 Mar 2026 13:38:24 +0300
Subject: net: macb: fix use-after-free access to PTP clock

PTP clock is registered on every opening of the interface and destroyed on
every closing.  However it may be accessed via get_ts_info ethtool call
which is possible while the interface is just present in the kernel.

BUG: KASAN: use-after-free in ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426
Read of size 4 at addr ffff8880194345cc by task syz.0.6/948

CPU: 1 PID: 948 Comm: syz.0.6 Not tainted 6.1.164+ #109
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:316 [inline]
 print_report+0x17f/0x496 mm/kasan/report.c:420
 kasan_report+0xd9/0x180 mm/kasan/report.c:524
 ptp_clock_index+0x47/0x50 drivers/ptp/ptp_clock.c:426
 gem_get_ts_info+0x138/0x1e0 drivers/net/ethernet/cadence/macb_main.c:3349
 macb_get_ts_info+0x68/0xb0 drivers/net/ethernet/cadence/macb_main.c:3371
 __ethtool_get_ts_info+0x17c/0x260 net/ethtool/common.c:558
 ethtool_get_ts_info net/ethtool/ioctl.c:2367 [inline]
 __dev_ethtool net/ethtool/ioctl.c:3017 [inline]
 dev_ethtool+0x2b05/0x6290 net/ethtool/ioctl.c:3095
 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510
 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215
 sock_ioctl+0x577/0x6d0 net/socket.c:1320
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:870 [inline]
 __se_sys_ioctl fs/ioctl.c:856 [inline]
 __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856
 do_syscall_x64 arch/x86/entry/common.c:46 [inline]
 do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
 </TASK>

Allocated by task 457:
 kmalloc include/linux/slab.h:563 [inline]
 kzalloc include/linux/slab.h:699 [inline]
 ptp_clock_register+0x144/0x10e0 drivers/ptp/ptp_clock.c:235
 gem_ptp_init+0x46f/0x930 drivers/net/ethernet/cadence/macb_ptp.c:375
 macb_open+0x901/0xd10 drivers/net/ethernet/cadence/macb_main.c:2920
 __dev_open+0x2ce/0x500 net/core/dev.c:1501
 __dev_change_flags+0x56a/0x740 net/core/dev.c:8651
 dev_change_flags+0x92/0x170 net/core/dev.c:8722
 do_setlink+0xaf8/0x3a80 net/core/rtnetlink.c:2833
 __rtnl_newlink+0xbf4/0x1940 net/core/rtnetlink.c:3608
 rtnl_newlink+0x63/0xa0 net/core/rtnetlink.c:3655
 rtnetlink_rcv_msg+0x3c6/0xed0 net/core/rtnetlink.c:6150
 netlink_rcv_skb+0x15d/0x430 net/netlink/af_netlink.c:2511
 netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
 netlink_unicast+0x6d7/0xa30 net/netlink/af_netlink.c:1344
 netlink_sendmsg+0x97e/0xeb0 net/netlink/af_netlink.c:1872
 sock_sendmsg_nosec net/socket.c:718 [inline]
 __sock_sendmsg+0x14b/0x180 net/socket.c:730
 __sys_sendto+0x320/0x3b0 net/socket.c:2152
 __do_sys_sendto net/socket.c:2164 [inline]
 __se_sys_sendto net/socket.c:2160 [inline]
 __x64_sys_sendto+0xdc/0x1b0 net/socket.c:2160
 do_syscall_x64 arch/x86/entry/common.c:46 [inline]
 do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Freed by task 938:
 kasan_slab_free include/linux/kasan.h:177 [inline]
 slab_free_hook mm/slub.c:1729 [inline]
 slab_free_freelist_hook mm/slub.c:1755 [inline]
 slab_free mm/slub.c:3687 [inline]
 __kmem_cache_free+0xbc/0x320 mm/slub.c:3700
 device_release+0xa0/0x240 drivers/base/core.c:2507
 kobject_cleanup lib/kobject.c:681 [inline]
 kobject_release lib/kobject.c:712 [inline]
 kref_put include/linux/kref.h:65 [inline]
 kobject_put+0x1cd/0x350 lib/kobject.c:729
 put_device+0x1b/0x30 drivers/base/core.c:3805
 ptp_clock_unregister+0x171/0x270 drivers/ptp/ptp_clock.c:391
 gem_ptp_remove+0x4e/0x1f0 drivers/net/ethernet/cadence/macb_ptp.c:404
 macb_close+0x1c8/0x270 drivers/net/ethernet/cadence/macb_main.c:2966
 __dev_close_many+0x1b9/0x310 net/core/dev.c:1585
 __dev_close net/core/dev.c:1597 [inline]
 __dev_change_flags+0x2bb/0x740 net/core/dev.c:8649
 dev_change_flags+0x92/0x170 net/core/dev.c:8722
 dev_ifsioc+0x151/0xe00 net/core/dev_ioctl.c:326
 dev_ioctl+0x33e/0x1070 net/core/dev_ioctl.c:572
 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215
 sock_ioctl+0x577/0x6d0 net/socket.c:1320
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:870 [inline]
 __se_sys_ioctl fs/ioctl.c:856 [inline]
 __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856
 do_syscall_x64 arch/x86/entry/common.c:46 [inline]
 do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Set the PTP clock pointer to NULL after unregistering.

Fixes: c2594d804d5c ("macb: Common code to enable ptp support for MACB/GEM")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://patch.msgid.link/20260316103826.74506-1-pchelkin@ispras.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_ptp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index c9e77819196e..d91f7b1aa39c 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -357,8 +357,10 @@ void gem_ptp_remove(struct net_device *ndev)
 {
 	struct macb *bp = netdev_priv(ndev);
 
-	if (bp->ptp_clock)
+	if (bp->ptp_clock) {
 		ptp_clock_unregister(bp->ptp_clock);
+		bp->ptp_clock = NULL;
+	}
 
 	gem_ptp_clear_timer(bp);
 
-- 
cgit v1.2.3


From 34b11cc56e4369bc08b1f4c4a04222d75ed596ce Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 16 Mar 2026 13:38:25 +0300
Subject: net: macb: fix uninitialized rx_fs_lock

If hardware doesn't support RX Flow Filters, rx_fs_lock spinlock is not
initialized leading to the following assertion splat triggerable via
set_rxnfc callback.

INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe
you didn't initialize this object before use?
turning off the locking correctness validator.
CPU: 1 PID: 949 Comm: syz.0.6 Not tainted 6.1.164+ #113
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x8d/0xba lib/dump_stack.c:106
 assign_lock_key kernel/locking/lockdep.c:974 [inline]
 register_lock_class+0x141b/0x17f0 kernel/locking/lockdep.c:1287
 __lock_acquire+0x74f/0x6c40 kernel/locking/lockdep.c:4928
 lock_acquire kernel/locking/lockdep.c:5662 [inline]
 lock_acquire+0x190/0x4b0 kernel/locking/lockdep.c:5627
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x33/0x50 kernel/locking/spinlock.c:162
 gem_del_flow_filter drivers/net/ethernet/cadence/macb_main.c:3562 [inline]
 gem_set_rxnfc+0x533/0xac0 drivers/net/ethernet/cadence/macb_main.c:3667
 ethtool_set_rxnfc+0x18c/0x280 net/ethtool/ioctl.c:961
 __dev_ethtool net/ethtool/ioctl.c:2956 [inline]
 dev_ethtool+0x229c/0x6290 net/ethtool/ioctl.c:3095
 dev_ioctl+0x637/0x1070 net/core/dev_ioctl.c:510
 sock_do_ioctl+0x20d/0x2c0 net/socket.c:1215
 sock_ioctl+0x577/0x6d0 net/socket.c:1320
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:870 [inline]
 __se_sys_ioctl fs/ioctl.c:856 [inline]
 __x64_sys_ioctl+0x18c/0x210 fs/ioctl.c:856
 do_syscall_x64 arch/x86/entry/common.c:46 [inline]
 do_syscall_64+0x35/0x80 arch/x86/entry/common.c:76
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

A more straightforward solution would be to always initialize rx_fs_lock,
just like rx_fs_list.  However, in this case the driver set_rxnfc callback
would return with a rather confusing error code, e.g. -EINVAL.  So deny
set_rxnfc attempts directly if the RX filtering feature is not supported
by hardware.

Fixes: ae8223de3df5 ("net: macb: Added support for RX filtering")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://patch.msgid.link/20260316103826.74506-2-pchelkin@ispras.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 033cff571904..c16ac9c76aa3 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3983,6 +3983,9 @@ static int gem_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 	struct macb *bp = netdev_priv(netdev);
 	int ret;
 
+	if (!(netdev->hw_features & NETIF_F_NTUPLE))
+		return -EOPNOTSUPP;
+
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXCLSRLINS:
 		if ((cmd->fs.location >= bp->max_tuples)
-- 
cgit v1.2.3


From 55dc632ab2ac2889b15995a9eef56c753d48ebc7 Mon Sep 17 00:00:00 2001
From: Ian Ray <ian.ray@gehealthcare.com>
Date: Tue, 17 Mar 2026 10:53:36 +0200
Subject: NFC: nxp-nci: allow GPIOs to sleep

Allow the firmware and enable GPIOs to sleep.

This fixes a `WARN_ON' and allows the driver to operate GPIOs which are
connected to I2C GPIO expanders.

-- >8 --
kernel: WARNING: CPU: 3 PID: 2636 at drivers/gpio/gpiolib.c:3880 gpiod_set_value+0x88/0x98
-- >8 --

Fixes: 43201767b44c ("NFC: nxp-nci: Convert to use GPIO descriptor")
Cc: stable@vger.kernel.org
Signed-off-by: Ian Ray <ian.ray@gehealthcare.com>
Link: https://patch.msgid.link/20260317085337.146545-1-ian.ray@gehealthcare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/nxp-nci/i2c.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c
index 6a5ce8ff91f0..b3d34433bd14 100644
--- a/drivers/nfc/nxp-nci/i2c.c
+++ b/drivers/nfc/nxp-nci/i2c.c
@@ -47,8 +47,8 @@ static int nxp_nci_i2c_set_mode(void *phy_id,
 {
 	struct nxp_nci_i2c_phy *phy = (struct nxp_nci_i2c_phy *) phy_id;
 
-	gpiod_set_value(phy->gpiod_fw, (mode == NXP_NCI_MODE_FW) ? 1 : 0);
-	gpiod_set_value(phy->gpiod_en, (mode != NXP_NCI_MODE_COLD) ? 1 : 0);
+	gpiod_set_value_cansleep(phy->gpiod_fw, (mode == NXP_NCI_MODE_FW) ? 1 : 0);
+	gpiod_set_value_cansleep(phy->gpiod_en, (mode != NXP_NCI_MODE_COLD) ? 1 : 0);
 	usleep_range(10000, 15000);
 
 	if (mode == NXP_NCI_MODE_COLD)
-- 
cgit v1.2.3


From 06413793526251870e20402c39930804f14d59c0 Mon Sep 17 00:00:00 2001
From: Minhong He <heminhong@kylinos.cn>
Date: Mon, 16 Mar 2026 15:33:01 +0800
Subject: ipv6: add NULL checks for idev in SRv6 paths

__in6_dev_get() can return NULL when the device has no IPv6 configuration
(e.g. MTU < IPV6_MIN_MTU or after NETDEV_UNREGISTER).

Add NULL checks for idev returned by __in6_dev_get() in both
seg6_hmac_validate_skb() and ipv6_srh_rcv() to prevent potential NULL
pointer dereferences.

Fixes: 1ababeba4a21 ("ipv6: implement dataplane support for rthdr type 4 (Segment Routing Header)")
Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Signed-off-by: Minhong He <heminhong@kylinos.cn>
Reviewed-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Link: https://patch.msgid.link/20260316073301.106643-1-heminhong@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/exthdrs.c   | 4 ++++
 net/ipv6/seg6_hmac.c | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 5e3610a926cf..95558fd6f447 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -379,6 +379,10 @@ static int ipv6_srh_rcv(struct sk_buff *skb)
 	hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
 
 	idev = __in6_dev_get(skb->dev);
+	if (!idev) {
+		kfree_skb(skb);
+		return -1;
+	}
 
 	accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled),
 			  READ_ONCE(idev->cnf.seg6_enabled));
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index ee6bac0160ac..e6964c6b0d38 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -184,6 +184,8 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb)
 	int require_hmac;
 
 	idev = __in6_dev_get(skb->dev);
+	if (!idev)
+		return false;
 
 	srh = (struct ipv6_sr_hdr *)skb_transport_header(skb);
 
-- 
cgit v1.2.3


From 146bd2a87a65aa407bb17fac70d8d583d19aba06 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 12 Mar 2026 13:53:07 -0700
Subject: bpf: Release module BTF IDR before module unload

Gregory reported in [0] that the global_map_resize test when run in
repeatedly ends up failing during program load. This stems from the fact
that BTF reference has not dropped to zero after the previous run's
module is unloaded, and the older module's BTF is still discoverable and
visible. Later, in libbpf, load_module_btfs() will find the ID for this
stale BTF, open its fd, and then it will be used during program load
where later steps taking module reference using btf_try_get_module()
fail since the underlying module for the BTF is gone.

Logically, once a module is unloaded, it's associated BTF artifacts
should become hidden. The BTF object inside the kernel may still remain
alive as long its reference counts are alive, but it should no longer be
discoverable.

To fix this, let us call btf_free_id() from the MODULE_STATE_GOING case
for the module unload to free the BTF associated IDR entry, and disable
its discovery once module unload returns to user space. If a race
happens during unload, the outcome is non-deterministic anyway. However,
user space should be able to rely on the guarantee that once it has
synchronously established a successful module unload, no more stale
artifacts associated with this module can be obtained subsequently.

Note that we must be careful to not invoke btf_free_id() in btf_put()
when btf_is_module() is true now. There could be a window where the
module unload drops a non-terminal reference, frees the IDR, but the
same ID gets reused and the second unconditional btf_free_id() ends up
releasing an unrelated entry.

To avoid a special case for btf_is_module() case, set btf->id to zero to
make btf_free_id() idempotent, such that we can unconditionally invoke it
from btf_put(), and also from the MODULE_STATE_GOING case. Since zero is
an invalid IDR, the idr_remove() should be a noop.

Note that we can be sure that by the time we reach final btf_put() for
btf_is_module() case, the btf_free_id() is already done, since the
module itself holds the BTF reference, and it will call this function
for the BTF before dropping its own reference.

  [0]: https://lore.kernel.org/bpf/cover.1773170190.git.grbell@redhat.com

Fixes: 36e68442d1af ("bpf: Load and verify kernel module BTFs")
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
Reported-by: Gregory Bell <grbell@redhat.com>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260312205307.1346991-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4872d2a6c42d..71f9143fe90f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1787,7 +1787,16 @@ static void btf_free_id(struct btf *btf)
 	 * of the _bh() version.
 	 */
 	spin_lock_irqsave(&btf_idr_lock, flags);
-	idr_remove(&btf_idr, btf->id);
+	if (btf->id) {
+		idr_remove(&btf_idr, btf->id);
+		/*
+		 * Clear the id here to make this function idempotent, since it will get
+		 * called a couple of times for module BTFs: on module unload, and then
+		 * the final btf_put(). btf_alloc_id() starts IDs with 1, so we can use
+		 * 0 as sentinel value.
+		 */
+		WRITE_ONCE(btf->id, 0);
+	}
 	spin_unlock_irqrestore(&btf_idr_lock, flags);
 }
 
@@ -8115,7 +8124,7 @@ static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct btf *btf = filp->private_data;
 
-	seq_printf(m, "btf_id:\t%u\n", btf->id);
+	seq_printf(m, "btf_id:\t%u\n", READ_ONCE(btf->id));
 }
 #endif
 
@@ -8197,7 +8206,7 @@ int btf_get_info_by_fd(const struct btf *btf,
 	if (copy_from_user(&info, uinfo, info_copy))
 		return -EFAULT;
 
-	info.id = btf->id;
+	info.id = READ_ONCE(btf->id);
 	ubtf = u64_to_user_ptr(info.btf);
 	btf_copy = min_t(u32, btf->data_size, info.btf_size);
 	if (copy_to_user(ubtf, btf->data, btf_copy))
@@ -8260,7 +8269,7 @@ int btf_get_fd_by_id(u32 id)
 
 u32 btf_obj_id(const struct btf *btf)
 {
-	return btf->id;
+	return READ_ONCE(btf->id);
 }
 
 bool btf_is_kernel(const struct btf *btf)
@@ -8382,6 +8391,13 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			if (btf_mod->module != module)
 				continue;
 
+			/*
+			 * For modules, we do the freeing of BTF IDR as soon as
+			 * module goes away to disable BTF discovery, since the
+			 * btf_try_get_module() on such BTFs will fail. This may
+			 * be called again on btf_put(), but it's ok to do so.
+			 */
+			btf_free_id(btf_mod->btf);
 			list_del(&btf_mod->list);
 			if (btf_mod->sysfs_attr)
 				sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr);
-- 
cgit v1.2.3


From b7e3a5d9c0d66b7fb44f63aef3bd734821afa0c8 Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Mon, 16 Mar 2026 11:46:01 +0200
Subject: net/mlx5: qos: Restrict RTNL area to avoid a lock cycle

A lock dependency cycle exists where:
1. mlx5_ib_roce_init -> mlx5_core_uplink_netdev_event_replay ->
mlx5_blocking_notifier_call_chain (takes notifier_rwsem) ->
mlx5e_mdev_notifier_event -> mlx5_netdev_notifier_register ->
register_netdevice_notifier_dev_net (takes rtnl)
=> notifier_rwsem -> rtnl

2. mlx5e_probe -> _mlx5e_probe ->
mlx5_core_uplink_netdev_set (takes uplink_netdev_lock) ->
mlx5_blocking_notifier_call_chain (takes notifier_rwsem)
=> uplink_netdev_lock -> notifier_rwsem

3: devlink_nl_rate_set_doit -> devlink_nl_rate_set ->
mlx5_esw_devlink_rate_leaf_tx_max_set -> esw_qos_devlink_rate_to_mbps ->
mlx5_esw_qos_max_link_speed_get (takes rtnl) ->
mlx5_esw_qos_lag_link_speed_get_locked ->
mlx5_uplink_netdev_get (takes uplink_netdev_lock)
=> rtnl -> uplink_netdev_lock
=> BOOM! (lock cycle)

Fix that by restricting the rtnl-protected section to just the necessary
part, the call to netdev_master_upper_dev_get and speed querying, so
that the last lock dependency is avoided and the cycle doesn't close.
This is safe because mlx5_uplink_netdev_get uses netdev_hold to keep the
uplink netdev alive while its master device is queried.

Use this opportunity to rename the ambiguously-named "hold_rtnl_lock"
argument to "take_rtnl" and remove the "_locked" suffix from
mlx5_esw_qos_lag_link_speed_get_locked.

Fixes: 6b4be64fd9fe ("net/mlx5e: Harden uplink netdev access against device unbind")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260316094603.6999-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 26178d0bac92..faccc60fc93a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1489,24 +1489,24 @@ out:
 	return err;
 }
 
-static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev)
+static u32 mlx5_esw_qos_lag_link_speed_get(struct mlx5_core_dev *mdev,
+					   bool take_rtnl)
 {
 	struct ethtool_link_ksettings lksettings;
 	struct net_device *slave, *master;
 	u32 speed = SPEED_UNKNOWN;
 
-	/* Lock ensures a stable reference to master and slave netdevice
-	 * while port speed of master is queried.
-	 */
-	ASSERT_RTNL();
-
 	slave = mlx5_uplink_netdev_get(mdev);
 	if (!slave)
 		goto out;
 
+	if (take_rtnl)
+		rtnl_lock();
 	master = netdev_master_upper_dev_get(slave);
 	if (master && !__ethtool_get_link_ksettings(master, &lksettings))
 		speed = lksettings.base.speed;
+	if (take_rtnl)
+		rtnl_unlock();
 
 out:
 	mlx5_uplink_netdev_put(mdev, slave);
@@ -1514,20 +1514,15 @@ out:
 }
 
 static int mlx5_esw_qos_max_link_speed_get(struct mlx5_core_dev *mdev, u32 *link_speed_max,
-					   bool hold_rtnl_lock, struct netlink_ext_ack *extack)
+					   bool take_rtnl,
+					   struct netlink_ext_ack *extack)
 {
 	int err;
 
 	if (!mlx5_lag_is_active(mdev))
 		goto skip_lag;
 
-	if (hold_rtnl_lock)
-		rtnl_lock();
-
-	*link_speed_max = mlx5_esw_qos_lag_link_speed_get_locked(mdev);
-
-	if (hold_rtnl_lock)
-		rtnl_unlock();
+	*link_speed_max = mlx5_esw_qos_lag_link_speed_get(mdev, take_rtnl);
 
 	if (*link_speed_max != (u32)SPEED_UNKNOWN)
 		return 0;
-- 
cgit v1.2.3


From 99b36850d881e2d65912b2520a1c80d0fcc9429a Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 16 Mar 2026 11:46:02 +0200
Subject: net/mlx5e: Prevent concurrent access to IPSec ASO context

The query or updating IPSec offload object is through Access ASO WQE.
The driver uses a single mlx5e_ipsec_aso struct for each PF, which
contains a shared DMA-mapped context for all ASO operations.

A race condition exists because the ASO spinlock is released before
the hardware has finished processing WQE. If a second operation is
initiated immediately after, it overwrites the shared context in the
DMA area.

When the first operation's completion is processed later, it reads
this corrupted context, leading to unexpected behavior and incorrect
results.

This commit fixes the race by introducing a private context within
each IPSec offload object. The shared ASO context is now copied to
this private context while the ASO spinlock is held. Subsequent
processing uses this saved, per-object context, ensuring its integrity
is maintained.

Fixes: 1ed78fc03307 ("net/mlx5e: Update IPsec soft and hard limits")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260316094603.6999-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h    |  1 +
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c         | 17 ++++++++---------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index f8eaaf37963b..abcbd38db9db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -287,6 +287,7 @@ struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_dwork *dwork;
 	struct mlx5e_ipsec_limits limits;
 	u32 rx_mapped_id;
+	u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)];
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 33344e00719b..71222f7247f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -370,20 +370,18 @@ static void mlx5e_ipsec_aso_update_soft(struct mlx5e_ipsec_sa_entry *sa_entry,
 static void mlx5e_ipsec_handle_limits(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
-	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
-	struct mlx5e_ipsec_aso *aso = ipsec->aso;
 	bool soft_arm, hard_arm;
 	u64 hard_cnt;
 
 	lockdep_assert_held(&sa_entry->x->lock);
 
-	soft_arm = !MLX5_GET(ipsec_aso, aso->ctx, soft_lft_arm);
-	hard_arm = !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm);
+	soft_arm = !MLX5_GET(ipsec_aso, sa_entry->ctx, soft_lft_arm);
+	hard_arm = !MLX5_GET(ipsec_aso, sa_entry->ctx, hard_lft_arm);
 	if (!soft_arm && !hard_arm)
 		/* It is not lifetime event */
 		return;
 
-	hard_cnt = MLX5_GET(ipsec_aso, aso->ctx, remove_flow_pkt_cnt);
+	hard_cnt = MLX5_GET(ipsec_aso, sa_entry->ctx, remove_flow_pkt_cnt);
 	if (!hard_cnt || hard_arm) {
 		/* It is possible to see packet counter equal to zero without
 		 * hard limit event armed. Such situation can be if packet
@@ -454,10 +452,8 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 		container_of(_work, struct mlx5e_ipsec_work, work);
 	struct mlx5e_ipsec_sa_entry *sa_entry = work->data;
 	struct mlx5_accel_esp_xfrm_attrs *attrs;
-	struct mlx5e_ipsec_aso *aso;
 	int ret;
 
-	aso = sa_entry->ipsec->aso;
 	attrs = &sa_entry->attrs;
 
 	spin_lock_bh(&sa_entry->x->lock);
@@ -466,8 +462,9 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 		goto unlock;
 
 	if (attrs->replay_esn.trigger &&
-	    !MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) {
-		u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter);
+	    !MLX5_GET(ipsec_aso, sa_entry->ctx, esn_event_arm)) {
+		u32 mode_param = MLX5_GET(ipsec_aso, sa_entry->ctx,
+					  mode_parameter);
 
 		mlx5e_ipsec_update_esn_state(sa_entry, mode_param);
 	}
@@ -629,6 +626,8 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
 			/* We are in atomic context */
 			udelay(10);
 	} while (ret && time_is_after_jiffies(expires));
+	if (!ret)
+		memcpy(sa_entry->ctx, aso->ctx, MLX5_ST_SZ_BYTES(ipsec_aso));
 	spin_unlock_bh(&aso->lock);
 	return ret;
 }
-- 
cgit v1.2.3


From beb6e2e5976a128b0cccf10d158124422210c5ef Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 16 Mar 2026 11:46:03 +0200
Subject: net/mlx5e: Fix race condition during IPSec ESN update

In IPSec full offload mode, the device reports an ESN (Extended
Sequence Number) wrap event to the driver. The driver validates this
event by querying the IPSec ASO and checking that the esn_event_arm
field is 0x0, which indicates an event has occurred. After handling
the event, the driver must re-arm the context by setting esn_event_arm
back to 0x1.

A race condition exists in this handling path. After validating the
event, the driver calls mlx5_accel_esp_modify_xfrm() to update the
kernel's xfrm state. This function temporarily releases and
re-acquires the xfrm state lock.

So, need to acknowledge the event first by setting esn_event_arm to
0x1. This prevents the driver from reprocessing the same ESN update if
the hardware sends events for other reason. Since the next ESN update
only occurs after nearly 2^31 packets are received, there's no risk of
missing an update, as it will happen long after this handling has
finished.

Processing the event twice causes the ESN high-order bits (esn_msb) to
be incremented incorrectly. The driver then programs the hardware with
this invalid ESN state, which leads to anti-replay failures and a
complete halt of IPSec traffic.

Fix this by re-arming the ESN event immediately after it is validated,
before calling mlx5_accel_esp_modify_xfrm(). This ensures that any
spurious, duplicate events are correctly ignored, closing the race
window.

Fixes: fef06678931f ("net/mlx5e: Fix ESN update kernel panic")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260316094603.6999-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    | 33 +++++++++-------------
 1 file changed, 14 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 71222f7247f1..05faad5083d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -310,10 +310,11 @@ static void mlx5e_ipsec_aso_update(struct mlx5e_ipsec_sa_entry *sa_entry,
 	mlx5e_ipsec_aso_query(sa_entry, data);
 }
 
-static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
-					 u32 mode_param)
+static void
+mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
+			     u32 mode_param,
+			     struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-	struct mlx5_accel_esp_xfrm_attrs attrs = {};
 	struct mlx5_wqe_aso_ctrl_seg data = {};
 
 	if (mode_param < MLX5E_IPSEC_ESN_SCOPE_MID) {
@@ -323,18 +324,7 @@ static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
 		sa_entry->esn_state.overlap = 1;
 	}
 
-	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &attrs);
-
-	/* It is safe to execute the modify below unlocked since the only flows
-	 * that could affect this HW object, are create, destroy and this work.
-	 *
-	 * Creation flow can't co-exist with this modify work, the destruction
-	 * flow would cancel this work, and this work is a single entity that
-	 * can't conflict with it self.
-	 */
-	spin_unlock_bh(&sa_entry->x->lock);
-	mlx5_accel_esp_modify_xfrm(sa_entry, &attrs);
-	spin_lock_bh(&sa_entry->x->lock);
+	mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, attrs);
 
 	data.data_offset_condition_operand =
 		MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET;
@@ -451,7 +441,9 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 	struct mlx5e_ipsec_work *work =
 		container_of(_work, struct mlx5e_ipsec_work, work);
 	struct mlx5e_ipsec_sa_entry *sa_entry = work->data;
+	struct mlx5_accel_esp_xfrm_attrs tmp = {};
 	struct mlx5_accel_esp_xfrm_attrs *attrs;
+	bool need_modify = false;
 	int ret;
 
 	attrs = &sa_entry->attrs;
@@ -461,19 +453,22 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 	if (ret)
 		goto unlock;
 
+	if (attrs->lft.soft_packet_limit != XFRM_INF)
+		mlx5e_ipsec_handle_limits(sa_entry);
+
 	if (attrs->replay_esn.trigger &&
 	    !MLX5_GET(ipsec_aso, sa_entry->ctx, esn_event_arm)) {
 		u32 mode_param = MLX5_GET(ipsec_aso, sa_entry->ctx,
 					  mode_parameter);
 
-		mlx5e_ipsec_update_esn_state(sa_entry, mode_param);
+		mlx5e_ipsec_update_esn_state(sa_entry, mode_param, &tmp);
+		need_modify = true;
 	}
 
-	if (attrs->lft.soft_packet_limit != XFRM_INF)
-		mlx5e_ipsec_handle_limits(sa_entry);
-
 unlock:
 	spin_unlock_bh(&sa_entry->x->lock);
+	if (need_modify)
+		mlx5_accel_esp_modify_xfrm(sa_entry, &tmp);
 	kfree(work);
 }
 
-- 
cgit v1.2.3


From b3a6df291fecf5f8a308953b65ca72b7fc9e015d Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Mon, 16 Mar 2026 18:02:41 -0700
Subject: udp_tunnel: fix NULL deref caused by udp_sock_create6 when
 CONFIG_IPV6=n

When CONFIG_IPV6 is disabled, the udp_sock_create6() function returns 0
(success) without actually creating a socket. Callers such as
fou_create() then proceed to dereference the uninitialized socket
pointer, resulting in a NULL pointer dereference.

The captured NULL deref crash:
  BUG: kernel NULL pointer dereference, address: 0000000000000018
  RIP: 0010:fou_nl_add_doit (net/ipv4/fou_core.c:590 net/ipv4/fou_core.c:764)
  [...]
  Call Trace:
    <TASK>
    genl_family_rcv_msg_doit.constprop.0 (net/netlink/genetlink.c:1114)
    genl_rcv_msg (net/netlink/genetlink.c:1194 net/netlink/genetlink.c:1209)
    [...]
    netlink_rcv_skb (net/netlink/af_netlink.c:2550)
    genl_rcv (net/netlink/genetlink.c:1219)
    netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344)
    netlink_sendmsg (net/netlink/af_netlink.c:1894)
    __sock_sendmsg (net/socket.c:727 (discriminator 1) net/socket.c:742 (discriminator 1))
    __sys_sendto (./include/linux/file.h:62 (discriminator 1) ./include/linux/file.h:83 (discriminator 1) net/socket.c:2183 (discriminator 1))
    __x64_sys_sendto (net/socket.c:2213 (discriminator 1) net/socket.c:2209 (discriminator 1) net/socket.c:2209 (discriminator 1))
    do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
    entry_SYSCALL_64_after_hwframe (net/arch/x86/entry/entry_64.S:130)

This patch makes udp_sock_create6 return -EPFNOSUPPORT instead, so
callers correctly take their error paths. There is only one caller of
the vulnerable function and only privileged users can trigger it.

Fixes: fd384412e199b ("udp_tunnel: Seperate ipv6 functions into its own file.")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260317010241.1893893-1-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/udp_tunnel.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index d9c6d04bb3b5..fc1fc43345b5 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -52,7 +52,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg,
 				   struct socket **sockp)
 {
-	return 0;
+	return -EPFNOSUPPORT;
 }
 #endif
 
-- 
cgit v1.2.3


From 605b52497bf89b3b154674deb135da98f916e390 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Mon, 16 Mar 2026 17:50:34 -0700
Subject: net: bonding: fix NULL deref in bond_debug_rlb_hash_show

rlb_clear_slave intentionally keeps RLB hash-table entries on
the rx_hashtbl_used_head list with slave set to NULL when no
replacement slave is available. However, bond_debug_rlb_hash_show
visites client_info->slave without checking if it's NULL.

Other used-list iterators in bond_alb.c already handle this NULL-slave
state safely:

- rlb_update_client returns early on !client_info->slave
- rlb_req_update_slave_clients, rlb_clear_slave, and rlb_rebalance
compare slave values before visiting
- lb_req_update_subnet_clients continues if slave is NULL

The following NULL deref crash can be trigger in
bond_debug_rlb_hash_show:

[    1.289791] BUG: kernel NULL pointer dereference, address: 0000000000000000
[    1.292058] RIP: 0010:bond_debug_rlb_hash_show (drivers/net/bonding/bond_debugfs.c:41)
[    1.293101] RSP: 0018:ffffc900004a7d00 EFLAGS: 00010286
[    1.293333] RAX: 0000000000000000 RBX: ffff888102b48200 RCX: ffff888102b48204
[    1.293631] RDX: ffff888102b48200 RSI: ffffffff839daad5 RDI: ffff888102815078
[    1.293924] RBP: ffff888102815078 R08: ffff888102b4820e R09: 0000000000000000
[    1.294267] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888100f929c0
[    1.294564] R13: ffff888100f92a00 R14: 0000000000000001 R15: ffffc900004a7ed8
[    1.294864] FS:  0000000001395380(0000) GS:ffff888196e75000(0000) knlGS:0000000000000000
[    1.295239] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    1.295480] CR2: 0000000000000000 CR3: 0000000102adc004 CR4: 0000000000772ef0
[    1.295897] Call Trace:
[    1.296134]  seq_read_iter (fs/seq_file.c:231)
[    1.296341]  seq_read (fs/seq_file.c:164)
[    1.296493]  full_proxy_read (fs/debugfs/file.c:378 (discriminator 1))
[    1.296658]  vfs_read (fs/read_write.c:572)
[    1.296981]  ksys_read (fs/read_write.c:717)
[    1.297132]  do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
[    1.297325]  entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

Add a NULL check and print "(none)" for entries with no assigned slave.

Fixes: caafa84251b88 ("bonding: add the debugfs interface to see RLB hash table")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260317005034.1888794-1-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_debugfs.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 8adbec7c5084..8967b65f6d84 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -34,11 +34,17 @@ static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
 	for (; hash_index != RLB_NULL_INDEX;
 	     hash_index = client_info->used_next) {
 		client_info = &(bond_info->rx_hashtbl[hash_index]);
-		seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n",
-			&client_info->ip_src,
-			&client_info->ip_dst,
-			&client_info->mac_dst,
-			client_info->slave->dev->name);
+		if (client_info->slave)
+			seq_printf(m, "%-15pI4 %-15pI4 %-17pM %s\n",
+				   &client_info->ip_src,
+				   &client_info->ip_dst,
+				   &client_info->mac_dst,
+				   client_info->slave->dev->name);
+		else
+			seq_printf(m, "%-15pI4 %-15pI4 %-17pM (none)\n",
+				   &client_info->ip_src,
+				   &client_info->ip_dst,
+				   &client_info->mac_dst);
 	}
 
 	spin_unlock_bh(&bond->mode_lock);
-- 
cgit v1.2.3


From a343fb1e03cfc9f6dc83a5efb2a8d33e9cdaf6b9 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Tue, 17 Mar 2026 15:14:40 +0100
Subject: soc: qcom: pmic_glink_altmode: Fix TBT->SAFE->!TBT transition

Similar to the case of commit d48708500610 ("soc: qcom:
pmic_glink_altmode: Fix SVID=DP && unconnected edge case"), leaving the
TBT altmode makes pmic_glink_altmode report a SVID=TBT && mux_ctrl=0
message.

Said commit reordered the check such that the SVID is processed before
checking for NO_CONN. Rework this to take into account valid values of
mux_ctrl first and hopefully solve this for good..

Fixes: d48708500610 ("soc: qcom: pmic_glink_altmode: Fix SVID=DP && unconnected edge case")
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260317-topic-tbt_pg_fixup-v1-1-325b8647bc82@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/pmic_glink_altmode.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
index b496b88842a2..619bad2c27ee 100644
--- a/drivers/soc/qcom/pmic_glink_altmode.c
+++ b/drivers/soc/qcom/pmic_glink_altmode.c
@@ -62,6 +62,9 @@ struct usbc_notify {
 	u8 orientation;
 	u8 mux_ctrl;
 #define MUX_CTRL_STATE_NO_CONN			0
+#define MUX_CTRL_STATE_USB3_ONLY		1
+#define MUX_CTRL_STATE_DP4LN			2
+#define MUX_CTRL_STATE_USB3_DP			3
 #define MUX_CTRL_STATE_TUNNELING		4
 
 	u8 res;
@@ -350,9 +353,12 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 
 	typec_switch_set(alt_port->typec_switch, alt_port->orientation);
 
-	if (alt_port->svid == USB_TYPEC_TBT_SID) {
-		pmic_glink_altmode_enable_tbt(altmode, alt_port);
-	} else if (alt_port->svid == USB_TYPEC_DP_SID) {
+	/*
+	 * MUX_CTRL_STATE_DP4LN/USB3_DP may only be set if SVID=DP, but we need
+	 * to special-case the SVID=DP && mux_ctrl=NO_CONN case to deliver a
+	 * HPD notification
+	 */
+	if (alt_port->svid == USB_TYPEC_DP_SID) {
 		if (alt_port->mux_ctrl == MUX_CTRL_STATE_NO_CONN) {
 			pmic_glink_altmode_safe(altmode, alt_port);
 		} else {
@@ -369,11 +375,18 @@ static void pmic_glink_altmode_worker(struct work_struct *work)
 
 		drm_aux_hpd_bridge_notify(&alt_port->bridge->dev, conn_status);
 	} else if (alt_port->mux_ctrl == MUX_CTRL_STATE_TUNNELING) {
-		pmic_glink_altmode_enable_usb4(altmode, alt_port);
+		if (alt_port->svid == USB_TYPEC_TBT_SID)
+			pmic_glink_altmode_enable_tbt(altmode, alt_port);
+		else
+			pmic_glink_altmode_enable_usb4(altmode, alt_port);
+	} else if (alt_port->mux_ctrl == MUX_CTRL_STATE_USB3_ONLY) {
+		pmic_glink_altmode_enable_usb(altmode, alt_port);
 	} else if (alt_port->mux_ctrl == MUX_CTRL_STATE_NO_CONN) {
 		pmic_glink_altmode_safe(altmode, alt_port);
 	} else {
-		pmic_glink_altmode_enable_usb(altmode, alt_port);
+		dev_err(altmode->dev, "Got unknown mux_ctrl: %u on port %u, forcing safe mode\n",
+			alt_port->mux_ctrl, alt_port->index);
+		pmic_glink_altmode_safe(altmode, alt_port);
 	}
 
 	pmic_glink_altmode_request(altmode, ALTMODE_PAN_ACK, alt_port->index);
-- 
cgit v1.2.3


From 340bba73c545bfc7e8fcbc5ee4c02f85088f024d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 11 Mar 2026 20:30:25 +0100
Subject: pinctrl: intel: Improve capability support

The register space of a certain capability starts at the offset just after
the respective node in the capability list. It means that there are no fixed
offsets for them from SoC to SoC generation and they have to be calculated
at run-time. Improve capability support by adding the respective calculation
algorithm and in the result enable PWM on more platforms that currently may
use the wrong register.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 9d32bb8bc13a..adaa37a42754 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -53,8 +53,6 @@
 #define PADOWN_MASK(p)			(GENMASK(3, 0) << PADOWN_SHIFT(p))
 #define PADOWN_GPP(p)			((p) / 8)
 
-#define PWMC				0x204
-
 /* Offset from pad_regs */
 #define PADCFG0				0x000
 #define PADCFG0_RXEVCFG_MASK		GENMASK(26, 25)
@@ -1549,8 +1547,10 @@ static int intel_pinctrl_pm_init(struct intel_pinctrl *pctrl)
 }
 
 static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl,
-				   struct intel_community *community)
+				   struct intel_community *community,
+				   unsigned short capability_offset)
 {
+	void __iomem *base = community->regs + capability_offset + 4;
 	static const struct pwm_lpss_boardinfo info = {
 		.clk_rate = 19200000,
 		.npwm = 1,
@@ -1564,7 +1564,7 @@ static int intel_pinctrl_probe_pwm(struct intel_pinctrl *pctrl,
 	if (!IS_REACHABLE(CONFIG_PWM_LPSS))
 		return 0;
 
-	chip = devm_pwm_lpss_probe(pctrl->dev, community->regs + PWMC, &info);
+	chip = devm_pwm_lpss_probe(pctrl->dev, base, &info);
 	return PTR_ERR_OR_ZERO(chip);
 }
 
@@ -1595,6 +1595,7 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 
 	for (i = 0; i < pctrl->ncommunities; i++) {
 		struct intel_community *community = &pctrl->communities[i];
+		unsigned short capability_offset[6];
 		void __iomem *regs;
 		u32 offset;
 		u32 value;
@@ -1622,15 +1623,19 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 			switch ((value & CAPLIST_ID_MASK) >> CAPLIST_ID_SHIFT) {
 			case CAPLIST_ID_GPIO_HW_INFO:
 				community->features |= PINCTRL_FEATURE_GPIO_HW_INFO;
+				capability_offset[CAPLIST_ID_GPIO_HW_INFO] = offset;
 				break;
 			case CAPLIST_ID_PWM:
 				community->features |= PINCTRL_FEATURE_PWM;
+				capability_offset[CAPLIST_ID_PWM] = offset;
 				break;
 			case CAPLIST_ID_BLINK:
 				community->features |= PINCTRL_FEATURE_BLINK;
+				capability_offset[CAPLIST_ID_BLINK] = offset;
 				break;
 			case CAPLIST_ID_EXP:
 				community->features |= PINCTRL_FEATURE_EXP;
+				capability_offset[CAPLIST_ID_EXP] = offset;
 				break;
 			default:
 				break;
@@ -1653,7 +1658,7 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 		if (ret)
 			return ret;
 
-		ret = intel_pinctrl_probe_pwm(pctrl, community);
+		ret = intel_pinctrl_probe_pwm(pctrl, community, capability_offset[CAPLIST_ID_PWM]);
 		if (ret)
 			return ret;
 	}
-- 
cgit v1.2.3


From a4337a24d13e9e3b98a113e71d6b80dc5ed5f8c4 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 11 Mar 2026 18:14:04 +0100
Subject: pinctrl: intel: Fix the revision for new features (1kOhm PD, HW
 debouncer)

The 1kOhm pull down and hardware debouncer are features of the revision 0.92
of the Chassis specification. Fix that in the code accordingly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index adaa37a42754..a5a264ba6fbb 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1611,7 +1611,7 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 		value = readl(regs + REVID);
 		if (value == ~0u)
 			return -ENODEV;
-		if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) {
+		if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x92) {
 			community->features |= PINCTRL_FEATURE_DEBOUNCE;
 			community->features |= PINCTRL_FEATURE_1K_PD;
 		}
-- 
cgit v1.2.3


From 1ca468e78ea97c3365befdd408f71bda4b295134 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 11 Mar 2026 18:15:58 +0100
Subject: pinctrl: intel: Enable 3-bit PAD_OWN feature

Starting from revision 1.1 of the Chassis specification the PAD_OWN
is represented by 3 bits instead of 2 bits in the previous revisions.
Update the driver to support this feature.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 21 ++++++++++++++++-----
 drivers/pinctrl/intel/pinctrl-intel.h |  1 +
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index a5a264ba6fbb..97bf5ec78db4 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -203,19 +203,25 @@ static bool intel_pad_owned_by_host(const struct intel_pinctrl *pctrl, unsigned
 	community = intel_get_community(pctrl, pin);
 	if (!community)
 		return false;
-	if (!community->padown_offset)
+
+	/* If padown_offset is not provided, assume host ownership */
+	padown = community->regs + community->padown_offset;
+	if (padown == community->regs)
 		return true;
 
+	/* New HW generations have extended PAD_OWN registers */
+	if (community->features & PINCTRL_FEATURE_3BIT_PAD_OWN)
+		return !(readl(padown + pin_to_padno(community, pin) * 4) & 7);
+
 	padgrp = intel_community_get_padgroup(community, pin);
 	if (!padgrp)
 		return false;
 
 	gpp_offset = padgroup_offset(padgrp, pin);
 	gpp = PADOWN_GPP(gpp_offset);
-	offset = community->padown_offset + padgrp->padown_num * 4 + gpp * 4;
-	padown = community->regs + offset;
+	offset = padgrp->padown_num * 4 + gpp * 4;
 
-	return !(readl(padown) & PADOWN_MASK(gpp_offset));
+	return !(readl(padown + offset) & PADOWN_MASK(gpp_offset));
 }
 
 static bool intel_pad_acpi_mode(const struct intel_pinctrl *pctrl, unsigned int pin)
@@ -1597,6 +1603,7 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 		struct intel_community *community = &pctrl->communities[i];
 		unsigned short capability_offset[6];
 		void __iomem *regs;
+		u32 revision;
 		u32 offset;
 		u32 value;
 
@@ -1611,10 +1618,14 @@ int intel_pinctrl_probe(struct platform_device *pdev,
 		value = readl(regs + REVID);
 		if (value == ~0u)
 			return -ENODEV;
-		if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x92) {
+
+		revision = (value & REVID_MASK) >> REVID_SHIFT;
+		if (revision >= 0x092) {
 			community->features |= PINCTRL_FEATURE_DEBOUNCE;
 			community->features |= PINCTRL_FEATURE_1K_PD;
 		}
+		if (revision >= 0x110)
+			community->features |= PINCTRL_FEATURE_3BIT_PAD_OWN;
 
 		/* Determine community features based on the capabilities */
 		offset = CAPLIST;
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 2f37109d5860..b5476b9de0db 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -150,6 +150,7 @@ struct intel_community {
 #define PINCTRL_FEATURE_PWM		BIT(3)
 #define PINCTRL_FEATURE_BLINK		BIT(4)
 #define PINCTRL_FEATURE_EXP		BIT(5)
+#define PINCTRL_FEATURE_3BIT_PAD_OWN	BIT(6)
 
 #define __INTEL_COMMUNITY(b, s, e, g, n, gs, gn, soc)		\
 	{							\
-- 
cgit v1.2.3


From 24f90fa3994b992d1a09003a3db2599330a5232a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 17 Mar 2026 12:23:08 +0100
Subject: netfilter: bpf: defer hook memory release until rcu readers are done

Yiming Qian reports UaF when concurrent process is dumping hooks via
nfnetlink_hooks:

BUG: KASAN: slab-use-after-free in nfnl_hook_dump_one.isra.0+0xe71/0x10f0
Read of size 8 at addr ffff888003edbf88 by task poc/79
Call Trace:
 <TASK>
 nfnl_hook_dump_one.isra.0+0xe71/0x10f0
 netlink_dump+0x554/0x12b0
 nfnl_hook_get+0x176/0x230
 [..]

Defer release until after concurrent readers have completed.

Reported-by: Yiming Qian <yimingqian591@gmail.com>
Fixes: 84601d6ee68a ("bpf: add bpf_link support for BPF_NETFILTER programs")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_bpf_link.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index 6f3a6411f4af..c20031891b86 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -170,7 +170,7 @@ static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 
 static const struct bpf_link_ops bpf_nf_link_lops = {
 	.release = bpf_nf_link_release,
-	.dealloc = bpf_nf_link_dealloc,
+	.dealloc_deferred = bpf_nf_link_dealloc,
 	.detach = bpf_nf_link_detach,
 	.show_fdinfo = bpf_nf_link_show_info,
 	.fill_link_info = bpf_nf_link_fill_link_info,
-- 
cgit v1.2.3


From d73f4b53aaaea4c95f245e491aa5eeb8a21874ce Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 17 Mar 2026 20:00:26 +0100
Subject: netfilter: nf_tables: release flowtable after rcu grace period on
 error

Call synchronize_rcu() after unregistering the hooks from error path,
since a hook that already refers to this flowtable can be already
registered, exposing this flowtable to packet path and nfnetlink_hook
control plane.

This error path is rare, it should only happen by reaching the maximum
number hooks or by failing to set up to hardware offload, just call
synchronize_rcu().

There is a check for already used device hooks by different flowtable
that could result in EEXIST at this late stage. The hook parser can be
updated to perform this check earlier to this error path really becomes
rarely exercised.

Uncovered by KASAN reported as use-after-free from nfnetlink_hook path
when dumping hooks.

Fixes: 3b49e2e94e6e ("netfilter: nf_tables: add flow table netlink frontend")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9b1c8d0a35fb..3922cff1bb3d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9203,6 +9203,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb,
 	return 0;
 
 err_flowtable_hooks:
+	synchronize_rcu();
 	nft_trans_destroy(trans);
 err_flowtable_trans:
 	nft_hooks_destroy(&flowtable->hook_list);
-- 
cgit v1.2.3


From dbdfaae9609629a9569362e3b8f33d0a20fd783c Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Thu, 19 Mar 2026 15:32:44 +0800
Subject: nfnetlink_osf: validate individual option lengths in fingerprints

nfnl_osf_add_callback() validates opt_num bounds and string
NUL-termination but does not check individual option length fields.
A zero-length option causes nf_osf_match_one() to enter the option
matching loop even when foptsize sums to zero, which matches packets
with no TCP options where ctx->optp is NULL:

 Oops: general protection fault
 KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
 RIP: 0010:nf_osf_match_one (net/netfilter/nfnetlink_osf.c:98)
 Call Trace:
  nf_osf_match (net/netfilter/nfnetlink_osf.c:227)
  xt_osf_match_packet (net/netfilter/xt_osf.c:32)
  ipt_do_table (net/ipv4/netfilter/ip_tables.c:293)
  nf_hook_slow (net/netfilter/core.c:623)
  ip_local_deliver (net/ipv4/ip_input.c:262)
  ip_rcv (net/ipv4/ip_input.c:573)

Additionally, an MSS option (kind=2) with length < 4 causes
out-of-bounds reads when nf_osf_match_one() unconditionally accesses
optp[2] and optp[3] for MSS value extraction.  While RFC 9293
section 3.2 specifies that the MSS option is always exactly 4
bytes (Kind=2, Length=4), the check uses "< 4" rather than
"!= 4" because lengths greater than 4 do not cause memory
safety issues -- the buffer is guaranteed to be at least
foptsize bytes by the ctx->optsize == foptsize check.

Reject fingerprints where any option has zero length, or where an MSS
option has length less than 4, at add time rather than trusting these
values in the packet matching hot path.

Fixes: 11eeef41d5f6 ("netfilter: passive OS fingerprint xtables match")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_osf.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 94e3eac5743a..45d9ad231a92 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -302,7 +302,9 @@ static int nfnl_osf_add_callback(struct sk_buff *skb,
 {
 	struct nf_osf_user_finger *f;
 	struct nf_osf_finger *kf = NULL, *sf;
+	unsigned int tot_opt_len = 0;
 	int err = 0;
+	int i;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -318,6 +320,17 @@ static int nfnl_osf_add_callback(struct sk_buff *skb,
 	if (f->opt_num > ARRAY_SIZE(f->opt))
 		return -EINVAL;
 
+	for (i = 0; i < f->opt_num; i++) {
+		if (!f->opt[i].length || f->opt[i].length > MAX_IPOPTLEN)
+			return -EINVAL;
+		if (f->opt[i].kind == OSFOPT_MSS && f->opt[i].length < 4)
+			return -EINVAL;
+
+		tot_opt_len += f->opt[i].length;
+		if (tot_opt_len > MAX_IPOPTLEN)
+			return -EINVAL;
+	}
+
 	if (!memchr(f->genre, 0, MAXGENRELEN) ||
 	    !memchr(f->subtype, 0, MAXGENRELEN) ||
 	    !memchr(f->version, 0, MAXGENRELEN))
-- 
cgit v1.2.3


From 8a63baadf08453f66eb582fdb6dd234f72024723 Mon Sep 17 00:00:00 2001
From: Muhammad Hammad Ijaz <mhijaz@amazon.com>
Date: Mon, 16 Mar 2026 12:31:01 -0700
Subject: net: mvpp2: guard flow control update with global_tx_fc in buffer
 switching

mvpp2_bm_switch_buffers() unconditionally calls
mvpp2_bm_pool_update_priv_fc() when switching between per-cpu and
shared buffer pool modes. This function programs CM3 flow control
registers via mvpp2_cm3_read()/mvpp2_cm3_write(), which dereference
priv->cm3_base without any NULL check.

When the CM3 SRAM resource is not present in the device tree (the
third reg entry added by commit 60523583b07c ("dts: marvell: add CM3
SRAM memory to cp11x ethernet device tree")), priv->cm3_base remains
NULL and priv->global_tx_fc is false. Any operation that triggers
mvpp2_bm_switch_buffers(), for example an MTU change that crosses
the jumbo frame threshold, will crash:

  Unable to handle kernel NULL pointer dereference at
  virtual address 0000000000000000
  Mem abort info:
    ESR = 0x0000000096000006
    EC = 0x25: DABT (current EL), IL = 32 bits
  pc : readl+0x0/0x18
  lr : mvpp2_cm3_read.isra.0+0x14/0x20
  Call trace:
   readl+0x0/0x18
   mvpp2_bm_pool_update_fc+0x40/0x12c
   mvpp2_bm_pool_update_priv_fc+0x94/0xd8
   mvpp2_bm_switch_buffers.isra.0+0x80/0x1c0
   mvpp2_change_mtu+0x140/0x380
   __dev_set_mtu+0x1c/0x38
   dev_set_mtu_ext+0x78/0x118
   dev_set_mtu+0x48/0xa8
   dev_ifsioc+0x21c/0x43c
   dev_ioctl+0x2d8/0x42c
   sock_ioctl+0x314/0x378

Every other flow control call site in the driver already guards
hardware access with either priv->global_tx_fc or port->tx_fc.
mvpp2_bm_switch_buffers() is the only place that omits this check.

Add the missing priv->global_tx_fc guard to both the disable and
re-enable calls in mvpp2_bm_switch_buffers(), consistent with the
rest of the driver.

Fixes: 3a616b92a9d1 ("net: mvpp2: Add TX flow control support for jumbo frames")
Signed-off-by: Muhammad Hammad Ijaz <mhijaz@amazon.com>
Reviewed-by: Gunnar Kudrjavets <gunnarku@amazon.com>
Link: https://patch.msgid.link/20260316193157.65748-1-mhijaz@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index d1b8650cb4b4..f442b874bb59 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5016,7 +5016,7 @@ static int mvpp2_bm_switch_buffers(struct mvpp2 *priv, bool percpu)
 	if (priv->percpu_pools)
 		numbufs = port->nrxqs * 2;
 
-	if (change_percpu)
+	if (change_percpu && priv->global_tx_fc)
 		mvpp2_bm_pool_update_priv_fc(priv, false);
 
 	for (i = 0; i < numbufs; i++)
@@ -5041,7 +5041,7 @@ static int mvpp2_bm_switch_buffers(struct mvpp2 *priv, bool percpu)
 			mvpp2_open(port->dev);
 	}
 
-	if (change_percpu)
+	if (change_percpu && priv->global_tx_fc)
 		mvpp2_bm_pool_update_priv_fc(priv, true);
 
 	return 0;
-- 
cgit v1.2.3


From 8fb6857f2f5e35179ff35e7d25358b9add681b7e Mon Sep 17 00:00:00 2001
From: Jori Koolstra <jkoolstra@xs4all.nl>
Date: Wed, 18 Mar 2026 21:39:52 +0100
Subject: vfs: fix docstring of hash_name()

The docstring of hash_name() is falsely reporting that it returns the
component length, whereas it returns a pointer to the terminating '/'
or NUL character in the pathname being resolved.

Signed-off-by: Jori Koolstra <jkoolstra@xs4all.nl>
Link: https://patch.msgid.link/20260318203953.5770-1-jkoolstra@xs4all.nl
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namei.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 58f715f7657e..9e5500dad14f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2437,8 +2437,14 @@ inside:
 EXPORT_SYMBOL(hashlen_string);
 
 /*
- * Calculate the length and hash of the path component, and
- * return the length as the result.
+ * hash_name - Calculate the length and hash of the path component
+ * @nd: the path resolution state
+ * @name: the pathname to read the component from
+ * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT,
+ * LAST_WORD_IS_DOTDOT, or some other value depending on whether the
+ * component is '.', '..', or something else. Otherwise, @lastword is 0.
+ *
+ * Returns: a pointer to the terminating '/' or NUL character in @name.
  */
 static inline const char *hash_name(struct nameidata *nd,
 				    const char *name,
-- 
cgit v1.2.3


From 7e57523490cd2efb52b1ea97f2e0a74c0fb634cd Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 18 Mar 2026 15:38:58 +0000
Subject: netfs: Fix read abandonment during retry

Under certain circumstances, all the remaining subrequests from a read
request will get abandoned during retry.  The abandonment process expects
the 'subreq' variable to be set to the place to start abandonment from, but
it doesn't always have a useful value (it will be uninitialised on the
first pass through the loop and it may point to a deleted subrequest on
later passes).

Fix the first jump to "abandon:" to set subreq to the start of the first
subrequest expected to need retry (which, in this abandonment case, turned
out unexpectedly to no longer have NEED_RETRY set).

Also clear the subreq pointer after discarding superfluous retryable
subrequests to cause an oops if we do try to access it.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/3775287.1773848338@warthog.procyon.org.uk
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/read_retry.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index 7793ba5e3e8f..cca9ac43c077 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -93,8 +93,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq)
 		       from->start, from->transferred, from->len);
 
 		if (test_bit(NETFS_SREQ_FAILED, &from->flags) ||
-		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags))
+		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) {
+			subreq = from;
 			goto abandon;
+		}
 
 		list_for_each_continue(next, &stream->subrequests) {
 			subreq = list_entry(next, struct netfs_io_subrequest, rreq_link);
@@ -178,6 +180,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq)
 				if (subreq == to)
 					break;
 			}
+			subreq = NULL;
 			continue;
 		}
 
-- 
cgit v1.2.3


From 8c6e9b60f5c7985a9fe41320556a92d7a33451df Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Mon, 16 Mar 2026 16:19:01 +0000
Subject: arm64: realm: Fix PTE_NS_SHARED for 52bit PA support

With LPA/LPA2, the top bits of the PFN (Bits[51:48]) end up in the lower bits
of the PTE. So, simply creating a mask of the "top IPA bit" doesn't work well
for these configurations to set the "top" bit at the output of Stage1
translation.

Fix this by using the __phys_to_pte_val() to do the right thing for all
configurations.

Tested using, kvmtool, placing the memory at a higher address (-m <size>@<Addr>).

 e.g:
 # lkvm run --realm -c 4 -m 512M@@128T -k Image --console serial

 sh-5.0# dmesg | grep "LPA2\|RSI"
[    0.000000] RME: Using RSI version 1.0
[    0.000000] CPU features: detected: 52-bit Virtual Addressing (LPA2)
[    0.777354] CPU features: detected: 52-bit Virtual Addressing for KVM (LPA2)

Fixes: 399306954996 ("arm64: realm: Query IPA size from the RMM")
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/rsi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c
index c64a06f58c0b..9e846ce4ef9c 100644
--- a/arch/arm64/kernel/rsi.c
+++ b/arch/arm64/kernel/rsi.c
@@ -12,6 +12,7 @@
 
 #include <asm/io.h>
 #include <asm/mem_encrypt.h>
+#include <asm/pgtable.h>
 #include <asm/rsi.h>
 
 static struct realm_config config;
@@ -146,7 +147,7 @@ void __init arm64_rsi_init(void)
 		return;
 	if (WARN_ON(rsi_get_realm_config(&config)))
 		return;
-	prot_ns_shared = BIT(config.ipa_bits - 1);
+	prot_ns_shared = __phys_to_pte_val(BIT(config.ipa_bits - 1));
 
 	if (arm64_ioremap_prot_hook_register(realm_ioremap_hook))
 		return;
-- 
cgit v1.2.3


From 0f9ea7141f365b4f27226898e62220fb98ef8dc6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 17 Mar 2026 09:10:13 -0700
Subject: net: shaper: protect late read accesses to the hierarchy

We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.

This is not proper, a conversion from a ref to a locked netdev
must include a liveness check (a check if the netdev hasn't been
unregistered already). Fix the read cases (those under RCU).
Writes needs a separate change to protect from creating the
hierarchy after flush has already run.

Fixes: 4b623f9f0f59 ("net-shapers: implement NL get operation")
Reported-by: Paul Moses <p@1g4.org>
Link: https://lore.kernel.org/20260309173450.538026-1-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20260317161014.779569-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/shaper/shaper.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
index 3fd6629cb999..6b4c87e12f1f 100644
--- a/net/shaper/shaper.c
+++ b/net/shaper/shaper.c
@@ -65,6 +65,21 @@ net_shaper_hierarchy(struct net_shaper_binding *binding)
 	return NULL;
 }
 
+static struct net_shaper_hierarchy *
+net_shaper_hierarchy_rcu(struct net_shaper_binding *binding)
+{
+	/* Readers look up the device and take a ref, then take RCU lock
+	 * later at which point netdev may have been unregistered and flushed.
+	 * READ_ONCE() pairs with WRITE_ONCE() in net_shaper_hierarchy_setup.
+	 */
+	if (binding->type == NET_SHAPER_BINDING_TYPE_NETDEV &&
+	    READ_ONCE(binding->netdev->reg_state) <= NETREG_REGISTERED)
+		return READ_ONCE(binding->netdev->net_shaper_hierarchy);
+
+	/* No other type supported yet. */
+	return NULL;
+}
+
 static const struct net_shaper_ops *
 net_shaper_ops(struct net_shaper_binding *binding)
 {
@@ -251,9 +266,10 @@ static struct net_shaper *
 net_shaper_lookup(struct net_shaper_binding *binding,
 		  const struct net_shaper_handle *handle)
 {
-	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
 	u32 index = net_shaper_handle_to_index(handle);
+	struct net_shaper_hierarchy *hierarchy;
 
+	hierarchy = net_shaper_hierarchy_rcu(binding);
 	if (!hierarchy || xa_get_mark(&hierarchy->shapers, index,
 				      NET_SHAPER_NOT_VALID))
 		return NULL;
@@ -778,17 +794,19 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb,
 
 	/* Don't error out dumps performed before any set operation. */
 	binding = net_shaper_binding_from_ctx(ctx);
-	hierarchy = net_shaper_hierarchy(binding);
-	if (!hierarchy)
-		return 0;
 
 	rcu_read_lock();
+	hierarchy = net_shaper_hierarchy_rcu(binding);
+	if (!hierarchy)
+		goto out_unlock;
+
 	for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index,
 				 U32_MAX, XA_PRESENT)); ctx->start_index++) {
 		ret = net_shaper_fill_one(skb, binding, shaper, info);
 		if (ret)
 			break;
 	}
+out_unlock:
 	rcu_read_unlock();
 
 	return ret;
-- 
cgit v1.2.3


From d75ec7e8ba1979a1eb0b9211d94d749cdce849c8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 17 Mar 2026 09:10:14 -0700
Subject: net: shaper: protect from late creation of hierarchy

We look up a netdev during prep of Netlink ops (pre- callbacks)
and take a ref to it. Then later in the body of the callback
we take its lock or RCU which are the actual protections.

The netdev may get unregistered in between the time we take
the ref and the time we lock it. We may allocate the hierarchy
after flush has already run, which would lead to a leak.

Take the instance lock in pre- already, this saves us from the race
and removes the need for dedicated lock/unlock callbacks completely.
After all, if there's any chance of write happening concurrently
with the flush - we're back to leaking the hierarchy.

We may take the lock for devices which don't support shapers but
we're only dealing with SET operations here, not taking the lock
would be optimizing for an error case.

Fixes: 93954b40f6a4 ("net-shapers: implement NL set and delete operations")
Link: https://lore.kernel.org/20260309173450.538026-1-p@1g4.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20260317161014.779569-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/net_shaper.yaml |  12 +--
 net/shaper/shaper.c                         | 134 +++++++++++++++-------------
 net/shaper/shaper_nl_gen.c                  |  12 +--
 net/shaper/shaper_nl_gen.h                  |   5 ++
 4 files changed, 89 insertions(+), 74 deletions(-)

diff --git a/Documentation/netlink/specs/net_shaper.yaml b/Documentation/netlink/specs/net_shaper.yaml
index 0b1b54be48f9..3f2ad772b64b 100644
--- a/Documentation/netlink/specs/net_shaper.yaml
+++ b/Documentation/netlink/specs/net_shaper.yaml
@@ -247,8 +247,8 @@ operations:
       flags: [admin-perm]
 
       do:
-        pre: net-shaper-nl-pre-doit
-        post: net-shaper-nl-post-doit
+        pre: net-shaper-nl-pre-doit-write
+        post: net-shaper-nl-post-doit-write
         request:
           attributes:
             - ifindex
@@ -278,8 +278,8 @@ operations:
       flags: [admin-perm]
 
       do:
-        pre: net-shaper-nl-pre-doit
-        post: net-shaper-nl-post-doit
+        pre: net-shaper-nl-pre-doit-write
+        post: net-shaper-nl-post-doit-write
         request:
           attributes: *ns-binding
 
@@ -309,8 +309,8 @@ operations:
       flags: [admin-perm]
 
       do:
-        pre: net-shaper-nl-pre-doit
-        post: net-shaper-nl-post-doit
+        pre: net-shaper-nl-pre-doit-write
+        post: net-shaper-nl-post-doit-write
         request:
           attributes:
             - ifindex
diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
index 6b4c87e12f1f..94bc9c7382ea 100644
--- a/net/shaper/shaper.c
+++ b/net/shaper/shaper.c
@@ -36,24 +36,6 @@ static struct net_shaper_binding *net_shaper_binding_from_ctx(void *ctx)
 	return &((struct net_shaper_nl_ctx *)ctx)->binding;
 }
 
-static void net_shaper_lock(struct net_shaper_binding *binding)
-{
-	switch (binding->type) {
-	case NET_SHAPER_BINDING_TYPE_NETDEV:
-		netdev_lock(binding->netdev);
-		break;
-	}
-}
-
-static void net_shaper_unlock(struct net_shaper_binding *binding)
-{
-	switch (binding->type) {
-	case NET_SHAPER_BINDING_TYPE_NETDEV:
-		netdev_unlock(binding->netdev);
-		break;
-	}
-}
-
 static struct net_shaper_hierarchy *
 net_shaper_hierarchy(struct net_shaper_binding *binding)
 {
@@ -219,12 +201,49 @@ static int net_shaper_ctx_setup(const struct genl_info *info, int type,
 	return 0;
 }
 
+/* Like net_shaper_ctx_setup(), but for "write" handlers (never for dumps!)
+ * Acquires the lock protecting the hierarchy (instance lock for netdev).
+ */
+static int net_shaper_ctx_setup_lock(const struct genl_info *info, int type,
+				     struct net_shaper_nl_ctx *ctx)
+{
+	struct net *ns = genl_info_net(info);
+	struct net_device *dev;
+	int ifindex;
+
+	if (GENL_REQ_ATTR_CHECK(info, type))
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[type]);
+	dev = netdev_get_by_index_lock(ns, ifindex);
+	if (!dev) {
+		NL_SET_BAD_ATTR(info->extack, info->attrs[type]);
+		return -ENOENT;
+	}
+
+	if (!dev->netdev_ops->net_shaper_ops) {
+		NL_SET_BAD_ATTR(info->extack, info->attrs[type]);
+		netdev_unlock(dev);
+		return -EOPNOTSUPP;
+	}
+
+	ctx->binding.type = NET_SHAPER_BINDING_TYPE_NETDEV;
+	ctx->binding.netdev = dev;
+	return 0;
+}
+
 static void net_shaper_ctx_cleanup(struct net_shaper_nl_ctx *ctx)
 {
 	if (ctx->binding.type == NET_SHAPER_BINDING_TYPE_NETDEV)
 		netdev_put(ctx->binding.netdev, &ctx->dev_tracker);
 }
 
+static void net_shaper_ctx_cleanup_unlock(struct net_shaper_nl_ctx *ctx)
+{
+	if (ctx->binding.type == NET_SHAPER_BINDING_TYPE_NETDEV)
+		netdev_unlock(ctx->binding.netdev);
+}
+
 static u32 net_shaper_handle_to_index(const struct net_shaper_handle *handle)
 {
 	return FIELD_PREP(NET_SHAPER_SCOPE_MASK, handle->scope) |
@@ -278,7 +297,7 @@ net_shaper_lookup(struct net_shaper_binding *binding,
 }
 
 /* Allocate on demand the per device shaper's hierarchy container.
- * Called under the net shaper lock
+ * Called under the lock protecting the hierarchy (instance lock for netdev)
  */
 static struct net_shaper_hierarchy *
 net_shaper_hierarchy_setup(struct net_shaper_binding *binding)
@@ -697,6 +716,22 @@ void net_shaper_nl_post_doit(const struct genl_split_ops *ops,
 	net_shaper_generic_post(info);
 }
 
+int net_shaper_nl_pre_doit_write(const struct genl_split_ops *ops,
+				struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_shaper_nl_ctx *ctx = (struct net_shaper_nl_ctx *)info->ctx;
+
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(info->ctx));
+
+	return net_shaper_ctx_setup_lock(info, NET_SHAPER_A_IFINDEX, ctx);
+}
+
+void net_shaper_nl_post_doit_write(const struct genl_split_ops *ops,
+				   struct sk_buff *skb, struct genl_info *info)
+{
+	net_shaper_ctx_cleanup_unlock((struct net_shaper_nl_ctx *)info->ctx);
+}
+
 int net_shaper_nl_pre_dumpit(struct netlink_callback *cb)
 {
 	struct net_shaper_nl_ctx *ctx = (struct net_shaper_nl_ctx *)cb->ctx;
@@ -824,45 +859,38 @@ int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info)
 
 	binding = net_shaper_binding_from_ctx(info->ctx);
 
-	net_shaper_lock(binding);
 	ret = net_shaper_parse_info(binding, info->attrs, info, &shaper,
 				    &exists);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	if (!exists)
 		net_shaper_default_parent(&shaper.handle, &shaper.parent);
 
 	hierarchy = net_shaper_hierarchy_setup(binding);
-	if (!hierarchy) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!hierarchy)
+		return -ENOMEM;
 
 	/* The 'set' operation can't create node-scope shapers. */
 	handle = shaper.handle;
 	if (handle.scope == NET_SHAPER_SCOPE_NODE &&
-	    !net_shaper_lookup(binding, &handle)) {
-		ret = -ENOENT;
-		goto unlock;
-	}
+	    !net_shaper_lookup(binding, &handle))
+		return -ENOENT;
 
 	ret = net_shaper_pre_insert(binding, &handle, info->extack);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	ops = net_shaper_ops(binding);
 	ret = ops->set(binding, &shaper, info->extack);
 	if (ret) {
 		net_shaper_rollback(binding);
-		goto unlock;
+		return ret;
 	}
 
 	net_shaper_commit(binding, 1, &shaper);
 
-unlock:
-	net_shaper_unlock(binding);
-	return ret;
+	return 0;
 }
 
 static int __net_shaper_delete(struct net_shaper_binding *binding,
@@ -1090,35 +1118,26 @@ int net_shaper_nl_delete_doit(struct sk_buff *skb, struct genl_info *info)
 
 	binding = net_shaper_binding_from_ctx(info->ctx);
 
-	net_shaper_lock(binding);
 	ret = net_shaper_parse_handle(info->attrs[NET_SHAPER_A_HANDLE], info,
 				      &handle);
 	if (ret)
-		goto unlock;
+		return ret;
 
 	hierarchy = net_shaper_hierarchy(binding);
-	if (!hierarchy) {
-		ret = -ENOENT;
-		goto unlock;
-	}
+	if (!hierarchy)
+		return -ENOENT;
 
 	shaper = net_shaper_lookup(binding, &handle);
-	if (!shaper) {
-		ret = -ENOENT;
-		goto unlock;
-	}
+	if (!shaper)
+		return -ENOENT;
 
 	if (handle.scope == NET_SHAPER_SCOPE_NODE) {
 		ret = net_shaper_pre_del_node(binding, shaper, info->extack);
 		if (ret)
-			goto unlock;
+			return ret;
 	}
 
-	ret = __net_shaper_delete(binding, shaper, info->extack);
-
-unlock:
-	net_shaper_unlock(binding);
-	return ret;
+	return __net_shaper_delete(binding, shaper, info->extack);
 }
 
 static int net_shaper_group_send_reply(struct net_shaper_binding *binding,
@@ -1167,21 +1186,17 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 	if (!net_shaper_ops(binding)->group)
 		return -EOPNOTSUPP;
 
-	net_shaper_lock(binding);
 	leaves_count = net_shaper_list_len(info, NET_SHAPER_A_LEAVES);
 	if (!leaves_count) {
 		NL_SET_BAD_ATTR(info->extack,
 				info->attrs[NET_SHAPER_A_LEAVES]);
-		ret = -EINVAL;
-		goto unlock;
+		return -EINVAL;
 	}
 
 	leaves = kcalloc(leaves_count, sizeof(struct net_shaper) +
 			 sizeof(struct net_shaper *), GFP_KERNEL);
-	if (!leaves) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!leaves)
+		return -ENOMEM;
 	old_nodes = (void *)&leaves[leaves_count];
 
 	ret = net_shaper_parse_node(binding, info->attrs, info, &node);
@@ -1258,9 +1273,6 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 
 free_leaves:
 	kfree(leaves);
-
-unlock:
-	net_shaper_unlock(binding);
 	return ret;
 
 free_msg:
@@ -1370,14 +1382,12 @@ static void net_shaper_flush(struct net_shaper_binding *binding)
 	if (!hierarchy)
 		return;
 
-	net_shaper_lock(binding);
 	xa_lock(&hierarchy->shapers);
 	xa_for_each(&hierarchy->shapers, index, cur) {
 		__xa_erase(&hierarchy->shapers, index);
 		kfree(cur);
 	}
 	xa_unlock(&hierarchy->shapers);
-	net_shaper_unlock(binding);
 
 	kfree(hierarchy);
 }
diff --git a/net/shaper/shaper_nl_gen.c b/net/shaper/shaper_nl_gen.c
index e8cccc4c1180..9b29be3ef19a 100644
--- a/net/shaper/shaper_nl_gen.c
+++ b/net/shaper/shaper_nl_gen.c
@@ -99,27 +99,27 @@ static const struct genl_split_ops net_shaper_nl_ops[] = {
 	},
 	{
 		.cmd		= NET_SHAPER_CMD_SET,
-		.pre_doit	= net_shaper_nl_pre_doit,
+		.pre_doit	= net_shaper_nl_pre_doit_write,
 		.doit		= net_shaper_nl_set_doit,
-		.post_doit	= net_shaper_nl_post_doit,
+		.post_doit	= net_shaper_nl_post_doit_write,
 		.policy		= net_shaper_set_nl_policy,
 		.maxattr	= NET_SHAPER_A_IFINDEX,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= NET_SHAPER_CMD_DELETE,
-		.pre_doit	= net_shaper_nl_pre_doit,
+		.pre_doit	= net_shaper_nl_pre_doit_write,
 		.doit		= net_shaper_nl_delete_doit,
-		.post_doit	= net_shaper_nl_post_doit,
+		.post_doit	= net_shaper_nl_post_doit_write,
 		.policy		= net_shaper_delete_nl_policy,
 		.maxattr	= NET_SHAPER_A_IFINDEX,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
 		.cmd		= NET_SHAPER_CMD_GROUP,
-		.pre_doit	= net_shaper_nl_pre_doit,
+		.pre_doit	= net_shaper_nl_pre_doit_write,
 		.doit		= net_shaper_nl_group_doit,
-		.post_doit	= net_shaper_nl_post_doit,
+		.post_doit	= net_shaper_nl_post_doit_write,
 		.policy		= net_shaper_group_nl_policy,
 		.maxattr	= NET_SHAPER_A_LEAVES,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
diff --git a/net/shaper/shaper_nl_gen.h b/net/shaper/shaper_nl_gen.h
index ec41c90431a4..42c46c52c775 100644
--- a/net/shaper/shaper_nl_gen.h
+++ b/net/shaper/shaper_nl_gen.h
@@ -18,12 +18,17 @@ extern const struct nla_policy net_shaper_leaf_info_nl_policy[NET_SHAPER_A_WEIGH
 
 int net_shaper_nl_pre_doit(const struct genl_split_ops *ops,
 			   struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_pre_doit_write(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_cap_pre_doit(const struct genl_split_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info);
 void
 net_shaper_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
 void
+net_shaper_nl_post_doit_write(const struct genl_split_ops *ops,
+			      struct sk_buff *skb, struct genl_info *info);
+void
 net_shaper_nl_cap_post_doit(const struct genl_split_ops *ops,
 			    struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_pre_dumpit(struct netlink_callback *cb);
-- 
cgit v1.2.3


From a437601a0a1383260222223440a95dd4322eb7fa Mon Sep 17 00:00:00 2001
From: Baojun Xu <baojun.xu@ti.com>
Date: Thu, 19 Mar 2026 17:07:47 +0800
Subject: ASoC: tas2781: Add null check for calibration data

For avoid null pointer problem if no calibration data exist.

Fixes: 55137f5a68b5e ("ASoC: tas2781: Put three different calibrated data solution into the same data structure")

Signed-off-by: Baojun Xu <baojun.xu@ti.com>
Link: https://patch.msgid.link/20260319090747.2090-1-baojun.xu@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2781-fmwlib.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
index 5798d518d94c..a1d86bd309f4 100644
--- a/sound/soc/codecs/tas2781-fmwlib.c
+++ b/sound/soc/codecs/tas2781-fmwlib.c
@@ -2550,6 +2550,9 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
 	int k = i * (cali_data->cali_dat_sz_per_dev + 1);
 	int rc;
 
+	if (!data || !cali_data->total_sz)
+		return;
+
 	if (data[k] != i) {
 		dev_err(priv->dev, "%s: no cal-data for dev %d from usr-spc\n",
 			__func__, i);
-- 
cgit v1.2.3


From 9b72283ec9b8685acdb3467de8fbc3352fdb70bb Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Mon, 2 Mar 2026 16:17:33 -0800
Subject: drm/xe/guc: Fail immediately on GuC load error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

By using the same variable for both the return of poll_timeout_us and
the return of the polled function guc_wait_ucode, the return value of
the latter is overwritten and lost after exiting the polling loop. Since
guc_wait_ucode returns -1 on GuC load failure, we lose that information
and always continue as if the GuC had been loaded correctly.

This is fixed by simply using 2 separate variables.

Fixes: a4916b4da448 ("drm/xe/guc: Refactor GuC load to use poll_timeout_us()")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://patch.msgid.link/20260303001732.2540493-2-daniele.ceraolospurio@intel.com
(cherry picked from commit c85ec5c5753a46b5c2aea1292536487be9470ffe)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 6df7c3f260e5..b0a3cddaa2ea 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -1124,14 +1124,14 @@ static int guc_wait_ucode(struct xe_guc *guc)
 	struct xe_guc_pc *guc_pc = &gt->uc.guc.pc;
 	u32 before_freq, act_freq, cur_freq;
 	u32 status = 0, tries = 0;
+	int load_result, ret;
 	ktime_t before;
 	u64 delta_ms;
-	int ret;
 
 	before_freq = xe_guc_pc_get_act_freq(guc_pc);
 	before = ktime_get();
 
-	ret = poll_timeout_us(ret = guc_load_done(gt, &status, &tries), ret,
+	ret = poll_timeout_us(load_result = guc_load_done(gt, &status, &tries), load_result,
 			      10 * USEC_PER_MSEC,
 			      GUC_LOAD_TIMEOUT_SEC * USEC_PER_SEC, false);
 
@@ -1139,7 +1139,7 @@ static int guc_wait_ucode(struct xe_guc *guc)
 	act_freq = xe_guc_pc_get_act_freq(guc_pc);
 	cur_freq = xe_guc_pc_get_cur_freq_fw(guc_pc);
 
-	if (ret) {
+	if (ret || load_result <= 0) {
 		xe_gt_err(gt, "load failed: status = 0x%08X, time = %lldms, freq = %dMHz (req %dMHz)\n",
 			  status, delta_ms, xe_guc_pc_get_act_freq(guc_pc),
 			  xe_guc_pc_get_cur_freq_fw(guc_pc));
-- 
cgit v1.2.3


From 26c638d5602e329e0b26281a74c6ec69dee12f23 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 10 Mar 2026 18:50:33 -0400
Subject: drm/xe: Always kill exec queues in xe_guc_submit_pause_abort
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

xe_guc_submit_pause_abort is intended to be called after something
disastrous occurs (e.g., VF migration fails, device wedging, or driver
unload) and should immediately trigger the teardown of remaining
submission state. With that, kill any remaining queues in this function.

Fixes: 7c4b7e34c83b ("drm/xe/vf: Abort VF post migration recovery on failure")
Cc: stable@vger.kernel.org
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-2-zhanjun.dong@intel.com
(cherry picked from commit 78f3bf00be4f15daead02ba32d4737129419c902)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 799ef9f48003..2d68f5317887 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2695,8 +2695,7 @@ void xe_guc_submit_pause_abort(struct xe_guc *guc)
 			continue;
 
 		xe_sched_submission_start(sched);
-		if (exec_queue_killed_or_banned_or_wedged(q))
-			xe_guc_exec_queue_trigger_cleanup(q);
+		guc_exec_queue_kill(q);
 	}
 	mutex_unlock(&guc->submission_state.lock);
 }
-- 
cgit v1.2.3


From fb3738693cbdce104bf12615e980a6a37ff9087d Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 10 Mar 2026 18:50:34 -0400
Subject: drm/xe: Forcefully tear down exec queues in GuC submit fini
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In GuC submit fini, forcefully tear down any exec queues by disabling
CTs, stopping the scheduler (which cleans up lost G2H), killing all
remaining queues, and resuming scheduling to allow any remaining cleanup
actions to complete and signal any remaining fences.

Split guc_submit_fini into device related and software only part. Using
device-managed and drm-managed action guarantees the correct ordering of
cleanup.

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Reviewed-by: Zhanjun Dong <zhanjun.dong@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-3-zhanjun.dong@intel.com
(cherry picked from commit a6ab444a111a59924bd9d0c1e0613a75a0a40b89)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc.c        | 26 +++++++++++++++++++--
 drivers/gpu/drm/xe/xe_guc.h        |  1 +
 drivers/gpu/drm/xe/xe_guc_submit.c | 48 ++++++++++++++++++++++++++++++--------
 3 files changed, 63 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index b0a3cddaa2ea..4ab65cae8743 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -1347,15 +1347,37 @@ int xe_guc_enable_communication(struct xe_guc *guc)
 	return 0;
 }
 
-int xe_guc_suspend(struct xe_guc *guc)
+/**
+ * xe_guc_softreset() - Soft reset GuC
+ * @guc: The GuC object
+ *
+ * Send soft reset command to GuC through mmio send.
+ *
+ * Return: 0 if success, otherwise error code
+ */
+int xe_guc_softreset(struct xe_guc *guc)
 {
-	struct xe_gt *gt = guc_to_gt(guc);
 	u32 action[] = {
 		XE_GUC_ACTION_CLIENT_SOFT_RESET,
 	};
 	int ret;
 
+	if (!xe_uc_fw_is_running(&guc->fw))
+		return 0;
+
 	ret = xe_guc_mmio_send(guc, action, ARRAY_SIZE(action));
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int xe_guc_suspend(struct xe_guc *guc)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	ret = xe_guc_softreset(guc);
 	if (ret) {
 		xe_gt_err(gt, "GuC suspend failed: %pe\n", ERR_PTR(ret));
 		return ret;
diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h
index 66e7edc70ed9..02514914f404 100644
--- a/drivers/gpu/drm/xe/xe_guc.h
+++ b/drivers/gpu/drm/xe/xe_guc.h
@@ -44,6 +44,7 @@ int xe_guc_opt_in_features_enable(struct xe_guc *guc);
 void xe_guc_runtime_suspend(struct xe_guc *guc);
 void xe_guc_runtime_resume(struct xe_guc *guc);
 int xe_guc_suspend(struct xe_guc *guc);
+int xe_guc_softreset(struct xe_guc *guc);
 void xe_guc_notify(struct xe_guc *guc);
 int xe_guc_auth_huc(struct xe_guc *guc, u32 rsa_addr);
 int xe_guc_mmio_send(struct xe_guc *guc, const u32 *request, u32 len);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 2d68f5317887..ef4d37b5c73c 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -48,6 +48,8 @@
 
 #define XE_GUC_EXEC_QUEUE_CGP_CONTEXT_ERROR_LEN		6
 
+static int guc_submit_reset_prepare(struct xe_guc *guc);
+
 static struct xe_guc *
 exec_queue_to_guc(struct xe_exec_queue *q)
 {
@@ -239,7 +241,7 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 		 EXEC_QUEUE_STATE_BANNED));
 }
 
-static void guc_submit_fini(struct drm_device *drm, void *arg)
+static void guc_submit_sw_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
 	struct xe_device *xe = guc_to_xe(guc);
@@ -257,6 +259,19 @@ static void guc_submit_fini(struct drm_device *drm, void *arg)
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
 }
 
+static void guc_submit_fini(void *arg)
+{
+	struct xe_guc *guc = arg;
+
+	/* Forcefully kill any remaining exec queues */
+	xe_guc_ct_stop(&guc->ct);
+	guc_submit_reset_prepare(guc);
+	xe_guc_softreset(guc);
+	xe_guc_submit_stop(guc);
+	xe_uc_fw_sanitize(&guc->fw);
+	xe_guc_submit_pause_abort(guc);
+}
+
 static void guc_submit_wedged_fini(void *arg)
 {
 	struct xe_guc *guc = arg;
@@ -326,7 +341,11 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 
 	guc->submission_state.initialized = true;
 
-	return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
+	err = drmm_add_action_or_reset(&xe->drm, guc_submit_sw_fini, guc);
+	if (err)
+		return err;
+
+	return devm_add_action_or_reset(xe->drm.dev, guc_submit_fini, guc);
 }
 
 /*
@@ -2230,6 +2249,7 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = {
 static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 {
 	struct xe_gpu_scheduler *sched = &q->guc->sched;
+	bool do_destroy = false;
 
 	/* Stop scheduling + flush any DRM scheduler operations */
 	xe_sched_submission_stop(sched);
@@ -2237,7 +2257,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 	/* Clean up lost G2H + reset engine state */
 	if (exec_queue_registered(q)) {
 		if (exec_queue_destroyed(q))
-			__guc_exec_queue_destroy(guc, q);
+			do_destroy = true;
 	}
 	if (q->guc->suspend_pending) {
 		set_exec_queue_suspended(q);
@@ -2273,18 +2293,15 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 			xe_guc_exec_queue_trigger_cleanup(q);
 		}
 	}
+
+	if (do_destroy)
+		__guc_exec_queue_destroy(guc, q);
 }
 
-int xe_guc_submit_reset_prepare(struct xe_guc *guc)
+static int guc_submit_reset_prepare(struct xe_guc *guc)
 {
 	int ret;
 
-	if (xe_gt_WARN_ON(guc_to_gt(guc), vf_recovery(guc)))
-		return 0;
-
-	if (!guc->submission_state.initialized)
-		return 0;
-
 	/*
 	 * Using an atomic here rather than submission_state.lock as this
 	 * function can be called while holding the CT lock (engine reset
@@ -2299,6 +2316,17 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 	return ret;
 }
 
+int xe_guc_submit_reset_prepare(struct xe_guc *guc)
+{
+	if (xe_gt_WARN_ON(guc_to_gt(guc), vf_recovery(guc)))
+		return 0;
+
+	if (!guc->submission_state.initialized)
+		return 0;
+
+	return guc_submit_reset_prepare(guc);
+}
+
 void xe_guc_submit_reset_wait(struct xe_guc *guc)
 {
 	wait_event(guc->ct.wq, xe_device_wedged(guc_to_xe(guc)) ||
-- 
cgit v1.2.3


From e0f82655df6fbb15b318e9d56724cd54b1cfb04d Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 10 Mar 2026 18:50:35 -0400
Subject: drm/xe: Trigger queue cleanup if not in wedged mode 2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The intent of wedging a device is to allow queues to continue running
only in wedged mode 2. In other modes, queues should initiate cleanup
and signal all remaining fences. Fix xe_guc_submit_wedge to correctly
clean up queues when wedge mode != 2.

Fixes: 7dbe8af13c18 ("drm/xe: Wedge the entire device")
Cc: stable@vger.kernel.org
Reviewed-by: Zhanjun Dong <zhanjun.dong@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-4-zhanjun.dong@intel.com
(cherry picked from commit e25ba41c8227c5393c16e4aab398076014bd345f)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ef4d37b5c73c..fc4f99d46763 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1271,6 +1271,7 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
  */
 void xe_guc_submit_wedge(struct xe_guc *guc)
 {
+	struct xe_device *xe = guc_to_xe(guc);
 	struct xe_gt *gt = guc_to_gt(guc);
 	struct xe_exec_queue *q;
 	unsigned long index;
@@ -1285,20 +1286,28 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 	if (!guc->submission_state.initialized)
 		return;
 
-	err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
-				       guc_submit_wedged_fini, guc);
-	if (err) {
-		xe_gt_err(gt, "Failed to register clean-up in wedged.mode=%s; "
-			  "Although device is wedged.\n",
-			  xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET));
-		return;
-	}
+	if (xe->wedged.mode == 2) {
+		err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
+					       guc_submit_wedged_fini, guc);
+		if (err) {
+			xe_gt_err(gt, "Failed to register clean-up on wedged.mode=2; "
+				  "Although device is wedged.\n");
+			return;
+		}
 
-	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (xe_exec_queue_get_unless_zero(q))
-			set_exec_queue_wedged(q);
-	mutex_unlock(&guc->submission_state.lock);
+		mutex_lock(&guc->submission_state.lock);
+		xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+			if (xe_exec_queue_get_unless_zero(q))
+				set_exec_queue_wedged(q);
+		mutex_unlock(&guc->submission_state.lock);
+	} else {
+		/* Forcefully kill any remaining exec queues, signal fences */
+		guc_submit_reset_prepare(guc);
+		xe_guc_submit_stop(guc);
+		xe_guc_softreset(guc);
+		xe_uc_fw_sanitize(&guc->fw);
+		xe_guc_submit_pause_abort(guc);
+	}
 }
 
 static bool guc_submit_hint_wedged(struct xe_guc *guc)
-- 
cgit v1.2.3


From 7838dd8367419e9fc43b79c038321cb3c04de2a2 Mon Sep 17 00:00:00 2001
From: Zhanjun Dong <zhanjun.dong@intel.com>
Date: Tue, 10 Mar 2026 18:50:37 -0400
Subject: drm/xe/guc: Ensure CT state transitions via STOP before DISABLED
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The GuC CT state transition requires moving to the STOP state before
entering the DISABLED state. Update the driver teardown sequence to make
the proper state machine transitions.

Fixes: ee4b32220a6b ("drm/xe/guc: Add devm release action to safely tear down CT")
Cc: stable@vger.kernel.org
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-6-zhanjun.dong@intel.com
(cherry picked from commit dace8cb0032f57ea67c87b3b92ad73c89dd2db44)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index d04589140b77..c80082b4c876 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -345,6 +345,7 @@ static void guc_action_disable_ct(void *arg)
 {
 	struct xe_guc_ct *ct = arg;
 
+	xe_guc_ct_stop(ct);
 	guc_ct_change_state(ct, XE_GUC_CT_STATE_DISABLED);
 }
 
-- 
cgit v1.2.3


From 38b8dcde231641f00eee977d245dbfe5f6b06e11 Mon Sep 17 00:00:00 2001
From: Brian Nguyen <brian3.nguyen@intel.com>
Date: Thu, 5 Mar 2026 17:15:48 +0000
Subject: drm/xe: Skip over non leaf pte for PRL generation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The check using xe_child->base.children was insufficient in determining
if a pte was a leaf node. So explicitly skip over every non-leaf pt and
conditionally abort if there is a scenario where a non-leaf pt is
interleaved between leaf pt, which results in the page walker skipping
over some leaf pt.

Note that the behavior being targeted for abort is
PD[0] = 2M PTE
PD[1] = PT -> 512 4K PTEs
PD[2] = 2M PTE

results in abort, page walker won't descend PD[1].

With new abort, ensuring valid PRL before handling a second abort.

v2:
 - Revert to previous assert.
 - Revised non-leaf handling for interleaf child pt and leaf pte.
 - Update comments to specifications. (Stuart)
 - Remove unnecessary XE_PTE_PS64. (Matthew B)

v3:
 - Modify secondary abort to only check non-leaf PTEs. (Matthew B)

Fixes: b912138df299 ("drm/xe: Create page reclaim list on unbind")
Signed-off-by: Brian Nguyen <brian3.nguyen@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Link: https://patch.msgid.link/20260305171546.67691-6-brian3.nguyen@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 1d123587525db86cc8f0d2beb35d9e33ca3ade83)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 13b355fadd58..2d9ce2c4cb4f 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1655,14 +1655,35 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset,
 	XE_WARN_ON(!level);
 	/* Check for leaf node */
 	if (xe_walk->prl && xe_page_reclaim_list_valid(xe_walk->prl) &&
-	    (!xe_child->base.children || !xe_child->base.children[first])) {
+	    xe_child->level <= MAX_HUGEPTE_LEVEL) {
 		struct iosys_map *leaf_map = &xe_child->bo->vmap;
 		pgoff_t count = xe_pt_num_entries(addr, next, xe_child->level, walk);
 
 		for (pgoff_t i = 0; i < count; i++) {
-			u64 pte = xe_map_rd(xe, leaf_map, (first + i) * sizeof(u64), u64);
+			u64 pte;
 			int ret;
 
+			/*
+			 * If not a leaf pt, skip unless non-leaf pt is interleaved between
+			 * leaf ptes which causes the page walk to skip over the child leaves
+			 */
+			if (xe_child->base.children && xe_child->base.children[first + i]) {
+				u64 pt_size = 1ULL << walk->shifts[xe_child->level];
+				bool edge_pt = (i == 0 && !IS_ALIGNED(addr, pt_size)) ||
+					       (i == count - 1 && !IS_ALIGNED(next, pt_size));
+
+				if (!edge_pt) {
+					xe_page_reclaim_list_abort(xe_walk->tile->primary_gt,
+								   xe_walk->prl,
+								   "PT is skipped by walk at level=%u offset=%lu",
+								   xe_child->level, first + i);
+					break;
+				}
+				continue;
+			}
+
+			pte = xe_map_rd(xe, leaf_map, (first + i) * sizeof(u64), u64);
+
 			/*
 			 * In rare scenarios, pte may not be written yet due to racy conditions.
 			 * In such cases, invalidate the PRL and fallback to full PPC invalidation.
@@ -1674,9 +1695,8 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset,
 			}
 
 			/* Ensure it is a defined page */
-			xe_tile_assert(xe_walk->tile,
-				       xe_child->level == 0 ||
-				       (pte & (XE_PTE_PS64 | XE_PDE_PS_2M | XE_PDPE_PS_1G)));
+			xe_tile_assert(xe_walk->tile, xe_child->level == 0 ||
+				       (pte & (XE_PDE_PS_2M | XE_PDPE_PS_1G)));
 
 			/* An entry should be added for 64KB but contigious 4K have XE_PTE_PS64 */
 			if (pte & XE_PTE_PS64)
@@ -1701,11 +1721,11 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset,
 	killed = xe_pt_check_kill(addr, next, level - 1, xe_child, action, walk);
 
 	/*
-	 * Verify PRL is active and if entry is not a leaf pte (base.children conditions),
-	 * there is a potential need to invalidate the PRL if any PTE (num_live) are dropped.
+	 * Verify if any PTE are potentially dropped at non-leaf levels, either from being
+	 * killed or the page walk covers the region.
 	 */
-	if (xe_walk->prl && level > 1 && xe_child->num_live &&
-	    xe_child->base.children && xe_child->base.children[first]) {
+	if (xe_walk->prl && xe_page_reclaim_list_valid(xe_walk->prl) &&
+	    xe_child->level > MAX_HUGEPTE_LEVEL && xe_child->num_live) {
 		bool covered = xe_pt_covers(addr, next, xe_child->level, &xe_walk->base);
 
 		/*
-- 
cgit v1.2.3


From 9be6fd9fbd2032b683e51374497768af9aaa228a Mon Sep 17 00:00:00 2001
From: Ashutosh Dixit <ashutosh.dixit@intel.com>
Date: Thu, 12 Mar 2026 22:36:30 -0700
Subject: drm/xe/oa: Allow reading after disabling OA stream
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some OA data might be present in the OA buffer when OA stream is
disabled. Allow UMD's to retrieve this data, so that all data till the
point when OA stream is disabled can be retrieved.

v2: Update tail pointer after disable (Umesh)

Fixes: efb315d0a013 ("drm/xe/oa/uapi: Read file_operation")
Cc: stable@vger.kernel.org
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Umesh Nerlige Ramappa<umesh.nerlige.ramappa@intel.com>
Link: https://patch.msgid.link/20260313053630.3176100-1-ashutosh.dixit@intel.com
(cherry picked from commit 4ff57c5e8dbba23b5457be12f9709d5c016da16e)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_oa.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 4dd3f29933cf..fa90441d3052 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -543,8 +543,7 @@ static ssize_t xe_oa_read(struct file *file, char __user *buf,
 	size_t offset = 0;
 	int ret;
 
-	/* Can't read from disabled streams */
-	if (!stream->enabled || !stream->sample)
+	if (!stream->sample)
 		return -EINVAL;
 
 	if (!(file->f_flags & O_NONBLOCK)) {
@@ -1460,6 +1459,10 @@ static void xe_oa_stream_disable(struct xe_oa_stream *stream)
 
 	if (stream->sample)
 		hrtimer_cancel(&stream->poll_check_timer);
+
+	/* Update stream->oa_buffer.tail to allow any final reports to be read */
+	if (xe_oa_buffer_check_unlocked(stream))
+		wake_up(&stream->poll_wq);
 }
 
 static int xe_oa_enable_preempt_timeslice(struct xe_oa_stream *stream)
-- 
cgit v1.2.3


From e6e3ea52bf07a0b7b9dff189616f189b83ee397a Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Thu, 12 Mar 2026 05:53:09 -0700
Subject: drm/xe/lrc: Fix uninitialized new_ts when capturing context timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Getting engine specific CTX TIMESTAMP register can fail. In that case,
if the context is active, new_ts is uninitialized. Fix that case by
initializing new_ts to the last value that was sampled in SW -
lrc->ctx_timestamp.

Flagged by static analysis.

v2: Fix new_ts initialization (Ashutosh)

Fixes: bb63e7257e63 ("drm/xe: Avoid toggling schedule state to check LRC timestamp in TDR")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patch.msgid.link/20260312125308.3126607-2-umesh.nerlige.ramappa@intel.com
(cherry picked from commit 466e75d48038af252187855058a7a9312db9d2f8)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b0f037bc227f..7b70cc01fdb3 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -2413,14 +2413,14 @@ static int get_ctx_timestamp(struct xe_lrc *lrc, u32 engine_id, u64 *reg_ctx_ts)
  * @lrc: Pointer to the lrc.
  *
  * Return latest ctx timestamp. With support for active contexts, the
- * calculation may bb slightly racy, so follow a read-again logic to ensure that
+ * calculation may be slightly racy, so follow a read-again logic to ensure that
  * the context is still active before returning the right timestamp.
  *
  * Returns: New ctx timestamp value
  */
 u64 xe_lrc_timestamp(struct xe_lrc *lrc)
 {
-	u64 lrc_ts, reg_ts, new_ts;
+	u64 lrc_ts, reg_ts, new_ts = lrc->ctx_timestamp;
 	u32 engine_id;
 
 	lrc_ts = xe_lrc_ctx_timestamp(lrc);
-- 
cgit v1.2.3


From cadf6019231b614ebbd9ec2a16e5997ecbd8d016 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 10 Mar 2026 13:48:03 +0100
Subject: can: netlink: can_changelink(): add missing error handling to call
 can_ctrlmode_changelink()

In commit e1a5cd9d6665 ("can: netlink: add can_ctrlmode_changelink()") the
CAN Control Mode (IFLA_CAN_CTRLMODE) handling was factored out into the
can_ctrlmode_changelink() function. But the call to
can_ctrlmode_changelink() is missing the error handling.

Add the missing error handling and propagation to the call
can_ctrlmode_changelink().

Cc: stable@vger.kernel.org
Fixes: e1a5cd9d6665 ("can: netlink: add can_ctrlmode_changelink()")
Link: https://patch.msgid.link/20260310-can_ctrlmode_changelink-add-error-handling-v1-1-0daf63d85922@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/netlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 0498198a4696..766d455950f5 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -601,7 +601,9 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	/* We need synchronization with dev->stop() */
 	ASSERT_RTNL();
 
-	can_ctrlmode_changelink(dev, data, extack);
+	err = can_ctrlmode_changelink(dev, data, extack);
+	if (err)
+		return err;
 
 	if (data[IFLA_CAN_BITTIMING]) {
 		struct can_bittiming bt;
-- 
cgit v1.2.3


From 7a57354756c7df223abe2c33774235ad70cb4231 Mon Sep 17 00:00:00 2001
From: Wenyuan Li <2063309626@qq.com>
Date: Mon, 16 Mar 2026 00:00:22 +0800
Subject: can: mcp251x: add error handling for power enable in open and resume

Add missing error handling for mcp251x_power_enable() calls in both
mcp251x_open() and mcp251x_can_resume() functions.

In mcp251x_open(), if power enable fails, jump to error path to close
candev without attempting to disable power again.

In mcp251x_can_resume(), properly check return values of power enable calls
for both power and transceiver regulators. If any fails, return the error
code to the PM framework and log the failure.

This ensures the driver properly handles power control failures and
maintains correct device state.

Signed-off-by: Wenyuan Li <2063309626@qq.com>
Link: https://patch.msgid.link/tencent_F3EFC5D7738AC548857B91657715E2D3AA06@qq.com
[mkl: fix patch description]
[mkl: mcp251x_can_resume(): replace goto by return]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/spi/mcp251x.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index bb7782582f40..0d0190ae094a 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1225,7 +1225,11 @@ static int mcp251x_open(struct net_device *net)
 	}
 
 	mutex_lock(&priv->mcp_lock);
-	mcp251x_power_enable(priv->transceiver, 1);
+	ret = mcp251x_power_enable(priv->transceiver, 1);
+	if (ret) {
+		dev_err(&spi->dev, "failed to enable transceiver power: %pe\n", ERR_PTR(ret));
+		goto out_close_candev;
+	}
 
 	priv->force_quit = 0;
 	priv->tx_skb = NULL;
@@ -1272,6 +1276,7 @@ out_free_irq:
 	mcp251x_hw_sleep(spi);
 out_close:
 	mcp251x_power_enable(priv->transceiver, 0);
+out_close_candev:
 	close_candev(net);
 	mutex_unlock(&priv->mcp_lock);
 	if (release_irq)
@@ -1516,11 +1521,25 @@ static int __maybe_unused mcp251x_can_resume(struct device *dev)
 {
 	struct spi_device *spi = to_spi_device(dev);
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
+	int ret = 0;
 
-	if (priv->after_suspend & AFTER_SUSPEND_POWER)
-		mcp251x_power_enable(priv->power, 1);
-	if (priv->after_suspend & AFTER_SUSPEND_UP)
-		mcp251x_power_enable(priv->transceiver, 1);
+	if (priv->after_suspend & AFTER_SUSPEND_POWER) {
+		ret = mcp251x_power_enable(priv->power, 1);
+		if (ret) {
+			dev_err(dev, "failed to restore power: %pe\n", ERR_PTR(ret));
+			return ret;
+		}
+	}
+
+	if (priv->after_suspend & AFTER_SUSPEND_UP) {
+		ret = mcp251x_power_enable(priv->transceiver, 1);
+		if (ret) {
+			dev_err(dev, "failed to restore transceiver power: %pe\n", ERR_PTR(ret));
+			if (priv->after_suspend & AFTER_SUSPEND_POWER)
+				mcp251x_power_enable(priv->power, 0);
+			return ret;
+		}
+	}
 
 	if (priv->after_suspend & (AFTER_SUSPEND_POWER | AFTER_SUSPEND_UP))
 		queue_work(priv->wq, &priv->restart_work);
-- 
cgit v1.2.3


From 46eee1661aa9b49966e6c43d07126fe408edda57 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Wed, 18 Mar 2026 18:34:13 +0100
Subject: can: statistics: add missing atomic access in hot path

Commit 80b5f90158d1 ("can: statistics: use atomic access in hot path")
fixed a KCSAN issue in can_receive() but missed to convert the 'matches'
variable used in can_rcv_filter().

Fixes: 80b5f90158d1 ("can: statistics: use atomic access in hot path")
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260318173413.28235-1-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/af_can.c | 4 ++--
 net/can/af_can.h | 2 +-
 net/can/proc.c   | 3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index f70e2ba0aadc..7bc86b176b4d 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -469,7 +469,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id,
 
 	rcv->can_id = can_id;
 	rcv->mask = mask;
-	rcv->matches = 0;
+	atomic_long_set(&rcv->matches, 0);
 	rcv->func = func;
 	rcv->data = data;
 	rcv->ident = ident;
@@ -573,7 +573,7 @@ EXPORT_SYMBOL(can_rx_unregister);
 static inline void deliver(struct sk_buff *skb, struct receiver *rcv)
 {
 	rcv->func(skb, rcv->data);
-	rcv->matches++;
+	atomic_long_inc(&rcv->matches);
 }
 
 static int can_rcv_filter(struct can_dev_rcv_lists *dev_rcv_lists, struct sk_buff *skb)
diff --git a/net/can/af_can.h b/net/can/af_can.h
index 22f3352c77fe..87887014f562 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -52,7 +52,7 @@ struct receiver {
 	struct hlist_node list;
 	canid_t can_id;
 	canid_t mask;
-	unsigned long matches;
+	atomic_long_t matches;
 	void (*func)(struct sk_buff *skb, void *data);
 	void *data;
 	char *ident;
diff --git a/net/can/proc.c b/net/can/proc.c
index 0938bf7dd646..de4d05ae3459 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -196,7 +196,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list,
 			"   %-5s     %03x    %08x  %pK  %pK  %8ld  %s\n";
 
 		seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask,
-				r->func, r->data, r->matches, r->ident);
+			   r->func, r->data, atomic_long_read(&r->matches),
+			   r->ident);
 	}
 }
 
-- 
cgit v1.2.3


From c8cfeb4b9dda2cdfce79519aee4aaff16310a7b6 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@foss.st.com>
Date: Tue, 17 Mar 2026 11:06:54 +0100
Subject: pinctrl: stm32: fix HDP driver dependency on GPIO_GENERIC

The HDP driver uses the generic GPIO chip API, but this configuration
may not be enabled.
Ensure it is enabled by selecting the appropriate option.

Fixes: 4bcff9c05b9d ("pinctrl: stm32: use new generic GPIO chip API")
Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/stm32/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/stm32/Kconfig b/drivers/pinctrl/stm32/Kconfig
index 5f67e1ee66dd..d6a171523012 100644
--- a/drivers/pinctrl/stm32/Kconfig
+++ b/drivers/pinctrl/stm32/Kconfig
@@ -65,6 +65,7 @@ config PINCTRL_STM32_HDP
 	select PINMUX
 	select GENERIC_PINCONF
 	select GPIOLIB
+	select GPIO_GENERIC
 	help
 	  The Hardware Debug Port allows the observation of internal signals.
 	  It uses configurable multiplexer to route signals in a dedicated observation register.
-- 
cgit v1.2.3


From 27459f86a43792d5c29f267a41dbd387601e772b Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 9 Mar 2026 20:16:14 +0800
Subject: soc: microchip: mpfs-control-scb: Fix resource leak on driver unbind

Use devm_mfd_add_devices() instead of mfd_add_devices() to ensure
child devices are properly removed when the driver unbinds.

Fixes: 4aac11c9a6e7 ("soc: microchip: add mfd drivers for two syscon regions on PolarFire SoC")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/soc/microchip/mpfs-control-scb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/microchip/mpfs-control-scb.c b/drivers/soc/microchip/mpfs-control-scb.c
index f0b84b1f49cb..8dda5704a389 100644
--- a/drivers/soc/microchip/mpfs-control-scb.c
+++ b/drivers/soc/microchip/mpfs-control-scb.c
@@ -14,8 +14,10 @@ static int mpfs_control_scb_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 
-	return mfd_add_devices(dev, PLATFORM_DEVID_NONE, mpfs_control_scb_devs,
-			       ARRAY_SIZE(mpfs_control_scb_devs), NULL, 0, NULL);
+	return devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+				    mpfs_control_scb_devs,
+				    ARRAY_SIZE(mpfs_control_scb_devs), NULL, 0,
+				    NULL);
 }
 
 static const struct of_device_id mpfs_control_scb_of_match[] = {
-- 
cgit v1.2.3


From 3bfc213d4675736567a4e263c51c25144d565949 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 9 Mar 2026 20:16:15 +0800
Subject: soc: microchip: mpfs-mss-top-sysreg: Fix resource leak on driver
 unbind

Use devm_mfd_add_devices() instead of mfd_add_devices() to ensure
child devices are properly removed when the driver unbinds.

Fixes: 4aac11c9a6e7 ("soc: microchip: add mfd drivers for two syscon regions on PolarFire SoC")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/soc/microchip/mpfs-mss-top-sysreg.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/microchip/mpfs-mss-top-sysreg.c b/drivers/soc/microchip/mpfs-mss-top-sysreg.c
index b2244e44ff0f..b0f42b8dd3ed 100644
--- a/drivers/soc/microchip/mpfs-mss-top-sysreg.c
+++ b/drivers/soc/microchip/mpfs-mss-top-sysreg.c
@@ -16,8 +16,10 @@ static int mpfs_mss_top_sysreg_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	int ret;
 
-	ret = mfd_add_devices(dev, PLATFORM_DEVID_NONE, mpfs_mss_top_sysreg_devs,
-			      ARRAY_SIZE(mpfs_mss_top_sysreg_devs) , NULL, 0, NULL);
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE,
+				   mpfs_mss_top_sysreg_devs,
+				   ARRAY_SIZE(mpfs_mss_top_sysreg_devs), NULL,
+				   0, NULL);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 01f2557aa684e514005541e71a3d01f4cd45c170 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 10 Mar 2026 18:50:39 -0400
Subject: drm/xe: Open-code GGTT MMIO access protection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GGTT MMIO access is currently protected by hotplug (drm_dev_enter),
which works correctly when the driver loads successfully and is later
unbound or unloaded. However, if driver load fails, this protection is
insufficient because drm_dev_unplug() is never called.

Additionally, devm release functions cannot guarantee that all BOs with
GGTT mappings are destroyed before the GGTT MMIO region is removed, as
some BOs may be freed asynchronously by worker threads.

To address this, introduce an open-coded flag, protected by the GGTT
lock, that guards GGTT MMIO access. The flag is cleared during the
dev_fini_ggtt devm release function to ensure MMIO access is disabled
once teardown begins.

Cc: stable@vger.kernel.org
Fixes: 919bb54e989c ("drm/xe: Fix missing runtime outer protection for ggtt_remove_node")
Reviewed-by: Zhanjun Dong <zhanjun.dong@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-8-zhanjun.dong@intel.com
(cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_ggtt.c       | 10 ++++------
 drivers/gpu/drm/xe/xe_ggtt_types.h |  5 ++++-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 2bda426a6986..d1561ebe4e56 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -313,6 +313,8 @@ static void dev_fini_ggtt(void *arg)
 {
 	struct xe_ggtt *ggtt = arg;
 
+	scoped_guard(mutex, &ggtt->lock)
+		ggtt->flags &= ~XE_GGTT_FLAGS_ONLINE;
 	drain_workqueue(ggtt->wq);
 }
 
@@ -377,6 +379,7 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	if (err)
 		return err;
 
+	ggtt->flags |= XE_GGTT_FLAGS_ONLINE;
 	err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt);
 	if (err)
 		return err;
@@ -410,13 +413,10 @@ static void xe_ggtt_initial_clear(struct xe_ggtt *ggtt)
 static void ggtt_node_remove(struct xe_ggtt_node *node)
 {
 	struct xe_ggtt *ggtt = node->ggtt;
-	struct xe_device *xe = tile_to_xe(ggtt->tile);
 	bool bound;
-	int idx;
-
-	bound = drm_dev_enter(&xe->drm, &idx);
 
 	mutex_lock(&ggtt->lock);
+	bound = ggtt->flags & XE_GGTT_FLAGS_ONLINE;
 	if (bound)
 		xe_ggtt_clear(ggtt, node->base.start, node->base.size);
 	drm_mm_remove_node(&node->base);
@@ -429,8 +429,6 @@ static void ggtt_node_remove(struct xe_ggtt_node *node)
 	if (node->invalidate_on_remove)
 		xe_ggtt_invalidate(ggtt);
 
-	drm_dev_exit(idx);
-
 free_node:
 	xe_ggtt_node_fini(node);
 }
diff --git a/drivers/gpu/drm/xe/xe_ggtt_types.h b/drivers/gpu/drm/xe/xe_ggtt_types.h
index d82b71a198bc..c002857bb761 100644
--- a/drivers/gpu/drm/xe/xe_ggtt_types.h
+++ b/drivers/gpu/drm/xe/xe_ggtt_types.h
@@ -28,11 +28,14 @@ struct xe_ggtt {
 	/** @size: Total usable size of this GGTT */
 	u64 size;
 
-#define XE_GGTT_FLAGS_64K BIT(0)
+#define XE_GGTT_FLAGS_64K       BIT(0)
+#define XE_GGTT_FLAGS_ONLINE	BIT(1)
 	/**
 	 * @flags: Flags for this GGTT
 	 * Acceptable flags:
 	 * - %XE_GGTT_FLAGS_64K - if PTE size is 64K. Otherwise, regular is 4K.
+	 * - %XE_GGTT_FLAGS_ONLINE - is GGTT online, protected by ggtt->lock
+	 *   after init
 	 */
 	unsigned int flags;
 	/** @scratch: Internal object allocation used as a scratch page */
-- 
cgit v1.2.3


From b9c310d72783cc2f30d103eed83920a5a29c671a Mon Sep 17 00:00:00 2001
From: Ali Norouzi <ali.norouzi@keysight.com>
Date: Thu, 19 Mar 2026 16:47:44 +0100
Subject: can: gw: fix OOB heap access in cgw_csum_crc8_rel()

cgw_csum_crc8_rel() correctly computes bounds-safe indices via calc_idx():

    int from = calc_idx(crc8->from_idx, cf->len);
    int to   = calc_idx(crc8->to_idx,   cf->len);
    int res  = calc_idx(crc8->result_idx, cf->len);

    if (from < 0 || to < 0 || res < 0)
        return;

However, the loop and the result write then use the raw s8 fields directly
instead of the computed variables:

    for (i = crc8->from_idx; ...)        /* BUG: raw negative index */
    cf->data[crc8->result_idx] = ...;    /* BUG: raw negative index */

With from_idx = to_idx = result_idx = -64 on a 64-byte CAN FD frame,
calc_idx(-64, 64) = 0 so the guard passes, but the loop iterates with
i = -64, reading cf->data[-64], and the write goes to cf->data[-64].
This write might end up to 56 (7.0-rc) or 40 (<= 6.19) bytes before the
start of the canfd_frame on the heap.

The companion function cgw_csum_xor_rel() uses `from`/`to`/`res`
correctly throughout; fix cgw_csum_crc8_rel() to match.

Confirmed with KASAN on linux-7.0-rc2:
  BUG: KASAN: slab-out-of-bounds in cgw_csum_crc8_rel+0x515/0x5b0
  Read of size 1 at addr ffff8880076619c8 by task poc_cgw_oob/62

To configure the can-gw crc8 checksums CAP_NET_ADMIN is needed.

Fixes: 456a8a646b25 ("can: gw: add support for CAN FD frames")
Cc: stable@vger.kernel.org
Reported-by: Ali Norouzi <ali.norouzi@keysight.com>
Reviewed-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Ali Norouzi <ali.norouzi@keysight.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260319-fix-can-gw-and-can-isotp-v2-1-c45d52c6d2d8@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/gw.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/can/gw.c b/net/can/gw.c
index 8ee4d67a07d3..0ec99f68aa45 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -375,10 +375,10 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf,
 		return;
 
 	if (from <= to) {
-		for (i = crc8->from_idx; i <= crc8->to_idx; i++)
+		for (i = from; i <= to; i++)
 			crc = crc8->crctab[crc ^ cf->data[i]];
 	} else {
-		for (i = crc8->from_idx; i >= crc8->to_idx; i--)
+		for (i = from; i >= to; i--)
 			crc = crc8->crctab[crc ^ cf->data[i]];
 	}
 
@@ -397,7 +397,7 @@ static void cgw_csum_crc8_rel(struct canfd_frame *cf,
 		break;
 	}
 
-	cf->data[crc8->result_idx] = crc ^ crc8->final_xor_val;
+	cf->data[res] = crc ^ crc8->final_xor_val;
 }
 
 static void cgw_csum_crc8_pos(struct canfd_frame *cf,
-- 
cgit v1.2.3


From 424e95d62110cdbc8fd12b40918f37e408e35a92 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Thu, 19 Mar 2026 16:47:45 +0100
Subject: can: isotp: fix tx.buf use-after-free in isotp_sendmsg()

isotp_sendmsg() uses only cmpxchg() on so->tx.state to serialize access
to so->tx.buf. isotp_release() waits for ISOTP_IDLE via
wait_event_interruptible() and then calls kfree(so->tx.buf).

If a signal interrupts the wait_event_interruptible() inside close()
while tx.state is ISOTP_SENDING, the loop exits early and release
proceeds to force ISOTP_SHUTDOWN and continues to kfree(so->tx.buf)
while sendmsg may still be reading so->tx.buf for the final CAN frame
in isotp_fill_dataframe().

The so->tx.buf can be allocated once when the standard tx.buf length needs
to be extended. Move the kfree() of this potentially extended tx.buf to
sk_destruct time when either isotp_sendmsg() and isotp_release() are done.

Fixes: 96d1c81e6a04 ("can: isotp: add module parameter for maximum pdu size")
Cc: stable@vger.kernel.org
Reported-by: Ali Norouzi <ali.norouzi@keysight.com>
Co-developed-by: Ali Norouzi <ali.norouzi@keysight.com>
Signed-off-by: Ali Norouzi <ali.norouzi@keysight.com>
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20260319-fix-can-gw-and-can-isotp-v2-2-c45d52c6d2d8@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/net/can/isotp.c b/net/can/isotp.c
index da3b72e7afcc..2770f43f4951 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1248,12 +1248,6 @@ static int isotp_release(struct socket *sock)
 	so->ifindex = 0;
 	so->bound = 0;
 
-	if (so->rx.buf != so->rx.sbuf)
-		kfree(so->rx.buf);
-
-	if (so->tx.buf != so->tx.sbuf)
-		kfree(so->tx.buf);
-
 	sock_orphan(sk);
 	sock->sk = NULL;
 
@@ -1622,6 +1616,21 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
 	return NOTIFY_DONE;
 }
 
+static void isotp_sock_destruct(struct sock *sk)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+
+	/* do the standard CAN sock destruct work */
+	can_sock_destruct(sk);
+
+	/* free potential extended PDU buffers */
+	if (so->rx.buf != so->rx.sbuf)
+		kfree(so->rx.buf);
+
+	if (so->tx.buf != so->tx.sbuf)
+		kfree(so->tx.buf);
+}
+
 static int isotp_init(struct sock *sk)
 {
 	struct isotp_sock *so = isotp_sk(sk);
@@ -1666,6 +1675,9 @@ static int isotp_init(struct sock *sk)
 	list_add_tail(&so->notifier, &isotp_notifier_list);
 	spin_unlock(&isotp_notifier_lock);
 
+	/* re-assign default can_sock_destruct() reference */
+	sk->sk_destruct = isotp_sock_destruct;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From b48731849609cbd8c53785a48976850b443153fd Mon Sep 17 00:00:00 2001
From: Anas Iqbal <mohd.abd.6602@gmail.com>
Date: Wed, 18 Mar 2026 08:42:12 +0000
Subject: net: dsa: bcm_sf2: fix missing clk_disable_unprepare() in error paths

Smatch reports:
drivers/net/dsa/bcm_sf2.c:997 bcm_sf2_sw_resume() warn:
'priv->clk' from clk_prepare_enable() not released on lines: 983,990.

The clock enabled by clk_prepare_enable() in bcm_sf2_sw_resume()
is not released if bcm_sf2_sw_rst() or bcm_sf2_cfp_resume() fails.

Add the missing clk_disable_unprepare() calls in the error paths
to properly release the clock resource.

Fixes: e9ec5c3bd238 ("net: dsa: bcm_sf2: request and handle clocks")
Reviewed-by: Jonas Gorski <jonas.gorski@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Anas Iqbal <mohd.abd.6602@gmail.com>
Link: https://patch.msgid.link/20260318084212.1287-1-mohd.abd.6602@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/bcm_sf2.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 960685596093..de3efa3ce9a7 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -980,15 +980,19 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
 	ret = bcm_sf2_sw_rst(priv);
 	if (ret) {
 		pr_err("%s: failed to software reset switch\n", __func__);
+		if (!priv->wol_ports_mask)
+			clk_disable_unprepare(priv->clk);
 		return ret;
 	}
 
 	bcm_sf2_crossbar_setup(priv);
 
 	ret = bcm_sf2_cfp_resume(ds);
-	if (ret)
+	if (ret) {
+		if (!priv->wol_ports_mask)
+			clk_disable_unprepare(priv->clk);
 		return ret;
-
+	}
 	if (priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, true);
 
-- 
cgit v1.2.3


From 614aefe56af8e13331e50220c936fc0689cf5675 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 18 Mar 2026 21:06:01 +0800
Subject: icmp: fix NULL pointer dereference in icmp_tag_validation()

icmp_tag_validation() unconditionally dereferences the result of
rcu_dereference(inet_protos[proto]) without checking for NULL.
The inet_protos[] array is sparse -- only about 15 of 256 protocol
numbers have registered handlers. When ip_no_pmtu_disc is set to 3
(hardened PMTU mode) and the kernel receives an ICMP Fragmentation
Needed error with a quoted inner IP header containing an unregistered
protocol number, the NULL dereference causes a kernel panic in
softirq context.

 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
 RIP: 0010:icmp_unreach (net/ipv4/icmp.c:1085 net/ipv4/icmp.c:1143)
 Call Trace:
  <IRQ>
  icmp_rcv (net/ipv4/icmp.c:1527)
  ip_protocol_deliver_rcu (net/ipv4/ip_input.c:207)
  ip_local_deliver_finish (net/ipv4/ip_input.c:242)
  ip_local_deliver (net/ipv4/ip_input.c:262)
  ip_rcv (net/ipv4/ip_input.c:573)
  __netif_receive_skb_one_core (net/core/dev.c:6164)
  process_backlog (net/core/dev.c:6628)
  handle_softirqs (kernel/softirq.c:561)
  </IRQ>

Add a NULL check before accessing icmp_strict_tag_validation. If the
protocol has no registered handler, return false since it cannot
perform strict tag validation.

Fixes: 8ed1dc44d3e9 ("ipv4: introduce hardened ip_no_pmtu_disc mode")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260318130558.1050247-4-bestswngs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index a62b4c4033cc..568bd1e95d44 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1079,10 +1079,12 @@ out:
 
 static bool icmp_tag_validation(int proto)
 {
+	const struct net_protocol *ipprot;
 	bool ok;
 
 	rcu_read_lock();
-	ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
+	ipprot = rcu_dereference(inet_protos[proto]);
+	ok = ipprot ? ipprot->icmp_strict_tag_validation : false;
 	rcu_read_unlock();
 	return ok;
 }
-- 
cgit v1.2.3


From 7ab4a7c5d969642782b8a5b608da0dd02aa9f229 Mon Sep 17 00:00:00 2001
From: Li Xiasong <lixiasong1@huawei.com>
Date: Thu, 19 Mar 2026 19:21:59 +0800
Subject: MPTCP: fix lock class name family in pm_nl_create_listen_socket

In mptcp_pm_nl_create_listen_socket(), use entry->addr.family
instead of sk->sk_family for lock class setup. The 'sk' parameter
is a netlink socket, not the MPTCP subflow socket being created.

Fixes: cee4034a3db1 ("mptcp: fix lockdep false positive in mptcp_pm_nl_create_listen_socket()")
Signed-off-by: Li Xiasong <lixiasong1@huawei.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260319112159.3118874-1-lixiasong1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_kernel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index b2b9df43960e..82e59f9c6dd9 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -838,7 +838,7 @@ static struct lock_class_key mptcp_keys[2];
 static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 					    struct mptcp_pm_addr_entry *entry)
 {
-	bool is_ipv6 = sk->sk_family == AF_INET6;
+	bool is_ipv6 = entry->addr.family == AF_INET6;
 	int addrlen = sizeof(struct sockaddr_in);
 	struct sockaddr_storage addr;
 	struct sock *newsk, *ssk;
-- 
cgit v1.2.3


From 65d046b2d8e0d6d855379a981869005fd6b6a41b Mon Sep 17 00:00:00 2001
From: Sanjay Yadav <sanjay.kumar.yadav@intel.com>
Date: Fri, 13 Mar 2026 12:46:09 +0530
Subject: drm/xe: Fix missing runtime PM reference in ccs_mode_store
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ccs_mode_store() calls xe_gt_reset() which internally invokes
xe_pm_runtime_get_noresume(). That function requires the caller
to already hold an outer runtime PM reference and warns if none
is held:

  [46.891177] xe 0000:03:00.0: [drm] Missing outer runtime PM protection
  [46.891178] WARNING: drivers/gpu/drm/xe/xe_pm.c:885 at
  xe_pm_runtime_get_noresume+0x8b/0xc0

Fix this by protecting xe_gt_reset() with the scope-based
guard(xe_pm_runtime)(xe), which is the preferred form when
the reference lifetime matches a single scope.

v2:
- Use scope-based guard(xe_pm_runtime)(xe) (Shuicheng)
- Update commit message accordingly

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7593
Fixes: 480b358e7d8e ("drm/xe: Do not wake device during a GT reset")
Cc: <stable@vger.kernel.org> # v6.19+
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Sanjay Yadav <sanjay.kumar.yadav@intel.com>
Reviewed-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patch.msgid.link/20260313071608.3459480-2-sanjay.kumar.yadav@intel.com
(cherry picked from commit 7937ea733f79b3f25e802a0c8360bf7423856f36)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_ccs_mode.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
index fe944687728c..03c1862ba497 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
@@ -12,6 +12,7 @@
 #include "xe_gt_printk.h"
 #include "xe_gt_sysfs.h"
 #include "xe_mmio.h"
+#include "xe_pm.h"
 #include "xe_sriov.h"
 
 static void __xe_gt_apply_ccs_mode(struct xe_gt *gt, u32 num_engines)
@@ -150,6 +151,7 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr,
 		xe_gt_info(gt, "Setting compute mode to %d\n", num_engines);
 		gt->ccs_mode = num_engines;
 		xe_gt_record_user_engines(gt);
+		guard(xe_pm_runtime)(xe);
 		xe_gt_reset(gt);
 	}
 
-- 
cgit v1.2.3


From 9d87cb22195b2c67405f5485d525190747ad5493 Mon Sep 17 00:00:00 2001
From: Minseo Park <jacob.park.9436@gmail.com>
Date: Sun, 15 Mar 2026 22:14:37 +0900
Subject: Bluetooth: L2CAP: Fix stack-out-of-bounds read in
 l2cap_ecred_conn_req

Syzbot reported a KASAN stack-out-of-bounds read in l2cap_build_cmd()
that is triggered by a malformed Enhanced Credit Based Connection Request.

The vulnerability stems from l2cap_ecred_conn_req(). The function allocates
a local stack buffer (`pdu`) designed to hold a maximum of 5 Source Channel
IDs (SCIDs), totaling 18 bytes. When an attacker sends a request with more
than 5 SCIDs, the function calculates `rsp_len` based on this unvalidated
`cmd_len` before checking if the number of SCIDs exceeds
L2CAP_ECRED_MAX_CID.

If the SCID count is too high, the function correctly jumps to the
`response` label to reject the packet, but `rsp_len` retains the
attacker's oversized value. Consequently, l2cap_send_cmd() is instructed
to read past the end of the 18-byte `pdu` buffer, triggering a
KASAN panic.

Fix this by moving the assignment of `rsp_len` to after the `num_scid`
boundary check. If the packet is rejected, `rsp_len` will safely
remain 0, and the error response will only read the 8-byte base header
from the stack.

Fixes: c28d2bff7044 ("Bluetooth: L2CAP: Fix result of L2CAP_ECRED_CONN_RSP when MTU is too short")
Reported-by: syzbot+b7f3e7d9a596bf6a63e3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b7f3e7d9a596bf6a63e3
Tested-by: syzbot+b7f3e7d9a596bf6a63e3@syzkaller.appspotmail.com
Signed-off-by: Minseo Park <jacob.park.9436@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 5deb6c4f1e41..0882b5ac2ecc 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -5081,14 +5081,14 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
 	cmd_len -= sizeof(*req);
 	num_scid = cmd_len / sizeof(u16);
 
-	/* Always respond with the same number of scids as in the request */
-	rsp_len = cmd_len;
-
 	if (num_scid > L2CAP_ECRED_MAX_CID) {
 		result = L2CAP_CR_LE_INVALID_PARAMS;
 		goto response;
 	}
 
+	/* Always respond with the same number of scids as in the request */
+	rsp_len = cmd_len;
+
 	mtu  = __le16_to_cpu(req->mtu);
 	mps  = __le16_to_cpu(req->mps);
 
-- 
cgit v1.2.3


From c65bd945d1c08c3db756821b6bf9f1c4a77b29c6 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 13 Mar 2026 05:22:39 +0900
Subject: Bluetooth: L2CAP: Validate PDU length before reading SDU length in
 l2cap_ecred_data_rcv()

l2cap_ecred_data_rcv() reads the SDU length field from skb->data using
get_unaligned_le16() without first verifying that skb contains at least
L2CAP_SDULEN_SIZE (2) bytes. When skb->len is less than 2, this reads
past the valid data in the skb.

The ERTM reassembly path correctly calls pskb_may_pull() before reading
the SDU length (l2cap_reassemble_sdu, L2CAP_SAR_START case). Apply the
same validation to the Enhanced Credit Based Flow Control data path.

Fixes: aac23bf63659 ("Bluetooth: Implement LE L2CAP reassembly")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 0882b5ac2ecc..30fd6848938e 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6690,6 +6690,11 @@ static int l2cap_ecred_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (!chan->sdu) {
 		u16 sdu_len;
 
+		if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) {
+			err = -EINVAL;
+			goto failed;
+		}
+
 		sdu_len = get_unaligned_le16(skb->data);
 		skb_pull(skb, L2CAP_SDULEN_SIZE);
 
-- 
cgit v1.2.3


From 598dbba9919c5e36c54fe1709b557d64120cb94b Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 13 Mar 2026 05:26:16 +0900
Subject: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing
 sock_hold

sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately
releases the lock without holding a reference to the socket. A concurrent
close() can free the socket between the lock release and the subsequent
sk->sk_state access, resulting in a use-after-free.

Other functions in the same file (sco_sock_timeout(), sco_conn_del())
correctly use sco_sock_hold() to safely hold a reference under the lock.

Fix by using sco_sock_hold() to take a reference before releasing the
lock, and adding sock_put() on all exit paths.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/sco.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e7db50165879..584e059de20a 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -401,7 +401,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb)
 	struct sock *sk;
 
 	sco_conn_lock(conn);
-	sk = conn->sk;
+	sk = sco_sock_hold(conn);
 	sco_conn_unlock(conn);
 
 	if (!sk)
@@ -410,11 +410,15 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb)
 	BT_DBG("sk %p len %u", sk, skb->len);
 
 	if (sk->sk_state != BT_CONNECTED)
-		goto drop;
+		goto drop_put;
 
-	if (!sock_queue_rcv_skb(sk, skb))
+	if (!sock_queue_rcv_skb(sk, skb)) {
+		sock_put(sk);
 		return;
+	}
 
+drop_put:
+	sock_put(sk);
 drop:
 	kfree_skb(skb);
 }
-- 
cgit v1.2.3


From 5f5fa4cd35f707344f65ce9e225b6528691dbbaa Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 16 Mar 2026 15:03:27 -0400
Subject: Bluetooth: MGMT: Fix dangling pointer on
 mgmt_add_adv_patterns_monitor_complete

This fixes the condition checking so mgmt_pending_valid is executed
whenever status != -ECANCELED otherwise calling mgmt_pending_free(cmd)
would kfree(cmd) without unlinking it from the list first, leaving a
dangling pointer. Any subsequent list traversal (e.g.,
mgmt_pending_foreach during __mgmt_power_off, or another
mgmt_pending_valid call) would dereference freed memory.

Link: https://lore.kernel.org/linux-bluetooth/20260315132013.75ab40c5@kernel.org/T/#m1418f9c82eeff8510c1beaa21cf53af20db96c06
Fixes: 302a1f674c00 ("Bluetooth: MGMT: Fix possible UAFs")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
---
 net/bluetooth/mgmt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d52238ce6a9a..e5f9287fb826 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5355,7 +5355,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev,
 	 * hci_adv_monitors_clear is about to be called which will take care of
 	 * freeing the adv_monitor instances.
 	 */
-	if (status == -ECANCELED && !mgmt_pending_valid(hdev, cmd))
+	if (status == -ECANCELED || !mgmt_pending_valid(hdev, cmd))
 		return;
 
 	monitor = cmd->user_data;
-- 
cgit v1.2.3


From b6807cfc195ef99e1ac37b2e1e60df40295daa8c Mon Sep 17 00:00:00 2001
From: Cen Zhang <zzzccc427@gmail.com>
Date: Sun, 15 Mar 2026 20:07:26 +0800
Subject: Bluetooth: hci_sync: annotate data-races around hdev->req_status

__hci_cmd_sync_sk() sets hdev->req_status under hdev->req_lock:

    hdev->req_status = HCI_REQ_PEND;

However, several other functions read or write hdev->req_status without
holding any lock:

  - hci_send_cmd_sync() reads req_status in hci_cmd_work (workqueue)
  - hci_cmd_sync_complete() reads/writes from HCI event completion
  - hci_cmd_sync_cancel() / hci_cmd_sync_cancel_sync() read/write
  - hci_abort_conn() reads in connection abort path

Since __hci_cmd_sync_sk() runs on hdev->req_workqueue while
hci_send_cmd_sync() runs on hdev->workqueue, these are different
workqueues that can execute concurrently on different CPUs. The plain
C accesses constitute a data race.

Add READ_ONCE()/WRITE_ONCE() annotations on all concurrent accesses
to hdev->req_status to prevent potential compiler optimizations that
could affect correctness (e.g., load fusing in the wait_event
condition or store reordering).

Signed-off-by: Cen Zhang <zzzccc427@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c |  2 +-
 net/bluetooth/hci_core.c |  2 +-
 net/bluetooth/hci_sync.c | 20 ++++++++++----------
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 6eb59e9f2aa8..e6393f17576b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -3095,7 +3095,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
 	 * hci_connect_le serializes the connection attempts so only one
 	 * connection can be in BT_CONNECT at time.
 	 */
-	if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) {
+	if (conn->state == BT_CONNECT && READ_ONCE(hdev->req_status) == HCI_REQ_PEND) {
 		switch (hci_skb_event(hdev->sent_cmd)) {
 		case HCI_EV_CONN_COMPLETE:
 		case HCI_EV_LE_CONN_COMPLETE:
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 31308c1de4ec..01f8ceeb1c0c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4126,7 +4126,7 @@ static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb)
 		kfree_skb(skb);
 	}
 
-	if (hdev->req_status == HCI_REQ_PEND &&
+	if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND &&
 	    !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) {
 		kfree_skb(hdev->req_skb);
 		hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL);
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 3166914b0d6c..45d16639874a 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -25,11 +25,11 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
 {
 	bt_dev_dbg(hdev, "result 0x%2.2x", result);
 
-	if (hdev->req_status != HCI_REQ_PEND)
+	if (READ_ONCE(hdev->req_status) != HCI_REQ_PEND)
 		return;
 
 	hdev->req_result = result;
-	hdev->req_status = HCI_REQ_DONE;
+	WRITE_ONCE(hdev->req_status, HCI_REQ_DONE);
 
 	/* Free the request command so it is not used as response */
 	kfree_skb(hdev->req_skb);
@@ -167,20 +167,20 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
 
 	hci_cmd_sync_add(&req, opcode, plen, param, event, sk);
 
-	hdev->req_status = HCI_REQ_PEND;
+	WRITE_ONCE(hdev->req_status, HCI_REQ_PEND);
 
 	err = hci_req_sync_run(&req);
 	if (err < 0)
 		return ERR_PTR(err);
 
 	err = wait_event_interruptible_timeout(hdev->req_wait_q,
-					       hdev->req_status != HCI_REQ_PEND,
+					       READ_ONCE(hdev->req_status) != HCI_REQ_PEND,
 					       timeout);
 
 	if (err == -ERESTARTSYS)
 		return ERR_PTR(-EINTR);
 
-	switch (hdev->req_status) {
+	switch (READ_ONCE(hdev->req_status)) {
 	case HCI_REQ_DONE:
 		err = -bt_to_errno(hdev->req_result);
 		break;
@@ -194,7 +194,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
 		break;
 	}
 
-	hdev->req_status = 0;
+	WRITE_ONCE(hdev->req_status, 0);
 	hdev->req_result = 0;
 	skb = hdev->req_rsp;
 	hdev->req_rsp = NULL;
@@ -665,9 +665,9 @@ void hci_cmd_sync_cancel(struct hci_dev *hdev, int err)
 {
 	bt_dev_dbg(hdev, "err 0x%2.2x", err);
 
-	if (hdev->req_status == HCI_REQ_PEND) {
+	if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) {
 		hdev->req_result = err;
-		hdev->req_status = HCI_REQ_CANCELED;
+		WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED);
 
 		queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work);
 	}
@@ -683,12 +683,12 @@ void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err)
 {
 	bt_dev_dbg(hdev, "err 0x%2.2x", err);
 
-	if (hdev->req_status == HCI_REQ_PEND) {
+	if (READ_ONCE(hdev->req_status) == HCI_REQ_PEND) {
 		/* req_result is __u32 so error must be positive to be properly
 		 * propagated.
 		 */
 		hdev->req_result = err < 0 ? -err : err;
-		hdev->req_status = HCI_REQ_CANCELED;
+		WRITE_ONCE(hdev->req_status, HCI_REQ_CANCELED);
 
 		wake_up_interruptible(&hdev->req_wait_q);
 	}
-- 
cgit v1.2.3


From 31148a7be723aa9f2e8fbd62424825ab8d577973 Mon Sep 17 00:00:00 2001
From: Anas Iqbal <mohd.abd.6602@gmail.com>
Date: Sun, 15 Mar 2026 10:51:37 +0000
Subject: Bluetooth: hci_ll: Fix firmware leak on error path

Smatch reports:

drivers/bluetooth/hci_ll.c:587 download_firmware() warn:
'fw' from request_firmware() not released on lines: 544.

In download_firmware(), if request_firmware() succeeds but the returned
firmware content is invalid (no data or zero size), the function returns
without releasing the firmware, resulting in a resource leak.

Fix this by calling release_firmware() before returning when
request_firmware() succeeded but the firmware content is invalid.

Fixes: 371805522f87 ("bluetooth: hci_uart: add LL protocol serdev driver support")
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Anas Iqbal <mohd.abd.6602@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_ll.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c
index 91acf24f1ef5..91c96ad12342 100644
--- a/drivers/bluetooth/hci_ll.c
+++ b/drivers/bluetooth/hci_ll.c
@@ -541,6 +541,8 @@ static int download_firmware(struct ll_device *lldev)
 	if (err || !fw->data || !fw->size) {
 		bt_dev_err(lldev->hu.hdev, "request_firmware failed(errno %d) for %s",
 			   err, bts_scr_name);
+		if (!err)
+			release_firmware(fw);
 		return -EINVAL;
 	}
 	ptr = (void *)fw->data;
-- 
cgit v1.2.3


From b6552e0503973daf6f23bd6ed9273ef131ee364f Mon Sep 17 00:00:00 2001
From: Helen Koike <koike@igalia.com>
Date: Thu, 19 Mar 2026 08:58:01 -0300
Subject: Bluetooth: L2CAP: Fix null-ptr-deref on l2cap_sock_ready_cb

Before using sk pointer, check if it is null.

Fix the following:

 KASAN: null-ptr-deref in range [0x0000000000000260-0x0000000000000267]
 CPU: 0 UID: 0 PID: 5985 Comm: kworker/0:5 Not tainted 7.0.0-rc4-00029-ga989fde763f4 #1 PREEMPT(full)
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-9.fc43 06/10/2025
 Workqueue: events l2cap_info_timeout
 RIP: 0010:kasan_byte_accessible+0x12/0x30
 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce
 veth0_macvtap: entered promiscuous mode
 RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202
 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001
 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000
 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001
 FS:  0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00005582615a5008 CR3: 000000007007e000 CR4: 0000000000752ef0
 PKRU: 55555554
 Call Trace:
  <TASK>
  __kasan_check_byte+0x12/0x40
  lock_acquire+0x79/0x2e0
  lock_sock_nested+0x48/0x100
  ? l2cap_sock_ready_cb+0x46/0x160
  l2cap_sock_ready_cb+0x46/0x160
  l2cap_conn_start+0x779/0xff0
  ? __pfx_l2cap_conn_start+0x10/0x10
  ? l2cap_info_timeout+0x60/0xa0
  ? __pfx___mutex_lock+0x10/0x10
  l2cap_info_timeout+0x68/0xa0
  ? process_scheduled_works+0xa8d/0x18c0
  process_scheduled_works+0xb6e/0x18c0
  ? __pfx_process_scheduled_works+0x10/0x10
  ? assign_work+0x3d5/0x5e0
  worker_thread+0xa53/0xfc0
  kthread+0x388/0x470
  ? __pfx_worker_thread+0x10/0x10
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x51e/0xb90
  ? __pfx_ret_from_fork+0x10/0x10
 veth1_macvtap: entered promiscuous mode
  ? __switch_to+0xc7d/0x1450
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>
 Modules linked in:
 ---[ end trace 0000000000000000 ]---
 batman_adv: batadv0: Interface activated: batadv_slave_0
 batman_adv: batadv0: Interface activated: batadv_slave_1
 netdevsim netdevsim7 netdevsim0: set [1, 0] type 2 family 0 port 6081 - 0
 netdevsim netdevsim7 netdevsim1: set [1, 0] type 2 family 0 port 6081 - 0
 netdevsim netdevsim7 netdevsim2: set [1, 0] type 2 family 0 port 6081 - 0
 netdevsim netdevsim7 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0
 RIP: 0010:kasan_byte_accessible+0x12/0x30
 Code: 79 ff ff ff 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 40 d6 48 c1 ef 03 48 b8 00 00 00 00 00 fc ff df <0f> b6 04 07 3c 08 0f 92 c0 c3 cc cce
 ieee80211 phy39: Selected rate control algorithm 'minstrel_ht'
 RSP: 0018:ffffc90006e0f808 EFLAGS: 00010202
 RAX: dffffc0000000000 RBX: ffffffff89746018 RCX: 0000000080000001
 RDX: 0000000000000000 RSI: ffffffff89746018 RDI: 000000000000004c
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
 R10: dffffc0000000000 R11: ffffffff8aae3e70 R12: 0000000000000000
 R13: 0000000000000260 R14: 0000000000000260 R15: 0000000000000001
 FS:  0000000000000000(0000) GS:ffff8880983c2000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f7e16139e9c CR3: 000000000e74e000 CR4: 0000000000752ef0
 PKRU: 55555554
 Kernel panic - not syncing: Fatal exception

Fixes: 54a59aa2b562 ("Bluetooth: Add l2cap_chan->ops->ready()")
Signed-off-by: Helen Koike <koike@igalia.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_sock.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 597686790371..71e8c1b45bce 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1698,6 +1698,9 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 	struct sock *sk = chan->data;
 	struct sock *parent;
 
+	if (!sk)
+		return;
+
 	lock_sock(sk);
 
 	parent = bt_sk(sk)->parent;
-- 
cgit v1.2.3


From 761fb8ec8778f0caf2bba5a41e3cff1ea86974f3 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 17 Mar 2026 11:54:01 -0400
Subject: Bluetooth: L2CAP: Fix regressions caused by reusing ident

This attempt to fix regressions caused by reusing ident which apparently
is not handled well on certain stacks causing the stack to not respond to
requests, so instead of simple returning the first unallocated id this
stores the last used tx_ident and then attempt to use the next until all
available ids are exausted and then cycle starting over to 1.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221120
Link: https://bugzilla.kernel.org/show_bug.cgi?id=221177
Fixes: 6c3ea155e5ee ("Bluetooth: L2CAP: Fix not tracking outstanding TX ident")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Tested-by: Christian Eggers <ceggers@arri.de>
---
 include/net/bluetooth/l2cap.h |  1 +
 net/bluetooth/l2cap_core.c    | 29 ++++++++++++++++++++++++++---
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 010f1a8fd15f..5172afee5494 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -658,6 +658,7 @@ struct l2cap_conn {
 	struct sk_buff		*rx_skb;
 	__u32			rx_len;
 	struct ida		tx_ida;
+	__u8			tx_ident;
 
 	struct sk_buff_head	pending_rx;
 	struct work_struct	pending_rx_work;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 30fd6848938e..3de3e3c8e966 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -926,16 +926,39 @@ int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator)
 
 static int l2cap_get_ident(struct l2cap_conn *conn)
 {
+	u8 max;
+	int ident;
+
 	/* LE link does not support tools like l2ping so use the full range */
 	if (conn->hcon->type == LE_LINK)
-		return ida_alloc_range(&conn->tx_ida, 1, 255, GFP_ATOMIC);
-
+		max = 255;
 	/* Get next available identificator.
 	 *    1 - 128 are used by kernel.
 	 *  129 - 199 are reserved.
 	 *  200 - 254 are used by utilities like l2ping, etc.
 	 */
-	return ida_alloc_range(&conn->tx_ida, 1, 128, GFP_ATOMIC);
+	else
+		max = 128;
+
+	/* Allocate ident using min as last used + 1 (cyclic) */
+	ident = ida_alloc_range(&conn->tx_ida, READ_ONCE(conn->tx_ident) + 1,
+				max, GFP_ATOMIC);
+	/* Force min 1 to start over */
+	if (ident <= 0) {
+		ident = ida_alloc_range(&conn->tx_ida, 1, max, GFP_ATOMIC);
+		if (ident <= 0) {
+			/* If all idents are in use, log an error, this is
+			 * extremely unlikely to happen and would indicate a bug
+			 * in the code that idents are not being freed properly.
+			 */
+			BT_ERR("Unable to allocate ident: %d", ident);
+			return 0;
+		}
+	}
+
+	WRITE_ONCE(conn->tx_ident, ident);
+
+	return ident;
 }
 
 static void l2cap_send_acl(struct l2cap_conn *conn, struct sk_buff *skb,
-- 
cgit v1.2.3


From 8f9f64c8f90dca07d3b9f1d7ce5d34ccd246c9dd Mon Sep 17 00:00:00 2001
From: Luca Leonardo Scorcia <l.scorcia@gmail.com>
Date: Tue, 17 Mar 2026 11:02:06 +0000
Subject: pinctrl: mediatek: common: Fix probe failure for devices without EINT

Some pinctrl devices like mt6397 or mt6392 don't support EINT at all, but
the mtk_eint_init function is always called and returns -ENODEV, which
then bubbles up and causes probe failure.

To address this only call mtk_eint_init if EINT pins are present.

Tested on Xiaomi Mi Smart Clock x04g (mt6392).

Fixes: e46df235b4e6 ("pinctrl: mediatek: refactor EINT related code for all MediaTek pinctrl can fit")
Signed-off-by: Luca Leonardo Scorcia <l.scorcia@gmail.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index d6a46fe0cda8..3f518dce6d23 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1135,9 +1135,12 @@ int mtk_pctrl_init(struct platform_device *pdev,
 		goto chip_error;
 	}
 
-	ret = mtk_eint_init(pctl, pdev);
-	if (ret)
-		goto chip_error;
+	/* Only initialize EINT if we have EINT pins */
+	if (data->eint_hw.ap_num > 0) {
+		ret = mtk_eint_init(pctl, pdev);
+		if (ret)
+			goto chip_error;
+	}
 
 	return 0;
 
-- 
cgit v1.2.3


From 23b5df09c27aec13962b30d32a4167ebdd043f8e Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 18 Mar 2026 21:43:51 -0300
Subject: smb: client: fix generic/694 due to wrong ->i_blocks

When updating ->i_size, make sure to always update ->i_blocks as well
until we query new allocation size from the server.

generic/694 was failing because smb3_simple_falloc() was missing the
update of ->i_blocks after calling cifs_setsize().  So, fix this by
updating ->i_blocks directly in cifs_setsize(), so all places that
call it doesn't need to worry about updating ->i_blocks later.

Reported-by: Shyam Prasad N <sprasad@microsoft.com>
Closes: https://lore.kernel.org/r/CANT5p=rqgRwaADB=b_PhJkqXjtfq3SFv41SSTXSVEHnuh871pA@mail.gmail.com
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h |  6 ++++++
 fs/smb/client/file.c     |  1 -
 fs/smb/client/inode.c    | 21 ++++++---------------
 fs/smb/client/smb2ops.c  | 20 ++++----------------
 4 files changed, 16 insertions(+), 32 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 7877d327dbb0..709e96e07791 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -2386,4 +2386,10 @@ static inline int cifs_open_create_options(unsigned int oflags, int opts)
 	return opts;
 }
 
+/*
+ * The number of blocks is not related to (i_size / i_blksize), but instead
+ * 512 byte (2**9) size is required for calculating num blocks.
+ */
+#define CIFS_INO_BLOCKS(size) DIV_ROUND_UP_ULL((u64)(size), 512)
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 27f61fe7e4e2..a69e05f86d7e 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -993,7 +993,6 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry)
 		if (!rc) {
 			netfs_resize_file(&cinode->netfs, 0, true);
 			cifs_setsize(inode, 0);
-			inode->i_blocks = 0;
 		}
 	}
 	if (cfile)
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 143fa2e665ed..888f9e35f14b 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -219,13 +219,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
 	 */
 	if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) {
 		i_size_write(inode, fattr->cf_eof);
-
-		/*
-		 * i_blocks is not related to (i_size / i_blksize),
-		 * but instead 512 byte (2**9) size is required for
-		 * calculating num blocks.
-		 */
-		inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9;
+		inode->i_blocks = CIFS_INO_BLOCKS(fattr->cf_bytes);
 	}
 
 	if (S_ISLNK(fattr->cf_mode) && fattr->cf_symlink_target) {
@@ -3015,6 +3009,11 @@ void cifs_setsize(struct inode *inode, loff_t offset)
 {
 	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
+	/*
+	 * Until we can query the server for actual allocation size,
+	 * this is best estimate we have for blocks allocated for a file.
+	 */
+	inode->i_blocks = CIFS_INO_BLOCKS(offset);
 	spin_unlock(&inode->i_lock);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	truncate_pagecache(inode, offset);
@@ -3087,14 +3086,6 @@ set_size_out:
 	if (rc == 0) {
 		netfs_resize_file(&cifsInode->netfs, size, true);
 		cifs_setsize(inode, size);
-		/*
-		 * i_blocks is not related to (i_size / i_blksize), but instead
-		 * 512 byte (2**9) size is required for calculating num blocks.
-		 * Until we can query the server for actual allocation size,
-		 * this is best estimate we have for blocks allocated for a file
-		 * Number of blocks must be rounded up so size 1 is not 0 blocks
-		 */
-		inode->i_blocks = (512 - 1 + size) >> 9;
 	}
 
 	return rc;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 98ac4e86bf99..509fcea28a42 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1497,6 +1497,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_file_network_open_info file_inf;
 	struct inode *inode;
+	u64 asize;
 	int rc;
 
 	rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid,
@@ -1520,14 +1521,9 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
 		inode_set_atime_to_ts(inode,
 				      cifs_NTtimeToUnix(file_inf.LastAccessTime));
 
-	/*
-	 * i_blocks is not related to (i_size / i_blksize),
-	 * but instead 512 byte (2**9) size is required for
-	 * calculating num blocks.
-	 */
-	if (le64_to_cpu(file_inf.AllocationSize) > 4096)
-		inode->i_blocks =
-			(512 - 1 + le64_to_cpu(file_inf.AllocationSize)) >> 9;
+	asize = le64_to_cpu(file_inf.AllocationSize);
+	if (asize > 4096)
+		inode->i_blocks = CIFS_INO_BLOCKS(asize);
 
 	/* End of file and Attributes should not have to be updated on close */
 	spin_unlock(&inode->i_lock);
@@ -2204,14 +2200,6 @@ smb2_duplicate_extents(const unsigned int xid,
 		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
 		if (rc)
 			goto duplicate_extents_out;
-
-		/*
-		 * Although also could set plausible allocation size (i_blocks)
-		 * here in addition to setting the file size, in reflink
-		 * it is likely that the target file is sparse. Its allocation
-		 * size will be queried on next revalidate, but it is important
-		 * to make sure that file's cached size is updated immediately
-		 */
 		netfs_resize_file(netfs_inode(inode), dest_off + len, true);
 		cifs_setsize(inode, dest_off + len);
 	}
-- 
cgit v1.2.3


From a54142d9ff49dadb8bd063b8d016546e5706184c Mon Sep 17 00:00:00 2001
From: Mickaël Salaün <mic@digikod.net>
Date: Tue, 10 Mar 2026 20:04:15 +0100
Subject: selftests/landlock: Test tsync interruption and cancellation paths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add tsync_interrupt test to exercise the signal interruption path in
landlock_restrict_sibling_threads().  When a signal interrupts
wait_for_completion_interruptible() while the calling thread waits for
sibling threads to finish credential preparation, the kernel:

1. Sets ERESTARTNOINTR to request a transparent syscall restart.
2. Calls cancel_tsync_works() to opportunistically dequeue task works
   that have not started running yet.
3. Breaks out of the preparation loop, then unblocks remaining
   task works via complete_all() and waits for them to finish.
4. Returns the error, causing abort_creds() in the syscall handler.

Specifically, cancel_tsync_works() in its entirety, the ERESTARTNOINTR
error branch in landlock_restrict_sibling_threads(), and the
abort_creds() error branch in the landlock_restrict_self() syscall
handler are timing-dependent and not exercised by the existing tsync
tests, making code coverage measurements non-deterministic.

The test spawns a signaler thread that rapidly sends SIGUSR1 to the
calling thread while it performs landlock_restrict_self() with
LANDLOCK_RESTRICT_SELF_TSYNC.  Since ERESTARTNOINTR causes a
transparent restart, userspace always sees the syscall succeed.

This is a best-effort coverage test: the interruption path is exercised
when the signal lands during the preparation wait, which depends on
thread scheduling.  The test creates enough idle sibling threads (200)
to ensure multiple serialized waves of credential preparation even on
machines with many cores (e.g., 64), widening the window for the
signaler.  Deterministic coverage would require wrapping the wait call
with ALLOW_ERROR_INJECTION() and using CONFIG_FAIL_FUNCTION.

Test coverage for security/landlock was 90.2% of 2105 lines according to
LLVM 21, and it is now 91.1% of 2105 lines with this new test.

Cc: Günther Noack <gnoack@google.com>
Cc: Justin Suess <utilityemal77@gmail.com>
Cc: Tingmao Wang <m@maowtm.org>
Cc: Yihan Ding <dingyihan@uniontech.com>
Link: https://lore.kernel.org/r/20260310190416.1913908-1-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/tsync_test.c | 91 ++++++++++++++++++++++++++-
 1 file changed, 90 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/landlock/tsync_test.c b/tools/testing/selftests/landlock/tsync_test.c
index 37ef0d2270db..2b9ad4f154f4 100644
--- a/tools/testing/selftests/landlock/tsync_test.c
+++ b/tools/testing/selftests/landlock/tsync_test.c
@@ -6,9 +6,10 @@
  */
 
 #define _GNU_SOURCE
+#include <linux/landlock.h>
 #include <pthread.h>
+#include <signal.h>
 #include <sys/prctl.h>
-#include <linux/landlock.h>
 
 #include "common.h"
 
@@ -158,4 +159,92 @@ TEST(competing_enablement)
 	EXPECT_EQ(0, close(ruleset_fd));
 }
 
+static void signal_nop_handler(int sig)
+{
+}
+
+struct signaler_data {
+	pthread_t target;
+	volatile bool stop;
+};
+
+static void *signaler_thread(void *data)
+{
+	struct signaler_data *sd = data;
+
+	while (!sd->stop)
+		pthread_kill(sd->target, SIGUSR1);
+
+	return NULL;
+}
+
+/*
+ * Number of idle sibling threads.  This must be large enough that even on
+ * machines with many cores, the sibling threads cannot all complete their
+ * credential preparation in a single parallel wave, otherwise the signaler
+ * thread has no window to interrupt wait_for_completion_interruptible().
+ * 200 threads on a 64-core machine yields ~3 serialized waves, giving the
+ * tight signal loop enough time to land an interruption.
+ */
+#define NUM_IDLE_THREADS 200
+
+/*
+ * Exercises the tsync interruption and cancellation paths in tsync.c.
+ *
+ * When a signal interrupts the calling thread while it waits for sibling
+ * threads to finish their credential preparation
+ * (wait_for_completion_interruptible in landlock_restrict_sibling_threads),
+ * the kernel sets ERESTARTNOINTR, cancels queued task works that have not
+ * started yet (cancel_tsync_works), then waits for the remaining works to
+ * finish.  On the error return, syscalls.c aborts the prepared credentials.
+ * The kernel automatically restarts the syscall, so userspace sees success.
+ */
+TEST(tsync_interrupt)
+{
+	size_t i;
+	pthread_t threads[NUM_IDLE_THREADS];
+	pthread_t signaler;
+	struct signaler_data sd;
+	struct sigaction sa = {};
+	const int ruleset_fd = create_ruleset(_metadata);
+
+	disable_caps(_metadata);
+
+	/* Install a no-op SIGUSR1 handler so the signal does not kill us. */
+	sa.sa_handler = signal_nop_handler;
+	sigemptyset(&sa.sa_mask);
+	ASSERT_EQ(0, sigaction(SIGUSR1, &sa, NULL));
+
+	ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+
+	for (i = 0; i < NUM_IDLE_THREADS; i++)
+		ASSERT_EQ(0, pthread_create(&threads[i], NULL, idle, NULL));
+
+	/*
+	 * Start a signaler thread that continuously sends SIGUSR1 to the
+	 * calling thread.  This maximizes the chance of interrupting
+	 * wait_for_completion_interruptible() in the kernel's tsync path.
+	 */
+	sd.target = pthread_self();
+	sd.stop = false;
+	ASSERT_EQ(0, pthread_create(&signaler, NULL, signaler_thread, &sd));
+
+	/*
+	 * The syscall may be interrupted and transparently restarted by the
+	 * kernel (ERESTARTNOINTR).  From userspace, it should always succeed.
+	 */
+	EXPECT_EQ(0, landlock_restrict_self(ruleset_fd,
+					    LANDLOCK_RESTRICT_SELF_TSYNC));
+
+	sd.stop = true;
+	ASSERT_EQ(0, pthread_join(signaler, NULL));
+
+	for (i = 0; i < NUM_IDLE_THREADS; i++) {
+		ASSERT_EQ(0, pthread_cancel(threads[i]));
+		ASSERT_EQ(0, pthread_join(threads[i], NULL));
+	}
+
+	EXPECT_EQ(0, close(ruleset_fd));
+}
+
 TEST_HARNESS_MAIN
-- 
cgit v1.2.3


From 3ecd3e03144b38a21a3b70254f1b9d2e16629b09 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 19 Mar 2026 14:29:09 -0600
Subject: io_uring/kbuf: fix missing BUF_MORE for incremental buffers at EOF

For a zero length transfer, io_kbuf_inc_commit() is called with !len.
Since we never enter the while loop to consume the buffers,
io_kbuf_inc_commit() ends up returning true, consuming the buffer. But
if no data was consumed, by definition it cannot have consumed the
buffer. Return false for that case.

Reported-by: Martin Michaelis <code@mgjm.de>
Cc: stable@vger.kernel.org
Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Link: https://github.com/axboe/liburing/issues/1553
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index e7f444953dfb..a4cb6752b7aa 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -34,6 +34,10 @@ struct io_provide_buf {
 
 static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 {
+	/* No data consumed, return false early to avoid consuming the buffer */
+	if (!len)
+		return false;
+
 	while (len) {
 		struct io_uring_buf *buf;
 		u32 buf_len, this_len;
-- 
cgit v1.2.3


From 418eab7a6f3c002d8e64d6e95ec27118017019af Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 19 Mar 2026 14:29:20 -0600
Subject: io_uring/kbuf: propagate BUF_MORE through early buffer commit path

When io_should_commit() returns true (eg for non-pollable files), buffer
commit happens at buffer selection time and sel->buf_list is set to
NULL. When __io_put_kbufs() generates CQE flags at completion time, it
calls __io_put_kbuf_ring() which finds a NULL buffer_list and hence
cannot determine whether the buffer was consumed or not. This means that
IORING_CQE_F_BUF_MORE is never set for non-pollable input with
incrementally consumed buffers.

Likewise for io_buffers_select(), which always commits upfront and
discards the return value of io_kbuf_commit().

Add REQ_F_BUF_MORE to store the result of io_kbuf_commit() during early
commit. Then __io_put_kbuf_ring() can check this flag and set
IORING_F_BUF_MORE accordingy.

Reported-by: Martin Michaelis <code@mgjm.de>
Cc: stable@vger.kernel.org
Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Link: https://github.com/axboe/liburing/issues/1553
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  3 +++
 io_uring/kbuf.c                | 10 +++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index dd1420bfcb73..214fdbd49052 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -541,6 +541,7 @@ enum {
 	REQ_F_BL_NO_RECYCLE_BIT,
 	REQ_F_BUFFERS_COMMIT_BIT,
 	REQ_F_BUF_NODE_BIT,
+	REQ_F_BUF_MORE_BIT,
 	REQ_F_HAS_METADATA_BIT,
 	REQ_F_IMPORT_BUFFER_BIT,
 	REQ_F_SQE_COPIED_BIT,
@@ -626,6 +627,8 @@ enum {
 	REQ_F_BUFFERS_COMMIT	= IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
 	/* buf node is valid */
 	REQ_F_BUF_NODE		= IO_REQ_FLAG(REQ_F_BUF_NODE_BIT),
+	/* incremental buffer consumption, more space available */
+	REQ_F_BUF_MORE		= IO_REQ_FLAG(REQ_F_BUF_MORE_BIT),
 	/* request has read/write metadata assigned */
 	REQ_F_HAS_METADATA	= IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT),
 	/*
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index a4cb6752b7aa..f72f38d22d2b 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -216,7 +216,8 @@ static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr));
 
 	if (io_should_commit(req, issue_flags)) {
-		io_kbuf_commit(req, sel.buf_list, *len, 1);
+		if (!io_kbuf_commit(req, sel.buf_list, *len, 1))
+			req->flags |= REQ_F_BUF_MORE;
 		sel.buf_list = NULL;
 	}
 	return sel;
@@ -349,7 +350,8 @@ int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg,
 		 */
 		if (ret > 0) {
 			req->flags |= REQ_F_BUFFERS_COMMIT | REQ_F_BL_NO_RECYCLE;
-			io_kbuf_commit(req, sel->buf_list, arg->out_len, ret);
+			if (!io_kbuf_commit(req, sel->buf_list, arg->out_len, ret))
+				req->flags |= REQ_F_BUF_MORE;
 		}
 	} else {
 		ret = io_provided_buffers_select(req, &arg->out_len, sel->buf_list, arg->iovs);
@@ -395,8 +397,10 @@ static inline bool __io_put_kbuf_ring(struct io_kiocb *req,
 
 	if (bl)
 		ret = io_kbuf_commit(req, bl, len, nr);
+	if (ret && (req->flags & REQ_F_BUF_MORE))
+		ret = false;
 
-	req->flags &= ~REQ_F_BUFFER_RING;
+	req->flags &= ~(REQ_F_BUFFER_RING | REQ_F_BUF_MORE);
 	return ret;
 }
 
-- 
cgit v1.2.3


From be5c5280cf2b20e363dc8e2a424dd200a29b1c77 Mon Sep 17 00:00:00 2001
From: Cui Chao <cuichao1753@phytium.com.cn>
Date: Thu, 19 Mar 2026 15:45:35 +0800
Subject: cxl: Adjust the startup priority of cxl_pmem to be higher than that
 of cxl_acpi

During the cxl_acpi probe process, it checks whether the cxl_nvb device
and driver have been attached. Currently, the startup priority of the
cxl_pmem driver is lower than that of the cxl_acpi driver. At this point,
the cxl_nvb driver has not yet been registered on the cxl_bus, causing
the attachment check to fail. This results in a failure to add the root
nvdimm bridge, leading to a cxl_acpi probe failure and ultimately
affecting the subsequent loading of cxl drivers. As a consequence, only
one mem device object exists on the cxl_bus, while the cxl_port device
objects and decoder device objects are missing.

The solution is to raise the startup priority of cxl_pmem to be higher
than that of cxl_acpi, ensuring that the cxl_pmem driver is registered
before the aforementioned attachment check occurs.

Co-developed-by: Wang Yinfeng <wangyinfeng@phytium.com.cn>
Signed-off-by: Wang Yinfeng <wangyinfeng@phytium.com.cn>
Signed-off-by: Cui Chao <cuichao1753@phytium.com.cn>
Fixes: e7e222ad73d9 ("cxl: Move devm_cxl_add_nvdimm_bridge() to cxl_pmem.ko")
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20260319074535.1709250-1-cuichao1753@phytium.com.cn
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/pmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index 082ec0f1c3a0..261dff7ced9f 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -554,7 +554,7 @@ static __exit void cxl_pmem_exit(void)
 
 MODULE_DESCRIPTION("CXL PMEM: Persistent Memory Support");
 MODULE_LICENSE("GPL v2");
-module_init(cxl_pmem_init);
+subsys_initcall(cxl_pmem_init);
 module_exit(cxl_pmem_exit);
 MODULE_IMPORT_NS("CXL");
 MODULE_ALIAS_CXL(CXL_DEVICE_NVDIMM_BRIDGE);
-- 
cgit v1.2.3


From aa79f996eb41e95aed85a1bd7f56bcd6a3842008 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 9 Mar 2026 08:50:16 +0100
Subject: i2c: cp2615: fix serial string NULL-deref at probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cp2615 driver uses the USB device serial string as the i2c adapter
name but does not make sure that the string exists.

Verify that the device has a serial number before accessing it to avoid
triggering a NULL-pointer dereference (e.g. with malicious devices).

Fixes: 4a7695429ead ("i2c: cp2615: add i2c driver for Silicon Labs' CP2615 Digital Audio Bridge")
Cc: stable@vger.kernel.org	# 5.13
Cc: Bence Csókás <bence98@sch.bme.hu>
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Bence Csókás <bence98@sch.bme.hu>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260309075016.25612-1-johan@kernel.org
---
 drivers/i2c/busses/i2c-cp2615.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/i2c/busses/i2c-cp2615.c b/drivers/i2c/busses/i2c-cp2615.c
index e2d7cd2390fc..8212875700e1 100644
--- a/drivers/i2c/busses/i2c-cp2615.c
+++ b/drivers/i2c/busses/i2c-cp2615.c
@@ -298,6 +298,9 @@ cp2615_i2c_probe(struct usb_interface *usbif, const struct usb_device_id *id)
 	if (!adap)
 		return -ENOMEM;
 
+	if (!usbdev->serial)
+		return -EINVAL;
+
 	strscpy(adap->name, usbdev->serial, sizeof(adap->name));
 	adap->owner = THIS_MODULE;
 	adap->dev.parent = &usbif->dev;
-- 
cgit v1.2.3


From be627abcc0d5dbd5882873bd85fbc18aa3d189ed Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 1 Mar 2026 17:21:01 +0100
Subject: i2c: fsi: Fix a potential leak in fsi_i2c_probe()

In the commit in Fixes:, when the code has been updated to use an explicit
for loop, instead of for_each_available_child_of_node(), the assumption
that a reference to a device_node structure would be released at each
iteration has been broken.

Now, an explicit of_node_put() is needed to release the reference.

Fixes: 095561f476ab ("i2c: fsi: Create busses for all ports")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: <stable@vger.kernel.org> # v5.3+
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/fd805c39f8de51edf303856103d782138a1633c8.1772382022.git.christophe.jaillet@wanadoo.fr
---
 drivers/i2c/busses/i2c-fsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-fsi.c b/drivers/i2c/busses/i2c-fsi.c
index 82c87e04ac6f..b2dc5ae1d0e4 100644
--- a/drivers/i2c/busses/i2c-fsi.c
+++ b/drivers/i2c/busses/i2c-fsi.c
@@ -729,6 +729,7 @@ static int fsi_i2c_probe(struct fsi_device *fsi_dev)
 		rc = i2c_add_adapter(&port->adapter);
 		if (rc < 0) {
 			dev_err(dev, "Failed to register adapter: %d\n", rc);
+			of_node_put(np);
 			kfree(port);
 			continue;
 		}
-- 
cgit v1.2.3


From cbcb3cfcdc436d6f91a3d95ecfa9c831abe14aed Mon Sep 17 00:00:00 2001
From: Mohammad Heib <mheib@redhat.com>
Date: Tue, 17 Mar 2026 19:08:06 +0200
Subject: ionic: fix persistent MAC address override on PF

The use of IONIC_CMD_LIF_SETATTR in the MAC address update path causes
the ionic firmware to update the LIF's identity in its persistent state.
Since the firmware state is maintained across host warm boots and driver
reloads, any MAC change on the Physical Function (PF) becomes "sticky.

This is problematic because it causes ethtool -P to report the
user-configured MAC as the permanent factory address, which breaks
system management tools that rely on a stable hardware identity.

While Virtual Functions (VFs) need this hardware-level programming to
properly handle MAC assignments in guest environments, the PF should
maintain standard transient behavior. This patch gates the
ionic_program_mac call using is_virtfn so that PF MAC changes remain
local to the netdev filters and do not overwrite the firmware's
permanent identity block.

Fixes: 19058be7c48c ("ionic: VF initial random MAC address if no assigned mac")
Signed-off-by: Mohammad Heib <mheib@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20260317170806.35390-1-mheib@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 8d040e611d5a..637e635bbf03 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1719,13 +1719,18 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
 	if (ether_addr_equal(netdev->dev_addr, mac))
 		return 0;
 
-	err = ionic_program_mac(lif, mac);
-	if (err < 0)
-		return err;
+	/* Only program macs for virtual functions to avoid losing the permanent
+	 * Mac across warm reset/reboot.
+	 */
+	if (lif->ionic->pdev->is_virtfn) {
+		err = ionic_program_mac(lif, mac);
+		if (err < 0)
+			return err;
 
-	if (err > 0)
-		netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
-			   __func__);
+		if (err > 0)
+			netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
+				   __func__);
+	}
 
 	err = eth_prepare_mac_addr_change(netdev, addr);
 	if (err)
-- 
cgit v1.2.3


From 78a6ee14f8b9e1c8f7c77612122444f3be8dc8cc Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Thu, 26 Feb 2026 14:11:27 +0100
Subject: i2c: pxa: defer reset on Armada 3700 when recovery is used

The I2C communication is completely broken on the Armada 3700 platform
since commit 0b01392c18b9 ("i2c: pxa: move to generic GPIO recovery").

For example, on the Methode uDPU board, probing of the two onboard
temperature sensors fails ...

  [    7.271713] i2c i2c-0: using pinctrl states for GPIO recovery
  [    7.277503] i2c i2c-0:  PXA I2C adapter
  [    7.282199] i2c i2c-1: using pinctrl states for GPIO recovery
  [    7.288241] i2c i2c-1:  PXA I2C adapter
  [    7.292947] sfp sfp-eth1: Host maximum power 3.0W
  [    7.299614] sfp sfp-eth0: Host maximum power 3.0W
  [    7.308178] lm75 1-0048: supply vs not found, using dummy regulator
  [   32.489631] lm75 1-0048: probe with driver lm75 failed with error -121
  [   32.496833] lm75 1-0049: supply vs not found, using dummy regulator
  [   82.890614] lm75 1-0049: probe with driver lm75 failed with error -121

... and accessing the plugged-in SFP modules also does not work:

  [  511.298537] sfp sfp-eth1: please wait, module slow to respond
  [  536.488530] sfp sfp-eth0: please wait, module slow to respond
  ...
  [ 1065.688536] sfp sfp-eth1: failed to read EEPROM: -EREMOTEIO
  [ 1090.888532] sfp sfp-eth0: failed to read EEPROM: -EREMOTEIO

After a discussion [1], there was an attempt to fix the problem by
reverting the offending change by commit 7b211c767121 ("Revert "i2c:
pxa: move to generic GPIO recovery""), but that only helped to fix
the issue in the 6.1.y stable tree. The reason behind the partial succes
is that there was another change in commit 20cb3fce4d60 ("i2c: Set i2c
pinctrl recovery info from it's device pinctrl") in the 6.3-rc1 cycle
which broke things further.

The cause of the problem is the same in case of both offending commits
mentioned above. Namely, the I2C core code changes the pinctrl state to
GPIO while running the recovery initialization code. Although the PXA
specific initialization also does this, but the key difference is that
it happens before the controller is getting enabled in i2c_pxa_reset(),
whereas in the case of the generic initialization it happens after that.

Change the code to reset the controller only before the first transfer
instead of before registering the controller. This ensures that the
controller is not enabled at the time when the generic recovery code
performs the pinctrl state changes, thus avoids the problem described
above.

As the result this change restores the original behaviour, which in
turn makes the I2C communication to work again as it can be seen from
the following log:

  [    7.363250] i2c i2c-0: using pinctrl states for GPIO recovery
  [    7.369041] i2c i2c-0:  PXA I2C adapter
  [    7.373673] i2c i2c-1: using pinctrl states for GPIO recovery
  [    7.379742] i2c i2c-1:  PXA I2C adapter
  [    7.384506] sfp sfp-eth1: Host maximum power 3.0W
  [    7.393013] sfp sfp-eth0: Host maximum power 3.0W
  [    7.399266] lm75 1-0048: supply vs not found, using dummy regulator
  [    7.407257] hwmon hwmon0: temp1_input not attached to any thermal zone
  [    7.413863] lm75 1-0048: hwmon0: sensor 'tmp75c'
  [    7.418746] lm75 1-0049: supply vs not found, using dummy regulator
  [    7.426371] hwmon hwmon1: temp1_input not attached to any thermal zone
  [    7.432972] lm75 1-0049: hwmon1: sensor 'tmp75c'
  [    7.755092] sfp sfp-eth1: module MENTECHOPTO      POS22-LDCC-KR    rev 1.0  sn MNC208U90009     dc 200828
  [    7.764997] mvneta d0040000.ethernet eth1: unsupported SFP module: no common interface modes
  [    7.785362] sfp sfp-eth0: module Mikrotik         S-RJ01           rev 1.0  sn 61B103C55C58     dc 201022
  [    7.803426] hwmon hwmon2: temp1_input not attached to any thermal zone

Link: https://lore.kernel.org/r/20230926160255.330417-1-robert.marko@sartura.hr #1

Cc: stable@vger.kernel.org # 6.3+
Fixes: 20cb3fce4d60 ("i2c: Set i2c pinctrl recovery info from it's device pinctrl")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Tested-by: Robert Marko <robert.marko@sartura.hr>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260226-i2c-pxa-fix-i2c-communication-v4-1-797a091dae87@gmail.com
---
 drivers/i2c/busses/i2c-pxa.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 09af3b3625f1..f55840b2eb9a 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -268,6 +268,7 @@ struct pxa_i2c {
 	struct pinctrl		*pinctrl;
 	struct pinctrl_state	*pinctrl_default;
 	struct pinctrl_state	*pinctrl_recovery;
+	bool			reset_before_xfer;
 };
 
 #define _IBMR(i2c)	((i2c)->reg_ibmr)
@@ -1144,6 +1145,11 @@ static int i2c_pxa_xfer(struct i2c_adapter *adap,
 {
 	struct pxa_i2c *i2c = adap->algo_data;
 
+	if (i2c->reset_before_xfer) {
+		i2c_pxa_reset(i2c);
+		i2c->reset_before_xfer = false;
+	}
+
 	return i2c_pxa_internal_xfer(i2c, msgs, num, i2c_pxa_do_xfer);
 }
 
@@ -1521,7 +1527,16 @@ static int i2c_pxa_probe(struct platform_device *dev)
 		}
 	}
 
-	i2c_pxa_reset(i2c);
+	/*
+	 * Skip reset on Armada 3700 when recovery is used to avoid
+	 * controller hang due to the pinctrl state changes done by
+	 * the generic recovery initialization code. The reset will
+	 * be performed later, prior to the first transfer.
+	 */
+	if (i2c_type == REGS_A3700 && i2c->adap.bus_recovery_info)
+		i2c->reset_before_xfer = true;
+	else
+		i2c_pxa_reset(i2c);
 
 	ret = i2c_add_numbered_adapter(&i2c->adap);
 	if (ret < 0)
-- 
cgit v1.2.3


From 4527025d440ce84bf56e75ce1df2e84cb8178616 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 17 Mar 2026 12:33:34 -0700
Subject: nfc: nci: fix circular locking dependency in nci_close_device

nci_close_device() flushes rx_wq and tx_wq while holding req_lock.
This causes a circular locking dependency because nci_rx_work()
running on rx_wq can end up taking req_lock too:

  nci_rx_work -> nci_rx_data_packet -> nci_data_exchange_complete
    -> __sk_destruct -> rawsock_destruct -> nfc_deactivate_target
    -> nci_deactivate_target -> nci_request -> mutex_lock(&ndev->req_lock)

Move the flush of rx_wq after req_lock has been released.
This should safe (I think) because NCI_UP has already been cleared
and the transport is closed, so the work will see it and return
-ENETDOWN.

NIPA has been hitting this running the nci selftest with a debug
kernel on roughly 4% of the runs.

Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation")
Reviewed-by: Ian Ray <ian.ray@gehealthcare.com>
Link: https://patch.msgid.link/20260317193334.988609-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/core.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 43d871525dbc..5f46c4b5720f 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -579,8 +579,7 @@ static int nci_close_device(struct nci_dev *ndev)
 	skb_queue_purge(&ndev->rx_q);
 	skb_queue_purge(&ndev->tx_q);
 
-	/* Flush RX and TX wq */
-	flush_workqueue(ndev->rx_wq);
+	/* Flush TX wq, RX wq flush can't be under the lock */
 	flush_workqueue(ndev->tx_wq);
 
 	/* Reset device */
@@ -592,13 +591,13 @@ static int nci_close_device(struct nci_dev *ndev)
 		      msecs_to_jiffies(NCI_RESET_TIMEOUT));
 
 	/* After this point our queues are empty
-	 * and no works are scheduled.
+	 * rx work may be running but will see that NCI_UP was cleared
 	 */
 	ndev->ops->close(ndev);
 
 	clear_bit(NCI_INIT, &ndev->flags);
 
-	/* Flush cmd wq */
+	/* Flush cmd and tx wq */
 	flush_workqueue(ndev->cmd_wq);
 
 	timer_delete_sync(&ndev->cmd_timer);
@@ -613,6 +612,9 @@ static int nci_close_device(struct nci_dev *ndev)
 
 	mutex_unlock(&ndev->req_lock);
 
+	/* rx_work may take req_lock via nci_deactivate_target */
+	flush_workqueue(ndev->rx_wq);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 7c770dadfda5cbbde6aa3c4363ed513f1d212bf8 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Wed, 18 Mar 2026 16:55:51 +0100
Subject: net: openvswitch: Avoid releasing netdev before teardown completes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The patch cited in the Fixes tag below changed the teardown code for
OVS ports to no longer unconditionally take the RTNL. After this change,
the netdev_destroy() callback can proceed immediately to the call_rcu()
invocation if the IFF_OVS_DATAPATH flag is already cleared on the
netdev.

The ovs_netdev_detach_dev() function clears the flag before completing
the unregistration, and if it gets preempted after clearing the flag (as
can happen on an -rt kernel), netdev_destroy() can complete and the
device can be freed before the unregistration completes. This leads to a
splat like:

[  998.393867] Oops: general protection fault, probably for non-canonical address 0xff00000001000239: 0000 [#1] SMP PTI
[  998.393877] CPU: 42 UID: 0 PID: 55177 Comm: ip Kdump: loaded Not tainted 6.12.0-211.1.1.el10_2.x86_64+rt #1 PREEMPT_RT
[  998.393886] Hardware name: Dell Inc. PowerEdge R740/0JMK61, BIOS 2.24.0 03/27/2025
[  998.393889] RIP: 0010:dev_set_promiscuity+0x8d/0xa0
[  998.393901] Code: 00 00 75 d8 48 8b 53 08 48 83 ba b0 02 00 00 00 75 ca 48 83 c4 08 5b c3 cc cc cc cc 48 83 bf 48 09 00 00 00 75 91 48 8b 47 08 <48> 83 b8 b0 02 00 00 00 74 97 eb 81 0f 1f 80 00 00 00 00 90 90 90
[  998.393906] RSP: 0018:ffffce5864a5f6a0 EFLAGS: 00010246
[  998.393912] RAX: ff00000000ffff89 RBX: ffff894d0adf5a05 RCX: 0000000000000000
[  998.393917] RDX: 0000000000000000 RSI: 00000000ffffffff RDI: ffff894d0adf5a05
[  998.393921] RBP: ffff894d19252000 R08: ffff894d19252000 R09: 0000000000000000
[  998.393924] R10: ffff894d19252000 R11: ffff894d192521b8 R12: 0000000000000006
[  998.393927] R13: ffffce5864a5f738 R14: 00000000ffffffe2 R15: 0000000000000000
[  998.393931] FS:  00007fad61971800(0000) GS:ffff894cc0140000(0000) knlGS:0000000000000000
[  998.393936] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  998.393940] CR2: 000055df0a2a6e40 CR3: 000000011c7fe003 CR4: 00000000007726f0
[  998.393944] PKRU: 55555554
[  998.393946] Call Trace:
[  998.393949]  <TASK>
[  998.393952]  ? show_trace_log_lvl+0x1b0/0x2f0
[  998.393961]  ? show_trace_log_lvl+0x1b0/0x2f0
[  998.393975]  ? dp_device_event+0x41/0x80 [openvswitch]
[  998.394009]  ? __die_body.cold+0x8/0x12
[  998.394016]  ? die_addr+0x3c/0x60
[  998.394027]  ? exc_general_protection+0x16d/0x390
[  998.394042]  ? asm_exc_general_protection+0x26/0x30
[  998.394058]  ? dev_set_promiscuity+0x8d/0xa0
[  998.394066]  ? ovs_netdev_detach_dev+0x3a/0x80 [openvswitch]
[  998.394092]  dp_device_event+0x41/0x80 [openvswitch]
[  998.394102]  notifier_call_chain+0x5a/0xd0
[  998.394106]  unregister_netdevice_many_notify+0x51b/0xa60
[  998.394110]  rtnl_dellink+0x169/0x3e0
[  998.394121]  ? rt_mutex_slowlock.constprop.0+0x95/0xd0
[  998.394125]  rtnetlink_rcv_msg+0x142/0x3f0
[  998.394128]  ? avc_has_perm_noaudit+0x69/0xf0
[  998.394130]  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
[  998.394132]  netlink_rcv_skb+0x50/0x100
[  998.394138]  netlink_unicast+0x292/0x3f0
[  998.394141]  netlink_sendmsg+0x21b/0x470
[  998.394145]  ____sys_sendmsg+0x39d/0x3d0
[  998.394149]  ___sys_sendmsg+0x9a/0xe0
[  998.394156]  __sys_sendmsg+0x7a/0xd0
[  998.394160]  do_syscall_64+0x7f/0x170
[  998.394162]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  998.394165] RIP: 0033:0x7fad61bf4724
[  998.394188] Code: 89 02 b8 ff ff ff ff eb bb 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 80 3d c5 e9 0c 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 89 54 24 1c 48 89
[  998.394189] RSP: 002b:00007ffd7e2f7cb8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
[  998.394191] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fad61bf4724
[  998.394193] RDX: 0000000000000000 RSI: 00007ffd7e2f7d20 RDI: 0000000000000003
[  998.394194] RBP: 00007ffd7e2f7d90 R08: 0000000000000010 R09: 000000000000003f
[  998.394195] R10: 000055df11558010 R11: 0000000000000202 R12: 00007ffd7e2f8380
[  998.394196] R13: 0000000069b233d7 R14: 000055df0a256040 R15: 0000000000000000
[  998.394200]  </TASK>

To fix this, reorder the operations in ovs_netdev_detach_dev() to only
clear the flag after completing the other operations, and introduce an
smp_wmb() to make the ordering requirement explicit. The smp_wmb() is
paired with a full smp_mb() in netdev_destroy() to make sure the
call_rcu() invocation does not happen before the unregister operations
are visible.

Reported-by: Minxi Hou <mhou@redhat.com>
Tested-by: Minxi Hou <mhou@redhat.com>
Fixes: 549822767630 ("net: openvswitch: Avoid needlessly taking the RTNL on vport destroy")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20260318155554.1133405-1-toke@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/vport-netdev.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 6574f9bcdc02..c688dee96503 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -151,11 +151,15 @@ static void vport_netdev_free(struct rcu_head *rcu)
 void ovs_netdev_detach_dev(struct vport *vport)
 {
 	ASSERT_RTNL();
-	vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
 	netdev_rx_handler_unregister(vport->dev);
 	netdev_upper_dev_unlink(vport->dev,
 				netdev_master_upper_dev_get(vport->dev));
 	dev_set_promiscuity(vport->dev, -1);
+
+	/* paired with smp_mb() in netdev_destroy() */
+	smp_wmb();
+
+	vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
 }
 
 static void netdev_destroy(struct vport *vport)
@@ -174,6 +178,9 @@ static void netdev_destroy(struct vport *vport)
 		rtnl_unlock();
 	}
 
+	/* paired with smp_wmb() in ovs_netdev_detach_dev() */
+	smp_mb();
+
 	call_rcu(&vport->rcu, vport_netdev_free);
 }
 
-- 
cgit v1.2.3


From 7a9f448d44127217fabc4065c5ba070d4e0b5d37 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 23 Feb 2026 16:44:59 +0100
Subject: scsi: ses: Handle positive SCSI error from ses_recv_diag()

ses_recv_diag() can return a positive value, which also means that an
error happened, so do not only test for negative values.

Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: stable <stable@kernel.org>
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://patch.msgid.link/2026022301-bony-overstock-a07f@gregkh
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ses.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 8e1686358e25..4c348645b04e 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -215,7 +215,7 @@ static unsigned char *ses_get_page2_descriptor(struct enclosure_device *edev,
 	unsigned char *type_ptr = ses_dev->page1_types;
 	unsigned char *desc_ptr = ses_dev->page2 + 8;
 
-	if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len) < 0)
+	if (ses_recv_diag(sdev, 2, ses_dev->page2, ses_dev->page2_len))
 		return NULL;
 
 	for (i = 0; i < ses_dev->page1_num_types; i++, type_ptr += 4) {
-- 
cgit v1.2.3


From 61d099ac4a7a8fb11ebdb6e2ec8d77f38e77362f Mon Sep 17 00:00:00 2001
From: Tyllis Xu <livelycarpet87@gmail.com>
Date: Sat, 14 Mar 2026 12:01:50 -0500
Subject: scsi: ibmvfc: Fix OOB access in ibmvfc_discover_targets_done()

A malicious or compromised VIO server can return a num_written value in the
discover targets MAD response that exceeds max_targets. This value is
stored directly in vhost->num_targets without validation, and is then used
as the loop bound in ibmvfc_alloc_targets() to index into disc_buf[], which
is only allocated for max_targets entries. Indices at or beyond max_targets
access kernel memory outside the DMA-coherent allocation.  The
out-of-bounds data is subsequently embedded in Implicit Logout and PLOGI
MADs that are sent back to the VIO server, leaking kernel memory.

Fix by clamping num_written to max_targets before storing it.

Fixes: 072b91f9c651 ("[SCSI] ibmvfc: IBM Power Virtual Fibre Channel Adapter Client Driver")
Reported-by: Yuhao Jiang <danisjiang@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Tyllis Xu <LivelyCarpet87@gmail.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
Acked-by: Tyrel Datwyler <tyreld@linux.ibm.com>
Link: https://patch.msgid.link/20260314170151.548614-1-LivelyCarpet87@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvfc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index a20fce04fe79..3dd2adda195e 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -4966,7 +4966,8 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt)
 	switch (mad_status) {
 	case IBMVFC_MAD_SUCCESS:
 		ibmvfc_dbg(vhost, "Discover Targets succeeded\n");
-		vhost->num_targets = be32_to_cpu(rsp->num_written);
+		vhost->num_targets = min_t(u32, be32_to_cpu(rsp->num_written),
+					   max_targets);
 		ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_ALLOC_TGTS);
 		break;
 	case IBMVFC_MAD_FAILED:
-- 
cgit v1.2.3


From 1333eee56cdf3f0cf67c6ab4114c2c9e0a952026 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 16 Mar 2026 20:23:29 -0400
Subject: scsi: target: tcm_loop: Drain commands in target_reset handler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

tcm_loop_target_reset() violates the SCSI EH contract: it returns SUCCESS
without draining any in-flight commands.  The SCSI EH documentation
(scsi_eh.rst) requires that when a reset handler returns SUCCESS the driver
has made lower layers "forget about timed out scmds" and is ready for new
commands.  Every other SCSI LLD (virtio_scsi, mpt3sas, ipr, scsi_debug,
mpi3mr) enforces this by draining or completing outstanding commands before
returning SUCCESS.

Because tcm_loop_target_reset() doesn't drain, the SCSI EH reuses in-flight
scsi_cmnd structures for recovery commands (e.g. TUR) while the target core
still has async completion work queued for the old se_cmd.  The memset in
queuecommand zeroes se_lun and lun_ref_active, causing
transport_lun_remove_cmd() to skip its percpu_ref_put().  The leaked LUN
reference prevents transport_clear_lun_ref() from completing, hanging
configfs LUN unlink forever in D-state:

  INFO: task rm:264 blocked for more than 122 seconds.
  rm              D    0   264    258 0x00004000
  Call Trace:
   __schedule+0x3d0/0x8e0
   schedule+0x36/0xf0
   transport_clear_lun_ref+0x78/0x90 [target_core_mod]
   core_tpg_remove_lun+0x28/0xb0 [target_core_mod]
   target_fabric_port_unlink+0x50/0x60 [target_core_mod]
   configfs_unlink+0x156/0x1f0 [configfs]
   vfs_unlink+0x109/0x290
   do_unlinkat+0x1d5/0x2d0

Fix this by making tcm_loop_target_reset() actually drain commands:

 1. Issue TMR_LUN_RESET via tcm_loop_issue_tmr() to drain all commands that
    the target core knows about (those not yet CMD_T_COMPLETE).

 2. Use blk_mq_tagset_busy_iter() to iterate all started requests and
    flush_work() on each se_cmd — this drains any deferred completion work
    for commands that already had CMD_T_COMPLETE set before the TMR (which
    the TMR skips via __target_check_io_state()).  This is the same pattern
    used by mpi3mr, scsi_debug, and libsas to drain outstanding commands
    during reset.

Fixes: e0eb5d38b732 ("scsi: target: tcm_loop: Use block cmd allocator for se_cmds")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Link: https://patch.msgid.link/27011aa34c8f6b1b94d2e3cf5655b6d037f53428.1773706803.git.josef@toxicpanda.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/loopback/tcm_loop.c | 52 +++++++++++++++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index d668bd19fd4a..528883d989b8 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/configfs.h>
+#include <linux/blk-mq.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/scsi_host.h>
@@ -269,15 +270,27 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc)
 	return (ret == TMR_FUNCTION_COMPLETE) ? SUCCESS : FAILED;
 }
 
+static bool tcm_loop_flush_work_iter(struct request *rq, void *data)
+{
+	struct scsi_cmnd *sc = blk_mq_rq_to_pdu(rq);
+	struct tcm_loop_cmd *tl_cmd = scsi_cmd_priv(sc);
+	struct se_cmd *se_cmd = &tl_cmd->tl_se_cmd;
+
+	flush_work(&se_cmd->work);
+	return true;
+}
+
 static int tcm_loop_target_reset(struct scsi_cmnd *sc)
 {
 	struct tcm_loop_hba *tl_hba;
 	struct tcm_loop_tpg *tl_tpg;
+	struct Scsi_Host *sh = sc->device->host;
+	int ret;
 
 	/*
 	 * Locate the tcm_loop_hba_t pointer
 	 */
-	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
+	tl_hba = *(struct tcm_loop_hba **)shost_priv(sh);
 	if (!tl_hba) {
 		pr_err("Unable to perform device reset without active I_T Nexus\n");
 		return FAILED;
@@ -286,11 +299,38 @@ static int tcm_loop_target_reset(struct scsi_cmnd *sc)
 	 * Locate the tl_tpg pointer from TargetID in sc->device->id
 	 */
 	tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
-	if (tl_tpg) {
-		tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
-		return SUCCESS;
-	}
-	return FAILED;
+	if (!tl_tpg)
+		return FAILED;
+
+	/*
+	 * Issue a LUN_RESET to drain all commands that the target core
+	 * knows about.  This handles commands not yet marked CMD_T_COMPLETE.
+	 */
+	ret = tcm_loop_issue_tmr(tl_tpg, sc->device->lun, 0, TMR_LUN_RESET);
+	if (ret != TMR_FUNCTION_COMPLETE)
+		return FAILED;
+
+	/*
+	 * Flush any deferred target core completion work that may still be
+	 * queued.  Commands that already had CMD_T_COMPLETE set before the TMR
+	 * are skipped by the TMR drain, but their async completion work
+	 * (transport_lun_remove_cmd → percpu_ref_put, release_cmd → scsi_done)
+	 * may still be pending in target_completion_wq.
+	 *
+	 * The SCSI EH will reuse in-flight scsi_cmnd structures for recovery
+	 * commands (e.g. TUR) immediately after this handler returns SUCCESS —
+	 * if deferred work is still pending, the memset in queuecommand would
+	 * zero the se_cmd while the work accesses it, leaking the LUN
+	 * percpu_ref and hanging configfs unlink forever.
+	 *
+	 * Use blk_mq_tagset_busy_iter() to find all started requests and
+	 * flush_work() on each — the same pattern used by mpi3mr, scsi_debug,
+	 * and other SCSI drivers to drain outstanding commands during reset.
+	 */
+	blk_mq_tagset_busy_iter(&sh->tag_set, tcm_loop_flush_work_iter, NULL);
+
+	tl_tpg->tl_transport_status = TCM_TRANSPORT_ONLINE;
+	return SUCCESS;
 }
 
 static const struct scsi_host_template tcm_loop_driver_template = {
-- 
cgit v1.2.3


From d71afa9deb4d413232ba16d693f7d43b321931b4 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Tue, 17 Mar 2026 14:31:47 +0800
Subject: scsi: scsi_transport_sas: Fix the maximum channel scanning issue

After commit 37c4e72b0651 ("scsi: Fix sas_user_scan() to handle wildcard
and multi-channel scans"), if the device supports multiple channels (0 to
shost->max_channel), user_scan() invokes updated sas_user_scan() to perform
the scan behavior for a specific transfer.  However, when the user
specifies shost->max_channel, it will return -EINVAL, which is not
expected.

Fix and support specifying the scan shost->max_channel for scanning.

Fixes: 37c4e72b0651 ("scsi: Fix sas_user_scan() to handle wildcard and multi-channel scans")
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Link: https://patch.msgid.link/20260317063147.2182562-1-liyihang9@huawei.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_transport_sas.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 12124f9d5ccd..13412702188e 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -1734,7 +1734,7 @@ static int sas_user_scan(struct Scsi_Host *shost, uint channel,
 		break;
 
 	default:
-		if (channel < shost->max_channel) {
+		if (channel <= shost->max_channel) {
 			res = scsi_scan_host_selected(shost, channel, id, lun,
 						      SCSI_SCAN_MANUAL);
 		} else {
-- 
cgit v1.2.3


From 01f784fc9d0ab2a6dac45ee443620e517cb2a19b Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Sat, 14 Mar 2026 01:17:40 +0000
Subject: scsi: target: file: Use kzalloc_flex for aio_cmd

The target_core_file doesn't initialize the aio_cmd->iocb for the
ki_write_stream. When a write command fd_execute_rw_aio() is executed,
we may get a bogus ki_write_stream value, causing unintended write
failure status when checking iocb->ki_write_stream > max_write_streams
in the block device.

Let's just use kzalloc_flex when allocating the aio_cmd and let
ki_write_stream=0 to fix this issue.

Fixes: 732f25a2895a ("fs: add a write stream field to the kiocb")
Fixes: c27683da6406 ("block: expose write streams for block device nodes")
Cc: stable@vger.kernel.org
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/f1a2f81c62f043e31f80bb92d5f29893400c8ee2.1773450782.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 3ae1f7137d9d..3d593af30aa5 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -276,7 +276,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	ssize_t len = 0;
 	int ret = 0, i;
 
-	aio_cmd = kmalloc_flex(*aio_cmd, bvecs, sgl_nents);
+	aio_cmd = kzalloc_flex(*aio_cmd, bvecs, sgl_nents);
 	if (!aio_cmd)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-- 
cgit v1.2.3


From e6d7eba23b666d85cacee0643be280d6ce1ebffc Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 20 Mar 2026 12:48:01 +0900
Subject: ata: libata-scsi: report correct sense field pointer in
 ata_scsiop_maint_in()

Commit 4ab7bb976343 ("ata: libata-scsi: Refactor ata_scsiop_maint_in()")
modified ata_scsiop_maint_in() to directly call
ata_scsi_set_invalid_field() to set the field pointer of the sense data
of a failed MAINTENANCE IN command. However, in the case of an invalid
command format, the sense data field incorrectly indicates byte 1 of
the CDB. Fix this to indicate byte 2 of the command.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: 4ab7bb976343 ("ata: libata-scsi: Refactor ata_scsiop_maint_in()")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-scsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index ad798e5246b4..3b65df914ebb 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3600,7 +3600,7 @@ static unsigned int ata_scsiop_maint_in(struct ata_device *dev,
 
 	if (cdb[2] != 1 && cdb[2] != 3) {
 		ata_dev_warn(dev, "invalid command format %d\n", cdb[2]);
-		ata_scsi_set_invalid_field(dev, cmd, 1, 0xff);
+		ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
 		return 0;
 	}
 
-- 
cgit v1.2.3


From c961cc86af01246a7ce706bbc29072d314e00880 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 18 Mar 2026 12:08:52 +0000
Subject: reset: rzg2l-usbphy-ctrl: Fix malformed MODULE_AUTHOR string

Fix a malformed MODULE_AUTHOR macro in the RZ/G2L USBPHY control driver
where the author's name and opening angle bracket were missing, leaving
only the email address with a stray closing >. Correct it to the standard
Name <email> format.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/reset-rzg2l-usbphy-ctrl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
index 05dd9b4a02df..fd75d9601a3b 100644
--- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c
+++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
@@ -350,4 +350,4 @@ module_platform_driver(rzg2l_usbphy_ctrl_driver);
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Renesas RZ/G2L USBPHY Control");
-MODULE_AUTHOR("biju.das.jz@bp.renesas.com>");
+MODULE_AUTHOR("Biju Das <biju.das.jz@bp.renesas.com>");
-- 
cgit v1.2.3


From eca58535b154e6951327319afda94ac80eae7dc3 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:45 +0200
Subject: dma-debug: Allow multiple invocations of overlapping entries

Repeated DMA mappings with DMA_ATTR_CPU_CACHE_CLEAN trigger the
following splat. This prevents using the attribute in cases where a DMA
region is shared and reused more than seven times.

 ------------[ cut here ]------------
 DMA-API: exceeded 7 overlapping mappings of cacheline 0x000000000438c440
 WARNING: kernel/dma/debug.c:467 at add_dma_entry+0x219/0x280, CPU#4: ibv_rc_pingpong/1644
 Modules linked in: xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core ib_core
 CPU: 4 UID: 2733 PID: 1644 Comm: ibv_rc_pingpong Not tainted 6.19.0+ #129 PREEMPT
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 RIP: 0010:add_dma_entry+0x221/0x280
 Code: c0 0f 84 f2 fe ff ff 83 e8 01 89 05 6d 99 11 01 e9 e4 fe ff ff 0f 8e 1f ff ff ff 48 8d 3d 07 ef 2d 01 be 07 00 00 00 48 89 e2 <67> 48 0f b9 3a e9 06 ff ff ff 48 c7 c7 98 05 2b 82 c6 05 72 92 28
 RSP: 0018:ff1100010e657970 EFLAGS: 00010002
 RAX: 0000000000000007 RBX: ff1100010234eb00 RCX: 0000000000000000
 RDX: ff1100010e657970 RSI: 0000000000000007 RDI: ffffffff82678660
 RBP: 000000000438c440 R08: 0000000000000228 R09: 0000000000000000
 R10: 00000000000001be R11: 000000000000089d R12: 0000000000000800
 R13: 00000000ffffffef R14: 0000000000000202 R15: ff1100010234eb00
 FS:  00007fb15f3f6740(0000) GS:ff110008dcc19000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fb15f32d3a0 CR3: 0000000116f59001 CR4: 0000000000373eb0
 Call Trace:
  <TASK>
  debug_dma_map_sg+0x1b4/0x390
  __dma_map_sg_attrs+0x6d/0x1a0
  dma_map_sgtable+0x19/0x30
  ib_umem_get+0x284/0x3b0 [ib_uverbs]
  mlx5_ib_reg_user_mr+0x68/0x2a0 [mlx5_ib]
  ib_uverbs_reg_mr+0x17f/0x2a0 [ib_uverbs]
  ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xc2/0x130 [ib_uverbs]
  ib_uverbs_cmd_verbs+0xa0b/0xae0 [ib_uverbs]
  ? ib_uverbs_handler_UVERBS_METHOD_QUERY_PORT_SPEED+0xe0/0xe0 [ib_uverbs]
  ? mmap_region+0x7a/0xb0
  ? do_mmap+0x3b8/0x5c0
  ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
  __x64_sys_ioctl+0x14f/0x8b0
  ? ksys_mmap_pgoff+0xc5/0x190
  do_syscall_64+0x8c/0xbf0
  entry_SYSCALL_64_after_hwframe+0x4b/0x53
 RIP: 0033:0x7fb15f5e4eed
 Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
 RSP: 002b:00007ffe09a5c540 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
 RAX: ffffffffffffffda RBX: 00007ffe09a5c5d0 RCX: 00007fb15f5e4eed
 RDX: 00007ffe09a5c5f0 RSI: 00000000c0181b01 RDI: 0000000000000003
 RBP: 00007ffe09a5c590 R08: 0000000000000028 R09: 00007ffe09a5c794
 R10: 0000000000000001 R11: 0000000000000246 R12: 00007ffe09a5c794
 R13: 000000000000000c R14: 0000000025a49170 R15: 000000000000000c
  </TASK>
 ---[ end trace 0000000000000000 ]---

Fixes: 61868dc55a11 ("dma-mapping: add DMA_ATTR_CPU_CACHE_CLEAN")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-1-1dde90a7f08b@nvidia.com
---
 kernel/dma/debug.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 86f87e43438c..be207be74996 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -453,7 +453,7 @@ static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
 	return overlap;
 }
 
-static void active_cacheline_inc_overlap(phys_addr_t cln)
+static void active_cacheline_inc_overlap(phys_addr_t cln, bool is_cache_clean)
 {
 	int overlap = active_cacheline_read_overlap(cln);
 
@@ -462,7 +462,7 @@ static void active_cacheline_inc_overlap(phys_addr_t cln)
 	/* If we overflowed the overlap counter then we're potentially
 	 * leaking dma-mappings.
 	 */
-	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+	WARN_ONCE(!is_cache_clean && overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
 		  pr_fmt("exceeded %d overlapping mappings of cacheline %pa\n"),
 		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
 }
@@ -495,7 +495,7 @@ static int active_cacheline_insert(struct dma_debug_entry *entry,
 	if (rc == -EEXIST) {
 		struct dma_debug_entry *existing;
 
-		active_cacheline_inc_overlap(cln);
+		active_cacheline_inc_overlap(cln, entry->is_cache_clean);
 		existing = radix_tree_lookup(&dma_active_cacheline, cln);
 		/* A lookup failure here after we got -EEXIST is unexpected. */
 		WARN_ON(!existing);
-- 
cgit v1.2.3


From 6f45b1604cf43945ef472ae4ef30354025307c19 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:46 +0200
Subject: dma-mapping: handle DMA_ATTR_CPU_CACHE_CLEAN in trace output

Tracing prints decoded DMA attribute flags, but it does not yet
include the recently added DMA_ATTR_CPU_CACHE_CLEAN. Add support
for decoding and displaying this attribute in the trace output.

Fixes: 61868dc55a11 ("dma-mapping: add DMA_ATTR_CPU_CACHE_CLEAN")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-2-1dde90a7f08b@nvidia.com
---
 include/trace/events/dma.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 33e99e792f1a..69cb3805ee81 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -32,7 +32,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_ALLOC_SINGLE_PAGES, "ALLOC_SINGLE_PAGES" }, \
 		{ DMA_ATTR_NO_WARN, "NO_WARN" }, \
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
-		{ DMA_ATTR_MMIO, "MMIO" })
+		{ DMA_ATTR_MMIO, "MMIO" }, \
+		{ DMA_ATTR_CPU_CACHE_CLEAN, "CACHE_CLEAN" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
-- 
cgit v1.2.3


From 9bb0a4d6a4433b75274204b083dac8e515d2007d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:47 +0200
Subject: dma-mapping: Clarify valid conditions for CPU cache line overlap

Rename the DMA_ATTR_CPU_CACHE_CLEAN attribute to better reflect that it
is debugging aid to inform DMA core code that CPU cache line overlaps are
allowed, and refine the documentation describing its use.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-3-1dde90a7f08b@nvidia.com
---
 Documentation/core-api/dma-attributes.rst | 22 ++++++++++++++--------
 drivers/virtio/virtio_ring.c              | 10 +++++-----
 include/linux/dma-mapping.h               |  8 ++++----
 include/trace/events/dma.h                |  2 +-
 kernel/dma/debug.c                        |  2 +-
 5 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 1d7bfad73b1c..48cfe86cc06d 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -149,11 +149,17 @@ For architectures that require cache flushing for DMA coherence
 DMA_ATTR_MMIO will not perform any cache flushing. The address
 provided must never be mapped cacheable into the CPU.
 
-DMA_ATTR_CPU_CACHE_CLEAN
-------------------------
-
-This attribute indicates the CPU will not dirty any cacheline overlapping this
-DMA_FROM_DEVICE/DMA_BIDIRECTIONAL buffer while it is mapped. This allows
-multiple small buffers to safely share a cacheline without risk of data
-corruption, suppressing DMA debug warnings about overlapping mappings.
-All mappings sharing a cacheline should have this attribute.
+DMA_ATTR_DEBUGGING_IGNORE_CACHELINES
+------------------------------------
+
+This attribute indicates that CPU cache lines may overlap for buffers mapped
+with DMA_FROM_DEVICE or DMA_BIDIRECTIONAL.
+
+Such overlap may occur when callers map multiple small buffers that reside
+within the same cache line. In this case, callers must guarantee that the CPU
+will not dirty these cache lines after the mappings are established. When this
+condition is met, multiple buffers can safely share a cache line without risking
+data corruption.
+
+All mappings that share a cache line must set this attribute to suppress DMA
+debug warnings about overlapping mappings.
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 335692d41617..fbca7ce1c6bf 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2912,10 +2912,10 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
  * @data: the token identifying the buffer.
  * @gfp: how to do memory allocations (if necessary).
  *
- * Same as virtqueue_add_inbuf but passes DMA_ATTR_CPU_CACHE_CLEAN to indicate
- * that the CPU will not dirty any cacheline overlapping this buffer while it
- * is available, and to suppress overlapping cacheline warnings in DMA debug
- * builds.
+ * Same as virtqueue_add_inbuf but passes DMA_ATTR_DEBUGGING_IGNORE_CACHELINES
+ * to indicate that the CPU will not dirty any cacheline overlapping this buffer
+ * while it is available, and to suppress overlapping cacheline warnings in DMA
+ * debug builds.
  *
  * Caller must ensure we don't call this with other virtqueue operations
  * at the same time (except where noted).
@@ -2928,7 +2928,7 @@ int virtqueue_add_inbuf_cache_clean(struct virtqueue *vq,
 				    gfp_t gfp)
 {
 	return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, false, gfp,
-			     DMA_ATTR_CPU_CACHE_CLEAN);
+			     DMA_ATTR_DEBUGGING_IGNORE_CACHELINES);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_cache_clean);
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 29973baa0581..da44394b3a1a 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -80,11 +80,11 @@
 #define DMA_ATTR_MMIO		(1UL << 10)
 
 /*
- * DMA_ATTR_CPU_CACHE_CLEAN: Indicates the CPU will not dirty any cacheline
- * overlapping this buffer while it is mapped for DMA. All mappings sharing
- * a cacheline must have this attribute for this to be considered safe.
+ * DMA_ATTR_DEBUGGING_IGNORE_CACHELINES: Indicates the CPU cache line can be
+ * overlapped. All mappings sharing a cacheline must have this attribute for
+ * this to be considered safe.
  */
-#define DMA_ATTR_CPU_CACHE_CLEAN	(1UL << 11)
+#define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES	(1UL << 11)
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 69cb3805ee81..8c64bc0721fe 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -33,7 +33,7 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_NO_WARN, "NO_WARN" }, \
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
 		{ DMA_ATTR_MMIO, "MMIO" }, \
-		{ DMA_ATTR_CPU_CACHE_CLEAN, "CACHE_CLEAN" })
+		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index be207be74996..83e1cfe05f08 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -601,7 +601,7 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	unsigned long flags;
 	int rc;
 
-	entry->is_cache_clean = !!(attrs & DMA_ATTR_CPU_CACHE_CLEAN);
+	entry->is_cache_clean = attrs & DMA_ATTR_DEBUGGING_IGNORE_CACHELINES;
 
 	bucket = get_hash_bucket(entry, &flags);
 	hash_bucket_add(bucket, entry);
-- 
cgit v1.2.3


From e6a58fa2556203a7f6731b4071705dc81cca5ca5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:48 +0200
Subject: dma-mapping: Introduce DMA require coherency attribute

The mapping buffers which carry this attribute require DMA coherent system.
This means that they can't take SWIOTLB path, can perform CPU cache overlap
and doesn't perform cache flushing.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-4-1dde90a7f08b@nvidia.com
---
 Documentation/core-api/dma-attributes.rst | 16 ++++++++++++++++
 include/linux/dma-mapping.h               |  7 +++++++
 include/trace/events/dma.h                |  3 ++-
 kernel/dma/debug.c                        |  3 ++-
 kernel/dma/mapping.c                      |  6 ++++++
 5 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 48cfe86cc06d..123c8468d58f 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -163,3 +163,19 @@ data corruption.
 
 All mappings that share a cache line must set this attribute to suppress DMA
 debug warnings about overlapping mappings.
+
+DMA_ATTR_REQUIRE_COHERENT
+-------------------------
+
+DMA mapping requests with the DMA_ATTR_REQUIRE_COHERENT fail on any
+system where SWIOTLB or cache management is required. This should only
+be used to support uAPI designs that require continuous HW DMA
+coherence with userspace processes, for example RDMA and DRM. At a
+minimum the memory being mapped must be userspace memory from
+pin_user_pages() or similar.
+
+Drivers should consider using dma_mmap_pages() instead of this
+interface when building their uAPIs, when possible.
+
+It must never be used in an in-kernel driver that only works with
+kernel memory.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index da44394b3a1a..482b919f040f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -86,6 +86,13 @@
  */
 #define DMA_ATTR_DEBUGGING_IGNORE_CACHELINES	(1UL << 11)
 
+/*
+ * DMA_ATTR_REQUIRE_COHERENT: Indicates that DMA coherency is required.
+ * All mappings that carry this attribute can't work with SWIOTLB and cache
+ * flushing.
+ */
+#define DMA_ATTR_REQUIRE_COHERENT	(1UL << 12)
+
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
  * be given to a device to use as a DMA source or target.  It is specific to a
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 8c64bc0721fe..63597b004424 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -33,7 +33,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_NO_WARN, "NO_WARN" }, \
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
 		{ DMA_ATTR_MMIO, "MMIO" }, \
-		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" })
+		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \
+		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 83e1cfe05f08..0677918f06a8 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -601,7 +601,8 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	unsigned long flags;
 	int rc;
 
-	entry->is_cache_clean = attrs & DMA_ATTR_DEBUGGING_IGNORE_CACHELINES;
+	entry->is_cache_clean = attrs & (DMA_ATTR_DEBUGGING_IGNORE_CACHELINES |
+					 DMA_ATTR_REQUIRE_COHERENT);
 
 	bucket = get_hash_bucket(entry, &flags);
 	hash_bucket_add(bucket, entry);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 3928a509c44c..6d3dd0bd3a88 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -164,6 +164,9 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return DMA_MAPPING_ERROR;
 
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return DMA_MAPPING_ERROR;
+
 	if (dma_map_direct(dev, ops) ||
 	    (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
@@ -235,6 +238,9 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 
 	BUG_ON(!valid_dma_direction(dir));
 
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return -EOPNOTSUPP;
+
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return 0;
 
-- 
cgit v1.2.3


From 453b8fb68f3641fea970db88b7d9a153ed2a37e8 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 9 Oct 2025 16:54:58 +0200
Subject: xen/privcmd: restrict usage in unprivileged domU

The Xen privcmd driver allows to issue arbitrary hypercalls from
user space processes. This is normally no problem, as access is
usually limited to root and the hypervisor will deny any hypercalls
affecting other domains.

In case the guest is booted using secure boot, however, the privcmd
driver would be enabling a root user process to modify e.g. kernel
memory contents, thus breaking the secure boot feature.

The only known case where an unprivileged domU is really needing to
use the privcmd driver is the case when it is acting as the device
model for another guest. In this case all hypercalls issued via the
privcmd driver will target that other guest.

Fortunately the privcmd driver can already be locked down to allow
only hypercalls targeting a specific domain, but this mode can be
activated from user land only today.

The target domain can be obtained from Xenstore, so when not running
in dom0 restrict the privcmd driver to that target domain from the
beginning, resolving the potential problem of breaking secure boot.

This is XSA-482

Reported-by: Teddy Astie <teddy.astie@vates.tech>
Fixes: 1c5de1939c20 ("xen: add privcmd driver")
Signed-off-by: Juergen Gross <jgross@suse.com>
---
V2:
- defer reading from Xenstore if Xenstore isn't ready yet (Jan Beulich)
- wait in open() if target domain isn't known yet
- issue message in case no target domain found (Jan Beulich)
---
 drivers/xen/privcmd.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 57 insertions(+), 3 deletions(-)

diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 1759cc18753f..a83bad69f4f2 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -12,6 +12,7 @@
 #include <linux/eventfd.h>
 #include <linux/file.h>
 #include <linux/kernel.h>
+#include <linux/kstrtox.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/poll.h>
@@ -30,7 +31,9 @@
 #include <linux/seq_file.h>
 #include <linux/miscdevice.h>
 #include <linux/moduleparam.h>
+#include <linux/notifier.h>
 #include <linux/virtio_mmio.h>
+#include <linux/wait.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
@@ -46,6 +49,7 @@
 #include <xen/page.h>
 #include <xen/xen-ops.h>
 #include <xen/balloon.h>
+#include <xen/xenbus.h>
 #ifdef CONFIG_XEN_ACPI
 #include <xen/acpi.h>
 #endif
@@ -72,6 +76,11 @@ struct privcmd_data {
 	domid_t domid;
 };
 
+/* DOMID_INVALID implies no restriction */
+static domid_t target_domain = DOMID_INVALID;
+static bool restrict_wait;
+static DECLARE_WAIT_QUEUE_HEAD(restrict_wait_wq);
+
 static int privcmd_vma_range_is_mapped(
                struct vm_area_struct *vma,
                unsigned long addr,
@@ -1563,13 +1572,16 @@ static long privcmd_ioctl(struct file *file,
 
 static int privcmd_open(struct inode *ino, struct file *file)
 {
-	struct privcmd_data *data = kzalloc_obj(*data);
+	struct privcmd_data *data;
+
+	if (wait_event_interruptible(restrict_wait_wq, !restrict_wait) < 0)
+		return -EINTR;
 
+	data = kzalloc_obj(*data);
 	if (!data)
 		return -ENOMEM;
 
-	/* DOMID_INVALID implies no restriction */
-	data->domid = DOMID_INVALID;
+	data->domid = target_domain;
 
 	file->private_data = data;
 	return 0;
@@ -1662,6 +1674,45 @@ static struct miscdevice privcmd_dev = {
 	.fops = &xen_privcmd_fops,
 };
 
+static int init_restrict(struct notifier_block *notifier,
+			 unsigned long event,
+			 void *data)
+{
+	char *target;
+	unsigned int domid;
+
+	/* Default to an guaranteed unused domain-id. */
+	target_domain = DOMID_IDLE;
+
+	target = xenbus_read(XBT_NIL, "target", "", NULL);
+	if (IS_ERR(target) || kstrtouint(target, 10, &domid)) {
+		pr_err("No target domain found, blocking all hypercalls\n");
+		goto out;
+	}
+
+	target_domain = domid;
+
+ out:
+	if (!IS_ERR(target))
+		kfree(target);
+
+	restrict_wait = false;
+	wake_up_all(&restrict_wait_wq);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block xenstore_notifier = {
+	.notifier_call = init_restrict,
+};
+
+static void __init restrict_driver(void)
+{
+	restrict_wait = true;
+
+	register_xenstore_notifier(&xenstore_notifier);
+}
+
 static int __init privcmd_init(void)
 {
 	int err;
@@ -1669,6 +1720,9 @@ static int __init privcmd_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (!xen_initial_domain())
+		restrict_driver();
+
 	err = misc_register(&privcmd_dev);
 	if (err != 0) {
 		pr_err("Could not register Xen privcmd device\n");
-- 
cgit v1.2.3


From 2536617f20ddc7c2f4cef59b549aa45d166b03b1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:49 +0200
Subject: dma-direct: prevent SWIOTLB path when DMA_ATTR_REQUIRE_COHERENT is
 set

DMA_ATTR_REQUIRE_COHERENT indicates that SWIOTLB must not be used.
Ensure the SWIOTLB path is declined whenever the DMA direct path is
selected.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-5-1dde90a7f08b@nvidia.com
---
 kernel/dma/direct.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e89f175e9c2d..6184ff303f08 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -84,7 +84,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 	dma_addr_t dma_addr;
 
 	if (is_swiotlb_force_bounce(dev)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return DMA_MAPPING_ERROR;
 
 		return swiotlb_map(dev, phys, size, dir, attrs);
@@ -98,7 +98,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 		dma_addr = phys_to_dma(dev, phys);
 		if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
 		    dma_kmalloc_needs_bounce(dev, size, dir)) {
-			if (is_swiotlb_active(dev))
+			if (is_swiotlb_active(dev) &&
+			    !(attrs & DMA_ATTR_REQUIRE_COHERENT))
 				return swiotlb_map(dev, phys, size, dir, attrs);
 
 			goto err_overflow;
@@ -123,7 +124,7 @@ static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 {
 	phys_addr_t phys;
 
-	if (attrs & DMA_ATTR_MMIO)
+	if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 		/* nothing to do: uncached and no swiotlb */
 		return;
 
-- 
cgit v1.2.3


From 636e6572e848339d2ae591949fe81de2cef00563 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:50 +0200
Subject: iommu/dma: add support for DMA_ATTR_REQUIRE_COHERENT attribute

Add support for the DMA_ATTR_REQUIRE_COHERENT attribute to the exported
functions. This attribute indicates that the SWIOTLB path must not be
used and that no sync operations should be performed.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-6-1dde90a7f08b@nvidia.com
---
 drivers/iommu/dma-iommu.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5dac64be61bb..94d514169642 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1211,7 +1211,7 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 	 */
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return DMA_MAPPING_ERROR;
 
 		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
@@ -1223,7 +1223,8 @@ dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 		arch_sync_dma_for_device(phys, size, dir);
 
 	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && !(attrs & DMA_ATTR_MMIO))
+	if (iova == DMA_MAPPING_ERROR &&
+	    !(attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)))
 		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 	return iova;
 }
@@ -1233,7 +1234,7 @@ void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 {
 	phys_addr_t phys;
 
-	if (attrs & DMA_ATTR_MMIO) {
+	if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT)) {
 		__iommu_dma_unmap(dev, dma_handle, size);
 		return;
 	}
@@ -1945,9 +1946,21 @@ int dma_iova_link(struct device *dev, struct dma_iova_state *state,
 	if (WARN_ON_ONCE(iova_start_pad && offset > 0))
 		return -EIO;
 
+	/*
+	 * DMA_IOVA_USE_SWIOTLB is set on state after some entry
+	 * took SWIOTLB path, which we were supposed to prevent
+	 * for DMA_ATTR_REQUIRE_COHERENT attribute.
+	 */
+	if (WARN_ON_ONCE((state->__size & DMA_IOVA_USE_SWIOTLB) &&
+			 (attrs & DMA_ATTR_REQUIRE_COHERENT)))
+		return -EOPNOTSUPP;
+
+	if (!dev_is_dma_coherent(dev) && (attrs & DMA_ATTR_REQUIRE_COHERENT))
+		return -EOPNOTSUPP;
+
 	if (dev_use_swiotlb(dev, size, dir) &&
 	    iova_unaligned(iovad, phys, size)) {
-		if (attrs & DMA_ATTR_MMIO)
+		if (attrs & (DMA_ATTR_MMIO | DMA_ATTR_REQUIRE_COHERENT))
 			return -EPERM;
 
 		return iommu_dma_iova_link_swiotlb(dev, state, phys, offset,
-- 
cgit v1.2.3


From d9d43a3f5c48d5a3d1da922f46c4a30d94d61ba5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:51 +0200
Subject: RDMA/umem: Tell DMA mapping that UMEM requires coherency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The RDMA subsystem exposes DMA regions through the verbs interface, which
assumes a coherent system. Use the DMA_ATTR_REQUIRE_COHERENCE attribute
to ensure coherency and avoid taking the SWIOTLB path.

The RDMA verbs programming model resembles HMM and assumes concurrent DMA
and CPU access to userspace memory. The hardware and programming model
support "one-sided" operations initiated remotely without any local CPU
involvement or notification. These include ATOMIC compare/swap, READ, and
WRITE. A remote CPU can use these operations to traverse data structures,
manipulate locks, and perform similar tasks without the host CPU’s
awareness. If SWIOTLB substitutes memory or DMA is not cache coherent,
these use cases break entirely.

In-kernel RDMA is fine with incoherent mappings because kernel users do
not rely on one-sided operations in ways that would expose these issues.

A given region may also be exported multiple times, which can trigger
warnings about cacheline overlaps. These warnings are suppressed when the
new attribute is used.

infiniband rocep8s0f0: mlx5_ib_reg_user_mr:1592:(pid 5812): start 0x2b28c000, iova 0x2b28c000, length 0x1000, access_flags 0x1
infiniband rocep8s0f0: mlx5_ib_reg_user_mr:1592:(pid 5812): start 0x2b28c001, iova 0x2b28c001, length 0xfff, access_flags 0x1
 ------------[ cut here ]------------
 DMA-API: mlx5_core 0000:08:00.0: cacheline tracking EEXIST, overlapping mappings aren't supported
 WARNING: kernel/dma/debug.c:620 at add_dma_entry+0x1bb/0x280, CPU#6: ibv_rc_pingpong/5812
 Modules linked in: veth xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat nf_nat xt_addrtype br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay mlx5_fwctl zram zsmalloc mlx5_ib fuse rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_core ib_core
 CPU: 6 UID: 2733 PID: 5812 Comm: ibv_rc_pingpong Tainted: G        W           6.19.0+ #129 PREEMPT
 Tainted: [W]=WARN
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 RIP: 0010:add_dma_entry+0x1be/0x280
 Code: 8b 7b 10 48 85 ff 0f 84 c3 00 00 00 48 8b 6f 50 48 85 ed 75 03 48 8b 2f e8 ff 8e 6a 00 48 89 c6 48 8d 3d 55 ef 2d 01 48 89 ea <67> 48 0f b9 3a 48 85 db 74 1a 48 c7 c7 b0 00 2b 82 e8 9c 25 fd ff
 RSP: 0018:ff11000138717978 EFLAGS: 00010286
 RAX: ffffffffa02d7831 RBX: ff1100010246de00 RCX: 0000000000000000
 RDX: ff110001036fac30 RSI: ffffffffa02d7831 RDI: ffffffff82678650
 RBP: ff110001036fac30 R08: ff11000110dcb4a0 R09: ff11000110dcb478
 R10: 0000000000000000 R11: ffffffff824b30a8 R12: 0000000000000000
 R13: 00000000ffffffef R14: 0000000000000202 R15: ff1100010246de00
 FS:  00007f59b411c740(0000) GS:ff110008dcc99000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007ffe538f7000 CR3: 000000010e066005 CR4: 0000000000373eb0
 Call Trace:
  <TASK>
  debug_dma_map_sg+0x1b4/0x390
  __dma_map_sg_attrs+0x6d/0x1a0
  dma_map_sgtable+0x19/0x30
  ib_umem_get+0x254/0x380 [ib_uverbs]
  mlx5_ib_reg_user_mr+0x68/0x2a0 [mlx5_ib]
  ib_uverbs_reg_mr+0x17f/0x2a0 [ib_uverbs]
  ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xc2/0x130 [ib_uverbs]
  ib_uverbs_cmd_verbs+0xa0b/0xae0 [ib_uverbs]
  ? ib_uverbs_handler_UVERBS_METHOD_QUERY_PORT_SPEED+0xe0/0xe0 [ib_uverbs]
  ? mmap_region+0x7a/0xb0
  ? do_mmap+0x3b8/0x5c0
  ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs]
  __x64_sys_ioctl+0x14f/0x8b0
  ? ksys_mmap_pgoff+0xc5/0x190
  do_syscall_64+0x8c/0xbf0
  entry_SYSCALL_64_after_hwframe+0x4b/0x53
 RIP: 0033:0x7f59b430aeed
 Code: 04 25 28 00 00 00 48 89 45 c8 31 c0 48 8d 45 10 c7 45 b0 10 00 00 00 48 89 45 b8 48 8d 45 d0 48 89 45 c0 b8 10 00 00 00 0f 05 <89> c2 3d 00 f0 ff ff 77 1a 48 8b 45 c8 64 48 2b 04 25 28 00 00 00
 RSP: 002b:00007ffe538f9430 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
 RAX: ffffffffffffffda RBX: 00007ffe538f94c0 RCX: 00007f59b430aeed
 RDX: 00007ffe538f94e0 RSI: 00000000c0181b01 RDI: 0000000000000003
 RBP: 00007ffe538f9480 R08: 0000000000000028 R09: 00007ffe538f9684
 R10: 0000000000000001 R11: 0000000000000246 R12: 00007ffe538f9684
 R13: 000000000000000c R14: 000000002b28d170 R15: 000000000000000c
  </TASK>
 ---[ end trace 0000000000000000 ]---

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-7-1dde90a7f08b@nvidia.com
---
 drivers/infiniband/core/umem.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index cff4fcca2c34..edc34c69f0f2 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -55,7 +55,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	if (dirty)
 		ib_dma_unmap_sgtable_attrs(dev, &umem->sgt_append.sgt,
-					   DMA_BIDIRECTIONAL, 0);
+					   DMA_BIDIRECTIONAL,
+					   DMA_ATTR_REQUIRE_COHERENT);
 
 	for_each_sgtable_sg(&umem->sgt_append.sgt, sg, i) {
 		unpin_user_page_range_dirty_lock(sg_page(sg),
@@ -169,7 +170,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	unsigned long lock_limit;
 	unsigned long new_pinned;
 	unsigned long cur_base;
-	unsigned long dma_attr = 0;
+	unsigned long dma_attr = DMA_ATTR_REQUIRE_COHERENT;
 	struct mm_struct *mm;
 	unsigned long npages;
 	int pinned, ret;
-- 
cgit v1.2.3


From f5ebf241c407dbf629fcf515015e139fcea2c2f0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 16 Mar 2026 21:06:52 +0200
Subject: mm/hmm: Indicate that HMM requires DMA coherency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

HMM is fundamentally about allowing a sophisticated device to perform DMA
directly to a process’s memory while the CPU accesses that same memory at
the same time. It is similar to SVA but does not rely on IOMMU support.
Because the entire model depends on concurrent access to shared memory, it
fails as a uAPI if SWIOTLB substitutes the memory or if the CPU caches are
not coherent with DMA.

Until now, there has been no reliable way to report this, and various
approximations have been used:

int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
                      size_t nr_entries, size_t dma_entry_size)
{
<...>
        /*
         * The HMM API violates our normal DMA buffer ownership rules and can't
         * transfer buffer ownership.  The dma_addressing_limited() check is a
         * best approximation to ensure no swiotlb buffering happens.
         */
        dma_need_sync = !dev->dma_skip_sync;
        if (dma_need_sync || dma_addressing_limited(dev))
                return -EOPNOTSUPP;

So let's mark mapped buffers with DMA_ATTR_REQUIRE_COHERENT attribute
to prevent silent data corruption if someone tries to use hmm in a system
with swiotlb or incoherent DMA

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260316-dma-debug-overlap-v3-8-1dde90a7f08b@nvidia.com
---
 mm/hmm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index f6c4ddff4bd6..5955f2f0c83d 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -778,7 +778,7 @@ dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
 	struct page *page = hmm_pfn_to_page(pfns[idx]);
 	phys_addr_t paddr = hmm_pfn_to_phys(pfns[idx]);
 	size_t offset = idx * map->dma_entry_size;
-	unsigned long attrs = 0;
+	unsigned long attrs = DMA_ATTR_REQUIRE_COHERENT;
 	dma_addr_t dma_addr;
 	int ret;
 
@@ -871,7 +871,7 @@ bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx)
 	struct dma_iova_state *state = &map->state;
 	dma_addr_t *dma_addrs = map->dma_list;
 	unsigned long *pfns = map->pfn_list;
-	unsigned long attrs = 0;
+	unsigned long attrs = DMA_ATTR_REQUIRE_COHERENT;
 
 	if ((pfns[idx] & valid_dma) != valid_dma)
 		return false;
-- 
cgit v1.2.3


From 1613462be621ad5103ec338a7b0ca0746ec4e5f1 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 14 Oct 2025 13:28:15 +0200
Subject: xen/privcmd: add boot control for restricted usage in domU

When running in an unprivileged domU under Xen, the privcmd driver
is restricted to allow only hypercalls against a target domain, for
which the current domU is acting as a device model.

Add a boot parameter "unrestricted" to allow all hypercalls (the
hypervisor will still refuse destructive hypercalls affecting other
guests).

Make this new parameter effective only in case the domU wasn't started
using secure boot, as otherwise hypercalls targeting the domU itself
might result in violating the secure boot functionality.

This is achieved by adding another lockdown reason, which can be
tested to not being set when applying the "unrestricted" option.

This is part of XSA-482

Signed-off-by: Juergen Gross <jgross@suse.com>
---
V2:
- new patch
---
 drivers/xen/privcmd.c    | 13 +++++++++++++
 include/linux/security.h |  1 +
 security/security.c      |  1 +
 3 files changed, 15 insertions(+)

diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index a83bad69f4f2..bbf9ee21306c 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -32,6 +32,7 @@
 #include <linux/miscdevice.h>
 #include <linux/moduleparam.h>
 #include <linux/notifier.h>
+#include <linux/security.h>
 #include <linux/virtio_mmio.h>
 #include <linux/wait.h>
 
@@ -72,6 +73,11 @@ module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint,
 MODULE_PARM_DESC(dm_op_buf_max_size,
 		 "Maximum size of a dm_op hypercall buffer");
 
+static bool unrestricted;
+module_param(unrestricted, bool, 0);
+MODULE_PARM_DESC(unrestricted,
+	"Don't restrict hypercalls to target domain if running in a domU");
+
 struct privcmd_data {
 	domid_t domid;
 };
@@ -1708,6 +1714,13 @@ static struct notifier_block xenstore_notifier = {
 
 static void __init restrict_driver(void)
 {
+	if (unrestricted) {
+		if (security_locked_down(LOCKDOWN_XEN_USER_ACTIONS))
+			pr_warn("Kernel is locked down, parameter \"unrestricted\" ignored\n");
+		else
+			return;
+	}
+
 	restrict_wait = true;
 
 	register_xenstore_notifier(&xenstore_notifier);
diff --git a/include/linux/security.h b/include/linux/security.h
index 83a646d72f6f..ee88dd2d2d1f 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -145,6 +145,7 @@ enum lockdown_reason {
 	LOCKDOWN_BPF_WRITE_USER,
 	LOCKDOWN_DBG_WRITE_KERNEL,
 	LOCKDOWN_RTAS_ERROR_INJECTION,
+	LOCKDOWN_XEN_USER_ACTIONS,
 	LOCKDOWN_INTEGRITY_MAX,
 	LOCKDOWN_KCORE,
 	LOCKDOWN_KPROBES,
diff --git a/security/security.c b/security/security.c
index 67af9228c4e9..a26c1474e2e4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -61,6 +61,7 @@ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = {
 	[LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM",
 	[LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM",
 	[LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection",
+	[LOCKDOWN_XEN_USER_ACTIONS] = "Xen guest user action",
 	[LOCKDOWN_INTEGRITY_MAX] = "integrity",
 	[LOCKDOWN_KCORE] = "/proc/kcore access",
 	[LOCKDOWN_KPROBES] = "use of kprobes",
-- 
cgit v1.2.3


From 215e5fe75881a7e2425df04aeeed47a903d5cd5d Mon Sep 17 00:00:00 2001
From: Cássio Gabriel <cassiogabrielcontato@gmail.com>
Date: Thu, 19 Mar 2026 21:45:26 -0300
Subject: ASoC: SOF: topology: reject invalid vendor array size in token parser
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sof_parse_token_sets() accepts array->size values that can be invalid
for a vendor tuple array header. In particular, a zero size does not
advance the parser state and can lead to non-progress parsing on
malformed topology data.

Validate array->size against the minimum header size and reject values
smaller than sizeof(*array) before parsing. This preserves behavior for
valid topologies and hardens malformed-input handling.

Signed-off-by: Cássio Gabriel <cassiogabrielcontato@gmail.com>
Acked-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20260319-sof-topology-array-size-fix-v1-1-f9191b16b1b7@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/topology.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index 18e2401152c8..35200d801fb7 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -736,7 +736,7 @@ static int sof_parse_token_sets(struct snd_soc_component *scomp,
 		asize = le32_to_cpu(array->size);
 
 		/* validate asize */
-		if (asize < 0) { /* FIXME: A zero-size array makes no sense */
+		if (asize < sizeof(*array)) {
 			dev_err(scomp->dev, "error: invalid array size 0x%x\n",
 				asize);
 			return -EINVAL;
-- 
cgit v1.2.3


From 2594196f4e3bd70782e7cf1e22e3e398cdb74f78 Mon Sep 17 00:00:00 2001
From: Hasun Park <hasunpark@gmail.com>
Date: Fri, 20 Mar 2026 01:33:21 +0900
Subject: ASoC: amd: acp: add ASUS HN7306EA quirk for legacy SDW machine

Add a DMI quirk entry for ASUS HN7306EA in the ACP SoundWire legacy
machine driver.

Set driver_data to ASOC_SDW_ACP_DMIC for this board so the
platform-specific DMIC quirk path is selected.

Signed-off-by: Hasun Park <hasunpark@gmail.com>
Link: https://patch.msgid.link/20260319163321.30326-1-hasunpark@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-sdw-legacy-mach.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
index c30ccf23005a..6388cd7cb28e 100644
--- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c
+++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
@@ -111,6 +111,14 @@ static const struct dmi_system_id soc_sdw_quirk_table[] = {
 		},
 		.driver_data = (void *)(ASOC_SDW_CODEC_SPKR),
 	},
+	{
+		.callback = soc_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HN7306EA"),
+		},
+		.driver_data = (void *)(ASOC_SDW_ACP_DMIC),
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 76f9377cd2ab7a9220c25d33940d9ca20d368172 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 19 Mar 2026 17:51:45 -0700
Subject: writeback: don't block sync for filesystems with no data integrity
 guarantees

Add a SB_I_NO_DATA_INTEGRITY superblock flag for filesystems that cannot
guarantee data persistence on sync (eg fuse). For superblocks with this
flag set, sync kicks off writeback of dirty inodes but does not wait
for the flusher threads to complete the writeback.

This replaces the per-inode AS_NO_DATA_INTEGRITY mapping flag added in
commit f9a49aa302a0 ("fs/writeback: skip AS_NO_DATA_INTEGRITY mappings
in wait_sb_inodes()"). The flag belongs at the superblock level because
data integrity is a filesystem-wide property, not a per-inode one.
Having this flag at the superblock level also allows us to skip having
to iterate every dirty inode in wait_sb_inodes() only to skip each inode
individually.

Prior to this commit, mappings with no data integrity guarantees skipped
waiting on writeback completion but still waited on the flusher threads
to finish initiating the writeback. Waiting on the flusher threads is
unnecessary. This commit kicks off writeback but does not wait on the
flusher threads. This change properly addresses a recent report [1] for
a suspend-to-RAM hang seen on fuse-overlayfs that was caused by waiting
on the flusher threads to finish:

Workqueue: pm_fs_sync pm_fs_sync_work_fn
Call Trace:
 <TASK>
 __schedule+0x457/0x1720
 schedule+0x27/0xd0
 wb_wait_for_completion+0x97/0xe0
 sync_inodes_sb+0xf8/0x2e0
 __iterate_supers+0xdc/0x160
 ksys_sync+0x43/0xb0
 pm_fs_sync_work_fn+0x17/0xa0
 process_one_work+0x193/0x350
 worker_thread+0x1a1/0x310
 kthread+0xfc/0x240
 ret_from_fork+0x243/0x280
 ret_from_fork_asm+0x1a/0x30
 </TASK>

On fuse this is problematic because there are paths that may cause the
flusher thread to block (eg if systemd freezes the user session cgroups
first, which freezes the fuse daemon, before invoking the kernel
suspend. The kernel suspend triggers ->write_node() which on fuse issues
a synchronous setattr request, which cannot be processed since the
daemon is frozen. Or if the daemon is buggy and cannot properly complete
writeback, initiating writeback on a dirty folio already under writeback
leads to writeback_get_folio() -> folio_prepare_writeback() ->
unconditional wait on writeback to finish, which will cause a hang).
This commit restores fuse to its prior behavior before tmp folios were
removed, where sync was essentially a no-op.

[1] https://lore.kernel.org/linux-fsdevel/CAJnrk1a-asuvfrbKXbEwwDSctvemF+6zfhdnuzO65Pt8HsFSRw@mail.gmail.com/T/#m632c4648e9cafc4239299887109ebd880ac6c5c1

Fixes: 0c58a97f919c ("fuse: remove tmp folio for writebacks and internal rb tree")
Reported-by: John <therealgraysky@proton.me>
Cc: stable@vger.kernel.org
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://patch.msgid.link/20260320005145.2483161-2-joannelkoong@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs-writeback.c              | 18 ++++++++++++------
 fs/fuse/file.c                 |  4 +---
 fs/fuse/inode.c                |  1 +
 include/linux/fs/super_types.h |  1 +
 include/linux/pagemap.h        | 11 -----------
 5 files changed, 15 insertions(+), 20 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d8dac1931595..3c75ee025bda 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2787,13 +2787,8 @@ static void wait_sb_inodes(struct super_block *sb)
 		 * The mapping can appear untagged while still on-list since we
 		 * do not have the mapping lock. Skip it here, wb completion
 		 * will remove it.
-		 *
-		 * If the mapping does not have data integrity semantics,
-		 * there's no need to wait for the writeout to complete, as the
-		 * mapping cannot guarantee that data is persistently stored.
 		 */
-		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) ||
-		    mapping_no_data_integrity(mapping))
+		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
 			continue;
 
 		spin_unlock_irq(&sb->s_inode_wblist_lock);
@@ -2928,6 +2923,17 @@ void sync_inodes_sb(struct super_block *sb)
 	 */
 	if (bdi == &noop_backing_dev_info)
 		return;
+
+	/*
+	 * If the superblock has SB_I_NO_DATA_INTEGRITY set, there's no need to
+	 * wait for the writeout to complete, as the filesystem cannot guarantee
+	 * data persistence on sync. Just kick off writeback and return.
+	 */
+	if (sb->s_iflags & SB_I_NO_DATA_INTEGRITY) {
+		wakeup_flusher_threads_bdi(bdi, WB_REASON_SYNC);
+		return;
+	}
+
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	/* protect against inode wb switch, see inode_switch_wbs_work_fn() */
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b1bb7153cb78..676fd9856bfb 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3201,10 +3201,8 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags)
 
 	inode->i_fop = &fuse_file_operations;
 	inode->i_data.a_ops = &fuse_file_aops;
-	if (fc->writeback_cache) {
+	if (fc->writeback_cache)
 		mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data);
-		mapping_set_no_data_integrity(&inode->i_data);
-	}
 
 	INIT_LIST_HEAD(&fi->write_files);
 	INIT_LIST_HEAD(&fi->queued_writes);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e57b8af06be9..c795abe47a4f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1709,6 +1709,7 @@ static void fuse_sb_defaults(struct super_block *sb)
 	sb->s_export_op = &fuse_export_operations;
 	sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE;
 	sb->s_iflags |= SB_I_NOIDMAP;
+	sb->s_iflags |= SB_I_NO_DATA_INTEGRITY;
 	if (sb->s_user_ns != &init_user_ns)
 		sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER;
 	sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index fa7638b81246..383050e7fdf5 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -338,5 +338,6 @@ struct super_block {
 #define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
 #define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
 #define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
+#define SB_I_NO_DATA_INTEGRITY	0x00008000 /* fs cannot guarantee data persistence on sync */
 
 #endif /* _LINUX_FS_SUPER_TYPES_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ec442af3f886..31a848485ad9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -210,7 +210,6 @@ enum mapping_flags {
 	AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9,
 	AS_KERNEL_FILE = 10,	/* mapping for a fake kernel file that shouldn't
 				   account usage to user cgroups */
-	AS_NO_DATA_INTEGRITY = 11, /* no data integrity guarantees */
 	/* Bits 16-25 are used for FOLIO_ORDER */
 	AS_FOLIO_ORDER_BITS = 5,
 	AS_FOLIO_ORDER_MIN = 16,
@@ -346,16 +345,6 @@ static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct addres
 	return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags);
 }
 
-static inline void mapping_set_no_data_integrity(struct address_space *mapping)
-{
-	set_bit(AS_NO_DATA_INTEGRITY, &mapping->flags);
-}
-
-static inline bool mapping_no_data_integrity(const struct address_space *mapping)
-{
-	return test_bit(AS_NO_DATA_INTEGRITY, &mapping->flags);
-}
-
 static inline gfp_t mapping_gfp_mask(const struct address_space *mapping)
 {
 	return mapping->gfp_mask;
-- 
cgit v1.2.3


From 217c0a5c177a3d4f7c8497950cbf5c36756e8bbb Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 20 Mar 2026 15:59:48 +0200
Subject: x86/efi: efi_unmap_boot_services: fix calculation of ranges_to_free
 size

ranges_to_free array should have enough room to store the entire EFI
memmap plus an extra element for NULL entry.
The calculation of this array size wrongly adds 1 to the overall size
instead of adding 1 to the number of elements.

Add parentheses to properly size the array.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: a4b0bf6a40f3 ("x86/efi: defer freeing of boot services memory")
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/platform/efi/quirks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 35caa5746115..79f0818131e8 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -424,7 +424,7 @@ void __init efi_unmap_boot_services(void)
 	if (efi_enabled(EFI_DBG))
 		return;
 
-	sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1;
+	sz = sizeof(*ranges_to_free) * (efi.memmap.nr_map + 1);
 	ranges_to_free = kzalloc(sz, GFP_KERNEL);
 	if (!ranges_to_free) {
 		pr_err("Failed to allocate storage for freeable EFI regions\n");
-- 
cgit v1.2.3


From 63f8b60151dc00895137bfadc987f258060ab264 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 20 Mar 2026 17:06:53 +0100
Subject: x86/entry/vdso: Fix path of included gettimeofday.c

Commit in Fixes forgot to convert one include path to be relative to the
kernel source directory after adding latter to flags-y.

Fix it.

  [ bp: Rewrite commit message. ]

Fixes: 693c819fedcd ("x86/entry/vdso: Refactor the vdso build")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20260307174406.1808981-1-vladimir.oltean@nxp.com
---
 arch/x86/entry/vdso/common/vclock_gettime.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/entry/vdso/common/vclock_gettime.c b/arch/x86/entry/vdso/common/vclock_gettime.c
index 027b7e88d753..57066f346b3f 100644
--- a/arch/x86/entry/vdso/common/vclock_gettime.c
+++ b/arch/x86/entry/vdso/common/vclock_gettime.c
@@ -13,7 +13,7 @@
 #include <linux/types.h>
 #include <vdso/gettime.h>
 
-#include "../../../../lib/vdso/gettimeofday.c"
+#include "lib/vdso/gettimeofday.c"
 
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
-- 
cgit v1.2.3


From 1c7bbaeed110b0fd9e65e173fb4d612f64a20d93 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 20 Mar 2026 10:51:18 -0700
Subject: coccinelle: kmalloc_obj: Remove default GFP_KERNEL arg

Remove any GFP_KERNEL arguments found in the new kmalloc_obj-family
helpers. This captures the script used in commit 189f164e573e ("Convert
remaining multi-line kmalloc_obj/flex GFP_KERNEL uses").

Link: https://patch.msgid.link/20260320175113.work.016-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 scripts/coccinelle/api/kmalloc_objs.cocci | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/scripts/coccinelle/api/kmalloc_objs.cocci b/scripts/coccinelle/api/kmalloc_objs.cocci
index db12b7be7247..e9a415b7b6f4 100644
--- a/scripts/coccinelle/api/kmalloc_objs.cocci
+++ b/scripts/coccinelle/api/kmalloc_objs.cocci
@@ -122,3 +122,14 @@ fresh identifier ALLOC_OBJS = script:python(ALLOC_ARRAY) { alloc_array(ALLOC_ARR
 -	ALLOC(struct_size_t(TYPE, FLEX, COUNT), GFP)
 +	ALLOC_FLEX(TYPE, FLEX, COUNT, GFP)
 )
+
+@drop_gfp_kernel depends on patch && !(file in "tools") && !(file in "samples")@
+identifier ALLOC = {kmalloc_obj,kmalloc_objs,kmalloc_flex,
+		    kzalloc_obj,kzalloc_objs,kzalloc_flex,
+		    kvmalloc_obj,kvmalloc_objs,kvmalloc_flex,
+		    kvzalloc_obj,kvzalloc_objs,kvzalloc_flex};
+@@
+
+	ALLOC(...
+-		 , GFP_KERNEL
+	     )
-- 
cgit v1.2.3


From 1f6aa5bbf1d0f81a8a2aafc16136e7dd9a609ff3 Mon Sep 17 00:00:00 2001
From: Kyle Meyer <kyle.meyer@hpe.com>
Date: Fri, 20 Mar 2026 12:19:20 -0500
Subject: x86/platform/uv: Handle deconfigured sockets

When a socket is deconfigured, it's mapped to SOCK_EMPTY (0xffff). This causes
a panic while allocating UV hub info structures.

Fix this by using NUMA_NO_NODE, allowing UV hub info structures to be
allocated on valid nodes.

Fixes: 8a50c5851927 ("x86/platform/uv: UV support for sub-NUMA clustering")
Signed-off-by: Kyle Meyer <kyle.meyer@hpe.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/ab2BmGL0ehVkkjKk@hpe.com
---
 arch/x86/kernel/apic/x2apic_uv_x.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 15209f220e1f..42568ceec481 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1708,8 +1708,22 @@ static void __init uv_system_init_hub(void)
 		struct uv_hub_info_s *new_hub;
 
 		/* Allocate & fill new per hub info list */
-		new_hub = (bid == 0) ?  &uv_hub_info_node0
-			: kzalloc_node(bytes, GFP_KERNEL, uv_blade_to_node(bid));
+		if (bid == 0) {
+			new_hub = &uv_hub_info_node0;
+		} else {
+			int nid;
+
+			/*
+			 * Deconfigured sockets are mapped to SOCK_EMPTY. Use
+			 * NUMA_NO_NODE to allocate on a valid node.
+			 */
+			nid = uv_blade_to_node(bid);
+			if (nid == SOCK_EMPTY)
+				nid = NUMA_NO_NODE;
+
+			new_hub = kzalloc_node(bytes, GFP_KERNEL, nid);
+		}
+
 		if (WARN_ON_ONCE(!new_hub)) {
 			/* do not kfree() bid 0, which is statically allocated */
 			while (--bid > 0)
-- 
cgit v1.2.3


From 7a618ca9b9c4769fc5adf7344bb1dd98f823da22 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 18 Mar 2026 17:20:18 -0700
Subject: init/Kconfig: Require a release version of clang-22 for
 CC_HAS_COUNTED_BY_PTR

Commit 150a04d817d8 ("compiler_types.h: Attributes: Add __counted_by_ptr
macro") used Clang 22.0.0 as a minimum supported version for
__counted_by_ptr, which made sense while 22.0.0 was the version of
LLVM's main branch to allow developers to easily test and develop uses
of __counted_by_ptr in their code. However, __counted_by_ptr requires a
change [1] merged towards the end of the 22 development cycle to avoid
errors when applied to void pointers.

  In file included from fs/xfs/xfs_attr_inactive.c:18:
  fs/xfs/libxfs/xfs_attr.h:59:2: error: 'counted_by' cannot be applied to a pointer with pointee of unknown size because 'void' is an incomplete type
     59 |         void                    *buffer __counted_by_ptr(bufsize);
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This is disruptive for deployed prerelease clang-22 builds (such as
Android LLVM) or when bisecting between llvmorg-21-init and the fix.

Require a released version of clang-22 (i.e., 21.1.0 or newer) to
enabled __counted_by_ptr to ensure all fixes needed for proper support
are present.

Fixes: 150a04d817d8 ("compiler_types.h: Attributes: Add __counted_by_ptr macro")
Link: https://github.com/llvm/llvm-project/commit/f29955a594aedf5943d492a999b83e8c6b8fafae [1]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20260318-counted_by_ptr-release-clang-22-v1-1-e017da246df0@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index b55deae9256c..399c0ed3b4a9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -146,7 +146,7 @@ config CC_HAS_COUNTED_BY
 config CC_HAS_COUNTED_BY_PTR
 	bool
 	# supported since clang 22
-	default y if CC_IS_CLANG && CLANG_VERSION >= 220000
+	default y if CC_IS_CLANG && CLANG_VERSION >= 220100
 	# supported since gcc 16.0.0
 	default y if CC_IS_GCC && GCC_VERSION >= 160000
 
-- 
cgit v1.2.3


From e7bae9a7a5e1251ab414291f4e9304d702bb9221 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 19 Mar 2026 21:31:22 -0700
Subject: hwmon: (max6639) Fix pulses-per-revolution implementation

The valid range for the pulses-per-revolution devicetree property is
1..4. The current code checks for a range of 1..5. Fix it.

Declare the variable used to retrieve pulses per revolution from
devicetree as u32 (unsigned) to match the of_property_read_u32() API.

The current code uses a postfix decrement when writing the pulses per
resolution into the chip. This has no effect since the value is evaluated
before it is decremented. Fix it by decrementing before evaluating the
value.

Fixes: 7506ebcd662b ("hwmon: (max6639) : Configure based on DT property")
Cc: Naresh Solanki <naresh.solanki@9elements.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/max6639.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/hwmon/max6639.c b/drivers/hwmon/max6639.c
index 9a3c515efe2e..163d31f17bd4 100644
--- a/drivers/hwmon/max6639.c
+++ b/drivers/hwmon/max6639.c
@@ -232,7 +232,7 @@ static int max6639_read_fan(struct device *dev, u32 attr, int channel,
 static int max6639_set_ppr(struct max6639_data *data, int channel, u8 ppr)
 {
 	/* Decrement the PPR value and shift left by 6 to match the register format */
-	return regmap_write(data->regmap, MAX6639_REG_FAN_PPR(channel), ppr-- << 6);
+	return regmap_write(data->regmap, MAX6639_REG_FAN_PPR(channel), --ppr << 6);
 }
 
 static int max6639_write_fan(struct device *dev, u32 attr, int channel,
@@ -524,8 +524,8 @@ static int max6639_probe_child_from_dt(struct i2c_client *client,
 
 {
 	struct device *dev = &client->dev;
-	u32 i;
-	int err, val;
+	u32 i, val;
+	int err;
 
 	err = of_property_read_u32(child, "reg", &i);
 	if (err) {
@@ -540,8 +540,8 @@ static int max6639_probe_child_from_dt(struct i2c_client *client,
 
 	err = of_property_read_u32(child, "pulses-per-revolution", &val);
 	if (!err) {
-		if (val < 1 || val > 5) {
-			dev_err(dev, "invalid pulses-per-revolution %d of %pOFn\n", val, child);
+		if (val < 1 || val > 4) {
+			dev_err(dev, "invalid pulses-per-revolution %u of %pOFn\n", val, child);
 			return -EINVAL;
 		}
 		data->ppr[i] = val;
-- 
cgit v1.2.3


From 317e49358ebbf6390fa439ef3c142f9239dd25fb Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Wed, 18 Mar 2026 14:36:58 +0800
Subject: net: macb: Move devm_{free,request}_irq() out of spin lock area
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The devm_free_irq() and devm_request_irq() functions should not be
executed in an atomic context.

During device suspend, all userspace processes and most kernel threads
are frozen. Additionally, we flush all tx/rx status, disable all macb
interrupts, and halt rx operations. Therefore, it is safe to split the
region protected by bp->lock into two independent sections, allowing
devm_free_irq() and devm_request_irq() to run in a non-atomic context.
This modification resolves the following lockdep warning:
  BUG: sleeping function called from invalid context at kernel/locking/mutex.c:591
  in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 501, name: rtcwake
  preempt_count: 1, expected: 0
  RCU nest depth: 1, expected: 0
  7 locks held by rtcwake/501:
   #0: ffff0008038c3408 (sb_writers#5){.+.+}-{0:0}, at: vfs_write+0xf8/0x368
   #1: ffff0008049a5e88 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0xbc/0x1c8
   #2: ffff00080098d588 (kn->active#70){.+.+}-{0:0}, at: kernfs_fop_write_iter+0xcc/0x1c8
   #3: ffff800081c84888 (system_transition_mutex){+.+.}-{4:4}, at: pm_suspend+0x1ec/0x290
   #4: ffff0008009ba0f8 (&dev->mutex){....}-{4:4}, at: device_suspend+0x118/0x4f0
   #5: ffff800081d00458 (rcu_read_lock){....}-{1:3}, at: rcu_lock_acquire+0x4/0x48
   #6: ffff0008031fb9e0 (&bp->lock){-.-.}-{3:3}, at: macb_suspend+0x144/0x558
  irq event stamp: 8682
  hardirqs last  enabled at (8681): [<ffff8000813c7d7c>] _raw_spin_unlock_irqrestore+0x44/0x88
  hardirqs last disabled at (8682): [<ffff8000813c7b58>] _raw_spin_lock_irqsave+0x38/0x98
  softirqs last  enabled at (7322): [<ffff8000800f1b4c>] handle_softirqs+0x52c/0x588
  softirqs last disabled at (7317): [<ffff800080010310>] __do_softirq+0x20/0x2c
  CPU: 1 UID: 0 PID: 501 Comm: rtcwake Not tainted 7.0.0-rc3-next-20260310-yocto-standard+ #125 PREEMPT
  Hardware name: ZynqMP ZCU102 Rev1.1 (DT)
  Call trace:
   show_stack+0x24/0x38 (C)
   __dump_stack+0x28/0x38
   dump_stack_lvl+0x64/0x88
   dump_stack+0x18/0x24
   __might_resched+0x200/0x218
   __might_sleep+0x38/0x98
   __mutex_lock_common+0x7c/0x1378
   mutex_lock_nested+0x38/0x50
   free_irq+0x68/0x2b0
   devm_irq_release+0x24/0x38
   devres_release+0x40/0x80
   devm_free_irq+0x48/0x88
   macb_suspend+0x298/0x558
   device_suspend+0x218/0x4f0
   dpm_suspend+0x244/0x3a0
   dpm_suspend_start+0x50/0x78
   suspend_devices_and_enter+0xec/0x560
   pm_suspend+0x194/0x290
   state_store+0x110/0x158
   kobj_attr_store+0x1c/0x30
   sysfs_kf_write+0xa8/0xd0
   kernfs_fop_write_iter+0x11c/0x1c8
   vfs_write+0x248/0x368
   ksys_write+0x7c/0xf8
   __arm64_sys_write+0x28/0x40
   invoke_syscall+0x4c/0xe8
   el0_svc_common+0x98/0xf0
   do_el0_svc+0x28/0x40
   el0_svc+0x54/0x1e0
   el0t_64_sync_handler+0x84/0x130
   el0t_64_sync+0x198/0x1a0

Fixes: 558e35ccfe95 ("net: macb: WoL support for GEM type of Ethernet controller")
Cc: stable@vger.kernel.org
Reviewed-by: Théo Lebrun <theo.lebrun@bootlin.com>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Link: https://patch.msgid.link/20260318-macb-irq-v2-1-f1179768ab24@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index c16ac9c76aa3..1b95226ae696 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5835,6 +5835,7 @@ static int __maybe_unused macb_suspend(struct device *dev)
 			/* write IP address into register */
 			tmp |= MACB_BFEXT(IP, be32_to_cpu(ifa->ifa_local));
 		}
+		spin_unlock_irqrestore(&bp->lock, flags);
 
 		/* Change interrupt handler and
 		 * Enable WoL IRQ on queue 0
@@ -5847,11 +5848,12 @@ static int __maybe_unused macb_suspend(struct device *dev)
 				dev_err(dev,
 					"Unable to request IRQ %d (error %d)\n",
 					bp->queues[0].irq, err);
-				spin_unlock_irqrestore(&bp->lock, flags);
 				return err;
 			}
+			spin_lock_irqsave(&bp->lock, flags);
 			queue_writel(bp->queues, IER, GEM_BIT(WOL));
 			gem_writel(bp, WOL, tmp);
+			spin_unlock_irqrestore(&bp->lock, flags);
 		} else {
 			err = devm_request_irq(dev, bp->queues[0].irq, macb_wol_interrupt,
 					       IRQF_SHARED, netdev->name, bp->queues);
@@ -5859,13 +5861,13 @@ static int __maybe_unused macb_suspend(struct device *dev)
 				dev_err(dev,
 					"Unable to request IRQ %d (error %d)\n",
 					bp->queues[0].irq, err);
-				spin_unlock_irqrestore(&bp->lock, flags);
 				return err;
 			}
+			spin_lock_irqsave(&bp->lock, flags);
 			queue_writel(bp->queues, IER, MACB_BIT(WOL));
 			macb_writel(bp, WOL, tmp);
+			spin_unlock_irqrestore(&bp->lock, flags);
 		}
-		spin_unlock_irqrestore(&bp->lock, flags);
 
 		enable_irq_wake(bp->queues[0].irq);
 	}
@@ -5932,6 +5934,8 @@ static int __maybe_unused macb_resume(struct device *dev)
 		queue_readl(bp->queues, ISR);
 		if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 			queue_writel(bp->queues, ISR, -1);
+		spin_unlock_irqrestore(&bp->lock, flags);
+
 		/* Replace interrupt handler on queue 0 */
 		devm_free_irq(dev, bp->queues[0].irq, bp->queues);
 		err = devm_request_irq(dev, bp->queues[0].irq, macb_interrupt,
@@ -5940,10 +5944,8 @@ static int __maybe_unused macb_resume(struct device *dev)
 			dev_err(dev,
 				"Unable to request IRQ %d (error %d)\n",
 				bp->queues[0].irq, err);
-			spin_unlock_irqrestore(&bp->lock, flags);
 			return err;
 		}
-		spin_unlock_irqrestore(&bp->lock, flags);
 
 		disable_irq_wake(bp->queues[0].irq);
 
-- 
cgit v1.2.3


From baa35a698cea26930679a20a7550bbb4c8319725 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Wed, 18 Mar 2026 14:36:59 +0800
Subject: net: macb: Protect access to net_device::ip_ptr with RCU lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Access to net_device::ip_ptr and its associated members must be
protected by an RCU lock. Since we are modifying this piece of code,
let's also move it to execute only when WAKE_ARP is enabled.

To minimize the duration of the RCU lock, a local variable is used to
temporarily store the IP address. This change resolves the following
RCU check warning:
  WARNING: suspicious RCU usage
  7.0.0-rc3-next-20260310-yocto-standard+ #122 Not tainted
  -----------------------------
  drivers/net/ethernet/cadence/macb_main.c:5944 suspicious rcu_dereference_check() usage!

  other info that might help us debug this:

  rcu_scheduler_active = 2, debug_locks = 1
  5 locks held by rtcwake/518:
   #0: ffff000803ab1408 (sb_writers#5){.+.+}-{0:0}, at: vfs_write+0xf8/0x368
   #1: ffff0008090bf088 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0xbc/0x1c8
   #2: ffff00080098d588 (kn->active#70){.+.+}-{0:0}, at: kernfs_fop_write_iter+0xcc/0x1c8
   #3: ffff800081c84888 (system_transition_mutex){+.+.}-{4:4}, at: pm_suspend+0x1ec/0x290
   #4: ffff0008009ba0f8 (&dev->mutex){....}-{4:4}, at: device_suspend+0x118/0x4f0

  stack backtrace:
  CPU: 3 UID: 0 PID: 518 Comm: rtcwake Not tainted 7.0.0-rc3-next-20260310-yocto-standard+ #122 PREEMPT
  Hardware name: ZynqMP ZCU102 Rev1.1 (DT)
  Call trace:
   show_stack+0x24/0x38 (C)
   __dump_stack+0x28/0x38
   dump_stack_lvl+0x64/0x88
   dump_stack+0x18/0x24
   lockdep_rcu_suspicious+0x134/0x1d8
   macb_suspend+0xd8/0x4c0
   device_suspend+0x218/0x4f0
   dpm_suspend+0x244/0x3a0
   dpm_suspend_start+0x50/0x78
   suspend_devices_and_enter+0xec/0x560
   pm_suspend+0x194/0x290
   state_store+0x110/0x158
   kobj_attr_store+0x1c/0x30
   sysfs_kf_write+0xa8/0xd0
   kernfs_fop_write_iter+0x11c/0x1c8
   vfs_write+0x248/0x368
   ksys_write+0x7c/0xf8
   __arm64_sys_write+0x28/0x40
   invoke_syscall+0x4c/0xe8
   el0_svc_common+0x98/0xf0
   do_el0_svc+0x28/0x40
   el0_svc+0x54/0x1e0
   el0t_64_sync_handler+0x84/0x130
   el0t_64_sync+0x198/0x1a0

Fixes: 0cb8de39a776 ("net: macb: Add ARP support to WOL")
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://patch.msgid.link/20260318-macb-irq-v2-2-f1179768ab24@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 1b95226ae696..944aab71795c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5776,9 +5776,9 @@ static int __maybe_unused macb_suspend(struct device *dev)
 	struct macb_queue *queue;
 	struct in_device *idev;
 	unsigned long flags;
+	u32 tmp, ifa_local;
 	unsigned int q;
 	int err;
-	u32 tmp;
 
 	if (!device_may_wakeup(&bp->dev->dev))
 		phy_exit(bp->phy);
@@ -5787,14 +5787,21 @@ static int __maybe_unused macb_suspend(struct device *dev)
 		return 0;
 
 	if (bp->wol & MACB_WOL_ENABLED) {
-		/* Check for IP address in WOL ARP mode */
-		idev = __in_dev_get_rcu(bp->dev);
-		if (idev)
-			ifa = rcu_dereference(idev->ifa_list);
-		if ((bp->wolopts & WAKE_ARP) && !ifa) {
-			netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n");
-			return -EOPNOTSUPP;
+		if (bp->wolopts & WAKE_ARP) {
+			/* Check for IP address in WOL ARP mode */
+			rcu_read_lock();
+			idev = __in_dev_get_rcu(bp->dev);
+			if (idev)
+				ifa = rcu_dereference(idev->ifa_list);
+			if (!ifa) {
+				rcu_read_unlock();
+				netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n");
+				return -EOPNOTSUPP;
+			}
+			ifa_local = be32_to_cpu(ifa->ifa_local);
+			rcu_read_unlock();
 		}
+
 		spin_lock_irqsave(&bp->lock, flags);
 
 		/* Disable Tx and Rx engines before  disabling the queues,
@@ -5833,7 +5840,7 @@ static int __maybe_unused macb_suspend(struct device *dev)
 		if (bp->wolopts & WAKE_ARP) {
 			tmp |= MACB_BIT(ARP);
 			/* write IP address into register */
-			tmp |= MACB_BFEXT(IP, be32_to_cpu(ifa->ifa_local));
+			tmp |= MACB_BFEXT(IP, ifa_local);
 		}
 		spin_unlock_irqrestore(&bp->lock, flags);
 
-- 
cgit v1.2.3


From 6931d21f87bc6d657f145798fad0bf077b82486c Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Thu, 19 Mar 2026 07:42:41 +0000
Subject: openvswitch: defer tunnel netdev_put to RCU release

ovs_netdev_tunnel_destroy() may run after NETDEV_UNREGISTER already
detached the device. Dropping the netdev reference in destroy can race
with concurrent readers that still observe vport->dev.

Do not release vport->dev in ovs_netdev_tunnel_destroy(). Instead, let
vport_netdev_free() drop the reference from the RCU callback, matching
the non-tunnel destroy path and avoiding additional synchronization
under RTNL.

Fixes: a9020fde67a6 ("openvswitch: Move tunnel destroy function to oppenvswitch module.")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Tested-by: Ao Zhou <n05ec@lzu.edu.cn>
Co-developed-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Link: https://patch.msgid.link/20260319074241.3405262-1-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/vport-netdev.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index c688dee96503..12055af832dc 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -196,8 +196,6 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
 	 */
 	if (vport->dev->reg_state == NETREG_REGISTERED)
 		rtnl_delete_link(vport->dev, 0, NULL);
-	netdev_put(vport->dev, &vport->dev_tracker);
-	vport->dev = NULL;
 	rtnl_unlock();
 
 	call_rcu(&vport->rcu, vport_netdev_free);
-- 
cgit v1.2.3


From 546b68ac893595877ffbd7751e5c55fd1c43ede6 Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Thu, 19 Mar 2026 08:02:27 +0000
Subject: openvswitch: validate MPLS set/set_masked payload length

validate_set() accepted OVS_KEY_ATTR_MPLS as variable-sized payload for
SET/SET_MASKED actions. In action handling, OVS expects fixed-size
MPLS key data (struct ovs_key_mpls).

Use the already normalized key_len (masked case included) and reject
non-matching MPLS action key sizes.

Reject invalid MPLS action payload lengths early.

Fixes: fbdcdd78da7c ("Change in Openvswitch to support MPLS label depth of 3 in ingress direction")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Tested-by: Ao Zhou <n05ec@lzu.edu.cn>
Co-developed-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Link: https://patch.msgid.link/20260319080228.3423307-1-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/flow_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 67fbf6e48a30..13052408a132 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2953,6 +2953,8 @@ static int validate_set(const struct nlattr *a,
 	case OVS_KEY_ATTR_MPLS:
 		if (!eth_p_mpls(eth_type))
 			return -EINVAL;
+		if (key_len != sizeof(struct ovs_key_mpls))
+			return -EINVAL;
 		break;
 
 	case OVS_KEY_ATTR_SCTP:
-- 
cgit v1.2.3


From 24dd586bb4cbba1889a50abe74143817a095c1c9 Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Wed, 18 Mar 2026 14:48:47 +0800
Subject: net/smc: fix double-free of smc_spd_priv when tee() duplicates splice
 pipe buffer

smc_rx_splice() allocates one smc_spd_priv per pipe_buffer and stores
the pointer in pipe_buffer.private.  The pipe_buf_operations for these
buffers used .get = generic_pipe_buf_get, which only increments the page
reference count when tee(2) duplicates a pipe buffer.  The smc_spd_priv
pointer itself was not handled, so after tee() both the original and the
cloned pipe_buffer share the same smc_spd_priv *.

When both pipes are subsequently released, smc_rx_pipe_buf_release() is
called twice against the same object:

  1st call: kfree(priv)  sock_put(sk)  smc_rx_update_cons()  [correct]
  2nd call: kfree(priv)  sock_put(sk)  smc_rx_update_cons()  [UAF]

KASAN reports a slab-use-after-free in smc_rx_pipe_buf_release(), which
then escalates to a NULL-pointer dereference and kernel panic via
smc_rx_update_consumer() when it chases the freed priv->smc pointer:

  BUG: KASAN: slab-use-after-free in smc_rx_pipe_buf_release+0x78/0x2a0
  Read of size 8 at addr ffff888004a45740 by task smc_splice_tee_/74
  Call Trace:
   <TASK>
   dump_stack_lvl+0x53/0x70
   print_report+0xce/0x650
   kasan_report+0xc6/0x100
   smc_rx_pipe_buf_release+0x78/0x2a0
   free_pipe_info+0xd4/0x130
   pipe_release+0x142/0x160
   __fput+0x1c6/0x490
   __x64_sys_close+0x4f/0x90
   do_syscall_64+0xa6/0x1a0
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>

  BUG: kernel NULL pointer dereference, address: 0000000000000020
  RIP: 0010:smc_rx_update_consumer+0x8d/0x350
  Call Trace:
   <TASK>
   smc_rx_pipe_buf_release+0x121/0x2a0
   free_pipe_info+0xd4/0x130
   pipe_release+0x142/0x160
   __fput+0x1c6/0x490
   __x64_sys_close+0x4f/0x90
   do_syscall_64+0xa6/0x1a0
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>
  Kernel panic - not syncing: Fatal exception

Beyond the memory-safety problem, duplicating an SMC splice buffer is
semantically questionable: smc_rx_update_cons() would advance the
consumer cursor twice for the same data, corrupting receive-window
accounting.  A refcount on smc_spd_priv could fix the double-free, but
the cursor-accounting issue would still need to be addressed separately.

The .get callback is invoked by both tee(2) and splice_pipe_to_pipe()
for partial transfers; both will now return -EFAULT.  Users who need
to duplicate SMC socket data must use a copy-based read path.

Fixes: 9014db202cb7 ("smc: add support for splice()")
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Link: https://patch.msgid.link/20260318064847.23341-1-tpluszz77@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/smc_rx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index d833e36f7fd4..c1d9b923938d 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -135,9 +135,16 @@ out:
 	sock_put(sk);
 }
 
+static bool smc_rx_pipe_buf_get(struct pipe_inode_info *pipe,
+				struct pipe_buffer *buf)
+{
+	/* smc_spd_priv in buf->private is not shareable; disallow cloning. */
+	return false;
+}
+
 static const struct pipe_buf_operations smc_pipe_ops = {
 	.release = smc_rx_pipe_buf_release,
-	.get = generic_pipe_buf_get
+	.get	 = smc_rx_pipe_buf_get,
 };
 
 static void smc_rx_spd_release(struct splice_pipe_desc *spd,
-- 
cgit v1.2.3


From 52501989c76206462d9b11a8485beef40ef41821 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 20 Mar 2026 00:02:52 +0100
Subject: rtnetlink: count IFLA_PARENT_DEV_{NAME,BUS_NAME} in if_nlmsg_size

Commit 00e77ed8e64d ("rtnetlink: add IFLA_PARENT_[DEV|DEV_BUS]_NAME")
added those attributes to rtnl_fill_ifinfo, but forgot to extend
if_nlmsg_size.

Fixes: 00e77ed8e64d ("rtnetlink: add IFLA_PARENT_[DEV|DEV_BUS]_NAME")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/0b849da95562af45487080528d60f578636aba5c.1773919462.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dad4b1054955..0fe279432d82 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1267,6 +1267,21 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev)
 	return size;
 }
 
+static size_t rtnl_dev_parent_size(const struct net_device *dev)
+{
+	size_t size = 0;
+
+	/* IFLA_PARENT_DEV_NAME */
+	if (dev->dev.parent)
+		size += nla_total_size(strlen(dev_name(dev->dev.parent)) + 1);
+
+	/* IFLA_PARENT_DEV_BUS_NAME */
+	if (dev->dev.parent && dev->dev.parent->bus)
+		size += nla_total_size(strlen(dev->dev.parent->bus->name) + 1);
+
+	return size;
+}
+
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
 				     u32 ext_filter_mask)
 {
@@ -1328,6 +1343,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(8)  /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
 	       + nla_total_size(2)  /* IFLA_HEADROOM */
 	       + nla_total_size(2)  /* IFLA_TAILROOM */
+	       + rtnl_dev_parent_size(dev)
 	       + 0;
 
 	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS))
-- 
cgit v1.2.3


From ee00a12593ffb69db4dd1a1c00ecb0253376874a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 20 Mar 2026 00:02:53 +0100
Subject: rtnetlink: count IFLA_INFO_SLAVE_KIND in if_nlmsg_size

rtnl_link_get_slave_info_data_size counts IFLA_INFO_SLAVE_DATA, but
rtnl_link_slave_info_fill adds both IFLA_INFO_SLAVE_DATA and
IFLA_INFO_SLAVE_KIND.

Fixes: ba7d49b1f0f8 ("rtnetlink: provide api for getting and setting slave info")
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/049843b532e23cde7ddba263c0bbe35ba6f0d26d.1773919462.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0fe279432d82..4a2278614250 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -707,11 +707,14 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev)
 		goto out;
 
 	ops = master_dev->rtnl_link_ops;
-	if (!ops || !ops->get_slave_size)
+	if (!ops)
+		goto out;
+	size += nla_total_size(strlen(ops->kind) + 1);  /* IFLA_INFO_SLAVE_KIND */
+	if (!ops->get_slave_size)
 		goto out;
 	/* IFLA_INFO_SLAVE_DATA + nested data */
-	size = nla_total_size(sizeof(struct nlattr)) +
-	       ops->get_slave_size(master_dev, dev);
+	size += nla_total_size(sizeof(struct nlattr)) +
+		ops->get_slave_size(master_dev, dev);
 
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From cbfa5be2bf64511d49b854a0f9fd6d0b5118621f Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 19 Mar 2026 16:48:12 -0700
Subject: net: bcmasp: fix double free of WoL irq

We do not need to free wol_irq since it was instantiated with
devm_request_irq(). So devres will free for us.

Fixes: a2f0751206b0 ("net: bcmasp: Add support for WoL magic packet")
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260319234813.1937315-2-justin.chen@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index aa6d8606849f..2034a1593db7 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -1152,12 +1152,6 @@ void bcmasp_enable_wol(struct bcmasp_intf *intf, bool en)
 	}
 }
 
-static void bcmasp_wol_irq_destroy(struct bcmasp_priv *priv)
-{
-	if (priv->wol_irq > 0)
-		free_irq(priv->wol_irq, priv);
-}
-
 static void bcmasp_eee_fixup(struct bcmasp_intf *intf, bool en)
 {
 	u32 reg, phy_lpi_overwrite;
@@ -1363,7 +1357,6 @@ static int bcmasp_probe(struct platform_device *pdev)
 	return ret;
 
 err_cleanup:
-	bcmasp_wol_irq_destroy(priv);
 	bcmasp_remove_intfs(priv);
 
 	return ret;
@@ -1376,7 +1369,6 @@ static void bcmasp_remove(struct platform_device *pdev)
 	if (!priv)
 		return;
 
-	bcmasp_wol_irq_destroy(priv);
 	bcmasp_remove_intfs(priv);
 }
 
-- 
cgit v1.2.3


From 27dfe9030acbc601c260b42ecdbb4e5858a97b53 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Thu, 19 Mar 2026 16:48:13 -0700
Subject: net: bcmasp: fix double disable of clk

Switch to devm_clk_get_optional() so we can manage the clock ourselves.
We dynamically control the clocks depending on the state of the interface
for power savings. The default state is clock disabled, so unbinding the
driver causes a double disable.

Fixes: 490cb412007d ("net: bcmasp: Add support for ASP2.0 Ethernet controller")
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260319234813.1937315-3-justin.chen@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 33 ++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 2034a1593db7..972474893a6b 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -1249,7 +1249,7 @@ static int bcmasp_probe(struct platform_device *pdev)
 	if (priv->irq <= 0)
 		return -EINVAL;
 
-	priv->clk = devm_clk_get_optional_enabled(dev, "sw_asp");
+	priv->clk = devm_clk_get_optional(dev, "sw_asp");
 	if (IS_ERR(priv->clk))
 		return dev_err_probe(dev, PTR_ERR(priv->clk),
 				     "failed to request clock\n");
@@ -1277,6 +1277,10 @@ static int bcmasp_probe(struct platform_device *pdev)
 
 	bcmasp_set_pdata(priv, pdata);
 
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to start clock\n");
+
 	/* Enable all clocks to ensure successful probing */
 	bcmasp_core_clock_set(priv, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE, 0);
 
@@ -1288,8 +1292,10 @@ static int bcmasp_probe(struct platform_device *pdev)
 
 	ret = devm_request_irq(&pdev->dev, priv->irq, bcmasp_isr, 0,
 			       pdev->name, priv);
-	if (ret)
-		return dev_err_probe(dev, ret, "failed to request ASP interrupt: %d", ret);
+	if (ret) {
+		dev_err(dev, "Failed to request ASP interrupt: %d", ret);
+		goto err_clock_disable;
+	}
 
 	/* Register mdio child nodes */
 	of_platform_populate(dev->of_node, bcmasp_mdio_of_match, NULL, dev);
@@ -1301,13 +1307,17 @@ static int bcmasp_probe(struct platform_device *pdev)
 
 	priv->mda_filters = devm_kcalloc(dev, priv->num_mda_filters,
 					 sizeof(*priv->mda_filters), GFP_KERNEL);
-	if (!priv->mda_filters)
-		return -ENOMEM;
+	if (!priv->mda_filters) {
+		ret = -ENOMEM;
+		goto err_clock_disable;
+	}
 
 	priv->net_filters = devm_kcalloc(dev, priv->num_net_filters,
 					 sizeof(*priv->net_filters), GFP_KERNEL);
-	if (!priv->net_filters)
-		return -ENOMEM;
+	if (!priv->net_filters) {
+		ret = -ENOMEM;
+		goto err_clock_disable;
+	}
 
 	bcmasp_core_init_filters(priv);
 
@@ -1316,7 +1326,8 @@ static int bcmasp_probe(struct platform_device *pdev)
 	ports_node = of_find_node_by_name(dev->of_node, "ethernet-ports");
 	if (!ports_node) {
 		dev_warn(dev, "No ports found\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_clock_disable;
 	}
 
 	i = 0;
@@ -1338,8 +1349,6 @@ static int bcmasp_probe(struct platform_device *pdev)
 	 */
 	bcmasp_core_clock_set(priv, 0, ASP_CTRL_CLOCK_CTRL_ASP_ALL_DISABLE);
 
-	clk_disable_unprepare(priv->clk);
-
 	/* Now do the registration of the network ports which will take care
 	 * of managing the clock properly.
 	 */
@@ -1352,12 +1361,16 @@ static int bcmasp_probe(struct platform_device *pdev)
 		count++;
 	}
 
+	clk_disable_unprepare(priv->clk);
+
 	dev_info(dev, "Initialized %d port(s)\n", count);
 
 	return ret;
 
 err_cleanup:
 	bcmasp_remove_intfs(priv);
+err_clock_disable:
+	clk_disable_unprepare(priv->clk);
 
 	return ret;
 }
-- 
cgit v1.2.3


From c1f2b0f2b5e37b2c27540a175aea2755a3799433 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawnguo@kernel.org>
Date: Fri, 27 Feb 2026 15:19:58 +0800
Subject: arm64: dts: hisilicon: poplar: Correct PCIe reset GPIO polarity

The PCIe reset GPIO on Poplar is actually active low.  The active high
worked before because kernel driver didn't respect the setting from DT.
This is changed since commit 1d26a55fbeb9 ("PCI: histb: Switch to using
gpiod API"), and thus PCIe on Poplar got brken since then.

Fix the problem by correcting the polarity.

Fixes: 32fa01761bd9 ("arm64: dts: hi3798cv200: enable PCIe support for poplar board")
Cc: stable@vger.kernel.org
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
index 7d370dac4c85..579d55daa7d0 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200-poplar.dts
@@ -179,7 +179,7 @@
 };
 
 &pcie {
-	reset-gpios = <&gpio4 4 GPIO_ACTIVE_HIGH>;
+	reset-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>;
 	vpcie-supply = <&reg_pcie>;
 	status = "okay";
 };
-- 
cgit v1.2.3


From 1af997cad473d505248df6d9577183bb91f69670 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawnguo@kernel.org>
Date: Fri, 27 Feb 2026 15:22:10 +0800
Subject: arm64: dts: hisilicon: hi3798cv200: Add missing dma-ranges

Reboot starts failing on Poplar since commit 8424ecdde7df ("arm64: mm:
Set ZONE_DMA size based on devicetree's dma-ranges"), which effectively
changes zone_dma_bits from 30 to 32 for arm64 platforms that do not
properly define dma-ranges in device tree.  It's unclear how Poplar reboot
gets broken by this change exactly, but a dma-ranges limiting zone_dma to
the first 1 GB fixes the regression.

Fixes: 2f20182ed670 ("arm64: dts: hisilicon: add dts files for hi3798cv200-poplar board")
Cc: stable@vger.kernel.org
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Wei Xu <xuwei5@hisilicon.com>
---
 arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
index f6bc001c3832..2f4ad5da5e33 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3798cv200.dtsi
@@ -122,6 +122,7 @@
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges = <0x0 0x0 0xf0000000 0x10000000>;
+		dma-ranges = <0x0 0x0 0x0 0x40000000>;
 
 		crg: clock-reset-controller@8a22000 {
 			compatible = "hisilicon,hi3798cv200-crg", "syscon", "simple-mfd";
-- 
cgit v1.2.3


From c3fd16c3b98ed726294feab2f94f876290bf7b61 Mon Sep 17 00:00:00 2001
From: Zubin Mithra <zsm@google.com>
Date: Wed, 18 Mar 2026 13:40:13 +0000
Subject: virt: tdx-guest: Fix handling of host controlled 'quote' buffer
 length

Validate host controlled value `quote_buf->out_len` that determines how
many bytes of the quote are copied out to guest userspace. In TDX
environments with remote attestation, quotes are not considered private,
and can be forwarded to an attestation server.

Catch scenarios where the host specifies a response length larger than
the guest's allocation, or otherwise races modifying the response while
the guest consumes it.

This prevents contents beyond the pages allocated for `quote_buf`
(up to TSM_REPORT_OUTBLOB_MAX) from being read out to guest userspace,
and possibly forwarded in attestation requests.

Recall that some deployments want per-container configs-tsm-report
interfaces, so the leak may cross container protection boundaries, not
just local root.

Fixes: f4738f56d1dc ("virt: tdx-guest: Add Quote generation support using TSM_REPORTS")
Cc: stable@vger.kernel.org
Signed-off-by: Zubin Mithra <zsm@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/virt/coco/tdx-guest/tdx-guest.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c
index 4252b147593a..7cee97559ba2 100644
--- a/drivers/virt/coco/tdx-guest/tdx-guest.c
+++ b/drivers/virt/coco/tdx-guest/tdx-guest.c
@@ -171,6 +171,8 @@ static void tdx_mr_deinit(const struct attribute_group *mr_grp)
 #define GET_QUOTE_SUCCESS		0
 #define GET_QUOTE_IN_FLIGHT		0xffffffffffffffff
 
+#define TDX_QUOTE_MAX_LEN		(GET_QUOTE_BUF_SIZE - sizeof(struct tdx_quote_buf))
+
 /* struct tdx_quote_buf: Format of Quote request buffer.
  * @version: Quote format version, filled by TD.
  * @status: Status code of Quote request, filled by VMM.
@@ -269,6 +271,7 @@ static int tdx_report_new_locked(struct tsm_report *report, void *data)
 	u8 *buf;
 	struct tdx_quote_buf *quote_buf = quote_data;
 	struct tsm_report_desc *desc = &report->desc;
+	u32 out_len;
 	int ret;
 	u64 err;
 
@@ -306,12 +309,17 @@ static int tdx_report_new_locked(struct tsm_report *report, void *data)
 		return ret;
 	}
 
-	buf = kvmemdup(quote_buf->data, quote_buf->out_len, GFP_KERNEL);
+	out_len = READ_ONCE(quote_buf->out_len);
+
+	if (out_len > TDX_QUOTE_MAX_LEN)
+		return -EFBIG;
+
+	buf = kvmemdup(quote_buf->data, out_len, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	report->outblob = buf;
-	report->outblob_len = quote_buf->out_len;
+	report->outblob_len = out_len;
 
 	/*
 	 * TODO: parse the PEM-formatted cert chain out of the quote buffer when
-- 
cgit v1.2.3


From 6c2128505f61b504c79a20b89596feba61388112 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Thu, 19 Mar 2026 17:08:08 -0700
Subject: bpf: Fix exception exit lock checking for subprogs

process_bpf_exit_full() passes check_lock = !curframe to
check_resource_leak(), which is false in cases when bpf_throw() is
called from a static subprog. This makes check_resource_leak() to skip
validation of active_rcu_locks, active_preempt_locks, and
active_irq_id on exception exits from subprogs.

At runtime bpf_throw() unwinds the stack via ORC without releasing any
user-acquired locks, which may cause various issues as the result.

Fix by setting check_lock = true for exception exits regardless of
curframe, since exceptions bypass all intermediate frame
cleanup. Update the error message prefix to "bpf_throw" for exception
exits to distinguish them from normal BPF_EXIT.

Fix reject_subprog_with_rcu_read_lock test which was previously
passing for the wrong reason. Test program returned directly from the
subprog call without closing the RCU section, so the error was
triggered by the unclosed RCU lock on normal exit, not by
bpf_throw. Update __msg annotations for affected tests to match the
new "bpf_throw" error prefix.

The spin_lock case is not affected because they are already checked [1]
at the call site in do_check_insn() before bpf_throw can run.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/kernel/bpf/verifier.c?h=v7.0-rc4#n21098

Assisted-by: Claude:claude-opus-4-6
Fixes: f18b03fabaa9 ("bpf: Implement BPF exceptions")
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260320000809.643798-1-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                               | 3 ++-
 tools/testing/selftests/bpf/progs/exceptions_fail.c | 9 ++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index df22bfc572e2..5c0e6809024f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20911,7 +20911,8 @@ static int process_bpf_exit_full(struct bpf_verifier_env *env,
 	 * state when it exits.
 	 */
 	int err = check_resource_leak(env, exception_exit,
-				      !env->cur_state->curframe,
+				      exception_exit || !env->cur_state->curframe,
+				      exception_exit ? "bpf_throw" :
 				      "BPF_EXIT instruction in main prog");
 	if (err)
 		return err;
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index 8a0fdff89927..d7f1c492e3dd 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -8,6 +8,7 @@
 #include "bpf_experimental.h"
 
 extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
 
 #define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
 
@@ -131,7 +132,7 @@ int reject_subprog_with_lock(void *ctx)
 }
 
 SEC("?tc")
-__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region")
+__failure __msg("bpf_throw cannot be used inside bpf_rcu_read_lock-ed region")
 int reject_with_rcu_read_lock(void *ctx)
 {
 	bpf_rcu_read_lock();
@@ -147,11 +148,13 @@ __noinline static int throwing_subprog(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region")
+__failure __msg("bpf_throw cannot be used inside bpf_rcu_read_lock-ed region")
 int reject_subprog_with_rcu_read_lock(void *ctx)
 {
 	bpf_rcu_read_lock();
-	return throwing_subprog(ctx);
+	throwing_subprog(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
 }
 
 static bool rbless(struct bpf_rb_node *n1, const struct bpf_rb_node *n2)
-- 
cgit v1.2.3


From a1e5c46eaed3151be93e1aec9af0d8f8db79b8f6 Mon Sep 17 00:00:00 2001
From: Ihor Solodrai <ihor.solodrai@linux.dev>
Date: Thu, 19 Mar 2026 17:08:09 -0700
Subject: selftests/bpf: Add tests for bpf_throw lock leak from subprogs

Add test cases to ensure the verifier correctly rejects bpf_throw from
subprogs when RCU, preempt, or IRQ locks are held:

  * reject_subprog_rcu_lock_throw: subprog acquires bpf_rcu_read_lock and
    then calls bpf_throw
  * reject_subprog_throw_preempt_lock: always-throwing subprog called while
    caller holds bpf_preempt_disable
  * reject_subprog_throw_irq_lock: always-throwing subprog called while
    caller holds bpf_local_irq_save

Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260320000809.643798-2-ihor.solodrai@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/progs/exceptions_fail.c  | 47 ++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
index d7f1c492e3dd..9ea1353488d7 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_fail.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -9,6 +9,10 @@
 
 extern void bpf_rcu_read_lock(void) __ksym;
 extern void bpf_rcu_read_unlock(void) __ksym;
+extern void bpf_preempt_disable(void) __ksym;
+extern void bpf_preempt_enable(void) __ksym;
+extern void bpf_local_irq_save(unsigned long *) __ksym;
+extern void bpf_local_irq_restore(unsigned long *) __ksym;
 
 #define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
 
@@ -349,4 +353,47 @@ int reject_exception_throw_cb_diff(struct __sk_buff *ctx)
 	return 0;
 }
 
+__noinline static int always_throws(void)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int rcu_lock_then_throw(void)
+{
+	bpf_rcu_read_lock();
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_throw cannot be used inside bpf_rcu_read_lock-ed region")
+int reject_subprog_rcu_lock_throw(void *ctx)
+{
+	rcu_lock_then_throw();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_throw cannot be used inside bpf_preempt_disable-ed region")
+int reject_subprog_throw_preempt_lock(void *ctx)
+{
+	bpf_preempt_disable();
+	always_throws();
+	bpf_preempt_enable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_throw cannot be used inside bpf_local_irq_save-ed region")
+int reject_subprog_throw_irq_lock(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	always_throws();
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From c77b30bd1dcb61f66c640ff7d2757816210c7cb0 Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Wed, 11 Mar 2026 01:11:15 +0000
Subject: bpf: Fix undefined behavior in interpreter sdiv/smod for INT_MIN

The BPF interpreter's signed 32-bit division and modulo handlers use
the kernel abs() macro on s32 operands. The abs() macro documentation
(include/linux/math.h) explicitly states the result is undefined when
the input is the type minimum. When DST contains S32_MIN (0x80000000),
abs((s32)DST) triggers undefined behavior and returns S32_MIN unchanged
on arm64/x86. This value is then sign-extended to u64 as
0xFFFFFFFF80000000, causing do_div() to compute the wrong result.

The verifier's abstract interpretation (scalar32_min_max_sdiv) computes
the mathematically correct result for range tracking, creating a
verifier/interpreter mismatch that can be exploited for out-of-bounds
map value access.

Introduce abs_s32() which handles S32_MIN correctly by casting to u32
before negating, avoiding signed overflow entirely. Replace all 8
abs((s32)...) call sites in the interpreter's sdiv32/smod32 handlers.

s32 is the only affected case -- the s64 division/modulo handlers do
not use abs().

Fixes: ec0e2da95f72 ("bpf: Support new signed div/mod instructions.")
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Mykyta Yatsenko <yatsenko@meta.com>
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Link: https://lore.kernel.org/r/20260311011116.2108005-2-qguanni@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9e126be33755..7b675a451ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1757,6 +1757,12 @@ bool bpf_opcode_in_insntable(u8 code)
 }
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+/* Absolute value of s32 without undefined behavior for S32_MIN */
+static u32 abs_s32(s32 x)
+{
+	return x >= 0 ? (u32)x : -(u32)x;
+}
+
 /**
  *	___bpf_prog_run - run eBPF program on a given context
  *	@regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1921,8 +1927,8 @@ select_insn:
 			DST = do_div(AX, (u32) SRC);
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			AX = do_div(AX, abs((s32)SRC));
+			AX = abs_s32((s32)DST);
+			AX = do_div(AX, abs_s32((s32)SRC));
 			if ((s32)DST < 0)
 				DST = (u32)-AX;
 			else
@@ -1949,8 +1955,8 @@ select_insn:
 			DST = do_div(AX, (u32) IMM);
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			AX = do_div(AX, abs((s32)IMM));
+			AX = abs_s32((s32)DST);
+			AX = do_div(AX, abs_s32((s32)IMM));
 			if ((s32)DST < 0)
 				DST = (u32)-AX;
 			else
@@ -1976,8 +1982,8 @@ select_insn:
 			DST = (u32) AX;
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			do_div(AX, abs((s32)SRC));
+			AX = abs_s32((s32)DST);
+			do_div(AX, abs_s32((s32)SRC));
 			if (((s32)DST < 0) == ((s32)SRC < 0))
 				DST = (u32)AX;
 			else
@@ -2003,8 +2009,8 @@ select_insn:
 			DST = (u32) AX;
 			break;
 		case 1:
-			AX = abs((s32)DST);
-			do_div(AX, abs((s32)IMM));
+			AX = abs_s32((s32)DST);
+			do_div(AX, abs_s32((s32)IMM));
 			if (((s32)DST < 0) == ((s32)IMM < 0))
 				DST = (u32)AX;
 			else
-- 
cgit v1.2.3


From 4ac95c65efeaf0c010199b2b2f5f78b06f28dab6 Mon Sep 17 00:00:00 2001
From: Jenny Guanni Qu <qguanni@gmail.com>
Date: Wed, 11 Mar 2026 01:11:16 +0000
Subject: selftests/bpf: Add tests for sdiv32/smod32 with INT_MIN dividend

Add tests to verify that signed 32-bit division and modulo operations
produce correct results when the dividend is INT_MIN (0x80000000).

The bug fixed in the previous commit only affects the BPF interpreter
path. When JIT is enabled (the default on most architectures), the
native CPU division instruction produces the correct result and these
tests pass regardless. With bpf_jit_enable=0, the interpreter is used
and without the previous fix, INT_MIN / 2 incorrectly returns
0x40000000 instead of 0xC0000000 due to abs(S32_MIN) undefined
behavior, causing these tests to fail.

Test cases:
  - SDIV32 INT_MIN / 2 = -1073741824 (imm and reg divisor)
  - SMOD32 INT_MIN % 2 = 0 (positive and negative divisor)

Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Jenny Guanni Qu <qguanni@gmail.com>
Link: https://lore.kernel.org/r/20260311011116.2108005-3-qguanni@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/verifier_sdiv.c | 58 +++++++++++++++++++++++
 1 file changed, 58 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index 148d2299e5b4..fd59d57e8e37 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -1209,6 +1209,64 @@ __naked void smod32_ri_divisor_neg_1(void)
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("SDIV32, INT_MIN divided by 2, imm")
+__success __success_unpriv __retval(-1073741824)
+__naked void sdiv32_int_min_div_2_imm(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w0 s/= 2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, INT_MIN divided by 2, reg")
+__success __success_unpriv __retval(-1073741824)
+__naked void sdiv32_int_min_div_2_reg(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, INT_MIN modulo 2, imm")
+__success __success_unpriv __retval(0)
+__naked void smod32_int_min_mod_2_imm(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w0 s%%= 2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, INT_MIN modulo -2, imm")
+__success __success_unpriv __retval(0)
+__naked void smod32_int_min_mod_neg2_imm(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w0 s%%= -2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+
 #else
 
 SEC("socket")
-- 
cgit v1.2.3


From c845894ebd6fb43226b3118d6b017942550910c5 Mon Sep 17 00:00:00 2001
From: Daniel Wade <danjwade95@gmail.com>
Date: Sat, 14 Mar 2026 13:15:20 +1100
Subject: bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR

maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the
source operand is a constant.  When dst has signed range [-1, 0], it
forks the verifier state: the pushed path gets dst = 0, the current
path gets dst = -1.

For BPF_AND this is correct: 0 & K == 0.
For BPF_OR this is wrong:    0 | K == K, not 0.

The pushed path therefore tracks dst as 0 when the runtime value is K,
producing an exploitable verifier/runtime divergence that allows
out-of-bounds map access.

Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to
push_stack(), so the pushed path re-executes the ALU instruction with
dst = 0 and naturally computes the correct result for any opcode.

Fixes: bffacdb80b93 ("bpf: Recognize special arithmetic shift in the verifier")
Signed-off-by: Daniel Wade <danjwade95@gmail.com>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260314021521.128361-2-danjwade95@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5c0e6809024f..62377bcb66fd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -15999,7 +15999,7 @@ static int maybe_fork_scalars(struct bpf_verifier_env *env, struct bpf_insn *ins
 	else
 		return 0;
 
-	branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+	branch = push_stack(env, env->insn_idx, env->insn_idx, false);
 	if (IS_ERR(branch))
 		return PTR_ERR(branch);
 
-- 
cgit v1.2.3


From 0ad1734cc5598d3ddb6126a8960efe85f0f807d7 Mon Sep 17 00:00:00 2001
From: Daniel Wade <danjwade95@gmail.com>
Date: Sat, 14 Mar 2026 13:15:21 +1100
Subject: selftests/bpf: Add tests for maybe_fork_scalars() OR vs AND handling

Add three test cases to verifier_bounds.c to verify that
maybe_fork_scalars() correctly tracks register values for BPF_OR
operations with constant source operands:

1. or_scalar_fork_rejects_oob: After ARSH 63 + OR 8, the pushed
   path should have dst = 8. With value_size = 8, accessing
   map_value + 8 is out of bounds and must be rejected.

2. and_scalar_fork_still_works: Regression test ensuring AND
   forking continues to work. ARSH 63 + AND 4 produces pushed
   dst = 0 and current dst = 4, both within value_size = 8.

3. or_scalar_fork_allows_inbounds: After ARSH 63 + OR 4, the
   pushed path has dst = 4, which is within value_size = 8
   and should be accepted.

These tests exercise the fix in the previous patch, which makes the
pushed path re-execute the ALU instruction so it computes the correct
result for BPF_OR.

Signed-off-by: Daniel Wade <danjwade95@gmail.com>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260314021521.128361-3-danjwade95@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../testing/selftests/bpf/progs/verifier_bounds.c  | 94 ++++++++++++++++++++++
 1 file changed, 94 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index e526315c718a..79a328276805 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -2037,4 +2037,98 @@ __naked void signed_unsigned_intersection32_case2(void *ctx)
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("maybe_fork_scalars: OR with constant rejects OOB")
+__failure __msg("invalid access to map value")
+__naked void or_scalar_fork_rejects_oob(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r9 = r0;					\
+	r6 = *(u64*)(r9 + 0);				\
+	r6 s>>= 63;					\
+	r6 |= 8;					\
+	/* r6 is -1 (current) or 8 (pushed) */		\
+	if r6 s< 0 goto l0_%=;				\
+	/* pushed path: r6 = 8, OOB for value_size=8 */	\
+	r9 += r6;					\
+	r0 = *(u8*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("maybe_fork_scalars: AND with constant still works")
+__success __retval(0)
+__naked void and_scalar_fork_still_works(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r9 = r0;					\
+	r6 = *(u64*)(r9 + 0);				\
+	r6 s>>= 63;					\
+	r6 &= 4;					\
+	/*						\
+	 * r6 is 0 (pushed, 0&4==0) or 4 (current)	\
+	 * both within value_size=8			\
+	 */						\
+	if r6 s< 0 goto l0_%=;				\
+	r9 += r6;					\
+	r0 = *(u8*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("maybe_fork_scalars: OR with constant allows in-bounds")
+__success __retval(0)
+__naked void or_scalar_fork_allows_inbounds(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r9 = r0;					\
+	r6 = *(u64*)(r9 + 0);				\
+	r6 s>>= 63;					\
+	r6 |= 4;					\
+	/*						\
+	 * r6 is -1 (current) or 4 (pushed)		\
+	 * pushed path: r6 = 4, within value_size=8	\
+	 */						\
+	if r6 s< 0 goto l0_%=;				\
+	r9 += r6;					\
+	r0 = *(u8*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From bc308be380c136800e1e94c6ce49cb53141d6506 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 19 Mar 2026 22:15:06 +0100
Subject: bpf: Fix sync_linked_regs regarding BPF_ADD_CONST32 zext propagation

Jenny reported that in sync_linked_regs() the BPF_ADD_CONST32 flag is
checked on known_reg (the register narrowed by a conditional branch)
instead of reg (the linked target register created by an alu32 operation).

Example case with reg:

  1. r6 = bpf_get_prandom_u32()
  2. r7 = r6 (linked, same id)
  3. w7 += 5 (alu32 -- r7 gets BPF_ADD_CONST32, zero-extended by CPU)
  4. if w6 < 0xFFFFFFFC goto safe (narrows r6 to [0xFFFFFFFC, 0xFFFFFFFF])
  5. sync_linked_regs() propagates to r7 but does NOT call zext_32_to_64()
  6. Verifier thinks r7 is [0x100000001, 0x100000004] instead of [1, 4]

Since known_reg above does not have BPF_ADD_CONST32 set above, zext_32_to_64()
is never called on alu32-derived linked registers. This causes the verifier
to track incorrect 64-bit bounds, while the CPU correctly zero-extends the
32-bit result.

The code checking known_reg->id was correct however (see scalars_alu32_wrap
selftest case), but the real fix needs to handle both directions - zext
propagation should be done when either register has BPF_ADD_CONST32, since
the linked relationship involves a 32-bit operation regardless of which
side has the flag.

Example case with known_reg (exercised also by scalars_alu32_wrap):

  1. r1 = r0; w1 += 0x100 (alu32 -- r1 gets BPF_ADD_CONST32)
  2. if r1 > 0x80 - known_reg = r1 (has BPF_ADD_CONST32), reg = r0 (doesn't)

Hence, fix it by checking for (reg->id | known_reg->id) & BPF_ADD_CONST32.

Moreover, sync_linked_regs() also has a soundness issue when two linked
registers used different ALU widths: one with BPF_ADD_CONST32 and the
other with BPF_ADD_CONST64. The delta relationship between linked registers
assumes the same arithmetic width though. When one register went through
alu32 (CPU zero-extends the 32-bit result) and the other went through
alu64 (no zero-extension), the propagation produces incorrect bounds.

Example:

  r6 = bpf_get_prandom_u32()     // fully unknown
  if r6 >= 0x100000000 goto out  // constrain r6 to [0, U32_MAX]
  r7 = r6
  w7 += 1                        // alu32: r7.id = N | BPF_ADD_CONST32
  r8 = r6
  r8 += 2                        // alu64: r8.id = N | BPF_ADD_CONST64
  if r7 < 0xFFFFFFFF goto out    // narrows r7 to [0xFFFFFFFF, 0xFFFFFFFF]

At the branch on r7, sync_linked_regs() runs with known_reg=r7
(BPF_ADD_CONST32) and reg=r8 (BPF_ADD_CONST64). The delta path
computes:

  r8 = r7 + (delta_r8 - delta_r7) = 0xFFFFFFFF + (2 - 1) = 0x100000000

Then, because known_reg->id has BPF_ADD_CONST32, zext_32_to_64(r8) is
called, truncating r8 to [0, 0]. But r8 used a 64-bit ALU op -- the
CPU does NOT zero-extend it. The actual CPU value of r8 is
0xFFFFFFFE + 2 = 0x100000000, not 0. The verifier now underestimates
r8's 64-bit bounds, which is a soundness violation.

Fix sync_linked_regs() by skipping propagation when the two registers
have mixed ALU widths (one BPF_ADD_CONST32, the other BPF_ADD_CONST64).

Lastly, fix regsafe() used for path pruning: the existing checks used
"& BPF_ADD_CONST" to test for offset linkage, which treated
BPF_ADD_CONST32 and BPF_ADD_CONST64 as equivalent.

Fixes: 7a433e519364 ("bpf: Support negative offsets, BPF_SUB, and alu32 for linked register tracking")
Reported-by: Jenny Guanni Qu <qguanni@gmail.com>
Co-developed-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260319211507.213816-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 62377bcb66fd..f108c01ff6d0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17415,6 +17415,12 @@ static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_s
 			continue;
 		if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST))
 			continue;
+		/*
+		 * Skip mixed 32/64-bit links: the delta relationship doesn't
+		 * hold across different ALU widths.
+		 */
+		if (((reg->id ^ known_reg->id) & BPF_ADD_CONST) == BPF_ADD_CONST)
+			continue;
 		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
 		    reg->off == known_reg->off) {
 			s32 saved_subreg_def = reg->subreg_def;
@@ -17442,7 +17448,7 @@ static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_s
 			scalar32_min_max_add(reg, &fake_reg);
 			scalar_min_max_add(reg, &fake_reg);
 			reg->var_off = tnum_add(reg->var_off, fake_reg.var_off);
-			if (known_reg->id & BPF_ADD_CONST32)
+			if ((reg->id | known_reg->id) & BPF_ADD_CONST32)
 				zext_32_to_64(reg);
 			reg_bounds_sync(reg);
 		}
@@ -19870,11 +19876,14 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		 * Also verify that new value satisfies old value range knowledge.
 		 */
 
-		/* ADD_CONST mismatch: different linking semantics */
-		if ((rold->id & BPF_ADD_CONST) && !(rcur->id & BPF_ADD_CONST))
-			return false;
-
-		if (rold->id && !(rold->id & BPF_ADD_CONST) && (rcur->id & BPF_ADD_CONST))
+		/*
+		 * ADD_CONST flags must match exactly: BPF_ADD_CONST32 and
+		 * BPF_ADD_CONST64 have different linking semantics in
+		 * sync_linked_regs() (alu32 zero-extends, alu64 does not),
+		 * so pruning across different flag types is unsafe.
+		 */
+		if (rold->id &&
+		    (rold->id & BPF_ADD_CONST) != (rcur->id & BPF_ADD_CONST))
 			return false;
 
 		/* Both have offset linkage: offsets must match */
-- 
cgit v1.2.3


From 4a04d13576fd69149b91672b5f1dc62eca272fa5 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 19 Mar 2026 22:15:07 +0100
Subject: selftests/bpf: Add a test cases for sync_linked_regs regarding zext
 propagation

Add multiple test cases for linked register tracking with alu32 ops:

  - Add a test that checks sync_linked_regs() regarding reg->id (the linked
    target register) for BPF_ADD_CONST32 rather than known_reg->id (the
    branch register).

  - Add a test case for linked register tracking that exposes the cross-type
    sync_linked_regs() bug. One register uses alu32 (w7 += 1, BPF_ADD_CONST32)
    and another uses alu64 (r8 += 2, BPF_ADD_CONST64), both linked to the
    same base register.

  - Add a test case that exercises regsafe() path pruning when two execution
    paths reach the same program point with linked registers carrying
    different ADD_CONST flags (BPF_ADD_CONST32 from alu32 vs BPF_ADD_CONST64
    from alu64). This particular test passes with and without the fix since
    the pruning will fail due to different ranges, but it would still be
    useful to carry this one as a regression test for the unreachable div
    by zero.

With the fix applied all the tests pass:

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t verifier_linked_scalars
  [...]
  ./test_progs -t verifier_linked_scalars
  #602/1   verifier_linked_scalars/scalars: find linked scalars:OK
  #602/2   verifier_linked_scalars/sync_linked_regs_preserves_id:OK
  #602/3   verifier_linked_scalars/scalars_neg:OK
  #602/4   verifier_linked_scalars/scalars_neg_sub:OK
  #602/5   verifier_linked_scalars/scalars_neg_alu32_add:OK
  #602/6   verifier_linked_scalars/scalars_neg_alu32_sub:OK
  #602/7   verifier_linked_scalars/scalars_pos:OK
  #602/8   verifier_linked_scalars/scalars_sub_neg_imm:OK
  #602/9   verifier_linked_scalars/scalars_double_add:OK
  #602/10  verifier_linked_scalars/scalars_sync_delta_overflow:OK
  #602/11  verifier_linked_scalars/scalars_sync_delta_overflow_large_range:OK
  #602/12  verifier_linked_scalars/scalars_alu32_big_offset:OK
  #602/13  verifier_linked_scalars/scalars_alu32_basic:OK
  #602/14  verifier_linked_scalars/scalars_alu32_wrap:OK
  #602/15  verifier_linked_scalars/scalars_alu32_zext_linked_reg:OK
  #602/16  verifier_linked_scalars/scalars_alu32_alu64_cross_type:OK
  #602/17  verifier_linked_scalars/scalars_alu32_alu64_regsafe_pruning:OK
  #602/18  verifier_linked_scalars/alu32_negative_offset:OK
  #602/19  verifier_linked_scalars/spurious_precision_marks:OK
  #602     verifier_linked_scalars:OK
  Summary: 1/19 PASSED, 0 SKIPPED, 0 FAILED

Co-developed-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260319211507.213816-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/verifier_linked_scalars.c  | 108 +++++++++++++++++++++
 1 file changed, 108 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
index 7bf7dbfd237d..f4f8a055af8a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
@@ -348,6 +348,114 @@ l0_%=:							\
 	: __clobber_all);
 }
 
+/*
+ * Test that sync_linked_regs() checks reg->id (the linked target register)
+ * for BPF_ADD_CONST32 rather than known_reg->id (the branch register).
+ */
+SEC("socket")
+__success
+__naked void scalars_alu32_zext_linked_reg(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	w7 += 1;		/* alu32: r7.id |= BPF_ADD_CONST32 */ \
+	r8 = 0xFFFFffff ll;					\
+	if r6 < r8 goto l0_%=;					\
+	/* r6 in [0xFFFFFFFF, 0xFFFFFFFF] */			\
+	/* sync_linked_regs: known_reg=r6, reg=r7 */		\
+	/* CPU: w7 = (u32)(0xFFFFFFFF + 1) = 0, zext -> r7 = 0 */ \
+	/* With fix: r7 64-bit = [0, 0] (zext applied) */	\
+	/* Without fix: r7 64-bit = [0x100000000] (no zext) */	\
+	r7 >>= 32;						\
+	if r7 == 0 goto l0_%=;					\
+	r0 /= 0;		/* unreachable with fix */	\
+l0_%=:								\
+	r0 = 0;							\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that sync_linked_regs() skips propagation when one register used
+ * alu32 (BPF_ADD_CONST32) and the other used alu64 (BPF_ADD_CONST64).
+ * The delta relationship doesn't hold across different ALU widths.
+ */
+SEC("socket")
+__failure __msg("div by zero")
+__naked void scalars_alu32_alu64_cross_type(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	w7 += 1;		/* alu32: BPF_ADD_CONST32, delta = 1 */ \
+	r8 = r6;		/* linked: same id as r6 */	\
+	r8 += 2;		/* alu64: BPF_ADD_CONST64, delta = 2 */ \
+	r9 = 0xFFFFffff ll;					\
+	if r7 < r9 goto l0_%=;					\
+	/* r7 = 0xFFFFFFFF */					\
+	/* sync: known_reg=r7 (ADD_CONST32), reg=r8 (ADD_CONST64) */ \
+	/* Without fix: r8 = zext(0xFFFFFFFF + 1) = 0 */	\
+	/* With fix: r8 stays [2, 0x100000001] (r8 >= 2) */	\
+	if r8 > 0 goto l1_%=;					\
+	goto l0_%=;						\
+l1_%=:								\
+	r0 /= 0;		/* div by zero */		\
+l0_%=:								\
+	r0 = 0;						\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Test that regsafe() prevents pruning when two paths reach the same program
+ * point with linked registers carrying different ADD_CONST flags (one
+ * BPF_ADD_CONST32 from alu32, another BPF_ADD_CONST64 from alu64).
+ */
+SEC("socket")
+__failure __msg("div by zero")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void scalars_alu32_alu64_regsafe_pruning(void)
+{
+	asm volatile ("						\
+	call %[bpf_get_prandom_u32];				\
+	w6 = w0;		/* r6 in [0, 0xFFFFFFFF] */	\
+	r7 = r6;		/* linked: same id as r6 */	\
+	/* Get another random value for the path branch */	\
+	call %[bpf_get_prandom_u32];				\
+	if r0 > 0 goto l_pathb_%=;				\
+	/* Path A: alu32 */					\
+	w7 += 1;		/* BPF_ADD_CONST32, delta = 1 */\
+	goto l_merge_%=;					\
+l_pathb_%=:							\
+	/* Path B: alu64 */					\
+	r7 += 1;		/* BPF_ADD_CONST64, delta = 1 */\
+l_merge_%=:							\
+	/* Merge point: regsafe() compares path B against cached path A. */ \
+	/* Narrow r6 to trigger sync_linked_regs for r7 */	\
+	r9 = 0xFFFFffff ll;					\
+	if r6 < r9 goto l0_%=;					\
+	/* r6 = 0xFFFFFFFF */					\
+	/* sync: r7 = 0xFFFFFFFF + 1 = 0x100000000 */		\
+	/* Path A: zext -> r7 = 0 */				\
+	/* Path B: no zext -> r7 = 0x100000000 */		\
+	r7 >>= 32;						\
+	if r7 == 0 goto l0_%=;					\
+	r0 /= 0;		/* div by zero on path B */	\
+l0_%=:								\
+	r0 = 0;						\
+	exit;							\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
 SEC("socket")
 __success
 void alu32_negative_offset(void)
-- 
cgit v1.2.3


From a6f22e50c7d51aa225c392c62c33f0fae11f734d Mon Sep 17 00:00:00 2001
From: Xuewen Yan <xuewen.yan@unisoc.com>
Date: Fri, 6 Mar 2026 15:59:54 +0800
Subject: tracing: Revert "tracing: Remove pid in task_rename tracing output"

This reverts commit e3f6a42272e028c46695acc83fc7d7c42f2750ad.

The commit says that the tracepoint only deals with the current task,
however the following case is not current task:

comm_write() {
    p = get_proc_task(inode);
    if (!p)
        return -ESRCH;

    if (same_thread_group(current, p))
        set_task_comm(p, buffer);
}
where set_task_comm() calls __set_task_comm() which records
the update of p and not current.

So revert the patch to show pid.

Cc: <mhiramat@kernel.org>
Cc: <mathieu.desnoyers@efficios.com>
Cc: <elver@google.com>
Cc: <kees@kernel.org>
Link: https://patch.msgid.link/20260306075954.4533-1-xuewen.yan@unisoc.com
Fixes: e3f6a42272e0 ("tracing: Remove pid in task_rename tracing output")
Reported-by: Guohua Yan <guohua.yan@unisoc.com>
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/trace/events/task.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/task.h b/include/trace/events/task.h
index 4f0759634306..b9a129eb54d9 100644
--- a/include/trace/events/task.h
+++ b/include/trace/events/task.h
@@ -38,19 +38,22 @@ TRACE_EVENT(task_rename,
 	TP_ARGS(task, comm),
 
 	TP_STRUCT__entry(
+		__field(	pid_t,	pid)
 		__array(	char, oldcomm,  TASK_COMM_LEN)
 		__array(	char, newcomm,  TASK_COMM_LEN)
 		__field(	short,	oom_score_adj)
 	),
 
 	TP_fast_assign(
+		__entry->pid = task->pid;
 		memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN);
 		strscpy(entry->newcomm, comm, TASK_COMM_LEN);
 		__entry->oom_score_adj = task->signal->oom_score_adj;
 	),
 
-	TP_printk("oldcomm=%s newcomm=%s oom_score_adj=%hd",
-		  __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj)
+	TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd",
+		__entry->pid, __entry->oldcomm,
+		__entry->newcomm, __entry->oom_score_adj)
 );
 
 /**
-- 
cgit v1.2.3


From 24869650dff34a6fc8fd1cc91b2058a72f9abc95 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 14 Mar 2026 18:13:31 -0500
Subject: iio: adc: ti-adc161s626: fix buffer read on big-endian

Rework ti_adc_trigger_handler() to properly handle data on big-endian
architectures. The scan data format is 16-bit CPU-endian, so we can't
cast it to a int * on big-endian and expect it to work. Instead, we
introduce a local int variable to read the data into, and then copy it
to the buffer.

Since the buffer isn't passed to any SPI functions, we don't need it to
be DMA-safe. So we can drop it from the driver data struct and just
use stack memory for the scan data.

Since there is only one data value (plus timestamp), we don't need an
array and can just declare a struct with the correct data type instead.

Also fix alignment of iio_get_time_ns() to ( while we are touching this.

Fixes: 4d671b71beef ("iio: adc: ti-adc161s626: add support for TI 1-channel differential ADCs")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-adc161s626.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/iio/adc/ti-adc161s626.c b/drivers/iio/adc/ti-adc161s626.c
index 28aa6b80160c..42968d96572b 100644
--- a/drivers/iio/adc/ti-adc161s626.c
+++ b/drivers/iio/adc/ti-adc161s626.c
@@ -70,8 +70,6 @@ struct ti_adc_data {
 
 	u8 read_size;
 	u8 shift;
-
-	u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
 };
 
 static int ti_adc_read_measurement(struct ti_adc_data *data,
@@ -114,15 +112,20 @@ static irqreturn_t ti_adc_trigger_handler(int irq, void *private)
 	struct iio_poll_func *pf = private;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ti_adc_data *data = iio_priv(indio_dev);
-	int ret;
+	struct {
+		s16 data;
+		aligned_s64 timestamp;
+	} scan = { };
+	int ret, val;
+
+	ret = ti_adc_read_measurement(data, &indio_dev->channels[0], &val);
+	if (ret)
+		goto exit_notify_done;
 
-	ret = ti_adc_read_measurement(data, &indio_dev->channels[0],
-				     (int *) &data->buffer);
-	if (!ret)
-		iio_push_to_buffers_with_timestamp(indio_dev,
-					data->buffer,
-					iio_get_time_ns(indio_dev));
+	scan.data = val;
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan, iio_get_time_ns(indio_dev));
 
+ exit_notify_done:
 	iio_trigger_notify_done(indio_dev->trig);
 
 	return IRQ_HANDLED;
-- 
cgit v1.2.3


From edca33a56297d5741ccf867669debec116681987 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 16 Mar 2026 13:07:34 -0400
Subject: tracing: Fix failure to read user space from system call trace events

The system call trace events call trace_user_fault_read() to read the user
space part of some system calls. This is done by grabbing a per-cpu
buffer, disabling migration, enabling preemption, calling
copy_from_user(), disabling preemption, enabling migration and checking if
the task was preempted while preemption was enabled. If it was, the buffer
is considered corrupted and it tries again.

There's a safety mechanism that will fail out of this loop if it fails 100
times (with a warning). That warning message was triggered in some
pi_futex stress tests. Enabling the sched_switch trace event and
traceoff_on_warning, showed the problem:

 pi_mutex_hammer-1375    [006] d..21   138.981648: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981651: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981656: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981659: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981664: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981667: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981671: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981675: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981679: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981682: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981687: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981690: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981695: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981698: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981703: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981706: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981711: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981714: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981719: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981722: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981727: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981730: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95
 pi_mutex_hammer-1375    [006] d..21   138.981735: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0
     migration/6-47      [006] d..2.   138.981738: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95

What happened was the task 1375 was flagged to be migrated. When
preemption was enabled, the migration thread woke up to migrate that task,
but failed because migration for that task was disabled. This caused the
loop to fail to exit because the task scheduled out while trying to read
user space.

Every time the task enabled preemption the migration thread would schedule
in, try to migrate the task, fail and let the task continue. But because
the loop would only enable preemption with migration disabled, it would
always fail because each time it enabled preemption to read user space,
the migration thread would try to migrate it.

To solve this, when the loop fails to read user space without being
scheduled out, enabled and disable preemption with migration enabled. This
will allow the migration task to successfully migrate the task and the
next loop should succeed to read user space without being scheduled out.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260316130734.1858a998@gandalf.local.home
Fixes: 64cf7d058a005 ("tracing: Have trace_marker use per-cpu data to read user space")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ebd996f8710e..bb4a62f4b953 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6783,6 +6783,23 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo,
 	 */
 
 	do {
+		/*
+		 * It is possible that something is trying to migrate this
+		 * task. What happens then, is when preemption is enabled,
+		 * the migration thread will preempt this task, try to
+		 * migrate it, fail, then let it run again. That will
+		 * cause this to loop again and never succeed.
+		 * On failures, enabled and disable preemption with
+		 * migration enabled, to allow the migration thread to
+		 * migrate this task.
+		 */
+		if (trys) {
+			preempt_enable_notrace();
+			preempt_disable_notrace();
+			cpu = smp_processor_id();
+			buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf;
+		}
+
 		/*
 		 * If for some reason, copy_from_user() always causes a context
 		 * switch, this would then cause an infinite loop.
-- 
cgit v1.2.3


From 07183aac4a6828e474f00b37c9d795d0d99e18a7 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 18 Mar 2026 18:55:12 -0400
Subject: tracing: Fix trace_marker copy link list updates

When the "copy_trace_marker" option is enabled for an instance, anything
written into /sys/kernel/tracing/trace_marker is also copied into that
instances buffer. When the option is set, that instance's trace_array
descriptor is added to the marker_copies link list. This list is protected
by RCU, as all iterations uses an RCU protected list traversal.

When the instance is deleted, all the flags that were enabled are cleared.
This also clears the copy_trace_marker flag and removes the trace_array
descriptor from the list.

The issue is after the flags are called, a direct call to
update_marker_trace() is performed to clear the flag. This function
returns true if the state of the flag changed and false otherwise. If it
returns true here, synchronize_rcu() is called to make sure all readers
see that its removed from the list.

But since the flag was already cleared, the state does not change and the
synchronization is never called, leaving a possible UAF bug.

Move the clearing of all flags below the updating of the copy_trace_marker
option which then makes sure the synchronization is performed.

Also use the flag for checking the state in update_marker_trace() instead
of looking at if the list is empty.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20260318185512.1b6c7db4@gandalf.local.home
Fixes: 7b382efd5e8a ("tracing: Allow the top level trace_marker to write into another instances")
Reported-by: Sasha Levin <sashal@kernel.org>
Closes: https://lore.kernel.org/all/20260225133122.237275-1-sashal@kernel.org/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bb4a62f4b953..a626211ceb9a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -555,7 +555,7 @@ static bool update_marker_trace(struct trace_array *tr, int enabled)
 	lockdep_assert_held(&event_mutex);
 
 	if (enabled) {
-		if (!list_empty(&tr->marker_list))
+		if (tr->trace_flags & TRACE_ITER(COPY_MARKER))
 			return false;
 
 		list_add_rcu(&tr->marker_list, &marker_copies);
@@ -563,10 +563,10 @@ static bool update_marker_trace(struct trace_array *tr, int enabled)
 		return true;
 	}
 
-	if (list_empty(&tr->marker_list))
+	if (!(tr->trace_flags & TRACE_ITER(COPY_MARKER)))
 		return false;
 
-	list_del_init(&tr->marker_list);
+	list_del_rcu(&tr->marker_list);
 	tr->trace_flags &= ~TRACE_ITER(COPY_MARKER);
 	return true;
 }
@@ -9761,18 +9761,19 @@ static int __remove_instance(struct trace_array *tr)
 
 	list_del(&tr->list);
 
-	/* Disable all the flags that were enabled coming in */
-	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) {
-		if ((1ULL << i) & ZEROED_TRACE_FLAGS)
-			set_tracer_flag(tr, 1ULL << i, 0);
-	}
-
 	if (printk_trace == tr)
 		update_printk_trace(&global_trace);
 
+	/* Must be done before disabling all the flags */
 	if (update_marker_trace(tr, 0))
 		synchronize_rcu();
 
+	/* Disable all the flags that were enabled coming in */
+	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) {
+		if ((1ULL << i) & ZEROED_TRACE_FLAGS)
+			set_tracer_flag(tr, 1ULL << i, 0);
+	}
+
 	tracing_set_nop(tr);
 	clear_ftrace_function_probes(tr);
 	event_trace_del_tracer(tr);
-- 
cgit v1.2.3


From 768461517a28d80fe81ea4d5d03a90cd184ea6ad Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 14 Mar 2026 18:13:32 -0500
Subject: iio: adc: ti-adc161s626: use DMA-safe memory for spi_read()

Add a DMA-safe buffer and use it for spi_read() instead of a stack
memory. All SPI buffers must be DMA-safe.

Since we only need up to 3 bytes, we just use a u8[] instead of __be16
and __be32 and change the conversion functions appropriately.

Fixes: 4d671b71beef ("iio: adc: ti-adc161s626: add support for TI 1-channel differential ADCs")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ti-adc161s626.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/iio/adc/ti-adc161s626.c b/drivers/iio/adc/ti-adc161s626.c
index 42968d96572b..be1cc2e77862 100644
--- a/drivers/iio/adc/ti-adc161s626.c
+++ b/drivers/iio/adc/ti-adc161s626.c
@@ -15,6 +15,7 @@
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/spi/spi.h>
+#include <linux/unaligned.h>
 #include <linux/iio/iio.h>
 #include <linux/iio/trigger.h>
 #include <linux/iio/buffer.h>
@@ -70,6 +71,7 @@ struct ti_adc_data {
 
 	u8 read_size;
 	u8 shift;
+	u8 buf[3] __aligned(IIO_DMA_MINALIGN);
 };
 
 static int ti_adc_read_measurement(struct ti_adc_data *data,
@@ -78,26 +80,20 @@ static int ti_adc_read_measurement(struct ti_adc_data *data,
 	int ret;
 
 	switch (data->read_size) {
-	case 2: {
-		__be16 buf;
-
-		ret = spi_read(data->spi, (void *) &buf, 2);
+	case 2:
+		ret = spi_read(data->spi, data->buf, 2);
 		if (ret)
 			return ret;
 
-		*val = be16_to_cpu(buf);
+		*val = get_unaligned_be16(data->buf);
 		break;
-	}
-	case 3: {
-		__be32 buf;
-
-		ret = spi_read(data->spi, (void *) &buf, 3);
+	case 3:
+		ret = spi_read(data->spi, data->buf, 3);
 		if (ret)
 			return ret;
 
-		*val = be32_to_cpu(buf) >> 8;
+		*val = get_unaligned_be24(data->buf);
 		break;
-	}
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From f35dbac6942171dc4ce9398d1d216a59224590a9 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 19 Mar 2026 18:12:19 +0900
Subject: ring-buffer: Fix to update per-subbuf entries of persistent ring
 buffer

Since the validation loop in rb_meta_validate_events() updates the same
cpu_buffer->head_page->entries, the other subbuf entries are not updated.
Fix to use head_page to update the entries field, since it is the cursor
in this loop.

Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Ian Rogers <irogers@google.com>
Fixes: 5f3b6e839f3c ("ring-buffer: Validate boot range memory events")
Link: https://patch.msgid.link/177391153882.193994.17158784065013676533.stgit@mhiramat.tok.corp.google.com
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 17d0ea0cc3e6..170170bd83bd 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2053,7 +2053,7 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer)
 
 		entries += ret;
 		entry_bytes += local_read(&head_page->page->commit);
-		local_set(&cpu_buffer->head_page->entries, ret);
+		local_set(&head_page->entries, ret);
 
 		if (head_page == cpu_buffer->commit_page)
 			break;
-- 
cgit v1.2.3


From 50b35c9e50a865600344ab1d8f9a8b3384d7e63d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 12 Mar 2026 13:37:38 +0100
Subject: ftrace: Use hash argument for tmp_ops in update_ftrace_direct_mod

The modify logic registers temporary ftrace_ops object (tmp_ops) to trigger
the slow path for all direct callers to be able to safely modify attached
addresses.

At the moment we use ops->func_hash for tmp_ops filter, which represents all
the systems attachments. It's faster to use just the passed hash filter, which
contains only the modified sites and is always a subset of the ops->func_hash.

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Menglong Dong <menglong8.dong@gmail.com>
Cc: Song Liu <song@kernel.org>
Link: https://patch.msgid.link/20260312123738.129926-1-jolsa@kernel.org
Fixes: e93672f770d7 ("ftrace: Add update_ftrace_direct_mod function")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8df69e702706..413310912609 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6606,9 +6606,9 @@ int update_ftrace_direct_mod(struct ftrace_ops *ops, struct ftrace_hash *hash, b
 	if (!orig_hash)
 		goto unlock;
 
-	/* Enable the tmp_ops to have the same functions as the direct ops */
+	/* Enable the tmp_ops to have the same functions as the hash object. */
 	ftrace_ops_init(&tmp_ops);
-	tmp_ops.func_hash = ops->func_hash;
+	tmp_ops.func_hash->filter_hash = hash;
 
 	err = register_ftrace_function_nolock(&tmp_ops);
 	if (err)
-- 
cgit v1.2.3


From fdc7aa54a5d44c05880a4aad7cfb41aacfd16d7b Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 14 Mar 2026 17:18:10 -0500
Subject: iio: light: vcnl4035: fix scan buffer on big-endian

Rework vcnl4035_trigger_consumer_handler() so that we are not passing
what should be a u16 value as an int * to regmap_read(). This won't
work on bit endian systems.

Instead, add a new unsigned int variable to pass to regmap_read(). Then
copy that value into the buffer struct.

The buffer array is replaced with a struct since there is only one value
being read. This allows us to use the correct u16 data type and has a
side-effect of simplifying the alignment specification.

Also fix the endianness of the scan format from little-endian to CPU
endianness. Since we are using regmap to read the value, it will be
CPU-endian.

Fixes: 55707294c4eb ("iio: light: Add support for vishay vcnl4035")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/vcnl4035.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c
index 963747927425..16aeb17067bc 100644
--- a/drivers/iio/light/vcnl4035.c
+++ b/drivers/iio/light/vcnl4035.c
@@ -103,17 +103,23 @@ static irqreturn_t vcnl4035_trigger_consumer_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct vcnl4035_data *data = iio_priv(indio_dev);
 	/* Ensure naturally aligned timestamp */
-	u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)]  __aligned(8) = { };
+	struct {
+		u16 als_data;
+		aligned_s64 timestamp;
+	} buffer = { };
+	unsigned int val;
 	int ret;
 
-	ret = regmap_read(data->regmap, VCNL4035_ALS_DATA, (int *)buffer);
+	ret = regmap_read(data->regmap, VCNL4035_ALS_DATA, &val);
 	if (ret < 0) {
 		dev_err(&data->client->dev,
 			"Trigger consumer can't read from sensor.\n");
 		goto fail_read;
 	}
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
-					iio_get_time_ns(indio_dev));
+
+	buffer.als_data = val;
+	iio_push_to_buffers_with_timestamp(indio_dev, &buffer,
+					   iio_get_time_ns(indio_dev));
 
 fail_read:
 	iio_trigger_notify_done(indio_dev->trig);
@@ -381,7 +387,7 @@ static const struct iio_chan_spec vcnl4035_channels[] = {
 			.sign = 'u',
 			.realbits = 16,
 			.storagebits = 16,
-			.endianness = IIO_LE,
+			.endianness = IIO_CPU,
 		},
 	},
 	{
@@ -395,7 +401,7 @@ static const struct iio_chan_spec vcnl4035_channels[] = {
 			.sign = 'u',
 			.realbits = 16,
 			.storagebits = 16,
-			.endianness = IIO_LE,
+			.endianness = IIO_CPU,
 		},
 	},
 };
-- 
cgit v1.2.3


From db08b1940f4beb25460b4a4e9da3446454f2e8fe Mon Sep 17 00:00:00 2001
From: Cheng-Yang Chou <yphbchou0911@gmail.com>
Date: Sat, 21 Mar 2026 18:54:58 +0800
Subject: sched_ext: Fix inconsistent NUMA node lookup in scx_select_cpu_dfl()

In the WAKE_SYNC path of scx_select_cpu_dfl(), waker_node was computed
with cpu_to_node(), while node (for prev_cpu) was computed with
scx_cpu_node_if_enabled(). When scx_builtin_idle_per_node is disabled,
idle_cpumask(waker_node) is called with a real node ID even though
per-node idle tracking is disabled, resulting in undefined behavior.

Fix by using scx_cpu_node_if_enabled() for waker_node as well, ensuring
both variables are computed consistently.

Fixes: 48849271e6611 ("sched_ext: idle: Per-node idle cpumasks")
Cc: stable@vger.kernel.org # v6.15+
Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_idle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index ba298ac3ce6c..0ae93cd64004 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -543,7 +543,7 @@ s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
 		 * piled up on it even if there is an idle core elsewhere on
 		 * the system.
 		 */
-		waker_node = cpu_to_node(cpu);
+		waker_node = scx_cpu_node_if_enabled(cpu);
 		if (!(current->flags & PF_EXITING) &&
 		    cpu_rq(cpu)->scx.local_dsq.nr == 0 &&
 		    (!(flags & SCX_PICK_IDLE_IN_NODE) || (waker_node == node)) &&
-- 
cgit v1.2.3


From 3a206a8649f83bec99a3517da5e7dac9c138875e Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Date: Wed, 18 Mar 2026 12:26:32 +0000
Subject: mm/rmap: clear vma->anon_vma on error

Commit 542eda1a8329 ("mm/rmap: improve anon_vma_clone(),
unlink_anon_vmas() comments, add asserts") alters the way errors are
handled, but overlooked one important aspect of clean up.

When a VMA encounters an error state in anon_vma_clone() (that is, on
attempted allocation of anon_vma_chain objects), it cleans up partially
established state in cleanup_partial_anon_vmas(), before returning an
error.

However, this occurs prior to anon_vma->num_active_vmas being incremented,
and it also fails to clear the VMA's vma->anon_vma field, which remains in
place.

This is immediately an inconsistent state, because
anon_vma->num_active_vmas is supposed to track the number of VMAs whose
vma->anon_vma field references that anon_vma, and now that count is
off-by-negative-1 for each VMA for which this error state has occurred.

When VMAs are unlinked from this anon_vma, unlink_anon_vmas() will
eventually underflow anon_vma->num_active_vmas, which will trigger a
warning.

This will always eventually happen, as we unlink anon_vma's at process
teardown.

It could also cause maybe_reuse_anon_vma() to incorrectly permit the reuse
of an anon_vma which has active VMAs attached, which will lead to a
persistently invalid state.

The solution is to clear the VMA's anon_vma field when we clean up partial
state, as the fact we are doing so indicates clearly that the VMA is not
correctly integrated into the anon_vma tree and thus this field is
invalid.

Link: https://lkml.kernel.org/r/20260318122632.63404-1-ljs@kernel.org
Fixes: 542eda1a8329 ("mm/rmap: improve anon_vma_clone(), unlink_anon_vmas() comments, add asserts")
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reported-by: Sasha Levin <sashal@kernel.org>
Closes: https://lore.kernel.org/linux-mm/20260302151547.2389070-1-sashal@kernel.org/
Reported-by: Jiakai Xu <jiakaipeanut@gmail.com>
Closes: https://lore.kernel.org/linux-mm/CAFb8wJvRhatRD-9DVmr5v5pixTMPEr3UKjYBJjCd09OfH55CKg@mail.gmail.com/
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Tested-by: Jiakai Xu <jiakaipeanut@gmail.com>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sasha Levin (Microsoft) <sashal@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/rmap.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/rmap.c b/mm/rmap.c
index 391337282e3f..8f08090d7eb9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -457,6 +457,13 @@ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma)
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
+
+	/*
+	 * The anon_vma assigned to this VMA is no longer valid, as we were not
+	 * able to correctly clone AVC state. Avoid inconsistent anon_vma tree
+	 * state by resetting.
+	 */
+	vma->anon_vma = NULL;
 }
 
 /**
-- 
cgit v1.2.3


From 26f775a054c3cda86ad465a64141894a90a9e145 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Thu, 19 Mar 2026 07:52:17 -0700
Subject: mm/damon/core: avoid use of half-online-committed context

One major usage of damon_call() is online DAMON parameters update.  It is
done by calling damon_commit_ctx() inside the damon_call() callback
function.  damon_commit_ctx() can fail for two reasons: 1) invalid
parameters and 2) internal memory allocation failures.  In case of
failures, the damon_ctx that attempted to be updated (commit destination)
can be partially updated (or, corrupted from a perspective), and therefore
shouldn't be used anymore.  The function only ensures the damon_ctx object
can safely deallocated using damon_destroy_ctx().

The API callers are, however, calling damon_commit_ctx() only after
asserting the parameters are valid, to avoid damon_commit_ctx() fails due
to invalid input parameters.  But it can still theoretically fail if the
internal memory allocation fails.  In the case, DAMON may run with the
partially updated damon_ctx.  This can result in unexpected behaviors
including even NULL pointer dereference in case of damos_commit_dests()
failure [1].  Such allocation failure is arguably too small to fail, so
the real world impact would be rare.  But, given the bad consequence, this
needs to be fixed.

Avoid such partially-committed (maybe-corrupted) damon_ctx use by saving
the damon_commit_ctx() failure on the damon_ctx object.  For this,
introduce damon_ctx->maybe_corrupted field.  damon_commit_ctx() sets it
when it is failed.  kdamond_call() checks if the field is set after each
damon_call_control->fn() is executed.  If it is set, ignore remaining
callback requests and return.  All kdamond_call() callers including
kdamond_fn() also check the maybe_corrupted field right after
kdamond_call() invocations.  If the field is set, break the kdamond_fn()
main loop so that DAMON sill doesn't use the context that might be
corrupted.

[sj@kernel.org: let kdamond_call() with cancel regardless of maybe_corrupted]
  Link: https://lkml.kernel.org/r/20260320031553.2479-1-sj@kernel.org
  Link: https://sashiko.dev/#/patchset/20260319145218.86197-1-sj%40kernel.org
Link: https://lkml.kernel.org/r/20260319145218.86197-1-sj@kernel.org
Link: https://lore.kernel.org/20260319043309.97966-1-sj@kernel.org [1]
Fixes: 3301f1861d34 ("mm/damon/sysfs: handle commit command using damon_call()")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.15+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 6 ++++++
 mm/damon/core.c       | 8 ++++++++
 2 files changed, 14 insertions(+)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index a4fea23da857..be3d198043ff 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -810,6 +810,12 @@ struct damon_ctx {
 	struct damos_walk_control *walk_control;
 	struct mutex walk_control_lock;
 
+	/*
+	 * indicate if this may be corrupted.  Currentonly this is set only for
+	 * damon_commit_ctx() failure.
+	 */
+	bool maybe_corrupted;
+
 	/* Working thread of the given DAMON context */
 	struct task_struct *kdamond;
 	/* Protects @kdamond field access */
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c1d1091d307e..3e1890d64d06 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1252,6 +1252,7 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 {
 	int err;
 
+	dst->maybe_corrupted = true;
 	if (!is_power_of_2(src->min_region_sz))
 		return -EINVAL;
 
@@ -1277,6 +1278,7 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 	dst->addr_unit = src->addr_unit;
 	dst->min_region_sz = src->min_region_sz;
 
+	dst->maybe_corrupted = false;
 	return 0;
 }
 
@@ -2678,6 +2680,8 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 			complete(&control->completion);
 		else if (control->canceled && control->dealloc_on_cancel)
 			kfree(control);
+		if (!cancel && ctx->maybe_corrupted)
+			break;
 	}
 
 	mutex_lock(&ctx->call_controls_lock);
@@ -2707,6 +2711,8 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
 		kdamond_usleep(min_wait_time);
 
 		kdamond_call(ctx, false);
+		if (ctx->maybe_corrupted)
+			return -EINVAL;
 		damos_walk_cancel(ctx);
 	}
 	return -EBUSY;
@@ -2790,6 +2796,8 @@ static int kdamond_fn(void *data)
 		 * kdamond_merge_regions() if possible, to reduce overhead
 		 */
 		kdamond_call(ctx, false);
+		if (ctx->maybe_corrupted)
+			break;
 		if (!list_empty(&ctx->schemes))
 			kdamond_apply_schemes(ctx);
 		else
-- 
cgit v1.2.3


From b0377ee8042985b0d91bf579afcc4ee9150db14d Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Thu, 19 Mar 2026 12:44:56 +0900
Subject: zram: do not slot_free() written-back slots

slot_free() basically completely resets the slots by clearing all of
its flags and attributes.  While zram_writeback_complete() restores
some of flags back (those that are necessary for async read
decompression) we still lose a lot of slot's metadata.  For example,
slot's ac-time, or ZRAM_INCOMPRESSIBLE.

More importantly, restoring flags/attrs requires extra attention as
some of the flags are directly affecting zram device stats.  And the
original code did not pay that attention.  Namely ZRAM_HUGE slots
handling in zram_writeback_complete().  The call to slot_free() would
decrement ->huge_pages, however when zram_writeback_complete() restored
the slot's ZRAM_HUGE flag, it would not get reflected in an incremented
->huge_pages.  So when the slot would finally get freed, slot_free()
would decrement ->huge_pages again, leading to underflow.

Fix this by open-coding the required memory free and stats updates in
zram_writeback_complete(), rather than calling the destructive
slot_free().  Since we now preserve the ZRAM_HUGE flag on written-back
slots (for the deferred decompression path), we also update slot_free()
to skip decrementing ->huge_pages if ZRAM_WB is set.

Link: https://lkml.kernel.org/r/20260320023143.2372879-1-senozhatsky@chromium.org
Link: https://lkml.kernel.org/r/20260319034912.1894770-1-senozhatsky@chromium.org
Fixes: d38fab605c667 ("zram: introduce compressed data writeback")
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Richard Chang <richardycc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/block/zram/zram_drv.c | 39 ++++++++++++++-------------------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a324ede6206d..af679375b193 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -917,9 +917,8 @@ static void zram_account_writeback_submit(struct zram *zram)
 
 static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 {
-	u32 size, index = req->pps->index;
-	int err, prio;
-	bool huge;
+	u32 index = req->pps->index;
+	int err;
 
 	err = blk_status_to_errno(req->bio.bi_status);
 	if (err) {
@@ -946,28 +945,13 @@ static int zram_writeback_complete(struct zram *zram, struct zram_wb_req *req)
 		goto out;
 	}
 
-	if (zram->compressed_wb) {
-		/*
-		 * ZRAM_WB slots get freed, we need to preserve data required
-		 * for read decompression.
-		 */
-		size = get_slot_size(zram, index);
-		prio = get_slot_comp_priority(zram, index);
-		huge = test_slot_flag(zram, index, ZRAM_HUGE);
-	}
-
-	slot_free(zram, index);
-	set_slot_flag(zram, index, ZRAM_WB);
+	clear_slot_flag(zram, index, ZRAM_IDLE);
+	if (test_slot_flag(zram, index, ZRAM_HUGE))
+		atomic64_dec(&zram->stats.huge_pages);
+	atomic64_sub(get_slot_size(zram, index), &zram->stats.compr_data_size);
+	zs_free(zram->mem_pool, get_slot_handle(zram, index));
 	set_slot_handle(zram, index, req->blk_idx);
-
-	if (zram->compressed_wb) {
-		if (huge)
-			set_slot_flag(zram, index, ZRAM_HUGE);
-		set_slot_size(zram, index, size);
-		set_slot_comp_priority(zram, index, prio);
-	}
-
-	atomic64_inc(&zram->stats.pages_stored);
+	set_slot_flag(zram, index, ZRAM_WB);
 
 out:
 	slot_unlock(zram, index);
@@ -2010,8 +1994,13 @@ static void slot_free(struct zram *zram, u32 index)
 	set_slot_comp_priority(zram, index, 0);
 
 	if (test_slot_flag(zram, index, ZRAM_HUGE)) {
+		/*
+		 * Writeback completion decrements ->huge_pages but keeps
+		 * ZRAM_HUGE flag for deferred decompression path.
+		 */
+		if (!test_slot_flag(zram, index, ZRAM_WB))
+			atomic64_dec(&zram->stats.huge_pages);
 		clear_slot_flag(zram, index, ZRAM_HUGE);
-		atomic64_dec(&zram->stats.huge_pages);
 	}
 
 	if (test_slot_flag(zram, index, ZRAM_WB)) {
-- 
cgit v1.2.3


From c7f27a8ab9f2f43570f0725256597a0d7abe2c5b Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Sat, 21 Mar 2026 20:30:45 -0700
Subject: workqueue: Fix false positive stall reports

On weakly ordered architectures (e.g., arm64), the lockless check in
wq_watchdog_timer_fn() can observe a reordering between the worklist
insertion and the last_progress_ts update. Specifically, the watchdog
can see a non-empty worklist (from a list_add) while reading a stale
last_progress_ts value, causing a false positive stall report.

This was confirmed by reading pool->last_progress_ts again after holding
pool->lock in wq_watchdog_timer_fn():

  workqueue watchdog: pool 7 false positive detected!
    lockless_ts=4784580465 locked_ts=4785033728
    diff=453263ms worklist_empty=0

To avoid slowing down the hot path (queue_work, etc.), recheck
last_progress_ts with pool->lock held. This will eliminate the false
positive with minimal overhead.

Remove two extra empty lines in wq_watchdog_timer_fn() as we are on it.

Fixes: 82607adcf9cd ("workqueue: implement lockup detector")
Cc: stable@vger.kernel.org # v4.5+
Assisted-by: claude-code:claude-opus-4-6
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b77119d71641..ff97b705f25e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7699,8 +7699,28 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		else
 			ts = touched;
 
-		/* did we stall? */
+		/*
+		 * Did we stall?
+		 *
+		 * Do a lockless check first. On weakly ordered
+		 * architectures, the lockless check can observe a
+		 * reordering between worklist insert_work() and
+		 * last_progress_ts update from __queue_work(). Since
+		 * __queue_work() is a much hotter path than the timer
+		 * function, we handle false positive here by reading
+		 * last_progress_ts again with pool->lock held.
+		 */
 		if (time_after(now, ts + thresh)) {
+			scoped_guard(raw_spinlock_irqsave, &pool->lock) {
+				pool_ts = pool->last_progress_ts;
+				if (time_after(pool_ts, touched))
+					ts = pool_ts;
+				else
+					ts = touched;
+			}
+			if (!time_after(now, ts + thresh))
+				continue;
+
 			lockup_detected = true;
 			stall_time = jiffies_to_msecs(now - pool_ts) / 1000;
 			max_stall_time = max(max_stall_time, stall_time);
@@ -7712,8 +7732,6 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 			pr_cont_pool_info(pool);
 			pr_cont(" stuck for %us!\n", stall_time);
 		}
-
-
 	}
 
 	if (lockup_detected)
-- 
cgit v1.2.3


From 67c3f99bed6f422ba343d2b70a2eeeccdfd91bef Mon Sep 17 00:00:00 2001
From: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Date: Fri, 30 Jan 2026 14:23:52 +0200
Subject: counter: rz-mtu3-cnt: prevent counter from being toggled multiple
 times

Runtime PM counter is incremented / decremented each time the sysfs
enable file is written to.

If user writes 0 to the sysfs enable file multiple times, runtime PM
usage count underflows, generating the following message.

rz-mtu3-counter rz-mtu3-counter.0: Runtime PM usage count underflow!

At the same time, hardware registers end up being accessed with clocks
off in rz_mtu3_terminate_counter() to disable an already disabled
channel.

If user writes 1 to the sysfs enable file multiple times, runtime PM
usage count will be incremented each time, requiring the same number of
0 writes to get it back to 0.

If user writes 0 to the sysfs enable file while PWM is in progress, PWM
is stopped without counter being the owner of the underlying MTU3
channel.

Check against the cached count_is_enabled value and exit if the user
is trying to set the same enable value.

Cc: stable@vger.kernel.org
Fixes: 0be8907359df ("counter: Add Renesas RZ/G2L MTU3a counter driver")
Signed-off-by: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Link: https://lore.kernel.org/r/20260130122353.2263273-5-cosmin-gabriel.tanislav.xa@renesas.com
Signed-off-by: William Breathitt Gray <wbg@kernel.org>
---
 drivers/counter/rz-mtu3-cnt.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/counter/rz-mtu3-cnt.c b/drivers/counter/rz-mtu3-cnt.c
index e755d54dfece..a4a8ef2d88f0 100644
--- a/drivers/counter/rz-mtu3-cnt.c
+++ b/drivers/counter/rz-mtu3-cnt.c
@@ -499,21 +499,25 @@ static int rz_mtu3_count_enable_write(struct counter_device *counter,
 	struct rz_mtu3_cnt *const priv = counter_priv(counter);
 	int ret = 0;
 
+	mutex_lock(&priv->lock);
+
+	if (priv->count_is_enabled[count->id] == enable)
+		goto exit;
+
 	if (enable) {
-		mutex_lock(&priv->lock);
 		pm_runtime_get_sync(ch->dev);
 		ret = rz_mtu3_initialize_counter(counter, count->id);
 		if (ret == 0)
 			priv->count_is_enabled[count->id] = true;
-		mutex_unlock(&priv->lock);
 	} else {
-		mutex_lock(&priv->lock);
 		rz_mtu3_terminate_counter(counter, count->id);
 		priv->count_is_enabled[count->id] = false;
 		pm_runtime_put(ch->dev);
-		mutex_unlock(&priv->lock);
 	}
 
+exit:
+	mutex_unlock(&priv->lock);
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From 2932095c114b98cbb40ccf34fc00d613cb17cead Mon Sep 17 00:00:00 2001
From: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Date: Fri, 30 Jan 2026 14:23:53 +0200
Subject: counter: rz-mtu3-cnt: do not use struct rz_mtu3_channel's dev member

The counter driver can use HW channels 1 and 2, while the PWM driver can
use HW channels 0, 1, 2, 3, 4, 6, 7.

The dev member is assigned both by the counter driver and the PWM driver
for channels 1 and 2, to their own struct device instance, overwriting
the previous value.

The sub-drivers race to assign their own struct device pointer to the
same struct rz_mtu3_channel's dev member.

The dev member of struct rz_mtu3_channel is used by the counter
sub-driver for runtime PM.

Depending on the probe order of the counter and PWM sub-drivers, the
dev member may point to the wrong struct device instance, causing the
counter sub-driver to do runtime PM actions on the wrong device.

To fix this, use the parent pointer of the counter, which is assigned
during probe to the correct struct device, not the struct device pointer
inside the shared struct rz_mtu3_channel.

Cc: stable@vger.kernel.org
Fixes: 0be8907359df ("counter: Add Renesas RZ/G2L MTU3a counter driver")
Signed-off-by: Cosmin Tanislav <cosmin-gabriel.tanislav.xa@renesas.com>
Link: https://lore.kernel.org/r/20260130122353.2263273-6-cosmin-gabriel.tanislav.xa@renesas.com
Signed-off-by: William Breathitt Gray <wbg@kernel.org>
---
 drivers/counter/rz-mtu3-cnt.c | 55 +++++++++++++++++++++----------------------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/drivers/counter/rz-mtu3-cnt.c b/drivers/counter/rz-mtu3-cnt.c
index a4a8ef2d88f0..7bfb6979193c 100644
--- a/drivers/counter/rz-mtu3-cnt.c
+++ b/drivers/counter/rz-mtu3-cnt.c
@@ -107,9 +107,9 @@ static bool rz_mtu3_is_counter_invalid(struct counter_device *counter, int id)
 	struct rz_mtu3_cnt *const priv = counter_priv(counter);
 	unsigned long tmdr;
 
-	pm_runtime_get_sync(priv->ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3);
-	pm_runtime_put(priv->ch->dev);
+	pm_runtime_put(counter->parent);
 
 	if (id == RZ_MTU3_32_BIT_CH && test_bit(RZ_MTU3_TMDR3_LWA, &tmdr))
 		return false;
@@ -165,12 +165,12 @@ static int rz_mtu3_count_read(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	if (count->id == RZ_MTU3_32_BIT_CH)
 		*val = rz_mtu3_32bit_ch_read(ch, RZ_MTU3_TCNTLW);
 	else
 		*val = rz_mtu3_16bit_ch_read(ch, RZ_MTU3_TCNT);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -187,26 +187,26 @@ static int rz_mtu3_count_write(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	if (count->id == RZ_MTU3_32_BIT_CH)
 		rz_mtu3_32bit_ch_write(ch, RZ_MTU3_TCNTLW, val);
 	else
 		rz_mtu3_16bit_ch_write(ch, RZ_MTU3_TCNT, val);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
 }
 
 static int rz_mtu3_count_function_read_helper(struct rz_mtu3_channel *const ch,
-					      struct rz_mtu3_cnt *const priv,
+					      struct counter_device *const counter,
 					      enum counter_function *function)
 {
 	u8 timer_mode;
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	timer_mode = rz_mtu3_8bit_ch_read(ch, RZ_MTU3_TMDR1);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 
 	switch (timer_mode & RZ_MTU3_TMDR1_PH_CNT_MODE_MASK) {
 	case RZ_MTU3_TMDR1_PH_CNT_MODE_1:
@@ -240,7 +240,7 @@ static int rz_mtu3_count_function_read(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	ret = rz_mtu3_count_function_read_helper(ch, priv, function);
+	ret = rz_mtu3_count_function_read_helper(ch, counter, function);
 	mutex_unlock(&priv->lock);
 
 	return ret;
@@ -279,9 +279,9 @@ static int rz_mtu3_count_function_write(struct counter_device *counter,
 		return -EINVAL;
 	}
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TMDR1, timer_mode);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -300,9 +300,9 @@ static int rz_mtu3_count_direction_read(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	tsr = rz_mtu3_8bit_ch_read(ch, RZ_MTU3_TSR);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 
 	*direction = (tsr & RZ_MTU3_TSR_TCFD) ?
 		COUNTER_COUNT_DIRECTION_FORWARD : COUNTER_COUNT_DIRECTION_BACKWARD;
@@ -377,14 +377,14 @@ static int rz_mtu3_count_ceiling_write(struct counter_device *counter,
 		return -EINVAL;
 	}
 
-	pm_runtime_get_sync(ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	if (count->id == RZ_MTU3_32_BIT_CH)
 		rz_mtu3_32bit_ch_write(ch, RZ_MTU3_TGRALW, ceiling);
 	else
 		rz_mtu3_16bit_ch_write(ch, RZ_MTU3_TGRA, ceiling);
 
 	rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TCR, RZ_MTU3_TCR_CCLR_TGRA);
-	pm_runtime_put(ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -495,7 +495,6 @@ static int rz_mtu3_count_enable_read(struct counter_device *counter,
 static int rz_mtu3_count_enable_write(struct counter_device *counter,
 				      struct counter_count *count, u8 enable)
 {
-	struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id);
 	struct rz_mtu3_cnt *const priv = counter_priv(counter);
 	int ret = 0;
 
@@ -505,14 +504,14 @@ static int rz_mtu3_count_enable_write(struct counter_device *counter,
 		goto exit;
 
 	if (enable) {
-		pm_runtime_get_sync(ch->dev);
+		pm_runtime_get_sync(counter->parent);
 		ret = rz_mtu3_initialize_counter(counter, count->id);
 		if (ret == 0)
 			priv->count_is_enabled[count->id] = true;
 	} else {
 		rz_mtu3_terminate_counter(counter, count->id);
 		priv->count_is_enabled[count->id] = false;
-		pm_runtime_put(ch->dev);
+		pm_runtime_put(counter->parent);
 	}
 
 exit:
@@ -544,9 +543,9 @@ static int rz_mtu3_cascade_counts_enable_get(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(priv->ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3);
-	pm_runtime_put(priv->ch->dev);
+	pm_runtime_put(counter->parent);
 	*cascade_enable = test_bit(RZ_MTU3_TMDR3_LWA, &tmdr);
 	mutex_unlock(&priv->lock);
 
@@ -563,10 +562,10 @@ static int rz_mtu3_cascade_counts_enable_set(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(priv->ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	rz_mtu3_shared_reg_update_bit(priv->ch, RZ_MTU3_TMDR3,
 				      RZ_MTU3_TMDR3_LWA, cascade_enable);
-	pm_runtime_put(priv->ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -583,9 +582,9 @@ static int rz_mtu3_ext_input_phase_clock_select_get(struct counter_device *count
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(priv->ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3);
-	pm_runtime_put(priv->ch->dev);
+	pm_runtime_put(counter->parent);
 	*ext_input_phase_clock_select = test_bit(RZ_MTU3_TMDR3_PHCKSEL, &tmdr);
 	mutex_unlock(&priv->lock);
 
@@ -602,11 +601,11 @@ static int rz_mtu3_ext_input_phase_clock_select_set(struct counter_device *count
 	if (ret)
 		return ret;
 
-	pm_runtime_get_sync(priv->ch->dev);
+	pm_runtime_get_sync(counter->parent);
 	rz_mtu3_shared_reg_update_bit(priv->ch, RZ_MTU3_TMDR3,
 				      RZ_MTU3_TMDR3_PHCKSEL,
 				      ext_input_phase_clock_select);
-	pm_runtime_put(priv->ch->dev);
+	pm_runtime_put(counter->parent);
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -644,7 +643,7 @@ static int rz_mtu3_action_read(struct counter_device *counter,
 	if (ret)
 		return ret;
 
-	ret = rz_mtu3_count_function_read_helper(ch, priv, &function);
+	ret = rz_mtu3_count_function_read_helper(ch, counter, &function);
 	if (ret) {
 		mutex_unlock(&priv->lock);
 		return ret;
-- 
cgit v1.2.3


From 4f51e6c0baae80e52bd013092e82a55678be31fc Mon Sep 17 00:00:00 2001
From: Valek Andrej <andrej.v@skyrain.eu>
Date: Fri, 13 Mar 2026 10:24:13 +0100
Subject: iio: accel: fix ADXL355 temperature signature value

Temperature was wrongly represented as 12-bit signed, confirmed by checking
the datasheet. Even if the temperature is negative, the value in the
register stays unsigned.

Fixes: 12ed27863ea3 iio: accel: Add driver support for ADXL355
Signed-off-by: Valek Andrej <andrej.v@skyrain.eu>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl355_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c
index 1c1d64d5cbcb..8f90c58f4100 100644
--- a/drivers/iio/accel/adxl355_core.c
+++ b/drivers/iio/accel/adxl355_core.c
@@ -745,7 +745,7 @@ static const struct iio_chan_spec adxl355_channels[] = {
 				      BIT(IIO_CHAN_INFO_OFFSET),
 		.scan_index = 3,
 		.scan_type = {
-			.sign = 's',
+			.sign = 'u',
 			.realbits = 12,
 			.storagebits = 16,
 			.endianness = IIO_BE,
-- 
cgit v1.2.3


From c354521708175d776d896f8bdae44b18711eccb6 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Mar 2026 13:20:24 +0200
Subject: iio: dac: ad5770r: fix error return in ad5770r_read_raw()

Return the error code from regmap_bulk_read() instead of 0 so
that I/O failures are properly propagated.

Fixes: cbbb819837f6 ("iio: dac: ad5770r: Add AD5770R support")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ad5770r.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ad5770r.c b/drivers/iio/dac/ad5770r.c
index cd47cb1c685c..6027e8d88b27 100644
--- a/drivers/iio/dac/ad5770r.c
+++ b/drivers/iio/dac/ad5770r.c
@@ -322,7 +322,7 @@ static int ad5770r_read_raw(struct iio_dev *indio_dev,
 				       chan->address,
 				       st->transf_buf, 2);
 		if (ret)
-			return 0;
+			return ret;
 
 		buf16 = get_unaligned_le16(st->transf_buf);
 		*val = buf16 >> 2;
-- 
cgit v1.2.3


From 9d3fa23d5d55a137fd4396d3d4799102587a7f2b Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Thu, 12 Mar 2026 13:20:23 +0200
Subject: iio: accel: adxl313: add missing error check in predisable

Check the return value of the FIFO bypass regmap_write() before
proceeding to disable interrupts.

Fixes: ff8093fa6ba4 ("iio: accel: adxl313: add buffered FIFO watermark with interrupt handling")
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl313_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/iio/accel/adxl313_core.c b/drivers/iio/accel/adxl313_core.c
index 9f5d4d2cb325..83dcac17a042 100644
--- a/drivers/iio/accel/adxl313_core.c
+++ b/drivers/iio/accel/adxl313_core.c
@@ -998,6 +998,8 @@ static int adxl313_buffer_predisable(struct iio_dev *indio_dev)
 
 	ret = regmap_write(data->regmap, ADXL313_REG_FIFO_CTL,
 			   FIELD_PREP(ADXL313_REG_FIFO_CTL_MODE_MSK, ADXL313_FIFO_BYPASS));
+	if (ret)
+		return ret;
 
 	ret = regmap_write(data->regmap, ADXL313_REG_INT_ENABLE, 0);
 	if (ret)
-- 
cgit v1.2.3


From 2452969ca1081fea6bd9ab7ad5e168a5d11f28ec Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 22 Feb 2026 17:45:39 +0800
Subject: iio: adc: nxp-sar-adc: Fix DMA channel leak in trigger mode

The DMA channel was requested in nxp_sar_adc_buffer_postenable() but
was only released in nxp_sar_adc_buffer_software_do_predisable().
This caused a DMA channel resource leak when operating in trigger mode.

Fix this by moving dma_request_chan() from
nxp_sar_adc_buffer_postenable() into
nxp_sar_adc_buffer_software_do_postenable(), ensuring the DMA channel
is only requested in software mode.

Fixes: 4434072a893e ("iio: adc: Add the NXP SAR ADC support for the s32g2/3 platforms")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/nxp-sar-adc.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/adc/nxp-sar-adc.c b/drivers/iio/adc/nxp-sar-adc.c
index 9efa883c277d..58103bf16aff 100644
--- a/drivers/iio/adc/nxp-sar-adc.c
+++ b/drivers/iio/adc/nxp-sar-adc.c
@@ -718,6 +718,10 @@ static int nxp_sar_adc_buffer_software_do_postenable(struct iio_dev *indio_dev)
 	struct nxp_sar_adc *info = iio_priv(indio_dev);
 	int ret;
 
+	info->dma_chan = dma_request_chan(indio_dev->dev.parent, "rx");
+	if (IS_ERR(info->dma_chan))
+		return PTR_ERR(info->dma_chan);
+
 	nxp_sar_adc_dma_channels_enable(info, *indio_dev->active_scan_mask);
 
 	nxp_sar_adc_dma_cfg(info, true);
@@ -738,6 +742,7 @@ out_stop_cyclic_dma:
 out_dma_channels_disable:
 	nxp_sar_adc_dma_cfg(info, false);
 	nxp_sar_adc_dma_channels_disable(info, *indio_dev->active_scan_mask);
+	dma_release_channel(info->dma_chan);
 
 	return ret;
 }
@@ -765,10 +770,6 @@ static int nxp_sar_adc_buffer_postenable(struct iio_dev *indio_dev)
 	unsigned long channel;
 	int ret;
 
-	info->dma_chan = dma_request_chan(indio_dev->dev.parent, "rx");
-	if (IS_ERR(info->dma_chan))
-		return PTR_ERR(info->dma_chan);
-
 	info->channels_used = 0;
 
 	/*
-- 
cgit v1.2.3


From 4cfdfeb6ac06079f92fccd977fa742d6c5b8dd3a Mon Sep 17 00:00:00 2001
From: Luca Leonardo Scorcia <l.scorcia@gmail.com>
Date: Wed, 25 Feb 2026 09:38:41 +0000
Subject: drm/mediatek: dsi: Store driver data before invoking
 mipi_dsi_host_register

The call to mipi_dsi_host_register triggers a callback to mtk_dsi_bind,
which uses dev_get_drvdata to retrieve the mtk_dsi struct, so this
structure needs to be stored inside the driver data before invoking it.

As drvdata is currently uninitialized it leads to a crash when
registering the DSI DRM encoder right after acquiring
the mode_config.idr_mutex, blocking all subsequent DRM operations.

Fixes the following crash during mediatek-drm probe (tested on Xiaomi
Smart Clock x04g):

Unable to handle kernel NULL pointer dereference at virtual address
 0000000000000040
[...]
Modules linked in: mediatek_drm(+) drm_display_helper cec drm_client_lib
 drm_dma_helper drm_kms_helper panel_simple
[...]
Call trace:
 drm_mode_object_add+0x58/0x98 (P)
 __drm_encoder_init+0x48/0x140
 drm_encoder_init+0x6c/0xa0
 drm_simple_encoder_init+0x20/0x34 [drm_kms_helper]
 mtk_dsi_bind+0x34/0x13c [mediatek_drm]
 component_bind_all+0x120/0x280
 mtk_drm_bind+0x284/0x67c [mediatek_drm]
 try_to_bring_up_aggregate_device+0x23c/0x320
 __component_add+0xa4/0x198
 component_add+0x14/0x20
 mtk_dsi_host_attach+0x78/0x100 [mediatek_drm]
 mipi_dsi_attach+0x2c/0x50
 panel_simple_dsi_probe+0x4c/0x9c [panel_simple]
 mipi_dsi_drv_probe+0x1c/0x28
 really_probe+0xc0/0x3dc
 __driver_probe_device+0x80/0x160
 driver_probe_device+0x40/0x120
 __device_attach_driver+0xbc/0x17c
 bus_for_each_drv+0x88/0xf0
 __device_attach+0x9c/0x1cc
 device_initial_probe+0x54/0x60
 bus_probe_device+0x34/0xa0
 device_add+0x5b0/0x800
 mipi_dsi_device_register_full+0xdc/0x16c
 mipi_dsi_host_register+0xc4/0x17c
 mtk_dsi_probe+0x10c/0x260 [mediatek_drm]
 platform_probe+0x5c/0xa4
 really_probe+0xc0/0x3dc
 __driver_probe_device+0x80/0x160
 driver_probe_device+0x40/0x120
 __driver_attach+0xc8/0x1f8
 bus_for_each_dev+0x7c/0xe0
 driver_attach+0x24/0x30
 bus_add_driver+0x11c/0x240
 driver_register+0x68/0x130
 __platform_register_drivers+0x64/0x160
 mtk_drm_init+0x24/0x1000 [mediatek_drm]
 do_one_initcall+0x60/0x1d0
 do_init_module+0x54/0x240
 load_module+0x1838/0x1dc0
 init_module_from_file+0xd8/0xf0
 __arm64_sys_finit_module+0x1b4/0x428
 invoke_syscall.constprop.0+0x48/0xc8
 do_el0_svc+0x3c/0xb8
 el0_svc+0x34/0xe8
 el0t_64_sync_handler+0xa0/0xe4
 el0t_64_sync+0x198/0x19c
Code: 52800022 941004ab 2a0003f3 37f80040 (29005a80)

Fixes: e4732b590a77 ("drm/mediatek: dsi: Register DSI host after acquiring clocks and PHY")
Signed-off-by: Luca Leonardo Scorcia <l.scorcia@gmail.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20260225094047.76780-1-l.scorcia@gmail.com/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 17c67f02016b..aaf6c9ebd319 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -1236,6 +1236,11 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 
 	dsi->host.ops = &mtk_dsi_ops;
 	dsi->host.dev = dev;
+
+	init_waitqueue_head(&dsi->irq_wait_queue);
+
+	platform_set_drvdata(pdev, dsi);
+
 	ret = mipi_dsi_host_register(&dsi->host);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to register DSI host\n");
@@ -1247,10 +1252,6 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, ret, "Failed to request DSI irq\n");
 	}
 
-	init_waitqueue_head(&dsi->irq_wait_queue);
-
-	platform_set_drvdata(pdev, dsi);
-
 	dsi->bridge.of_node = dev->of_node;
 	dsi->bridge.type = DRM_MODE_CONNECTOR_DSI;
 
-- 
cgit v1.2.3


From ec69c9e88315c4be70c283f18c2ff130da6320b5 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Tue, 3 Mar 2026 13:32:11 +0900
Subject: i2c: tegra: Don't mark devices with pins as IRQ safe

I2C devices with associated pinctrl states (DPAUX I2C controllers)
will change pinctrl state during runtime PM. This requires taking
a mutex, so these devices cannot be marked as IRQ safe.

Add PINCTRL as dependency to avoid build errors.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Reported-by: Russell King <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/all/E1vsNBv-00000009nfA-27ZK@rmk-PC.armlinux.org.uk/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/i2c/busses/Kconfig     | 2 ++
 drivers/i2c/busses/i2c-tegra.c | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e11d50750e63..7cb6b9b864a7 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -1213,6 +1213,8 @@ config I2C_TEGRA
 	tristate "NVIDIA Tegra internal I2C controller"
 	depends on ARCH_TEGRA || (COMPILE_TEST && (ARC || ARM || ARM64 || M68K || RISCV || SUPERH || SPARC))
 	# COMPILE_TEST needs architectures with readsX()/writesX() primitives
+	depends on PINCTRL
+	# ARCH_TEGRA implies PINCTRL, but the COMPILE_TEST side doesn't.
 	help
 	  If you say yes to this option, support will be included for the
 	  I2C controller embedded in NVIDIA Tegra SOCs
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index bec619b9af4e..4eaeb395d5db 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -2047,8 +2047,11 @@ static int tegra_i2c_probe(struct platform_device *pdev)
 	 *
 	 * VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't
 	 * be used for atomic transfers. ACPI device is not IRQ safe also.
+	 *
+	 * Devices with pinctrl states cannot be marked IRQ-safe as the pinctrl
+	 * state transitions during runtime PM require mutexes.
 	 */
-	if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev))
+	if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev) && !i2c_dev->dev->pins)
 		pm_runtime_irq_safe(i2c_dev->dev);
 
 	pm_runtime_enable(i2c_dev->dev);
-- 
cgit v1.2.3


From 4ddd7588fae6175e748cff22c79faafb4d455d42 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Mar 2026 15:42:16 -0300
Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources

To pick up the changes from these csets:

  9073428bb204d921 ("x86/sev: Allow IBPB-on-Entry feature for SNP guests")

That cause no changes to tooling as it doesn't include a new MSR to be
captured by the tools/perf/trace/beauty/tracepoints/x86_msr.sh script.

Just silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/msr-index.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index da5275d8eda6..6673601246b3 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -740,7 +740,10 @@
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
 #define MSR_AMD64_SNP_SECURE_AVIC_BIT	18
 #define MSR_AMD64_SNP_SECURE_AVIC	BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT)
-#define MSR_AMD64_SNP_RESV_BIT		19
+#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19)
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT	23
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY	BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		24
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
 #define MSR_AMD64_SAVIC_CONTROL		0xc0010138
 #define MSR_AMD64_SAVIC_EN_BIT		0
-- 
cgit v1.2.3


From 3c71ae8ec9adde96f5ecfcbeef62ccf1d420f83f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Mar 2026 15:47:05 -0300
Subject: tools headers UAPI: Sync linux/kvm.h with the kernel sources

To pick the changes in:

  da142f3d373a6dda ("KVM: Remove subtle "struct kvm_stats_desc" pseudo-overlay")

That just rebuilds perf, as these patches don't add any new KVM ioctl to
be harvested for the 'perf trace' ioctl syscall argument beautifiers.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 65500f5db379..80364d4dbebb 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -14,6 +14,10 @@
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
+#ifdef __KERNEL__
+#include <linux/kvm_types.h>
+#endif
+
 #define KVM_API_VERSION 12
 
 /*
@@ -1601,7 +1605,11 @@ struct kvm_stats_desc {
 	__u16 size;
 	__u32 offset;
 	__u32 bucket_size;
+#ifdef __KERNEL__
+	char name[KVM_STATS_NAME_SIZE];
+#else
 	char name[];
+#endif
 };
 
 #define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
-- 
cgit v1.2.3


From 0a8b2a0857ede906f7b74a435b11778336770bea Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Mar 2026 15:48:54 -0300
Subject: tools headers UAPI: Sync x86's asm/kvm.h with the kernel sources

To pick the changes in:

  e2ffe85b6d2bb778 ("KVM: x86: Introduce KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM")

That just rebuilds kvm-stat.c on x86, no change in functionality.

This silences these perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Jim Mattson <jmattson@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 846a63215ce1..0d4538fa6c31 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -476,6 +476,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 #define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
+#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
-- 
cgit v1.2.3


From 493ad070cbcb0d62deed877d90e80e554cac7f01 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sun, 22 Mar 2026 18:33:28 -0300
Subject: tools headers: Synchronize linux/build_bug.h with the kernel sources

To pick up the changes in:

  6ffd853b0b10e1e2 ("build_bug.h: correct function parameters names in kernel-doc")

That just add some comments, addressing this perf tools build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/build_bug.h include/linux/build_bug.h

Please take a look at tools/include/uapi/README for further info on this
synchronization process.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/build_bug.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index ab2aa97bd8ce..406923bd4846 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -32,7 +32,8 @@
 /**
  * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
  *		      error message.
- * @condition: the condition which the compiler should know is false.
+ * @cond: the condition which the compiler should know is false.
+ * @msg: build-time error message
  *
  * See BUILD_BUG_ON for description.
  */
@@ -60,6 +61,7 @@
 
 /**
  * static_assert - check integer constant expression at build time
+ * @expr: expression to be checked
  *
  * static_assert() is a wrapper for the C11 _Static_assert, with a
  * little macro magic to make the message optional (defaulting to the
-- 
cgit v1.2.3


From c369299895a591d96745d6492d4888259b004a9e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 22 Mar 2026 14:42:17 -0700
Subject: Linux 7.0-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index c9b7bee102e8..2294decf0afc 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 9bbb19d21ded7d78645506f20d8c44895e3d0fb9 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Tue, 17 Mar 2026 08:52:01 +0900
Subject: ksmbd: do not expire session on binding failure

When a multichannel session binding request fails (e.g. wrong password),
the error path unconditionally sets sess->state = SMB2_SESSION_EXPIRED.
However, during binding, sess points to the target session looked up via
ksmbd_session_lookup_slowpath() -- which belongs to another connection's
user. This allows a remote attacker to invalidate any active session by
simply sending a binding request with a wrong password (DoS).

Fix this by skipping session expiration when the failed request was
a binding attempt, since the session does not belong to the current
connection. The reference taken by ksmbd_session_lookup_slowpath() is
still correctly released via ksmbd_user_session_put().

Cc: stable@vger.kernel.org
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 9c44e71e3c3b..8fa780e8efd0 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1939,8 +1939,14 @@ out_err:
 			if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION)
 				try_delay = true;
 
-			sess->last_active = jiffies;
-			sess->state = SMB2_SESSION_EXPIRED;
+			/*
+			 * For binding requests, session belongs to another
+			 * connection. Do not expire it.
+			 */
+			if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) {
+				sess->last_active = jiffies;
+				sess->state = SMB2_SESSION_EXPIRED;
+			}
 			ksmbd_user_session_put(sess);
 			work->sess = NULL;
 			if (try_delay) {
-- 
cgit v1.2.3


From 48623ec358c1c600fa1e38368746f933e0f1a617 Mon Sep 17 00:00:00 2001
From: Werner Kasselman <werner@verivus.com>
Date: Mon, 16 Mar 2026 11:38:47 +0000
Subject: ksmbd: fix use-after-free and NULL deref in smb_grant_oplock()

smb_grant_oplock() has two issues in the oplock publication sequence:

1) opinfo is linked into ci->m_op_list (via opinfo_add) before
   add_lease_global_list() is called.  If add_lease_global_list()
   fails (kmalloc returns NULL), the error path frees the opinfo
   via __free_opinfo() while it is still linked in ci->m_op_list.
   Concurrent m_op_list readers (opinfo_get_list, or direct iteration
   in smb_break_all_levII_oplock) dereference the freed node.

2) opinfo->o_fp is assigned after add_lease_global_list() publishes
   the opinfo on the global lease list.  A concurrent
   find_same_lease_key() can walk the lease list and dereference
   opinfo->o_fp->f_ci while o_fp is still NULL.

Fix by restructuring the publication sequence to eliminate post-publish
failure:

- Set opinfo->o_fp before any list publication (fixes NULL deref).
- Preallocate lease_table via alloc_lease_table() before opinfo_add()
  so add_lease_global_list() becomes infallible after publication.
- Keep the original m_op_list publication order (opinfo_add before
  lease list) so concurrent opens via same_client_has_lease() and
  opinfo_get_list() still see the in-flight grant.
- Use opinfo_put() instead of __free_opinfo() on err_out so that
  the RCU-deferred free path is used.

This also requires splitting add_lease_global_list() to take a
preallocated lease_table and changing its return type from int to void,
since it can no longer fail.

Fixes: 1dfd062caa16 ("ksmbd: fix use-after-free by using call_rcu() for oplock_info")
Cc: stable@vger.kernel.org
Signed-off-by: Werner Kasselman <werner@verivus.com>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 72 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 45 insertions(+), 27 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 393a4ae47cc1..9b2bb8764a80 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -82,11 +82,19 @@ static void lease_del_list(struct oplock_info *opinfo)
 	spin_unlock(&lb->lb_lock);
 }
 
-static void lb_add(struct lease_table *lb)
+static struct lease_table *alloc_lease_table(struct oplock_info *opinfo)
 {
-	write_lock(&lease_list_lock);
-	list_add(&lb->l_entry, &lease_table_list);
-	write_unlock(&lease_list_lock);
+	struct lease_table *lb;
+
+	lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP);
+	if (!lb)
+		return NULL;
+
+	memcpy(lb->client_guid, opinfo->conn->ClientGUID,
+	       SMB2_CLIENT_GUID_SIZE);
+	INIT_LIST_HEAD(&lb->lease_list);
+	spin_lock_init(&lb->lb_lock);
+	return lb;
 }
 
 static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx)
@@ -1042,34 +1050,27 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2)
 	lease2->version = lease1->version;
 }
 
-static int add_lease_global_list(struct oplock_info *opinfo)
+static void add_lease_global_list(struct oplock_info *opinfo,
+				  struct lease_table *new_lb)
 {
 	struct lease_table *lb;
 
-	read_lock(&lease_list_lock);
+	write_lock(&lease_list_lock);
 	list_for_each_entry(lb, &lease_table_list, l_entry) {
 		if (!memcmp(lb->client_guid, opinfo->conn->ClientGUID,
 			    SMB2_CLIENT_GUID_SIZE)) {
 			opinfo->o_lease->l_lb = lb;
 			lease_add_list(opinfo);
-			read_unlock(&lease_list_lock);
-			return 0;
+			write_unlock(&lease_list_lock);
+			kfree(new_lb);
+			return;
 		}
 	}
-	read_unlock(&lease_list_lock);
 
-	lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP);
-	if (!lb)
-		return -ENOMEM;
-
-	memcpy(lb->client_guid, opinfo->conn->ClientGUID,
-	       SMB2_CLIENT_GUID_SIZE);
-	INIT_LIST_HEAD(&lb->lease_list);
-	spin_lock_init(&lb->lb_lock);
-	opinfo->o_lease->l_lb = lb;
+	opinfo->o_lease->l_lb = new_lb;
 	lease_add_list(opinfo);
-	lb_add(lb);
-	return 0;
+	list_add(&new_lb->l_entry, &lease_table_list);
+	write_unlock(&lease_list_lock);
 }
 
 static void set_oplock_level(struct oplock_info *opinfo, int level,
@@ -1189,6 +1190,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 	int err = 0;
 	struct oplock_info *opinfo = NULL, *prev_opinfo = NULL;
 	struct ksmbd_inode *ci = fp->f_ci;
+	struct lease_table *new_lb = NULL;
 	bool prev_op_has_lease;
 	__le32 prev_op_state = 0;
 
@@ -1291,21 +1293,37 @@ set_lev:
 	set_oplock_level(opinfo, req_op_level, lctx);
 
 out:
-	opinfo_count_inc(fp);
-	opinfo_add(opinfo, fp);
-
+	/*
+	 * Set o_fp before any publication so that concurrent readers
+	 * (e.g. find_same_lease_key() on the lease list) that
+	 * dereference opinfo->o_fp don't hit a NULL pointer.
+	 *
+	 * Keep the original publication order so concurrent opens can
+	 * still observe the in-flight grant via ci->m_op_list, but make
+	 * everything after opinfo_add() no-fail by preallocating any new
+	 * lease_table first.
+	 */
+	opinfo->o_fp = fp;
 	if (opinfo->is_lease) {
-		err = add_lease_global_list(opinfo);
-		if (err)
+		new_lb = alloc_lease_table(opinfo);
+		if (!new_lb) {
+			err = -ENOMEM;
 			goto err_out;
+		}
 	}
 
+	opinfo_count_inc(fp);
+	opinfo_add(opinfo, fp);
+
+	if (opinfo->is_lease)
+		add_lease_global_list(opinfo, new_lb);
+
 	rcu_assign_pointer(fp->f_opinfo, opinfo);
-	opinfo->o_fp = fp;
 
 	return 0;
 err_out:
-	__free_opinfo(opinfo);
+	kfree(new_lb);
+	opinfo_put(opinfo);
 	return err;
 }
 
-- 
cgit v1.2.3


From 309b44ed684496ed3f9c5715d10b899338623512 Mon Sep 17 00:00:00 2001
From: Werner Kasselman <werner@verivus.com>
Date: Tue, 17 Mar 2026 07:55:37 +0000
Subject: ksmbd: fix memory leaks and NULL deref in smb2_lock()

smb2_lock() has three error handling issues after list_del() detaches
smb_lock from lock_list at no_check_cl:

1) If vfs_lock_file() returns an unexpected error in the non-UNLOCK
   path, goto out leaks smb_lock and its flock because the out:
   handler only iterates lock_list and rollback_list, neither of
   which contains the detached smb_lock.

2) If vfs_lock_file() returns -ENOENT in the UNLOCK path, goto out
   leaks smb_lock and flock for the same reason.  The error code
   returned to the dispatcher is also stale.

3) In the rollback path, smb_flock_init() can return NULL on
   allocation failure.  The result is dereferenced unconditionally,
   causing a kernel NULL pointer dereference.  Add a NULL check to
   prevent the crash and clean up the bookkeeping; the VFS lock
   itself cannot be rolled back without the allocation and will be
   released at file or connection teardown.

Fix cases 1 and 2 by hoisting the locks_free_lock()/kfree() to before
the if(!rc) check in the UNLOCK branch so all exit paths share one
free site, and by freeing smb_lock and flock before goto out in the
non-UNLOCK branch.  Propagate the correct error code in both cases.
Fix case 3 by wrapping the VFS unlock in an if(rlock) guard and adding
a NULL check for locks_free_lock(rlock) in the shared cleanup.

Found via call-graph analysis using sqry.

Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Suggested-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Werner Kasselman <werner@verivus.com>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 8fa780e8efd0..24f8d58493d0 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7592,14 +7592,15 @@ retry:
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:
 		if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) {
+			locks_free_lock(flock);
+			kfree(smb_lock);
 			if (!rc) {
 				ksmbd_debug(SMB, "File unlocked\n");
 			} else if (rc == -ENOENT) {
 				rsp->hdr.Status = STATUS_NOT_LOCKED;
+				err = rc;
 				goto out;
 			}
-			locks_free_lock(flock);
-			kfree(smb_lock);
 		} else {
 			if (rc == FILE_LOCK_DEFERRED) {
 				void **argv;
@@ -7668,6 +7669,9 @@ skip:
 				spin_unlock(&work->conn->llist_lock);
 				ksmbd_debug(SMB, "successful in taking lock\n");
 			} else {
+				locks_free_lock(flock);
+				kfree(smb_lock);
+				err = rc;
 				goto out;
 			}
 		}
@@ -7698,13 +7702,17 @@ out:
 		struct file_lock *rlock = NULL;
 
 		rlock = smb_flock_init(filp);
-		rlock->c.flc_type = F_UNLCK;
-		rlock->fl_start = smb_lock->start;
-		rlock->fl_end = smb_lock->end;
+		if (rlock) {
+			rlock->c.flc_type = F_UNLCK;
+			rlock->fl_start = smb_lock->start;
+			rlock->fl_end = smb_lock->end;
 
-		rc = vfs_lock_file(filp, F_SETLK, rlock, NULL);
-		if (rc)
-			pr_err("rollback unlock fail : %d\n", rc);
+			rc = vfs_lock_file(filp, F_SETLK, rlock, NULL);
+			if (rc)
+				pr_err("rollback unlock fail : %d\n", rc);
+		} else {
+			pr_err("rollback unlock alloc failed\n");
+		}
 
 		list_del(&smb_lock->llist);
 		spin_lock(&work->conn->llist_lock);
@@ -7714,7 +7722,8 @@ out:
 		spin_unlock(&work->conn->llist_lock);
 
 		locks_free_lock(smb_lock->fl);
-		locks_free_lock(rlock);
+		if (rlock)
+			locks_free_lock(rlock);
 		kfree(smb_lock);
 	}
 out2:
-- 
cgit v1.2.3


From 0e55f63dd08f09651d39e1b709a91705a8a0ddcb Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 13 Mar 2026 14:45:58 +0900
Subject: ksmbd: replace hardcoded hdr2_len with offsetof() in
 smb2_calc_max_out_buf_len()

After this commit (e2b76ab8b5c9 "ksmbd: add support for read compound"),
response buffer management was changed to use dynamic iov array.
In the new design, smb2_calc_max_out_buf_len() expects the second
argument (hdr2_len) to be the offset of ->Buffer field in the
response structure, not a hardcoded magic number.
Fix the remaining call sites to use the correct offsetof() value.

Cc: stable@vger.kernel.org
Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound")
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 24f8d58493d0..f5f1bf5f642e 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4452,8 +4452,9 @@ int smb2_query_dir(struct ksmbd_work *work)
 	d_info.wptr = (char *)rsp->Buffer;
 	d_info.rptr = (char *)rsp->Buffer;
 	d_info.out_buf_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_directory_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (d_info.out_buf_len < 0) {
 		rc = -EINVAL;
 		goto err_out;
@@ -4720,8 +4721,9 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp,
 	}
 
 	buf_free_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_info_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (buf_free_len < 0)
 		return -EINVAL;
 
@@ -5047,8 +5049,9 @@ static int get_file_stream_info(struct ksmbd_work *work,
 	file_info = (struct smb2_file_stream_info *)rsp->Buffer;
 
 	buf_free_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
+		smb2_calc_max_out_buf_len(work,
+				offsetof(struct smb2_query_info_rsp, Buffer),
+				le32_to_cpu(req->OutputBufferLength));
 	if (buf_free_len < 0)
 		goto out;
 
@@ -8206,8 +8209,9 @@ int smb2_ioctl(struct ksmbd_work *work)
 	buffer = (char *)req + le32_to_cpu(req->InputOffset);
 
 	cnt_code = le32_to_cpu(req->CtlCode);
-	ret = smb2_calc_max_out_buf_len(work, 48,
-					le32_to_cpu(req->MaxOutputResponse));
+	ret = smb2_calc_max_out_buf_len(work,
+			offsetof(struct smb2_ioctl_rsp, Buffer),
+			le32_to_cpu(req->MaxOutputResponse));
 	if (ret < 0) {
 		rsp->hdr.Status = STATUS_INVALID_PARAMETER;
 		goto out;
-- 
cgit v1.2.3


From 08441f10f4dc09fdeb64529953ac308abc79dd38 Mon Sep 17 00:00:00 2001
From: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Date: Mon, 16 Mar 2026 16:19:19 -0700
Subject: drm/i915/gmbus: fix spurious timeout on 512-byte burst reads

When reading exactly 512 bytes with burst read enabled, the
extra_byte_added path breaks out of the inner do-while without
decrementing len. The outer while(len) then re-enters and gmbus_wait()
times out since all data has been delivered. Decrement len before the
break so the outer loop terminates correctly.

Fixes: d5dc0f43f268 ("drm/i915/gmbus: Enable burst read")
Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patch.msgid.link/20260316231920.135438-2-samasth.norway.ananda@oracle.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 4ab0f09ee73fc853d00466682635f67c531f909c)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_gmbus.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index a7bce0c6a17e..264e6843bff1 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -496,8 +496,10 @@ gmbus_xfer_read_chunk(struct intel_display *display,
 
 		val = intel_de_read_fw(display, GMBUS3(display));
 		do {
-			if (extra_byte_added && len == 1)
+			if (extra_byte_added && len == 1) {
+				len--;
 				break;
+			}
 
 			*buf++ = val & 0xff;
 			val >>= 8;
-- 
cgit v1.2.3


From 6ad2a661ff0d3d94884947d2a593311ba46d34c2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 13 Mar 2026 13:07:40 +0200
Subject: drm/i915: Order OP vs. timeout correctly in __wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Put the barrier() before the OP so that anything we read out in
OP and check in COND will actually be read out after the timeout
has been evaluated.

Currently the only place where we use OP is __intel_wait_for_register(),
but the use there is precisely susceptible to this reordering, assuming
the ktime_*() stuff itself doesn't act as a sufficient barrier:

__intel_wait_for_register(...)
{
	...
	ret = __wait_for(reg_value = intel_uncore_read_notrace(...),
 			 (reg_value & mask) == value, ...);
	...
}

Cc: stable@vger.kernel.org
Fixes: 1c3c1dc66a96 ("drm/i915: Add compiler barrier to wait_for")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260313110740.24620-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit a464bace0482aa9a83e9aa7beefbaf44cd58e6cf)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_wait_util.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_wait_util.h b/drivers/gpu/drm/i915/i915_wait_util.h
index 7376898e3bf8..e1ed7921ec70 100644
--- a/drivers/gpu/drm/i915/i915_wait_util.h
+++ b/drivers/gpu/drm/i915/i915_wait_util.h
@@ -25,9 +25,9 @@
 	might_sleep();							\
 	for (;;) {							\
 		const bool expired__ = ktime_after(ktime_get_raw(), end__); \
-		OP;							\
 		/* Guarantee COND check prior to timeout */		\
 		barrier();						\
+		OP;							\
 		if (COND) {						\
 			ret__ = 0;					\
 			break;						\
-- 
cgit v1.2.3


From bfa71b7a9dc6b5b8af157686e03308291141d00c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 16 Mar 2026 18:39:51 +0200
Subject: drm/i915: Unlink NV12 planes earlier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

unlink_nv12_plane() will clobber parts of the plane state
potentially already set up by plane_atomic_check(), so we
must make sure not to call the two in the wrong order.
The problem happens when a plane previously selected as
a Y plane is now configured as a normal plane by user space.
plane_atomic_check() will first compute the proper plane
state based on the userspace request, and unlink_nv12_plane()
later clears some of the state.

This used to work on account of unlink_nv12_plane() skipping
the state clearing based on the plane visibility. But I removed
that check, thinking it was an impossible situation. Now when
that situation happens unlink_nv12_plane() will just WARN
and proceed to clobber the state.

Rather than reverting to the old way of doing things, I think
it's more clear if we unlink the NV12 planes before we even
compute the new plane state.

Cc: stable@vger.kernel.org
Reported-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Closes: https://lore.kernel.org/intel-gfx/20260212004852.1920270-1-khaled.almahallawy@intel.com/
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Fixes: 6a01df2f1b2a ("drm/i915: Remove pointless visible check in unlink_nv12_plane()")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260316163953.12905-2-ville.syrjala@linux.intel.com
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
(cherry picked from commit 017ecd04985573eeeb0745fa2c23896fb22ee0cc)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_plane.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_plane.c b/drivers/gpu/drm/i915/display/intel_plane.c
index e06a0618b4c6..076b9b356481 100644
--- a/drivers/gpu/drm/i915/display/intel_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_plane.c
@@ -436,11 +436,16 @@ void intel_plane_copy_hw_state(struct intel_plane_state *plane_state,
 		drm_framebuffer_get(plane_state->hw.fb);
 }
 
+static void unlink_nv12_plane(struct intel_crtc_state *crtc_state,
+			      struct intel_plane_state *plane_state);
+
 void intel_plane_set_invisible(struct intel_crtc_state *crtc_state,
 			       struct intel_plane_state *plane_state)
 {
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
+	unlink_nv12_plane(crtc_state, plane_state);
+
 	crtc_state->active_planes &= ~BIT(plane->id);
 	crtc_state->scaled_planes &= ~BIT(plane->id);
 	crtc_state->nv12_planes &= ~BIT(plane->id);
@@ -1513,6 +1518,9 @@ static void unlink_nv12_plane(struct intel_crtc_state *crtc_state,
 	struct intel_display *display = to_intel_display(plane_state);
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
+	if (!plane_state->planar_linked_plane)
+		return;
+
 	plane_state->planar_linked_plane = NULL;
 
 	if (!plane_state->is_y_plane)
@@ -1550,8 +1558,7 @@ static int icl_check_nv12_planes(struct intel_atomic_state *state,
 		if (plane->pipe != crtc->pipe)
 			continue;
 
-		if (plane_state->planar_linked_plane)
-			unlink_nv12_plane(crtc_state, plane_state);
+		unlink_nv12_plane(crtc_state, plane_state);
 	}
 
 	if (!crtc_state->nv12_planes)
-- 
cgit v1.2.3


From 710abda58055ed5eaa8958107633cc12a365c328 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Date: Wed, 18 Mar 2026 15:00:53 +0100
Subject: gpio: shared: call gpio_chip::of_xlate() if set

OF-based GPIO controller drivers may provide a translation function that
calculates the real chip offset from whatever devicetree sources
provide. We need to take this into account in the shared GPIO management
and call of_xlate() if it's provided and adjust the entry->offset we
initially set when scanning the tree.

To that end: modify the shared GPIO API to take the GPIO chip as
argument on setup (to avoid having to rcu_dereference() it from the GPIO
device) and protect the access to entry->offset with the existing lock.

Fixes: a060b8c511ab ("gpiolib: implement low-level, shared GPIO support")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Closes: https://lore.kernel.org/all/921ba8ce-b18e-4a99-966d-c763d22081e2@nvidia.com/
Reviewed-by: Linus Walleij <linusw@kernel.org>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Link: https://patch.msgid.link/20260318-gpio-shared-xlate-v2-1-0ce34c707e81@oss.qualcomm.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib-shared.c | 27 ++++++++++++++++++++++++++-
 drivers/gpio/gpiolib-shared.h |  4 ++--
 drivers/gpio/gpiolib.c        |  2 +-
 3 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c
index 17a7128b6bd9..3a8db9bf456d 100644
--- a/drivers/gpio/gpiolib-shared.c
+++ b/drivers/gpio/gpiolib-shared.c
@@ -506,8 +506,9 @@ static void gpio_shared_remove_adev(struct auxiliary_device *adev)
 	auxiliary_device_uninit(adev);
 }
 
-int gpio_device_setup_shared(struct gpio_device *gdev)
+int gpiochip_setup_shared(struct gpio_chip *gc)
 {
+	struct gpio_device *gdev = gc->gpiodev;
 	struct gpio_shared_entry *entry;
 	struct gpio_shared_ref *ref;
 	struct gpio_desc *desc;
@@ -532,12 +533,34 @@ int gpio_device_setup_shared(struct gpio_device *gdev)
 	 * exposing shared pins. Find them and create the proxy devices.
 	 */
 	list_for_each_entry(entry, &gpio_shared_list, list) {
+		guard(mutex)(&entry->lock);
+
 		if (!device_match_fwnode(&gdev->dev, entry->fwnode))
 			continue;
 
 		if (list_count_nodes(&entry->refs) <= 1)
 			continue;
 
+#if IS_ENABLED(CONFIG_OF)
+		if (is_of_node(entry->fwnode) && gc->of_xlate) {
+			/*
+			 * This is the earliest that we can tranlate the
+			 * devicetree offset to the chip offset.
+			 */
+			struct of_phandle_args gpiospec = { };
+
+			gpiospec.np = to_of_node(entry->fwnode);
+			gpiospec.args_count = 2;
+			gpiospec.args[0] = entry->offset;
+
+			ret = gc->of_xlate(gc, &gpiospec, NULL);
+			if (ret < 0)
+				return ret;
+
+			entry->offset = ret;
+		}
+#endif /* CONFIG_OF */
+
 		desc = &gdev->descs[entry->offset];
 
 		__set_bit(GPIOD_FLAG_SHARED, &desc->flags);
@@ -575,6 +598,8 @@ void gpio_device_teardown_shared(struct gpio_device *gdev)
 	struct gpio_shared_ref *ref;
 
 	list_for_each_entry(entry, &gpio_shared_list, list) {
+		guard(mutex)(&entry->lock);
+
 		if (!device_match_fwnode(&gdev->dev, entry->fwnode))
 			continue;
 
diff --git a/drivers/gpio/gpiolib-shared.h b/drivers/gpio/gpiolib-shared.h
index 40568ef7364c..e11e260e1f59 100644
--- a/drivers/gpio/gpiolib-shared.h
+++ b/drivers/gpio/gpiolib-shared.h
@@ -14,14 +14,14 @@ struct device;
 
 #if IS_ENABLED(CONFIG_GPIO_SHARED)
 
-int gpio_device_setup_shared(struct gpio_device *gdev);
+int gpiochip_setup_shared(struct gpio_chip *gc);
 void gpio_device_teardown_shared(struct gpio_device *gdev);
 int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id,
 				 unsigned long lflags);
 
 #else
 
-static inline int gpio_device_setup_shared(struct gpio_device *gdev)
+static inline int gpiochip_setup_shared(struct gpio_chip *gc)
 {
 	return 0;
 }
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index f52d2d3efac4..d82fcf3fb458 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1211,7 +1211,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	if (ret)
 		goto err_remove_irqchip_mask;
 
-	ret = gpio_device_setup_shared(gdev);
+	ret = gpiochip_setup_shared(gc);
 	if (ret)
 		goto err_remove_irqchip;
 
-- 
cgit v1.2.3


From ec42a3a90ae9ae64b16d01a2e5d32ec0865ca8cf Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Date: Wed, 18 Mar 2026 15:00:54 +0100
Subject: gpio: shared: handle pins shared by child nodes of devices

Shared GPIOs may be assigned to child nodes of device nodes which don't
themselves bind to any struct device. We need to pass the firmware node
that is the actual consumer to gpiolib-shared and compare against it
instead of unconditionally using the fwnode of the consumer device.

Fixes: a060b8c511ab ("gpiolib: implement low-level, shared GPIO support")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Closes: https://lore.kernel.org/all/921ba8ce-b18e-4a99-966d-c763d22081e2@nvidia.com/
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Link: https://patch.msgid.link/20260318-gpio-shared-xlate-v2-2-0ce34c707e81@oss.qualcomm.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib-shared.c | 6 +++---
 drivers/gpio/gpiolib-shared.h | 7 +++++--
 drivers/gpio/gpiolib.c        | 4 ++--
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c
index 3a8db9bf456d..e257212fa5e3 100644
--- a/drivers/gpio/gpiolib-shared.c
+++ b/drivers/gpio/gpiolib-shared.c
@@ -443,8 +443,8 @@ static bool gpio_shared_dev_is_reset_gpio(struct device *consumer,
 }
 #endif /* CONFIG_RESET_GPIO */
 
-int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id,
-				 unsigned long lflags)
+int gpio_shared_add_proxy_lookup(struct device *consumer, struct fwnode_handle *fwnode,
+				 const char *con_id, unsigned long lflags)
 {
 	const char *dev_id = dev_name(consumer);
 	struct gpiod_lookup_table *lookup;
@@ -458,7 +458,7 @@ int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id,
 			if (!ref->fwnode && device_is_compatible(consumer, "reset-gpio")) {
 				if (!gpio_shared_dev_is_reset_gpio(consumer, entry, ref))
 					continue;
-			} else if (!device_match_fwnode(consumer, ref->fwnode)) {
+			} else if (fwnode != ref->fwnode) {
 				continue;
 			}
 
diff --git a/drivers/gpio/gpiolib-shared.h b/drivers/gpio/gpiolib-shared.h
index e11e260e1f59..15e72a8dcdb1 100644
--- a/drivers/gpio/gpiolib-shared.h
+++ b/drivers/gpio/gpiolib-shared.h
@@ -11,13 +11,15 @@
 struct gpio_device;
 struct gpio_desc;
 struct device;
+struct fwnode_handle;
 
 #if IS_ENABLED(CONFIG_GPIO_SHARED)
 
 int gpiochip_setup_shared(struct gpio_chip *gc);
 void gpio_device_teardown_shared(struct gpio_device *gdev);
-int gpio_shared_add_proxy_lookup(struct device *consumer, const char *con_id,
-				 unsigned long lflags);
+int gpio_shared_add_proxy_lookup(struct device *consumer,
+				 struct fwnode_handle *fwnode,
+				 const char *con_id, unsigned long lflags);
 
 #else
 
@@ -29,6 +31,7 @@ static inline int gpiochip_setup_shared(struct gpio_chip *gc)
 static inline void gpio_device_teardown_shared(struct gpio_device *gdev) { }
 
 static inline int gpio_shared_add_proxy_lookup(struct device *consumer,
+					       struct fwnode_handle *fwnode,
 					       const char *con_id,
 					       unsigned long lflags)
 {
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d82fcf3fb458..300de30fd920 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -4714,8 +4714,8 @@ struct gpio_desc *gpiod_find_and_request(struct device *consumer,
 			 * lookup table for the proxy device as previously
 			 * we only knew the consumer's fwnode.
 			 */
-			ret = gpio_shared_add_proxy_lookup(consumer, con_id,
-							   lookupflags);
+			ret = gpio_shared_add_proxy_lookup(consumer, fwnode,
+							   con_id, lookupflags);
 			if (ret)
 				return ERR_PTR(ret);
 
-- 
cgit v1.2.3


From e942498385bf80f4d6d075b47174035545eb6a2e Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 17 Mar 2026 09:51:52 +0800
Subject: xfs: only assert new size for datafork during truncate extents

The assertion functions properly because we currently only truncate the
attr to a zero size. Any other new size of the attr is not preempted.
Make this assertion is specific to the datafork, preparing for
subsequent patches to truncate the attribute to a non-zero size.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Long Li <leo.lilong@huawei.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_inode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 50c0404f9064..beaa26ec62da 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1048,7 +1048,8 @@ xfs_itruncate_extents_flags(
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	if (icount_read(VFS_I(ip)))
 		xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
-	ASSERT(new_size <= XFS_ISIZE(ip));
+	if (whichfork == XFS_DATA_FORK)
+		ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
 	ASSERT(ip->i_itemp->ili_lock_flags == 0);
-- 
cgit v1.2.3


From ce4e789cf3561c9fac73cc24445bfed9ea0c514b Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 17 Mar 2026 09:51:53 +0800
Subject: xfs: factor out xfs_attr3_node_entry_remove

Factor out wrapper xfs_attr3_node_entry_remove function, which
exported for external use.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Long Li <leo.lilong@huawei.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_da_btree.c | 53 +++++++++++++++++++++++++++++++++++---------
 fs/xfs/libxfs/xfs_da_btree.h |  2 ++
 2 files changed, 44 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 09d4c17b3e7b..ad801b7bd2dd 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1506,21 +1506,20 @@ xfs_da3_fixhashpath(
 }
 
 /*
- * Remove an entry from an intermediate node.
+ * Internal implementation to remove an entry from an intermediate node.
  */
 STATIC void
-xfs_da3_node_remove(
-	struct xfs_da_state	*state,
-	struct xfs_da_state_blk	*drop_blk)
+__xfs_da3_node_remove(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_da_geometry  *geo,
+	struct xfs_da_state_blk *drop_blk)
 {
 	struct xfs_da_intnode	*node;
 	struct xfs_da3_icnode_hdr nodehdr;
 	struct xfs_da_node_entry *btree;
 	int			index;
 	int			tmp;
-	struct xfs_inode	*dp = state->args->dp;
-
-	trace_xfs_da_node_remove(state->args);
 
 	node = drop_blk->bp->b_addr;
 	xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr, node);
@@ -1536,17 +1535,17 @@ xfs_da3_node_remove(
 		tmp  = nodehdr.count - index - 1;
 		tmp *= (uint)sizeof(xfs_da_node_entry_t);
 		memmove(&btree[index], &btree[index + 1], tmp);
-		xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+		xfs_trans_log_buf(tp, drop_blk->bp,
 		    XFS_DA_LOGRANGE(node, &btree[index], tmp));
 		index = nodehdr.count - 1;
 	}
 	memset(&btree[index], 0, sizeof(xfs_da_node_entry_t));
-	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
+	xfs_trans_log_buf(tp, drop_blk->bp,
 	    XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index])));
 	nodehdr.count -= 1;
 	xfs_da3_node_hdr_to_disk(dp->i_mount, node, &nodehdr);
-	xfs_trans_log_buf(state->args->trans, drop_blk->bp,
-	    XFS_DA_LOGRANGE(node, &node->hdr, state->args->geo->node_hdr_size));
+	xfs_trans_log_buf(tp, drop_blk->bp,
+	    XFS_DA_LOGRANGE(node, &node->hdr, geo->node_hdr_size));
 
 	/*
 	 * Copy the last hash value from the block to propagate upwards.
@@ -1554,6 +1553,38 @@ xfs_da3_node_remove(
 	drop_blk->hashval = be32_to_cpu(btree[index - 1].hashval);
 }
 
+/*
+ * Remove an entry from an intermediate node.
+ */
+STATIC void
+xfs_da3_node_remove(
+	struct xfs_da_state	*state,
+	struct xfs_da_state_blk	*drop_blk)
+{
+	trace_xfs_da_node_remove(state->args);
+
+	__xfs_da3_node_remove(state->args->trans, state->args->dp,
+			state->args->geo, drop_blk);
+}
+
+/*
+ * Remove an entry from an intermediate attr node at the specified index.
+ */
+void
+xfs_attr3_node_entry_remove(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_buf		*bp,
+	int			index)
+{
+	struct xfs_da_state_blk blk = {
+		.index		= index,
+		.bp		= bp,
+	};
+
+	__xfs_da3_node_remove(tp, dp, dp->i_mount->m_attr_geo, &blk);
+}
+
 /*
  * Unbalance the elements between two intermediate nodes,
  * move all Btree elements from one node into another.
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 354d5d65043e..afcf2d3c7a21 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -184,6 +184,8 @@ int	xfs_da3_split(xfs_da_state_t *state);
 int	xfs_da3_join(xfs_da_state_t *state);
 void	xfs_da3_fixhashpath(struct xfs_da_state *state,
 			    struct xfs_da_state_path *path_to_to_fix);
+void	xfs_attr3_node_entry_remove(struct xfs_trans *tp, struct xfs_inode *dp,
+			    struct xfs_buf *bp, int index);
 
 /*
  * Routines used for finding things in the Btree.
-- 
cgit v1.2.3


From e65bb55d7f8c2041c8fdb73cd29b0b4cad4ed847 Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 17 Mar 2026 09:51:54 +0800
Subject: xfs: factor out xfs_attr3_leaf_init

Factor out wrapper xfs_attr3_leaf_init function, which exported for
external use.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Long Li <leo.lilong@huawei.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_leaf.c | 22 ++++++++++++++++++++++
 fs/xfs/libxfs/xfs_attr_leaf.h |  3 +++
 2 files changed, 25 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 47f48ae555c0..2b78041e8672 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -1415,6 +1415,28 @@ xfs_attr3_leaf_create(
 	return 0;
 }
 
+/*
+ * Reinitialize an existing attr fork block as an empty leaf, and attach
+ * the buffer to tp.
+ */
+int
+xfs_attr3_leaf_init(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	xfs_dablk_t		blkno)
+{
+	struct xfs_buf		*bp = NULL;
+	struct xfs_da_args	args = {
+		.trans		= tp,
+		.dp		= dp,
+		.owner		= dp->i_ino,
+		.geo		= dp->i_mount->m_attr_geo,
+	};
+
+	ASSERT(tp != NULL);
+
+	return xfs_attr3_leaf_create(&args, blkno, &bp);
+}
 /*
  * Split the leaf node, rebalance, then add the new entry.
  *
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index aca46da2bc50..72639efe6ac3 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -87,6 +87,9 @@ int	xfs_attr3_leaf_list_int(struct xfs_buf *bp,
 /*
  * Routines used for shrinking the Btree.
  */
+
+int	xfs_attr3_leaf_init(struct xfs_trans *tp, struct xfs_inode *dp,
+				xfs_dablk_t blkno);
 int	xfs_attr3_leaf_toosmall(struct xfs_da_state *state, int *retval);
 void	xfs_attr3_leaf_unbalance(struct xfs_da_state *state,
 				       struct xfs_da_state_blk *drop_blk,
-- 
cgit v1.2.3


From b854e1c4eff3473b6d3a9ae74129ac5c48bc0b61 Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Tue, 17 Mar 2026 09:51:55 +0800
Subject: xfs: close crash window in attr dabtree inactivation

When inactivating an inode with node-format extended attributes,
xfs_attr3_node_inactive() invalidates all child leaf/node blocks via
xfs_trans_binval(), but intentionally does not remove the corresponding
entries from their parent node blocks.  The implicit assumption is that
xfs_attr_inactive() will truncate the entire attr fork to zero extents
afterwards, so log recovery will never reach the root node and follow
those stale pointers.

However, if a log shutdown occurs after the leaf/node block cancellations
commit but before the attr bmap truncation commits, this assumption
breaks.  Recovery replays the attr bmap intact (the inode still has
attr fork extents), but suppresses replay of all cancelled leaf/node
blocks, maybe leaving them as stale data on disk.  On the next mount,
xlog_recover_process_iunlinks() retries inactivation and attempts to
read the root node via the attr bmap. If the root node was not replayed,
reading the unreplayed root block triggers a metadata verification
failure immediately; if it was replayed, following its child pointers
to unreplayed child blocks triggers the same failure:

 XFS (pmem0): Metadata corruption detected at
 xfs_da3_node_read_verify+0x53/0x220, xfs_da3_node block 0x78
 XFS (pmem0): Unmount and run xfs_repair
 XFS (pmem0): First 128 bytes of corrupted metadata buffer:
 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000050: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000060: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 00000070: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 XFS (pmem0): metadata I/O error in "xfs_da_read_buf+0x104/0x190" at daddr 0x78 len 8 error 117

Fix this in two places:

In xfs_attr3_node_inactive(), after calling xfs_trans_binval() on a
child block, immediately remove the entry that references it from the
parent node in the same transaction.  This eliminates the window where
the parent holds a pointer to a cancelled block.  Once all children are
removed, the now-empty root node is converted to a leaf block within the
same transaction. This node-to-leaf conversion is necessary for crash
safety. If the system shutdown after the empty node is written to the
log but before the second-phase bmap truncation commits, log recovery
will attempt to verify the root block on disk. xfs_da3_node_verify()
does not permit a node block with count == 0; such a block will fail
verification and trigger a metadata corruption shutdown. on the other
hand, leaf blocks are allowed to have this transient state.

In xfs_attr_inactive(), split the attr fork truncation into two explicit
phases.  First, truncate all extents beyond the root block (the child
extents whose parent references have already been removed above).
Second, invalidate the root block and truncate the attr bmap to zero in
a single transaction.  The two operations in the second phase must be
atomic: as long as the attr bmap has any non-zero length, recovery can
follow it to the root block, so the root block invalidation must commit
together with the bmap-to-zero truncation.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_attr_inactive.c | 95 +++++++++++++++++++++++++++-------------------
 1 file changed, 57 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 92331991f9fd..a5b69c0fbfd0 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -140,7 +140,7 @@ xfs_attr3_node_inactive(
 	xfs_daddr_t		parent_blkno, child_blkno;
 	struct xfs_buf		*child_bp;
 	struct xfs_da3_icnode_hdr ichdr;
-	int			error, i;
+	int			error;
 
 	/*
 	 * Since this code is recursive (gasp!) we must protect ourselves.
@@ -152,7 +152,7 @@ xfs_attr3_node_inactive(
 		return -EFSCORRUPTED;
 	}
 
-	xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr);
+	xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr);
 	parent_blkno = xfs_buf_daddr(bp);
 	if (!ichdr.count) {
 		xfs_trans_brelse(*trans, bp);
@@ -167,7 +167,7 @@ xfs_attr3_node_inactive(
 	 * over the leaves removing all of them.  If this is higher up
 	 * in the tree, recurse downward.
 	 */
-	for (i = 0; i < ichdr.count; i++) {
+	while (ichdr.count > 0) {
 		/*
 		 * Read the subsidiary block to see what we have to work with.
 		 * Don't do this in a transaction.  This is a depth-first
@@ -218,29 +218,32 @@ xfs_attr3_node_inactive(
 		xfs_trans_binval(*trans, child_bp);
 		child_bp = NULL;
 
+		error = xfs_da3_node_read_mapped(*trans, dp,
+				parent_blkno, &bp, XFS_ATTR_FORK);
+		if (error)
+			return error;
+
 		/*
-		 * If we're not done, re-read the parent to get the next
-		 * child block number.
+		 * Remove entry from parent node, prevents being indexed to.
 		 */
-		if (i + 1 < ichdr.count) {
-			struct xfs_da3_icnode_hdr phdr;
+		xfs_attr3_node_entry_remove(*trans, dp, bp, 0);
+
+		xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr);
+		bp = NULL;
 
-			error = xfs_da3_node_read_mapped(*trans, dp,
-					parent_blkno, &bp, XFS_ATTR_FORK);
+		if (ichdr.count > 0) {
+			/*
+			 * If we're not done, get the next child block number.
+			 */
+			child_fsb = be32_to_cpu(ichdr.btree[0].before);
+
+			/*
+			 * Atomically commit the whole invalidate stuff.
+			 */
+			error = xfs_trans_roll_inode(trans, dp);
 			if (error)
 				return error;
-			xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr,
-						  bp->b_addr);
-			child_fsb = be32_to_cpu(phdr.btree[i + 1].before);
-			xfs_trans_brelse(*trans, bp);
-			bp = NULL;
 		}
-		/*
-		 * Atomically commit the whole invalidate stuff.
-		 */
-		error = xfs_trans_roll_inode(trans, dp);
-		if (error)
-			return  error;
 	}
 
 	return 0;
@@ -257,10 +260,8 @@ xfs_attr3_root_inactive(
 	struct xfs_trans	**trans,
 	struct xfs_inode	*dp)
 {
-	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_blkinfo	*info;
 	struct xfs_buf		*bp;
-	xfs_daddr_t		blkno;
 	int			error;
 
 	/*
@@ -272,7 +273,6 @@ xfs_attr3_root_inactive(
 	error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK);
 	if (error)
 		return error;
-	blkno = xfs_buf_daddr(bp);
 
 	/*
 	 * Invalidate the tree, even if the "tree" is only a single leaf block.
@@ -283,10 +283,26 @@ xfs_attr3_root_inactive(
 	case cpu_to_be16(XFS_DA_NODE_MAGIC):
 	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
 		error = xfs_attr3_node_inactive(trans, dp, bp, 1);
+		/*
+		 * Empty root node block are not allowed, convert it to leaf.
+		 */
+		if (!error)
+			error = xfs_attr3_leaf_init(*trans, dp, 0);
+		if (!error)
+			error = xfs_trans_roll_inode(trans, dp);
 		break;
 	case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
 	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
 		error = xfs_attr3_leaf_inactive(trans, dp, bp);
+		/*
+		 * Reinit the leaf before truncating extents so that a crash
+		 * mid-truncation leaves an empty leaf rather than one with
+		 * entries that may reference freed remote value blocks.
+		 */
+		if (!error)
+			error = xfs_attr3_leaf_init(*trans, dp, 0);
+		if (!error)
+			error = xfs_trans_roll_inode(trans, dp);
 		break;
 	default:
 		xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
@@ -295,21 +311,6 @@ xfs_attr3_root_inactive(
 		xfs_trans_brelse(*trans, bp);
 		break;
 	}
-	if (error)
-		return error;
-
-	/*
-	 * Invalidate the incore copy of the root block.
-	 */
-	error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno,
-			XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp);
-	if (error)
-		return error;
-	xfs_trans_binval(*trans, bp);	/* remove from cache */
-	/*
-	 * Commit the invalidate and start the next transaction.
-	 */
-	error = xfs_trans_roll_inode(trans, dp);
 
 	return error;
 }
@@ -328,6 +329,7 @@ xfs_attr_inactive(
 {
 	struct xfs_trans	*trans;
 	struct xfs_mount	*mp;
+	struct xfs_buf          *bp;
 	int			lock_mode = XFS_ILOCK_SHARED;
 	int			error = 0;
 
@@ -363,10 +365,27 @@ xfs_attr_inactive(
 	 * removal below.
 	 */
 	if (dp->i_af.if_nextents > 0) {
+		/*
+		 * Invalidate and truncate all blocks but leave the root block.
+		 */
 		error = xfs_attr3_root_inactive(&trans, dp);
 		if (error)
 			goto out_cancel;
 
+		error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK,
+				XFS_FSB_TO_B(mp, mp->m_attr_geo->fsbcount));
+		if (error)
+			goto out_cancel;
+
+		/*
+		 * Invalidate and truncate the root block and ensure that the
+		 * operation is completed within a single transaction.
+		 */
+		error = xfs_da_get_buf(trans, dp, 0, &bp, XFS_ATTR_FORK);
+		if (error)
+			goto out_cancel;
+
+		xfs_trans_binval(trans, bp);
 		error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
 		if (error)
 			goto out_cancel;
-- 
cgit v1.2.3


From d72f2084e30966097c8eae762e31986a33c3c0ae Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Fri, 20 Mar 2026 10:11:29 +0800
Subject: xfs: fix ri_total validation in xlog_recover_attri_commit_pass2

The ri_total checks for SET/REPLACE operations are hardcoded to 3,
but xfs_attri_item_size() only emits a value iovec when value_len > 0,
so ri_total is 2 when value_len == 0.

For PPTR_SET/PPTR_REMOVE/PPTR_REPLACE, value_len is validated by
xfs_attri_validate() to be exactly sizeof(struct xfs_parent_rec) and
is never zero, so their hardcoded checks remain correct.

This problem may cause log recovery failures. The following script can be
used to reproduce the problem:

 #!/bin/bash
 mkfs.xfs -f /dev/sda
 mount /dev/sda /mnt/test/
 touch /mnt/test/file
 for i in {1..200}; do
         attr -s "user.attr_$i" -V "value_$i" /mnt/test/file > /dev/null
 done
 echo 1 > /sys/fs/xfs/debug/larp
 echo 1 > /sys/fs/xfs/sda/errortag/larp
 attr -s "user.zero" -V "" /mnt/test/file
 echo 0 > /sys/fs/xfs/sda/errortag/larp
 umount /mnt/test
 mount /dev/sda /mnt/test/  # mount failed

Fix this by deriving the expected count dynamically as "2 + !!value_len"
for SET/REPLACE operations.

Cc: stable@vger.kernel.org # v6.9
Fixes: ad206ae50eca ("xfs: check opcode and iovec count match in xlog_recover_attri_commit_pass2")
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_attr_item.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 354472bf45f1..83d09635b200 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -1047,8 +1047,8 @@ xlog_recover_attri_commit_pass2(
 		break;
 	case XFS_ATTRI_OP_FLAGS_SET:
 	case XFS_ATTRI_OP_FLAGS_REPLACE:
-		/* Log item, attr name, attr value */
-		if (item->ri_total != 3) {
+		/* Log item, attr name, optional attr value */
+		if (item->ri_total != 2 + !!attri_formatp->alfi_value_len) {
 			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
 					     attri_formatp, len);
 			return -EFSCORRUPTED;
-- 
cgit v1.2.3


From c6c56ff975f046be25f527231a239e37920aca5e Mon Sep 17 00:00:00 2001
From: Long Li <leo.lilong@huawei.com>
Date: Fri, 20 Mar 2026 10:11:30 +0800
Subject: xfs: remove redundant validation in xlog_recover_attri_commit_pass2

Remove the redundant post-parse validation switch. By the time that
block is reached, xfs_attri_validate() has already guaranteed all name
lengths are non-zero via xfs_attri_validate_namelen(), and
xfs_attri_validate_name_iovec() has already returned -EFSCORRUPTED for
NULL names. For the REMOVE case, attr_value and value_len are
structurally guaranteed to be NULL/zero because the parsing loop only
populates them when value_len != 0. All checks in that switch are
therefore dead code.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_attr_item.c | 46 ----------------------------------------------
 1 file changed, 46 deletions(-)

diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 83d09635b200..82324f42537b 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -1132,52 +1132,6 @@ xlog_recover_attri_commit_pass2(
 		return -EFSCORRUPTED;
 	}
 
-	switch (op) {
-	case XFS_ATTRI_OP_FLAGS_REMOVE:
-		/* Regular remove operations operate only on names. */
-		if (attr_value != NULL || value_len != 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		fallthrough;
-	case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE:
-	case XFS_ATTRI_OP_FLAGS_PPTR_SET:
-	case XFS_ATTRI_OP_FLAGS_SET:
-	case XFS_ATTRI_OP_FLAGS_REPLACE:
-		/*
-		 * Regular xattr set/remove/replace operations require a name
-		 * and do not take a newname.  Values are optional for set and
-		 * replace.
-		 *
-		 * Name-value set/remove operations must have a name, do not
-		 * take a newname, and can take a value.
-		 */
-		if (attr_name == NULL || name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		break;
-	case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE:
-		/*
-		 * Name-value replace operations require the caller to
-		 * specify the old and new names and values explicitly.
-		 * Values are optional.
-		 */
-		if (attr_name == NULL || name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		if (attr_new_name == NULL || new_name_len == 0) {
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
-					     attri_formatp, len);
-			return -EFSCORRUPTED;
-		}
-		break;
-	}
-
 	/*
 	 * Memory alloc failure will cause replay to abort.  We attach the
 	 * name/value buffer to the recovered incore log item and drop our
-- 
cgit v1.2.3


From 8de4e0f44c638c66cdc5eeb4d5ab9acd61c31e4f Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Fri, 20 Mar 2026 22:56:38 +0800
Subject: gpio: qixis-fpga: Fix error handling for devm_regmap_init_mmio()

devm_regmap_init_mmio() returns an ERR_PTR() on failure, not NULL.
The original code checked for NULL which would never trigger on error,
potentially leading to an invalid pointer dereference.
Use IS_ERR() and PTR_ERR() to properly handle the error case.

Fixes: e88500247dc3 ("gpio: add QIXIS FPGA GPIO controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260320-qixis-v1-1-a8efc22e8945@gmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpio-qixis-fpga.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-qixis-fpga.c b/drivers/gpio/gpio-qixis-fpga.c
index 6e67f43ac0bd..3ced47db1521 100644
--- a/drivers/gpio/gpio-qixis-fpga.c
+++ b/drivers/gpio/gpio-qixis-fpga.c
@@ -60,8 +60,8 @@ static int qixis_cpld_gpio_probe(struct platform_device *pdev)
 			return PTR_ERR(reg);
 
 		regmap = devm_regmap_init_mmio(&pdev->dev, reg, &regmap_config_8r_8v);
-		if (!regmap)
-			return -ENODEV;
+		if (IS_ERR(regmap))
+			return PTR_ERR(regmap);
 
 		/* In this case, the offset of our register is 0 inside the
 		 * regmap area that we just created.
-- 
cgit v1.2.3


From 907150bbe566e23714a25d7bcb910f236c3c44c0 Mon Sep 17 00:00:00 2001
From: Mihai Sain <mihai.sain@microchip.com>
Date: Mon, 9 Feb 2026 11:07:35 +0200
Subject: ARM: dts: microchip: sam9x7: fix gpio-lines count for pioB

The pioB controller on the SAM9X7 SoC actually supports 27 GPIO lines.
The previous value of 26 was incorrect, leading to the last pin being
unavailable for use by the GPIO subsystem.
Update the #gpio-lines property to reflect
the correct hardware specification.

Fixes: 41af45af8bc3 ("ARM: dts: at91: sam9x7: add device tree for SoC")
Signed-off-by: Mihai Sain <mihai.sain@microchip.com>
Link: https://lore.kernel.org/r/20260209090735.2016-1-mihai.sain@microchip.com
Signed-off-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
---
 arch/arm/boot/dts/microchip/sam9x7.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/microchip/sam9x7.dtsi b/arch/arm/boot/dts/microchip/sam9x7.dtsi
index 46dacbbd201d..d242d7a934d0 100644
--- a/arch/arm/boot/dts/microchip/sam9x7.dtsi
+++ b/arch/arm/boot/dts/microchip/sam9x7.dtsi
@@ -1226,7 +1226,7 @@
 				interrupt-controller;
 				#gpio-cells = <2>;
 				gpio-controller;
-				#gpio-lines = <26>;
+				#gpio-lines = <27>;
 				clocks = <&pmc PMC_TYPE_PERIPHERAL 3>;
 			};
 
-- 
cgit v1.2.3


From fbffb8c7c7bb4d38e9f65e0bee446685011de5d8 Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Sat, 21 Mar 2026 15:42:40 +0800
Subject: reset: gpio: fix double free in reset_add_gpio_aux_device() error
 path

When __auxiliary_device_add() fails, reset_add_gpio_aux_device()
calls auxiliary_device_uninit(adev).

The device release callback reset_gpio_aux_device_release() frees
adev, but the current error path then calls kfree(adev) again,
causing a double free.

Keep kfree(adev) for the auxiliary_device_init() failure path, but
avoid freeing adev after auxiliary_device_uninit().

Fixes: 5fc4e4cf7a22 ("reset: gpio: use software nodes to setup the GPIO lookup")
Cc: stable@vger.kernel.org
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index fceec45c8afc..352c2360603b 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -856,7 +856,6 @@ static int reset_add_gpio_aux_device(struct device *parent,
 	ret = __auxiliary_device_add(adev, "reset");
 	if (ret) {
 		auxiliary_device_uninit(adev);
-		kfree(adev);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From a0e0c2f8c5f32b675f58e25a9338283cedb5ad2b Mon Sep 17 00:00:00 2001
From: Yixun Lan <dlan@kernel.org>
Date: Fri, 20 Mar 2026 11:06:17 +0000
Subject: reset: spacemit: k3: Decouple composite reset lines

Instead of grouping several different reset lines into one composite
reset, decouple them to individual ones which make it more aligned
with underlying hardware. And for DWC USB driver, it will match well
with the number of the reset property in the DT bindings.

The DWC3 USB host controller in K3 SoC has three reset lines - AHB, VCC,
PHY. The PCIe controller also has three reset lines - DBI, Slave, Master.
Also three reset lines each for UCIE and RCPU block.

As an agreement with maintainer, the reset IDs has been rearranged as
contiguous number but keep most part unchanged to avoid break patches
which already sent to mailing list. The changes of DT binding header file
and reset driver are merged together as one single commit to avoid
git-bisect breakage.

Fixes: 938ce3b16582 ("reset: spacemit: Add SpacemiT K3 reset driver")
Fixes: 216e0a5e98e5 ("dt-bindings: soc: spacemit: Add K3 reset support and IDs")
Signed-off-by: Yixun Lan <dlan@kernel.org>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/spacemit/reset-spacemit-k3.c     | 60 +++++++++++++++-----------
 include/dt-bindings/reset/spacemit,k3-resets.h | 48 +++++++++++++++------
 2 files changed, 72 insertions(+), 36 deletions(-)

diff --git a/drivers/reset/spacemit/reset-spacemit-k3.c b/drivers/reset/spacemit/reset-spacemit-k3.c
index e9e32e4c1ba5..9841f5e057b2 100644
--- a/drivers/reset/spacemit/reset-spacemit-k3.c
+++ b/drivers/reset/spacemit/reset-spacemit-k3.c
@@ -112,16 +112,21 @@ static const struct ccu_reset_data k3_apmu_resets[] = {
 	[RESET_APMU_SDH0]	= RESET_DATA(APMU_SDH0_CLK_RES_CTRL,	0, BIT(1)),
 	[RESET_APMU_SDH1]	= RESET_DATA(APMU_SDH1_CLK_RES_CTRL,	0, BIT(1)),
 	[RESET_APMU_SDH2]	= RESET_DATA(APMU_SDH2_CLK_RES_CTRL,	0, BIT(1)),
-	[RESET_APMU_USB2]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0,
-				BIT(1)|BIT(2)|BIT(3)),
-	[RESET_APMU_USB3_PORTA]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0,
-				BIT(5)|BIT(6)|BIT(7)),
-	[RESET_APMU_USB3_PORTB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0,
-				BIT(9)|BIT(10)|BIT(11)),
-	[RESET_APMU_USB3_PORTC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0,
-				BIT(13)|BIT(14)|BIT(15)),
-	[RESET_APMU_USB3_PORTD]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0,
-				BIT(17)|BIT(18)|BIT(19)),
+	[RESET_APMU_USB2_AHB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(1)),
+	[RESET_APMU_USB2_VCC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(2)),
+	[RESET_APMU_USB2_PHY]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(3)),
+	[RESET_APMU_USB3_A_AHB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(5)),
+	[RESET_APMU_USB3_A_VCC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(6)),
+	[RESET_APMU_USB3_A_PHY]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(7)),
+	[RESET_APMU_USB3_B_AHB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(9)),
+	[RESET_APMU_USB3_B_VCC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(10)),
+	[RESET_APMU_USB3_B_PHY]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(11)),
+	[RESET_APMU_USB3_C_AHB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(13)),
+	[RESET_APMU_USB3_C_VCC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(14)),
+	[RESET_APMU_USB3_C_PHY]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(15)),
+	[RESET_APMU_USB3_D_AHB]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(17)),
+	[RESET_APMU_USB3_D_VCC]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(18)),
+	[RESET_APMU_USB3_D_PHY]	= RESET_DATA(APMU_USB_CLK_RES_CTRL,	0, BIT(19)),
 	[RESET_APMU_QSPI]	= RESET_DATA(APMU_QSPI_CLK_RES_CTRL,	0, BIT(1)),
 	[RESET_APMU_QSPI_BUS]	= RESET_DATA(APMU_QSPI_CLK_RES_CTRL,	0, BIT(0)),
 	[RESET_APMU_DMA]	= RESET_DATA(APMU_DMA_CLK_RES_CTRL,	0, BIT(0)),
@@ -151,10 +156,12 @@ static const struct ccu_reset_data k3_apmu_resets[] = {
 	[RESET_APMU_CPU7_SW]	= RESET_DATA(APMU_PMU_CC2_AP,		BIT(26), 0),
 	[RESET_APMU_C1_MPSUB_SW]	= RESET_DATA(APMU_PMU_CC2_AP,	BIT(28), 0),
 	[RESET_APMU_MPSUB_DBG]	= RESET_DATA(APMU_PMU_CC2_AP,		BIT(29), 0),
-	[RESET_APMU_UCIE]	= RESET_DATA(APMU_UCIE_CTRL,
-				BIT(1) | BIT(2) | BIT(3), 0),
-	[RESET_APMU_RCPU]	= RESET_DATA(APMU_RCPU_CLK_RES_CTRL,	0,
-				BIT(3) | BIT(2) | BIT(0)),
+	[RESET_APMU_UCIE_IP]	= RESET_DATA(APMU_UCIE_CTRL,		BIT(1),  0),
+	[RESET_APMU_UCIE_HOT]	= RESET_DATA(APMU_UCIE_CTRL,		BIT(2),  0),
+	[RESET_APMU_UCIE_MON]	= RESET_DATA(APMU_UCIE_CTRL,		BIT(3),  0),
+	[RESET_APMU_RCPU_AUDIO_SYS]	= RESET_DATA(APMU_RCPU_CLK_RES_CTRL,	0, BIT(0)),
+	[RESET_APMU_RCPU_MCU_CORE]	= RESET_DATA(APMU_RCPU_CLK_RES_CTRL,	0, BIT(2)),
+	[RESET_APMU_RCPU_AUDIO_APMU]	= RESET_DATA(APMU_RCPU_CLK_RES_CTRL,	0, BIT(3)),
 	[RESET_APMU_DSI4LN2_ESCCLK]	= RESET_DATA(APMU_LCD_CLK_RES_CTRL3,	0, BIT(3)),
 	[RESET_APMU_DSI4LN2_LCD_SW]	= RESET_DATA(APMU_LCD_CLK_RES_CTRL3,	0, BIT(4)),
 	[RESET_APMU_DSI4LN2_LCD_MCLK]	= RESET_DATA(APMU_LCD_CLK_RES_CTRL4,	0, BIT(9)),
@@ -164,16 +171,21 @@ static const struct ccu_reset_data k3_apmu_resets[] = {
 	[RESET_APMU_UFS_ACLK]	= RESET_DATA(APMU_UFS_CLK_RES_CTRL,	0, BIT(0)),
 	[RESET_APMU_EDP0]	= RESET_DATA(APMU_LCD_EDP_CTRL,		0, BIT(0)),
 	[RESET_APMU_EDP1]	= RESET_DATA(APMU_LCD_EDP_CTRL,		0, BIT(16)),
-	[RESET_APMU_PCIE_PORTA]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_A,	0,
-				BIT(5) | BIT(4) | BIT(3)),
-	[RESET_APMU_PCIE_PORTB]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_B,	0,
-				BIT(5) | BIT(4) | BIT(3)),
-	[RESET_APMU_PCIE_PORTC]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_C,	0,
-				BIT(5) | BIT(4) | BIT(3)),
-	[RESET_APMU_PCIE_PORTD]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_D,	0,
-				BIT(5) | BIT(4) | BIT(3)),
-	[RESET_APMU_PCIE_PORTE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_E,	0,
-				BIT(5) | BIT(4) | BIT(3)),
+	[RESET_APMU_PCIE_A_DBI]		= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_A,	0, BIT(3)),
+	[RESET_APMU_PCIE_A_SLAVE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_A,	0, BIT(4)),
+	[RESET_APMU_PCIE_A_MASTER]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_A,	0, BIT(5)),
+	[RESET_APMU_PCIE_B_DBI]		= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_B,	0, BIT(3)),
+	[RESET_APMU_PCIE_B_SLAVE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_B,	0, BIT(4)),
+	[RESET_APMU_PCIE_B_MASTER]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_B,	0, BIT(5)),
+	[RESET_APMU_PCIE_C_DBI]		= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_C,	0, BIT(3)),
+	[RESET_APMU_PCIE_C_SLAVE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_C,	0, BIT(4)),
+	[RESET_APMU_PCIE_C_MASTER]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_C,	0, BIT(5)),
+	[RESET_APMU_PCIE_D_DBI]		= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_D,	0, BIT(3)),
+	[RESET_APMU_PCIE_D_SLAVE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_D,	0, BIT(4)),
+	[RESET_APMU_PCIE_D_MASTER]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_D,	0, BIT(5)),
+	[RESET_APMU_PCIE_E_DBI]		= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_E,	0, BIT(3)),
+	[RESET_APMU_PCIE_E_SLAVE]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_E,	0, BIT(4)),
+	[RESET_APMU_PCIE_E_MASTER]	= RESET_DATA(APMU_PCIE_CLK_RES_CTRL_E,	0, BIT(5)),
 	[RESET_APMU_EMAC0]	= RESET_DATA(APMU_EMAC0_CLK_RES_CTRL,	0, BIT(1)),
 	[RESET_APMU_EMAC1]	= RESET_DATA(APMU_EMAC1_CLK_RES_CTRL,	0, BIT(1)),
 	[RESET_APMU_EMAC2]	= RESET_DATA(APMU_EMAC2_CLK_RES_CTRL,	0, BIT(1)),
diff --git a/include/dt-bindings/reset/spacemit,k3-resets.h b/include/dt-bindings/reset/spacemit,k3-resets.h
index 79ac1c22b7b5..dc1ef009ba79 100644
--- a/include/dt-bindings/reset/spacemit,k3-resets.h
+++ b/include/dt-bindings/reset/spacemit,k3-resets.h
@@ -97,11 +97,11 @@
 #define RESET_APMU_SDH0          13
 #define RESET_APMU_SDH1          14
 #define RESET_APMU_SDH2          15
-#define RESET_APMU_USB2          16
-#define RESET_APMU_USB3_PORTA    17
-#define RESET_APMU_USB3_PORTB    18
-#define RESET_APMU_USB3_PORTC    19
-#define RESET_APMU_USB3_PORTD    20
+#define RESET_APMU_USB2_AHB      16
+#define RESET_APMU_USB2_VCC      17
+#define RESET_APMU_USB2_PHY      18
+#define RESET_APMU_USB3_A_AHB    19
+#define RESET_APMU_USB3_A_VCC    20
 #define RESET_APMU_QSPI          21
 #define RESET_APMU_QSPI_BUS      22
 #define RESET_APMU_DMA           23
@@ -132,8 +132,8 @@
 #define RESET_APMU_CPU7_SW       48
 #define RESET_APMU_C1_MPSUB_SW   49
 #define RESET_APMU_MPSUB_DBG     50
-#define RESET_APMU_UCIE          51
-#define RESET_APMU_RCPU          52
+#define RESET_APMU_USB3_A_PHY    51	/* USB3 A */
+#define RESET_APMU_USB3_B_AHB    52
 #define RESET_APMU_DSI4LN2_ESCCLK     53
 #define RESET_APMU_DSI4LN2_LCD_SW     54
 #define RESET_APMU_DSI4LN2_LCD_MCLK   55
@@ -143,16 +143,40 @@
 #define RESET_APMU_UFS_ACLK      59
 #define RESET_APMU_EDP0          60
 #define RESET_APMU_EDP1          61
-#define RESET_APMU_PCIE_PORTA    62
-#define RESET_APMU_PCIE_PORTB    63
-#define RESET_APMU_PCIE_PORTC    64
-#define RESET_APMU_PCIE_PORTD    65
-#define RESET_APMU_PCIE_PORTE    66
+#define RESET_APMU_USB3_B_VCC    62	/* USB3 B */
+#define RESET_APMU_USB3_B_PHY    63
+#define RESET_APMU_USB3_C_AHB    64
+#define RESET_APMU_USB3_C_VCC    65
+#define RESET_APMU_USB3_C_PHY    66
 #define RESET_APMU_EMAC0         67
 #define RESET_APMU_EMAC1         68
 #define RESET_APMU_EMAC2         69
 #define RESET_APMU_ESPI_MCLK     70
 #define RESET_APMU_ESPI_SCLK     71
+#define RESET_APMU_USB3_D_AHB    72	/* USB3 D */
+#define RESET_APMU_USB3_D_VCC    73
+#define RESET_APMU_USB3_D_PHY    74
+#define RESET_APMU_UCIE_IP       75
+#define RESET_APMU_UCIE_HOT      76
+#define RESET_APMU_UCIE_MON      77
+#define RESET_APMU_RCPU_AUDIO_SYS     78
+#define RESET_APMU_RCPU_MCU_CORE      79
+#define RESET_APMU_RCPU_AUDIO_APMU    80
+#define RESET_APMU_PCIE_A_DBI    81
+#define RESET_APMU_PCIE_A_SLAVE  82
+#define RESET_APMU_PCIE_A_MASTER 83
+#define RESET_APMU_PCIE_B_DBI    84
+#define RESET_APMU_PCIE_B_SLAVE  85
+#define RESET_APMU_PCIE_B_MASTER 86
+#define RESET_APMU_PCIE_C_DBI    87
+#define RESET_APMU_PCIE_C_SLAVE  88
+#define RESET_APMU_PCIE_C_MASTER 89
+#define RESET_APMU_PCIE_D_DBI    90
+#define RESET_APMU_PCIE_D_SLAVE  91
+#define RESET_APMU_PCIE_D_MASTER 92
+#define RESET_APMU_PCIE_E_DBI    93
+#define RESET_APMU_PCIE_E_SLAVE  94
+#define RESET_APMU_PCIE_E_MASTER 95
 
 /* DCIU resets*/
 #define RESET_DCIU_HDMA          0
-- 
cgit v1.2.3


From 05243d490bb7852a8acca7b5b5658019c7797a52 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Wed, 18 Mar 2026 07:56:52 +0000
Subject: x86/cpu: Enable FSGSBASE early in cpu_init_exception_handling()

Move FSGSBASE enablement from identify_cpu() to cpu_init_exception_handling()
to ensure it is enabled before any exceptions can occur on both boot and
secondary CPUs.

== Background ==

Exception entry code (paranoid_entry()) uses ALTERNATIVE patching based on
X86_FEATURE_FSGSBASE to decide whether to use RDGSBASE/WRGSBASE instructions
or the slower RDMSR/SWAPGS sequence for saving/restoring GSBASE.

On boot CPU, ALTERNATIVE patching happens after enabling FSGSBASE in CR4.
When the feature is available, the code is permanently patched to use
RDGSBASE/WRGSBASE, which require CR4.FSGSBASE=1 to execute without triggering

== Boot Sequence ==

Boot CPU (with CR pinning enabled):
  trap_init()
    cpu_init()                   <- Uses unpatched code (RDMSR/SWAPGS)
      x2apic_setup()
  ...
  arch_cpu_finalize_init()
    identify_boot_cpu()
      identify_cpu()
        cr4_set_bits(X86_CR4_FSGSBASE)  # Enables the feature
	# This becomes part of cr4_pinned_bits
    ...
    alternative_instructions()   <- Patches code to use RDGSBASE/WRGSBASE

Secondary CPUs (with CR pinning enabled):
  start_secondary()
    cr4_init()                   <- Code already patched, CR4.FSGSBASE=1
                                    set implicitly via cr4_pinned_bits

    cpu_init()                   <- exceptions work because FSGSBASE is
                                    already enabled

Secondary CPU (with CR pinning disabled):
  start_secondary()
    cr4_init()                   <- Code already patched, CR4.FSGSBASE=0
    cpu_init()
      x2apic_setup()
        rdmsrq(MSR_IA32_APICBASE)  <- Triggers #VC in SNP guests
          exc_vmm_communication()
            paranoid_entry()       <- Uses RDGSBASE with CR4.FSGSBASE=0
                                      (patched code)
    ...
    ap_starting()
      identify_secondary_cpu()
        identify_cpu()
	  cr4_set_bits(X86_CR4_FSGSBASE)  <- Enables the feature, which is
                                             too late

== CR Pinning ==

Currently, for secondary CPUs, CR4.FSGSBASE is set implicitly through
CR-pinning: the boot CPU sets it during identify_cpu(), it becomes part of
cr4_pinned_bits, and cr4_init() applies those pinned bits to secondary CPUs.
This works but creates an undocumented dependency between cr4_init() and the
pinning mechanism.

== Problem ==

Secondary CPUs boot after alternatives have been applied globally. They
execute already-patched paranoid_entry() code that uses RDGSBASE/WRGSBASE
instructions, which require CR4.FSGSBASE=1. Upcoming changes to CR pinning
behavior will break the implicit dependency, causing secondary CPUs to
generate #UD.

This issue manifests itself on AMD SEV-SNP guests, where the rdmsrq() in
x2apic_setup() triggers a #VC exception early during cpu_init(). The #VC
handler (exc_vmm_communication()) executes the patched paranoid_entry() path.
Without CR4.FSGSBASE enabled, RDGSBASE instructions trigger #UD.

== Fix ==

Enable FSGSBASE explicitly in cpu_init_exception_handling() before loading
exception handlers. This makes the dependency explicit and ensures both
boot and secondary CPUs have FSGSBASE enabled before paranoid_entry()
executes.

Fixes: c82965f9e530 ("x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit")
Reported-by: Borislav Petkov <bp@alien8.de>
Suggested-by: Sohil Mehta <sohil.mehta@intel.com>
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/20260318075654.1792916-2-nikunj@amd.com
---
 arch/x86/kernel/cpu/common.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a8ff4376c286..7840b224d6a7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2050,12 +2050,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	setup_umip(c);
 	setup_lass(c);
 
-	/* Enable FSGSBASE instructions if available. */
-	if (cpu_has(c, X86_FEATURE_FSGSBASE)) {
-		cr4_set_bits(X86_CR4_FSGSBASE);
-		elf_hwcap2 |= HWCAP2_FSGSBASE;
-	}
-
 	/*
 	 * The vendor-specific functions might have changed features.
 	 * Now we do "generic changes."
@@ -2416,6 +2410,18 @@ void cpu_init_exception_handling(bool boot_cpu)
 	/* GHCB needs to be setup to handle #VC. */
 	setup_ghcb();
 
+	/*
+	 * On CPUs with FSGSBASE support, paranoid_entry() uses
+	 * ALTERNATIVE-patched RDGSBASE/WRGSBASE instructions. Secondary CPUs
+	 * boot after alternatives are patched globally, so early exceptions
+	 * execute patched code that depends on FSGSBASE. Enable the feature
+	 * before any exceptions occur.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_FSGSBASE)) {
+		cr4_set_bits(X86_CR4_FSGSBASE);
+		elf_hwcap2 |= HWCAP2_FSGSBASE;
+	}
+
 	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
 		/* The boot CPU has enabled FRED during early boot */
 		if (!boot_cpu)
-- 
cgit v1.2.3


From 8f13c0c6cb75cc4421d5a60fc060e9e6fd9d1097 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 20 Mar 2026 14:54:06 +0530
Subject: cpufreq: Don't skip cpufreq_frequency_table_cpuinfo()

The commit 6db0f533d320 ("cpufreq: preserve freq_table_sorted
across suspend/hibernate") unintentionally made a change where
cpufreq_frequency_table_cpuinfo() isn't getting called anymore
for old policies getting re-initialized.

This leads to potentially invalid values of policy->max and
policy->cpuinfo_max_freq.

Fix the issue by reverting the original commit and adding the condition
for just the sorting function.

Fixes: 6db0f533d320 ("cpufreq: preserve freq_table_sorted across suspend/hibernate")
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 6.19+ <stable@vger.kernel.org> # 6.19+
Link: https://patch.msgid.link/65ba5c45749267c82e8a87af3dc788b37a0b3f48.1773998611.git.viresh.kumar@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c    | 9 +++------
 drivers/cpufreq/freq_table.c | 4 ++++
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 277884d91913..1f794524a1d9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1427,12 +1427,9 @@ static int cpufreq_policy_online(struct cpufreq_policy *policy,
 		 * If there is a problem with its frequency table, take it
 		 * offline and drop it.
 		 */
-		if (policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_ASCENDING &&
-		    policy->freq_table_sorted != CPUFREQ_TABLE_SORTED_DESCENDING) {
-			ret = cpufreq_table_validate_and_sort(policy);
-			if (ret)
-				goto out_offline_policy;
-		}
+		ret = cpufreq_table_validate_and_sort(policy);
+		if (ret)
+			goto out_offline_policy;
 
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 7f251daf03ce..5b364d8da4f9 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -360,6 +360,10 @@ int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy)
 	if (policy_has_boost_freq(policy))
 		policy->boost_supported = true;
 
+	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING ||
+	    policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_DESCENDING)
+		return 0;
+
 	return set_freq_table_sorted(policy);
 }
 
-- 
cgit v1.2.3


From 6a28fb8cb28b9eb39a392e531d938a889eacafc5 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 20 Mar 2026 15:08:14 +0530
Subject: cpufreq: conservative: Reset requested_freq on limits change

A recently reported issue highlighted that the cached requested_freq
is not guaranteed to stay in sync with policy->cur. If the platform
changes the actual CPU frequency after the governor sets one (e.g.
due to platform-specific frequency scaling) and a re-sync occurs
later, policy->cur may diverge from requested_freq.

This can lead to incorrect behavior in the conservative governor.
For example, the governor may assume the CPU is already running at
the maximum frequency and skip further increases even though there
is still headroom.

Avoid this by resetting the cached requested_freq to policy->cur on
detecting a change in policy limits.

Reported-by: Lifeng Zheng <zhenglifeng1@huawei.com>
Tested-by: Lifeng Zheng <zhenglifeng1@huawei.com>
Link: https://lore.kernel.org/all/20260210115458.3493646-1-zhenglifeng1@huawei.com/
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Zhongqiu Han <zhongqiu.han@oss.qualcomm.com>
Cc: All applicable <stable@vger.kernel.org>
Link: https://patch.msgid.link/d846a141a98ac0482f20560fcd7525c0f0ec2f30.1773999467.git.viresh.kumar@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq_conservative.c | 12 ++++++++++++
 drivers/cpufreq/cpufreq_governor.c     |  3 +++
 drivers/cpufreq/cpufreq_governor.h     |  1 +
 3 files changed, 16 insertions(+)

diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index e0e847764511..df01d33993d8 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -313,6 +313,17 @@ static void cs_start(struct cpufreq_policy *policy)
 	dbs_info->requested_freq = policy->cur;
 }
 
+static void cs_limits(struct cpufreq_policy *policy)
+{
+	struct cs_policy_dbs_info *dbs_info = to_dbs_info(policy->governor_data);
+
+	/*
+	 * The limits have changed, so may have the current frequency. Reset
+	 * requested_freq to avoid any unintended outcomes due to the mismatch.
+	 */
+	dbs_info->requested_freq = policy->cur;
+}
+
 static struct dbs_governor cs_governor = {
 	.gov = CPUFREQ_DBS_GOVERNOR_INITIALIZER("conservative"),
 	.kobj_type = { .default_groups = cs_groups },
@@ -322,6 +333,7 @@ static struct dbs_governor cs_governor = {
 	.init = cs_init,
 	.exit = cs_exit,
 	.start = cs_start,
+	.limits = cs_limits,
 };
 
 #define CPU_FREQ_GOV_CONSERVATIVE	(cs_governor.gov)
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 36eb7aee4bcd..acf101878733 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -563,6 +563,7 @@ EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop);
 
 void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 {
+	struct dbs_governor *gov = dbs_governor_of(policy);
 	struct policy_dbs_info *policy_dbs;
 
 	/* Protect gov->gdbs_data against cpufreq_dbs_governor_exit() */
@@ -574,6 +575,8 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
 	mutex_lock(&policy_dbs->update_mutex);
 	cpufreq_policy_apply_limits(policy);
 	gov_update_sample_delay(policy_dbs, 0);
+	if (gov->limits)
+		gov->limits(policy);
 	mutex_unlock(&policy_dbs->update_mutex);
 
 out:
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 168c23fd7fca..1462d59277bd 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -138,6 +138,7 @@ struct dbs_governor {
 	int (*init)(struct dbs_data *dbs_data);
 	void (*exit)(struct dbs_data *dbs_data);
 	void (*start)(struct cpufreq_policy *policy);
+	void (*limits)(struct cpufreq_policy *policy);
 };
 
 static inline struct dbs_governor *dbs_governor_of(struct cpufreq_policy *policy)
-- 
cgit v1.2.3


From 734eba62cd32cb9ceffa09e57cdc03d761528525 Mon Sep 17 00:00:00 2001
From: Alberto Garcia <berto@igalia.com>
Date: Mon, 9 Mar 2026 18:39:41 +0100
Subject: PM: hibernate: Drain trailing zero pages on userspace restore

Commit 005e8dddd497 ("PM: hibernate: don't store zero pages in the
image file") added an optimization to skip zero-filled pages in the
hibernation image. On restore, zero pages are handled internally by
snapshot_write_next() in a loop that processes them without returning
to the caller.

With the userspace restore interface, writing the last non-zero page
to /dev/snapshot is followed by the SNAPSHOT_ATOMIC_RESTORE ioctl. At
this point there are no more calls to snapshot_write_next() so any
trailing zero pages are not processed, snapshot_image_loaded() fails
because handle->cur is smaller than expected, the ioctl returns -EPERM
and the image is not restored.

The in-kernel restore path is not affected by this because the loop in
load_image() in swap.c calls snapshot_write_next() until it returns 0.
It is this final call that drains any trailing zero pages.

Fixed by calling snapshot_write_next() in snapshot_write_finalize(),
giving the kernel the chance to drain any trailing zero pages.

Fixes: 005e8dddd497 ("PM: hibernate: don't store zero pages in the image file")
Signed-off-by: Alberto Garcia <berto@igalia.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Link: https://patch.msgid.link/ef5a7c5e3e3dbd17dcb20efaa0c53a47a23498bb.1773075892.git.berto@igalia.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/snapshot.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 6e1321837c66..a564650734dc 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -2855,6 +2855,17 @@ int snapshot_write_finalize(struct snapshot_handle *handle)
 {
 	int error;
 
+	/*
+	 * Call snapshot_write_next() to drain any trailing zero pages,
+	 * but make sure we're in the data page region first.
+	 * This function can return PAGE_SIZE if the kernel was expecting
+	 * another copy page. Return -ENODATA in that situation.
+	 */
+	if (handle->cur > nr_meta_pages + 1) {
+		error = snapshot_write_next(handle);
+		if (error)
+			return error > 0 ? -ENODATA : error;
+	}
 	copy_last_highmem_page();
 	error = hibernate_restore_protect_page(handle->buffer);
 	/* Do that only if we have loaded the image entirely */
-- 
cgit v1.2.3


From 93702ed64fd0c433289b3846c2cefced4a88a043 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Wed, 4 Mar 2026 15:11:02 +0100
Subject: MAINTAINERS: change email address of Denis Benato
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I have been using a linux.dev email since that is hugely better than gmail.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Signed-off-by: Denis Benato <benato.denis96@gmail.com>
Link: https://patch.msgid.link/20260304141102.63732-1-denis.benato@linux.dev
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55af015174a5..27377c282e67 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3989,7 +3989,7 @@ F:	drivers/hwmon/asus-ec-sensors.c
 ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS
 M:	Corentin Chary <corentin.chary@gmail.com>
 M:	Luke D. Jones <luke@ljones.dev>
-M:	Denis Benato <benato.denis96@gmail.com>
+M:	Denis Benato <denis.benato@linux.dev>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 W:	https://asus-linux.org/
-- 
cgit v1.2.3


From e0836f48e19147a85ae652335e517b0385a32fd3 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Mon, 9 Mar 2026 19:35:57 +0100
Subject: platform/x86: asus-armoury: add support for GA503QM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model GA503QM.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260309183559.433555-2-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 208f6fe16168..1979b5c47bc9 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1080,6 +1080,20 @@ static const struct dmi_system_id power_limits[] = {
 			.requires_fan_curve = true,
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GA503QM"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_def = 35,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 65,
+				.ppt_pl2_sppt_max = 80,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GA503QR"),
-- 
cgit v1.2.3


From d2723918d51b238b42efcaac553697aa84f15232 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Mon, 9 Mar 2026 19:35:58 +0100
Subject: platform/x86: asus-armoury: add support for G614FP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model G614FP.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260309183559.433555-3-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 1979b5c47bc9..230d614a00e4 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1610,6 +1610,40 @@ static const struct dmi_system_id power_limits[] = {
 			.requires_fan_curve = true,
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "G614FP"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 30,
+				.ppt_pl1_spl_max = 120,
+				.ppt_pl2_sppt_min = 65,
+				.ppt_pl2_sppt_def = 140,
+				.ppt_pl2_sppt_max = 165,
+				.ppt_pl3_fppt_min = 65,
+				.ppt_pl3_fppt_def = 140,
+				.ppt_pl3_fppt_max = 165,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 15,
+				.nv_tgp_min = 50,
+				.nv_tgp_max = 100,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 25,
+				.ppt_pl1_spl_max = 65,
+				.ppt_pl2_sppt_min = 25,
+				.ppt_pl2_sppt_max = 65,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 75,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.requires_fan_curve = true,
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G614J"),
-- 
cgit v1.2.3


From 55b964dfbadc3729d3606849471eab11705f578a Mon Sep 17 00:00:00 2001
From: Raed <thisisraed@outlook.com>
Date: Wed, 11 Mar 2026 18:43:38 +0530
Subject: platform/x86: hp-wmi: Add Omen 16-xf0xxx (8BCA) support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-xf0xxx board 8BCA uses the same Victus-S fan and
thermal WMI path as other recently supported Omen/Victus boards,
but it requires Omen v1 thermal profile parameters for correct
platform profile behavior.

Add board 8BCA to victus_s_thermal_profile_boards[] and map it
to omen_v1_thermal_params.

Validated on HP Omen 16-xf0xxx (board 8BCA):
- /sys/firmware/acpi/platform_profile exposes
	low-power/balanced/performance
- fan RPM reporting works (fan1_input/fan2_input)
- manual fan control works through hp-wmi hwmon (pwm1/pwm1_enable)

Signed-off-by: Raed <thisisraed@outlook.com>
Link: https://patch.msgid.link/20260311131338.965249-1-youaretalkingtoraed@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 68ede7e5757a..0a3fc2942ed0 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -183,6 +183,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BBE") },
 		.driver_data = (void *)&victus_s_thermal_params,
 	},
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCA") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BCD") },
 		.driver_data = (void *)&omen_v1_thermal_params,
-- 
cgit v1.2.3


From 84d29bfd1929d08f092851162a3d055a2134d043 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Fri, 27 Feb 2026 21:11:06 +0530
Subject: platform/x86: hp-wmi: Add support for Omen 16-wf1xxx (8C76)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-wf1xxx (board ID: 8C76) has the same WMI interface as
other Victus S boards, but requires quirks for correctly switching
thermal profile (similar to board 8C78).

Add the DMI board name to victus_s_thermal_profile_boards[] table and
map it to omen_v1_thermal_params.

Testing on board 8C76 confirmed that platform profile is registered
successfully and fan RPMs are readable and controllable.

Tested-by: WJ Enderlava <jie7172585@gmail.com>
Reported-by: WJ Enderlava <jie7172585@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221149
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260227154106.226809-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 0a3fc2942ed0..0e5d491fd450 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -199,6 +199,10 @@ static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BD5") },
 		.driver_data = (void *)&victus_s_thermal_params,
 	},
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8C76") },
+		.driver_data = (void *)&omen_v1_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8C78") },
 		.driver_data = (void *)&omen_v1_thermal_params,
-- 
cgit v1.2.3


From 435da773966c80e1b2b6aea75460ef0e893fd9e9 Mon Sep 17 00:00:00 2001
From: Krishna Chomal <krishna.chomal108@gmail.com>
Date: Mon, 2 Mar 2026 13:05:25 +0530
Subject: platform/x86: hp-wmi: Add support for Omen 16-k0xxx (8A4D)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Omen 16-k0xxx (board ID: 8A4D) has the same WMI interface as
other Victus S boards, but requires additional quirks for correctly
switching thermal profile.

Create a new quirk omen_v1_legacy_thermal_params which allows a board to
use Omen V1 thermal values, but rely on the older legacy
HP_OMEN_EC_THERMAL_PROFILE_OFFSET. Add the DMI board name to
victus_s_thermal_profile_boards[] table and map it to the newly added
quirk.

Testing on board 8A4D confirmed that platform profile is registered
successfully and fan RPMs are readable and controllable.

Tested-by: Qinfeng Wu <qwqgong@gmail.com>
Reported-by: Qinfeng Wu <qwqgong@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221150
Signed-off-by: Krishna Chomal <krishna.chomal108@gmail.com>
Link: https://patch.msgid.link/20260302073525.71037-1-krishna.chomal108@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 0e5d491fd450..988a0acc9622 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -120,6 +120,13 @@ static const struct thermal_profile_params omen_v1_thermal_params = {
 	.ec_tp_offset	= HP_VICTUS_S_EC_THERMAL_PROFILE_OFFSET,
 };
 
+static const struct thermal_profile_params omen_v1_legacy_thermal_params = {
+	.performance	= HP_OMEN_V1_THERMAL_PROFILE_PERFORMANCE,
+	.balanced	= HP_OMEN_V1_THERMAL_PROFILE_DEFAULT,
+	.low_power	= HP_OMEN_V1_THERMAL_PROFILE_DEFAULT,
+	.ec_tp_offset	= HP_OMEN_EC_THERMAL_PROFILE_OFFSET,
+};
+
 /*
  * A generic pointer for the currently-active board's thermal profile
  * parameters.
@@ -175,6 +182,10 @@ static const char * const victus_thermal_profile_boards[] = {
 
 /* DMI Board names of Victus 16-r and Victus 16-s laptops */
 static const struct dmi_system_id victus_s_thermal_profile_boards[] __initconst = {
+	{
+		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8A4D") },
+		.driver_data = (void *)&omen_v1_legacy_thermal_params,
+	},
 	{
 		.matches = { DMI_MATCH(DMI_BOARD_NAME, "8BAB") },
 		.driver_data = (void *)&omen_v1_thermal_params,
-- 
cgit v1.2.3


From 9f11d9b15efb5f77e810b6dfbeb01b4650a79eae Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 3 Mar 2026 02:46:35 -0500
Subject: platform/x86: ISST: Check HWP support before MSR access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On some systems, HWP can be explicitly disabled in the BIOS settings
When HWP is disabled by firmware, the HWP CPUID bit is not set, and
attempting to read MSR_PM_ENABLE will result in a General Protection
(GP) fault.

  unchecked MSR access error: RDMSR from 0x770 at rIP: 0xffffffffc33db92e (disable_dynamic_sst_features+0xe/0x50 [isst_tpmi_core])
  Call Trace:
   <TASK>
   ? ex_handler_msr+0xf6/0x150
   ? fixup_exception+0x1ad/0x340
   ? gp_try_fixup_and_notify+0x1e/0xb0
   ? exc_general_protection+0xc9/0x390
   ? terminate_walk+0x64/0x100
   ? asm_exc_general_protection+0x22/0x30
   ? disable_dynamic_sst_features+0xe/0x50 [isst_tpmi_core]
   isst_if_def_ioctl+0xece/0x1050 [isst_tpmi_core]
   ? ioctl_has_perm.constprop.42+0xe0/0x130
   isst_if_def_ioctl+0x10d/0x1a0 [isst_if_common]
   __se_sys_ioctl+0x86/0xc0
   do_syscall_64+0x8a/0x100
   entry_SYSCALL_64_after_hwframe+0x78/0xe2
  RIP: 0033:0x7f36eaef54a7

Add a check for X86_FEATURE_HWP before accessing the MSR. If HWP is
not available, return true safely.

Fixes: 12a7d2cb811d ("platform/x86: ISST: Add SST-CP support via TPMI")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260303074635.2218-1-lirongqing@baidu.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index b8cdaa233ea9..6f46cbb2898f 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -558,6 +558,9 @@ static bool disable_dynamic_sst_features(void)
 {
 	u64 value;
 
+	if (!static_cpu_has(X86_FEATURE_HWP))
+		return true;
+
 	rdmsrq(MSR_PM_ENABLE, value);
 	return !(value & 0x1);
 }
-- 
cgit v1.2.3


From 5a3955f3602950d1888df743a5b1889e43b5cb60 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 13 Mar 2026 14:06:34 -0700
Subject: platform/x86: lenovo: wmi-gamezone: Drop gz_chain_head
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The gz_chain_head variable has been unused since the driver's initial
addition to the tree. Its use was eliminated between v3 and v4 during
development but due to the reference of gz_chain_head's wait_list
member, the compiler could not warn that it was unused.

After a (tip) commit ("locking/rwsem: Remove the list_head from struct
rw_semaphore"), which removed a reference to the variable passed to
__RWSEM_INITIALIZER(), certain configurations show an unused variable
warning from the Lenovo wmi-gamezone driver:

  drivers/platform/x86/lenovo/wmi-gamezone.c:34:31: warning: 'gz_chain_head' defined but not used [-Wunused-variable]
     34 | static BLOCKING_NOTIFIER_HEAD(gz_chain_head);
        |                               ^~~~~~~~~~~~~
  include/linux/notifier.h:119:39: note: in definition of macro 'BLOCKING_NOTIFIER_HEAD'
    119 |         struct blocking_notifier_head name =                    \
        |                                       ^~~~

Remove the variable to prevent the warning from showing up.

Fixes: 22024ac5366f ("platform/x86: Add Lenovo Gamezone WMI Driver")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://patch.msgid.link/20260313-lenovo-wmi-gamezone-remove-gz_chain_head-v1-1-ce5231f0c6fa@kernel.org
[ij: reorganized the changelog]
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/lenovo/wmi-gamezone.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/platform/x86/lenovo/wmi-gamezone.c b/drivers/platform/x86/lenovo/wmi-gamezone.c
index 381836d29a96..c7fe7e3c9f17 100644
--- a/drivers/platform/x86/lenovo/wmi-gamezone.c
+++ b/drivers/platform/x86/lenovo/wmi-gamezone.c
@@ -31,8 +31,6 @@
 #define LWMI_GZ_METHOD_ID_SMARTFAN_SET 44
 #define LWMI_GZ_METHOD_ID_SMARTFAN_GET 45
 
-static BLOCKING_NOTIFIER_HEAD(gz_chain_head);
-
 struct lwmi_gz_priv {
 	enum thermal_mode current_mode;
 	struct notifier_block event_nb;
-- 
cgit v1.2.3


From 2061f7b042f88d372cca79615f8425f3564c0b40 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 06:01:35 -0700
Subject: platform/olpc: olpc-xo175-ec: Fix overflow error message to print
 inlen
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The command length check validates inlen (> 5), but the error message
incorrectly printed resp_len. Print inlen so the log reflects the
actual command length.

Fixes: 0c3d931b3ab9e ("Platform: OLPC: Add XO-1.75 EC driver")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Acked-by: Lubomir Rintel <lkundrak@v3.sk>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260310130138.700687-1-alok.a.tiwari@oracle.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/olpc/olpc-xo175-ec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/olpc/olpc-xo175-ec.c b/drivers/platform/olpc/olpc-xo175-ec.c
index fa7b3bda688a..bee271a4fda1 100644
--- a/drivers/platform/olpc/olpc-xo175-ec.c
+++ b/drivers/platform/olpc/olpc-xo175-ec.c
@@ -482,7 +482,7 @@ static int olpc_xo175_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *resp,
 	dev_dbg(dev, "CMD %x, %zd bytes expected\n", cmd, resp_len);
 
 	if (inlen > 5) {
-		dev_err(dev, "command len %zd too big!\n", resp_len);
+		dev_err(dev, "command len %zd too big!\n", inlen);
 		return -EOVERFLOW;
 	}
 
-- 
cgit v1.2.3


From 7ff61be5a4844d4aaa31732a5831dd5cd6136448 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 10 Mar 2026 05:53:05 -0700
Subject: platform/x86/amd/hsmp: Fix typo in error message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a typo in the HSMP error message where "tmeout" should be "timeout".

Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20260310125307.700108-1-alok.a.tiwari@oracle.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hsmp/hsmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 19f82c1d3090..631ffc0978d1 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -117,7 +117,7 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms
 	}
 
 	if (unlikely(mbox_status == HSMP_STATUS_NOT_READY)) {
-		dev_err(sock->dev, "Message ID 0x%X failure : SMU tmeout (status = 0x%X)\n",
+		dev_err(sock->dev, "Message ID 0x%X failure : SMU timeout (status = 0x%X)\n",
 			msg->msg_id, mbox_status);
 		return -ETIMEDOUT;
 	} else if (unlikely(mbox_status == HSMP_ERR_INVALID_MSG)) {
-- 
cgit v1.2.3


From 0198d2743207d67f995cd6df89e267e1b9f5e1f1 Mon Sep 17 00:00:00 2001
From: Matthew Schwartz <matthew.schwartz@linux.dev>
Date: Thu, 12 Mar 2026 14:22:46 -0700
Subject: platform/x86: asus-nb-wmi: add DMI quirk for ASUS ROG Flow Z13-KJP
 GZ302EAC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ASUS ROG Flow Z13-KJP GZ302EAC model uses sys_vendor name ASUS
rather than ASUSTeK COMPUTER INC., but it needs the same folio quirk as
the other ROG Flow Z13. To keep things simple, just match on sys_vendor
ASUS since it covers both.

Signed-off-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260312212246.1608080-1-matthew.schwartz@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-nb-wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index a38a65f5c550..b4677c5bba5b 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -548,7 +548,7 @@ static const struct dmi_system_id asus_quirks[] = {
 		.callback = dmi_matched,
 		.ident = "ASUS ROG Z13",
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUS"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow Z13"),
 		},
 		.driver_data = &quirk_asus_z13,
-- 
cgit v1.2.3


From 8a243d972aff2e0b0141048a3feaf3b13d78985c Mon Sep 17 00:00:00 2001
From: Matthew Schwartz <matthew.schwartz@linux.dev>
Date: Thu, 12 Mar 2026 17:49:39 -0700
Subject: platform/x86: asus-armoury: add support for GZ302EA and GZ302EAC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for tablet models GZ302EA and GZ302EAC.

Signed-off-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Reviewed-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260313004939.4103835-1-matthew.schwartz@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 230d614a00e4..569743746347 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1532,6 +1532,35 @@ static const struct dmi_system_id power_limits[] = {
 			},
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GZ302EA"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_def = 60,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 32,
+				.ppt_pl2_sppt_def = 75,
+				.ppt_pl2_sppt_max = 92,
+				.ppt_pl3_fppt_min = 45,
+				.ppt_pl3_fppt_def = 86,
+				.ppt_pl3_fppt_max = 93,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_def = 45,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 32,
+				.ppt_pl2_sppt_def = 52,
+				.ppt_pl2_sppt_max = 92,
+				.ppt_pl3_fppt_min = 45,
+				.ppt_pl3_fppt_def = 71,
+				.ppt_pl3_fppt_max = 93,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "G513I"),
-- 
cgit v1.2.3


From e02ea3ae8ee40d5835a845884c7b161a27c10bcb Mon Sep 17 00:00:00 2001
From: David McFarland <corngood@gmail.com>
Date: Thu, 5 Feb 2026 19:16:24 -0400
Subject: platform/x86: intel-hid: disable wakeup_mode during hibernation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a freeze handler which clears wakeup_mode. This fixes aborted hibernation on
Dell Precision 3880.

  Wakeup event detected during hibernation, rolling back

This system sends power button events during hibernation, even when triggered by
software.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218634
Fixes: 0c4cae1bc00d ("PM: hibernate: Avoid missing wakeup events during hibernation")
Signed-off-by: David McFarland <corngood@gmail.com>
Link: https://patch.msgid.link/20260205231629.1336348-1-corngood@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 95c405c8bac0..2ddd8af8c1ce 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -438,6 +438,14 @@ static int intel_hid_pl_suspend_handler(struct device *device)
 	return 0;
 }
 
+static int intel_hid_pl_freeze_handler(struct device *device)
+{
+	struct intel_hid_priv *priv = dev_get_drvdata(device);
+
+	priv->wakeup_mode = false;
+	return intel_hid_pl_suspend_handler(device);
+}
+
 static int intel_hid_pl_resume_handler(struct device *device)
 {
 	intel_hid_pm_complete(device);
@@ -452,7 +460,7 @@ static int intel_hid_pl_resume_handler(struct device *device)
 static const struct dev_pm_ops intel_hid_pl_pm_ops = {
 	.prepare = intel_hid_pm_prepare,
 	.complete = intel_hid_pm_complete,
-	.freeze  = intel_hid_pl_suspend_handler,
+	.freeze  = intel_hid_pl_freeze_handler,
 	.thaw  = intel_hid_pl_resume_handler,
 	.restore  = intel_hid_pl_resume_handler,
 	.suspend  = intel_hid_pl_suspend_handler,
-- 
cgit v1.2.3


From a8d51efb5929ae308895455a3e496b5eca2cd143 Mon Sep 17 00:00:00 2001
From: Youngjun Park <youngjun.park@lge.com>
Date: Sun, 22 Mar 2026 21:05:28 +0900
Subject: PM: sleep: Drop spurious WARN_ON() from pm_restore_gfp_mask()

Commit 35e4a69b2003f ("PM: sleep: Allow pm_restrict_gfp_mask()
stacking") introduced refcount-based GFP mask management that warns
when pm_restore_gfp_mask() is called with saved_gfp_count == 0.

Some hibernation paths call pm_restore_gfp_mask() defensively where
the GFP mask may or may not be restricted depending on the execution
path. For example, the uswsusp interface invokes it in
SNAPSHOT_CREATE_IMAGE, SNAPSHOT_UNFREEZE, and snapshot_release().
Before the stacking change this was a silent no-op; it now triggers
a spurious WARNING.

Remove the WARN_ON() wrapper from the !saved_gfp_count check while
retaining the check itself, so that defensive calls remain harmless
without producing false warnings.

Fixes: 35e4a69b2003f ("PM: sleep: Allow pm_restrict_gfp_mask() stacking")
Signed-off-by: Youngjun Park <youngjun.park@lge.com>
[ rjw: Subject tweak ]
Link: https://patch.msgid.link/20260322120528.750178-1-youngjun.park@lge.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/power/main.c b/kernel/power/main.c
index 5f8c9e12eaec..5429e9f19b65 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -40,7 +40,7 @@ void pm_restore_gfp_mask(void)
 {
 	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 
-	if (WARN_ON(!saved_gfp_count) || --saved_gfp_count)
+	if (!saved_gfp_count || --saved_gfp_count)
 		return;
 
 	gfp_allowed_mask = saved_gfp_mask;
-- 
cgit v1.2.3


From 411df123c017169922cc767affce76282b8e6c85 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 19 Mar 2026 12:07:59 +0100
Subject: x86/cpu: Remove X86_CR4_FRED from the CR4 pinned bits mask

Commit in Fixes added the FRED CR4 bit to the CR4 pinned bits mask so
that whenever something else modifies CR4, that bit remains set. Which
in itself is a perfectly fine idea.

However, there's an issue when during boot FRED is initialized: first on
the BSP and later on the APs. Thus, there's a window in time when
exceptions cannot be handled.

This becomes particularly nasty when running as SEV-{ES,SNP} or TDX
guests which, when they manage to trigger exceptions during that short
window described above, triple fault due to FRED MSRs not being set up
yet.

See Link tag below for a much more detailed explanation of the
situation.

So, as a result, the commit in that Link URL tried to address this
shortcoming by temporarily disabling CR4 pinning when an AP is not
online yet.

However, that is a problem in itself because in this case, an attack on
the kernel needs to only modify the online bit - a single bit in RW
memory - and then disable CR4 pinning and then disable SM*P, leading to
more and worse things to happen to the system.

So, instead, remove the FRED bit from the CR4 pinning mask, thus
obviating the need to temporarily disable CR4 pinning.

If someone manages to disable FRED when poking at CR4, then
idt_invalidate() would make sure the system would crash'n'burn on the
first exception triggered, which is a much better outcome security-wise.

Fixes: ff45746fbf00 ("x86/cpu: Add X86_CR4_FRED macro")
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org> # 6.12+
Link: https://lore.kernel.org/r/177385987098.1647592.3381141860481415647.tip-bot2@tip-bot2
---
 arch/x86/kernel/cpu/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7840b224d6a7..c57e8972d30f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -433,7 +433,7 @@ static __always_inline void setup_lass(struct cpuinfo_x86 *c)
 
 /* These bits should not change their value after CPU init is finished. */
 static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
-					     X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED;
+					     X86_CR4_FSGSBASE | X86_CR4_CET;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
-- 
cgit v1.2.3


From 34420cb92dbb9e37ff6c6603f4f5e1807db3f1de Mon Sep 17 00:00:00 2001
From: Huiwen He <hehuiwen@kylinos.cn>
Date: Mon, 23 Mar 2026 17:08:12 +0800
Subject: smb/client: ensure smb2_mapping_table rebuild on cmd changes

The current rule for smb2_mapping_table.c uses `$(call cmd,...)`, which
fails to track command line modifications in the Makefile (e.g., modifying
the command to `perl -d` or `perl -w` for debug will not trigger a rebuild)
and does not generate the required .cmd file for Kbuild.

Fix this by transitioning to the standard `$(call if_changed,...)` macro.
This includes adding the `FORCE` prerequisite and appending the output
file to the `targets` variable so Kbuild can track it properly.

As a result, Kbuild now automatically handles the cleaning of the
generated file, allowing us to safely drop the redundant `clean-files`
assignment.

Fixes: c527e13a7a66 ("cifs: Autogenerate SMB2 error mapping table")
Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/Makefile | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile
index 26b6105f04d1..1a6e1e1c9764 100644
--- a/fs/smb/client/Makefile
+++ b/fs/smb/client/Makefile
@@ -48,8 +48,8 @@ cifs-$(CONFIG_CIFS_COMPRESSION) += compress.o compress/lz77.o
 # Build the SMB2 error mapping table from smb2status.h
 #
 $(obj)/smb2_mapping_table.c: $(src)/../common/smb2status.h \
-			    $(src)/gen_smb2_mapping
-	$(call cmd,gen_smb2_mapping)
+			     $(src)/gen_smb2_mapping FORCE
+	$(call if_changed,gen_smb2_mapping)
 
 $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c
 
@@ -58,4 +58,5 @@ quiet_cmd_gen_smb2_mapping = GEN     $@
 
 obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o
 
-clean-files	+= smb2_mapping_table.c
+# Let Kbuild handle tracking and cleaning
+targets += smb2_mapping_table.c
-- 
cgit v1.2.3


From 3645eb7e3915990a149460c151a00894cb586253 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Wed, 18 Mar 2026 07:56:54 +0000
Subject: x86/fred: Fix early boot failures on SEV-ES/SNP guests

FRED-enabled SEV-(ES,SNP) guests fail to boot due to the following issues
in the early boot sequence:

* FRED does not have a #VC exception handler in the dispatch logic

* Early FRED #VC exceptions attempt to use uninitialized per-CPU GHCBs
  instead of boot_ghcb

Add X86_TRAP_VC case to fred_hwexc() with a new exc_vmm_communication()
function that provides the unified entry point FRED requires, dispatching
to existing user/kernel handlers based on privilege level. The function is
already declared via DECLARE_IDTENTRY_VC().

Fix early GHCB access by falling back to boot_ghcb in
__sev_{get,put}_ghcb() when per-CPU GHCBs are not yet initialized.

Fixes: 14619d912b65 ("x86/fred: FRED entry/exit and dispatch code")
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: <stable@kernel.org>  # 6.12+
Link: https://patch.msgid.link/20260318075654.1792916-4-nikunj@amd.com
---
 arch/x86/coco/sev/noinstr.c |  6 ++++++
 arch/x86/entry/entry_fred.c | 14 ++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/arch/x86/coco/sev/noinstr.c b/arch/x86/coco/sev/noinstr.c
index 9d94aca4a698..5afd663a1c21 100644
--- a/arch/x86/coco/sev/noinstr.c
+++ b/arch/x86/coco/sev/noinstr.c
@@ -121,6 +121,9 @@ noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
 
 	WARN_ON(!irqs_disabled());
 
+	if (!sev_cfg.ghcbs_initialized)
+		return boot_ghcb;
+
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;
 
@@ -164,6 +167,9 @@ noinstr void __sev_put_ghcb(struct ghcb_state *state)
 
 	WARN_ON(!irqs_disabled());
 
+	if (!sev_cfg.ghcbs_initialized)
+		return;
+
 	data = this_cpu_read(runtime_data);
 	ghcb = &data->ghcb_page;
 
diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index 88c757ac8ccd..fbe2d10dd737 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -177,6 +177,16 @@ static noinstr void fred_extint(struct pt_regs *regs)
 	}
 }
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+noinstr void exc_vmm_communication(struct pt_regs *regs, unsigned long error_code)
+{
+	if (user_mode(regs))
+		return user_exc_vmm_communication(regs, error_code);
+	else
+		return kernel_exc_vmm_communication(regs, error_code);
+}
+#endif
+
 static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code)
 {
 	/* Optimize for #PF. That's the only exception which matters performance wise */
@@ -207,6 +217,10 @@ static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code)
 #ifdef CONFIG_X86_CET
 	case X86_TRAP_CP: return exc_control_protection(regs, error_code);
 #endif
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	case X86_TRAP_VC: return exc_vmm_communication(regs, error_code);
+#endif
+
 	default: return fred_bad_type(regs, error_code);
 	}
 
-- 
cgit v1.2.3


From 42e06688c6cb7217578133bed67e9e3c1f061a58 Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Fri, 20 Mar 2026 18:52:30 +0100
Subject: pinctrl: sunxi: pass down flags to pinctrl routines

Recent changes in the Allwinner pinctrl/GPIO IP made us add some quirks,
which the new SoCs (A523 family) need to use. We now have a comfortable
"flags" field on the per-SoC setup side, to tag those quirks we need, but
were translating those flag bits into specific fields for runtime use, in
the init routine.
Now the newest Allwinner GPIO IP adds even more quirks and exceptions,
some of a boolean nature.
To avoid inventing various new boolean flags for the runtime struct
sunxi_pinctrl, let's just directly pass on the flags variable used by the
setup code, so runtime can check for those various quirk bits directly.

Rename the "variant" member to "flags", and directly copy the value from
the setup code into there. Move the variant masking from the init
routine to the functions which actually use the "variant" value.

This mostly paves the way for the new A733 IP generation, which needs
more quirks to be checked at runtime.

Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Michal Piekos <michal.piekos@mmpsystems.pl>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/sunxi/pinctrl-sunxi.c | 23 ++++++++++++++---------
 drivers/pinctrl/sunxi/pinctrl-sunxi.h |  2 +-
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index c990b6118172..685b79fc0bf8 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -157,6 +157,7 @@ sunxi_pinctrl_desc_find_function_by_name(struct sunxi_pinctrl *pctl,
 					 const char *pin_name,
 					 const char *func_name)
 {
+	unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK;
 	int i;
 
 	for (i = 0; i < pctl->desc->npins; i++) {
@@ -168,7 +169,7 @@ sunxi_pinctrl_desc_find_function_by_name(struct sunxi_pinctrl *pctl,
 			while (func->name) {
 				if (!strcmp(func->name, func_name) &&
 					(!func->variant ||
-					func->variant & pctl->variant))
+					func->variant & variant))
 					return func;
 
 				func++;
@@ -209,6 +210,8 @@ sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl,
 						const u16 pin_num,
 						const u8 muxval)
 {
+	unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK;
+
 	for (unsigned int i = 0; i < pctl->desc->npins; i++) {
 		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
 		struct sunxi_desc_function *func = pin->functions;
@@ -216,7 +219,7 @@ sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl,
 		if (pin->pin.number != pin_num)
 			continue;
 
-		if (pin->variant && !(pctl->variant & pin->variant))
+		if (pin->variant && !(variant & pin->variant))
 			continue;
 
 		while (func->name) {
@@ -1338,6 +1341,7 @@ static int sunxi_pinctrl_add_function(struct sunxi_pinctrl *pctl,
 static int sunxi_pinctrl_build_state(struct platform_device *pdev)
 {
 	struct sunxi_pinctrl *pctl = platform_get_drvdata(pdev);
+	unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK;
 	void *ptr;
 	int i;
 
@@ -1362,7 +1366,7 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev)
 		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
 		struct sunxi_pinctrl_group *group = pctl->groups + pctl->ngroups;
 
-		if (pin->variant && !(pctl->variant & pin->variant))
+		if (pin->variant && !(variant & pin->variant))
 			continue;
 
 		group->name = pin->pin.name;
@@ -1387,11 +1391,11 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev)
 		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
 		struct sunxi_desc_function *func;
 
-		if (pin->variant && !(pctl->variant & pin->variant))
+		if (pin->variant && !(variant & pin->variant))
 			continue;
 
 		for (func = pin->functions; func->name; func++) {
-			if (func->variant && !(pctl->variant & func->variant))
+			if (func->variant && !(variant & func->variant))
 				continue;
 
 			/* Create interrupt mapping while we're at it */
@@ -1419,14 +1423,14 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev)
 		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
 		struct sunxi_desc_function *func;
 
-		if (pin->variant && !(pctl->variant & pin->variant))
+		if (pin->variant && !(variant & pin->variant))
 			continue;
 
 		for (func = pin->functions; func->name; func++) {
 			struct sunxi_pinctrl_function *func_item;
 			const char **func_grp;
 
-			if (func->variant && !(pctl->variant & func->variant))
+			if (func->variant && !(variant & func->variant))
 				continue;
 
 			func_item = sunxi_pinctrl_find_function_by_name(pctl,
@@ -1568,7 +1572,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 
 	pctl->dev = &pdev->dev;
 	pctl->desc = desc;
-	pctl->variant = flags & SUNXI_PINCTRL_VARIANT_MASK;
+	pctl->flags = flags;
 	if (flags & SUNXI_PINCTRL_NEW_REG_LAYOUT) {
 		pctl->bank_mem_size = D1_BANK_MEM_SIZE;
 		pctl->pull_regs_offset = D1_PULL_REGS_OFFSET;
@@ -1604,8 +1608,9 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 
 	for (i = 0, pin_idx = 0; i < pctl->desc->npins; i++) {
 		const struct sunxi_desc_pin *pin = pctl->desc->pins + i;
+		unsigned long variant = pctl->flags & SUNXI_PINCTRL_VARIANT_MASK;
 
-		if (pin->variant && !(pctl->variant & pin->variant))
+		if (pin->variant && !(variant & pin->variant))
 			continue;
 
 		pins[pin_idx++] = pin->pin;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index ad26e4de16a8..22bffac1c3f0 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -174,7 +174,7 @@ struct sunxi_pinctrl {
 	unsigned			*irq_array;
 	raw_spinlock_t			lock;
 	struct pinctrl_dev		*pctl_dev;
-	unsigned long			variant;
+	unsigned long			flags;
 	u32				bank_mem_size;
 	u32				pull_regs_offset;
 	u32				dlevel_field_width;
-- 
cgit v1.2.3


From 70f8915ea4e909826306a8567c7fa46959e278db Mon Sep 17 00:00:00 2001
From: Michal Piekos <michal.piekos@mmpsystems.pl>
Date: Fri, 20 Mar 2026 18:52:31 +0100
Subject: pinctrl: sunxi: fix gpiochip_lock_as_irq() failure when pinmux is
 unknown

Fixes kernel hang during boot due to inability to set up IRQ on AXP313a.

The issue is caused by gpiochip_lock_as_irq() which is failing when gpio
is in uninitialized state.

Solution is to set pinmux to GPIO INPUT in
sunxi_pinctrl_irq_request_resources() if it wasn't initialized
earlier.

Tested on Orange Pi Zero 3.

Fixes: 01e10d0272b9 ("pinctrl: sunxi: Implement gpiochip::get_direction()")
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Chen-Yu Tsai <wens@kernel.org>
Signed-off-by: Michal Piekos <michal.piekos@mmpsystems.pl>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/sunxi/pinctrl-sunxi.c | 20 ++++++++++++++++++--
 drivers/pinctrl/sunxi/pinctrl-sunxi.h |  2 ++
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 685b79fc0bf8..d3042e0c9712 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -1092,6 +1092,9 @@ static int sunxi_pinctrl_irq_request_resources(struct irq_data *d)
 {
 	struct sunxi_pinctrl *pctl = irq_data_get_irq_chip_data(d);
 	struct sunxi_desc_function *func;
+	unsigned int offset;
+	u32 reg, shift, mask;
+	u8 disabled_mux, muxval;
 	int ret;
 
 	func = sunxi_pinctrl_desc_find_function_by_pin(pctl,
@@ -1099,8 +1102,21 @@ static int sunxi_pinctrl_irq_request_resources(struct irq_data *d)
 	if (!func)
 		return -EINVAL;
 
-	ret = gpiochip_lock_as_irq(pctl->chip,
-			pctl->irq_array[d->hwirq] - pctl->desc->pin_base);
+	offset = pctl->irq_array[d->hwirq] - pctl->desc->pin_base;
+	sunxi_mux_reg(pctl, offset, &reg, &shift, &mask);
+	muxval = (readl(pctl->membase + reg) & mask) >> shift;
+
+	/* Change muxing to GPIO INPUT mode if at reset value */
+	if (pctl->flags & SUNXI_PINCTRL_NEW_REG_LAYOUT)
+		disabled_mux = SUN4I_FUNC_DISABLED_NEW;
+	else
+		disabled_mux = SUN4I_FUNC_DISABLED_OLD;
+
+	if (muxval == disabled_mux)
+		sunxi_pmx_set(pctl->pctl_dev, pctl->irq_array[d->hwirq],
+			      SUN4I_FUNC_INPUT);
+
+	ret = gpiochip_lock_as_irq(pctl->chip, offset);
 	if (ret) {
 		dev_err(pctl->dev, "unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index 22bffac1c3f0..0daf7600e2fb 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -86,6 +86,8 @@
 
 #define SUN4I_FUNC_INPUT	0
 #define SUN4I_FUNC_IRQ		6
+#define SUN4I_FUNC_DISABLED_OLD 7
+#define SUN4I_FUNC_DISABLED_NEW 15
 
 #define SUNXI_PINCTRL_VARIANT_MASK	GENMASK(7, 0)
 #define SUNXI_PINCTRL_NEW_REG_LAYOUT	BIT(8)
-- 
cgit v1.2.3


From a3e93cac25316aad03bf561e3c205f4ca0b8f452 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 20 Mar 2026 10:25:21 +0100
Subject: x86/cpu: Add comment clarifying CRn pinning

To avoid future confusion on the purpose and design of the CRn pinning code.

Also note that if the attacker controls page-tables, the CRn bits lose much of
the attraction anyway.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://patch.msgid.link/20260320092521.GG3739106@noisy.programming.kicks-ass.net
---
 arch/x86/kernel/cpu/common.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c57e8972d30f..ec0670114efa 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -434,6 +434,19 @@ static __always_inline void setup_lass(struct cpuinfo_x86 *c)
 /* These bits should not change their value after CPU init is finished. */
 static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP |
 					     X86_CR4_FSGSBASE | X86_CR4_CET;
+
+/*
+ * The CR pinning protects against ROP on the 'mov %reg, %CRn' instruction(s).
+ * Since you can ROP directly to these instructions (barring shadow stack),
+ * any protection must follow immediately and unconditionally after that.
+ *
+ * Specifically, the CR[04] write functions below will have the value
+ * validation controlled by the @cr_pinning static_branch which is
+ * __ro_after_init, just like the cr4_pinned_bits value.
+ *
+ * Once set, an attacker will have to defeat page-tables to get around these
+ * restrictions. Which is a much bigger ask than 'simple' ROP.
+ */
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
-- 
cgit v1.2.3


From 87997b6c6516e049cbaf2fc6810b213d587a06b1 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Tue, 17 Feb 2026 16:41:18 +0100
Subject: drm/xe/pf: Fix use-after-free in migration restore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When an error is returned from xe_sriov_pf_migration_restore_produce(),
the data pointer is not set to NULL, which can trigger use-after-free
in subsequent .write() calls.
Set the pointer to NULL upon error to fix the problem.

Fixes: 1ed30397c0b92 ("drm/xe/pf: Add support for encap/decap of bitstream to/from packet")
Reported-by: Sebastian Österlund <sebastian.osterlund@intel.com>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7230
Reviewed-by: Shuicheng Lin <shuicheng.lin@intel.com>
Link: https://patch.msgid.link/20260217154118.176902-1-michal.winiarski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
(cherry picked from commit 4f53d8c6d23527d734fe3531d08e15cb170a0819)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sriov_packet.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_sriov_packet.c b/drivers/gpu/drm/xe/xe_sriov_packet.c
index 968f32496282..2ae9eff2a7c0 100644
--- a/drivers/gpu/drm/xe/xe_sriov_packet.c
+++ b/drivers/gpu/drm/xe/xe_sriov_packet.c
@@ -341,6 +341,8 @@ ssize_t xe_sriov_packet_write_single(struct xe_device *xe, unsigned int vfid,
 		ret = xe_sriov_pf_migration_restore_produce(xe, vfid, *data);
 		if (ret) {
 			xe_sriov_packet_free(*data);
+			*data = NULL;
+
 			return ret;
 		}
 
-- 
cgit v1.2.3


From ef3d549e1deb3466c61f3b01d22fc3fe3e5efb08 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 19 Mar 2026 00:12:34 +0800
Subject: spi: sn-f-ospi: Fix resource leak in f_ospi_probe()

In f_ospi_probe(), when num_cs validation fails, it returns without
calling spi_controller_put() on the SPI controller, which causes a
resource leak.

Use devm_spi_alloc_host() instead of spi_alloc_host() to ensure the
SPI controller is properly freed when probe fails.

Fixes: 1b74dd64c861 ("spi: Add Socionext F_OSPI SPI flash controller driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260319-sn-f-v1-1-33a6738d2da8@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sn-f-ospi.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c
index bfcc140df810..1f554aa7ca27 100644
--- a/drivers/spi/spi-sn-f-ospi.c
+++ b/drivers/spi/spi-sn-f-ospi.c
@@ -612,7 +612,7 @@ static int f_ospi_probe(struct platform_device *pdev)
 	u32 num_cs = OSPI_NUM_CS;
 	int ret;
 
-	ctlr = spi_alloc_host(dev, sizeof(*ospi));
+	ctlr = devm_spi_alloc_host(dev, sizeof(*ospi));
 	if (!ctlr)
 		return -ENOMEM;
 
@@ -635,16 +635,12 @@ static int f_ospi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ospi);
 
 	ospi->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(ospi->base)) {
-		ret = PTR_ERR(ospi->base);
-		goto err_put_ctlr;
-	}
+	if (IS_ERR(ospi->base))
+		return PTR_ERR(ospi->base);
 
 	ospi->clk = devm_clk_get_enabled(dev, NULL);
-	if (IS_ERR(ospi->clk)) {
-		ret = PTR_ERR(ospi->clk);
-		goto err_put_ctlr;
-	}
+	if (IS_ERR(ospi->clk))
+		return PTR_ERR(ospi->clk);
 
 	mutex_init(&ospi->mlock);
 
@@ -661,9 +657,6 @@ static int f_ospi_probe(struct platform_device *pdev)
 err_destroy_mutex:
 	mutex_destroy(&ospi->mlock);
 
-err_put_ctlr:
-	spi_controller_put(ctlr);
-
 	return ret;
 }
 
-- 
cgit v1.2.3


From a42c9b8b0c00ecd9b7467844f2fbfc766898bf54 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Thu, 19 Mar 2026 00:12:35 +0800
Subject: spi: sn-f-ospi: Use devm_mutex_init() to simplify code

Switch to devm_mutex_init() to handle mutex destruction automatically.
This simplifies the error paths in probe() and removes the need for an
explicit mutex_destroy() in remove() callback.

Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260319-sn-f-v1-2-33a6738d2da8@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sn-f-ospi.c | 25 +++++--------------------
 1 file changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c
index 1f554aa7ca27..3c61c799723b 100644
--- a/drivers/spi/spi-sn-f-ospi.c
+++ b/drivers/spi/spi-sn-f-ospi.c
@@ -642,29 +642,15 @@ static int f_ospi_probe(struct platform_device *pdev)
 	if (IS_ERR(ospi->clk))
 		return PTR_ERR(ospi->clk);
 
-	mutex_init(&ospi->mlock);
-
-	ret = f_ospi_init(ospi);
+	ret = devm_mutex_init(dev, &ospi->mlock);
 	if (ret)
-		goto err_destroy_mutex;
+		return ret;
 
-	ret = devm_spi_register_controller(dev, ctlr);
+	ret = f_ospi_init(ospi);
 	if (ret)
-		goto err_destroy_mutex;
-
-	return 0;
-
-err_destroy_mutex:
-	mutex_destroy(&ospi->mlock);
-
-	return ret;
-}
-
-static void f_ospi_remove(struct platform_device *pdev)
-{
-	struct f_ospi *ospi = platform_get_drvdata(pdev);
+		return ret;
 
-	mutex_destroy(&ospi->mlock);
+	return devm_spi_register_controller(dev, ctlr);
 }
 
 static const struct of_device_id f_ospi_dt_ids[] = {
@@ -679,7 +665,6 @@ static struct platform_driver f_ospi_driver = {
 		.of_match_table = f_ospi_dt_ids,
 	},
 	.probe = f_ospi_probe,
-	.remove = f_ospi_remove,
 };
 module_platform_driver(f_ospi_driver);
 
-- 
cgit v1.2.3


From 38dfd294e24c0f397413799c2e5633aedb2058bf Mon Sep 17 00:00:00 2001
From: Muhammad Usama Anjum <usama.anjum@arm.com>
Date: Tue, 10 Mar 2026 17:17:39 +0000
Subject: mailmap: update email address for Muhammad Usama Anjum

Add updated email address.

Link: https://lkml.kernel.org/r/20260310171757.3970390-1-usama.anjum@arm.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Carlos Bilbao <carlos.bilbao@kernel.org>
Cc: Hans Verkuil <hverkuil@kernel.org>
Cc: Jakub Kacinski <kuba@kernel.org>
Cc: Martin Kepplinger <martink@posteo.de>
Cc: Shannon Nelson <sln@onemain.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 40b4db2b2d60..7d14504daf24 100644
--- a/.mailmap
+++ b/.mailmap
@@ -587,6 +587,7 @@ Morten Welinder <terra@gnome.org>
 Morten Welinder <welinder@anemone.rentec.com>
 Morten Welinder <welinder@darter.rentec.com>
 Morten Welinder <welinder@troll.com>
+Muhammad Usama Anjum <usama.anjum@arm.com> <usama.anjum@collabora.com>
 Mukesh Ojha <quic_mojha@quicinc.com> <mojha@codeaurora.org>
 Muna Sinada <quic_msinada@quicinc.com> <msinada@codeaurora.org>
 Murali Nalajala <quic_mnalajal@quicinc.com> <mnalajal@codeaurora.org>
-- 
cgit v1.2.3


From 631c1111501f34980649242751e93cfdadfd1f1c Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Date: Mon, 16 Mar 2026 14:01:22 +0000
Subject: mm/zswap: add missing kunmap_local()

Commit e2c3b6b21c77 ("mm: zswap: use SG list decompression APIs from
zsmalloc") updated zswap_decompress() to use the scatterwalk API to copy
data for uncompressed pages.

In doing so, it mapped kernel memory locally for 32-bit kernels using
kmap_local_folio(), however it never unmapped this memory.

This resulted in the linked syzbot report where a BUG_ON() is triggered
due to leaking the kmap slot.

This patch fixes the issue by explicitly unmapping the established kmap.


Also, add flush_dcache_folio() after the kunmap_local() call

I had assumed that a new folio here combined with the flush that is done at
the point of setting the PTE would suffice, but it doesn't seem that's
actually the case, as update_mmu_cache() will in many archtectures only
actually flush entries where a dcache flush was done on a range previously.

I had also wondered whether kunmap_local() might suffice, but it doesn't
seem to be the case.

Some arches do seem to actually dcache flush on unmap, parisc does it if
CONFIG_HIGHMEM is not set by setting ARCH_HAS_FLUSH_ON_KUNMAP and calling
kunmap_flush_on_unmap() from __kunmap_local(), otherwise non-CONFIG_HIGHMEM
callers do nothing here.

Otherwise arch_kmap_local_pre_unmap() is called which does:

* sparc - flush_cache_all()
* arm - if VIVT, __cpuc_flush_dcache_area()
* otherwise - nothing

Also arch_kmap_local_post_unmap() is called which does:

* arm - local_flush_tlb_kernel_page()
* csky - kmap_flush_tlb()
* microblaze, ppc - local_flush_tlb_page()
* mips - local_flush_tlb_one()
* sparc - flush_tlb_all() (again)
* x86 - arch_flush_lazy_mmu_mode()
* otherwise - nothing

But this is only if it's high memory, and doesn't cover all architectures,
so is presumably intended to handle other cache consistency concerns.

In any case, VIPT is problematic here whether low or high memory (in spite
of what the documentation claims, see [0] - 'the kernel did write to a page
that is in the page cache page and / or in high memory'), because dirty
cache lines may exist at the set indexed by the kernel direct mapping,
which won't exist in the set indexed by any subsequent userland mapping,
meaning userland might read stale data from L2 cache.

Even if the documentation is correct and low memory is fine not to be
flushed here, we can't be sure as to whether the memory is low or high
(kmap_local_folio() will be a no-op if low), and this call should be
harmless if it is low.

VIVT would require more work if the memory were shared and already mapped,
but this isn't the case here, and would anyway be handled by the dcache
flush call.

In any case, we definitely need this flush as far as I can tell.

And we should probably consider updating the documentation unless it turns
out there's somehow dcache synchronisation that happens for low
memory/64-bit kernels elsewhere?

[ljs@kernel.org: add flush_dcache_folio() after the kunmap_local() call]
  Link: https://lkml.kernel.org/r/13e09a99-181f-45ac-a18d-057faf94bccb@lucifer.local
Link: https://lkml.kernel.org/r/20260316140122.339697-1-ljs@kernel.org
Link: https://docs.kernel.org/core-api/cachetlb.html [0]
Fixes: e2c3b6b21c77 ("mm: zswap: use SG list decompression APIs from zsmalloc")
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reported-by: syzbot+fe426bef95363177631d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69b75e2c.050a0220.12d28.015a.GAE@google.com
Acked-by: Yosry Ahmed <yosry@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Acked-by: Yosry Ahmed <yosry@kernel.org>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/zswap.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index e6ec3295bdb0..16b2ef7223e1 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -942,9 +942,15 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 
 	/* zswap entries of length PAGE_SIZE are not compressed. */
 	if (entry->length == PAGE_SIZE) {
+		void *dst;
+
 		WARN_ON_ONCE(input->length != PAGE_SIZE);
-		memcpy_from_sglist(kmap_local_folio(folio, 0), input, 0, PAGE_SIZE);
+
+		dst = kmap_local_folio(folio, 0);
+		memcpy_from_sglist(dst, input, 0, PAGE_SIZE);
 		dlen = PAGE_SIZE;
+		kunmap_local(dst);
+		flush_dcache_folio(folio);
 	} else {
 		sg_init_table(&output, 1);
 		sg_set_folio(&output, folio, PAGE_SIZE, 0);
-- 
cgit v1.2.3


From 84481e705ab07ed46e56587fe846af194acacafe Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 16 Mar 2026 16:51:17 -0700
Subject: mm/damon/stat: monitor all System RAM resources

DAMON_STAT usage document (Documentation/admin-guide/mm/damon/stat.rst)
says it monitors the system's entire physical memory.  But, it is
monitoring only the biggest System RAM resource of the system.  When there
are multiple System RAM resources, this results in monitoring only an
unexpectedly small fraction of the physical memory.  For example, suppose
the system has a 500 GiB System RAM, 10 MiB non-System RAM, and 500 GiB
System RAM resources in order on the physical address space.  DAMON_STAT
will monitor only the first 500 GiB System RAM.  This situation is
particularly common on NUMA systems.

Select a physical address range that covers all System RAM areas of the
system, to fix this issue and make it work as documented.

[sj@kernel.org: return error if monitoring target region is invalid]
  Link: https://lkml.kernel.org/r/20260317053631.87907-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20260316235118.873-1-sj@kernel.org
Fixes: 369c415e6073 ("mm/damon: introduce DAMON_STAT module")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.17+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/stat.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/mm/damon/stat.c b/mm/damon/stat.c
index 25fb44ccf99d..cf2c5a541eee 100644
--- a/mm/damon/stat.c
+++ b/mm/damon/stat.c
@@ -145,12 +145,59 @@ static int damon_stat_damon_call_fn(void *data)
 	return 0;
 }
 
+struct damon_stat_system_ram_range_walk_arg {
+	bool walked;
+	struct resource res;
+};
+
+static int damon_stat_system_ram_walk_fn(struct resource *res, void *arg)
+{
+	struct damon_stat_system_ram_range_walk_arg *a = arg;
+
+	if (!a->walked) {
+		a->walked = true;
+		a->res.start = res->start;
+	}
+	a->res.end = res->end;
+	return 0;
+}
+
+static unsigned long damon_stat_res_to_core_addr(resource_size_t ra,
+		unsigned long addr_unit)
+{
+	/*
+	 * Use div_u64() for avoiding linking errors related with __udivdi3,
+	 * __aeabi_uldivmod, or similar problems.  This should also improve the
+	 * performance optimization (read div_u64() comment for the detail).
+	 */
+	if (sizeof(ra) == 8 && sizeof(addr_unit) == 4)
+		return div_u64(ra, addr_unit);
+	return ra / addr_unit;
+}
+
+static int damon_stat_set_monitoring_region(struct damon_target *t,
+		unsigned long addr_unit, unsigned long min_region_sz)
+{
+	struct damon_addr_range addr_range;
+	struct damon_stat_system_ram_range_walk_arg arg = {};
+
+	walk_system_ram_res(0, -1, &arg, damon_stat_system_ram_walk_fn);
+	if (!arg.walked)
+		return -EINVAL;
+	addr_range.start = damon_stat_res_to_core_addr(
+			arg.res.start, addr_unit);
+	addr_range.end = damon_stat_res_to_core_addr(
+			arg.res.end + 1, addr_unit);
+	if (addr_range.end <= addr_range.start)
+		return -EINVAL;
+	return damon_set_regions(t, &addr_range, 1, min_region_sz);
+}
+
 static struct damon_ctx *damon_stat_build_ctx(void)
 {
 	struct damon_ctx *ctx;
 	struct damon_attrs attrs;
 	struct damon_target *target;
-	unsigned long start = 0, end = 0;
 
 	ctx = damon_new_ctx();
 	if (!ctx)
@@ -180,8 +227,8 @@ static struct damon_ctx *damon_stat_build_ctx(void)
 	if (!target)
 		goto free_out;
 	damon_add_target(ctx, target);
-	if (damon_set_region_biggest_system_ram_default(target, &start, &end,
-							ctx->min_region_sz))
+	if (damon_stat_set_monitoring_region(target, ctx->addr_unit,
+				ctx->min_region_sz))
 		goto free_out;
 	return ctx;
 free_out:
-- 
cgit v1.2.3


From 5a184f1cb43a8e035251c635f5c47da5dc3e3049 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 20 Mar 2026 11:12:17 +0100
Subject: ASoC: Intel: catpt: Fix the device initialization

The DMA mask shall be coerced before any buffer allocations for the
device are done.  At the same time explain why DMA mask of 31 bits is
used in the first place.

Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Fixes: 7a10b66a5df9 ("ASoC: Intel: catpt: Device driver lifecycle")
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20260320101217.1243688-1-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/catpt/device.c | 10 +++++++++-
 sound/soc/intel/catpt/dsp.c    |  3 ---
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/catpt/device.c b/sound/soc/intel/catpt/device.c
index 0638aecba40d..0b3f20e384c7 100644
--- a/sound/soc/intel/catpt/device.c
+++ b/sound/soc/intel/catpt/device.c
@@ -281,7 +281,15 @@ static int catpt_acpi_probe(struct platform_device *pdev)
 	if (IS_ERR(cdev->pci_ba))
 		return PTR_ERR(cdev->pci_ba);
 
-	/* alloc buffer for storing DRAM context during dx transitions */
+	/*
+	 * As per design HOST is responsible for preserving firmware's runtime
+	 * context during D0 -> D3 -> D0 transitions.  Addresses used for DMA
+	 * to/from HOST memory shall be outside the reserved range of 0xFFFxxxxx.
+	 */
+	ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31));
+	if (ret)
+		return ret;
+
 	cdev->dxbuf_vaddr = dmam_alloc_coherent(dev, catpt_dram_size(cdev),
 						&cdev->dxbuf_paddr, GFP_KERNEL);
 	if (!cdev->dxbuf_vaddr)
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 008a20a2acbd..677f348909c8 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -125,9 +125,6 @@ int catpt_dmac_probe(struct catpt_dev *cdev)
 	dmac->dev = cdev->dev;
 	dmac->irq = cdev->irq;
 
-	ret = dma_coerce_mask_and_coherent(cdev->dev, DMA_BIT_MASK(31));
-	if (ret)
-		return ret;
 	/*
 	 * Caller is responsible for putting device in D0 to allow
 	 * for I/O and memory access before probing DW.
-- 
cgit v1.2.3


From 63542bb402b7013171c9f621c28b609eda4dbf1f Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 22 Mar 2026 21:29:56 +0800
Subject: spi: meson-spicc: Fix double-put in remove path

meson_spicc_probe() registers the controller with
devm_spi_register_controller(), so teardown already drops the
controller reference via devm cleanup.

Calling spi_controller_put() again in meson_spicc_remove()
causes a double-put.

Fixes: 8311ee2164c5 ("spi: meson-spicc: fix memory leak in meson_spicc_remove")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260322-rockchip-v1-1-fac3f0c6dad8@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-meson-spicc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index a7001b9e36e6..57768da3205d 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -1101,8 +1101,6 @@ static void meson_spicc_remove(struct platform_device *pdev)
 
 	/* Disable SPI */
 	writel(0, spicc->base + SPICC_CONREG);
-
-	spi_controller_put(spicc->host);
 }
 
 static const struct meson_spicc_data meson_spicc_gx_data = {
-- 
cgit v1.2.3


From aed3d041ab061ec8a64f50a3edda0f4db7280025 Mon Sep 17 00:00:00 2001
From: Yussuf Khalil <dev@pp3345.net>
Date: Fri, 6 Mar 2026 12:06:35 +0000
Subject: drm/amd/display: Do not skip unrelated mode changes in DSC validation

Starting with commit 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in
atomic check"), amdgpu resets the CRTC state mode_changed flag to false when
recomputing the DSC configuration results in no timing change for a particular
stream.

However, this is incorrect in scenarios where a change in MST/DSC configuration
happens in the same KMS commit as another (unrelated) mode change. For example,
the integrated panel of a laptop may be configured differently (e.g., HDR
enabled/disabled) depending on whether external screens are attached. In this
case, plugging in external DP-MST screens may result in the mode_changed flag
being dropped incorrectly for the integrated panel if its DSC configuration
did not change during precomputation in pre_validate_dsc().

At this point, however, dm_update_crtc_state() has already created new streams
for CRTCs with DSC-independent mode changes. In turn,
amdgpu_dm_commit_streams() will never release the old stream, resulting in a
memory leak. amdgpu_dm_atomic_commit_tail() will never acquire a reference to
the new stream either, which manifests as a use-after-free when the stream gets
disabled later on:

BUG: KASAN: use-after-free in dc_stream_release+0x25/0x90 [amdgpu]
Write of size 4 at addr ffff88813d836524 by task kworker/9:9/29977

Workqueue: events drm_mode_rmfb_work_fn
Call Trace:
 <TASK>
 dump_stack_lvl+0x6e/0xa0
 print_address_description.constprop.0+0x88/0x320
 ? dc_stream_release+0x25/0x90 [amdgpu]
 print_report+0xfc/0x1ff
 ? srso_alias_return_thunk+0x5/0xfbef5
 ? __virt_addr_valid+0x225/0x4e0
 ? dc_stream_release+0x25/0x90 [amdgpu]
 kasan_report+0xe1/0x180
 ? dc_stream_release+0x25/0x90 [amdgpu]
 kasan_check_range+0x125/0x200
 dc_stream_release+0x25/0x90 [amdgpu]
 dc_state_destruct+0x14d/0x5c0 [amdgpu]
 dc_state_release.part.0+0x4e/0x130 [amdgpu]
 dm_atomic_destroy_state+0x3f/0x70 [amdgpu]
 drm_atomic_state_default_clear+0x8ee/0xf30
 ? drm_mode_object_put.part.0+0xb1/0x130
 __drm_atomic_state_free+0x15c/0x2d0
 atomic_remove_fb+0x67e/0x980

Since there is no reliable way of figuring out whether a CRTC has unrelated
mode changes pending at the time of DSC validation, remember the value of the
mode_changed flag from before the point where a CRTC was marked as potentially
affected by a change in DSC configuration. Reset the mode_changed flag to this
earlier value instead in pre_validate_dsc().

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5004
Fixes: 17ce8a6907f7 ("drm/amd/display: Add dsc pre-validation in atomic check")
Signed-off-by: Yussuf Khalil <dev@pp3345.net>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit cc7c7121ae082b7b82891baa7280f1ff2608f22b)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c           | 5 +++++
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h           | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 4 +++-
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 085cc98bd875..a9c398b1516b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -12523,6 +12523,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	}
 
 	if (dc_resource_is_dsc_encoding_supported(dc)) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+			dm_new_crtc_state->mode_changed_independent_from_dsc = new_crtc_state->mode_changed;
+		}
+
 		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
 				ret = add_affected_mst_dsc_crtcs(state, crtc);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 800813671748..d15812d51d72 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -984,6 +984,7 @@ struct dm_crtc_state {
 
 	bool freesync_vrr_info_changed;
 
+	bool mode_changed_independent_from_dsc;
 	bool dsc_force_changed;
 	bool vrr_supported;
 	struct mod_freesync_config freesync_config;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7be50e8c0636..5d8c4c7020b1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -1744,9 +1744,11 @@ int pre_validate_dsc(struct drm_atomic_state *state,
 			int ind = find_crtc_index_in_state_by_stream(state, stream);
 
 			if (ind >= 0) {
+				struct dm_crtc_state *dm_new_crtc_state = to_dm_crtc_state(state->crtcs[ind].new_state);
+
 				DRM_INFO_ONCE("%s:%d MST_DSC no mode changed for stream 0x%p\n",
 						__func__, __LINE__, stream);
-				state->crtcs[ind].new_state->mode_changed = 0;
+				dm_new_crtc_state->base.mode_changed = dm_new_crtc_state->mode_changed_independent_from_dsc;
 			}
 		}
 	}
-- 
cgit v1.2.3


From 2d300ebfc411205fa31ba7741c5821d381912381 Mon Sep 17 00:00:00 2001
From: Ruijing Dong <ruijing.dong@amd.com>
Date: Tue, 17 Mar 2026 13:54:11 -0400
Subject: drm/amdgpu: fix strsep() corrupting lockup_timeout on multi-GPU (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

amdgpu_device_get_job_timeout_settings() passes a pointer directly
to the global amdgpu_lockup_timeout[] buffer into strsep().
strsep() destructively replaces delimiter characters with '\0'
in-place.

On multi-GPU systems, this function is called once per device.
When a multi-value setting like "0,0,0,-1" is used, the first
GPU's call transforms the global buffer into "0\00\00\0-1". The
second GPU then sees only "0" (terminated at the first '\0'),
parses a single value, hits the single-value fallthrough
(index == 1), and applies timeout=0 to all rings — causing
immediate false job timeouts.

Fix this by copying into a stack-local array before calling
strsep(), so the global module parameter buffer remains intact
across calls. The buffer is AMDGPU_MAX_TIMEOUT_PARAM_LENGTH
(256) bytes, which is safe for the stack.

v2: wrap commit message to 72 columns, add Assisted-by tag.
v3: use stack array with strscpy() instead of kstrdup()/kfree()
    to avoid unnecessary heap allocation (Christian).

This patch was developed with assistance from Claude (claude-opus-4-6).

Assisted-by: Claude:claude-opus-4-6
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 94d79f51efecb74be1d88dde66bdc8bfcca17935)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d8296dfc5e8a..6d8531f9b882 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4207,7 +4207,8 @@ fail:
 
 static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 {
-	char *input = amdgpu_lockup_timeout;
+	char buf[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
+	char *input = buf;
 	char *timeout_setting = NULL;
 	int index = 0;
 	long timeout;
@@ -4217,9 +4218,17 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 	adev->gfx_timeout = adev->compute_timeout = adev->sdma_timeout =
 		adev->video_timeout = msecs_to_jiffies(2000);
 
-	if (!strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH))
+	if (!strnlen(amdgpu_lockup_timeout, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH))
 		return 0;
 
+	/*
+	 * strsep() destructively modifies its input by replacing delimiters
+	 * with '\0'. Use a stack copy so the global module parameter buffer
+	 * remains intact for multi-GPU systems where this function is called
+	 * once per device.
+	 */
+	strscpy(buf, amdgpu_lockup_timeout, sizeof(buf));
+
 	while ((timeout_setting = strsep(&input, ",")) &&
 	       strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
 		ret = kstrtol(timeout_setting, 0, &timeout);
-- 
cgit v1.2.3


From 14b81abe7bdc25f8097906fc2f91276ffedb2d26 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Mon, 16 Mar 2026 11:01:30 -0400
Subject: drm/amdgpu: prevent immediate PASID reuse case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PASID resue could cause interrupt issue when process
immediately runs into hw state left by previous
process exited with the same PASID, it's possible that
page faults are still pending in the IH ring buffer when
the process exits and frees up its PASID. To prevent the
case, it uses idr cyclic allocator same as kernel pid's.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8f1de51f49be692de137c8525106e0fce2d1912d)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 45 +++++++++++++++++++++++----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c  |  1 +
 3 files changed, 34 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 64c519cd7395..d88523568b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -35,10 +35,13 @@
  * PASIDs are global address space identifiers that can be shared
  * between the GPU, an IOMMU and the driver. VMs on different devices
  * may use the same PASID if they share the same address
- * space. Therefore PASIDs are allocated using a global IDA. VMs are
- * looked up from the PASID per amdgpu_device.
+ * space. Therefore PASIDs are allocated using IDR cyclic allocator
+ * (similar to kernel PID allocation) which naturally delays reuse.
+ * VMs are looked up from the PASID per amdgpu_device.
  */
-static DEFINE_IDA(amdgpu_pasid_ida);
+
+static DEFINE_IDR(amdgpu_pasid_idr);
+static DEFINE_SPINLOCK(amdgpu_pasid_idr_lock);
 
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
@@ -50,8 +53,8 @@ struct amdgpu_pasid_cb {
  * amdgpu_pasid_alloc - Allocate a PASID
  * @bits: Maximum width of the PASID in bits, must be at least 1
  *
- * Allocates a PASID of the given width while keeping smaller PASIDs
- * available if possible.
+ * Uses kernel's IDR cyclic allocator (same as PID allocation).
+ * Allocates sequentially with automatic wrap-around.
  *
  * Returns a positive integer on success. Returns %-EINVAL if bits==0.
  * Returns %-ENOSPC if no PASID was available. Returns %-ENOMEM on
@@ -59,14 +62,15 @@ struct amdgpu_pasid_cb {
  */
 int amdgpu_pasid_alloc(unsigned int bits)
 {
-	int pasid = -EINVAL;
+	int pasid;
 
-	for (bits = min(bits, 31U); bits > 0; bits--) {
-		pasid = ida_alloc_range(&amdgpu_pasid_ida, 1U << (bits - 1),
-					(1U << bits) - 1, GFP_KERNEL);
-		if (pasid != -ENOSPC)
-			break;
-	}
+	if (bits == 0)
+		return -EINVAL;
+
+	spin_lock(&amdgpu_pasid_idr_lock);
+	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
+				 1U << bits, GFP_KERNEL);
+	spin_unlock(&amdgpu_pasid_idr_lock);
 
 	if (pasid >= 0)
 		trace_amdgpu_pasid_allocated(pasid);
@@ -81,7 +85,10 @@ int amdgpu_pasid_alloc(unsigned int bits)
 void amdgpu_pasid_free(u32 pasid)
 {
 	trace_amdgpu_pasid_freed(pasid);
-	ida_free(&amdgpu_pasid_ida, pasid);
+
+	spin_lock(&amdgpu_pasid_idr_lock);
+	idr_remove(&amdgpu_pasid_idr, pasid);
+	spin_unlock(&amdgpu_pasid_idr_lock);
 }
 
 static void amdgpu_pasid_free_cb(struct dma_fence *fence,
@@ -616,3 +623,15 @@ void amdgpu_vmid_mgr_fini(struct amdgpu_device *adev)
 		}
 	}
 }
+
+/**
+ * amdgpu_pasid_mgr_cleanup - cleanup PASID manager
+ *
+ * Cleanup the IDR allocator.
+ */
+void amdgpu_pasid_mgr_cleanup(void)
+{
+	spin_lock(&amdgpu_pasid_idr_lock);
+	idr_destroy(&amdgpu_pasid_idr);
+	spin_unlock(&amdgpu_pasid_idr_lock);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index b3649cd3af56..a57919478d3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -74,6 +74,7 @@ int amdgpu_pasid_alloc(unsigned int bits);
 void amdgpu_pasid_free(u32 pasid);
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 			       u32 pasid);
+void amdgpu_pasid_mgr_cleanup(void);
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index c60cbce356cf..d54afeb7b2a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2898,6 +2898,7 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 	xa_destroy(&adev->vm_manager.pasids);
 
 	amdgpu_vmid_mgr_fini(adev);
+	amdgpu_pasid_mgr_cleanup();
 }
 
 /**
-- 
cgit v1.2.3


From 37c2caa167b0b8aca4f74c32404c5288b876a2a3 Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Mon, 9 Mar 2026 11:16:08 -0600
Subject: drm/amd/display: Fix drm_edid leak in amdgpu_dm

[WHAT]
When a sink is connected, aconnector->drm_edid was overwritten without
freeing the previous allocation, causing a memory leak on resume.

[HOW]
Free the previous drm_edid before updating it.

Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Chuanyu Tseng <chuanyu.tseng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 52024a94e7111366141cfc5d888b2ef011f879e5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a9c398b1516b..acc3d8dad4a3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3909,8 +3909,9 @@ void amdgpu_dm_update_connector_after_detect(
 
 		aconnector->dc_sink = sink;
 		dc_sink_retain(aconnector->dc_sink);
+		drm_edid_free(aconnector->drm_edid);
+		aconnector->drm_edid = NULL;
 		if (sink->dc_edid.length == 0) {
-			aconnector->drm_edid = NULL;
 			hdmi_cec_unset_edid(aconnector);
 			if (aconnector->dc_link->aux_mode) {
 				drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux);
-- 
cgit v1.2.3


From cdbc3b62cfc2785da32b82260f852370cc1f2a6a Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Wed, 18 Mar 2026 13:48:30 +0800
Subject: drm/amd/pm: Skip redundant UCLK restore in smu_v13_0_6

Only reapply UCLK soft limits during PP_OD_RESTORE_DEFAULT when the
current max differs from the DPM table max. This avoids redundant
SMC updates and prevents -EINVAL on restore when no change is needed.

Fixes: b7a900344546 ("drm/amd/pm: Allow setting max UCLK on SMU v13.0.6")
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 17f11bbbc76c8e83c8474ea708316b1e3631d927)
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 896b51c8a9a7..b44a85697a30 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2122,6 +2122,7 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu,
 {
 	struct smu_dpm_context *smu_dpm = &(smu->smu_dpm);
 	struct smu_13_0_dpm_context *dpm_context = smu_dpm->dpm_context;
+	struct smu_dpm_table *uclk_table = &dpm_context->dpm_tables.uclk_table;
 	struct smu_umd_pstate_table *pstate_table = &smu->pstate_table;
 	uint32_t min_clk;
 	uint32_t max_clk;
@@ -2221,14 +2222,16 @@ static int smu_v13_0_6_usr_edit_dpm_table(struct smu_context *smu,
 			if (ret)
 				return ret;
 
-			min_clk = SMU_DPM_TABLE_MIN(
-				&dpm_context->dpm_tables.uclk_table);
-			max_clk = SMU_DPM_TABLE_MAX(
-				&dpm_context->dpm_tables.uclk_table);
-			ret = smu_v13_0_6_set_soft_freq_limited_range(
-				smu, SMU_UCLK, min_clk, max_clk, false);
-			if (ret)
-				return ret;
+			if (SMU_DPM_TABLE_MAX(uclk_table) !=
+			    pstate_table->uclk_pstate.curr.max) {
+				min_clk = SMU_DPM_TABLE_MIN(&dpm_context->dpm_tables.uclk_table);
+				max_clk = SMU_DPM_TABLE_MAX(&dpm_context->dpm_tables.uclk_table);
+				ret = smu_v13_0_6_set_soft_freq_limited_range(smu,
+									      SMU_UCLK, min_clk,
+									      max_clk, false);
+				if (ret)
+					return ret;
+			}
 			smu_v13_0_reset_custom_level(smu);
 		}
 		break;
-- 
cgit v1.2.3


From 2f0e491faee43181b6a86e90f34016b256042fe1 Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Wed, 18 Mar 2026 13:52:57 +0800
Subject: drm/amd/pm: Return -EOPNOTSUPP for unsupported OD_MCLK on smu_v13_0_6

When SET_UCLK_MAX capability is absent, return -EOPNOTSUPP from
smu_v13_0_6_emit_clk_levels() for OD_MCLK instead of 0. This makes
unsupported OD_MCLK reporting consistent with other clock types
and allows callers to skip the entry cleanly.

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d82e0a72d9189e8acd353988e1a57f85ce479e37)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index b44a85697a30..870bcc86fd79 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -1391,7 +1391,7 @@ static int smu_v13_0_6_emit_clk_levels(struct smu_context *smu,
 		break;
 	case SMU_OD_MCLK:
 		if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SET_UCLK_MAX)))
-			return 0;
+			return -EOPNOTSUPP;
 
 		size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
 		size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n",
-- 
cgit v1.2.3


From 3e6dd28a11083e83e11a284d99fcc9eb748c321c Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Thu, 19 Mar 2026 21:17:38 -0400
Subject: drm/amd/pm: disable OD_FAN_CURVE if temp or pwm range invalid for smu
 v13

Forcibly disable the OD_FAN_CURVE feature when temperature or PWM range is invalid,
otherwise PMFW will reject this configuration on smu v13.0.x

example:
$ sudo cat /sys/bus/pci/devices/<BDF>/gpu_od/fan_ctrl/fan_curve

OD_FAN_CURVE:
0: 0C 0%
1: 0C 0%
2: 0C 0%
3: 0C 0%
4: 0C 0%
OD_RANGE:
FAN_CURVE(hotspot temp): 0C 0C
FAN_CURVE(fan speed): 0% 0%

$ echo "0 50 40" | sudo tee fan_curve

kernel log:
[  756.442527] amdgpu 0000:03:00.0: amdgpu: Fan curve temp setting(50) must be within [0, 0]!
[  777.345800] amdgpu 0000:03:00.0: amdgpu: Fan curve temp setting(50) must be within [0, 0]!

Closes: https://github.com/ROCm/amdgpu/issues/208
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 470891606c5a97b1d0d937e0aa67a3bed9fcb056)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c   | 33 +++++++++++++++++++++-
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c   | 33 +++++++++++++++++++++-
 2 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a8d63d4d1f6e..554f616328c3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -59,6 +59,10 @@
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v13_0_0_dpm_features = {
 	.bits = {
 		SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
@@ -1043,8 +1047,35 @@ static bool smu_v13_0_0_is_od_feature_supported(struct smu_context *smu,
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v13_0_0_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v13_0_0_get_od_setting_limits(struct smu_context *smu,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 5500a0f12f0e..f331e87858c9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -59,6 +59,10 @@
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v13_0_7_dpm_features = {
 	.bits = {
 		SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
@@ -1053,8 +1057,35 @@ static bool smu_v13_0_7_is_od_feature_supported(struct smu_context *smu,
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v13_0_7_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v13_0_7_get_od_setting_limits(struct smu_context *smu,
-- 
cgit v1.2.3


From b52fe51f724385b3ed81e37e510a4a33107e8161 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 17 Feb 2026 17:35:42 +0000
Subject: btrfs: fix super block offset in error message in
 btrfs_validate_super()

Fix the superblock offset mismatch error message in
btrfs_validate_super(): we changed it so that it considers all the
superblocks, but the message still assumes we're only looking at the
first one.

The change from %u to %llu is because we're changing from a constant to
a u64.

Fixes: 069ec957c35e ("btrfs: Refactor btrfs_check_super_valid")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b1b53d713ee9..3524976ccc1d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2531,8 +2531,8 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info,
 
 	if (mirror_num >= 0 &&
 	    btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
-		btrfs_err(fs_info, "super offset mismatch %llu != %u",
-			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+		btrfs_err(fs_info, "super offset mismatch %llu != %llu",
+			  btrfs_super_bytenr(sb), btrfs_sb_offset(mirror_num));
 		ret = -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 5254d4181add9dfaa5e3519edd71cc8f752b2f85 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 17 Feb 2026 14:46:50 +0000
Subject: btrfs: fix zero size inode with non-zero size after log replay

When logging that an inode exists, as part of logging a new name or
logging new dir entries for a directory, we always set the generation of
the logged inode item to 0. This is to signal during log replay (in
overwrite_item()), that we should not set the i_size since we only logged
that an inode exists, so the i_size of the inode in the subvolume tree
must be preserved (as when we log new names or that an inode exists, we
don't log extents).

This works fine except when we have already logged an inode in full mode
or it's the first time we are logging an inode created in a past
transaction, that inode has a new i_size of 0 and then we log a new name
for the inode (due to a new hardlink or a rename), in which case we log
an i_size of 0 for the inode and a generation of 0, which causes the log
replay code to not update the inode's i_size to 0 (in overwrite_item()).

An example scenario:

  mkdir /mnt/dir
  xfs_io -f -c "pwrite 0 64K" /mnt/dir/foo

  sync

  xfs_io -c "truncate 0" -c "fsync" /mnt/dir/foo

  ln /mnt/dir/foo /mnt/dir/bar

  xfs_io -c "fsync" /mnt/dir

  <power fail>

After log replay the file remains with a size of 64K. This is because when
we first log the inode, when we fsync file foo, we log its current i_size
of 0, and then when we create a hard link we log again the inode in exists
mode (LOG_INODE_EXISTS) but we set a generation of 0 for the inode item we
add to the log tree, so during log replay overwrite_item() sees that the
generation is 0 and i_size is 0 so we skip updating the inode's i_size
from 64K to 0.

Fix this by making sure at fill_inode_item() we always log the real
generation of the inode if it was logged in the current transaction with
the i_size we logged before. Also if an inode created in a previous
transaction is logged in exists mode only, make sure we log the i_size
stored in the inode item located from the commit root, so that if we log
multiple times that the inode exists we get the correct i_size.

A test case for fstests will follow soon.

Reported-by: Vyacheslav Kovalevsky <slava.kovalevskiy.2014@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/af8c15fa-4e41-4bb2-885c-0bc4e97532a6@gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 98 +++++++++++++++++++++++++++++++++++------------------
 1 file changed, 65 insertions(+), 33 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9ff3933bc382..fce1b16a882b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4616,21 +4616,32 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 			    struct inode *inode, bool log_inode_only,
 			    u64 logged_isize)
 {
+	u64 gen = BTRFS_I(inode)->generation;
 	u64 flags;
 
 	if (log_inode_only) {
-		/* set the generation to zero so the recover code
-		 * can tell the difference between an logging
-		 * just to say 'this inode exists' and a logging
-		 * to say 'update this inode with these values'
+		/*
+		 * Set the generation to zero so the recover code can tell the
+		 * difference between a logging just to say 'this inode exists'
+		 * and a logging to say 'update this inode with these values'.
+		 * But only if the inode was not already logged before.
+		 * We access ->logged_trans directly since it was already set
+		 * up in the call chain by btrfs_log_inode(), and data_race()
+		 * to avoid false alerts from KCSAN and since it was set already
+		 * and one can set it to 0 since that only happens on eviction
+		 * and we are holding a ref on the inode.
 		 */
-		btrfs_set_inode_generation(leaf, item, 0);
+		ASSERT(data_race(BTRFS_I(inode)->logged_trans) > 0);
+		if (data_race(BTRFS_I(inode)->logged_trans) < trans->transid)
+			gen = 0;
+
 		btrfs_set_inode_size(leaf, item, logged_isize);
 	} else {
-		btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
 		btrfs_set_inode_size(leaf, item, inode->i_size);
 	}
 
+	btrfs_set_inode_generation(leaf, item, gen);
+
 	btrfs_set_inode_uid(leaf, item, i_uid_read(inode));
 	btrfs_set_inode_gid(leaf, item, i_gid_read(inode));
 	btrfs_set_inode_mode(leaf, item, inode->i_mode);
@@ -5448,42 +5459,63 @@ process:
 	return 0;
 }
 
-static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
-			     struct btrfs_path *path, u64 *size_ret)
+static int get_inode_size_to_log(struct btrfs_trans_handle *trans,
+				 struct btrfs_inode *inode,
+				 struct btrfs_path *path, u64 *size_ret)
 {
 	struct btrfs_key key;
+	struct btrfs_inode_item *item;
 	int ret;
 
 	key.objectid = btrfs_ino(inode);
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	ret = btrfs_search_slot(NULL, log, &key, path, 0, 0);
-	if (ret < 0) {
-		return ret;
-	} else if (ret > 0) {
-		*size_ret = 0;
-	} else {
-		struct btrfs_inode_item *item;
+	/*
+	 * Our caller called inode_logged(), so logged_trans is up to date.
+	 * Use data_race() to silence any warning from KCSAN. Once logged_trans
+	 * is set, it can only be reset to 0 after inode eviction.
+	 */
+	if (data_race(inode->logged_trans) == trans->transid) {
+		ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0);
+	} else if (inode->generation < trans->transid) {
+		path->search_commit_root = true;
+		path->skip_locking = true;
+		ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0);
+		path->search_commit_root = false;
+		path->skip_locking = false;
 
-		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
-				      struct btrfs_inode_item);
-		*size_ret = btrfs_inode_size(path->nodes[0], item);
-		/*
-		 * If the in-memory inode's i_size is smaller then the inode
-		 * size stored in the btree, return the inode's i_size, so
-		 * that we get a correct inode size after replaying the log
-		 * when before a power failure we had a shrinking truncate
-		 * followed by addition of a new name (rename / new hard link).
-		 * Otherwise return the inode size from the btree, to avoid
-		 * data loss when replaying a log due to previously doing a
-		 * write that expands the inode's size and logging a new name
-		 * immediately after.
-		 */
-		if (*size_ret > inode->vfs_inode.i_size)
-			*size_ret = inode->vfs_inode.i_size;
+	} else {
+		*size_ret = 0;
+		return 0;
 	}
 
+	/*
+	 * If the inode was logged before or is from a past transaction, then
+	 * its inode item must exist in the log root or in the commit root.
+	 */
+	ASSERT(ret <= 0);
+	if (WARN_ON_ONCE(ret > 0))
+		ret = -ENOENT;
+
+	if (ret < 0)
+		return ret;
+
+	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+			      struct btrfs_inode_item);
+	*size_ret = btrfs_inode_size(path->nodes[0], item);
+	/*
+	 * If the in-memory inode's i_size is smaller then the inode size stored
+	 * in the btree, return the inode's i_size, so that we get a correct
+	 * inode size after replaying the log when before a power failure we had
+	 * a shrinking truncate followed by addition of a new name (rename / new
+	 * hard link). Otherwise return the inode size from the btree, to avoid
+	 * data loss when replaying a log due to previously doing a write that
+	 * expands the inode's size and logging a new name immediately after.
+	 */
+	if (*size_ret > inode->vfs_inode.i_size)
+		*size_ret = inode->vfs_inode.i_size;
+
 	btrfs_release_path(path);
 	return 0;
 }
@@ -6996,7 +7028,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			ret = drop_inode_items(trans, log, path, inode,
 					       BTRFS_XATTR_ITEM_KEY);
 	} else {
-		if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) {
+		if (inode_only == LOG_INODE_EXISTS) {
 			/*
 			 * Make sure the new inode item we write to the log has
 			 * the same isize as the current one (if it exists).
@@ -7010,7 +7042,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			 * (zeroes), as if an expanding truncate happened,
 			 * instead of getting a file of 4Kb only.
 			 */
-			ret = logged_inode_size(log, inode, path, &logged_isize);
+			ret = get_inode_size_to_log(trans, inode, path, &logged_isize);
 			if (ret)
 				goto out_unlock;
 		}
-- 
cgit v1.2.3


From a4376d9a5d4c9610e69def3fc0b32c86a7ab7a41 Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Sun, 1 Mar 2026 21:17:04 +0900
Subject: btrfs: fix leak of kobject name for sub-group space_info

When create_space_info_sub_group() allocates elements of
space_info->sub_group[], kobject_init_and_add() is called for each
element via btrfs_sysfs_add_space_info_type(). However, when
check_removing_space_info() frees these elements, it does not call
btrfs_sysfs_remove_space_info() on them. As a result, kobject_put() is
not called and the associated kobj->name objects are leaked.

This memory leak is reproduced by running the blktests test case
zbd/009 on kernels built with CONFIG_DEBUG_KMEMLEAK. The kmemleak
feature reports the following error:

unreferenced object 0xffff888112877d40 (size 16):
  comm "mount", pid 1244, jiffies 4294996972
  hex dump (first 16 bytes):
    64 61 74 61 2d 72 65 6c 6f 63 00 c4 c6 a7 cb 7f  data-reloc......
  backtrace (crc 53ffde4d):
    __kmalloc_node_track_caller_noprof+0x619/0x870
    kstrdup+0x42/0xc0
    kobject_set_name_vargs+0x44/0x110
    kobject_init_and_add+0xcf/0x150
    btrfs_sysfs_add_space_info_type+0xfc/0x210 [btrfs]
    create_space_info_sub_group.constprop.0+0xfb/0x1b0 [btrfs]
    create_space_info+0x211/0x320 [btrfs]
    btrfs_init_space_info+0x15a/0x1b0 [btrfs]
    open_ctree+0x33c7/0x4a50 [btrfs]
    btrfs_get_tree.cold+0x9f/0x1ee [btrfs]
    vfs_get_tree+0x87/0x2f0
    vfs_cmd_create+0xbd/0x280
    __do_sys_fsconfig+0x3df/0x990
    do_syscall_64+0x136/0x1540
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

To avoid the leak, call btrfs_sysfs_remove_space_info() instead of
kfree() for the elements.

Fixes: f92ee31e031c ("btrfs: introduce btrfs_space_info sub-group")
Link: https://lore.kernel.org/linux-block/b9488881-f18d-4f47-91a5-3c9bf63955a5@wdc.com/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index fa55d868ecd8..f7fcff7dca8f 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -4584,7 +4584,7 @@ static void check_removing_space_info(struct btrfs_space_info *space_info)
 		for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) {
 			if (space_info->sub_group[i]) {
 				check_removing_space_info(space_info->sub_group[i]);
-				kfree(space_info->sub_group[i]);
+				btrfs_sysfs_remove_space_info(space_info->sub_group[i]);
 				space_info->sub_group[i] = NULL;
 			}
 		}
-- 
cgit v1.2.3


From 0dcabcb920a5c143c568f37c26c6f2b4b9206bd1 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Fri, 13 Mar 2026 18:35:26 +1030
Subject: btrfs: zlib: handle page aligned compressed size correctly

[BUG]
Since commit 3d74a7556fba ("btrfs: zlib: introduce zlib_compress_bio()
helper"), there are some reports about different crashes in zlib
compression path. One of the symptoms is list corruption like the
following:

  list_del corruption. next->prev should be fffffbb340204a08, but was ffff8d6517cb7de0. (next=fffffbb3402d62c8)
  ------------[ cut here ]------------
  kernel BUG at lib/list_debug.c:65!
  Oops: invalid opcode: 0000 [#1] SMP NOPTI
  CPU: 1 UID: 0 PID: 21436 Comm: kworker/u16:7 Not tainted 7.0.0-rc2-jcg+ #1 PREEMPT
  Hardware name: LENOVO 10VGS02P00/3130, BIOS M1XKT57A 02/10/2022
  Workqueue: btrfs-delalloc btrfs_work_helper [btrfs]
  RIP: 0010:__list_del_entry_valid_or_report+0xec/0xf0
  Call Trace:
   <TASK>
   btrfs_alloc_compr_folio+0xae/0xc0 [btrfs]
   zlib_compress_bio+0x39d/0x6a0 [btrfs]
   btrfs_compress_bio+0x2e3/0x3d0 [btrfs]
   compress_file_range+0x2b0/0x660 [btrfs]
   btrfs_work_helper+0xdb/0x3e0 [btrfs]
   process_one_work+0x192/0x3d0
   worker_thread+0x19a/0x310
   kthread+0xdf/0x120
   ret_from_fork+0x22e/0x310
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  ---[ end trace 0000000000000000 ]---

Other symptoms include VM_BUG_ON() during folio_put() but it's rarer.

David Sterba firstly reported this during his CI runs but unfortunately
I'm unable to hit it.

Meanwhile zstd/lzo doesn't seem to have the same problem.

[CAUSE]
During zlib_compress_bio() every time the output buffer is full, we
queue the full folio into the compressed bio, and allocate a new folio
as the output folio.

After the input has finished, we loop through zlib_deflate() with
Z_FINISH to flush all output.

And when that is done, we still need to check if the last folio has any
content, and if so we still need to queue that part into the compressed
bio.

The problem is in the final folio handling, if the final folio is full
(for x86_64 the folio size is 4K), the length to queue is calculated by

  u32 cur_len = offset_in_folio(out_folio, workspace->strm.total_out);

But since total_out is 4K aligned, the resulted @cur_len will be 0, then
we hit the bio_add_folio(), which has a quirk that if bio_add_folio()
got an length 0, it will still queue the folio into the bio, but return
false.

In that case we go to out: tag, which calls btrfs_free_compr_folio() to
release @out_folio, which may put the out folio into the btrfs global
pool list.

On the other hand, that @out_folio is already added to the
compressed bio, and will later be released again by
cleanup_compressed_bio(), which results double release.

And if this time we still need to put the folio into the btrfs global
pool list, it will result a list corruption because it's already in the
list.

[FIX]
Instead of offset_inside_folio(), directly use the difference between
strm.total_out and bi_size.
So that if the last folio is completely full, we can still properly
queue the full folio other than queueing zero byte.

Fixes: 3d74a7556fba ("btrfs: zlib: introduce zlib_compress_bio() helper")
Reported-by: David Sterba <dsterba@suse.com>
Reported-by: Jean-Christophe Guillain <jean-christophe@guillain.net>
Reported-by: syzbot+3c4d8371d65230f852a2@syzkaller.appspotmail.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=221176
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zlib.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 0a8fcee16428..27fc2b828002 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -308,7 +308,9 @@ int zlib_compress_bio(struct list_head *ws, struct compressed_bio *cb)
 	}
 	/* Queue the remaining part of the folio. */
 	if (workspace->strm.total_out > bio->bi_iter.bi_size) {
-		u32 cur_len = offset_in_folio(out_folio, workspace->strm.total_out);
+		const u32 cur_len = workspace->strm.total_out - bio->bi_iter.bi_size;
+
+		ASSERT(cur_len <= folio_size(out_folio));
 
 		if (!bio_add_folio(bio, out_folio, cur_len, 0)) {
 			ret = -E2BIG;
-- 
cgit v1.2.3


From a85b46db143fda5869e7d8df8f258ccef5fa1719 Mon Sep 17 00:00:00 2001
From: Goldwyn Rodrigues <rgoldwyn@suse.de>
Date: Fri, 13 Mar 2026 14:11:39 -0400
Subject: btrfs: tracepoints: get correct superblock from dentry in event
 btrfs_sync_file()

If overlay is used on top of btrfs, dentry->d_sb translates to overlay's
super block and fsid assignment will lead to a crash.

Use file_inode(file)->i_sb to always get btrfs_sb.

Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 include/trace/events/btrfs.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 125bdc166bfe..0864700f76e0 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -769,12 +769,15 @@ TRACE_EVENT(btrfs_sync_file,
 	),
 
 	TP_fast_assign(
-		const struct dentry *dentry = file->f_path.dentry;
-		const struct inode *inode = d_inode(dentry);
+		struct dentry *dentry = file_dentry(file);
+		struct inode *inode = file_inode(file);
+		struct dentry *parent = dget_parent(dentry);
+		struct inode *parent_inode = d_inode(parent);
 
-		TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb));
+		dput(parent);
+		TP_fast_assign_fsid(btrfs_sb(inode->i_sb));
 		__entry->ino		= btrfs_ino(BTRFS_I(inode));
-		__entry->parent		= btrfs_ino(BTRFS_I(d_inode(dentry->d_parent)));
+		__entry->parent		= btrfs_ino(BTRFS_I(parent_inode));
 		__entry->datasync	= datasync;
 		__entry->root_objectid	= btrfs_root_id(BTRFS_I(inode)->root);
 	),
-- 
cgit v1.2.3


From 1c37d896b12dfd0d4c96e310b0033c6676933917 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 18 Mar 2026 16:17:59 +0000
Subject: btrfs: fix lost error when running device stats on multiple devices
 fs

Whenever we get an error updating the device stats item for a device in
btrfs_run_dev_stats() we allow the loop to go to the next device, and if
updating the stats item for the next device succeeds, we end up losing
the error we had from the previous device.

Fix this by breaking out of the loop once we get an error and make sure
it's returned to the caller. Since we are in the transaction commit path
(and in the critical section actually), returning the error will result
in a transaction abort.

Fixes: 733f4fbbc108 ("Btrfs: read device stats on mount, write modified ones during commit")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8fbd736aad9f..117e13d245f6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -8099,8 +8099,9 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans)
 		smp_rmb();
 
 		ret = update_dev_stat_item(trans, device);
-		if (!ret)
-			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
+		if (ret)
+			break;
+		atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-- 
cgit v1.2.3


From c7fcd269e1e07b2aa4bb37ffce7543c340796433 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Mon, 23 Feb 2026 13:51:57 +0100
Subject: ice: set max queues in alloc_etherdev_mqs()

When allocating netdevice using alloc_etherdev_mqs() the maximum
supported queues number should be passed. The vsi->alloc_txq/rxq is
storing current number of queues, not the maximum ones.

Use the same function for getting max Tx and Rx queues which is used
during ethtool -l call to set maximum number of queues during netdev
allocation.

Reproduction steps:
$ethtool -l $pf # says current 16, max 64
$ethtool -S $pf # fine
$ethtool -L $pf combined 40 # crash

[491187.472594] Call Trace:
[491187.472829]  <TASK>
[491187.473067]  netif_set_xps_queue+0x26/0x40
[491187.473305]  ice_vsi_cfg_txq+0x265/0x3d0 [ice]
[491187.473619]  ice_vsi_cfg_lan_txqs+0x68/0xa0 [ice]
[491187.473918]  ice_vsi_cfg_lan+0x2b/0xa0 [ice]
[491187.474202]  ice_vsi_open+0x71/0x170 [ice]
[491187.474484]  ice_vsi_recfg_qs+0x17f/0x230 [ice]
[491187.474759]  ? dev_get_min_mp_channel_count+0xab/0xd0
[491187.474987]  ice_set_channels+0x185/0x3d0 [ice]
[491187.475278]  ethnl_set_channels+0x26f/0x340

Fixes: ee13aa1a2c5a ("ice: use netif_get_num_default_rss_queues()")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Alexander Nowlin <alexander.nowlin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h         | 22 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 18 ------------------
 drivers/net/ethernet/intel/ice/ice_main.c    |  4 ++--
 3 files changed, 24 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2b2b22af42be..eb3a48330cc1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -839,6 +839,28 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
+/**
+ * ice_get_max_txq - return the maximum number of Tx queues for in a PF
+ * @pf: PF structure
+ *
+ * Return: maximum number of Tx queues
+ */
+static inline int ice_get_max_txq(struct ice_pf *pf)
+{
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq);
+}
+
+/**
+ * ice_get_max_rxq - return the maximum number of Rx queues for in a PF
+ * @pf: PF structure
+ *
+ * Return: maximum number of Rx queues
+ */
+static inline int ice_get_max_rxq(struct ice_pf *pf)
+{
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq);
+}
+
 /**
  * ice_get_main_vsi - Get the PF VSI
  * @pf: PF instance
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 301947d53ede..e4e1eab05bd5 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3773,24 +3773,6 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info)
 	return 0;
 }
 
-/**
- * ice_get_max_txq - return the maximum number of Tx queues for in a PF
- * @pf: PF structure
- */
-static int ice_get_max_txq(struct ice_pf *pf)
-{
-	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq);
-}
-
-/**
- * ice_get_max_rxq - return the maximum number of Rx queues for in a PF
- * @pf: PF structure
- */
-static int ice_get_max_rxq(struct ice_pf *pf)
-{
-	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq);
-}
-
 /**
  * ice_get_combined_cnt - return the current number of combined channels
  * @vsi: PF VSI pointer
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index e7308e381e2f..3c36e3641b9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4699,8 +4699,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	struct net_device *netdev;
 	u8 mac_addr[ETH_ALEN];
 
-	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
-				    vsi->alloc_rxq);
+	netdev = alloc_etherdev_mqs(sizeof(*np), ice_get_max_txq(vsi->back),
+				    ice_get_max_rxq(vsi->back));
 	if (!netdev)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From ad85de0fc09eb3236e73df5acb2bc257625103f5 Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Thu, 12 Feb 2026 08:53:10 +0100
Subject: ice: fix inverted ready check for VF representors

Commit 0f00a897c9fcbd ("ice: check if SF is ready in ethtool ops")
refactored the VF readiness check into a generic repr->ops.ready()
callback but implemented ice_repr_ready_vf() with inverted logic:

  return !ice_check_vf_ready_for_cfg(repr->vf);

ice_check_vf_ready_for_cfg() returns 0 on success, so the negation
makes ready() return non-zero when the VF is ready. All callers treat
non-zero as "not ready, skip", causing ndo_get_stats64, get_drvinfo,
get_strings and get_ethtool_stats to always bail out in switchdev mode.

Remove the erroneous negation. The SF variant ice_repr_ready_sf() is
already correct (returns !active, i.e. non-zero when not active).

Fixes: 0f00a897c9fcbd ("ice: check if SF is ready in ethtool ops")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_repr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 90f99443a922..68cdd04dd3aa 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -315,7 +315,7 @@ ice_repr_reg_netdev(struct net_device *netdev, const struct net_device_ops *ops)
 
 static int ice_repr_ready_vf(struct ice_repr *repr)
 {
-	return !ice_check_vf_ready_for_cfg(repr->vf);
+	return ice_check_vf_ready_for_cfg(repr->vf);
 }
 
 static int ice_repr_ready_sf(struct ice_repr *repr)
-- 
cgit v1.2.3


From 2d8c5098b847f37dde8351fb5b5d190f1bb5c576 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wenst@chromium.org>
Date: Thu, 26 Feb 2026 17:22:33 +0800
Subject: PCI/pwrctrl: Do not power off on pwrctrl device removal

With the move to explicit pwrctrl power on/off APIs, the caller, i.e., the
PCI controller driver, should manage the power state. The pwrctrl drivers
should not try to clean up or power off when they are removed, as this
might end up disabling an already disabled regulator, causing a big
warning.  This can be triggered if a PCI controller driver's .remove()
callback calls pci_pwrctrl_destroy_devices() after
pci_pwrctrl_power_off_devices().

Drop the devm cleanup parts that turn off regulators from the pwrctrl
drivers.

Fixes: b921aa3f8dec ("PCI/pwrctrl: Switch to pwrctrl create, power on/off, destroy APIs")
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20260226092234.3859740-1-wenst@chromium.org
---
 drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c | 12 ------------
 drivers/pci/pwrctrl/slot.c               |  1 -
 2 files changed, 13 deletions(-)

diff --git a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
index 0d0377283c37..c7e4beec160a 100644
--- a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
+++ b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c
@@ -68,13 +68,6 @@ static int pwrseq_pwrctrl_power_off(struct pci_pwrctrl *pwrctrl)
 	return pwrseq_power_off(pwrseq->pwrseq);
 }
 
-static void devm_pwrseq_pwrctrl_power_off(void *data)
-{
-	struct pwrseq_pwrctrl *pwrseq = data;
-
-	pwrseq_pwrctrl_power_off(&pwrseq->pwrctrl);
-}
-
 static int pwrseq_pwrctrl_probe(struct platform_device *pdev)
 {
 	const struct pwrseq_pwrctrl_pdata *pdata;
@@ -101,11 +94,6 @@ static int pwrseq_pwrctrl_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(pwrseq->pwrseq),
 				     "Failed to get the power sequencer\n");
 
-	ret = devm_add_action_or_reset(dev, devm_pwrseq_pwrctrl_power_off,
-				       pwrseq);
-	if (ret)
-		return ret;
-
 	pwrseq->pwrctrl.power_on = pwrseq_pwrctrl_power_on;
 	pwrseq->pwrctrl.power_off = pwrseq_pwrctrl_power_off;
 
diff --git a/drivers/pci/pwrctrl/slot.c b/drivers/pci/pwrctrl/slot.c
index 082af81efe25..b87639253ae2 100644
--- a/drivers/pci/pwrctrl/slot.c
+++ b/drivers/pci/pwrctrl/slot.c
@@ -63,7 +63,6 @@ static void devm_slot_pwrctrl_release(void *data)
 {
 	struct slot_pwrctrl *slot = data;
 
-	slot_pwrctrl_power_off(&slot->pwrctrl);
 	regulator_bulk_free(slot->num_supplies, slot->supplies);
 }
 
-- 
cgit v1.2.3


From 2526e440df2725e7328d59b835a164826f179b93 Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Thu, 12 Feb 2026 08:53:11 +0100
Subject: ice: use ice_update_eth_stats() for representor stats

ice_repr_get_stats64() and __ice_get_ethtool_stats() call
ice_update_vsi_stats() on the VF's src_vsi. This always returns early
because ICE_VSI_DOWN is permanently set for VF VSIs - ice_up() is never
called on them since queues are managed by iavf through virtchnl.

In __ice_get_ethtool_stats() the original code called
ice_update_vsi_stats() for all VSIs including representors, iterated
over ice_gstrings_vsi_stats[] to populate the data, and then bailed out
with an early return before the per-queue ring stats section. That early
return was necessary because representor VSIs have no rings on the PF
side - the rings belong to the VF driver (iavf), so accessing per-queue
stats would be invalid.

Move the representor handling to the top of __ice_get_ethtool_stats()
and call ice_update_eth_stats() directly to read the hardware GLV_*
counters. This matches ice_get_vf_stats() which already uses
ice_update_eth_stats() for the same VF VSI in legacy mode. Apply the
same fix to ice_repr_get_stats64().

Note that ice_gstrings_vsi_stats[] contains five software ring counters
(rx_buf_failed, rx_page_failed, tx_linearize, tx_busy, tx_restart) that
are always zero for representors since the PF never processes packets on
VF rings. This is pre-existing behavior unchanged by this patch.

Fixes: 7aae80cef7ba ("ice: add port representor ethtool ops and stats")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 14 +++++++++++---
 drivers/net/ethernet/intel/ice/ice_repr.c    |  3 ++-
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index e4e1eab05bd5..e6a20af6f63d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1930,6 +1930,17 @@ __ice_get_ethtool_stats(struct net_device *netdev,
 	int i = 0;
 	char *p;
 
+	if (ice_is_port_repr_netdev(netdev)) {
+		ice_update_eth_stats(vsi);
+
+		for (j = 0; j < ICE_VSI_STATS_LEN; j++) {
+			p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset;
+			data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat ==
+				     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+		}
+		return;
+	}
+
 	ice_update_pf_stats(pf);
 	ice_update_vsi_stats(vsi);
 
@@ -1939,9 +1950,6 @@ __ice_get_ethtool_stats(struct net_device *netdev,
 			     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
 
-	if (ice_is_port_repr_netdev(netdev))
-		return;
-
 	/* populate per queue stats */
 	rcu_read_lock();
 
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 68cdd04dd3aa..096566c697f4 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2019-2021, Intel Corporation. */
 
 #include "ice.h"
+#include "ice_lib.h"
 #include "ice_eswitch.h"
 #include "devlink/devlink.h"
 #include "devlink/port.h"
@@ -67,7 +68,7 @@ ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 		return;
 	vsi = repr->src_vsi;
 
-	ice_update_vsi_stats(vsi);
+	ice_update_eth_stats(vsi);
 	eth_stats = &vsi->eth_stats;
 
 	stats->tx_packets = eth_stats->tx_unicast + eth_stats->tx_broadcast +
-- 
cgit v1.2.3


From fecacfc95f195b99c71c579a472120d0b4ed65fa Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Sat, 14 Feb 2026 19:14:25 +0000
Subject: iavf: fix out-of-bounds writes in iavf_get_ethtool_stats()

iavf incorrectly uses real_num_tx_queues for ETH_SS_STATS. Since the
value could change in runtime, we should use num_tx_queues instead.

Moreover iavf_get_ethtool_stats() uses num_active_queues while
iavf_get_sset_count() and iavf_get_stat_strings() use
real_num_tx_queues, which triggers out-of-bounds writes when we do
"ethtool -L" and "ethtool -S" simultaneously [1].

For example when we change channels from 1 to 8, Thread 3 could be
scheduled before Thread 2, and out-of-bounds writes could be triggered
in Thread 3:

Thread 1 (ethtool -L)       Thread 2 (work)        Thread 3 (ethtool -S)
iavf_set_channels()
...
iavf_alloc_queues()
-> num_active_queues = 8
iavf_schedule_finish_config()
                                                   iavf_get_sset_count()
                                                   real_num_tx_queues: 1
                                                   -> buffer for 1 queue
                                                   iavf_get_ethtool_stats()
                                                   num_active_queues: 8
                                                   -> out-of-bounds!
                            iavf_finish_config()
                            -> real_num_tx_queues = 8

Use immutable num_tx_queues in all related functions to avoid the issue.

[1]
 BUG: KASAN: vmalloc-out-of-bounds in iavf_add_one_ethtool_stat+0x200/0x270
 Write of size 8 at addr ffffc900031c9080 by task ethtool/5800

 CPU: 1 UID: 0 PID: 5800 Comm: ethtool Not tainted 6.19.0-enjuk-08403-g8137e3db7f1c #241 PREEMPT(full)
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x6f/0xb0
  print_report+0x170/0x4f3
  kasan_report+0xe1/0x180
  iavf_add_one_ethtool_stat+0x200/0x270
  iavf_get_ethtool_stats+0x14c/0x2e0
  __dev_ethtool+0x3d0c/0x5830
  dev_ethtool+0x12d/0x270
  dev_ioctl+0x53c/0xe30
  sock_do_ioctl+0x1a9/0x270
  sock_ioctl+0x3d4/0x5e0
  __x64_sys_ioctl+0x137/0x1c0
  do_syscall_64+0xf3/0x690
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
 RIP: 0033:0x7f7da0e6e36d
 ...
  </TASK>

 The buggy address belongs to a 1-page vmalloc region starting at 0xffffc900031c9000 allocated at __dev_ethtool+0x3cc9/0x5830
 The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000
 index:0xffff88813a013de0 pfn:0x13a013
 flags: 0x200000000000000(node=0|zone=2)
 raw: 0200000000000000 0000000000000000 dead000000000122 0000000000000000
 raw: ffff88813a013de0 0000000000000000 00000001ffffffff 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  ffffc900031c8f80: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffffc900031c9000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 >ffffc900031c9080: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
                    ^
  ffffc900031c9100: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
  ffffc900031c9180: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8

Fixes: 64430f70ba6f ("iavf: Fix displaying queue statistics shown by ethtool")
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 31 +++++++++++++-------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index ab67c709d5a0..1cd1f3f2930a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -313,14 +313,13 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset)
 {
 	/* Report the maximum number queues, even if not every queue is
 	 * currently configured. Since allocation of queues is in pairs,
-	 * use netdev->real_num_tx_queues * 2. The real_num_tx_queues is set
-	 * at device creation and never changes.
+	 * use netdev->num_tx_queues * 2. The num_tx_queues is set at
+	 * device creation and never changes.
 	 */
 
 	if (sset == ETH_SS_STATS)
 		return IAVF_STATS_LEN +
-			(IAVF_QUEUE_STATS_LEN * 2 *
-			 netdev->real_num_tx_queues);
+		       (IAVF_QUEUE_STATS_LEN * 2 * netdev->num_tx_queues);
 	else
 		return -EINVAL;
 }
@@ -345,19 +344,19 @@ static void iavf_get_ethtool_stats(struct net_device *netdev,
 	iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats);
 
 	rcu_read_lock();
-	/* As num_active_queues describe both tx and rx queues, we can use
-	 * it to iterate over rings' stats.
+	/* Use num_tx_queues to report stats for the maximum number of queues.
+	 * Queues beyond num_active_queues will report zero.
 	 */
-	for (i = 0; i < adapter->num_active_queues; i++) {
-		struct iavf_ring *ring;
+	for (i = 0; i < netdev->num_tx_queues; i++) {
+		struct iavf_ring *tx_ring = NULL, *rx_ring = NULL;
 
-		/* Tx rings stats */
-		ring = &adapter->tx_rings[i];
-		iavf_add_queue_stats(&data, ring);
+		if (i < adapter->num_active_queues) {
+			tx_ring = &adapter->tx_rings[i];
+			rx_ring = &adapter->rx_rings[i];
+		}
 
-		/* Rx rings stats */
-		ring = &adapter->rx_rings[i];
-		iavf_add_queue_stats(&data, ring);
+		iavf_add_queue_stats(&data, tx_ring);
+		iavf_add_queue_stats(&data, rx_ring);
 	}
 	rcu_read_unlock();
 }
@@ -376,9 +375,9 @@ static void iavf_get_stat_strings(struct net_device *netdev, u8 *data)
 	iavf_add_stat_strings(&data, iavf_gstrings_stats);
 
 	/* Queues are always allocated in pairs, so we just use
-	 * real_num_tx_queues for both Tx and Rx queues.
+	 * num_tx_queues for both Tx and Rx queues.
 	 */
-	for (i = 0; i < netdev->real_num_tx_queues; i++) {
+	for (i = 0; i < netdev->num_tx_queues; i++) {
 		iavf_add_stat_strings(&data, iavf_gstrings_queue_stats,
 				      "tx", i);
 		iavf_add_stat_strings(&data, iavf_gstrings_queue_stats,
-- 
cgit v1.2.3


From 1eb0db7e39da3d20ff6dfb8d359655329ea6f839 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Mon, 2 Mar 2026 17:28:31 -0800
Subject: idpf: clear stale cdev_info ptr

Deinit calls idpf_idc_deinit_core_aux_device to free the cdev_info
memory, but leaves the adapter->cdev_info field with a stale pointer
value. This will bypass subsequent "if (!cdev_info)" checks if cdev_info
is not reallocated. For example, if idc_init fails after a reset,
cdev_info will already have been freed during the reset handling, but it
will not have been reallocated. The next reset or rmmod will result in a
crash.

[  +0.000008] BUG: kernel NULL pointer dereference, address: 00000000000000d0
[  +0.000033] #PF: supervisor read access in kernel mode
[  +0.000020] #PF: error_code(0x0000) - not-present page
[  +0.000017] PGD 2097dfa067 P4D 0
[  +0.000017] Oops: Oops: 0000 [#1] SMP NOPTI
...
[  +0.000018] RIP: 0010:device_del+0x3e/0x3d0
[  +0.000010] Call Trace:
[  +0.000010]  <TASK>
[  +0.000012]  idpf_idc_deinit_core_aux_device+0x36/0x70 [idpf]
[  +0.000034]  idpf_vc_core_deinit+0x3e/0x180 [idpf]
[  +0.000035]  idpf_remove+0x40/0x1d0 [idpf]
[  +0.000035]  pci_device_remove+0x42/0xb0
[  +0.000020]  device_release_driver_internal+0x19c/0x200
[  +0.000024]  driver_detach+0x48/0x90
[  +0.000018]  bus_remove_driver+0x6d/0x100
[  +0.000023]  pci_unregister_driver+0x2e/0xb0
[  +0.000022]  __do_sys_delete_module.isra.0+0x18c/0x2b0
[  +0.000025]  ? kmem_cache_free+0x2c2/0x390
[  +0.000023]  do_syscall_64+0x107/0x7d0
[  +0.000023]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Pass the adapter struct into idpf_idc_deinit_core_aux_device instead and
clear the cdev_info ptr.

Fixes: f4312e6bfa2a ("idpf: implement core RDMA auxiliary dev create, init, and destroy")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf.h          | 2 +-
 drivers/net/ethernet/intel/idpf/idpf_idc.c      | 6 ++++--
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index b206fba092c8..ec1b75f039bb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -1066,7 +1066,7 @@ bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val);
 int idpf_idc_init(struct idpf_adapter *adapter);
 int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
 			       enum iidc_function_type ftype);
-void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info);
+void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter);
 void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info);
 void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info);
 void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info,
diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
index bd4785fb8d3e..7e4f4ac92653 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_idc.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -470,10 +470,11 @@ err_privd_alloc:
 
 /**
  * idpf_idc_deinit_core_aux_device - de-initialize Auxiliary Device(s)
- * @cdev_info: IDC core device info pointer
+ * @adapter: driver private data structure
  */
-void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
+void idpf_idc_deinit_core_aux_device(struct idpf_adapter *adapter)
 {
+	struct iidc_rdma_core_dev_info *cdev_info = adapter->cdev_info;
 	struct iidc_rdma_priv_dev_info *privd;
 
 	if (!cdev_info)
@@ -485,6 +486,7 @@ void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
 	kfree(privd->mapped_mem_regions);
 	kfree(privd);
 	kfree(cdev_info);
+	adapter->cdev_info = NULL;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d5a877e1fef8..113ecfc16dd7 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -3668,7 +3668,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 
 	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
-	idpf_idc_deinit_core_aux_device(adapter->cdev_info);
+	idpf_idc_deinit_core_aux_device(adapter);
 	idpf_rel_rx_pt_lkup(adapter);
 	idpf_intr_rel(adapter);
 
-- 
cgit v1.2.3


From b5e5797e3cd1fd1561b212b2b94f8865d07f2890 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 6 Mar 2026 18:12:47 -0800
Subject: idpf: only assign num refillqs if allocation was successful

As reported by AI review [1], if the refillqs allocation fails, refillqs
will be NULL but num_refillqs will be non-zero. The release function
will then dereference refillqs since it thinks the refillqs are present,
resulting in a NULL ptr dereference.

Only assign the num refillqs if the allocation was successful. This will
prevent the release function from entering the loop and accessing
refillqs.

[1] https://lore.kernel.org/netdev/20260227035625.2632753-1-kuba@kernel.org/

Fixes: 95af467d9a4e3 ("idpf: configure resources for RX queues")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 252259993022..f6b3b15364ff 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -1860,13 +1860,13 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport,
 			idpf_queue_assign(HSPLIT_EN, q, hs);
 			idpf_queue_assign(RSC_EN, q, rsc);
 
-			bufq_set->num_refillqs = num_rxq;
 			bufq_set->refillqs = kcalloc(num_rxq, swq_size,
 						     GFP_KERNEL);
 			if (!bufq_set->refillqs) {
 				err = -ENOMEM;
 				goto err_alloc;
 			}
+			bufq_set->num_refillqs = num_rxq;
 			for (unsigned int k = 0; k < bufq_set->num_refillqs; k++) {
 				struct idpf_sw_queue *refillq =
 					&bufq_set->refillqs[k];
-- 
cgit v1.2.3


From 70bb843794d150db8e653c9ab288c8533da00837 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Mon, 23 Mar 2026 19:05:22 +0800
Subject: PCI/pwrctrl: Fix pci_pwrctrl_is_required() device node leak

The for_each_endpoint_of_node() macro requires calling of_node_put() on the
endpoint node when breaking out of the loop early.

Add of_node_put(endpoint) before the early return to release the reference.

Fixes: cf3287fb2c1f ("PCI/pwrctrl: Ensure that remote endpoint node parent has supply requirement")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20260323-pwctrl-v1-1-f5c03a2df7fb@gmail.com
---
 drivers/pci/pwrctrl/core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c
index 7754baed67f2..97cff5b8ca88 100644
--- a/drivers/pci/pwrctrl/core.c
+++ b/drivers/pci/pwrctrl/core.c
@@ -299,8 +299,10 @@ static bool pci_pwrctrl_is_required(struct device_node *np)
 			struct device_node *remote __free(device_node) =
 				of_graph_get_remote_port_parent(endpoint);
 			if (remote) {
-				if (of_pci_supply_present(remote))
+				if (of_pci_supply_present(remote)) {
+					of_node_put(endpoint);
 					return true;
+				}
 			}
 		}
 	}
-- 
cgit v1.2.3


From 05f643d6f7e699198ccc47e634de3879a8ec26a3 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Mon, 23 Mar 2026 07:52:39 +0100
Subject: Documentation: PCI: Document PCIe TLP Header decoder for AER messages

The prefix/header of a TLP that caused an error may be recorded in the AER
Capability and emitted to the kernel log in raw hex format.  Document the
existence and usage of tlp-tool, which decodes the TLP Header into
human-readable form.

The TLP Header hints at the root cause of an error, yet is often ignored
because of its seeming opaqueness.  Instead, PCIe errors are frequently
worked around by a change in the kernel without fully understanding the
actual source of the problem.  With more documentation on available tools
we'll hopefully come up with better solutions.

There are also wireshark dissectors for TLPs, but it seems they expect a
complete TLP, not just the header, and they cannot grok the hex format
emitted by the kernel directly.  tlp-tool appears to be the most cut and
dried solution out there.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Maciej Grochowski <mx2pg@pm.me>
Link: https://patch.msgid.link/bf826c41b4c1d255c7dcb16e266b52f774d944ed.1774246067.git.lukas@wunner.de
---
 Documentation/PCI/pcieaer-howto.rst | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/PCI/pcieaer-howto.rst b/Documentation/PCI/pcieaer-howto.rst
index 3210c4792978..90fdfddd3ae5 100644
--- a/Documentation/PCI/pcieaer-howto.rst
+++ b/Documentation/PCI/pcieaer-howto.rst
@@ -85,6 +85,16 @@ In the example, 'Requester ID' means the ID of the device that sent
 the error message to the Root Port. Please refer to PCIe specs for other
 fields.
 
+The 'TLP Header' is the prefix/header of the TLP that caused the error
+in raw hex format. To decode the TLP Header into human-readable form
+one may use tlp-tool:
+
+https://github.com/mmpg-x86/tlp-tool
+
+Example usage::
+
+  curl -L https://git.kernel.org/linus/2ca1c94ce0b6 | rtlp-tool --aer
+
 AER Ratelimits
 --------------
 
-- 
cgit v1.2.3


From 6af51e9f31336632263c4680b2a3712295103e1f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 20 Mar 2026 07:22:59 +0000
Subject: ipv6: Remove permanent routes from tb6_gc_hlist when all exceptions
 expire.

Commit 5eb902b8e719 ("net/ipv6: Remove expired routes with a
separated list of routes.") introduced a per-table GC list and
changed GC to iterate over that list instead of traversing
the entire route table.

However, it forgot to add permanent routes to tb6_gc_hlist
when exception routes are added.

Commit cfe82469a00f ("ipv6: add exception routes to GC list
in rt6_insert_exception") fixed that issue but introduced
another one.

Even after all exception routes expire, the permanent routes
remain in tb6_gc_hlist, potentially negating the performance
benefits intended by the initial change.

Let's count gc_args->more before and after rt6_age_exceptions()
and remove the permanent route when the delta is 0.

Note that the next patch will reuse fib6_age_exceptions().

Fixes: cfe82469a00f ("ipv6: add exception routes to GC list in rt6_insert_exception")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260320072317.2561779-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_fib.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 9058e71241dc..fadfca49d6b1 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2348,6 +2348,17 @@ static void fib6_flush_trees(struct net *net)
 /*
  *	Garbage collection
  */
+static void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
+				unsigned long now)
+{
+	bool may_expire = rt->fib6_flags & RTF_EXPIRES && rt->expires;
+	int old_more = gc_args->more;
+
+	rt6_age_exceptions(rt, gc_args, now);
+
+	if (!may_expire && old_more == gc_args->more)
+		fib6_remove_gc_list(rt);
+}
 
 static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 {
@@ -2370,7 +2381,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	 *	Note, that clones are aged out
 	 *	only if they are not in use now.
 	 */
-	rt6_age_exceptions(rt, gc_args, now);
+	fib6_age_exceptions(rt, gc_args, now);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 4be7b99c253f0c85a255cc1db7127ba3232dfa30 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 20 Mar 2026 07:23:00 +0000
Subject: ipv6: Don't remove permanent routes with exceptions from
 tb6_gc_hlist.

The cited commit mechanically put fib6_remove_gc_list()
just after every fib6_clean_expires() call.

When a temporary route is promoted to a permanent route,
there may already be exception routes tied to it.

If fib6_remove_gc_list() removes the route from tb6_gc_hlist,
such exception routes will no longer be aged.

Let's replace fib6_remove_gc_list() with a new helper
fib6_may_remove_gc_list() and use fib6_age_exceptions() there.

Note that net->ipv6 is only compiled when CONFIG_IPV6 is
enabled, so fib6_{add,remove,may_remove}_gc_list() are guarded.

Fixes: 5eb902b8e719 ("net/ipv6: Remove expired routes with a separated list of routes.")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260320072317.2561779-3-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip6_fib.h | 21 ++++++++++++++++++++-
 net/ipv6/addrconf.c   |  4 ++--
 net/ipv6/ip6_fib.c    |  6 +++---
 net/ipv6/route.c      |  2 +-
 4 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 88b0dd4d8e09..9f8b6814a96a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -507,12 +507,14 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int flags);
 
+void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
+			 unsigned long now);
 void fib6_run_gc(unsigned long expires, struct net *net, bool force);
-
 void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* Add the route to the gc list if it is not already there
  *
  * The callers should hold f6i->fib6_table->tb6_lock.
@@ -545,6 +547,23 @@ static inline void fib6_remove_gc_list(struct fib6_info *f6i)
 		hlist_del_init(&f6i->gc_link);
 }
 
+static inline void fib6_may_remove_gc_list(struct net *net,
+					   struct fib6_info *f6i)
+{
+	struct fib6_gc_args gc_args;
+
+	if (hlist_unhashed(&f6i->gc_link))
+		return;
+
+	gc_args.timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval);
+	gc_args.more = 0;
+
+	rcu_read_lock();
+	fib6_age_exceptions(f6i, &gc_args, jiffies);
+	rcu_read_unlock();
+}
+#endif
+
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 0e55f139e05d..f4e23b543585 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2862,7 +2862,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 					fib6_add_gc_list(rt);
 				} else {
 					fib6_clean_expires(rt);
-					fib6_remove_gc_list(rt);
+					fib6_may_remove_gc_list(net, rt);
 				}
 
 				spin_unlock_bh(&table->tb6_lock);
@@ -4840,7 +4840,7 @@ static int modify_prefix_route(struct net *net, struct inet6_ifaddr *ifp,
 
 		if (!(flags & RTF_EXPIRES)) {
 			fib6_clean_expires(f6i);
-			fib6_remove_gc_list(f6i);
+			fib6_may_remove_gc_list(net, f6i);
 		} else {
 			fib6_set_expires(f6i, expires);
 			fib6_add_gc_list(f6i);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index fadfca49d6b1..dd26657b6a4a 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1133,7 +1133,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES)) {
 					fib6_clean_expires(iter);
-					fib6_remove_gc_list(iter);
+					fib6_may_remove_gc_list(info->nl_net, iter);
 				} else {
 					fib6_set_expires(iter, rt->expires);
 					fib6_add_gc_list(iter);
@@ -2348,8 +2348,8 @@ static void fib6_flush_trees(struct net *net)
 /*
  *	Garbage collection
  */
-static void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
-				unsigned long now)
+void fib6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
+			 unsigned long now)
 {
 	bool may_expire = rt->fib6_flags & RTF_EXPIRES && rt->expires;
 	int old_more = gc_args->more;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 08cd86f49bf9..cb521700cee7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1033,7 +1033,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 
 		if (!addrconf_finite_timeout(lifetime)) {
 			fib6_clean_expires(rt);
-			fib6_remove_gc_list(rt);
+			fib6_may_remove_gc_list(net, rt);
 		} else {
 			fib6_set_expires(rt, jiffies + HZ * lifetime);
 			fib6_add_gc_list(rt);
-- 
cgit v1.2.3


From 3e9e84e92c9c2eec396ee62a2e47b85781520c57 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 20 Mar 2026 07:23:01 +0000
Subject: selftest: net: Add GC test for temporary routes with exceptions.

Without the prior commit, IPv6 GC cannot track exceptions tied
to permanent routes if they were originally added as temporary
routes.

Let's add a test case for the issue.

  1. Add temporary routes
  2. Create exceptions for the temporary routes
  3. Promote the routes to permanent routes
  4. Check if GC can find and purge the exceptions

A few notes:

  + At step 4, unlike other test cases, we cannot wait for
    $GC_WAIT_TIME.  While the exceptions are always iterable via
    netlink (since it traverses the entire fib tree instead of
    tb6_gc_hlist), rt6_nh_dump_exceptions() skips expired entries.

    If we waited for the expiration time, we would be unable to
    distinguish whether the exceptions were truly purged by GC or
    just hidden due to being expired.

  + For the same reason, at step 2, we use ICMPv6 redirect message
    instead of Packet Too Big message.  This is because MTU exceptions
    always have RTF_EXPIRES, and rt6_age_examine_exception() does not
    respect the period specified by net.ipv6.route.flush=1.

  + We add a neighbour entry for the redirect target with NTF_ROUTER.
    Without this, the exceptions would be removed at step 3 when the
    fib6_may_remove_gc_list() is called.

Without the fix, the exceptions remain even after GC is triggered
by sysctl -wq net.ipv6.route.flush=1.

  FAIL: Expected 0 routes, got 5
      TEST: ipv6 route garbage collection (promote to permanent routes)   [FAIL]

With the fix, GC purges the exceptions properly.

      TEST: ipv6 route garbage collection (promote to permanent routes)   [ OK ]

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20260320072317.2561779-4-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_tests.sh | 61 ++++++++++++++++++++++++++++++--
 1 file changed, 58 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index c5694cc4ddd2..829f72c8ee07 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -868,6 +868,64 @@ fib6_gc_test()
 	check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l)
 	log_test $ret 0 "ipv6 route garbage collection (replace with permanent)"
 
+	# Delete dummy_10 and remove all routes
+	$IP link del dev dummy_10
+
+	# rd6 is required for the next test. (ipv6toolkit)
+	if [ ! -x "$(command -v rd6)" ]; then
+	    echo "SKIP: rd6 not found."
+	    set +e
+	    cleanup &> /dev/null
+	    return
+	fi
+
+	setup_ns ns2
+	$IP link add veth1 type veth peer veth2 netns $ns2
+	$IP link set veth1 up
+	ip -netns $ns2 link set veth2 up
+	$IP addr add fe80:dead::1/64 dev veth1
+	ip -netns $ns2 addr add fe80:dead::2/64 dev veth2
+
+	# Add NTF_ROUTER neighbour to prevent rt6_age_examine_exception()
+	# from removing not-yet-expired exceptions.
+	ip -netns $ns2 link set veth2 address 00:11:22:33:44:55
+	$IP neigh add fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router
+
+	$NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_redirects=1
+	$NS_EXEC sysctl -wq net.ipv6.conf.veth1.forwarding=0
+
+	# Temporary routes
+	for i in $(seq 1 5); do
+	    # Expire route after $EXPIRE seconds
+	    $IP -6 route add 2001:10::$i \
+		via fe80:dead::2 dev veth1 expires $EXPIRE
+
+	    ip netns exec $ns2 rd6 -i veth2 \
+		-s fe80:dead::2 -d fe80:dead::1 \
+		-r 2001:10::$i -t fe80:dead::3 -p ICMP6
+	done
+
+	check_rt_num 5 $($IP -6 route list | grep expires | grep 2001:10:: | wc -l)
+
+	# Promote to permanent routes by "prepend" (w/o NLM_F_EXCL and NLM_F_REPLACE)
+	for i in $(seq 1 5); do
+	    # -EEXIST, but the temporary route becomes the permanent route.
+	    $IP -6 route append 2001:10::$i \
+		via fe80:dead::2 dev veth1 2>/dev/null || true
+	done
+
+	check_rt_num 5 $($IP -6 route list | grep -v expires | grep 2001:10:: | wc -l)
+	check_rt_num 5 $($IP -6 route list cache | grep 2001:10:: | wc -l)
+
+	# Trigger GC instead of waiting $GC_WAIT_TIME.
+	# rt6_nh_dump_exceptions() just skips expired exceptions.
+	$NS_EXEC sysctl -wq net.ipv6.route.flush=1
+	check_rt_num 0 $($IP -6 route list cache | grep 2001:10:: | wc -l)
+	log_test $ret 0 "ipv6 route garbage collection (promote to permanent routes)"
+
+	$IP neigh del fe80:dead::3 lladdr 00:11:22:33:44:55 dev veth1 router
+	$IP link del veth1
+
 	# ra6 is required for the next test. (ipv6toolkit)
 	if [ ! -x "$(command -v ra6)" ]; then
 	    echo "SKIP: ra6 not found."
@@ -876,9 +934,6 @@ fib6_gc_test()
 	    return
 	fi
 
-	# Delete dummy_10 and remove all routes
-	$IP link del dev dummy_10
-
 	# Create a pair of veth devices to send a RA message from one
 	# device to another.
 	$IP link add veth1 type veth peer name veth2
-- 
cgit v1.2.3


From 42156f93d123436f2a27c468f18c966b7e5db796 Mon Sep 17 00:00:00 2001
From: Yochai Eisenrich <echelonh@gmail.com>
Date: Thu, 19 Mar 2026 22:06:10 +0200
Subject: net: fix fanout UAF in packet_release() via NETDEV_UP race

`packet_release()` has a race window where `NETDEV_UP` can re-register a
socket into a fanout group's `arr[]` array. The re-registration is not
cleaned up by `fanout_release()`, leaving a dangling pointer in the fanout
array.
`packet_release()` does NOT zero `po->num` in its `bind_lock` section.
After releasing `bind_lock`, `po->num` is still non-zero and `po->ifindex`
still matches the bound device. A concurrent `packet_notifier(NETDEV_UP)`
that already found the socket in `sklist` can re-register the hook.
For fanout sockets, this re-registration calls `__fanout_link(sk, po)`
which adds the socket back into `f->arr[]` and increments `f->num_members`,
but does NOT increment `f->sk_ref`.

The fix sets `po->num` to zero in `packet_release` while `bind_lock` is
held to prevent NETDEV_UP from linking, preventing the race window.

This bug was found following an additional audit with Claude Code based
on CVE-2025-38617.

Fixes: ce06b03e60fc ("packet: Add helpers to register/unregister ->prot_hook")
Link: https://blog.calif.io/p/a-race-within-a-race-exploiting-cve
Signed-off-by: Yochai Eisenrich <echelonh@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260319200610.25101-1-echelonh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/packet/af_packet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 72d0935139f0..bb2d88205e5a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -3135,6 +3135,7 @@ static int packet_release(struct socket *sock)
 
 	spin_lock(&po->bind_lock);
 	unregister_prot_hook(sk, false);
+	WRITE_ONCE(po->num, 0);
 	packet_cached_dev_reset(po);
 
 	if (po->prot_hook.dev) {
-- 
cgit v1.2.3


From 1065913dedfd3a8269816835bfe810b6e2c28579 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Fri, 20 Mar 2026 17:43:15 +0800
Subject: net: airoha: add RCU lock around dev_fill_forward_path

Since 0417adf367a0 ("ppp: fix race conditions in ppp_fill_forward_path")
dev_fill_forward_path() should be called with RCU read lock held. This
fix was applied to net, while the Airoha flowtable commit was applied to
net-next, so it hadn't been an issue until net was merged into net-next.

Fixes: a8bdd935d1dd ("net: airoha: Add wlan flowtable TX offload")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260320094315.525126-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_ppe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 42dbe8f93231..5724f8f2defd 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -227,7 +227,9 @@ static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr,
 	if (!dev)
 		return -ENODEV;
 
+	rcu_read_lock();
 	err = dev_fill_forward_path(dev, addr, &stack);
+	rcu_read_unlock();
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 3f0f591b44b04a77ff561676ae53fcfd7532a54c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Mar 2026 16:49:19 +0100
Subject: net: b44: always select CONFIG_FIXED_PHY

When CONFIG_FIXED_PHY=m but CONFIG_B44=y, the kernel fails to link:

ld.lld: error: undefined symbol: fixed_phy_unregister
>>> referenced by b44.c
>>>               drivers/net/ethernet/broadcom/b44.o:(b44_remove_one) in archive vmlinux.a

ld.lld: error: undefined symbol: fixed_phy_register_100fd
>>> referenced by b44.c
>>>               drivers/net/ethernet/broadcom/b44.o:(b44_register_phy_one) in archive vmlinux.a

The fixed phy support is small enough that just always enabling it
for b44 is the simplest solution, and it avoids adding ugly #ifdef
checks.

Fixes: 10d2f15afba2 ("net: b44: register a fixed phy using fixed_phy_register_100fd if needed")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20260320154927.674555-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index cd7dddeb91dd..9787c1857e13 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -25,7 +25,7 @@ config B44
 	select SSB
 	select MII
 	select PHYLIB
-	select FIXED_PHY if BCM47XX
+	select FIXED_PHY
 	help
 	  If you have a network (Ethernet) controller of this type, say Y
 	  or M here.
-- 
cgit v1.2.3


From e537dd15d0d4ad989d56a1021290f0c674dd8b28 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 19 Mar 2026 11:18:17 -0700
Subject: udp: Fix wildcard bind conflict check when using hash2

When binding a udp_sock to a local address and port, UDP uses
two hashes (udptable->hash and udptable->hash2) for collision
detection. The current code switches to "hash2" when
hslot->count > 10.

"hash2" is keyed by local address and local port.
"hash" is keyed by local port only.

The issue can be shown in the following bind sequence (pseudo code):

bind(fd1,  "[fd00::1]:8888")
bind(fd2,  "[fd00::2]:8888")
bind(fd3,  "[fd00::3]:8888")
bind(fd4,  "[fd00::4]:8888")
bind(fd5,  "[fd00::5]:8888")
bind(fd6,  "[fd00::6]:8888")
bind(fd7,  "[fd00::7]:8888")
bind(fd8,  "[fd00::8]:8888")
bind(fd9,  "[fd00::9]:8888")
bind(fd10, "[fd00::10]:8888")

/* Correctly return -EADDRINUSE because "hash" is used
 * instead of "hash2". udp_lib_lport_inuse() detects the
 * conflict.
 */
bind(fail_fd, "[::]:8888")

/* After one more socket is bound to "[fd00::11]:8888",
 * hslot->count exceeds 10 and "hash2" is used instead.
 */
bind(fd11, "[fd00::11]:8888")
bind(fail_fd, "[::]:8888")      /* succeeds unexpectedly */

The same issue applies to the IPv4 wildcard address "0.0.0.0"
and the IPv4-mapped wildcard address "::ffff:0.0.0.0". For
example, if there are existing sockets bound to
"192.168.1.[1-11]:8888", then binding "0.0.0.0:8888" or
"[::ffff:0.0.0.0]:8888" can also miss the conflict when
hslot->count > 10.

TCP inet_csk_get_port() already has the correct check in
inet_use_bhash2_on_bind(). Rename it to
inet_use_hash2_on_bind() and move it to inet_hashtables.h
so udp.c can reuse it in this fix.

Fixes: 30fff9231fad ("udp: bind() optimisation")
Reported-by: Andrew Onyshchuk <oandrew@meta.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260319181817.1901357-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_hashtables.h   | 14 ++++++++++++++
 net/ipv4/inet_connection_sock.c | 20 +++-----------------
 net/ipv4/udp.c                  |  2 +-
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 5a979dcab538..6d936e9f2fd3 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -264,6 +264,20 @@ inet_bhashfn_portaddr(const struct inet_hashinfo *hinfo, const struct sock *sk,
 	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
+static inline bool inet_use_hash2_on_bind(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
+			return false;
+
+		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			return true;
+	}
+#endif
+	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
+}
+
 struct inet_bind_hashbucket *
 inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port);
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 5dfac6ce1110..e961936b6be7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -154,20 +154,6 @@ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 }
 EXPORT_SYMBOL(inet_sk_get_local_port_range);
 
-static bool inet_use_bhash2_on_bind(const struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6) {
-		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
-			return false;
-
-		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
-			return true;
-	}
-#endif
-	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
-}
-
 static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
 			       kuid_t uid, bool relax,
 			       bool reuseport_cb_ok, bool reuseport_ok)
@@ -259,7 +245,7 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 	 * checks separately because their spinlocks have to be acquired/released
 	 * independently of each other, to prevent possible deadlocks
 	 */
-	if (inet_use_bhash2_on_bind(sk))
+	if (inet_use_hash2_on_bind(sk))
 		return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax,
 						   reuseport_cb_ok, reuseport_ok);
 
@@ -376,7 +362,7 @@ other_parity_scan:
 		head = &hinfo->bhash[inet_bhashfn(net, port,
 						  hinfo->bhash_size)];
 		spin_lock_bh(&head->lock);
-		if (inet_use_bhash2_on_bind(sk)) {
+		if (inet_use_hash2_on_bind(sk)) {
 			if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false))
 				goto next_port;
 		}
@@ -562,7 +548,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 				check_bind_conflict = false;
 		}
 
-		if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) {
+		if (check_bind_conflict && inet_use_hash2_on_bind(sk)) {
 			if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true))
 				goto fail_unlock;
 		}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b60fad393e18..cb99a3c27053 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -287,7 +287,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 	} else {
 		hslot = udp_hashslot(udptable, net, snum);
 		spin_lock_bh(&hslot->lock);
-		if (hslot->count > 10) {
+		if (inet_use_hash2_on_bind(sk) && hslot->count > 10) {
 			int exist;
 			unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
 
-- 
cgit v1.2.3


From 70b439bf06f6a12e491f827fa81a9887a11501f9 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Fri, 20 Mar 2026 17:42:22 +0800
Subject: net: enetc: fix the output issue of 'ethtool --show-ring'

Currently, enetc_get_ringparam() only provides rx_pending and tx_pending,
but 'ethtool --show-ring' no longer displays these fields. Because the
ringparam retrieval path has moved to the new netlink interface, where
rings_fill_reply() emits the *x_pending only if the *x_max_pending values
are non-zero. So rx_max_pending and tx_max_pending to are added to
enetc_get_ringparam() to fix the issue.

Note that the maximum tx/rx ring size of hardware is 64K, but we haven't
added set_ringparam() to make the ring size configurable. To avoid users
mistakenly believing that the ring size can be increased, so set
the *x_max_pending to priv->*x_bd_count.

Fixes: e4a1717b677c ("ethtool: provide ring sizes with RINGS_GET request")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20260320094222.706339-1-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index fed89d4f1e1d..2fe140ddebb2 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -813,6 +813,8 @@ static void enetc_get_ringparam(struct net_device *ndev,
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 
+	ring->rx_max_pending = priv->rx_bd_count;
+	ring->tx_max_pending = priv->tx_bd_count;
 	ring->rx_pending = priv->rx_bd_count;
 	ring->tx_pending = priv->tx_bd_count;
 
-- 
cgit v1.2.3


From 6896ca5a9d05275fbeb38640c9bbdb95698de188 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@kernel.org>
Date: Tue, 24 Mar 2026 01:19:26 +0800
Subject: arm64: dts: allwinner: sun55i: Fix r-spi DMA

r-spi has DRQs for both the main and MCU DMA controllers on the A523 SoC
family, however it seems it that it is mainly routed to the MCU DMA
controller, with no obvious way to change it.

Change the DMA channels of r-spi to the MCU so that it works properly.

Fixes: 1bec3bd1f839 ("arm64: dts: allwinner: sun55i: Add SPI controllers")
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Link: https://patch.msgid.link/20260323171927.1256507-1-wens@kernel.org
Signed-off-by: Chen-Yu Tsai <wens@kernel.org>
---
 arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi b/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi
index 9335977751e2..a4230205c02b 100644
--- a/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun55i-a523.dtsi
@@ -901,7 +901,7 @@
 			interrupts = <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&r_ccu CLK_BUS_R_SPI>, <&r_ccu CLK_R_SPI>;
 			clock-names = "ahb", "mod";
-			dmas = <&dma 53>, <&dma 53>;
+			dmas = <&mcu_dma 13>, <&mcu_dma 13>;
 			dma-names = "rx", "tx";
 			resets = <&r_ccu RST_BUS_R_SPI>;
 			status = "disabled";
-- 
cgit v1.2.3


From 966a08c293cb9290d3fe932961404e87b3f81327 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@oss.qualcomm.com>
Date: Thu, 22 Jan 2026 17:40:40 +0530
Subject: dt-bindings: display: msm: qcm2290-mdss: Fix iommus property

Fix IOMMU DT propety for display via dropping SMMU stream IDs which
relates to secure context bank. Assigning Linux kernel (HLOS) VMID
to secure context bank stream IDs is incorrect. The maximum value
for iommus property is updated accordingly.

These DT bindings changes should be backwards compatible.

Signed-off-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20260122121042.579270-2-sumit.garg@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml          | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
index f0cdb5422688..2772cdec7e42 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
@@ -33,7 +33,7 @@ properties:
       - const: core
 
   iommus:
-    maxItems: 2
+    maxItems: 1
 
   interconnects:
     items:
@@ -107,9 +107,7 @@ examples:
         interconnect-names = "mdp0-mem",
                              "cpu-cfg";
 
-        iommus = <&apps_smmu 0x420 0x2>,
-                 <&apps_smmu 0x421 0x0>;
-        ranges;
+        iommus = <&apps_smmu 0x420 0x2>;
 
         display-controller@5e01000 {
             compatible = "qcom,qcm2290-dpu";
-- 
cgit v1.2.3


From 7e59cd4ad586afd87f67491cf91fa1141292cf57 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@oss.qualcomm.com>
Date: Thu, 22 Jan 2026 17:40:41 +0530
Subject: dt-bindings: media: venus: Fix iommus property

Fix IOMMU DT propety for venus via dropping SMMU stream IDs which
relates to secure context bank. Assigning Linux kernel (HLOS) VMID
to secure context bank stream IDs is incorrect. The maximum value
for iommus property is updated accordingly.

These DT bindings changes should be backwards compatible.

Signed-off-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20260122121042.579270-3-sumit.garg@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 Documentation/devicetree/bindings/media/qcom,qcm2290-venus.yaml | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/qcom,qcm2290-venus.yaml b/Documentation/devicetree/bindings/media/qcom,qcm2290-venus.yaml
index 3f3ee82fc878..7e6dc410c2d2 100644
--- a/Documentation/devicetree/bindings/media/qcom,qcm2290-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,qcm2290-venus.yaml
@@ -42,7 +42,7 @@ properties:
       - const: vcodec0_bus
 
   iommus:
-    maxItems: 5
+    maxItems: 2
 
   interconnects:
     maxItems: 2
@@ -102,10 +102,7 @@ examples:
         memory-region = <&pil_video_mem>;
 
         iommus = <&apps_smmu 0x860 0x0>,
-                 <&apps_smmu 0x880 0x0>,
-                 <&apps_smmu 0x861 0x04>,
-                 <&apps_smmu 0x863 0x0>,
-                 <&apps_smmu 0x804 0xe0>;
+                 <&apps_smmu 0x880 0x0>;
 
         interconnects = <&mmnrt_virt MASTER_VIDEO_P0 RPM_ALWAYS_TAG
                          &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
-- 
cgit v1.2.3


From 2c409e03fc04b5cded81b7add9ce509706c922e3 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@oss.qualcomm.com>
Date: Thu, 22 Jan 2026 17:40:42 +0530
Subject: arm64: dts: qcom: agatti: Fix IOMMU DT properties

Fix IOMMU DT propeties for GPU, display and video peripherals via
dropping SMMU stream IDs which relates to secure context bank.

This problem only surfaced when the Gunyah based firmware stack is
ported on Agatti replacing the legacy QHEE based firmware stack. Assigning
Linux kernel (HLOS) VMID to secure context bank stream IDs is treated
as a fault by Gunyah hypervisor which were previously ignored by QHEE
hypervisor.

The DT changes should be backwards compatible with legacy QHEE based
firmware stack too.

Suggested-by: Prakash Gupta <guptap@qti.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260122121042.579270-4-sumit.garg@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/agatti.dtsi | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/agatti.dtsi b/arch/arm64/boot/dts/qcom/agatti.dtsi
index 76b93b7bd50f..893cb0689013 100644
--- a/arch/arm64/boot/dts/qcom/agatti.dtsi
+++ b/arch/arm64/boot/dts/qcom/agatti.dtsi
@@ -1669,8 +1669,7 @@
 					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>;
 			interconnect-names = "gfx-mem";
 
-			iommus = <&adreno_smmu 0 1>,
-				 <&adreno_smmu 2 0>;
+			iommus = <&adreno_smmu 0 1>;
 			operating-points-v2 = <&gpu_opp_table>;
 			power-domains = <&rpmpd QCM2290_VDDCX>;
 			qcom,gmu = <&gmu_wrapper>;
@@ -1951,8 +1950,7 @@
 
 			power-domains = <&dispcc MDSS_GDSC>;
 
-			iommus = <&apps_smmu 0x420 0x2>,
-				 <&apps_smmu 0x421 0x0>;
+			iommus = <&apps_smmu 0x420 0x2>;
 			interconnects = <&mmrt_virt MASTER_MDP0 RPM_ALWAYS_TAG
 					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
 					<&bimc MASTER_APPSS_PROC RPM_ALWAYS_TAG
@@ -2436,10 +2434,7 @@
 
 			memory-region = <&pil_video_mem>;
 			iommus = <&apps_smmu 0x860 0x0>,
-				 <&apps_smmu 0x880 0x0>,
-				 <&apps_smmu 0x861 0x04>,
-				 <&apps_smmu 0x863 0x0>,
-				 <&apps_smmu 0x804 0xe0>;
+				 <&apps_smmu 0x880 0x0>;
 
 			interconnects = <&mmnrt_virt MASTER_VIDEO_P0 RPM_ALWAYS_TAG
 					 &bimc SLAVE_EBI1 RPM_ALWAYS_TAG>,
-- 
cgit v1.2.3


From 77fcf58df15edcf3f5b5421f24814fb72796def9 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 20 Mar 2026 11:29:00 +0200
Subject: drm/i915/dp_tunnel: Fix error handling when clearing stream BW in
 atomic state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clearing the DP tunnel stream BW in the atomic state involves getting
the tunnel group state, which can fail. Handle the error accordingly.

This fixes at least one issue where drm_dp_tunnel_atomic_set_stream_bw()
failed to get the tunnel group state returning -EDEADLK, which wasn't
handled. This lead to the ctx->contended warn later in modeset_lock()
while taking a WW mutex for another object in the same atomic state, and
thus within the same already contended WW context.

Moving intel_crtc_state_alloc() later would avoid freeing saved_state on
the error path; this stable patch leaves that simplification for a
follow-up.

Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Fixes: a4efae87ecb2 ("drm/i915/dp: Compute DP tunnel BW during encoder state computation")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7617
Reviewed-by: Michał Grzelak <michal.grzelak@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patch.msgid.link/20260320092900.13210-1-imre.deak@intel.com
(cherry picked from commit fb69d0076e687421188bc8103ab0e8e5825b1df1)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c   |  8 +++++++-
 drivers/gpu/drm/i915/display/intel_dp_tunnel.c | 20 ++++++++++++++------
 drivers/gpu/drm/i915/display/intel_dp_tunnel.h | 11 +++++++----
 3 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index c4246481fc2f..0f82bf771a92 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4602,6 +4602,7 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state,
 	struct intel_crtc_state *crtc_state =
 		intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_crtc_state *saved_state;
+	int err;
 
 	saved_state = intel_crtc_state_alloc(crtc);
 	if (!saved_state)
@@ -4610,7 +4611,12 @@ intel_crtc_prepare_cleared_state(struct intel_atomic_state *state,
 	/* free the old crtc_state->hw members */
 	intel_crtc_free_hw_state(crtc_state);
 
-	intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state);
+	err = intel_dp_tunnel_atomic_clear_stream_bw(state, crtc_state);
+	if (err) {
+		kfree(saved_state);
+
+		return err;
+	}
 
 	/* FIXME: before the switch to atomic started, a new pipe_config was
 	 * kzalloc'd. Code that depends on any field being zero should be
diff --git a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c
index 83865c02d477..55b423fd6b6f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_tunnel.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_tunnel.c
@@ -621,19 +621,27 @@ int intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state,
  *
  * Clear any DP tunnel stream BW requirement set by
  * intel_dp_tunnel_atomic_compute_stream_bw().
+ *
+ * Returns 0 in case of success, a negative error code otherwise.
  */
-void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-					    struct intel_crtc_state *crtc_state)
+int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
+					   struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	int err;
 
 	if (!crtc_state->dp_tunnel_ref.tunnel)
-		return;
+		return 0;
+
+	err = drm_dp_tunnel_atomic_set_stream_bw(&state->base,
+						 crtc_state->dp_tunnel_ref.tunnel,
+						 crtc->pipe, 0);
+	if (err)
+		return err;
 
-	drm_dp_tunnel_atomic_set_stream_bw(&state->base,
-					   crtc_state->dp_tunnel_ref.tunnel,
-					   crtc->pipe, 0);
 	drm_dp_tunnel_ref_put(&crtc_state->dp_tunnel_ref);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/display/intel_dp_tunnel.h b/drivers/gpu/drm/i915/display/intel_dp_tunnel.h
index 7f0f720e8dca..10ab9eebcef6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_tunnel.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_tunnel.h
@@ -40,8 +40,8 @@ int intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state,
 					     struct intel_dp *intel_dp,
 					     const struct intel_connector *connector,
 					     struct intel_crtc_state *crtc_state);
-void intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-					    struct intel_crtc_state *crtc_state);
+int intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
+					   struct intel_crtc_state *crtc_state);
 
 int intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state,
 					      struct intel_crtc *crtc);
@@ -88,9 +88,12 @@ intel_dp_tunnel_atomic_compute_stream_bw(struct intel_atomic_state *state,
 	return 0;
 }
 
-static inline void
+static inline int
 intel_dp_tunnel_atomic_clear_stream_bw(struct intel_atomic_state *state,
-				       struct intel_crtc_state *crtc_state) {}
+				       struct intel_crtc_state *crtc_state)
+{
+	return 0;
+}
 
 static inline int
 intel_dp_tunnel_atomic_add_state_for_crtc(struct intel_atomic_state *state,
-- 
cgit v1.2.3


From f621324dfb3d6719cc9ffe65e8ec6051664ca059 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 23 Mar 2026 14:00:17 -0700
Subject: iomap: fix lockdep complaint when reads fail

Zorro Lang reported the following lockdep splat:

"While running fstests xfs/556 on kernel 7.0.0-rc4+ (HEAD=04a9f1766954),
a lockdep warning was triggered indicating an inconsistent lock state
for sb->s_type->i_lock_key.

"The deadlock might occur because iomap_read_end_io (called from a
hardware interrupt completion path) invokes fserror_report, which then
calls igrab.  igrab attempts to acquire the i_lock spinlock. However,
the i_lock is frequently acquired in process context with interrupts
enabled. If an interrupt occurs while a process holds the i_lock, and
that interrupt handler calls fserror_report, the system deadlocks.

"I hit this warning several times by running xfs/556 (mostly) or
generic/648 on xfs. More details refer to below console log."

along with this dmesg, for which I've cleaned up the stacktraces:

 run fstests xfs/556 at 2026-03-18 20:05:30
 XFS (sda3): Mounting V5 Filesystem 396e9164-c45a-4e05-be9d-b38c2c5c6477
 XFS (sda3): Ending clean mount
 XFS (sda3): Unmounting Filesystem 396e9164-c45a-4e05-be9d-b38c2c5c6477
 XFS (sda3): Mounting V5 Filesystem bf3f89c3-3c45-4650-a9c7-744f39c0191e
 XFS (sda3): Ending clean mount
 XFS (sda3): Unmounting Filesystem bf3f89c3-3c45-4650-a9c7-744f39c0191e
 XFS (dm-0): Mounting V5 Filesystem bf3f89c3-3c45-4650-a9c7-744f39c0191e
 XFS (dm-0): Ending clean mount
 device-mapper: table: 253:0: adding target device (start sect 209 len 1) caused an alignment inconsistency
 device-mapper: table: 253:0: adding target device (start sect 210 len 62914350) caused an alignment inconsistency
 buffer_io_error: 6 callbacks suppressed
 Buffer I/O error on dev dm-0, logical block 209, async page read
 Buffer I/O error on dev dm-0, logical block 209, async page read
 XFS (dm-0): Unmounting Filesystem bf3f89c3-3c45-4650-a9c7-744f39c0191e
 XFS (dm-0): Mounting V5 Filesystem bf3f89c3-3c45-4650-a9c7-744f39c0191e
 XFS (dm-0): Ending clean mount

 ================================
 WARNING: inconsistent lock state
 7.0.0-rc4+ #1 Tainted: G S      W
 --------------------------------
 inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
 od/2368602 [HC1[1]:SC0[0]:HE0:SE1] takes:
 ff1100069f2b4a98 (&sb->s_type->i_lock_key#31){?.+.}-{3:3}, at: igrab+0x28/0x1a0
 {HARDIRQ-ON-W} state was registered at:
   __lock_acquire+0x40d/0xbd0
   lock_acquire.part.0+0xbd/0x260
   _raw_spin_lock+0x37/0x80
   unlock_new_inode+0x66/0x2a0
   xfs_iget+0x67b/0x7b0 [xfs]
   xfs_mountfs+0xde4/0x1c80 [xfs]
   xfs_fs_fill_super+0xe86/0x17a0 [xfs]
   get_tree_bdev_flags+0x312/0x590
   vfs_get_tree+0x8d/0x2f0
   vfs_cmd_create+0xb2/0x240
   __do_sys_fsconfig+0x3d8/0x9a0
   do_syscall_64+0x13a/0x1520
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
 irq event stamp: 3118
 hardirqs last  enabled at (3117): [<ffffffffb54e4ad8>] _raw_spin_unlock_irq+0x28/0x50
 hardirqs last disabled at (3118): [<ffffffffb54b84c9>] common_interrupt+0x19/0xe0
 softirqs last  enabled at (3040): [<ffffffffb290ca28>] handle_softirqs+0x6b8/0x950
 softirqs last disabled at (3023): [<ffffffffb290ce4d>] __irq_exit_rcu+0xfd/0x250

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&sb->s_type->i_lock_key#31);
   <Interrupt>
     lock(&sb->s_type->i_lock_key#31);

  *** DEADLOCK ***

 1 lock held by od/2368602:
  #0: ff1100069f2b4b58 (&sb->s_type->i_mutex_key#19){++++}-{4:4}, at: xfs_ilock+0x324/0x4b0 [xfs]

 stack backtrace:
 CPU: 15 UID: 0 PID: 2368602 Comm: od Kdump: loaded Tainted: G S      W           7.0.0-rc4+ #1 PREEMPT(full)
 Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
 Hardware name: Dell Inc. PowerEdge R660/0R5JJC, BIOS 2.1.5 03/14/2024
 Call Trace:
  <IRQ>
  dump_stack_lvl+0x6f/0xb0
  print_usage_bug.part.0+0x230/0x2c0
  mark_lock_irq+0x3ce/0x5b0
  mark_lock+0x1cb/0x3d0
  mark_usage+0x109/0x120
  __lock_acquire+0x40d/0xbd0
  lock_acquire.part.0+0xbd/0x260
  _raw_spin_lock+0x37/0x80
  igrab+0x28/0x1a0
  fserror_report+0x127/0x2d0
  iomap_finish_folio_read+0x13c/0x280
  iomap_read_end_io+0x10e/0x2c0
  clone_endio+0x37e/0x780 [dm_mod]
  blk_update_request+0x448/0xf00
  scsi_end_request+0x74/0x750
  scsi_io_completion+0xe9/0x7c0
  _scsih_io_done+0x6ba/0x1ca0 [mpt3sas]
  _base_process_reply_queue+0x249/0x15b0 [mpt3sas]
  _base_interrupt+0x95/0xe0 [mpt3sas]
  __handle_irq_event_percpu+0x1f0/0x780
  handle_irq_event+0xa9/0x1c0
  handle_edge_irq+0x2ef/0x8a0
  __common_interrupt+0xa0/0x170
  common_interrupt+0xb7/0xe0
  </IRQ>
  <TASK>
  asm_common_interrupt+0x26/0x40
 RIP: 0010:_raw_spin_unlock_irq+0x2e/0x50
 Code: 0f 1f 44 00 00 53 48 8b 74 24 08 48 89 fb 48 83 c7 18 e8 b5 73 5e fd 48 89 df e8 ed e2 5e fd e8 08 78 8f fd fb bf 01 00 00 00 <e8> 8d 56 4d fd 65 8b 05 46 d5 1d 03 85 c0 74 06 5b c3 cc cc cc cc
 RSP: 0018:ffa0000027d07538 EFLAGS: 00000206
 RAX: 0000000000000c2d RBX: ffffffffb6614bc8 RCX: 0000000000000080
 RDX: 0000000000000000 RSI: ffffffffb6306a01 RDI: 0000000000000001
 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
 R10: ffffffffb75efc67 R11: 0000000000000001 R12: ff1100015ada0000
 R13: 0000000000000083 R14: 0000000000000002 R15: ffffffffb6614c10
  folio_wait_bit_common+0x407/0x780
  filemap_update_page+0x8e7/0xbd0
  filemap_get_pages+0x904/0xc50
  filemap_read+0x320/0xc20
  xfs_file_buffered_read+0x2aa/0x380 [xfs]
  xfs_file_read_iter+0x263/0x4a0 [xfs]
  vfs_read+0x6cb/0xb70
  ksys_read+0xf9/0x1d0
  do_syscall_64+0x13a/0x1520

Zorro's diagnosis makes sense, so the solution is to kick the failed
read handling to a workqueue much like we added for writeback ioends in
commit 294f54f849d846 ("fserror: fix lockdep complaint when igrabbing
inode").

Cc: Zorro Lang <zlang@redhat.com>
Link: https://lore.kernel.org/linux-xfs/20260319194303.efw4wcu7c4idhthz@doltdoltdolt/
Fixes: a9d573ee88af98 ("iomap: report file I/O errors to the VFS")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Link: https://patch.msgid.link/20260323210017.GL6223@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/bio.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 50 insertions(+), 1 deletion(-)

diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c
index fc045f2e4c45..edd908183058 100644
--- a/fs/iomap/bio.c
+++ b/fs/iomap/bio.c
@@ -8,7 +8,10 @@
 #include "internal.h"
 #include "trace.h"
 
-static void iomap_read_end_io(struct bio *bio)
+static DEFINE_SPINLOCK(failed_read_lock);
+static struct bio_list failed_read_list = BIO_EMPTY_LIST;
+
+static void __iomap_read_end_io(struct bio *bio)
 {
 	int error = blk_status_to_errno(bio->bi_status);
 	struct folio_iter fi;
@@ -18,6 +21,52 @@ static void iomap_read_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
+static void
+iomap_fail_reads(
+	struct work_struct	*work)
+{
+	struct bio		*bio;
+	struct bio_list		tmp = BIO_EMPTY_LIST;
+	unsigned long		flags;
+
+	spin_lock_irqsave(&failed_read_lock, flags);
+	bio_list_merge_init(&tmp, &failed_read_list);
+	spin_unlock_irqrestore(&failed_read_lock, flags);
+
+	while ((bio = bio_list_pop(&tmp)) != NULL) {
+		__iomap_read_end_io(bio);
+		cond_resched();
+	}
+}
+
+static DECLARE_WORK(failed_read_work, iomap_fail_reads);
+
+static void iomap_fail_buffered_read(struct bio *bio)
+{
+	unsigned long flags;
+
+	/*
+	 * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions
+	 * in the fserror code.  The caller no longer owns the bio reference
+	 * after the spinlock drops.
+	 */
+	spin_lock_irqsave(&failed_read_lock, flags);
+	if (bio_list_empty(&failed_read_list))
+		WARN_ON_ONCE(!schedule_work(&failed_read_work));
+	bio_list_add(&failed_read_list, bio);
+	spin_unlock_irqrestore(&failed_read_lock, flags);
+}
+
+static void iomap_read_end_io(struct bio *bio)
+{
+	if (bio->bi_status) {
+		iomap_fail_buffered_read(bio);
+		return;
+	}
+
+	__iomap_read_end_io(bio);
+}
+
 static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx)
 {
 	struct bio *bio = ctx->read_ctx;
-- 
cgit v1.2.3


From 38ec410b99a5ee6566f75650ce3d4fd632940fd0 Mon Sep 17 00:00:00 2001
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Date: Fri, 20 Mar 2026 10:18:17 +0800
Subject: virtio-net: correct hdr_len handling for VIRTIO_NET_F_GUEST_HDRLEN

The commit be50da3e9d4a ("net: virtio_net: implement exact header length
guest feature") introduces support for the VIRTIO_NET_F_GUEST_HDRLEN
feature in virtio-net.

This feature requires virtio-net to set hdr_len to the actual header
length of the packet when transmitting, the number of
bytes from the start of the packet to the beginning of the
transport-layer payload.

However, in practice, hdr_len was being set using skb_headlen(skb),
which is clearly incorrect. This commit fixes that issue.

Fixes: be50da3e9d4a ("net: virtio_net: implement exact header length guest feature")
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20260320021818.111741-2-xuanzhuo@linux.alibaba.com
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/tun_vnet.h     |  2 +-
 drivers/net/virtio_net.c   |  6 +++++-
 include/linux/virtio_net.h | 34 ++++++++++++++++++++++++++++++----
 3 files changed, 36 insertions(+), 6 deletions(-)

diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index a5f93b6c4482..fa5cab9d3e55 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -244,7 +244,7 @@ tun_vnet_hdr_tnl_from_skb(unsigned int flags,
 
 	if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload,
 					tun_vnet_is_little_endian(flags),
-					vlan_hlen, true)) {
+					vlan_hlen, true, false)) {
 		struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr;
 		struct skb_shared_info *sinfo = skb_shinfo(skb);
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 72d6a9c6a5a2..7106333ef904 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3267,8 +3267,12 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
 	struct virtio_net_hdr_v1_hash_tunnel *hdr;
 	int num_sg;
 	unsigned hdr_len = vi->hdr_len;
+	bool feature_hdrlen;
 	bool can_push;
 
+	feature_hdrlen = virtio_has_feature(vi->vdev,
+					    VIRTIO_NET_F_GUEST_HDRLEN);
+
 	pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest);
 
 	/* Make sure it's safe to cast between formats */
@@ -3288,7 +3292,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan)
 
 	if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl,
 					virtio_is_little_endian(vi->vdev), 0,
-					false))
+					false, feature_hdrlen))
 		return -EPROTO;
 
 	if (vi->mergeable_rx_bufs)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 75dabb763c65..361b60c8be68 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -207,6 +207,23 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
 }
 
+/* This function must be called after virtio_net_hdr_from_skb(). */
+static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb,
+					   struct virtio_net_hdr *hdr,
+					   bool little_endian)
+{
+	u16 hdr_len;
+
+	hdr_len = skb_transport_offset(skb);
+
+	if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4)
+		hdr_len += sizeof(struct udphdr);
+	else
+		hdr_len += tcp_hdrlen(skb);
+
+	hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len);
+}
+
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
@@ -385,7 +402,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 			    bool tnl_hdr_negotiated,
 			    bool little_endian,
 			    int vlan_hlen,
-			    bool has_data_valid)
+			    bool has_data_valid,
+			    bool feature_hdrlen)
 {
 	struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr;
 	unsigned int inner_nh, outer_th;
@@ -394,9 +412,17 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 
 	tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL |
 						    SKB_GSO_UDP_TUNNEL_CSUM);
-	if (!tnl_gso_type)
-		return virtio_net_hdr_from_skb(skb, hdr, little_endian,
-					       has_data_valid, vlan_hlen);
+	if (!tnl_gso_type) {
+		ret = virtio_net_hdr_from_skb(skb, hdr, little_endian,
+					      has_data_valid, vlan_hlen);
+		if (ret)
+			return ret;
+
+		if (feature_hdrlen && hdr->hdr_len)
+			__virtio_net_set_hdrlen(skb, hdr, little_endian);
+
+		return ret;
+	}
 
 	/* Tunnel support not negotiated but skb ask for it. */
 	if (!tnl_hdr_negotiated)
-- 
cgit v1.2.3


From 6c860dc02a8e60b438e26940227dfa641fcdb66a Mon Sep 17 00:00:00 2001
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Date: Fri, 20 Mar 2026 10:18:18 +0800
Subject: virtio-net: correct hdr_len handling for tunnel gso

The commit a2fb4bc4e2a6a03 ("net: implement virtio helpers to handle UDP
GSO tunneling.") introduces support for the UDP GSO tunnel feature in
virtio-net.

The virtio spec says:

    If the \field{gso_type} has the VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 bit or
    VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 bit set, \field{hdr_len} accounts for
    all the headers up to and including the inner transport.

The commit did not update the hdr_len to include the inner transport.

I observed that the "hdr_len" is 116 for this packet:

    17:36:18.241105 52:55:00:d1:27:0a > 2e:2c:df:46:a9:e1, ethertype IPv4 (0x0800), length 2912: (tos 0x0, ttl 64, id 45197, offset 0, flags [none], proto UDP (17), length 2898)
        192.168.122.100.50613 > 192.168.122.1.4789: [bad udp cksum 0x8106 -> 0x26a0!] VXLAN, flags [I] (0x08), vni 1
    fa:c3:ba:82:05:ee > ce:85:0c:31:77:e5, ethertype IPv4 (0x0800), length 2862: (tos 0x0, ttl 64, id 14678, offset 0, flags [DF], proto TCP (6), length 2848)
        192.168.3.1.49880 > 192.168.3.2.9898: Flags [P.], cksum 0x9266 (incorrect -> 0xaa20), seq 515667:518463, ack 1, win 64, options [nop,nop,TS val 2990048824 ecr 2798801412], length 2796

116 = 14(mac) + 20(ip) + 8(udp) + 8(vxlan) + 14(inner mac) + 20(inner ip) + 32(innner tcp)

Fixes: a2fb4bc4e2a6a03 ("net: implement virtio helpers to handle UDP GSO tunneling.")
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20260320021818.111741-3-xuanzhuo@linux.alibaba.com
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/virtio_net.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 361b60c8be68..f36d21b5bc19 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -224,6 +224,22 @@ static inline void __virtio_net_set_hdrlen(const struct sk_buff *skb,
 	hdr->hdr_len = __cpu_to_virtio16(little_endian, hdr_len);
 }
 
+/* This function must be called after virtio_net_hdr_from_skb(). */
+static inline void __virtio_net_set_tnl_hdrlen(const struct sk_buff *skb,
+					       struct virtio_net_hdr *hdr)
+{
+	u16 hdr_len;
+
+	hdr_len = skb_inner_transport_offset(skb);
+
+	if (hdr->gso_type == VIRTIO_NET_HDR_GSO_UDP_L4)
+		hdr_len += sizeof(struct udphdr);
+	else
+		hdr_len += inner_tcp_hdrlen(skb);
+
+	hdr->hdr_len = __cpu_to_virtio16(true, hdr_len);
+}
+
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
@@ -440,6 +456,9 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
 	if (ret)
 		return ret;
 
+	if (feature_hdrlen && hdr->hdr_len)
+		__virtio_net_set_tnl_hdrlen(skb, hdr);
+
 	if (skb->protocol == htons(ETH_P_IPV6))
 		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
 	else
-- 
cgit v1.2.3


From 425000dbf17373a4ab8be9428f5dc055ef870a56 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Fri, 20 Mar 2026 15:21:26 +0800
Subject: team: fix header_ops type confusion with non-Ethernet ports

Similar to commit 950803f72547 ("bonding: fix type confusion in
bond_setup_by_slave()") team has the same class of header_ops type
confusion.

For non-Ethernet ports, team_setup_by_port() copies port_dev->header_ops
directly. When the team device later calls dev_hard_header() or
dev_parse_header(), these callbacks can run with the team net_device
instead of the real lower device, so netdev_priv(dev) is interpreted as
the wrong private type and can crash.

The syzbot report shows a crash in bond_header_create(), but the root
cause is in team: the topology is gre -> bond -> team, and team calls
the inherited header_ops with its own net_device instead of the lower
device, so bond_header_create() receives a team device and interprets
netdev_priv() as bonding private data, causing a type confusion crash.

Fix this by introducing team header_ops wrappers for create/parse,
selecting a team port under RCU, and calling the lower device callbacks
with port->dev, so each callback always sees the correct net_device
context.

Also pass the selected lower device to the lower parse callback, so
recursion is bounded in stacked non-Ethernet topologies and parse
callbacks always run with the correct device context.

Fixes: 1d76efe1577b ("team: add support for non-ethernet devices")
Reported-by: syzbot+3d8bc31c45e11450f24c@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/69b46af7.050a0220.36eb34.000e.GAE@google.com/T/
Cc: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260320072139.134249-2-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/team/team_core.c | 65 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index b7282f5c9632..120aeb539d9f 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -2058,6 +2058,68 @@ static const struct ethtool_ops team_ethtool_ops = {
  * rt netlink interface
  ***********************/
 
+/* For tx path we need a linkup && enabled port and for parse any port
+ * suffices.
+ */
+static struct team_port *team_header_port_get_rcu(struct team *team,
+						  bool txable)
+{
+	struct team_port *port;
+
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		if (!txable || team_port_txable(port))
+			return port;
+	}
+
+	return NULL;
+}
+
+static int team_header_create(struct sk_buff *skb, struct net_device *team_dev,
+			      unsigned short type, const void *daddr,
+			      const void *saddr, unsigned int len)
+{
+	struct team *team = netdev_priv(team_dev);
+	const struct header_ops *port_ops;
+	struct team_port *port;
+	int ret = 0;
+
+	rcu_read_lock();
+	port = team_header_port_get_rcu(team, true);
+	if (port) {
+		port_ops = READ_ONCE(port->dev->header_ops);
+		if (port_ops && port_ops->create)
+			ret = port_ops->create(skb, port->dev,
+					       type, daddr, saddr, len);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static int team_header_parse(const struct sk_buff *skb,
+			     const struct net_device *team_dev,
+			     unsigned char *haddr)
+{
+	struct team *team = netdev_priv(team_dev);
+	const struct header_ops *port_ops;
+	struct team_port *port;
+	int ret = 0;
+
+	rcu_read_lock();
+	port = team_header_port_get_rcu(team, false);
+	if (port) {
+		port_ops = READ_ONCE(port->dev->header_ops);
+		if (port_ops && port_ops->parse)
+			ret = port_ops->parse(skb, port->dev, haddr);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static const struct header_ops team_header_ops = {
+	.create		= team_header_create,
+	.parse		= team_header_parse,
+};
+
 static void team_setup_by_port(struct net_device *dev,
 			       struct net_device *port_dev)
 {
@@ -2066,7 +2128,8 @@ static void team_setup_by_port(struct net_device *dev,
 	if (port_dev->type == ARPHRD_ETHER)
 		dev->header_ops	= team->header_ops_cache;
 	else
-		dev->header_ops	= port_dev->header_ops;
+		dev->header_ops	= port_dev->header_ops ?
+				  &team_header_ops : NULL;
 	dev->type = port_dev->type;
 	dev->hard_header_len = port_dev->hard_header_len;
 	dev->needed_headroom = port_dev->needed_headroom;
-- 
cgit v1.2.3


From 56063823b9f0e2acdca4d621face5c6a7a1f4c99 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Fri, 20 Mar 2026 15:21:27 +0800
Subject: selftests: team: add non-Ethernet header_ops reproducer

Add a team selftest that sets up:
  g0 (gre) -> b0 (bond) -> t0 (team)

and triggers IPv6 traffic on t0. This reproduces the non-Ethernet
header_ops confusion scenario and protects against regressions in stacked
team/bond/gre configurations.

Using this script, the panic reported by syzkaller can be reproduced [1].

After the fix:

  # ./non_ether_header_ops.sh
  PASS: non-Ethernet header_ops stacking did not crash

[1] https://syzkaller.appspot.com/bug?extid=3d8bc31c45e11450f24c

Cc: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Link: https://patch.msgid.link/20260320072139.134249-3-jiayuan.chen@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/team/Makefile  |  1 +
 tools/testing/selftests/drivers/net/team/config    |  2 ++
 .../drivers/net/team/non_ether_header_ops.sh       | 41 ++++++++++++++++++++++
 3 files changed, 44 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh

diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 45a3e7ad3dcb..02d6f51d5a06 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -3,6 +3,7 @@
 
 TEST_PROGS := \
 	dev_addr_lists.sh \
+	non_ether_header_ops.sh \
 	options.sh \
 	propagation.sh \
 	refleak.sh \
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 558e1d0cf565..5d36a22ef080 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,7 +1,9 @@
+CONFIG_BONDING=y
 CONFIG_DUMMY=y
 CONFIG_IPV6=y
 CONFIG_MACVLAN=y
 CONFIG_NETDEVSIM=m
+CONFIG_NET_IPGRE=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
diff --git a/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh
new file mode 100755
index 000000000000..948a43576bdc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/non_ether_header_ops.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# shellcheck disable=SC2154
+#
+# Reproduce the non-Ethernet header_ops confusion scenario with:
+#   g0 (gre) -> b0 (bond) -> t0 (team)
+#
+# Before the fix, direct header_ops inheritance in this stack could call
+# callbacks with the wrong net_device context and crash.
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/lib.sh
+
+trap cleanup_all_ns EXIT
+
+setup_ns ns1
+
+ip -n "$ns1" link add d0 type dummy
+ip -n "$ns1" addr add 10.10.10.1/24 dev d0
+ip -n "$ns1" link set d0 up
+
+ip -n "$ns1" link add g0 type gre local 10.10.10.1
+ip -n "$ns1" link add b0 type bond mode active-backup
+ip -n "$ns1" link add t0 type team
+
+ip -n "$ns1" link set g0 master b0
+ip -n "$ns1" link set b0 master t0
+
+ip -n "$ns1" link set g0 up
+ip -n "$ns1" link set b0 up
+ip -n "$ns1" link set t0 up
+
+# IPv6 address assignment triggers MLD join reports that call
+# dev_hard_header() on t0, exercising the inherited header_ops path.
+ip -n "$ns1" -6 addr add 2001:db8:1::1/64 dev t0 nodad
+for i in $(seq 1 20); do
+	ip netns exec "$ns1" ping -6 -I t0 ff02::1 -c1 -W1 &>/dev/null || true
+done
+
+echo "PASS: non-Ethernet header_ops stacking did not crash"
+exit "$EXIT_STATUS"
-- 
cgit v1.2.3


From fbddf68d7b4e1e6da7a78dd7fbd8ec376536584a Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Mon, 23 Mar 2026 08:36:35 -0700
Subject: platform/x86: ISST: Correct locked bit width
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SST-PP locked bit width is set to three bits. It should be only one bit.
Use SST_PP_LOCK_WIDTH define instead of SST_PP_LEVEL_WIDTH.

Fixes: ea009e4769fa ("platform/x86: ISST: Add SST-PP support via TPMI")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260323153635.3263828-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 6f46cbb2898f..e238c3105c78 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -872,7 +872,7 @@ static int isst_if_get_perf_level(void __user *argp)
 	_read_pp_info("current_level", perf_level.current_level, SST_PP_STATUS_OFFSET,
 		      SST_PP_LEVEL_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE)
 	_read_pp_info("locked", perf_level.locked, SST_PP_STATUS_OFFSET,
-		      SST_PP_LOCK_START, SST_PP_LEVEL_WIDTH, SST_MUL_FACTOR_NONE)
+		      SST_PP_LOCK_START, SST_PP_LOCK_WIDTH, SST_MUL_FACTOR_NONE)
 	_read_pp_info("feature_state", perf_level.feature_state, SST_PP_STATUS_OFFSET,
 		      SST_PP_FEATURE_STATE_START, SST_PP_FEATURE_STATE_WIDTH, SST_MUL_FACTOR_NONE)
 	perf_level.enabled = !!(power_domain_info->sst_header.cap_mask & BIT(1));
-- 
cgit v1.2.3


From eb8c426c9803beb171f89d15fea17505eb517714 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Fri, 20 Mar 2026 17:44:39 +0000
Subject: net: ti: icssg-prueth: fix use-after-free of CPPI descriptor in RX
 path

cppi5_hdesc_get_psdata() returns a pointer into the CPPI descriptor.
In both emac_rx_packet() and emac_rx_packet_zc(), the descriptor is
freed via k3_cppi_desc_pool_free() before the psdata pointer is used
by emac_rx_timestamp(), which dereferences psdata[0] and psdata[1].
This constitutes a use-after-free on every received packet that goes
through the timestamp path.

Defer the descriptor free until after all accesses through the psdata
pointer are complete. For emac_rx_packet(), move the free into the
requeue label so both early-exit and success paths free the descriptor
after all accesses are done. For emac_rx_packet_zc(), move the free to
the end of the loop body after emac_dispatch_skb_zc() (which calls
emac_rx_timestamp()) has returned.

Fixes: 46eeb90f03e0 ("net: ti: icssg-prueth: Use page_pool API for RX buffer allocation")
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260320174439.41080-1-devnexen@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 0a3cf2f848a5..fd4e7622f123 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -962,7 +962,6 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id,
 		pkt_len -= 4;
 		cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
 		psdata = cppi5_hdesc_get_psdata(desc_rx);
-		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 		count++;
 		xsk_buff_set_size(xdp, pkt_len);
 		xsk_buff_dma_sync_for_cpu(xdp);
@@ -988,6 +987,7 @@ static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id,
 			emac_dispatch_skb_zc(emac, xdp, psdata);
 			xsk_buff_free(xdp);
 		}
+		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 	}
 
 	if (xdp_status & ICSSG_XDP_REDIR)
@@ -1057,7 +1057,6 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state)
 	/* firmware adds 4 CRC bytes, strip them */
 	pkt_len -= 4;
 	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
-	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
 	/* if allocation fails we drop the packet but push the
 	 * descriptor back to the ring with old page to prevent a stall
@@ -1115,6 +1114,7 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state)
 	ndev->stats.rx_packets++;
 
 requeue:
+	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 	/* queue another RX DMA */
 	ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page,
 					PRUETH_MAX_PKT_SIZE);
-- 
cgit v1.2.3


From c4336a07eb6b2526dc2b62928b5104b41a7f81f5 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 20 Mar 2026 15:01:46 -0400
Subject: net: correctly handle tunneled traffic on IPV6_CSUM GSO fallback

NETIF_F_IPV6_CSUM only advertises support for checksum offload of
packets without IPv6 extension headers. Packets with extension
headers must fall back onto software checksumming. Since TSO
depends on checksum offload, those must revert to GSO.

The below commit introduces that fallback. It always checks
network header length. For tunneled packets, the inner header length
must be checked instead. Extend the check accordingly.

A special case is tunneled packets without inner IP protocol. Such as
RFC 6951 SCTP in UDP. Those are not standard IPv6 followed by
transport header either, so also must revert to the software GSO path.

Cc: stable@vger.kernel.org
Fixes: 864e3396976e ("net: gso: Forbid IPv6 TSO with extensions on devices with only IPV6_CSUM")
Reported-by: Tangxin Xie <xietangxin@yeah.net>
Closes: https://lore.kernel.org/netdev/0414e7e2-9a1c-4d7c-a99d-b9039cf68f40@yeah.net/
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260320190148.2409107-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/dev.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 14a83f2035b9..fc5557062414 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3769,6 +3769,22 @@ static netdev_features_t dflt_features_check(struct sk_buff *skb,
 	return vlan_features_check(skb, features);
 }
 
+static bool skb_gso_has_extension_hdr(const struct sk_buff *skb)
+{
+	if (!skb->encapsulation)
+		return ((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 ||
+			 (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
+			  vlan_get_protocol(skb) == htons(ETH_P_IPV6))) &&
+			skb_transport_header_was_set(skb) &&
+			skb_network_header_len(skb) != sizeof(struct ipv6hdr));
+	else
+		return (!skb_inner_network_header_was_set(skb) ||
+			((skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 ||
+			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
+			   inner_ip_hdr(skb)->version == 6)) &&
+			 skb_inner_network_header_len(skb) != sizeof(struct ipv6hdr)));
+}
+
 static netdev_features_t gso_features_check(const struct sk_buff *skb,
 					    struct net_device *dev,
 					    netdev_features_t features)
@@ -3816,11 +3832,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	 * so neither does TSO that depends on it.
 	 */
 	if (features & NETIF_F_IPV6_CSUM &&
-	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 ||
-	     (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
-	      vlan_get_protocol(skb) == htons(ETH_P_IPV6))) &&
-	    skb_transport_header_was_set(skb) &&
-	    skb_network_header_len(skb) != sizeof(struct ipv6hdr))
+	    skb_gso_has_extension_hdr(skb))
 		features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4);
 
 	return features;
-- 
cgit v1.2.3


From ec66ec6a5a8f53e7c70085749e8d68f4431c630f Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Tue, 24 Mar 2026 11:33:24 +0200
Subject: wifi: iwlwifi: mld: Fix MLO scan timing

Calculate MLO scan start time based on actual
scan start notification from firmware instead of recording
time when scan command is sent.

Currently, MLO scan start time was captured immediately
after sending the scan command to firmware. However, the
actual scan start time may differ due to the FW being busy
with a previous scan.

In that case, the link selection code will think that the MLO
scan is too old, and will warn.

To fix it, Implement start scan notification handling to
capture the precise moment when firmware begins the scan
operation.

Fixes: 9324731b9985 ("wifi: iwlwifi: mld: avoid selecting bad links")
Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20260324113316.4c56b8bac533.I6e656d8cc30bb82c96aabadedd62bd67f4c46bf9@changeid
---
 .../net/wireless/intel/iwlwifi/fw/api/commands.h   |  5 ++++
 drivers/net/wireless/intel/iwlwifi/fw/api/scan.h   | 10 ++++++++
 drivers/net/wireless/intel/iwlwifi/mld/mld.c       |  1 +
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c       |  4 +--
 drivers/net/wireless/intel/iwlwifi/mld/notif.c     |  5 ++++
 drivers/net/wireless/intel/iwlwifi/mld/scan.c      | 30 +++++++++++++++++++---
 drivers/net/wireless/intel/iwlwifi/mld/scan.h      |  9 ++++---
 7 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 8d64a271bb94..36159a769916 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -296,6 +296,11 @@ enum iwl_legacy_cmds {
 	 */
 	SCAN_OFFLOAD_UPDATE_PROFILES_CMD = 0x6E,
 
+	/**
+	 * @SCAN_START_NOTIFICATION_UMAC: uses &struct iwl_umac_scan_start
+	 */
+	SCAN_START_NOTIFICATION_UMAC = 0xb2,
+
 	/**
 	 * @MATCH_FOUND_NOTIFICATION: scan match found
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 60f0a4924ddf..46fcc32608e3 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -1156,6 +1156,16 @@ enum iwl_umac_scan_abort_status {
 	IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND,
 };
 
+/**
+ * struct iwl_umac_scan_start - scan start notification
+ * @uid: scan id, &enum iwl_umac_scan_uid_offsets
+ * @reserved: for future use
+ */
+struct iwl_umac_scan_start {
+	__le32 uid;
+	__le32 reserved;
+} __packed; /* SCAN_START_UMAC_API_S_VER_1 */
+
 /**
  * struct iwl_umac_scan_complete - scan complete notification
  * @uid: scan id, &enum iwl_umac_scan_uid_offsets
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index 495e9d8f3af6..9af79297c3b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -171,6 +171,7 @@ static const struct iwl_hcmd_names iwl_mld_legacy_names[] = {
 	HCMD_NAME(MISSED_BEACONS_NOTIFICATION),
 	HCMD_NAME(MAC_PM_POWER_TABLE),
 	HCMD_NAME(MFUART_LOAD_NOTIFICATION),
+	HCMD_NAME(SCAN_START_NOTIFICATION_UMAC),
 	HCMD_NAME(RSS_CONFIG_CMD),
 	HCMD_NAME(SCAN_ITERATION_COMPLETE_UMAC),
 	HCMD_NAME(REPLY_RX_MPDU_CMD),
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index f842f5183223..fbff5915f7fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -739,7 +739,7 @@ iwl_mld_set_link_sel_data(struct iwl_mld *mld,
 
 		/* Ignore any BSS that was not seen in the last MLO scan */
 		if (ktime_before(link_conf->bss->ts_boottime,
-				 mld->scan.last_mlo_scan_time))
+				 mld->scan.last_mlo_scan_start_time))
 			continue;
 
 		data[n_data].link_id = link_id;
@@ -945,7 +945,7 @@ static void _iwl_mld_select_links(struct iwl_mld *mld,
 	if (!mld_vif->authorized || hweight16(usable_links) <= 1)
 		return;
 
-	if (WARN(ktime_before(mld->scan.last_mlo_scan_time,
+	if (WARN(ktime_before(mld->scan.last_mlo_scan_start_time,
 			      ktime_sub_ns(ktime_get_boottime_ns(),
 					   5ULL * NSEC_PER_SEC)),
 		"Last MLO scan was too long ago, can't select links\n"))
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
index 240526d8b632..9c88a8579a75 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/notif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
@@ -287,6 +287,8 @@ static void iwl_mld_handle_beacon_notification(struct iwl_mld *mld,
  * at least enough bytes to cover the structure listed in the CMD_VER_ENTRY.
  */
 
+CMD_VERSIONS(scan_start_notif,
+	     CMD_VER_ENTRY(1, iwl_umac_scan_start))
 CMD_VERSIONS(scan_complete_notif,
 	     CMD_VER_ENTRY(1, iwl_umac_scan_complete))
 CMD_VERSIONS(scan_iter_complete_notif,
@@ -360,6 +362,7 @@ DEFINE_SIMPLE_CANCELLATION(datapath_monitor, iwl_datapath_monitor_notif,
 			   link_id)
 DEFINE_SIMPLE_CANCELLATION(roc, iwl_roc_notif, activity)
 DEFINE_SIMPLE_CANCELLATION(scan_complete, iwl_umac_scan_complete, uid)
+DEFINE_SIMPLE_CANCELLATION(scan_start, iwl_umac_scan_start, uid)
 DEFINE_SIMPLE_CANCELLATION(probe_resp_data, iwl_probe_resp_data_notif,
 			   mac_id)
 DEFINE_SIMPLE_CANCELLATION(uapsd_misbehaving_ap, iwl_uapsd_misbehaving_ap_notif,
@@ -402,6 +405,8 @@ const struct iwl_rx_handler iwl_mld_rx_handlers[] = {
 			     RX_HANDLER_SYNC)
 	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, BA_NOTIF, compressed_ba_notif,
 			     RX_HANDLER_SYNC)
+	RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_START_NOTIFICATION_UMAC,
+			   scan_start_notif)
 	RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_COMPLETE_UMAC,
 			   scan_complete_notif)
 	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, SCAN_ITERATION_COMPLETE_UMAC,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.c b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
index a1a4cf3ab3d3..abd4281b4b0e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
@@ -473,6 +473,9 @@ iwl_mld_scan_get_cmd_gen_flags(struct iwl_mld *mld,
 	    params->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_TRIGGER_UHB_SCAN;
 
+	if (scan_status == IWL_MLD_SCAN_INT_MLO)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_NTF_START;
+
 	if (params->enable_6ghz_passive)
 		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_6GHZ_PASSIVE_SCAN;
 
@@ -1817,9 +1820,6 @@ static void iwl_mld_int_mlo_scan_start(struct iwl_mld *mld,
 	ret = _iwl_mld_single_scan_start(mld, vif, req, &ies,
 					 IWL_MLD_SCAN_INT_MLO);
 
-	if (!ret)
-		mld->scan.last_mlo_scan_time = ktime_get_boottime_ns();
-
 	IWL_DEBUG_SCAN(mld, "Internal MLO scan: ret=%d\n", ret);
 }
 
@@ -1904,6 +1904,30 @@ void iwl_mld_handle_match_found_notif(struct iwl_mld *mld,
 	ieee80211_sched_scan_results(mld->hw);
 }
 
+void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt)
+{
+	struct iwl_umac_scan_complete *notif = (void *)pkt->data;
+	u32 uid = le32_to_cpu(notif->uid);
+
+	if (IWL_FW_CHECK(mld, uid >= ARRAY_SIZE(mld->scan.uid_status),
+			 "FW reports out-of-range scan UID %d\n", uid))
+		return;
+
+	if (IWL_FW_CHECK(mld, !(mld->scan.uid_status[uid] & mld->scan.status),
+			 "FW reports scan UID %d we didn't trigger\n", uid))
+		return;
+
+	IWL_DEBUG_SCAN(mld, "Scan started: uid=%u type=%u\n", uid,
+		       mld->scan.uid_status[uid]);
+	if (IWL_FW_CHECK(mld, mld->scan.uid_status[uid] != IWL_MLD_SCAN_INT_MLO,
+			 "FW reports scan start notification %d we didn't trigger\n",
+			 mld->scan.uid_status[uid]))
+		return;
+
+	mld->scan.last_mlo_scan_start_time = ktime_get_boottime_ns();
+}
+
 void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
 					struct iwl_rx_packet *pkt)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.h b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
index 69110f0cfc8e..de5620e7f463 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
@@ -27,6 +27,9 @@ int iwl_mld_sched_scan_start(struct iwl_mld *mld,
 void iwl_mld_handle_match_found_notif(struct iwl_mld *mld,
 				      struct iwl_rx_packet *pkt);
 
+void iwl_mld_handle_scan_start_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt);
+
 void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
 					struct iwl_rx_packet *pkt);
 
@@ -114,8 +117,8 @@ enum iwl_mld_traffic_load {
  *	in jiffies.
  * @last_start_time_jiffies: stores the last start time in jiffies
  *	(interface up/reset/resume).
- * @last_mlo_scan_time: start time of the last MLO scan in nanoseconds since
- *	boot.
+ * @last_mlo_scan_start_time: start time of the last MLO scan in nanoseconds
+ * since boot.
  */
 struct iwl_mld_scan {
 	/* Add here fields that need clean up on restart */
@@ -136,7 +139,7 @@ struct iwl_mld_scan {
 	void *cmd;
 	unsigned long last_6ghz_passive_jiffies;
 	unsigned long last_start_time_jiffies;
-	u64 last_mlo_scan_time;
+	u64 last_mlo_scan_start_time;
 };
 
 /**
-- 
cgit v1.2.3


From 323156c3541e23da7e582008a7ac30cd51b60acd Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 24 Mar 2026 11:33:25 +0200
Subject: wifi: iwlwifi: mvm: don't send a 6E related command when not
 supported

MCC_ALLOWED_AP_TYPE_CMD is related to 6E support. Do not send it if the
device doesn't support 6E.
Apparently, the firmware is mistakenly advertising support for this
command even on AX201 which does not support 6E and then the firmware
crashes.

Fixes: 0d2fc8821a7d ("wifi: iwlwifi: nvm: parse the VLP/AFC bit from regulatory")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220804
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20260324113316.e171f0163f2a.I0c444d1f82d1773054e7ffc391ad49697d58f44e@changeid
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 43cf94c9a36b..6cc78661116e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -470,7 +470,8 @@ static void iwl_mvm_uats_init(struct iwl_mvm *mvm)
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 	};
 
-	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) {
+	if (mvm->trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210 ||
+	    !mvm->trans->cfg->uhb_supported) {
 		IWL_DEBUG_RADIO(mvm, "UATS feature is not supported\n");
 		return;
 	}
-- 
cgit v1.2.3


From 687a95d204e72e52f2e6bc7a994cc82f76b2678f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 24 Mar 2026 11:33:26 +0200
Subject: wifi: iwlwifi: mld: correctly set wifi generation data

In each MAC context, the firmware expects the wifi generation
data, i.e. whether or not HE/EHT (and in the future UHR) is
enabled on that MAC.

However, this is currently handled wrong in two ways:
 - EHT is only enabled when the interface is also an MLD, but
   we currently allow (despite the spec) connecting with EHT
   but without MLO.
 - when HE or EHT are used by TDLS peers, the firmware needs
   to have them enabled regardless of the AP

Fix this by iterating setting up the data depending on the
interface type:
 - for AP, just set it according to the BSS configuration
 - for monitor, set it according to HW capabilities
 - otherwise, particularly for client, iterate all stations
   and then their links on the interface in question and set
   according to their capabilities, this handles the AP and
   TDLS peers. Re-calculate this whenever a TDLS station is
   marked associated or removed so that it's kept updated,
   for the AP it's already updated on assoc/disassoc.

Fixes: d1e879ec600f ("wifi: iwlwifi: add iwlmld sub-driver")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20260319110722.404713b22177.Ic972b5e557d011a5438f8f97c1e793cc829e2ea9@changeid
Link: https://patch.msgid.link/20260324093333.2953495-1-miriam.rachel.korenblit@intel.com
---
 drivers/net/wireless/intel/iwlwifi/mld/iface.c    | 101 +++++++++++++++-------
 drivers/net/wireless/intel/iwlwifi/mld/mac80211.c |  19 ++++
 2 files changed, 88 insertions(+), 32 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
index 29df747c8938..9215fc7e2eca 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
@@ -111,14 +111,75 @@ static bool iwl_mld_is_nic_ack_enabled(struct iwl_mld *mld,
 			       IEEE80211_HE_MAC_CAP2_ACK_EN);
 }
 
-static void iwl_mld_set_he_support(struct iwl_mld *mld,
-				   struct ieee80211_vif *vif,
-				   struct iwl_mac_config_cmd *cmd)
+struct iwl_mld_mac_wifi_gen_sta_iter_data {
+	struct ieee80211_vif *vif;
+	struct iwl_mac_wifi_gen_support *support;
+};
+
+static void iwl_mld_mac_wifi_gen_sta_iter(void *_data,
+					  struct ieee80211_sta *sta)
 {
-	if (vif->type == NL80211_IFTYPE_AP)
-		cmd->wifi_gen.he_ap_support = 1;
-	else
-		cmd->wifi_gen.he_support = 1;
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_mac_wifi_gen_sta_iter_data *data = _data;
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
+
+	if (mld_sta->vif != data->vif)
+		return;
+
+	for_each_sta_active_link(data->vif, sta, link_sta, link_id) {
+		if (link_sta->he_cap.has_he)
+			data->support->he_support = 1;
+		if (link_sta->eht_cap.has_eht)
+			data->support->eht_support = 1;
+	}
+}
+
+static void iwl_mld_set_wifi_gen(struct iwl_mld *mld,
+				 struct ieee80211_vif *vif,
+				 struct iwl_mac_wifi_gen_support *support)
+{
+	struct iwl_mld_mac_wifi_gen_sta_iter_data sta_iter_data = {
+		.vif = vif,
+		.support = support,
+	};
+	struct ieee80211_bss_conf *link_conf;
+	unsigned int link_id;
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_MONITOR:
+		/* for sniffer, set to HW capabilities */
+		support->he_support = 1;
+		support->eht_support = mld->trans->cfg->eht_supported;
+		break;
+	case NL80211_IFTYPE_AP:
+		/* for AP set according to the link configs */
+		for_each_vif_active_link(vif, link_conf, link_id) {
+			support->he_ap_support |= link_conf->he_support;
+			support->eht_support |= link_conf->eht_support;
+		}
+		break;
+	default:
+		/*
+		 * If we have MLO enabled, then the firmware needs to enable
+		 * address translation for the station(s) we add. That depends
+		 * on having EHT enabled in firmware, which in turn depends on
+		 * mac80211 in the iteration below.
+		 * However, mac80211 doesn't enable capabilities on the AP STA
+		 * until it has parsed the association response successfully,
+		 * so set EHT (and HE as a pre-requisite for EHT) when the vif
+		 * is an MLD.
+		 */
+		if (ieee80211_vif_is_mld(vif)) {
+			support->he_support = 1;
+			support->eht_support = 1;
+		}
+
+		ieee80211_iterate_stations_mtx(mld->hw,
+					       iwl_mld_mac_wifi_gen_sta_iter,
+					       &sta_iter_data);
+		break;
+	}
 }
 
 /* fill the common part for all interface types */
@@ -128,8 +189,6 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 					u32 action)
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct ieee80211_bss_conf *link_conf;
-	unsigned int link_id;
 
 	lockdep_assert_wiphy(mld->wiphy);
 
@@ -147,29 +206,7 @@ static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
 	cmd->nic_not_ack_enabled =
 		cpu_to_le32(!iwl_mld_is_nic_ack_enabled(mld, vif));
 
-	/* If we have MLO enabled, then the firmware needs to enable
-	 * address translation for the station(s) we add. That depends
-	 * on having EHT enabled in firmware, which in turn depends on
-	 * mac80211 in the code below.
-	 * However, mac80211 doesn't enable HE/EHT until it has parsed
-	 * the association response successfully, so just skip all that
-	 * and enable both when we have MLO.
-	 */
-	if (ieee80211_vif_is_mld(vif)) {
-		iwl_mld_set_he_support(mld, vif, cmd);
-		cmd->wifi_gen.eht_support = 1;
-		return;
-	}
-
-	for_each_vif_active_link(vif, link_conf, link_id) {
-		if (!link_conf->he_support)
-			continue;
-
-		iwl_mld_set_he_support(mld, vif, cmd);
-
-		/* EHT, if supported, was already set above */
-		break;
-	}
+	iwl_mld_set_wifi_gen(mld, vif, &cmd->wifi_gen);
 }
 
 static void iwl_mld_fill_mac_cmd_sta(struct iwl_mld *mld,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 0c53d6bd9651..71a9a72c9ac0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -1761,6 +1761,16 @@ static int iwl_mld_move_sta_state_up(struct iwl_mld *mld,
 
 		if (vif->type == NL80211_IFTYPE_STATION)
 			iwl_mld_link_set_2mhz_block(mld, vif, sta);
+
+		if (sta->tdls) {
+			/*
+			 * update MAC since wifi generation flags may change,
+			 * we also update MAC on association to the AP via the
+			 * vif assoc change
+			 */
+			iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+		}
+
 		/* Now the link_sta's capabilities are set, update the FW */
 		iwl_mld_config_tlc(mld, vif, sta);
 
@@ -1873,6 +1883,15 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld,
 			/* just removed last TDLS STA, so enable PM */
 			iwl_mld_update_mac_power(mld, vif, false);
 		}
+
+		if (sta->tdls) {
+			/*
+			 * update MAC since wifi generation flags may change,
+			 * we also update MAC on disassociation to the AP via
+			 * the vif assoc change
+			 */
+			iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+		}
 	} else {
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 647b8a2fe474474704110db6bd07f7a139e621eb Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Sat, 21 Mar 2026 22:04:41 +0800
Subject: net: macb: Use dev_consume_skb_any() to free TX SKBs

The napi_consume_skb() function is not intended to be called in an IRQ
disabled context. However, after commit 6bc8a5098bf4 ("net: macb: Fix
tx_ptr_lock locking"), the freeing of TX SKBs is performed with IRQs
disabled. To resolve the following call trace, use dev_consume_skb_any()
for freeing TX SKBs:
   WARNING: kernel/softirq.c:430 at __local_bh_enable_ip+0x174/0x188, CPU#0: ksoftirqd/0/15
   Modules linked in:
   CPU: 0 UID: 0 PID: 15 Comm: ksoftirqd/0 Not tainted 7.0.0-rc4-next-20260319-yocto-standard-dirty #37 PREEMPT
   Hardware name: ZynqMP ZCU102 Rev1.1 (DT)
   pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
   pc : __local_bh_enable_ip+0x174/0x188
   lr : local_bh_enable+0x24/0x38
   sp : ffff800082b3bb10
   x29: ffff800082b3bb10 x28: ffff0008031f3c00 x27: 000000000011ede0
   x26: ffff000800a7ff00 x25: ffff800083937ce8 x24: 0000000000017a80
   x23: ffff000803243a78 x22: 0000000000000040 x21: 0000000000000000
   x20: ffff000800394c80 x19: 0000000000000200 x18: 0000000000000001
   x17: 0000000000000001 x16: ffff000803240000 x15: 0000000000000000
   x14: ffffffffffffffff x13: 0000000000000028 x12: ffff000800395650
   x11: ffff8000821d1528 x10: ffff800081c2bc08 x9 : ffff800081c1e258
   x8 : 0000000100000301 x7 : ffff8000810426ec x6 : 0000000000000000
   x5 : 0000000000000001 x4 : 0000000000000001 x3 : 0000000000000000
   x2 : 0000000000000008 x1 : 0000000000000200 x0 : ffff8000810428dc
   Call trace:
    __local_bh_enable_ip+0x174/0x188 (P)
    local_bh_enable+0x24/0x38
    skb_attempt_defer_free+0x190/0x1d8
    napi_consume_skb+0x58/0x108
    macb_tx_poll+0x1a4/0x558
    __napi_poll+0x50/0x198
    net_rx_action+0x1f4/0x3d8
    handle_softirqs+0x16c/0x560
    run_ksoftirqd+0x44/0x80
    smpboot_thread_fn+0x1d8/0x338
    kthread+0x120/0x150
    ret_from_fork+0x10/0x20
   irq event stamp: 29751
   hardirqs last  enabled at (29750): [<ffff8000813be184>] _raw_spin_unlock_irqrestore+0x44/0x88
   hardirqs last disabled at (29751): [<ffff8000813bdf60>] _raw_spin_lock_irqsave+0x38/0x98
   softirqs last  enabled at (29150): [<ffff8000800f1aec>] handle_softirqs+0x504/0x560
   softirqs last disabled at (29153): [<ffff8000800f2fec>] run_ksoftirqd+0x44/0x80

Fixes: 6bc8a5098bf4 ("net: macb: Fix tx_ptr_lock locking")
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260321-macb-tx-v1-1-b383a58dd4e6@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 944aab71795c..fc4dd0757646 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1071,7 +1071,7 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budge
 	}
 
 	if (tx_skb->skb) {
-		napi_consume_skb(tx_skb->skb, budget);
+		dev_consume_skb_any(tx_skb->skb);
 		tx_skb->skb = NULL;
 	}
 }
-- 
cgit v1.2.3


From 91049ec2e18376ec2192e73ef7be4c7110436350 Mon Sep 17 00:00:00 2001
From: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Date: Sat, 21 Mar 2026 02:20:11 +0100
Subject: ASoC: dt-bindings: stm32: Fix incorrect compatible string in
 stm32h7-sai match

The conditional block that defines clock constraints for the stm32h7-sai
variant references "st,stm32mph7-sai", which does not match any compatible
string in the enum. As a result, clock validation for the h7 variant is
silently skipped. Correct the compatible string to "st,stm32h7-sai".

Fixes: 8509bb1f11a1f ("ASoC: dt-bindings: add stm32mp25 support for sai")
Signed-off-by: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Reviewed-by: Olivier Moysan <olivier.moysan@foss.st.com>
Link: https://patch.msgid.link/20260321012011.125791-1-jihed.chaibi.dev@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/st,stm32-sai.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
index 4a7129d0b157..551edf39e766 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
+++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
@@ -164,7 +164,7 @@ allOf:
       properties:
         compatible:
           contains:
-            const: st,stm32mph7-sai
+            const: st,stm32h7-sai
     then:
       properties:
         clocks:
-- 
cgit v1.2.3


From 8121353a4bf8e38afee26299419a78ec108e14a6 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Tue, 24 Mar 2026 10:49:59 +0000
Subject: rust: regulator: do not assume that regulator_get() returns non-null

The Rust `Regulator` abstraction uses `NonNull` to wrap the underlying
`struct regulator` pointer. When `CONFIG_REGULATOR` is disabled, the C
stub for `regulator_get` returns `NULL`. `from_err_ptr` does not treat
`NULL` as an error, so it was passed to `NonNull::new_unchecked`,
causing undefined behavior.

Fix this by using a raw pointer `*mut bindings::regulator` instead of
`NonNull`. This allows `inner` to be `NULL` when `CONFIG_REGULATOR` is
disabled, and leverages the C stubs which are designed to handle `NULL`
or are no-ops.

Fixes: 9b614ceada7c ("rust: regulator: add a bare minimum regulator abstraction")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Closes: https://lore.kernel.org/r/20260322193830.89324-1-ojeda@kernel.org
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Link: https://patch.msgid.link/20260324-regulator-fix-v1-1-a5244afa3c15@google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 rust/kernel/regulator.rs | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/rust/kernel/regulator.rs b/rust/kernel/regulator.rs
index 4f7837c7e53a..41e730cedc81 100644
--- a/rust/kernel/regulator.rs
+++ b/rust/kernel/regulator.rs
@@ -23,7 +23,10 @@ use crate::{
     prelude::*,
 };
 
-use core::{marker::PhantomData, mem::ManuallyDrop, ptr::NonNull};
+use core::{
+    marker::PhantomData,
+    mem::ManuallyDrop, //
+};
 
 mod private {
     pub trait Sealed {}
@@ -229,15 +232,17 @@ pub fn devm_enable_optional(dev: &Device<Bound>, name: &CStr) -> Result {
 ///
 /// # Invariants
 ///
-/// - `inner` is a non-null wrapper over a pointer to a `struct
-///   regulator` obtained from [`regulator_get()`].
+/// - `inner` is a pointer obtained from a successful call to
+///   [`regulator_get()`]. It is treated as an opaque token that may only be
+///   accessed using C API methods (e.g., it may be `NULL` if the C API returns
+///   `NULL`).
 ///
 /// [`regulator_get()`]: https://docs.kernel.org/driver-api/regulator.html#c.regulator_get
 pub struct Regulator<State>
 where
     State: RegulatorState,
 {
-    inner: NonNull<bindings::regulator>,
+    inner: *mut bindings::regulator,
     _phantom: PhantomData<State>,
 }
 
@@ -249,7 +254,7 @@ impl<T: RegulatorState> Regulator<T> {
         // SAFETY: Safe as per the type invariants of `Regulator`.
         to_result(unsafe {
             bindings::regulator_set_voltage(
-                self.inner.as_ptr(),
+                self.inner,
                 min_voltage.as_microvolts(),
                 max_voltage.as_microvolts(),
             )
@@ -259,7 +264,7 @@ impl<T: RegulatorState> Regulator<T> {
     /// Gets the current voltage of the regulator.
     pub fn get_voltage(&self) -> Result<Voltage> {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        let voltage = unsafe { bindings::regulator_get_voltage(self.inner.as_ptr()) };
+        let voltage = unsafe { bindings::regulator_get_voltage(self.inner) };
 
         to_result(voltage).map(|()| Voltage::from_microvolts(voltage))
     }
@@ -270,10 +275,8 @@ impl<T: RegulatorState> Regulator<T> {
             // received from the C code.
             from_err_ptr(unsafe { bindings::regulator_get(dev.as_raw(), name.as_char_ptr()) })?;
 
-        // SAFETY: We can safely trust `inner` to be a pointer to a valid
-        // regulator if `ERR_PTR` was not returned.
-        let inner = unsafe { NonNull::new_unchecked(inner) };
-
+        // INVARIANT: `inner` is a pointer obtained from `regulator_get()`, and
+        // the call was successful.
         Ok(Self {
             inner,
             _phantom: PhantomData,
@@ -282,12 +285,12 @@ impl<T: RegulatorState> Regulator<T> {
 
     fn enable_internal(&self) -> Result {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        to_result(unsafe { bindings::regulator_enable(self.inner.as_ptr()) })
+        to_result(unsafe { bindings::regulator_enable(self.inner) })
     }
 
     fn disable_internal(&self) -> Result {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        to_result(unsafe { bindings::regulator_disable(self.inner.as_ptr()) })
+        to_result(unsafe { bindings::regulator_disable(self.inner) })
     }
 }
 
@@ -349,7 +352,7 @@ impl<T: IsEnabled> Regulator<T> {
     /// Checks if the regulator is enabled.
     pub fn is_enabled(&self) -> bool {
         // SAFETY: Safe as per the type invariants of `Regulator`.
-        unsafe { bindings::regulator_is_enabled(self.inner.as_ptr()) != 0 }
+        unsafe { bindings::regulator_is_enabled(self.inner) != 0 }
     }
 }
 
@@ -359,11 +362,11 @@ impl<T: RegulatorState> Drop for Regulator<T> {
             // SAFETY: By the type invariants, we know that `self` owns a
             // reference on the enabled refcount, so it is safe to relinquish it
             // now.
-            unsafe { bindings::regulator_disable(self.inner.as_ptr()) };
+            unsafe { bindings::regulator_disable(self.inner) };
         }
         // SAFETY: By the type invariants, we know that `self` owns a reference,
         // so it is safe to relinquish it now.
-        unsafe { bindings::regulator_put(self.inner.as_ptr()) };
+        unsafe { bindings::regulator_put(self.inner) };
     }
 }
 
-- 
cgit v1.2.3


From cfb385a8dc88d86a805a5682eaa68f59fa5c0ec3 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Date: Mon, 23 Mar 2026 23:17:48 +0000
Subject: ASoC: codecs: wcd934x: fix typo in dt parsing

Looks like we ended up with a typo during device tree data parsing
as part of 4f16b6351bbff ("ASoC: codecs: wcd: add common helper for wcd
codecs") patch.
 This will result in not parsing the device tree data and results in
zero mic bias values.

Fix this by calling wcd_dt_parse_micbias_info instead of
wcd_dt_parse_mbhc_data.

Fixes: 4f16b6351bbff ("ASoC: codecs: wcd: add common helper for wcd codecs")
Cc: Stable@vger.kernel.org
Reported-by: Joel Selvaraj <foss@joelselvaraj.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://patch.msgid.link/20260323231748.2217967-1-srinivas.kandagatla@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wcd934x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index c8db33f78a1b..bc41a1466c70 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -2172,7 +2172,7 @@ static int wcd934x_init_dmic(struct snd_soc_component *comp)
 	u32 def_dmic_rate, dmic_clk_drv;
 	int ret;
 
-	ret = wcd_dt_parse_mbhc_data(comp->dev, &wcd->mbhc_cfg);
+	ret = wcd_dt_parse_micbias_info(&wcd->common);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 56781a4597706cd25185b1dedc38841ec6c31496 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Thu, 19 Mar 2026 15:30:34 -0700
Subject: drm/xe: Implement recent spec updates to Wa_16025250150

The hardware teams noticed that the originally documented workaround
steps for Wa_16025250150 may not be sufficient to fully avoid a hardware
issue.  The workaround documentation has been augmented to suggest
programming one additional register; make the corresponding change in
the driver.

Fixes: 7654d51f1fd8 ("drm/xe/xe2hpg: Add Wa_16025250150")
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
Link: https://patch.msgid.link/20260319-wa_16025250150_part2-v1-1-46b1de1a31b2@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit a31566762d4075646a8a2214586158b681e94305)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_gt_regs.h | 1 +
 drivers/gpu/drm/xe/xe_wa.c           | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 24fc64fc832e..9d66f168ab8a 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -553,6 +553,7 @@
 #define   ENABLE_SMP_LD_RENDER_SURFACE_CONTROL	REG_BIT(44 - 32)
 #define   FORCE_SLM_FENCE_SCOPE_TO_TILE		REG_BIT(42 - 32)
 #define   FORCE_UGM_FENCE_SCOPE_TO_TILE		REG_BIT(41 - 32)
+#define   L3_128B_256B_WRT_DIS			REG_BIT(40 - 32)
 #define   MAXREQS_PER_BANK			REG_GENMASK(39 - 32, 37 - 32)
 #define   DISABLE_128B_EVICTION_COMMAND_UDW	REG_BIT(36 - 32)
 
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 462c2fa712e0..d7e309ad9aba 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -247,7 +247,8 @@ static const struct xe_rtp_entry_sr gt_was[] = {
 				   LSN_DIM_Z_WGT_MASK,
 				   LSN_LNI_WGT(1) | LSN_LNE_WGT(1) |
 				   LSN_DIM_X_WGT(1) | LSN_DIM_Y_WGT(1) |
-				   LSN_DIM_Z_WGT(1)))
+				   LSN_DIM_Z_WGT(1)),
+			SET(LSC_CHICKEN_BIT_0_UDW, L3_128B_256B_WRT_DIS))
 	},
 
 	/* Xe2_HPM */
-- 
cgit v1.2.3


From e225b36f83d7926c1f2035923bb0359d851fdb73 Mon Sep 17 00:00:00 2001
From: Reshma Immaculate Rajkumar <reshma.rajkumar@oss.qualcomm.com>
Date: Thu, 19 Mar 2026 12:26:08 +0530
Subject: wifi: ath11k: Pass the correct value of each TID during a stop AMPDU
 session

During ongoing traffic, a request to stop an AMPDU session
for one TID could incorrectly affect other active sessions.
This can happen because an incorrect TID reference would be
passed when updating the BA session state, causing the wrong
session to be stopped. As a result, the affected session would
be reduced to a minimal BA size, leading to a noticeable
throughput degradation.

Fix this issue by passing the correct argument from
ath11k_dp_rx_ampdu_stop() to ath11k_peer_rx_tid_reo_update()
during a stop AMPDU session. Instead of passing peer->tx_tid, which
is the base address of the array, corresponding to TID 0; pass
the value of &peer->rx_tid[params->tid], where the different TID numbers
are accounted for.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.9.0.1-02146-QCAHKSWPL_SILICONZ-1

Fixes: d5c65159f2895 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Signed-off-by: Reshma Immaculate Rajkumar <reshma.rajkumar@oss.qualcomm.com>
Reviewed-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260319065608.2408179-1-reshma.rajkumar@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 49d959b2e148..85defe11750d 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include <linux/ieee80211.h>
@@ -1110,9 +1110,8 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_peer *peer;
 	struct ath11k_sta *arsta = ath11k_sta_to_arsta(params->sta);
+	struct dp_rx_tid *rx_tid;
 	int vdev_id = arsta->arvif->vdev_id;
-	dma_addr_t paddr;
-	bool active;
 	int ret;
 
 	spin_lock_bh(&ab->base_lock);
@@ -1124,15 +1123,14 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar,
 		return -ENOENT;
 	}
 
-	paddr = peer->rx_tid[params->tid].paddr;
-	active = peer->rx_tid[params->tid].active;
+	rx_tid = &peer->rx_tid[params->tid];
 
-	if (!active) {
+	if (!rx_tid->active) {
 		spin_unlock_bh(&ab->base_lock);
 		return 0;
 	}
 
-	ret = ath11k_peer_rx_tid_reo_update(ar, peer, peer->rx_tid, 1, 0, false);
+	ret = ath11k_peer_rx_tid_reo_update(ar, peer, rx_tid, 1, 0, false);
 	spin_unlock_bh(&ab->base_lock);
 	if (ret) {
 		ath11k_warn(ab, "failed to update reo for rx tid %d: %d\n",
@@ -1141,7 +1139,8 @@ int ath11k_dp_rx_ampdu_stop(struct ath11k *ar,
 	}
 
 	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id,
-						     params->sta->addr, paddr,
+						     params->sta->addr,
+						     rx_tid->paddr,
 						     params->tid, 1, 1);
 	if (ret)
 		ath11k_warn(ab, "failed to send wmi to delete rx tid %d\n",
-- 
cgit v1.2.3


From 4242625f272974dd1947f73b10d884eab3b277cd Mon Sep 17 00:00:00 2001
From: Reshma Immaculate Rajkumar <reshma.rajkumar@oss.qualcomm.com>
Date: Fri, 27 Feb 2026 16:31:23 +0530
Subject: wifi: ath12k: Pass the correct value of each TID during a stop AMPDU
 session

With traffic ongoing for data TID [TID 0], an DELBA request to
stop AMPDU for the BA session was received on management TID [TID 4].
The corresponding TID number was incorrectly passed to stop the BA session,
resulting in the BA session for data TIDs being stopped and the BA size
being reduced to 1, causing an overall dip in TCP throughput.

Fix this issue by passing the correct argument from
ath12k_dp_rx_ampdu_stop() to ath12k_dp_arch_peer_rx_tid_reo_update()
during an AMPDU stop session. Instead of passing peer->dp_peer->rx_tid,
which is the base address of the array, corresponding to TID 0, pass
the value of &peer->dp_peer->rx_tid[params->tid]. With this, the
different TID numbers are accounted for.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Reshma Immaculate Rajkumar <reshma.rajkumar@oss.qualcomm.com>
Reviewed-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20260227110123.3726354-1-reshma.rajkumar@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 5a82ede65dd3..244d5230a5bd 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -735,6 +735,7 @@ int ath12k_dp_rx_ampdu_stop(struct ath12k *ar,
 	struct ath12k_dp *dp = ath12k_ab_to_dp(ab);
 	struct ath12k_dp_link_peer *peer;
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(params->sta);
+	struct ath12k_dp_rx_tid *rx_tid;
 	struct ath12k_link_sta *arsta;
 	int vdev_id;
 	bool active;
@@ -770,7 +771,8 @@ int ath12k_dp_rx_ampdu_stop(struct ath12k *ar,
 		return 0;
 	}
 
-	ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, peer->dp_peer->rx_tid,
+	rx_tid = &peer->dp_peer->rx_tid[params->tid];
+	ret = ath12k_dp_arch_peer_rx_tid_reo_update(dp, peer, rx_tid,
 						    1, 0, false);
 	spin_unlock_bh(&dp->dp_lock);
 	if (ret) {
-- 
cgit v1.2.3


From d049e56b1739101d1c4d81deedb269c52a8dbba0 Mon Sep 17 00:00:00 2001
From: Yasuaki Torimaru <yasuakitorimaru@gmail.com>
Date: Tue, 24 Mar 2026 19:06:24 +0900
Subject: wifi: wilc1000: fix u8 overflow in SSID scan buffer size calculation

The variable valuesize is declared as u8 but accumulates the total
length of all SSIDs to scan. Each SSID contributes up to 33 bytes
(IEEE80211_MAX_SSID_LEN + 1), and with WILC_MAX_NUM_PROBED_SSID (10)
SSIDs the total can reach 330, which wraps around to 74 when stored
in a u8.

This causes kmalloc to allocate only 75 bytes while the subsequent
memcpy writes up to 331 bytes into the buffer, resulting in a 256-byte
heap buffer overflow.

Widen valuesize from u8 to u32 to accommodate the full range.

Fixes: c5c77ba18ea6 ("staging: wilc1000: Add SDIO/SPI 802.11 driver")
Cc: stable@vger.kernel.org
Signed-off-by: Yasuaki Torimaru <yasuakitorimaru@gmail.com>
Link: https://patch.msgid.link/20260324100624.983458-1-yasuakitorimaru@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/microchip/wilc1000/hif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index f354b11cb919..944b2a812b63 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -163,7 +163,7 @@ int wilc_scan(struct wilc_vif *vif, u8 scan_source,
 	u32 index = 0;
 	u32 i, scan_timeout;
 	u8 *buffer;
-	u8 valuesize = 0;
+	u32 valuesize = 0;
 	u8 *search_ssid_vals = NULL;
 	const u8 ch_list_len = request->n_channels;
 	struct host_if_drv *hif_drv = vif->hif_drv;
-- 
cgit v1.2.3


From 0fd56fad9c56356e7fa7a7c52e7ecbf807a44eb0 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Mon, 23 Mar 2026 16:08:45 +0800
Subject: wifi: wl1251: validate packet IDs before indexing tx_frames

wl1251_tx_packet_cb() uses the firmware completion ID directly to index
the fixed 16-entry wl->tx_frames[] array. The ID is a raw u8 from the
completion block, and the callback does not currently verify that it
fits the array before dereferencing it.

Reject completion IDs that fall outside wl->tx_frames[] and keep the
existing NULL check in the same guard. This keeps the fix local to the
trust boundary and avoids touching the rest of the completion flow.

Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Link: https://patch.msgid.link/20260323080845.40033-1-pengpeng@iscas.ac.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wl1251/tx.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ti/wl1251/tx.c b/drivers/net/wireless/ti/wl1251/tx.c
index 2da8c0d5105b..4489aa77bb0f 100644
--- a/drivers/net/wireless/ti/wl1251/tx.c
+++ b/drivers/net/wireless/ti/wl1251/tx.c
@@ -402,12 +402,14 @@ static void wl1251_tx_packet_cb(struct wl1251 *wl,
 	int hdrlen;
 	u8 *frame;
 
-	skb = wl->tx_frames[result->id];
-	if (skb == NULL) {
-		wl1251_error("SKB for packet %d is NULL", result->id);
+	if (unlikely(result->id >= ARRAY_SIZE(wl->tx_frames) ||
+		     wl->tx_frames[result->id] == NULL)) {
+		wl1251_error("invalid packet id %u", result->id);
 		return;
 	}
 
+	skb = wl->tx_frames[result->id];
+
 	info = IEEE80211_SKB_CB(skb);
 
 	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK) &&
-- 
cgit v1.2.3


From f7e775c4694782844c66da5316fed82881835cf8 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Thu, 19 Mar 2026 17:31:19 +0000
Subject: hwmon: (pmbus/ina233) Fix error handling and sign extension in shunt
 voltage read

ina233_read_word_data() reads MFR_READ_VSHUNT via pmbus_read_word_data()
but has two issues:

1. The return value is not checked for errors before being used in
   arithmetic. A negative error code from a failed I2C transaction is
   passed directly to DIV_ROUND_CLOSEST(), producing garbage data.

2. MFR_READ_VSHUNT is a 16-bit two's complement value. Negative shunt
   voltages (values with bit 15 set) are treated as large positive
   values since pmbus_read_word_data() returns them zero-extended in an
   int. This leads to incorrect scaling in the VIN coefficient
   conversion.

Fix both issues by adding an error check, casting to s16 for proper
sign extension, and clamping the result to a valid non-negative range.
The clamp is necessary because read_word_data callbacks must return
non-negative values on success (negative values indicate errors to the
pmbus core).

Fixes: b64b6cb163f16 ("hwmon: Add driver for TI INA233 Current and Power Monitor")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260319173055.125271-2-sanman.pradhan@hpe.com
[groeck: Fixed clamp to avoid losing the sign bit]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/ina233.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/pmbus/ina233.c b/drivers/hwmon/pmbus/ina233.c
index 2d8b5a5347ed..7aebd854763a 100644
--- a/drivers/hwmon/pmbus/ina233.c
+++ b/drivers/hwmon/pmbus/ina233.c
@@ -72,7 +72,8 @@ static int ina233_read_word_data(struct i2c_client *client, int page,
 
 		/* Adjust returned value to match VIN coefficients */
 		/* VIN: 1.25 mV VSHUNT: 2.5 uV LSB */
-		ret = DIV_ROUND_CLOSEST(ret * 25, 12500);
+		ret = clamp_val(DIV_ROUND_CLOSEST((s16)ret * 25, 12500),
+				S16_MIN, S16_MAX) & 0xffff;
 		break;
 	default:
 		ret = -ENODATA;
-- 
cgit v1.2.3


From 3075a3951f7708da5a8ab47b0b7d068a32f69e58 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Thu, 19 Mar 2026 17:31:29 +0000
Subject: hwmon: (pmbus/isl68137) Add mutex protection for AVS enable sysfs
 attributes

The custom avs0_enable and avs1_enable sysfs attributes access PMBus
registers through the exported API helpers (pmbus_read_byte_data,
pmbus_read_word_data, pmbus_write_word_data, pmbus_update_byte_data)
without holding the PMBus update_lock mutex. These exported helpers do
not acquire the mutex internally, unlike the core's internal callers
which hold the lock before invoking them.

The store callback is especially vulnerable: it performs a multi-step
read-modify-write sequence (read VOUT_COMMAND, write VOUT_COMMAND, then
update OPERATION) where concurrent access from another thread could
interleave and corrupt the register state.

Add pmbus_lock_interruptible()/pmbus_unlock() around both the show and
store callbacks to serialize PMBus register access with the rest of the
driver.

Fixes: 038a9c3d1e424 ("hwmon: (pmbus/isl68137) Add driver for Intersil ISL68137 PWM Controller")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260319173055.125271-3-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/isl68137.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c
index e7dac26b5be6..3e3a887aad05 100644
--- a/drivers/hwmon/pmbus/isl68137.c
+++ b/drivers/hwmon/pmbus/isl68137.c
@@ -96,7 +96,15 @@ static ssize_t isl68137_avs_enable_show_page(struct i2c_client *client,
 					     int page,
 					     char *buf)
 {
-	int val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+	int val;
+
+	val = pmbus_lock_interruptible(client);
+	if (val)
+		return val;
+
+	val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+
+	pmbus_unlock(client);
 
 	if (val < 0)
 		return val;
@@ -118,6 +126,10 @@ static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client,
 
 	op_val = result ? ISL68137_VOUT_AVS : 0;
 
+	rc = pmbus_lock_interruptible(client);
+	if (rc)
+		return rc;
+
 	/*
 	 * Writes to VOUT setpoint over AVSBus will persist after the VRM is
 	 * switched to PMBus control. Switching back to AVSBus control
@@ -129,17 +141,20 @@ static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client,
 		rc = pmbus_read_word_data(client, page, 0xff,
 					  PMBUS_VOUT_COMMAND);
 		if (rc < 0)
-			return rc;
+			goto unlock;
 
 		rc = pmbus_write_word_data(client, page, PMBUS_VOUT_COMMAND,
 					   rc);
 		if (rc < 0)
-			return rc;
+			goto unlock;
 	}
 
 	rc = pmbus_update_byte_data(client, page, PMBUS_OPERATION,
 				    ISL68137_VOUT_AVS, op_val);
 
+unlock:
+	pmbus_unlock(client);
+
 	return (rc < 0) ? rc : count;
 }
 
-- 
cgit v1.2.3


From 0adc752b4f7d82af7bd14f7cad3091b3b5d702ba Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Mon, 23 Mar 2026 00:24:25 +0000
Subject: hwmon: (peci/cputemp) Fix crit_hyst returning delta instead of
 absolute temperature

The hwmon sysfs ABI expects tempN_crit_hyst to report the temperature at
which the critical condition clears, not the hysteresis delta from the
critical limit.

The peci cputemp driver currently returns tjmax - tcontrol for
crit_hyst_type, which is the hysteresis margin rather than the
corresponding absolute temperature.

Return tcontrol directly, and update the documentation accordingly.

Fixes: bf3608f338e9 ("hwmon: peci: Add cputemp driver")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260323002352.93417-2-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/peci-cputemp.rst | 10 ++++++----
 drivers/hwmon/peci/cputemp.c         |  2 +-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/Documentation/hwmon/peci-cputemp.rst b/Documentation/hwmon/peci-cputemp.rst
index fe0422248dc5..266b62a46f49 100644
--- a/Documentation/hwmon/peci-cputemp.rst
+++ b/Documentation/hwmon/peci-cputemp.rst
@@ -51,8 +51,9 @@ temp1_max		Provides thermal control temperature of the CPU package
 temp1_crit		Provides shutdown temperature of the CPU package which
 			is also known as the maximum processor junction
 			temperature, Tjmax or Tprochot.
-temp1_crit_hyst		Provides the hysteresis value from Tcontrol to Tjmax of
-			the CPU package.
+temp1_crit_hyst		Provides the hysteresis temperature of the CPU
+			package. Returns Tcontrol, the temperature at which
+			the critical condition clears.
 
 temp2_label		"DTS"
 temp2_input		Provides current temperature of the CPU package scaled
@@ -62,8 +63,9 @@ temp2_max		Provides thermal control temperature of the CPU package
 temp2_crit		Provides shutdown temperature of the CPU package which
 			is also known as the maximum processor junction
 			temperature, Tjmax or Tprochot.
-temp2_crit_hyst		Provides the hysteresis value from Tcontrol to Tjmax of
-			the CPU package.
+temp2_crit_hyst		Provides the hysteresis temperature of the CPU
+			package. Returns Tcontrol, the temperature at which
+			the critical condition clears.
 
 temp3_label		"Tcontrol"
 temp3_input		Provides current Tcontrol temperature of the CPU
diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c
index b2fc936851e1..badec53ff446 100644
--- a/drivers/hwmon/peci/cputemp.c
+++ b/drivers/hwmon/peci/cputemp.c
@@ -131,7 +131,7 @@ static int get_temp_target(struct peci_cputemp *priv, enum peci_temp_target_type
 		*val = priv->temp.target.tjmax;
 		break;
 	case crit_hyst_type:
-		*val = priv->temp.target.tjmax - priv->temp.target.tcontrol;
+		*val = priv->temp.target.tcontrol;
 		break;
 	default:
 		ret = -EOPNOTSUPP;
-- 
cgit v1.2.3


From b0c9d8ae71509f25690d57f2efddebf7f4b12194 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Mon, 23 Mar 2026 00:24:37 +0000
Subject: hwmon: (peci/cputemp) Fix off-by-one in cputemp_is_visible()

cputemp_is_visible() validates the channel index against
CPUTEMP_CHANNEL_NUMS, but currently uses '>' instead of '>='.
As a result, channel == CPUTEMP_CHANNEL_NUMS is not rejected even though
valid indices are 0 .. CPUTEMP_CHANNEL_NUMS - 1.

Fix the bounds check by using '>=' so invalid channel indices are
rejected before indexing the core bitmap.

Fixes: bf3608f338e9 ("hwmon: peci: Add cputemp driver")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260323002352.93417-3-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/peci/cputemp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/peci/cputemp.c b/drivers/hwmon/peci/cputemp.c
index badec53ff446..457089c561b4 100644
--- a/drivers/hwmon/peci/cputemp.c
+++ b/drivers/hwmon/peci/cputemp.c
@@ -319,7 +319,7 @@ static umode_t cputemp_is_visible(const void *data, enum hwmon_sensor_types type
 {
 	const struct peci_cputemp *priv = data;
 
-	if (channel > CPUTEMP_CHANNEL_NUMS)
+	if (channel >= CPUTEMP_CHANNEL_NUMS)
 		return 0;
 
 	if (channel < channel_core)
-- 
cgit v1.2.3


From cc34d77dd48708d810c12bfd6f5bf03304f6c824 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 24 Mar 2026 01:59:15 +0100
Subject: spi: use generic driver_override infrastructure

When a driver is probed through __driver_attach(), the bus' match()
callback is called without the device lock held, thus accessing the
driver_override field without a lock, which can cause a UAF.

Fix this by using the driver-core driver_override infrastructure taking
care of proper locking internally.

Note that calling match() from __driver_attach() without the device lock
held is intentional. [1]

Also note that we do not enable the driver_override feature of struct
bus_type, as SPI - in contrast to most other buses - passes "" to
sysfs_emit() when the driver_override pointer is NULL. Thus, printing
"\n" instead of "(null)\n".

Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1]
Reported-by: Gui-Dong Han <hanguidong02@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220789
Fixes: 5039563e7c25 ("spi: Add driver_override SPI device attribute")
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patch.msgid.link/20260324005919.2408620-12-dakr@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 19 +++++++------------
 include/linux/spi/spi.h |  5 -----
 2 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 53dee314d76a..4101c2803eb3 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -50,7 +50,6 @@ static void spidev_release(struct device *dev)
 	struct spi_device	*spi = to_spi_device(dev);
 
 	spi_controller_put(spi->controller);
-	kfree(spi->driver_override);
 	free_percpu(spi->pcpu_statistics);
 	kfree(spi);
 }
@@ -73,10 +72,9 @@ static ssize_t driver_override_store(struct device *dev,
 				     struct device_attribute *a,
 				     const char *buf, size_t count)
 {
-	struct spi_device *spi = to_spi_device(dev);
 	int ret;
 
-	ret = driver_set_override(dev, &spi->driver_override, buf, count);
+	ret = __device_set_driver_override(dev, buf, count);
 	if (ret)
 		return ret;
 
@@ -86,13 +84,8 @@ static ssize_t driver_override_store(struct device *dev,
 static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *a, char *buf)
 {
-	const struct spi_device *spi = to_spi_device(dev);
-	ssize_t len;
-
-	device_lock(dev);
-	len = sysfs_emit(buf, "%s\n", spi->driver_override ? : "");
-	device_unlock(dev);
-	return len;
+	guard(spinlock)(&dev->driver_override.lock);
+	return sysfs_emit(buf, "%s\n", dev->driver_override.name ?: "");
 }
 static DEVICE_ATTR_RW(driver_override);
 
@@ -376,10 +369,12 @@ static int spi_match_device(struct device *dev, const struct device_driver *drv)
 {
 	const struct spi_device	*spi = to_spi_device(dev);
 	const struct spi_driver	*sdrv = to_spi_driver(drv);
+	int ret;
 
 	/* Check override first, and if set, only use the named driver */
-	if (spi->driver_override)
-		return strcmp(spi->driver_override, drv->name) == 0;
+	ret = device_match_driver_override(dev, drv);
+	if (ret >= 0)
+		return ret;
 
 	/* Attempt an OF style match */
 	if (of_driver_match_device(dev, drv))
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index af7cfee7b8f6..0dc671c07d3a 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -159,10 +159,6 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  * @modalias: Name of the driver to use with this device, or an alias
  *	for that name.  This appears in the sysfs "modalias" attribute
  *	for driver coldplugging, and in uevents used for hotplugging
- * @driver_override: If the name of a driver is written to this attribute, then
- *	the device will bind to the named driver and only the named driver.
- *	Do not set directly, because core frees it; use driver_set_override() to
- *	set or clear it.
  * @pcpu_statistics: statistics for the spi_device
  * @word_delay: delay to be inserted between consecutive
  *	words of a transfer
@@ -224,7 +220,6 @@ struct spi_device {
 	void			*controller_state;
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
-	const char		*driver_override;
 
 	/* The statistics */
 	struct spi_statistics __percpu	*pcpu_statistics;
-- 
cgit v1.2.3


From 744fabc338e87b95c4d1ff7c95bc8c0f834c6d99 Mon Sep 17 00:00:00 2001
From: Alexey Velichayshiy <a.velichayshiy@ispras.ru>
Date: Sat, 7 Feb 2026 18:03:22 +0300
Subject: wifi: iwlwifi: mvm: fix potential out-of-bounds read in
 iwl_mvm_nd_match_info_handler()

The memcpy function assumes the dynamic array notif->matches is at least
as large as the number of bytes to copy. Otherwise, results->matches may
contain unwanted data. To guarantee safety, extend the validation in one
of the checks to ensure sufficient packet length.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Cc: stable@vger.kernel.org
Fixes: 5ac54afd4d97 ("wifi: iwlwifi: mvm: Add handling for scan offload match info notification")
Signed-off-by: Alexey Velichayshiy <a.velichayshiy@ispras.ru>
Link: https://patch.msgid.link/20260207150335.1013646-1-a.velichayshiy@ispras.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index a19f9d2e9346..9a74f60c9185 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -2807,7 +2807,7 @@ static void iwl_mvm_nd_match_info_handler(struct iwl_mvm *mvm,
 	if (IS_ERR_OR_NULL(vif))
 		return;
 
-	if (len < sizeof(struct iwl_scan_offload_match_info)) {
+	if (len < sizeof(struct iwl_scan_offload_match_info) + matches_len) {
 		IWL_ERR(mvm, "Invalid scan match info notification\n");
 		return;
 	}
-- 
cgit v1.2.3


From 53a7c171e9dd833f0a96b545adcb89bd57387239 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Sun, 8 Mar 2026 12:02:21 +0100
Subject: ovl: fix wrong detection of 32bit inode numbers

The implicit FILEID_INO32_GEN encoder was changed to be explicit,
so we need to fix the detection.

When mounting overlayfs with upperdir and lowerdir on different ext4
filesystems, the expected kmsg log is:

  overlayfs: "xino" feature enabled using 32 upper inode bits.

But instead, since the regressing commit, the kmsg log was:

  overlayfs: "xino" feature enabled using 2 upper inode bits.

Fixes: e21fc2038c1b9 ("exportfs: make ->encode_fh() a mandatory method for NFS export")
Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/overlayfs/util.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 3f1b763a8bb4..2ea769f311c3 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -85,7 +85,10 @@ int ovl_can_decode_fh(struct super_block *sb)
 	if (!exportfs_can_decode_fh(sb->s_export_op))
 		return 0;
 
-	return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN;
+	if (sb->s_export_op->encode_fh == generic_encode_ino32_fh)
+		return FILEID_INO32_GEN;
+
+	return -1;
 }
 
 struct dentry *ovl_indexdir(struct super_block *sb)
-- 
cgit v1.2.3


From 938c418422c4b08523ae39aebbd828428dcfefd2 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Mon, 23 Mar 2026 17:48:57 +0800
Subject: erofs: update the Kconfig description

Refine the description to better highlight its features and use cases.

In addition, add instructions for building it as a module and clarify
the compression option.

Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/Kconfig | 45 ++++++++++++++++++++++++++++++---------------
 1 file changed, 30 insertions(+), 15 deletions(-)

diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index a9f645f57bb2..97c48ebe8458 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -16,22 +16,36 @@ config EROFS_FS
 	select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE
 	select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD
 	help
-	  EROFS (Enhanced Read-Only File System) is a lightweight read-only
-	  file system with modern designs (e.g. no buffer heads, inline
-	  xattrs/data, chunk-based deduplication, multiple devices, etc.) for
-	  scenarios which need high-performance read-only solutions, e.g.
-	  smartphones with Android OS, LiveCDs and high-density hosts with
-	  numerous containers;
-
-	  It also provides transparent compression and deduplication support to
-	  improve storage density and maintain relatively high compression
-	  ratios, and it implements in-place decompression to temporarily reuse
-	  page cache for compressed data using proper strategies, which is
-	  quite useful for ensuring guaranteed end-to-end runtime decompression
+	  EROFS (Enhanced Read-Only File System) is a modern, lightweight,
+	  secure read-only filesystem for various use cases, such as immutable
+	  system images, container images, application sandboxes, and datasets.
+
+	  EROFS uses a flexible, hierarchical on-disk design so that features
+	  can be enabled on demand: the core on-disk format is block-aligned in
+	  order to perform optimally on all kinds of devices, including block
+	  and memory-backed devices; the format is easy to parse and has zero
+	  metadata redundancy, unlike generic filesystems, making it ideal for
+	  filesystem auditing and remote access; inline data, random-access
+	  friendly directory data, inline/shared extended attributes and
+	  chunk-based deduplication ensure space efficiency while maintaining
+	  high performance.
+
+	  Optionally, it supports multiple devices to reference external data,
+	  enabling data sharing for container images.
+
+	  It also has advanced encoded on-disk layouts, particularly for data
+	  compression and fine-grained deduplication. It utilizes fixed-size
+	  output compression to improve storage density while keeping relatively
+	  high compression ratios. Furthermore, it implements in-place
+	  decompression to reuse file pages to keep compressed data temporarily
+	  with proper strategies, which ensures guaranteed end-to-end runtime
 	  performance under extreme memory pressure without extra cost.
 
-	  See the documentation at <file:Documentation/filesystems/erofs.rst>
-	  and the web pages at <https://erofs.docs.kernel.org> for more details.
+	  For more details, see the web pages at <https://erofs.docs.kernel.org>
+	  and the documentation at <file:Documentation/filesystems/erofs.rst>.
+
+	  To compile EROFS filesystem support as a module, choose M here. The
+	  module will be called erofs.
 
 	  If unsure, say N.
 
@@ -105,7 +119,8 @@ config EROFS_FS_ZIP
 	depends on EROFS_FS
 	default y
 	help
-	  Enable transparent compression support for EROFS file systems.
+	  Enable EROFS compression layouts so that filesystems containing
+	  compressed files can be parsed by the kernel.
 
 	  If you don't want to enable compression feature, say N.
 
-- 
cgit v1.2.3


From f6484cadbcaf26b5844b51bd7307a663dda48ef6 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 25 Mar 2026 00:54:59 +0800
Subject: ACPI: EC: clean up handlers on probe failure in acpi_ec_setup()

When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware
platforms, it has already started the EC and installed the address
space handler with the struct acpi_ec pointer as handler context.
However, acpi_ec_setup() propagates the error without any cleanup.

The caller acpi_ec_add() then frees the struct acpi_ec for non-boot
instances, leaving a dangling handler context in ACPICA.

Any subsequent AML evaluation that accesses an EC OpRegion field
dispatches into acpi_ec_space_handler() with the freed pointer,
causing a use-after-free:

 BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289)
 Write of size 8 at addr ffff88800721de38 by task init/1
 Call Trace:
  <TASK>
  mutex_lock (kernel/locking/mutex.c:289)
  acpi_ec_space_handler (drivers/acpi/ec.c:1362)
  acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293)
  acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246)
  acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509)
  acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700)
  acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327)
  acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392)
  </TASK>

 Allocated by task 1:
  acpi_ec_alloc (drivers/acpi/ec.c:1424)
  acpi_ec_add (drivers/acpi/ec.c:1692)

 Freed by task 1:
  kfree (mm/slub.c:6876)
  acpi_ec_add (drivers/acpi/ec.c:1751)

The bug triggers on reduced-hardware EC platforms (ec->gpe < 0)
when the GPIO IRQ provider defers probing. Once the stale handler
exists, any unprivileged sysfs read that causes AML to touch an
EC OpRegion (battery, thermal, backlight) exercises the dangling
pointer.

Fix this by calling ec_remove_handlers() in the error path of
acpi_ec_setup() before clearing first_ec. ec_remove_handlers()
checks each EC_FLAGS_* bit before acting, so it is safe to call
regardless of how far ec_install_handlers() progressed:

  -ENODEV  (handler not installed): only calls acpi_ec_stop()
  -EPROBE_DEFER (handler installed): removes handler, stops EC

Fixes: 03e9a0e05739 ("ACPI: EC: Consolidate event handler installation code")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Link: https://patch.msgid.link/20260324165458.1337233-2-bestswngs@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 5f63ed120a2c..6f0065257a77 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1656,6 +1656,8 @@ static int acpi_ec_setup(struct acpi_ec *ec, struct acpi_device *device, bool ca
 
 	ret = ec_install_handlers(ec, device, call_reg);
 	if (ret) {
+		ec_remove_handlers(ec);
+
 		if (ec == first_ec)
 			first_ec = NULL;
 
-- 
cgit v1.2.3


From 7150850146ebfa4ca998f653f264b8df6f7f85be Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 23 Mar 2026 13:41:18 +0530
Subject: drm/amdgpu: Fix fence put before wait in amdgpu_amdkfd_submit_ib
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

amdgpu_amdkfd_submit_ib() submits a GPU job and gets a fence
from amdgpu_ib_schedule(). This fence is used to wait for job
completion.

Currently, the code drops the fence reference using dma_fence_put()
before calling dma_fence_wait().

If dma_fence_put() releases the last reference, the fence may be
freed before dma_fence_wait() is called. This can lead to a
use-after-free.

Fix this by waiting on the fence first and releasing the reference
only after dma_fence_wait() completes.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:697 amdgpu_amdkfd_submit_ib() warn: passing freed memory 'f' (line 696)

Fixes: 9ae55f030dc5 ("drm/amdgpu: Follow up change to previous drm scheduler change.")
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8b9e5259adc385b61a6590a13b82ae0ac2bd3482)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 40c22438b1d2..4f27c75abedb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -692,9 +692,9 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev,
 		goto err_ib_sched;
 	}
 
-	/* Drop the initial kref_init count (see drm_sched_main as example) */
-	dma_fence_put(f);
 	ret = dma_fence_wait(f, false);
+	/* Drop the returned fence reference after the wait completes */
+	dma_fence_put(f);
 
 err_ib_sched:
 	amdgpu_job_free(job);
-- 
cgit v1.2.3


From 9da4f9964abcaeb6e19797d5e3b10faad338a786 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 20 Mar 2026 12:33:48 -0400
Subject: drm/amd/display: check if ext_caps is valid in BL setup

LVDS connectors don't have extended backlight caps so check
if the pointer is valid before accessing it.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5012
Fixes: 1454642960b0 ("drm/amd: Re-introduce property to control adaptive backlight modulation")
Cc: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 3f797396d7f4eb9bb6eded184bbc6f033628a6f6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index acc3d8dad4a3..2328c1aa0ead 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5423,7 +5423,7 @@ static void setup_backlight_device(struct amdgpu_display_manager *dm,
 	caps = &dm->backlight_caps[aconnector->bl_idx];
 
 	/* Only offer ABM property when non-OLED and user didn't turn off by module parameter */
-	if (!caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0)
+	if (caps->ext_caps && !caps->ext_caps->bits.oled && amdgpu_dm_abm_level < 0)
 		drm_object_attach_property(&aconnector->base.base,
 					   dm->adev->mode_info.abm_level_property,
 					   ABM_SYSFS_CONTROL);
-- 
cgit v1.2.3


From 429aec2bc0ae1e20ce96066d57e9f91f79b660df Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 23 Mar 2026 14:28:57 +0530
Subject: drm/amdkfd: Fix NULL pointer check order in kfd_ioctl_create_process
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In kfd_ioctl_create_process(), the pointer 'p' is used before checking
if it is NULL.

The code accesses p->context_id before validating 'p'. This can lead
to a possible NULL pointer dereference.

Move the NULL check before using 'p' so that the pointer is validated
before access.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_chardev.c:3177 kfd_ioctl_create_process() warn: variable dereferenced before check 'p' (see line 3174)

Fixes: cc6b66d661fd ("amdkfd: introduce new ioctl AMDKFD_IOC_CREATE_PROCESS")
Cc: Zhu Lingshan <lingshan.zhu@amd.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 19d4149b22f57094bfc4b86b742381b3ca394ead)
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 09dabb3b3297..462a32abf720 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -3170,11 +3170,11 @@ static int kfd_ioctl_create_process(struct file *filep, struct kfd_process *p, v
 	struct kfd_process *process;
 	int ret;
 
-	/* Each FD owns only one kfd_process */
-	if (p->context_id != KFD_CONTEXT_ID_PRIMARY)
+	if (!filep->private_data || !p)
 		return -EINVAL;
 
-	if (!filep->private_data || !p)
+	/* Each FD owns only one kfd_process */
+	if (p->context_id != KFD_CONTEXT_ID_PRIMARY)
 		return -EINVAL;
 
 	mutex_lock(&kfd_processes_mutex);
-- 
cgit v1.2.3


From 28922a43fdab715ed771175e8326ad7e13808be3 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Thu, 19 Mar 2026 03:36:50 -0400
Subject: drm/amd/pm: disable OD_FAN_CURVE if temp or pwm range invalid for smu
 v14

Forcibly disable the OD_FAN_CURVE feature when temperature or PWM range is invalid,
otherwise PMFW will reject this configuration on smu v14.0.2/14.0.3.

example:
$ sudo cat /sys/bus/pci/devices/<BDF>/gpu_od/fan_ctrl/fan_curve

OD_FAN_CURVE:
0: 0C 0%
1: 0C 0%
2: 0C 0%
3: 0C 0%
4: 0C 0%
OD_RANGE:
FAN_CURVE(hotspot temp): 0C 0C
FAN_CURVE(fan speed): 0% 0%

$ echo "0 50 40" | sudo tee fan_curve

kernel log:
[  969.761627] amdgpu 0000:03:00.0: amdgpu: Fan curve temp setting(50) must be within [0, 0]!
[ 1010.897800] amdgpu 0000:03:00.0: amdgpu: Fan curve temp setting(50) must be within [0, 0]!

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ab4905d466b60f170d85e19ca2a5d2b159aeb780)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c   | 33 +++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 73762d9b5969..c3ebfac062a7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -56,6 +56,10 @@
 
 #define to_amdgpu_device(x) (container_of(x, struct amdgpu_device, pm.smu_i2c))
 
+static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
+					      int od_feature_bit,
+					      int32_t *min, int32_t *max);
+
 static const struct smu_feature_bits smu_v14_0_2_dpm_features = {
 	.bits = { SMU_FEATURE_BIT_INIT(FEATURE_DPM_GFXCLK_BIT),
 		  SMU_FEATURE_BIT_INIT(FEATURE_DPM_UCLK_BIT),
@@ -922,8 +926,35 @@ static bool smu_v14_0_2_is_od_feature_supported(struct smu_context *smu,
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	const OverDriveLimits_t * const overdrive_upperlimits =
 				&pptable->SkuTable.OverDriveLimitsBasicMax;
+	int32_t min_value, max_value;
+	bool feature_enabled;
 
-	return overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit);
+	switch (od_feature_bit) {
+	case PP_OD_FEATURE_FAN_CURVE_BIT:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		if (feature_enabled) {
+			smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_TEMP,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+
+			smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_FAN_CURVE_PWM,
+							  &min_value, &max_value);
+			if (!min_value && !max_value) {
+				feature_enabled = false;
+				goto out;
+			}
+		}
+		break;
+	default:
+		feature_enabled = !!(overdrive_upperlimits->FeatureCtrlMask & (1U << od_feature_bit));
+		break;
+	}
+
+out:
+	return feature_enabled;
 }
 
 static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu,
-- 
cgit v1.2.3


From 4e9597f22a3cb8600c72fc266eaac57981d834c8 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Mon, 23 Mar 2026 09:58:36 +0530
Subject: drm/amdgpu: Handle GPU page faults correctly on non-4K page systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During a GPU page fault, the driver restores the SVM range and then maps it
into the GPU page tables. The current implementation passes a GPU-page-size
(4K-based) PFN to svm_range_restore_pages() to restore the range.

SVM ranges are tracked using system-page-size PFNs. On systems where the
system page size is larger than 4K, using GPU-page-size PFNs to restore the
range causes two problems:

Range lookup fails:
Because the restore function receives PFNs in GPU (4K) units, the SVM
range lookup does not find the existing range. This will result in a
duplicate SVM range being created.

VMA lookup failure:
The restore function also tries to locate the VMA for the faulting address.
It converts the GPU-page-size PFN into an address using the system page
size, which results in an incorrect address on non-4K page-size systems.
As a result, the VMA lookup fails with the message: "address 0xxxx VMA is
removed".

This patch passes the system-page-size PFN to svm_range_restore_pages() so
that the SVM range is restored correctly on non-4K page systems.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 074fe395fb13247b057f60004c7ebcca9f38ef46)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d54afeb7b2a7..a677e38a493b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2974,14 +2974,14 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 	if (!root)
 		return false;
 
-	addr /= AMDGPU_GPU_PAGE_SIZE;
-
 	if (is_compute_context && !svm_range_restore_pages(adev, pasid, vmid,
-	    node_id, addr, ts, write_fault)) {
+	    node_id, addr >> PAGE_SHIFT, ts, write_fault)) {
 		amdgpu_bo_unref(&root);
 		return true;
 	}
 
+	addr /= AMDGPU_GPU_PAGE_SIZE;
+
 	r = amdgpu_bo_reserve(root, true);
 	if (r)
 		goto error_unref;
-- 
cgit v1.2.3


From 90d239cc53723c1a3f89ce08eac17bf3a9e9f2d4 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 26 Feb 2026 17:12:08 -0500
Subject: drm/amd/display: Fix DCE LVDS handling

LVDS does not use an HPD pin so it may be invalid.  Handle
this case correctly in link encoder creation.

Fixes: 7c8fb3b8e9ba ("drm/amd/display: Add hpd_source index check for DCE60/80/100/110/112/120 link encoders")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/5012
Cc: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Cc: Roman Li <roman.li@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 3b5620f7ee688177fcf65cf61588c5435bce1872)
Cc: stable@vger.kernel.org
---
 .../drm/amd/display/dc/resource/dce100/dce100_resource.c   |  6 ++----
 .../drm/amd/display/dc/resource/dce110/dce110_resource.c   |  5 +++--
 .../drm/amd/display/dc/resource/dce112/dce112_resource.c   |  5 +++--
 .../drm/amd/display/dc/resource/dce120/dce120_resource.c   |  5 +++--
 .../gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c | 14 ++++++--------
 .../gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c |  6 ++----
 6 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
index 92c123aca0c9..fdcf8db6be50 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
@@ -650,9 +650,6 @@ static struct link_encoder *dce100_link_encoder_create(
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
@@ -661,7 +658,8 @@ static struct link_encoder *dce100_link_encoder_create(
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c
index 95852d277c22..ab71f645c90e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce110/dce110_resource.c
@@ -671,7 +671,7 @@ static struct link_encoder *dce110_link_encoder_create(
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
@@ -682,7 +682,8 @@ static struct link_encoder *dce110_link_encoder_create(
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
index 58c6a00397cf..b7051bfd4326 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
@@ -632,7 +632,7 @@ static struct link_encoder *dce112_link_encoder_create(
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
@@ -643,7 +643,8 @@ static struct link_encoder *dce112_link_encoder_create(
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
index 71d76b021375..7ee70f7b3aa7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
@@ -716,7 +716,7 @@ static struct link_encoder *dce120_link_encoder_create(
 		kzalloc_obj(struct dce110_link_encoder);
 	int link_regs_id;
 
-	if (!enc110 || enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
+	if (!enc110)
 		return NULL;
 
 	link_regs_id =
@@ -727,7 +727,8 @@ static struct link_encoder *dce120_link_encoder_create(
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 
 	return &enc110->base;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
index c27645708286..3d52973dd7f2 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
@@ -746,18 +746,16 @@ static struct link_encoder *dce60_link_encoder_create(
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
 	dce60_link_encoder_construct(enc110,
-				      enc_init_data,
-				      &link_enc_feature,
-				      &link_enc_regs[link_regs_id],
-				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				     enc_init_data,
+				     &link_enc_feature,
+				     &link_enc_regs[link_regs_id],
+				     &link_enc_aux_regs[enc_init_data->channel - 1],
+				     enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				     NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
index d66d8ac6d897..89927727a0d9 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
@@ -752,9 +752,6 @@ static struct link_encoder *dce80_link_encoder_create(
 		return &enc110->base;
 	}
 
-	if (enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs))
-		return NULL;
-
 	link_regs_id =
 		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
 
@@ -763,7 +760,8 @@ static struct link_encoder *dce80_link_encoder_create(
 				      &link_enc_feature,
 				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
-				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
+				      enc_init_data->hpd_source >= ARRAY_SIZE(link_enc_hpd_regs) ?
+				      NULL : &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
 }
 
-- 
cgit v1.2.3


From 7dfe9846016b15816e287a4650be1ff1b48c5ab4 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 24 Mar 2026 10:23:46 -0700
Subject: thermal: intel: int340x: soc_slider: Set offset only for balanced
 mode

The slider offset can be set via debugfs for balanced mode. The offset
should be only applicable in balanced mode. For other modes, it should
be 0 when writing to MMIO offset,

Fixes: 8306bcaba06d ("thermal: intel: int340x: Add module parameter to change slider offset")
Tested-by: Erin Park <erin.park@intel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 6.18+ <stable@vger.kernel.org> # 6.18+
[ rjw: Subject and changelog tweaks ]
Link: https://patch.msgid.link/20260324172346.3317145-1-srinivas.pandruvada@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 .../thermal/intel/int340x_thermal/processor_thermal_soc_slider.c  | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c
index 49ff3bae7271..91f291627132 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_soc_slider.c
@@ -176,15 +176,21 @@ static inline void write_soc_slider(struct proc_thermal_device *proc_priv, u64 v
 
 static void set_soc_power_profile(struct proc_thermal_device *proc_priv, int slider)
 {
+	u8 offset;
 	u64 val;
 
 	val = read_soc_slider(proc_priv);
 	val &= ~SLIDER_MASK;
 	val |= FIELD_PREP(SLIDER_MASK, slider) | BIT(SLIDER_ENABLE_BIT);
 
+	if (slider == SOC_SLIDER_VALUE_MINIMUM || slider == SOC_SLIDER_VALUE_MAXIMUM)
+		offset = 0;
+	else
+		offset = slider_offset;
+
 	/* Set the slider offset from module params */
 	val &= ~SLIDER_OFFSET_MASK;
-	val |= FIELD_PREP(SLIDER_OFFSET_MASK, slider_offset);
+	val |= FIELD_PREP(SLIDER_OFFSET_MASK, offset);
 
 	write_soc_slider(proc_priv, val);
 }
-- 
cgit v1.2.3


From a23811061a553c70c42de0e811b2ec15b2d54157 Mon Sep 17 00:00:00 2001
From: "Panagiotis \"Ivory\" Vasilopoulos" <git@n0toose.net>
Date: Wed, 4 Mar 2026 19:13:04 +0100
Subject: landlock: Expand restrict flags example for ABI version 8
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add LANDLOCK_RESTRICT_SELF_TSYNC to the backwards compatibility example
for restrict flags. This introduces completeness, similar to that of
the ruleset attributes example. However, as the new example can impact
enforcement in certain cases, an appropriate warning is also included.

Additionally, I modified the two comments of the example to make them
more consistent with the ruleset attributes example's.

Signed-off-by: Panagiotis "Ivory" Vasilopoulos <git@n0toose.net>
Co-developed-by: Dan Cojocaru <dan@dcdev.ro>
Signed-off-by: Dan Cojocaru <dan@dcdev.ro>
Reviewed-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20260304-landlock-docs-add-tsync-example-v4-1-819a276f05c5@n0toose.net
[mic: Update date, improve comments consistency, fix newline issue]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 Documentation/userspace-api/landlock.rst | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst
index 13134bccdd39..7f86d7a37dc2 100644
--- a/Documentation/userspace-api/landlock.rst
+++ b/Documentation/userspace-api/landlock.rst
@@ -8,7 +8,7 @@ Landlock: unprivileged access control
 =====================================
 
 :Author: Mickaël Salaün
-:Date: January 2026
+:Date: March 2026
 
 The goal of Landlock is to enable restriction of ambient rights (e.g. global
 filesystem or network access) for a set of processes.  Because Landlock
@@ -197,12 +197,27 @@ similar backwards compatibility check is needed for the restrict flags
 
 .. code-block:: c
 
-    __u32 restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON;
-    if (abi < 7) {
-        /* Clear logging flags unsupported before ABI 7. */
+    __u32 restrict_flags =
+        LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON |
+        LANDLOCK_RESTRICT_SELF_TSYNC;
+    switch (abi) {
+    case 1 ... 6:
+        /* Removes logging flags for ABI < 7 */
         restrict_flags &= ~(LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF |
                             LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON |
                             LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF);
+        __attribute__((fallthrough));
+    case 7:
+        /*
+         * Removes multithreaded enforcement flag for ABI < 8
+         *
+         * WARNING: Without this flag, calling landlock_restrict_self(2) is
+         * only equivalent if the calling process is single-threaded. Below
+         * ABI v8 (and as of ABI v8, when not using this flag), a Landlock
+         * policy would only be enforced for the calling thread and its
+         * children (and not for all threads, including parents and siblings).
+         */
+        restrict_flags &= ~LANDLOCK_RESTRICT_SELF_TSYNC;
     }
 
 The next step is to restrict the current thread from gaining more privileges
-- 
cgit v1.2.3


From 57ad0d4a00f5d3e80f33ba2da8d560c73d83dc22 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 6 Mar 2026 13:50:31 +0100
Subject: s390/cpum_sf: Cap sampling rate to prevent lsctl exception

commit fcc43a7e294f ("s390/configs: Set HZ=1000") changed the interrupt
frequency of the system. On machines with heavy load and many perf event
overflows, this might lead to an exception. Dmesg displays these entries:
  [112.242542] cpum_sf: Loading sampling controls failed: op 1 err -22
One line per CPU online.

The root cause is the CPU Measurement sampling facility overflow
adjustment. Whenever an overflow (too much samples per tick) occurs, the
sampling rate is adjusted and increased. This was done without observing
the maximum sampling rate limit. When the current sampling interval is
higher than the maximum sampling rate limit, the lsctl instruction raises
an exception. The error messages is the result of such an exception.
Observe the upper limit when the new sampling rate is recalculated.

Cc: stable@vger.kernel.org
Fixes: 39d4a501a9ef ("s390/cpum_sf: Adjust sampling interval to avoid hitting sample limits")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_sf.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index c92c29de725e..7bfeb5208177 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1168,6 +1168,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 static void hw_perf_event_update(struct perf_event *event, int flush_all)
 {
 	unsigned long long event_overflow, sampl_overflow, num_sdb;
+	struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
 	struct hw_perf_event *hwc = &event->hw;
 	union hws_trailer_header prev, new;
 	struct hws_trailer_entry *te;
@@ -1247,8 +1248,11 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 	 * are dropped.
 	 * Slightly increase the interval to avoid hitting this limit.
 	 */
-	if (event_overflow)
+	if (event_overflow) {
 		SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+		if (SAMPL_RATE(hwc) > cpuhw->qsi.max_sampl_rate)
+			SAMPL_RATE(hwc) = cpuhw->qsi.max_sampl_rate;
+	}
 }
 
 static inline unsigned long aux_sdb_index(struct aux_buffer *aux,
-- 
cgit v1.2.3


From c8d46f17c2fc7d25c18e60c008928aecab26184d Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@linux.ibm.com>
Date: Thu, 19 Mar 2026 09:06:52 +0100
Subject: s390/zcrypt: Fix memory leak with CCA cards used as accelerator

Tests showed that there is a memory leak if CCA cards are used as
accelerator for clear key RSA requests (ME and CRT). With the last
rework for the memory allocation the AP messages are allocated by
ap_init_apmsg() but for some reason on two places (ME and CRT) the
older allocation was still in place. So the first allocation simple
was never freed.

Fixes: 57db62a130ce ("s390/ap/zcrypt: Rework AP message buffer allocation")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-s390/CAHj4cs9H67Uz0iVaRQv447p7JFPRPy3TKAT4=Y6_e=wSHCZM5w@mail.gmail.com/
Reported-by: Nadja Hariz <Nadia.Hariz@ibm.com>
Cc: stable@vger.kernel.org
Reviewed-by: Ingo Franzki <ifranzki@linux.ibm.com>
Reviewed-by: Holger Dengler <dengler@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 drivers/s390/crypto/zcrypt_msgtype6.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index a0dcab5dc4f2..23a32221e41a 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -953,6 +953,10 @@ static atomic_t zcrypt_step = ATOMIC_INIT(0);
 /*
  * The request distributor calls this function if it picked the CEXxC
  * device to handle a modexpo request.
+ * This function assumes that ap_msg has been initialized with
+ * ap_init_apmsg() and thus a valid buffer with the size of
+ * ap_msg->bufsize is available within ap_msg. Also the caller has
+ * to make sure ap_release_apmsg() is always called even on failure.
  * @zq: pointer to zcrypt_queue structure that identifies the
  *	CEXxC device to the request distributor
  * @mex: pointer to the modexpo request buffer
@@ -964,21 +968,17 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq,
 	struct ap_response_type *resp_type = &ap_msg->response;
 	int rc;
 
-	ap_msg->msg = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!ap_msg->msg)
-		return -ENOMEM;
-	ap_msg->bufsize = PAGE_SIZE;
 	ap_msg->receive = zcrypt_msgtype6_receive;
 	ap_msg->psmid = (((unsigned long)current->pid) << 32) +
 		atomic_inc_return(&zcrypt_step);
 	rc = icamex_msg_to_type6mex_msgx(zq, ap_msg, mex);
 	if (rc)
-		goto out_free;
+		goto out;
 	resp_type->type = CEXXC_RESPONSE_TYPE_ICA;
 	init_completion(&resp_type->work);
 	rc = ap_queue_message(zq->queue, ap_msg);
 	if (rc)
-		goto out_free;
+		goto out;
 	rc = wait_for_completion_interruptible(&resp_type->work);
 	if (rc == 0) {
 		rc = ap_msg->rc;
@@ -991,15 +991,17 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq,
 		ap_cancel_message(zq->queue, ap_msg);
 	}
 
-out_free:
-	free_page((unsigned long)ap_msg->msg);
-	ap_msg->msg = NULL;
+out:
 	return rc;
 }
 
 /*
  * The request distributor calls this function if it picked the CEXxC
  * device to handle a modexpo_crt request.
+ * This function assumes that ap_msg has been initialized with
+ * ap_init_apmsg() and thus a valid buffer with the size of
+ * ap_msg->bufsize is available within ap_msg. Also the caller has
+ * to make sure ap_release_apmsg() is always called even on failure.
  * @zq: pointer to zcrypt_queue structure that identifies the
  *	CEXxC device to the request distributor
  * @crt: pointer to the modexpoc_crt request buffer
@@ -1011,21 +1013,17 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq,
 	struct ap_response_type *resp_type = &ap_msg->response;
 	int rc;
 
-	ap_msg->msg = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!ap_msg->msg)
-		return -ENOMEM;
-	ap_msg->bufsize = PAGE_SIZE;
 	ap_msg->receive = zcrypt_msgtype6_receive;
 	ap_msg->psmid = (((unsigned long)current->pid) << 32) +
 		atomic_inc_return(&zcrypt_step);
 	rc = icacrt_msg_to_type6crt_msgx(zq, ap_msg, crt);
 	if (rc)
-		goto out_free;
+		goto out;
 	resp_type->type = CEXXC_RESPONSE_TYPE_ICA;
 	init_completion(&resp_type->work);
 	rc = ap_queue_message(zq->queue, ap_msg);
 	if (rc)
-		goto out_free;
+		goto out;
 	rc = wait_for_completion_interruptible(&resp_type->work);
 	if (rc == 0) {
 		rc = ap_msg->rc;
@@ -1038,9 +1036,7 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq,
 		ap_cancel_message(zq->queue, ap_msg);
 	}
 
-out_free:
-	free_page((unsigned long)ap_msg->msg);
-	ap_msg->msg = NULL;
+out:
 	return rc;
 }
 
-- 
cgit v1.2.3


From 1b164b876c36c3eb5561dd9b37702b04401b0166 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 24 Mar 2026 10:21:25 -1000
Subject: cgroup: Wait for dying tasks to leave on rmdir

a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup") hid PF_EXITING
tasks from cgroup.procs so that systemd doesn't see tasks that have already
been reaped via waitpid(). However, the populated counter (nr_populated_csets)
is only decremented when the task later passes through cgroup_task_dead() in
finish_task_switch(). This means cgroup.procs can appear empty while the
cgroup is still populated, causing rmdir to fail with -EBUSY.

Fix this by making cgroup_rmdir() wait for dying tasks to fully leave. If the
cgroup is populated but all remaining tasks have PF_EXITING set (the task
iterator returns none due to the existing filter), wait for a kick from
cgroup_task_dead() and retry. The wait is brief as tasks are removed from the
cgroup's css_set between PF_EXITING assertion in do_exit() and
cgroup_task_dead() in finish_task_switch().

v2: cgroup_is_populated() true to false transition happens under css_set_lock
    not cgroup_mutex, so retest under css_set_lock before sleeping to avoid
    missed wakeups (Sebastian).

Fixes: a72f73c4dd9b ("cgroup: Don't expose dead tasks in cgroup")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202603222104.2c81684e-lkp@intel.com
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Bert Karwatzki <spasswolf@web.de>
Cc: Michal Koutny <mkoutny@suse.com>
Cc: cgroups@vger.kernel.org
---
 include/linux/cgroup-defs.h |  3 ++
 kernel/cgroup/cgroup.c      | 86 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 86 insertions(+), 3 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index bb92f5c169ca..7f87399938fa 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -609,6 +609,9 @@ struct cgroup {
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
 
+	/* used by cgroup_rmdir() to wait for dying tasks to leave */
+	wait_queue_head_t dying_populated_waitq;
+
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 01fc2a93f3ef..2163054e1aa6 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2126,6 +2126,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 #endif
 
 	init_waitqueue_head(&cgrp->offline_waitq);
+	init_waitqueue_head(&cgrp->dying_populated_waitq);
 	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
 
@@ -6224,6 +6225,76 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	return 0;
 };
 
+/**
+ * cgroup_drain_dying - wait for dying tasks to leave before rmdir
+ * @cgrp: the cgroup being removed
+ *
+ * The PF_EXITING filter in css_task_iter_advance() hides exiting tasks from
+ * cgroup.procs so that userspace (e.g. systemd) doesn't see tasks that have
+ * already been reaped via waitpid(). However, the populated counter
+ * (nr_populated_csets) is only decremented when the task later passes through
+ * cgroup_task_dead() in finish_task_switch(). This creates a window where
+ * cgroup.procs appears empty but cgroup_is_populated() is still true, causing
+ * rmdir to fail with -EBUSY.
+ *
+ * This function bridges that gap. If the cgroup is populated but all remaining
+ * tasks have PF_EXITING set, we wait for cgroup_task_dead() to process them.
+ * Tasks are removed from the cgroup's css_set in cgroup_task_dead() called from
+ * finish_task_switch(). As the window between PF_EXITING and cgroup_task_dead()
+ * is short, the number of PF_EXITING tasks on the list is small and the wait
+ * is brief.
+ *
+ * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we
+ * retry the full check from scratch.
+ *
+ * Must be called with cgroup_mutex held.
+ */
+static int cgroup_drain_dying(struct cgroup *cgrp)
+	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+	DEFINE_WAIT(wait);
+
+	lockdep_assert_held(&cgroup_mutex);
+retry:
+	if (!cgroup_is_populated(cgrp))
+		return 0;
+
+	/* Same iterator as cgroup.threads - if any task is visible, it's busy */
+	css_task_iter_start(&cgrp->self, 0, &it);
+	task = css_task_iter_next(&it);
+	css_task_iter_end(&it);
+
+	if (task)
+		return -EBUSY;
+
+	/*
+	 * All remaining tasks are PF_EXITING and will pass through
+	 * cgroup_task_dead() shortly. Wait for a kick and retry.
+	 *
+	 * cgroup_is_populated() can't transition from false to true while
+	 * we're holding cgroup_mutex, but the true to false transition
+	 * happens under css_set_lock (via cgroup_task_dead()). We must
+	 * retest and prepare_to_wait() under css_set_lock. Otherwise, the
+	 * transition can happen between our first test and
+	 * prepare_to_wait(), and we sleep with no one to wake us.
+	 */
+	spin_lock_irq(&css_set_lock);
+	if (!cgroup_is_populated(cgrp)) {
+		spin_unlock_irq(&css_set_lock);
+		return 0;
+	}
+	prepare_to_wait(&cgrp->dying_populated_waitq, &wait,
+			TASK_UNINTERRUPTIBLE);
+	spin_unlock_irq(&css_set_lock);
+	mutex_unlock(&cgroup_mutex);
+	schedule();
+	finish_wait(&cgrp->dying_populated_waitq, &wait);
+	mutex_lock(&cgroup_mutex);
+	goto retry;
+}
+
 int cgroup_rmdir(struct kernfs_node *kn)
 {
 	struct cgroup *cgrp;
@@ -6233,9 +6304,12 @@ int cgroup_rmdir(struct kernfs_node *kn)
 	if (!cgrp)
 		return 0;
 
-	ret = cgroup_destroy_locked(cgrp);
-	if (!ret)
-		TRACE_CGROUP_PATH(rmdir, cgrp);
+	ret = cgroup_drain_dying(cgrp);
+	if (!ret) {
+		ret = cgroup_destroy_locked(cgrp);
+		if (!ret)
+			TRACE_CGROUP_PATH(rmdir, cgrp);
+	}
 
 	cgroup_kn_unlock(kn);
 	return ret;
@@ -6995,6 +7069,7 @@ void cgroup_task_exit(struct task_struct *tsk)
 
 static void do_cgroup_task_dead(struct task_struct *tsk)
 {
+	struct cgrp_cset_link *link;
 	struct css_set *cset;
 	unsigned long flags;
 
@@ -7008,6 +7083,11 @@ static void do_cgroup_task_dead(struct task_struct *tsk)
 	if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live))
 		list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 
+	/* kick cgroup_drain_dying() waiters, see cgroup_rmdir() */
+	list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
+		if (waitqueue_active(&link->cgrp->dying_populated_waitq))
+			wake_up(&link->cgrp->dying_populated_waitq);
+
 	if (dl_task(tsk))
 		dec_dl_tasks_cs(tsk);
 
-- 
cgit v1.2.3


From 6680c162b4850976ee52b57372eddc4450c1d074 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 24 Mar 2026 10:21:47 -1000
Subject: selftests/cgroup: Don't require synchronous populated update on task
 exit

test_cgcore_populated (test_core) and test_cgkill_{simple,tree,forkbomb}
(test_kill) check cgroup.events "populated 0" immediately after reaping
child tasks with waitpid(). This used to work because cgroup_task_exit() in
do_exit() unlinked tasks from css_sets before exit_notify() woke up
waitpid().

d245698d727a ("cgroup: Defer task cgroup unlink until after the task is done
switching out") moved the unlink to cgroup_task_dead() in
finish_task_switch(), which runs after exit_notify(). The populated counter
is now decremented after the parent's waitpid() can return, so there is no
longer a synchronous ordering guarantee. On PREEMPT_RT, where
cgroup_task_dead() is further deferred through lazy irq_work, the race
window is even larger.

The synchronous populated transition was never part of the cgroup interface
contract - it was an implementation artifact. Use cg_read_strcmp_wait() which
retries for up to 1 second, matching what these tests actually need to
verify: that the cgroup eventually becomes unpopulated after all tasks exit.

Fixes: d245698d727a ("cgroup: Defer task cgroup unlink until after the task is done switching out")
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Christian Brauner <brauner@kernel.org>
Cc: cgroups@vger.kernel.org
---
 tools/testing/selftests/cgroup/lib/cgroup_util.c         | 15 +++++++++++++++
 tools/testing/selftests/cgroup/lib/include/cgroup_util.h |  2 ++
 tools/testing/selftests/cgroup/test_core.c               |  3 ++-
 tools/testing/selftests/cgroup/test_kill.c               |  7 ++++---
 4 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index ce6c2642fd9b..6a7295347e90 100644
--- a/tools/testing/selftests/cgroup/lib/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -123,6 +123,21 @@ int cg_read_strcmp(const char *cgroup, const char *control,
 	return ret;
 }
 
+int cg_read_strcmp_wait(const char *cgroup, const char *control,
+			    const char *expected)
+{
+	int i, ret;
+
+	for (i = 0; i < 100; i++) {
+		ret = cg_read_strcmp(cgroup, control, expected);
+		if (!ret)
+			return ret;
+		usleep(10000);
+	}
+
+	return ret;
+}
+
 int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
 {
 	char buf[PAGE_SIZE];
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index 77f386dab5e8..567b1082974c 100644
--- a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -61,6 +61,8 @@ extern int cg_read(const char *cgroup, const char *control,
 		   char *buf, size_t len);
 extern int cg_read_strcmp(const char *cgroup, const char *control,
 			  const char *expected);
+extern int cg_read_strcmp_wait(const char *cgroup, const char *control,
+				   const char *expected);
 extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 102262555a59..7b83c7e7c9d4 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -233,7 +233,8 @@ static int test_cgcore_populated(const char *root)
 	if (err)
 		goto cleanup;
 
-	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+	if (cg_read_strcmp_wait(cg_test_d, "cgroup.events",
+				   "populated 0\n"))
 		goto cleanup;
 
 	/* Remove cgroup. */
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index c8c9d306925b..f6cd23a8ecc7 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -86,7 +86,7 @@ cleanup:
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)
@@ -190,7 +190,8 @@ cleanup:
 		wait_for_pid(pids[i]);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup[0], "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup[0], "cgroup.events",
+				   "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	for (i = 9; i >= 0 && cgroup[i]; i--) {
@@ -251,7 +252,7 @@ cleanup:
 		wait_for_pid(pid);
 
 	if (ret == KSFT_PASS &&
-	    cg_read_strcmp(cgroup, "cgroup.events", "populated 0\n"))
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
 		ret = KSFT_FAIL;
 
 	if (cgroup)
-- 
cgit v1.2.3


From 5d16467ae56343b9205caedf85e3a131e0914ad8 Mon Sep 17 00:00:00 2001
From: Zhan Xusheng <zhanxusheng1024@gmail.com>
Date: Mon, 23 Mar 2026 14:11:30 +0800
Subject: alarmtimer: Fix argument order in alarm_timer_forward()

alarm_timer_forward() passes arguments to alarm_forward() in the wrong
order:

  alarm_forward(alarm, timr->it_interval, now);

However, alarm_forward() is defined as:

  u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval);

and uses the second argument as the current time:

  delta = ktime_sub(now, alarm->node.expires);

Passing the interval as "now" results in incorrect delta computation,
which can lead to missed expirations or incorrect overrun accounting.

This issue has been present since the introduction of
alarm_timer_forward().

Fix this by swapping the arguments.

Fixes: e7561f1633ac ("alarmtimer: Implement forward callback")
Signed-off-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260323061130.29991-1-zhanxusheng@xiaomi.com
---
 kernel/time/alarmtimer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 069d93bfb0c7..b64db405ba5c 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -540,7 +540,7 @@ static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return alarm_forward(alarm, timr->it_interval, now);
+	return alarm_forward(alarm, now, timr->it_interval);
 }
 
 /**
-- 
cgit v1.2.3


From 2f0407ed923b7eb363424033fc12fe253da139c4 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 24 Mar 2026 23:54:07 +0800
Subject: erofs: fix .fadvise() for page cache sharing

Currently, .fadvise() doesn't work well if page cache sharing is on
since shared inodes belong to a pseudo fs generated with init_pseudo(),
and sb->s_bdi is the default one &noop_backing_dev_info.

Then, generic_fadvise() will just behave as a no-op if sb->s_bdi is
&noop_backing_dev_info, but as the bdev fs (the bdev fs changes
inode_to_bdi() instead), it's actually NOT a pure memfs.

Let's generate a real bdi for erofs_ishare_mnt instead.

Fixes: d86d7817c042 ("erofs: implement .fadvise for page cache share")
Reviewed-by: Hongbo Li <lihongbo22@huawei.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/ishare.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c
index 829d50d5c717..ec433bacc592 100644
--- a/fs/erofs/ishare.c
+++ b/fs/erofs/ishare.c
@@ -200,8 +200,19 @@ struct inode *erofs_real_inode(struct inode *inode, bool *need_iput)
 
 int __init erofs_init_ishare(void)
 {
-	erofs_ishare_mnt = kern_mount(&erofs_anon_fs_type);
-	return PTR_ERR_OR_ZERO(erofs_ishare_mnt);
+	struct vfsmount *mnt;
+	int ret;
+
+	mnt = kern_mount(&erofs_anon_fs_type);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+	/* generic_fadvise() doesn't work if s_bdi == &noop_backing_dev_info */
+	ret = super_setup_bdi(mnt->mnt_sb);
+	if (ret)
+		kern_unmount(mnt);
+	else
+		erofs_ishare_mnt = mnt;
+	return ret;
 }
 
 void erofs_exit_ishare(void)
-- 
cgit v1.2.3


From ba8bda9a0896746053aa97ac6c3e08168729172c Mon Sep 17 00:00:00 2001
From: xietangxin <xietangxin@yeah.net>
Date: Thu, 12 Mar 2026 10:54:06 +0800
Subject: virtio_net: Fix UAF on dst_ops when IFF_XMIT_DST_RELEASE is cleared
 and napi_tx is false

A UAF issue occurs when the virtio_net driver is configured with napi_tx=N
and the device's IFF_XMIT_DST_RELEASE flag is cleared
(e.g., during the configuration of tc route filter rules).

When IFF_XMIT_DST_RELEASE is removed from the net_device, the network stack
expects the driver to hold the reference to skb->dst until the packet
is fully transmitted and freed. In virtio_net with napi_tx=N,
skbs may remain in the virtio transmit ring for an extended period.

If the network namespace is destroyed while these skbs are still pending,
the corresponding dst_ops structure has freed. When a subsequent packet
is transmitted, free_old_xmit() is triggered to clean up old skbs.
It then calls dst_release() on the skb associated with the stale dst_entry.
Since the dst_ops (referenced by the dst_entry) has already been freed,
a UAF kernel paging request occurs.

fix it by adds skb_dst_drop(skb) in start_xmit to explicitly release
the dst reference before the skb is queued in virtio_net.

Call Trace:
 Unable to handle kernel paging request at virtual address ffff80007e150000
 CPU: 2 UID: 0 PID: 6236 Comm: ping Kdump: loaded Not tainted 7.0.0-rc1+ #6 PREEMPT
  ...
  percpu_counter_add_batch+0x3c/0x158 lib/percpu_counter.c:98 (P)
  dst_release+0xe0/0x110  net/core/dst.c:177
  skb_release_head_state+0xe8/0x108 net/core/skbuff.c:1177
  sk_skb_reason_drop+0x54/0x2d8 net/core/skbuff.c:1255
  dev_kfree_skb_any_reason+0x64/0x78 net/core/dev.c:3469
  napi_consume_skb+0x1c4/0x3a0 net/core/skbuff.c:1527
  __free_old_xmit+0x164/0x230  drivers/net/virtio_net.c:611 [virtio_net]
  free_old_xmit drivers/net/virtio_net.c:1081 [virtio_net]
  start_xmit+0x7c/0x530 drivers/net/virtio_net.c:3329 [virtio_net]
  ...

Reproduction Steps:
NETDEV="enp3s0"

config_qdisc_route_filter() {
    tc qdisc del dev $NETDEV root
    tc qdisc add dev $NETDEV root handle 1: prio
    tc filter add dev $NETDEV parent 1:0 \
	protocol ip prio 100 route to 100 flowid 1:1
    ip route add 192.168.1.100/32 dev $NETDEV realm 100
}

test_ns() {
    ip netns add testns
    ip link set $NETDEV netns testns
    ip netns exec testns ifconfig $NETDEV  10.0.32.46/24
    ip netns exec testns ping -c 1 10.0.32.1
    ip netns del testns
}

config_qdisc_route_filter

test_ns
sleep 2
test_ns

Fixes: f2fc6a54585a ("[NETNS][IPV6] route6 - move ip6_dst_ops inside the network namespace")
Cc: stable@vger.kernel.org
Signed-off-by: xietangxin <xietangxin@yeah.net>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Fixes: 0287587884b1 ("net: better IFF_XMIT_DST_RELEASE support")
Link: https://patch.msgid.link/20260312025406.15641-1-xietangxin@yeah.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7106333ef904..ab2108ee206a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3355,6 +3355,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Don't wait up for transmitted skbs to be freed. */
 	if (!use_napi) {
 		skb_orphan(skb);
+		skb_dst_drop(skb);
 		nf_reset_ct(skb);
 	}
 
-- 
cgit v1.2.3


From 71399707876b93240f236f48b8062f3423a5fe97 Mon Sep 17 00:00:00 2001
From: Thangaraj Samynathan <thangaraj.s@microchip.com>
Date: Mon, 23 Mar 2026 12:23:45 +0530
Subject: net: lan743x: fix duplex configuration in mac_link_up

The driver does not explicitly configure the MAC duplex mode when
bringing the link up. As a result, the MAC may retain a stale duplex
setting from a previous link state, leading to duplex mismatches with
the link partner and degraded network performance.

Update lan743x_phylink_mac_link_up() to set or clear the MAC_CR_DPX_
bit according to the negotiated duplex mode.

This ensures the MAC configuration is consistent with the phylink
resolved state.

Fixes: a5f199a8d8a03 ("net: lan743x: Migrate phylib to phylink")
Signed-off-by: Thangaraj Samynathan <thangaraj.s@microchip.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20260323065345.144915-1-thangaraj.s@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a3845edf0e48..f0b5dd752f08 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -3053,6 +3053,11 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config,
 	else if (speed == SPEED_100)
 		mac_cr |= MAC_CR_CFG_L_;
 
+	if (duplex == DUPLEX_FULL)
+		mac_cr |= MAC_CR_DPX_;
+	else
+		mac_cr &= ~MAC_CR_DPX_;
+
 	lan743x_csr_write(adapter, MAC_CR, mac_cr);
 
 	lan743x_ptp_update_latency(adapter, speed);
-- 
cgit v1.2.3


From 09474055f2619be9445ba4245e4013741ed01a5e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 23 Mar 2026 16:19:43 +0100
Subject: rtnetlink: fix leak of SRCU struct in rtnl_link_register

Commit 6b57ff21a310 ("rtnetlink: Protect link_ops by mutex.") swapped
the EEXIST check with the init_srcu_struct, but didn't add cleanup of
the SRCU struct we just allocated in case of error.

Fixes: 6b57ff21a310 ("rtnetlink: Protect link_ops by mutex.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/e77fe499f9a58c547b33b5212b3596dad417cec6.1774025341.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4a2278614250..fae8034efbff 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -629,6 +629,9 @@ int rtnl_link_register(struct rtnl_link_ops *ops)
 unlock:
 	mutex_unlock(&link_ops_mutex);
 
+	if (err)
+		cleanup_srcu_struct(&ops->srcu);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(rtnl_link_register);
-- 
cgit v1.2.3


From 815980fe6dbb01ad4007e8b260a45617f598b76d Mon Sep 17 00:00:00 2001
From: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Date: Mon, 23 Mar 2026 18:49:20 +0100
Subject: net_sched: codel: fix stale state for empty flows in fq_codel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When codel_dequeue() finds an empty queue, it resets vars->dropping
but does not reset vars->first_above_time.  The reference CoDel
algorithm (Nichols & Jacobson, ACM Queue 2012) resets both:

  dodeque_result codel_queue_t::dodeque(time_t now) {
      ...
      if (r.p == NULL) {
          first_above_time = 0;   // <-- Linux omits this
      }
      ...
  }

Note that codel_should_drop() does reset first_above_time when called
with a NULL skb, but codel_dequeue() returns early before ever calling
codel_should_drop() in the empty-queue case.  The post-drop code paths
do reach codel_should_drop(NULL) and correctly reset the timer, so a
dropped packet breaks the cycle -- but the next delivered packet
re-arms first_above_time and the cycle repeats.

For sparse flows such as ICMP ping (one packet every 200ms-1s), the
first packet arms first_above_time, the flow goes empty, and the
second packet arrives after the interval has elapsed and gets dropped.
The pattern repeats, producing sustained loss on flows that are not
actually congested.

Test: veth pair, fq_codel, BQL disabled, 30000 iptables rules in the
consumer namespace (NAPI-64 cycle ~14ms, well above fq_codel's 5ms
target), ping at 5 pps under UDP flood:

  Before fix:  26% ping packet loss
  After fix:    0% ping packet loss

Fix by resetting first_above_time to zero in the empty-queue path
of codel_dequeue(), matching the reference algorithm.

Fixes: 76e3cc126bb2 ("codel: Controlled Delay AQM")
Fixes: d068ca2ae2e6 ("codel: split into multiple files")
Co-developed-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Reported-by: Chris Arges <carges@cloudflare.com>
Tested-by: Jonas Köppeler <j.koeppeler@tu-berlin.de>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/all/20260318134826.1281205-7-hawk@kernel.org/
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260323174920.253526-1-hawk@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/codel_impl.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h
index 78a27ac73070..b2c359c6dd1b 100644
--- a/include/net/codel_impl.h
+++ b/include/net/codel_impl.h
@@ -158,6 +158,7 @@ static struct sk_buff *codel_dequeue(void *ctx,
 	bool drop;
 
 	if (!skb) {
+		vars->first_above_time = 0;
 		vars->dropping = false;
 		return skb;
 	}
-- 
cgit v1.2.3


From c4ea7d8907cf72b259bf70bd8c2e791e1c4ff70f Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Tue, 24 Mar 2026 00:57:30 +0800
Subject: net: mana: fix use-after-free in add_adev() error path

If auxiliary_device_add() fails, add_adev() jumps to add_fail and calls
auxiliary_device_uninit(adev).

The auxiliary device has its release callback set to adev_release(),
which frees the containing struct mana_adev. Since adev is embedded in
struct mana_adev, the subsequent fall-through to init_fail and access
to adev->id may result in a use-after-free.

Fix this by saving the allocated auxiliary device id in a local
variable before calling auxiliary_device_add(), and use that saved id
in the cleanup path after auxiliary_device_uninit().

Fixes: a69839d4327d ("net: mana: Add support for auxiliary device")
Cc: stable@vger.kernel.org
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Link: https://patch.msgid.link/20260323165730.945365-1-lgs201920130244@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9017e806ecda..dca62fb9a3a9 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -3425,6 +3425,7 @@ static int add_adev(struct gdma_dev *gd, const char *name)
 	struct auxiliary_device *adev;
 	struct mana_adev *madev;
 	int ret;
+	int id;
 
 	madev = kzalloc_obj(*madev);
 	if (!madev)
@@ -3434,7 +3435,8 @@ static int add_adev(struct gdma_dev *gd, const char *name)
 	ret = mana_adev_idx_alloc();
 	if (ret < 0)
 		goto idx_fail;
-	adev->id = ret;
+	id = ret;
+	adev->id = id;
 
 	adev->name = name;
 	adev->dev.parent = gd->gdma_context->dev;
@@ -3460,7 +3462,7 @@ add_fail:
 	auxiliary_device_uninit(adev);
 
 init_fail:
-	mana_adev_idx_free(adev->id);
+	mana_adev_idx_free(id);
 
 idx_fail:
 	kfree(madev);
-- 
cgit v1.2.3


From 2cdaff22ed26f1e619aa2b43f27bb84f2c6ef8f8 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Wed, 25 Mar 2026 02:55:48 +0100
Subject: dma-mapping: add missing `inline` for `dma_free_attrs`

Under an UML build for an upcoming series [1], I got `-Wstatic-in-inline`
for `dma_free_attrs`:

      BINDGEN rust/bindings/bindings_generated.rs - due to target missing
    In file included from rust/helpers/helpers.c:59:
    rust/helpers/dma.c:17:2: warning: static function 'dma_free_attrs' is used in an inline function with external linkage [-Wstatic-in-inline]
       17 |         dma_free_attrs(dev, size, cpu_addr, dma_handle, attrs);
          |         ^
    rust/helpers/dma.c:12:1: note: use 'static' to give inline function 'rust_helper_dma_free_attrs' internal linkage
       12 | __rust_helper void rust_helper_dma_free_attrs(struct device *dev, size_t size,
          | ^
          | static

The issue is that `dma_free_attrs` was not marked `inline` when it was
introduced alongside the rest of the stubs.

Thus mark it.

Fixes: ed6ccf10f24b ("dma-mapping: properly stub out the DMA API for !CONFIG_HAS_DMA")
Closes: https://lore.kernel.org/rust-for-linux/20260322194616.89847-1-ojeda@kernel.org/ [1]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260325015548.70912-1-ojeda@kernel.org
---
 include/linux/dma-mapping.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 482b919f040f..99ef042ecdb4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -255,8 +255,8 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 {
 	return NULL;
 }
-static void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_handle, unsigned long attrs)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
 {
 }
 static inline void *dmam_alloc_attrs(struct device *dev, size_t size,
-- 
cgit v1.2.3


From bfe9e314d7574d1c5c851972e7aee342733819d2 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Wed, 18 Mar 2026 10:02:09 +0000
Subject: drm/xe: always keep track of remap prev/next

During 3D workload, user is reporting hitting:

[  413.361679] WARNING: drivers/gpu/drm/xe/xe_vm.c:1217 at vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe], CPU#7: vkd3d_queue/9925
[  413.361944] CPU: 7 UID: 1000 PID: 9925 Comm: vkd3d_queue Kdump: loaded Not tainted 7.0.0-070000rc3-generic #202603090038 PREEMPT(lazy)
[  413.361949] RIP: 0010:vm_bind_ioctl_ops_unwind+0x1e2/0x2e0 [xe]
[  413.362074] RSP: 0018:ffffd4c25c3df930 EFLAGS: 00010282
[  413.362077] RAX: 0000000000000000 RBX: ffff8f3ee817ed10 RCX: 0000000000000000
[  413.362078] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[  413.362079] RBP: ffffd4c25c3df980 R08: 0000000000000000 R09: 0000000000000000
[  413.362081] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f41fbf99380
[  413.362082] R13: ffff8f3ee817e968 R14: 00000000ffffffef R15: ffff8f43d00bd380
[  413.362083] FS:  00000001040ff6c0(0000) GS:ffff8f4696d89000(0000) knlGS:00000000330b0000
[  413.362085] CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
[  413.362086] CR2: 00007ddfc4747000 CR3: 00000002e6262005 CR4: 0000000000f72ef0
[  413.362088] PKRU: 55555554
[  413.362089] Call Trace:
[  413.362092]  <TASK>
[  413.362096]  xe_vm_bind_ioctl+0xa9a/0xc60 [xe]

Which seems to hint that the vma we are re-inserting for the ops unwind
is either invalid or overlapping with something already inserted in the
vm. It shouldn't be invalid since this is a re-insertion, so must have
worked before. Leaving the likely culprit as something already placed
where we want to insert the vma.

Following from that, for the case where we do something like a rebind in
the middle of a vma, and one or both mapped ends are already compatible,
we skip doing the rebind of those vma and set next/prev to NULL. As well
as then adjust the original unmap va range, to avoid unmapping the ends.
However, if we trigger the unwind path, we end up with three va, with
the two ends never being removed and the original va range in the middle
still being the shrunken size.

If this occurs, one failure mode is when another unwind op needs to
interact with that range, which can happen with a vector of binds. For
example, if we need to re-insert something in place of the original va.
In this case the va is still the shrunken version, so when removing it
and then doing a re-insert it can overlap with the ends, which were
never removed, triggering a warning like above, plus leaving the vm in a
bad state.

With that, we need two things here:

 1) Stop nuking the prev/next tracking for the skip cases. Instead
    relying on checking for skip prev/next, where needed. That way on the
    unwind path, we now correctly remove both ends.

 2) Undo the unmap va shrinkage, on the unwind path. With the two ends
    now removed the unmap va should expand back to the original size again,
    before re-insertion.

v2:
  - Update the explanation in the commit message, based on an actual IGT of
    triggering this issue, rather than conjecture.
  - Also undo the unmap shrinkage, for the skip case. With the two ends
    now removed, the original unmap va range should expand back to the
    original range.
v3:
  - Track the old start/range separately. vma_size/start() uses the va
    info directly.

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/7602
Fixes: 8f33b4f054fc ("drm/xe: Avoid doing rebinds")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260318100208.78097-2-matthew.auld@intel.com
(cherry picked from commit aec6969f75afbf4e01fd5fb5850ed3e9c27043ac)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c       | 12 ++++++------
 drivers/gpu/drm/xe/xe_vm.c       | 22 ++++++++++++++++++----
 drivers/gpu/drm/xe/xe_vm_types.h |  4 ++++
 3 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 2d9ce2c4cb4f..713a303c9053 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1442,9 +1442,9 @@ static int op_check_svm_userptr(struct xe_vm *vm, struct xe_vma_op *op,
 		err = vma_check_userptr(vm, op->map.vma, pt_update);
 		break;
 	case DRM_GPUVA_OP_REMAP:
-		if (op->remap.prev)
+		if (op->remap.prev && !op->remap.skip_prev)
 			err = vma_check_userptr(vm, op->remap.prev, pt_update);
-		if (!err && op->remap.next)
+		if (!err && op->remap.next && !op->remap.skip_next)
 			err = vma_check_userptr(vm, op->remap.next, pt_update);
 		break;
 	case DRM_GPUVA_OP_UNMAP:
@@ -2198,12 +2198,12 @@ static int op_prepare(struct xe_vm *vm,
 
 		err = unbind_op_prepare(tile, pt_update_ops, old);
 
-		if (!err && op->remap.prev) {
+		if (!err && op->remap.prev && !op->remap.skip_prev) {
 			err = bind_op_prepare(vm, tile, pt_update_ops,
 					      op->remap.prev, false);
 			pt_update_ops->wait_vm_bookkeep = true;
 		}
-		if (!err && op->remap.next) {
+		if (!err && op->remap.next && !op->remap.skip_next) {
 			err = bind_op_prepare(vm, tile, pt_update_ops,
 					      op->remap.next, false);
 			pt_update_ops->wait_vm_bookkeep = true;
@@ -2428,10 +2428,10 @@ static void op_commit(struct xe_vm *vm,
 
 		unbind_op_commit(vm, tile, pt_update_ops, old, fence, fence2);
 
-		if (op->remap.prev)
+		if (op->remap.prev && !op->remap.skip_prev)
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.prev,
 				       fence, fence2, false);
-		if (op->remap.next)
+		if (op->remap.next && !op->remap.skip_next)
 			bind_op_commit(vm, tile, pt_update_ops, op->remap.next,
 				       fence, fence2, false);
 		break;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index a82e3a4fb389..ffdbab106a58 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2554,7 +2554,6 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 			if (!err && op->remap.skip_prev) {
 				op->remap.prev->tile_present =
 					tile_present;
-				op->remap.prev = NULL;
 			}
 		}
 		if (op->remap.next) {
@@ -2564,11 +2563,13 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 			if (!err && op->remap.skip_next) {
 				op->remap.next->tile_present =
 					tile_present;
-				op->remap.next = NULL;
 			}
 		}
 
-		/* Adjust for partial unbind after removing VMA from VM */
+		/*
+		 * Adjust for partial unbind after removing VMA from VM. In case
+		 * of unwind we might need to undo this later.
+		 */
 		if (!err) {
 			op->base.remap.unmap->va->va.addr = op->remap.start;
 			op->base.remap.unmap->va->va.range = op->remap.range;
@@ -2687,6 +2688,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			op->remap.start = xe_vma_start(old);
 			op->remap.range = xe_vma_size(old);
+			op->remap.old_start = op->remap.start;
+			op->remap.old_range = op->remap.range;
 
 			flags |= op->base.remap.unmap->va->flags & XE_VMA_CREATE_MASK;
 			if (op->base.remap.prev) {
@@ -2835,8 +2838,19 @@ static void xe_vma_op_unwind(struct xe_vm *vm, struct xe_vma_op *op,
 			xe_svm_notifier_lock(vm);
 			vma->gpuva.flags &= ~XE_VMA_DESTROYED;
 			xe_svm_notifier_unlock(vm);
-			if (post_commit)
+			if (post_commit) {
+				/*
+				 * Restore the old va range, in case of the
+				 * prev/next skip optimisation. Otherwise what
+				 * we re-insert here could be smaller than the
+				 * original range.
+				 */
+				op->base.remap.unmap->va->va.addr =
+					op->remap.old_start;
+				op->base.remap.unmap->va->va.range =
+					op->remap.old_range;
 				xe_vm_insert_vma(vm, vma);
+			}
 		}
 		break;
 	}
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 437f64202f3b..e2946e311d7a 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -373,6 +373,10 @@ struct xe_vma_op_remap {
 	u64 start;
 	/** @range: range of the VMA unmap */
 	u64 range;
+	/** @old_start: Original start of the VMA we unmap */
+	u64 old_start;
+	/** @old_range: Original range of the VMA we unmap */
+	u64 old_range;
 	/** @skip_prev: skip prev rebind */
 	bool skip_prev;
 	/** @skip_next: skip next rebind */
-- 
cgit v1.2.3


From c991ca3238410b611a2ce59adeca9b55850aff69 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Wed, 25 Mar 2026 17:20:17 +0800
Subject: ASoC: SDCA: remove the max count of initialization table

The number of the initialization table may exceed 2048.
Therefore, this patch removes the limitation and allows the driver to
allocate memory dynamically based on the size of the initialization table.

Signed-off-by: Shuming Fan <shumingf@realtek.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260325092017.3221640-1-shumingf@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sdca_function.h   | 5 -----
 sound/soc/sdca/sdca_functions.c | 3 ---
 2 files changed, 8 deletions(-)

diff --git a/include/sound/sdca_function.h b/include/sound/sdca_function.h
index 79bd5a7a0f88..0e871c786513 100644
--- a/include/sound/sdca_function.h
+++ b/include/sound/sdca_function.h
@@ -26,11 +26,6 @@ struct sdca_function_desc;
  */
 #define SDCA_MAX_ENTITY_COUNT 128
 
-/*
- * Sanity check on number of initialization writes, can be expanded if needed.
- */
-#define SDCA_MAX_INIT_COUNT 2048
-
 /*
  * The Cluster IDs are 16-bit, so a maximum of 65535 Clusters per
  * function can be represented, however limit this to a slightly
diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c
index e0ed593697ba..d27ffb25ad97 100644
--- a/sound/soc/sdca/sdca_functions.c
+++ b/sound/soc/sdca/sdca_functions.c
@@ -216,9 +216,6 @@ static int find_sdca_init_table(struct device *dev,
 	} else if (num_init_writes % sizeof(*raw) != 0) {
 		dev_err(dev, "%pfwP: init table size invalid\n", function_node);
 		return -EINVAL;
-	} else if ((num_init_writes / sizeof(*raw)) > SDCA_MAX_INIT_COUNT) {
-		dev_err(dev, "%pfwP: maximum init table size exceeded\n", function_node);
-		return -EINVAL;
 	}
 
 	raw = kzalloc(num_init_writes, GFP_KERNEL);
-- 
cgit v1.2.3


From bf08749a6abb6d1959bfdc0edc32c640df407558 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Wed, 25 Mar 2026 05:13:06 +0000
Subject: hwmon: (adm1177) fix sysfs ABI violation and current unit conversion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The adm1177 driver exposes the current alert threshold through
hwmon_curr_max_alarm. This violates the hwmon sysfs ABI, where
*_alarm attributes are read-only status flags and writable thresholds
must use currN_max.

The driver also stores the threshold internally in microamps, while
currN_max is defined in milliamps. Convert the threshold accordingly
on both the read and write paths.

Widen the cached threshold and related calculations to 64 bits so
that small shunt resistor values do not cause truncation or overflow.
Also use 64-bit arithmetic for the mA/uA conversions, clamp writes
to the range the hardware can represent, and propagate failures from
adm1177_write_alert_thr() instead of silently ignoring them.

Update the hwmon documentation to reflect the attribute rename and
the correct units returned by the driver.

Fixes: 09b08ac9e8d5 ("hwmon: (adm1177) Add ADM1177 Hot Swap Controller and Digital Power Monitor driver")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Acked-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20260325051246.28262-1-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/adm1177.rst |  8 +++---
 drivers/hwmon/adm1177.c         | 54 +++++++++++++++++++++++------------------
 2 files changed, 35 insertions(+), 27 deletions(-)

diff --git a/Documentation/hwmon/adm1177.rst b/Documentation/hwmon/adm1177.rst
index 1c85a2af92bf..375f6d6e03a7 100644
--- a/Documentation/hwmon/adm1177.rst
+++ b/Documentation/hwmon/adm1177.rst
@@ -27,10 +27,10 @@ for details.
 Sysfs entries
 -------------
 
-The following attributes are supported. Current maxim attribute
+The following attributes are supported. Current maximum attribute
 is read-write, all other attributes are read-only.
 
-in0_input		Measured voltage in microvolts.
+in0_input		Measured voltage in millivolts.
 
-curr1_input		Measured current in microamperes.
-curr1_max_alarm		Overcurrent alarm in microamperes.
+curr1_input		Measured current in milliamperes.
+curr1_max		Overcurrent shutdown threshold in milliamperes.
diff --git a/drivers/hwmon/adm1177.c b/drivers/hwmon/adm1177.c
index 8b2c965480e3..7888afe8dafd 100644
--- a/drivers/hwmon/adm1177.c
+++ b/drivers/hwmon/adm1177.c
@@ -10,6 +10,8 @@
 #include <linux/hwmon.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
 
@@ -33,7 +35,7 @@
 struct adm1177_state {
 	struct i2c_client	*client;
 	u32			r_sense_uohm;
-	u32			alert_threshold_ua;
+	u64			alert_threshold_ua;
 	bool			vrange_high;
 };
 
@@ -48,7 +50,7 @@ static int adm1177_write_cmd(struct adm1177_state *st, u8 cmd)
 }
 
 static int adm1177_write_alert_thr(struct adm1177_state *st,
-				   u32 alert_threshold_ua)
+				   u64 alert_threshold_ua)
 {
 	u64 val;
 	int ret;
@@ -91,8 +93,8 @@ static int adm1177_read(struct device *dev, enum hwmon_sensor_types type,
 			*val = div_u64((105840000ull * dummy),
 				       4096 * st->r_sense_uohm);
 			return 0;
-		case hwmon_curr_max_alarm:
-			*val = st->alert_threshold_ua;
+		case hwmon_curr_max:
+			*val = div_u64(st->alert_threshold_ua, 1000);
 			return 0;
 		default:
 			return -EOPNOTSUPP;
@@ -126,9 +128,10 @@ static int adm1177_write(struct device *dev, enum hwmon_sensor_types type,
 	switch (type) {
 	case hwmon_curr:
 		switch (attr) {
-		case hwmon_curr_max_alarm:
-			adm1177_write_alert_thr(st, val);
-			return 0;
+		case hwmon_curr_max:
+			val = clamp_val(val, 0,
+					div_u64(105840000ULL, st->r_sense_uohm));
+			return adm1177_write_alert_thr(st, (u64)val * 1000);
 		default:
 			return -EOPNOTSUPP;
 		}
@@ -156,7 +159,7 @@ static umode_t adm1177_is_visible(const void *data,
 			if (st->r_sense_uohm)
 				return 0444;
 			return 0;
-		case hwmon_curr_max_alarm:
+		case hwmon_curr_max:
 			if (st->r_sense_uohm)
 				return 0644;
 			return 0;
@@ -170,7 +173,7 @@ static umode_t adm1177_is_visible(const void *data,
 
 static const struct hwmon_channel_info * const adm1177_info[] = {
 	HWMON_CHANNEL_INFO(curr,
-			   HWMON_C_INPUT | HWMON_C_MAX_ALARM),
+			   HWMON_C_INPUT | HWMON_C_MAX),
 	HWMON_CHANNEL_INFO(in,
 			   HWMON_I_INPUT),
 	NULL
@@ -192,7 +195,8 @@ static int adm1177_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	struct device *hwmon_dev;
 	struct adm1177_state *st;
-	u32 alert_threshold_ua;
+	u64 alert_threshold_ua;
+	u32 prop;
 	int ret;
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
@@ -208,22 +212,26 @@ static int adm1177_probe(struct i2c_client *client)
 	if (device_property_read_u32(dev, "shunt-resistor-micro-ohms",
 				     &st->r_sense_uohm))
 		st->r_sense_uohm = 0;
-	if (device_property_read_u32(dev, "adi,shutdown-threshold-microamp",
-				     &alert_threshold_ua)) {
-		if (st->r_sense_uohm)
-			/*
-			 * set maximum default value from datasheet based on
-			 * shunt-resistor
-			 */
-			alert_threshold_ua = div_u64(105840000000,
-						     st->r_sense_uohm);
-		else
-			alert_threshold_ua = 0;
+	if (!device_property_read_u32(dev, "adi,shutdown-threshold-microamp",
+				      &prop)) {
+		alert_threshold_ua = prop;
+	} else if (st->r_sense_uohm) {
+		/*
+		 * set maximum default value from datasheet based on
+		 * shunt-resistor
+		 */
+		alert_threshold_ua = div_u64(105840000000ULL,
+					     st->r_sense_uohm);
+	} else {
+		alert_threshold_ua = 0;
 	}
 	st->vrange_high = device_property_read_bool(dev,
 						    "adi,vrange-high-enable");
-	if (alert_threshold_ua && st->r_sense_uohm)
-		adm1177_write_alert_thr(st, alert_threshold_ua);
+	if (alert_threshold_ua && st->r_sense_uohm) {
+		ret = adm1177_write_alert_thr(st, alert_threshold_ua);
+		if (ret)
+			return ret;
+	}
 
 	ret = adm1177_write_cmd(st, ADM1177_CMD_V_CONT |
 				    ADM1177_CMD_I_CONT |
-- 
cgit v1.2.3


From c673efd5db2223c2e8b885025bcd96bca6cdb171 Mon Sep 17 00:00:00 2001
From: Shuming Fan <shumingf@realtek.com>
Date: Wed, 25 Mar 2026 19:04:06 +0800
Subject: ASoC: SDCA: fix finding wrong entity

This patch fixes an issue like:
where searching for the entity 'FU 11' could incorrectly match 'FU 113' first.
The driver should first perform an exact match on the full string name.
If no exact match is found, it can then fall back to a partial match.

Fixes: 48fa77af2f4a ("ASoC: SDCA: Add terminal type into input/output widget name")
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20260325110406.3232420-1-shumingf@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdca/sdca_functions.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c
index d27ffb25ad97..dca60ee8e62c 100644
--- a/sound/soc/sdca/sdca_functions.c
+++ b/sound/soc/sdca/sdca_functions.c
@@ -1601,10 +1601,19 @@ static int find_sdca_entities(struct device *dev, struct sdw_slave *sdw,
 static struct sdca_entity *find_sdca_entity_by_label(struct sdca_function_data *function,
 						     const char *entity_label)
 {
+	struct sdca_entity *entity = NULL;
 	int i;
 
 	for (i = 0; i < function->num_entities; i++) {
-		struct sdca_entity *entity = &function->entities[i];
+		entity = &function->entities[i];
+
+		/* check whole string first*/
+		if (!strcmp(entity->label, entity_label))
+			return entity;
+	}
+
+	for (i = 0; i < function->num_entities; i++) {
+		entity = &function->entities[i];
 
 		if (!strncmp(entity->label, entity_label, strlen(entity_label)))
 			return entity;
-- 
cgit v1.2.3


From e398978ddf18fe5a2fc8299c77e6fe50e6c306c4 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 25 Mar 2026 13:34:18 +0100
Subject: workqueue: Better describe stall check

Try to be more explicit why the workqueue watchdog does not take
pool->lock by default. Spin locks are full memory barriers which
delay anything. Obviously, they would primary delay operations
on the related worker pools.

Explain why it is enough to prevent the false positive by re-checking
the timestamp under the pool->lock.

Finally, make it clear what would be the alternative solution in
__queue_work() which is a hotter path.

Signed-off-by: Petr Mladek <pmladek@suse.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ff97b705f25e..eda756556341 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7702,13 +7702,14 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
 		/*
 		 * Did we stall?
 		 *
-		 * Do a lockless check first. On weakly ordered
-		 * architectures, the lockless check can observe a
-		 * reordering between worklist insert_work() and
-		 * last_progress_ts update from __queue_work(). Since
-		 * __queue_work() is a much hotter path than the timer
-		 * function, we handle false positive here by reading
-		 * last_progress_ts again with pool->lock held.
+		 * Do a lockless check first to do not disturb the system.
+		 *
+		 * Prevent false positives by double checking the timestamp
+		 * under pool->lock. The lock makes sure that the check reads
+		 * an updated pool->last_progress_ts when this CPU saw
+		 * an already updated pool->worklist above. It seems better
+		 * than adding another barrier into __queue_work() which
+		 * is a hotter path.
 		 */
 		if (time_after(now, ts + thresh)) {
 			scoped_guard(raw_spinlock_irqsave, &pool->lock) {
-- 
cgit v1.2.3


From 175b45ed343a9c547b5f45293d3ea08d38a7b6f4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Sat, 14 Mar 2026 04:12:58 -0700
Subject: srcu: Use raw spinlocks so call_srcu() can be used under
 preempt_disable()

Tree SRCU has used non-raw spinlocks for many years, motivated by a desire
to avoid unnecessary real-time latency and the absence of any reason to
use raw spinlocks.  However, the recent use of SRCU in tracing as the
underlying implementation of RCU Tasks Trace means that call_srcu()
is invoked from preemption-disabled regions of code, which in turn
requires that any locks acquired by call_srcu() or its callees must be
raw spinlocks.

This commit therefore converts SRCU's spinlocks to raw spinlocks.

[boqun: Add Fixes tag]

Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Fixes: c27cea4416a3 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast")
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/srcutree.h |   8 +--
 kernel/rcu/rcu.h         |   9 +++
 kernel/rcu/srcutree.c    | 174 +++++++++++++++++++----------------------------
 3 files changed, 82 insertions(+), 109 deletions(-)

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 958cb7ef41cb..dfb31d11ff05 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -34,7 +34,7 @@ struct srcu_data {
 						/* Values: SRCU_READ_FLAVOR_.*  */
 
 	/* Update-side state. */
-	spinlock_t __private lock ____cacheline_internodealigned_in_smp;
+	raw_spinlock_t __private lock ____cacheline_internodealigned_in_smp;
 	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
 	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
 	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
@@ -55,7 +55,7 @@ struct srcu_data {
  * Node in SRCU combining tree, similar in function to rcu_data.
  */
 struct srcu_node {
-	spinlock_t __private lock;
+	raw_spinlock_t __private lock;
 	unsigned long srcu_have_cbs[4];		/* GP seq for children having CBs, but only */
 						/*  if greater than ->srcu_gp_seq. */
 	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs have CBs for given GP? */
@@ -74,7 +74,7 @@ struct srcu_usage {
 						/* First node at each level. */
 	int srcu_size_state;			/* Small-to-big transition state. */
 	struct mutex srcu_cb_mutex;		/* Serialize CB preparation. */
-	spinlock_t __private lock;		/* Protect counters and size state. */
+	raw_spinlock_t __private lock;		/* Protect counters and size state. */
 	struct mutex srcu_gp_mutex;		/* Serialize GP work. */
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
 	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
@@ -156,7 +156,7 @@ struct srcu_struct {
 
 #define __SRCU_USAGE_INIT(name)									\
 {												\
-	.lock = __SPIN_LOCK_UNLOCKED(name.lock),						\
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock),						\
 	.srcu_gp_seq = SRCU_GP_SEQ_INITIAL_VAL,							\
 	.srcu_gp_seq_needed = SRCU_GP_SEQ_INITIAL_VAL_WITH_STATE,				\
 	.srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL,					\
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index dc5d614b372c..9b10b57b79ad 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -502,6 +502,15 @@ do {									\
 	___locked;							\
 })
 
+#define raw_spin_trylock_irqsave_rcu_node(p, flags)			\
+({									\
+	bool ___locked = raw_spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
+									\
+	if (___locked)							\
+		smp_mb__after_unlock_lock();				\
+	___locked;							\
+})
+
 #define raw_lockdep_assert_held_rcu_node(p)				\
 	lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
 
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index aef8e91ad33e..2328827f8775 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -77,42 +77,6 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
 static void srcu_delay_timer(struct timer_list *t);
 
-/* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
-#define spin_lock_rcu_node(p)							\
-do {										\
-	spin_lock(&ACCESS_PRIVATE(p, lock));					\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_unlock_rcu_node(p) spin_unlock(&ACCESS_PRIVATE(p, lock))
-
-#define spin_lock_irq_rcu_node(p)						\
-do {										\
-	spin_lock_irq(&ACCESS_PRIVATE(p, lock));				\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_unlock_irq_rcu_node(p)						\
-	spin_unlock_irq(&ACCESS_PRIVATE(p, lock))
-
-#define spin_lock_irqsave_rcu_node(p, flags)					\
-do {										\
-	spin_lock_irqsave(&ACCESS_PRIVATE(p, lock), flags);			\
-	smp_mb__after_unlock_lock();						\
-} while (0)
-
-#define spin_trylock_irqsave_rcu_node(p, flags)					\
-({										\
-	bool ___locked = spin_trylock_irqsave(&ACCESS_PRIVATE(p, lock), flags); \
-										\
-	if (___locked)								\
-		smp_mb__after_unlock_lock();					\
-	___locked;								\
-})
-
-#define spin_unlock_irqrestore_rcu_node(p, flags)				\
-	spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags)			\
-
 /*
  * Initialize SRCU per-CPU data.  Note that statically allocated
  * srcu_struct structures might already have srcu_read_lock() and
@@ -131,7 +95,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp)
 	 */
 	for_each_possible_cpu(cpu) {
 		sdp = per_cpu_ptr(ssp->sda, cpu);
-		spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(sdp, lock));
 		rcu_segcblist_init(&sdp->srcu_cblist);
 		sdp->srcu_cblist_invoking = false;
 		sdp->srcu_gp_seq_needed = ssp->srcu_sup->srcu_gp_seq;
@@ -186,7 +150,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
 
 	/* Each pass through this loop initializes one srcu_node structure. */
 	srcu_for_each_node_breadth_first(ssp, snp) {
-		spin_lock_init(&ACCESS_PRIVATE(snp, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(snp, lock));
 		BUILD_BUG_ON(ARRAY_SIZE(snp->srcu_have_cbs) !=
 			     ARRAY_SIZE(snp->srcu_data_have_cbs));
 		for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
@@ -242,7 +206,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	if (!ssp->srcu_sup)
 		return -ENOMEM;
 	if (!is_static)
-		spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
+		raw_spin_lock_init(&ACCESS_PRIVATE(ssp->srcu_sup, lock));
 	ssp->srcu_sup->srcu_size_state = SRCU_SIZE_SMALL;
 	ssp->srcu_sup->node = NULL;
 	mutex_init(&ssp->srcu_sup->srcu_cb_mutex);
@@ -394,20 +358,20 @@ static void srcu_transition_to_big(struct srcu_struct *ssp)
 	/* Double-checked locking on ->srcu_size-state. */
 	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL)
 		return;
-	spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
 	if (smp_load_acquire(&ssp->srcu_sup->srcu_size_state) != SRCU_SIZE_SMALL) {
-		spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+		raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 		return;
 	}
 	__srcu_transition_to_big(ssp);
-	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
  * Check to see if the just-encountered contention event justifies
  * a transition to SRCU_SIZE_BIG.
  */
-static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
+static void raw_spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
 {
 	unsigned long j;
 
@@ -429,16 +393,16 @@ static void spin_lock_irqsave_check_contention(struct srcu_struct *ssp)
  * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
  * parameter permits this.
  */
-static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags)
+static void raw_spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned long *flags)
 {
 	struct srcu_struct *ssp = sdp->ssp;
 
-	if (spin_trylock_irqsave_rcu_node(sdp, *flags))
+	if (raw_spin_trylock_irqsave_rcu_node(sdp, *flags))
 		return;
-	spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
-	spin_lock_irqsave_check_contention(ssp);
-	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, *flags);
-	spin_lock_irqsave_rcu_node(sdp, *flags);
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
+	raw_spin_lock_irqsave_check_contention(ssp);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, *flags);
+	raw_spin_lock_irqsave_rcu_node(sdp, *flags);
 }
 
 /*
@@ -447,12 +411,12 @@ static void spin_lock_irqsave_sdp_contention(struct srcu_data *sdp, unsigned lon
  * to SRCU_SIZE_BIG.  But only if the srcutree.convert_to_big module
  * parameter permits this.
  */
-static void spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags)
+static void raw_spin_lock_irqsave_ssp_contention(struct srcu_struct *ssp, unsigned long *flags)
 {
-	if (spin_trylock_irqsave_rcu_node(ssp->srcu_sup, *flags))
+	if (raw_spin_trylock_irqsave_rcu_node(ssp->srcu_sup, *flags))
 		return;
-	spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
-	spin_lock_irqsave_check_contention(ssp);
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, *flags);
+	raw_spin_lock_irqsave_check_contention(ssp);
 }
 
 /*
@@ -470,13 +434,13 @@ static void check_init_srcu_struct(struct srcu_struct *ssp)
 	/* The smp_load_acquire() pairs with the smp_store_release(). */
 	if (!rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq_needed))) /*^^^*/
 		return; /* Already initialized. */
-	spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
 	if (!rcu_seq_state(ssp->srcu_sup->srcu_gp_seq_needed)) {
-		spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+		raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 		return;
 	}
 	init_srcu_struct_fields(ssp, true);
-	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
@@ -742,9 +706,9 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 	unsigned long delay;
 	struct srcu_usage *sup = ssp->srcu_sup;
 
-	spin_lock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 	delay = srcu_get_delay(ssp);
-	spin_unlock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 	if (WARN_ON(!delay))
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
@@ -960,7 +924,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	mutex_lock(&sup->srcu_cb_mutex);
 
 	/* End the current grace period. */
-	spin_lock_irq_rcu_node(sup);
+	raw_spin_lock_irq_rcu_node(sup);
 	idx = rcu_seq_state(sup->srcu_gp_seq);
 	WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
 	if (srcu_gp_is_expedited(ssp))
@@ -971,7 +935,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	gpseq = rcu_seq_current(&sup->srcu_gp_seq);
 	if (ULONG_CMP_LT(sup->srcu_gp_seq_needed_exp, gpseq))
 		WRITE_ONCE(sup->srcu_gp_seq_needed_exp, gpseq);
-	spin_unlock_irq_rcu_node(sup);
+	raw_spin_unlock_irq_rcu_node(sup);
 	mutex_unlock(&sup->srcu_gp_mutex);
 	/* A new grace period can start at this point.  But only one. */
 
@@ -983,7 +947,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	} else {
 		idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
 		srcu_for_each_node_breadth_first(ssp, snp) {
-			spin_lock_irq_rcu_node(snp);
+			raw_spin_lock_irq_rcu_node(snp);
 			cbs = false;
 			last_lvl = snp >= sup->level[rcu_num_lvls - 1];
 			if (last_lvl)
@@ -998,7 +962,7 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 			else
 				mask = snp->srcu_data_have_cbs[idx];
 			snp->srcu_data_have_cbs[idx] = 0;
-			spin_unlock_irq_rcu_node(snp);
+			raw_spin_unlock_irq_rcu_node(snp);
 			if (cbs)
 				srcu_schedule_cbs_snp(ssp, snp, mask, cbdelay);
 		}
@@ -1008,27 +972,27 @@ static void srcu_gp_end(struct srcu_struct *ssp)
 	if (!(gpseq & counter_wrap_check))
 		for_each_possible_cpu(cpu) {
 			sdp = per_cpu_ptr(ssp->sda, cpu);
-			spin_lock_irq_rcu_node(sdp);
+			raw_spin_lock_irq_rcu_node(sdp);
 			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed + 100))
 				sdp->srcu_gp_seq_needed = gpseq;
 			if (ULONG_CMP_GE(gpseq, sdp->srcu_gp_seq_needed_exp + 100))
 				sdp->srcu_gp_seq_needed_exp = gpseq;
-			spin_unlock_irq_rcu_node(sdp);
+			raw_spin_unlock_irq_rcu_node(sdp);
 		}
 
 	/* Callback initiation done, allow grace periods after next. */
 	mutex_unlock(&sup->srcu_cb_mutex);
 
 	/* Start a new grace period if needed. */
-	spin_lock_irq_rcu_node(sup);
+	raw_spin_lock_irq_rcu_node(sup);
 	gpseq = rcu_seq_current(&sup->srcu_gp_seq);
 	if (!rcu_seq_state(gpseq) &&
 	    ULONG_CMP_LT(gpseq, sup->srcu_gp_seq_needed)) {
 		srcu_gp_start(ssp);
-		spin_unlock_irq_rcu_node(sup);
+		raw_spin_unlock_irq_rcu_node(sup);
 		srcu_reschedule(ssp, 0);
 	} else {
-		spin_unlock_irq_rcu_node(sup);
+		raw_spin_unlock_irq_rcu_node(sup);
 	}
 
 	/* Transition to big if needed. */
@@ -1059,19 +1023,19 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp
 			if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_sup->srcu_gp_seq, s)) ||
 			    (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)))
 				return;
-			spin_lock_irqsave_rcu_node(snp, flags);
+			raw_spin_lock_irqsave_rcu_node(snp, flags);
 			sgsne = snp->srcu_gp_seq_needed_exp;
 			if (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s)) {
-				spin_unlock_irqrestore_rcu_node(snp, flags);
+				raw_spin_unlock_irqrestore_rcu_node(snp, flags);
 				return;
 			}
 			WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-			spin_unlock_irqrestore_rcu_node(snp, flags);
+			raw_spin_unlock_irqrestore_rcu_node(snp, flags);
 		}
-	spin_lock_irqsave_ssp_contention(ssp, &flags);
+	raw_spin_lock_irqsave_ssp_contention(ssp, &flags);
 	if (ULONG_CMP_LT(ssp->srcu_sup->srcu_gp_seq_needed_exp, s))
 		WRITE_ONCE(ssp->srcu_sup->srcu_gp_seq_needed_exp, s);
-	spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
 }
 
 /*
@@ -1109,12 +1073,12 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) {
 			if (WARN_ON_ONCE(rcu_seq_done(&sup->srcu_gp_seq, s)) && snp != snp_leaf)
 				return; /* GP already done and CBs recorded. */
-			spin_lock_irqsave_rcu_node(snp, flags);
+			raw_spin_lock_irqsave_rcu_node(snp, flags);
 			snp_seq = snp->srcu_have_cbs[idx];
 			if (!srcu_invl_snp_seq(snp_seq) && ULONG_CMP_GE(snp_seq, s)) {
 				if (snp == snp_leaf && snp_seq == s)
 					snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
-				spin_unlock_irqrestore_rcu_node(snp, flags);
+				raw_spin_unlock_irqrestore_rcu_node(snp, flags);
 				if (snp == snp_leaf && snp_seq != s) {
 					srcu_schedule_cbs_sdp(sdp, do_norm ? SRCU_INTERVAL : 0);
 					return;
@@ -1129,11 +1093,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 			sgsne = snp->srcu_gp_seq_needed_exp;
 			if (!do_norm && (srcu_invl_snp_seq(sgsne) || ULONG_CMP_LT(sgsne, s)))
 				WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
-			spin_unlock_irqrestore_rcu_node(snp, flags);
+			raw_spin_unlock_irqrestore_rcu_node(snp, flags);
 		}
 
 	/* Top of tree, must ensure the grace period will be started. */
-	spin_lock_irqsave_ssp_contention(ssp, &flags);
+	raw_spin_lock_irqsave_ssp_contention(ssp, &flags);
 	if (ULONG_CMP_LT(sup->srcu_gp_seq_needed, s)) {
 		/*
 		 * Record need for grace period s.  Pair with load
@@ -1160,7 +1124,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		else if (list_empty(&sup->work.work.entry))
 			list_add(&sup->work.work.entry, &srcu_boot_list);
 	}
-	spin_unlock_irqrestore_rcu_node(sup, flags);
+	raw_spin_unlock_irqrestore_rcu_node(sup, flags);
 }
 
 /*
@@ -1172,9 +1136,9 @@ static bool try_check_zero(struct srcu_struct *ssp, int idx, int trycount)
 {
 	unsigned long curdelay;
 
-	spin_lock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 	curdelay = !srcu_get_delay(ssp);
-	spin_unlock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 
 	for (;;) {
 		if (srcu_readers_active_idx_check(ssp, idx))
@@ -1285,12 +1249,12 @@ static bool srcu_should_expedite(struct srcu_struct *ssp)
 		return false;
 	/* If the local srcu_data structure has callbacks, not idle.  */
 	sdp = raw_cpu_ptr(ssp->sda);
-	spin_lock_irqsave_rcu_node(sdp, flags);
+	raw_spin_lock_irqsave_rcu_node(sdp, flags);
 	if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
-		spin_unlock_irqrestore_rcu_node(sdp, flags);
+		raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
 		return false; /* Callbacks already present, so not idle. */
 	}
-	spin_unlock_irqrestore_rcu_node(sdp, flags);
+	raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
 
 	/*
 	 * No local callbacks, so probabilistically probe global state.
@@ -1350,7 +1314,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 		sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id());
 	else
 		sdp = raw_cpu_ptr(ssp->sda);
-	spin_lock_irqsave_sdp_contention(sdp, &flags);
+	raw_spin_lock_irqsave_sdp_contention(sdp, &flags);
 	if (rhp)
 		rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
 	/*
@@ -1410,7 +1374,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 		sdp->srcu_gp_seq_needed_exp = s;
 		needexp = true;
 	}
-	spin_unlock_irqrestore_rcu_node(sdp, flags);
+	raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
 
 	/* Ensure that snp node tree is fully initialized before traversing it */
 	if (ss_state < SRCU_SIZE_WAIT_BARRIER)
@@ -1522,7 +1486,7 @@ static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
 
 	/*
 	 * Make sure that later code is ordered after the SRCU grace
-	 * period.  This pairs with the spin_lock_irq_rcu_node()
+	 * period.  This pairs with the raw_spin_lock_irq_rcu_node()
 	 * in srcu_invoke_callbacks().  Unlike Tree RCU, this is needed
 	 * because the current CPU might have been totally uninvolved with
 	 * (and thus unordered against) that grace period.
@@ -1701,7 +1665,7 @@ static void srcu_barrier_cb(struct rcu_head *rhp)
  */
 static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp)
 {
-	spin_lock_irq_rcu_node(sdp);
+	raw_spin_lock_irq_rcu_node(sdp);
 	atomic_inc(&ssp->srcu_sup->srcu_barrier_cpu_cnt);
 	sdp->srcu_barrier_head.func = srcu_barrier_cb;
 	debug_rcu_head_queue(&sdp->srcu_barrier_head);
@@ -1710,7 +1674,7 @@ static void srcu_barrier_one_cpu(struct srcu_struct *ssp, struct srcu_data *sdp)
 		debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
 		atomic_dec(&ssp->srcu_sup->srcu_barrier_cpu_cnt);
 	}
-	spin_unlock_irq_rcu_node(sdp);
+	raw_spin_unlock_irq_rcu_node(sdp);
 }
 
 /**
@@ -1761,7 +1725,7 @@ static void srcu_expedite_current_cb(struct rcu_head *rhp)
 	bool needcb = false;
 	struct srcu_data *sdp = container_of(rhp, struct srcu_data, srcu_ec_head);
 
-	spin_lock_irqsave_sdp_contention(sdp, &flags);
+	raw_spin_lock_irqsave_sdp_contention(sdp, &flags);
 	if (sdp->srcu_ec_state == SRCU_EC_IDLE) {
 		WARN_ON_ONCE(1);
 	} else if (sdp->srcu_ec_state == SRCU_EC_PENDING) {
@@ -1771,7 +1735,7 @@ static void srcu_expedite_current_cb(struct rcu_head *rhp)
 		sdp->srcu_ec_state = SRCU_EC_PENDING;
 		needcb = true;
 	}
-	spin_unlock_irqrestore_rcu_node(sdp, flags);
+	raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
 	// If needed, requeue ourselves as an expedited SRCU callback.
 	if (needcb)
 		__call_srcu(sdp->ssp, &sdp->srcu_ec_head, srcu_expedite_current_cb, false);
@@ -1795,7 +1759,7 @@ void srcu_expedite_current(struct srcu_struct *ssp)
 
 	migrate_disable();
 	sdp = this_cpu_ptr(ssp->sda);
-	spin_lock_irqsave_sdp_contention(sdp, &flags);
+	raw_spin_lock_irqsave_sdp_contention(sdp, &flags);
 	if (sdp->srcu_ec_state == SRCU_EC_IDLE) {
 		sdp->srcu_ec_state = SRCU_EC_PENDING;
 		needcb = true;
@@ -1804,7 +1768,7 @@ void srcu_expedite_current(struct srcu_struct *ssp)
 	} else {
 		WARN_ON_ONCE(sdp->srcu_ec_state != SRCU_EC_REPOST);
 	}
-	spin_unlock_irqrestore_rcu_node(sdp, flags);
+	raw_spin_unlock_irqrestore_rcu_node(sdp, flags);
 	// If needed, queue an expedited SRCU callback.
 	if (needcb)
 		__call_srcu(ssp, &sdp->srcu_ec_head, srcu_expedite_current_cb, false);
@@ -1848,17 +1812,17 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 	 */
 	idx = rcu_seq_state(smp_load_acquire(&ssp->srcu_sup->srcu_gp_seq)); /* ^^^ */
 	if (idx == SRCU_STATE_IDLE) {
-		spin_lock_irq_rcu_node(ssp->srcu_sup);
+		raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 		if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) {
 			WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq));
-			spin_unlock_irq_rcu_node(ssp->srcu_sup);
+			raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			return;
 		}
 		idx = rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq));
 		if (idx == SRCU_STATE_IDLE)
 			srcu_gp_start(ssp);
-		spin_unlock_irq_rcu_node(ssp->srcu_sup);
+		raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 		if (idx != SRCU_STATE_IDLE) {
 			mutex_unlock(&ssp->srcu_sup->srcu_gp_mutex);
 			return; /* Someone else started the grace period. */
@@ -1872,10 +1836,10 @@ static void srcu_advance_state(struct srcu_struct *ssp)
 			return; /* readers present, retry later. */
 		}
 		srcu_flip(ssp);
-		spin_lock_irq_rcu_node(ssp->srcu_sup);
+		raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 		rcu_seq_set_state(&ssp->srcu_sup->srcu_gp_seq, SRCU_STATE_SCAN2);
 		ssp->srcu_sup->srcu_n_exp_nodelay = 0;
-		spin_unlock_irq_rcu_node(ssp->srcu_sup);
+		raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 	}
 
 	if (rcu_seq_state(READ_ONCE(ssp->srcu_sup->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
@@ -1913,7 +1877,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 
 	ssp = sdp->ssp;
 	rcu_cblist_init(&ready_cbs);
-	spin_lock_irq_rcu_node(sdp);
+	raw_spin_lock_irq_rcu_node(sdp);
 	WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
 	rcu_segcblist_advance(&sdp->srcu_cblist,
 			      rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
@@ -1924,7 +1888,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	 */
 	if (sdp->srcu_cblist_invoking ||
 	    !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
-		spin_unlock_irq_rcu_node(sdp);
+		raw_spin_unlock_irq_rcu_node(sdp);
 		return;  /* Someone else on the job or nothing to do. */
 	}
 
@@ -1932,7 +1896,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	sdp->srcu_cblist_invoking = true;
 	rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
 	len = ready_cbs.len;
-	spin_unlock_irq_rcu_node(sdp);
+	raw_spin_unlock_irq_rcu_node(sdp);
 	rhp = rcu_cblist_dequeue(&ready_cbs);
 	for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
 		debug_rcu_head_unqueue(rhp);
@@ -1947,11 +1911,11 @@ static void srcu_invoke_callbacks(struct work_struct *work)
 	 * Update counts, accelerate new callbacks, and if needed,
 	 * schedule another round of callback invocation.
 	 */
-	spin_lock_irq_rcu_node(sdp);
+	raw_spin_lock_irq_rcu_node(sdp);
 	rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
 	sdp->srcu_cblist_invoking = false;
 	more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
-	spin_unlock_irq_rcu_node(sdp);
+	raw_spin_unlock_irq_rcu_node(sdp);
 	/* An SRCU barrier or callbacks from previous nesting work pending */
 	if (more)
 		srcu_schedule_cbs_sdp(sdp, 0);
@@ -1965,7 +1929,7 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
 {
 	bool pushgp = true;
 
-	spin_lock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 	if (ULONG_CMP_GE(ssp->srcu_sup->srcu_gp_seq, ssp->srcu_sup->srcu_gp_seq_needed)) {
 		if (!WARN_ON_ONCE(rcu_seq_state(ssp->srcu_sup->srcu_gp_seq))) {
 			/* All requests fulfilled, time to go idle. */
@@ -1975,7 +1939,7 @@ static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay)
 		/* Outstanding request and no GP.  Start one. */
 		srcu_gp_start(ssp);
 	}
-	spin_unlock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 
 	if (pushgp)
 		queue_delayed_work(rcu_gp_wq, &ssp->srcu_sup->work, delay);
@@ -1995,9 +1959,9 @@ static void process_srcu(struct work_struct *work)
 	ssp = sup->srcu_ssp;
 
 	srcu_advance_state(ssp);
-	spin_lock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_lock_irq_rcu_node(ssp->srcu_sup);
 	curdelay = srcu_get_delay(ssp);
-	spin_unlock_irq_rcu_node(ssp->srcu_sup);
+	raw_spin_unlock_irq_rcu_node(ssp->srcu_sup);
 	if (curdelay) {
 		WRITE_ONCE(sup->reschedule_count, 0);
 	} else {
-- 
cgit v1.2.3


From 61bbcfb50514a8a94e035a7349697a3790ab4783 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 20 Mar 2026 20:29:20 -0700
Subject: srcu: Push srcu_node allocation to GP when non-preemptible

When the srcutree.convert_to_big and srcutree.big_cpu_lim kernel boot
parameters specify initialization-time allocation of the srcu_node
tree for statically allocated srcu_struct structures (for example, in
DEFINE_SRCU() at build time instead of init_srcu_struct() at runtime),
init_srcu_struct_nodes() will attempt to dynamically allocate this tree
at the first run-time update-side use of this srcu_struct structure,
but while holding a raw spinlock.  Because the memory allocator can
acquire non-raw spinlocks, this can result in lockdep splats.

This commit therefore uses the same SRCU_SIZE_ALLOC trick that is used
when the first run-time update-side use of this srcu_struct structure
happens before srcu_init() is called.  The actual allocation then takes
place from workqueue context at the ends of upcoming SRCU grace periods.

[boqun: Adjust the sha1 of the Fixes tag]

Fixes: 175b45ed343a ("srcu: Use raw spinlocks so call_srcu() can be used under preempt_disable()")
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
---
 kernel/rcu/srcutree.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 2328827f8775..678bd9a73875 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -227,9 +227,12 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	ssp->srcu_sup->srcu_gp_seq_needed_exp = SRCU_GP_SEQ_INITIAL_VAL;
 	ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
-		if (!init_srcu_struct_nodes(ssp, is_static ? GFP_ATOMIC : GFP_KERNEL))
+		if (!preemptible())
+			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_ALLOC);
+		else if (init_srcu_struct_nodes(ssp, GFP_KERNEL))
+			WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
+		else
 			goto err_free_sda;
-		WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
 	}
 	ssp->srcu_sup->srcu_ssp = ssp;
 	smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed,
-- 
cgit v1.2.3


From 7c405fb3279b39244b260b54f1bd6488689ae235 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun@kernel.org>
Date: Wed, 18 Mar 2026 17:56:21 -0700
Subject: rcu: Use an intermediate irq_work to start process_srcu()

Since commit c27cea4416a3 ("rcu: Re-implement RCU Tasks Trace in terms
of SRCU-fast") we switched to SRCU in BPF. However as BPF instrument can
happen basically everywhere (including where a scheduler lock is held),
call_srcu() now needs to avoid acquiring scheduler lock because
otherwise it could cause deadlock [1]. Fix this by following what the
previous RCU Tasks Trace did: using an irq_work to delay the queuing of
the work to start process_srcu().

[boqun: Apply Joel's feedback]
[boqun: Apply Andrea's test feedback]

Reported-by: Andrea Righi <arighi@nvidia.com>
Closes: https://lore.kernel.org/all/abjzvz_tL_siV17s@gpd4/
Fixes: commit c27cea4416a3 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast")
Link: https://lore.kernel.org/rcu/3c4c5a29-24ea-492d-aeee-e0d9605b4183@nvidia.com/ [1]
Suggested-by: Zqiang <qiang.zhang@linux.dev>
Tested-by: Andrea Righi <arighi@nvidia.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Boqun Feng <boqun@kernel.org>
---
 include/linux/srcutree.h |  1 +
 kernel/rcu/srcutree.c    | 30 ++++++++++++++++++++++++++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index dfb31d11ff05..be76fa4fc170 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -95,6 +95,7 @@ struct srcu_usage {
 	unsigned long reschedule_jiffies;
 	unsigned long reschedule_count;
 	struct delayed_work work;
+	struct irq_work irq_work;
 	struct srcu_struct *srcu_ssp;
 };
 
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 678bd9a73875..0d01cd8c4b4a 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
+#include <linux/irq_work.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
@@ -75,6 +76,7 @@ static bool __read_mostly srcu_init_done;
 static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
+static void srcu_irq_work(struct irq_work *work);
 static void srcu_delay_timer(struct timer_list *t);
 
 /*
@@ -216,6 +218,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	mutex_init(&ssp->srcu_sup->srcu_barrier_mutex);
 	atomic_set(&ssp->srcu_sup->srcu_barrier_cpu_cnt, 0);
 	INIT_DELAYED_WORK(&ssp->srcu_sup->work, process_srcu);
+	init_irq_work(&ssp->srcu_sup->irq_work, srcu_irq_work);
 	ssp->srcu_sup->sda_is_static = is_static;
 	if (!is_static) {
 		ssp->sda = alloc_percpu(struct srcu_data);
@@ -716,6 +719,8 @@ void cleanup_srcu_struct(struct srcu_struct *ssp)
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
+	/* Wait for irq_work to finish first as it may queue a new work. */
+	irq_work_sync(&sup->irq_work);
 	flush_delayed_work(&sup->work);
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
@@ -1121,9 +1126,13 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp,
 		// it isn't.  And it does not have to be.  After all, it
 		// can only be executed during early boot when there is only
 		// the one boot CPU running with interrupts still disabled.
+		//
+		// Use an irq_work here to avoid acquiring runqueue lock with
+		// srcu rcu_node::lock held. BPF instrument could introduce the
+		// opposite dependency, hence we need to break the possible
+		// locking dependency here.
 		if (likely(srcu_init_done))
-			queue_delayed_work(rcu_gp_wq, &sup->work,
-					   !!srcu_get_delay(ssp));
+			irq_work_queue(&sup->irq_work);
 		else if (list_empty(&sup->work.work.entry))
 			list_add(&sup->work.work.entry, &srcu_boot_list);
 	}
@@ -1982,6 +1991,23 @@ static void process_srcu(struct work_struct *work)
 	srcu_reschedule(ssp, curdelay);
 }
 
+static void srcu_irq_work(struct irq_work *work)
+{
+	struct srcu_struct *ssp;
+	struct srcu_usage *sup;
+	unsigned long delay;
+	unsigned long flags;
+
+	sup = container_of(work, struct srcu_usage, irq_work);
+	ssp = sup->srcu_ssp;
+
+	raw_spin_lock_irqsave_rcu_node(ssp->srcu_sup, flags);
+	delay = srcu_get_delay(ssp);
+	raw_spin_unlock_irqrestore_rcu_node(ssp->srcu_sup, flags);
+
+	queue_delayed_work(rcu_gp_wq, &sup->work, !!delay);
+}
+
 void srcutorture_get_gp_data(struct srcu_struct *ssp, int *flags,
 			     unsigned long *gp_seq)
 {
-- 
cgit v1.2.3


From a6fc88b22bc8d12ad52e8412c667ec0f5bf055af Mon Sep 17 00:00:00 2001
From: Joel Fernandes <joelagnelf@nvidia.com>
Date: Mon, 23 Mar 2026 20:14:18 -0400
Subject: srcu: Use irq_work to start GP in tiny SRCU

Tiny SRCU's srcu_gp_start_if_needed() directly calls schedule_work(),
which acquires the workqueue pool->lock.

This causes a lockdep splat when call_srcu() is called with a scheduler
lock held, due to:

  call_srcu() [holding pi_lock]
    srcu_gp_start_if_needed()
      schedule_work() -> pool->lock

  workqueue_init() / create_worker() [holding pool->lock]
    wake_up_process() -> try_to_wake_up() -> pi_lock

Also add irq_work_sync() to cleanup_srcu_struct() to prevent a
use-after-free if a queued irq_work fires after cleanup begins.

Tested with rcutorture SRCU-T and no lockdep warnings.

[ Thanks to Boqun for similar fix in patch "rcu: Use an intermediate irq_work
to start process_srcu()" ]

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun@kernel.org>
---
 include/linux/srcutiny.h |  4 ++++
 kernel/rcu/srcutiny.c    | 19 ++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index dec7cbe015aa..905b629e8fa3 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -11,6 +11,7 @@
 #ifndef _LINUX_SRCU_TINY_H
 #define _LINUX_SRCU_TINY_H
 
+#include <linux/irq_work_types.h>
 #include <linux/swait.h>
 
 struct srcu_struct {
@@ -24,18 +25,21 @@ struct srcu_struct {
 	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
 	struct rcu_head **srcu_cb_tail;	/* Pending callbacks: Tail. */
 	struct work_struct srcu_work;	/* For driving grace periods. */
+	struct irq_work srcu_irq_work;	/* Defer schedule_work() to irq work. */
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 };
 
 void srcu_drive_gp(struct work_struct *wp);
+void srcu_tiny_irq_work(struct irq_work *irq_work);
 
 #define __SRCU_STRUCT_INIT(name, __ignored, ___ignored, ____ignored)	\
 {									\
 	.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),	\
 	.srcu_cb_tail = &name.srcu_cb_head,				\
 	.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp),	\
+	.srcu_irq_work = { .func = srcu_tiny_irq_work },		\
 	__SRCU_DEP_MAP_INIT(name)					\
 }
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 3450c3751ef7..a2e2d516e51b 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/export.h>
+#include <linux/irq_work.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate_wait.h>
@@ -41,6 +42,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp)
 	ssp->srcu_idx_max = 0;
 	INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
 	INIT_LIST_HEAD(&ssp->srcu_work.entry);
+	init_irq_work(&ssp->srcu_irq_work, srcu_tiny_irq_work);
 	return 0;
 }
 
@@ -84,6 +86,7 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
+	irq_work_sync(&ssp->srcu_irq_work);
 	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
 	WARN_ON(ssp->srcu_gp_waiting);
@@ -177,6 +180,20 @@ void srcu_drive_gp(struct work_struct *wp)
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
+/*
+ * Use an irq_work to defer schedule_work() to avoid acquiring the workqueue
+ * pool->lock while the caller might hold scheduler locks, causing lockdep
+ * splats due to workqueue_init() doing a wakeup.
+ */
+void srcu_tiny_irq_work(struct irq_work *irq_work)
+{
+	struct srcu_struct *ssp;
+
+	ssp = container_of(irq_work, struct srcu_struct, srcu_irq_work);
+	schedule_work(&ssp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_tiny_irq_work);
+
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
 	unsigned long cookie;
@@ -189,7 +206,7 @@ static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
 		if (likely(srcu_init_done))
-			schedule_work(&ssp->srcu_work);
+			irq_work_queue(&ssp->srcu_irq_work);
 		else if (list_empty(&ssp->srcu_work.entry))
 			list_add(&ssp->srcu_work.entry, &srcu_boot_list);
 	}
-- 
cgit v1.2.3


From ed8444006df9863ffa682e315352c44a49d9f4cb Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut+renesas@mailbox.org>
Date: Tue, 24 Mar 2026 15:33:28 +0100
Subject: arm64: dts: renesas: sparrow-hawk: Reserve first 128 MiB of DRAM

Mark the first 128 MiB of DRAM as reserved. The first 128 MiB of DRAM
may optionally be used by TFA and other firmware for its own purposes,
and in such case, Linux must not use this memory.

On this platform, U-Boot runs in EL3 and starts TFA BL31 and Linux from
a single combined fitImage. U-Boot has full access to all memory in the
0x40000000..0xbfffffff range, as well memory in the memory banks in the
64-bit address ranges, and therefore U-Boot patches this full complete
view of platform memory layout into the DT that is passed to the next
stage.

The next stage is TFA BL31 and then the Linux kernel. The TFA BL31 does
not modify the DT passed from U-Boot to TFA BL31 and then to Linux with
any new reserved-memory {} node to reserve memory areas used by the TFA
BL31 to prevent the next stage from using those areas, which lets Linux
to use all of the available DRAM as described in the DT that was passed
in by U-Boot, including the areas that are newly utilized by TFA BL31.

In case of high DRAM utilization, for example in case of four instances
of "memtester 3900M" running in parallel, unless the memory used by TFA
BL31 is properly reserved, Linux may use and corrupt the memory used by
TFA BL31, which would often lead to system becoming unresponsive.

Until TFA BL31 can properly fill its own reserved-memory node into the
DT, and to assure older versions of TFA BL31 do not cause problems, add
explicitly reserved-memory {} node which prevents Linux from using the
first 128 MiB of DRAM.

Note that TFA BL31 can be adjusted to use different memory areas, this
newly added reserved-memory {} node follows longer-term practice on the
R-Car SoCs where the first 128 MiB of DRAM is reserved for firmware use.
In case user does modify TFA BL31 to use different memory ranges, they
must either use a future version of TFA BL31 which properly patches a
reserved-memory {} node into the DT, or they must adjust the address
ranges of this reserved-memory {} node accordingly.

Fixes: a719915e76f2 ("arm64: dts: renesas: r8a779g3: Add Retronix R-Car V4H Sparrow Hawk board support")
Cc: stable@vger.kernel.org
Signed-off-by: Marek Vasut <marek.vasut+renesas@mailbox.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20260324143342.17872-1-marek.vasut+renesas@mailbox.org
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts
index ff07d984cbf2..812b133cf29e 100644
--- a/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts
+++ b/arch/arm64/boot/dts/renesas/r8a779g3-sparrow-hawk.dts
@@ -118,6 +118,17 @@
 		reg = <0x6 0x00000000 0x1 0x00000000>;
 	};
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		tfa@40000000 {
+			reg = <0x0 0x40000000 0x0 0x8000000>;
+			no-map;
+		};
+	};
+
 	/* Page 27 / DSI to Display */
 	dp-con {
 		compatible = "dp-connector";
-- 
cgit v1.2.3


From 7b3b1e5a87b2f5e35c52b5386d7c327be869454f Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Mon, 16 Mar 2026 14:07:42 -0700
Subject: PCI: hv: Set default NUMA node to 0 for devices without affinity info

When hv_pci_assign_numa_node() processes a device that does not have
HV_PCI_DEVICE_FLAG_NUMA_AFFINITY set or has an out-of-range
virtual_numa_node, the device NUMA node is left unset. On x86_64,
the uninitialized default happens to be 0, but on ARM64 it is
NUMA_NO_NODE (-1).

Tests show that when no NUMA information is available from the Hyper-V
host, devices perform best when assigned to node 0. With NUMA_NO_NODE
the kernel may spread work across NUMA nodes, which degrades
performance on Hyper-V, particularly for high-throughput devices like
MANA.

Always set the device NUMA node to 0 before the conditional NUMA
affinity check, so that devices get a performant default when the host
provides no NUMA information, and behavior is consistent on both
x86_64 and ARM64.

Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2")
Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/pci/controller/pci-hyperv.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 2c7a406b4ba8..38a790f642a1 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -2485,6 +2485,14 @@ static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
 		if (!hv_dev)
 			continue;
 
+		/*
+		 * If the Hyper-V host doesn't provide a NUMA node for the
+		 * device, default to node 0. With NUMA_NO_NODE the kernel
+		 * may spread work across NUMA nodes, which degrades
+		 * performance on Hyper-V.
+		 */
+		set_dev_node(&dev->dev, 0);
+
 		if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY &&
 		    hv_dev->desc.virtual_numa_node < num_possible_nodes())
 			/*
-- 
cgit v1.2.3


From f39f905e55f529b036321220af1ba4f4085564a5 Mon Sep 17 00:00:00 2001
From: Zhang Chen <zhangchen01@kylinos.cn>
Date: Thu, 19 Mar 2026 17:32:11 +0800
Subject: Bluetooth: L2CAP: Fix send LE flow credits in ACL link

When the L2CAP channel mode is L2CAP_MODE_ERTM/L2CAP_MODE_STREAMING,
l2cap_publish_rx_avail will be called and le flow credits will be sent in
l2cap_chan_rx_avail, even though the link type is ACL.

The logs in question as follows:
> ACL Data RX: Handle 129 flags 0x02 dlen 12
      L2CAP: Unknown (0x16) ident 4 len 4
        40 00 ed 05
< ACL Data TX: Handle 129 flags 0x00 dlen 10
      L2CAP: Command Reject (0x01) ident 4 len 2
        Reason: Command not understood (0x0000)

Bluetooth: Unknown BR/EDR signaling command 0x16
Bluetooth: Wrong link type (-22)

Fixes: ce60b9231b66 ("Bluetooth: compute LE flow credits based on recvbuf space")
Signed-off-by: Zhang Chen <zhangchen01@kylinos.cn>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 3de3e3c8e966..6fd884203dc6 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6630,6 +6630,10 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan)
 	struct l2cap_le_credits pkt;
 	u16 return_credits = l2cap_le_rx_credits(chan);
 
+	if (chan->mode != L2CAP_MODE_LE_FLOWCTL &&
+	    chan->mode != L2CAP_MODE_EXT_FLOWCTL)
+		return;
+
 	if (chan->rx_credits >= return_credits)
 		return;
 
-- 
cgit v1.2.3


From 94d8e6fe5d0818e9300e514e095a200bd5ff93ae Mon Sep 17 00:00:00 2001
From: Cen Zhang <zzzccc427@gmail.com>
Date: Wed, 18 Mar 2026 20:54:03 +0800
Subject: Bluetooth: btintel: serialize btintel_hw_error() with
 hci_req_sync_lock

btintel_hw_error() issues two __hci_cmd_sync() calls (HCI_OP_RESET
and Intel exception-info retrieval) without holding
hci_req_sync_lock().  This lets it race against
hci_dev_do_close() -> btintel_shutdown_combined(), which also runs
__hci_cmd_sync() under the same lock.  When both paths manipulate
hdev->req_status/req_rsp concurrently, the close path may free the
response skb first, and the still-running hw_error path hits a
slab-use-after-free in kfree_skb().

Wrap the whole recovery sequence in hci_req_sync_lock/unlock so it
is serialized with every other synchronous HCI command issuer.

Below is the data race report and the kasan report:

  BUG: data-race in __hci_cmd_sync_sk / btintel_shutdown_combined

  read of hdev->req_rsp at net/bluetooth/hci_sync.c:199
  by task kworker/u17:1/83:
   __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200
   __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223
   btintel_hw_error+0x114/0x670 drivers/bluetooth/btintel.c:254
   hci_error_reset+0x348/0xa30 net/bluetooth/hci_core.c:1030

  write/free by task ioctl/22580:
   btintel_shutdown_combined+0xd0/0x360
    drivers/bluetooth/btintel.c:3648
   hci_dev_close_sync+0x9ae/0x2c10 net/bluetooth/hci_sync.c:5246
   hci_dev_do_close+0x232/0x460 net/bluetooth/hci_core.c:526

  BUG: KASAN: slab-use-after-free in
   sk_skb_reason_drop+0x43/0x380 net/core/skbuff.c:1202
  Read of size 4 at addr ffff888144a738dc
  by task kworker/u17:1/83:
   __hci_cmd_sync_sk+0x12f2/0x1c30 net/bluetooth/hci_sync.c:200
   __hci_cmd_sync+0x55/0x80 net/bluetooth/hci_sync.c:223
   btintel_hw_error+0x186/0x670 drivers/bluetooth/btintel.c:260

Fixes: 973bb97e5aee ("Bluetooth: btintel: Add generic function for handling hardware errors")
Signed-off-by: Cen Zhang <zzzccc427@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 246b6205c5e0..ab146894ba4e 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -251,11 +251,13 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code)
 
 	bt_dev_err(hdev, "Hardware error 0x%2.2x", code);
 
+	hci_req_sync_lock(hdev);
+
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		bt_dev_err(hdev, "Reset after hardware error failed (%ld)",
 			   PTR_ERR(skb));
-		return;
+		goto unlock;
 	}
 	kfree_skb(skb);
 
@@ -263,18 +265,21 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code)
 	if (IS_ERR(skb)) {
 		bt_dev_err(hdev, "Retrieving Intel exception info failed (%ld)",
 			   PTR_ERR(skb));
-		return;
+		goto unlock;
 	}
 
 	if (skb->len != 13) {
 		bt_dev_err(hdev, "Exception info size mismatch");
 		kfree_skb(skb);
-		return;
+		goto unlock;
 	}
 
 	bt_dev_err(hdev, "Exception info %s", (char *)(skb->data + 1));
 
 	kfree_skb(skb);
+
+unlock:
+	hci_req_sync_unlock(hdev);
 }
 EXPORT_SYMBOL_GPL(btintel_hw_error);
 
-- 
cgit v1.2.3


From 00fdebbbc557a2fc21321ff2eaa22fd70c078608 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 20 Mar 2026 20:01:26 +0900
Subject: Bluetooth: L2CAP: Fix deadlock in l2cap_conn_del()

l2cap_conn_del() calls cancel_delayed_work_sync() for both info_timer
and id_addr_timer while holding conn->lock. However, the work functions
l2cap_info_timeout() and l2cap_conn_update_id_addr() both acquire
conn->lock, creating a potential AB-BA deadlock if the work is already
executing when l2cap_conn_del() takes the lock.

Move the work cancellations before acquiring conn->lock and use
disable_delayed_work_sync() to additionally prevent the works from
being rearmed after cancellation, consistent with the pattern used in
hci_conn_del().

Fixes: ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in hci_chan_del")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 6fd884203dc6..2603c98d7ed1 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1771,6 +1771,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 
 	BT_DBG("hcon %p conn %p, err %d", hcon, conn, err);
 
+	disable_delayed_work_sync(&conn->info_timer);
+	disable_delayed_work_sync(&conn->id_addr_timer);
+
 	mutex_lock(&conn->lock);
 
 	kfree_skb(conn->rx_skb);
@@ -1786,8 +1789,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 
 	ida_destroy(&conn->tx_ida);
 
-	cancel_delayed_work_sync(&conn->id_addr_timer);
-
 	l2cap_unregister_all_users(conn);
 
 	/* Force the connection to be immediately dropped */
@@ -1806,9 +1807,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 		l2cap_chan_put(chan);
 	}
 
-	if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT)
-		cancel_delayed_work_sync(&conn->info_timer);
-
 	hci_chan_del(conn->hchan);
 	conn->hchan = NULL;
 
-- 
cgit v1.2.3


From 25f420a0d4cfd61d3d23ec4b9c56d9f443d91377 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 20 Mar 2026 20:23:10 +0900
Subject: Bluetooth: L2CAP: Fix ERTM re-init and zero pdu_len infinite loop

l2cap_config_req() processes CONFIG_REQ for channels in BT_CONNECTED
state to support L2CAP reconfiguration (e.g. MTU changes). However,
since both CONF_INPUT_DONE and CONF_OUTPUT_DONE are already set from
the initial configuration, the reconfiguration path falls through to
l2cap_ertm_init(), which re-initializes tx_q, srej_q, srej_list, and
retrans_list without freeing the previous allocations and sets
chan->sdu to NULL without freeing the existing skb. This leaks all
previously allocated ERTM resources.

Additionally, l2cap_parse_conf_req() does not validate the minimum
value of remote_mps derived from the RFC max_pdu_size option. A zero
value propagates to l2cap_segment_sdu() where pdu_len becomes zero,
causing the while loop to never terminate since len is never
decremented, exhausting all available memory.

Fix the double-init by skipping l2cap_ertm_init() and
l2cap_chan_ready() when the channel is already in BT_CONNECTED state,
while still allowing the reconfiguration parameters to be updated
through l2cap_parse_conf_req(). Also add a pdu_len zero check in
l2cap_segment_sdu() as a safeguard.

Fixes: 96298f640104 ("Bluetooth: L2CAP: handle l2cap config request during open state")
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 2603c98d7ed1..95c65fece39b 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2398,6 +2398,9 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan,
 	/* Remote device may have requested smaller PDUs */
 	pdu_len = min_t(size_t, pdu_len, chan->remote_mps);
 
+	if (!pdu_len)
+		return -EINVAL;
+
 	if (len <= pdu_len) {
 		sar = L2CAP_SAR_UNSEGMENTED;
 		sdu_len = 0;
@@ -4333,14 +4336,16 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
 	if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) {
 		set_default_fcs(chan);
 
-		if (chan->mode == L2CAP_MODE_ERTM ||
-		    chan->mode == L2CAP_MODE_STREAMING)
-			err = l2cap_ertm_init(chan);
+		if (chan->state != BT_CONNECTED) {
+			if (chan->mode == L2CAP_MODE_ERTM ||
+			    chan->mode == L2CAP_MODE_STREAMING)
+				err = l2cap_ertm_init(chan);
 
-		if (err < 0)
-			l2cap_send_disconn_req(chan, -err);
-		else
-			l2cap_chan_ready(chan);
+			if (err < 0)
+				l2cap_send_disconn_req(chan, -err);
+			else
+				l2cap_chan_ready(chan);
+		}
 
 		goto unlock;
 	}
-- 
cgit v1.2.3


From 129fa608b6ad08b8ab7178eeb2ec272c993aaccc Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Wed, 25 Mar 2026 08:42:45 +0800
Subject: Bluetooth: btusb: clamp SCO altsetting table indices

btusb_work() maps the number of active SCO links to USB alternate
settings through a three-entry lookup table when CVSD traffic uses
transparent voice settings. The lookup currently indexes alts[] with
data->sco_num - 1 without first constraining sco_num to the number of
available table entries.

While the table only defines alternate settings for up to three SCO
links, data->sco_num comes from hci_conn_num() and is used directly.
Cap the lookup to the last table entry before indexing it so the
driver keeps selecting the highest supported alternate setting without
reading past alts[].

Fixes: baac6276c0a9 ("Bluetooth: btusb: handle mSBC audio over USB Endpoints")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index a1c5eb993e47..5c535f3ab722 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2376,8 +2376,11 @@ static void btusb_work(struct work_struct *work)
 		if (data->air_mode == HCI_NOTIFY_ENABLE_SCO_CVSD) {
 			if (hdev->voice_setting & 0x0020) {
 				static const int alts[3] = { 2, 4, 5 };
+				unsigned int sco_idx;
 
-				new_alts = alts[data->sco_num - 1];
+				sco_idx = min_t(unsigned int, data->sco_num - 1,
+						ARRAY_SIZE(alts) - 1);
+				new_alts = alts[sco_idx];
 			} else {
 				new_alts = data->sco_num;
 			}
-- 
cgit v1.2.3


From 789b06f9f39cdc7e895bdab2c034e39c41c8f8d6 Mon Sep 17 00:00:00 2001
From: Alexander Popov <alex.popov@linux.com>
Date: Wed, 25 Mar 2026 01:46:02 +0300
Subject: wifi: virt_wifi: remove SET_NETDEV_DEV to avoid use-after-free

Currently we execute `SET_NETDEV_DEV(dev, &priv->lowerdev->dev)` for
the virt_wifi net devices. However, unregistering a virt_wifi device in
netdev_run_todo() can happen together with the device referenced by
SET_NETDEV_DEV().

It can result in use-after-free during the ethtool operations performed
on a virt_wifi device that is currently being unregistered. Such a net
device can have the `dev.parent` field pointing to the freed memory,
but ethnl_ops_begin() calls `pm_runtime_get_sync(dev->dev.parent)`.

Let's remove SET_NETDEV_DEV for virt_wifi to avoid bugs like this:

 ==================================================================
 BUG: KASAN: slab-use-after-free in __pm_runtime_resume+0xe2/0xf0
 Read of size 2 at addr ffff88810cfc46f8 by task pm/606

 Call Trace:
  <TASK>
  dump_stack_lvl+0x4d/0x70
  print_report+0x170/0x4f3
  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  kasan_report+0xda/0x110
  ? __pm_runtime_resume+0xe2/0xf0
  ? __pm_runtime_resume+0xe2/0xf0
  __pm_runtime_resume+0xe2/0xf0
  ethnl_ops_begin+0x49/0x270
  ethnl_set_features+0x23c/0xab0
  ? __pfx_ethnl_set_features+0x10/0x10
  ? kvm_sched_clock_read+0x11/0x20
  ? local_clock_noinstr+0xf/0xf0
  ? local_clock+0x10/0x30
  ? kasan_save_track+0x25/0x60
  ? __kasan_kmalloc+0x7f/0x90
  ? genl_family_rcv_msg_attrs_parse.isra.0+0x150/0x2c0
  genl_family_rcv_msg_doit+0x1e7/0x2c0
  ? __pfx_genl_family_rcv_msg_doit+0x10/0x10
  ? __pfx_cred_has_capability.isra.0+0x10/0x10
  ? stack_trace_save+0x8e/0xc0
  genl_rcv_msg+0x411/0x660
  ? __pfx_genl_rcv_msg+0x10/0x10
  ? __pfx_ethnl_set_features+0x10/0x10
  netlink_rcv_skb+0x121/0x380
  ? __pfx_genl_rcv_msg+0x10/0x10
  ? __pfx_netlink_rcv_skb+0x10/0x10
  ? __pfx_down_read+0x10/0x10
  genl_rcv+0x23/0x30
  netlink_unicast+0x60f/0x830
  ? __pfx_netlink_unicast+0x10/0x10
  ? __pfx___alloc_skb+0x10/0x10
  netlink_sendmsg+0x6ea/0xbc0
  ? __pfx_netlink_sendmsg+0x10/0x10
  ? __futex_queue+0x10b/0x1f0
  ____sys_sendmsg+0x7a2/0x950
  ? copy_msghdr_from_user+0x26b/0x430
  ? __pfx_____sys_sendmsg+0x10/0x10
  ? __pfx_copy_msghdr_from_user+0x10/0x10
  ___sys_sendmsg+0xf8/0x180
  ? __pfx____sys_sendmsg+0x10/0x10
  ? __pfx_futex_wait+0x10/0x10
  ? fdget+0x2e4/0x4a0
  __sys_sendmsg+0x11f/0x1c0
  ? __pfx___sys_sendmsg+0x10/0x10
  do_syscall_64+0xe2/0x570
  ? exc_page_fault+0x66/0xb0
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
  </TASK>

This fix may be combined with another one in the ethtool subsystem:
https://lore.kernel.org/all/20260322075917.254874-1-alex.popov@linux.com/T/#u

Fixes: d43c65b05b848e0b ("ethtool: runtime-resume netdev parent in ethnl_ops_begin")
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Popov <alex.popov@linux.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20260324224607.374327-1-alex.popov@linux.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/virt_wifi.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
index 885dc7243e8d..97bd39d89e98 100644
--- a/drivers/net/wireless/virtual/virt_wifi.c
+++ b/drivers/net/wireless/virtual/virt_wifi.c
@@ -557,7 +557,6 @@ static int virt_wifi_newlink(struct net_device *dev,
 	eth_hw_addr_inherit(dev, priv->lowerdev);
 	netif_stacked_transfer_operstate(priv->lowerdev, dev);
 
-	SET_NETDEV_DEV(dev, &priv->lowerdev->dev);
 	dev->ieee80211_ptr = kzalloc_obj(*dev->ieee80211_ptr);
 
 	if (!dev->ieee80211_ptr) {
-- 
cgit v1.2.3


From 805a5bd1c3f307d45ae4e9cf8915ef16d585a54a Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Tue, 24 Mar 2026 16:41:07 -0700
Subject: hwmon: (pmbus) Mark lowest/average/highest/rated attributes as
 read-only

Writing those attributes is not supported, so mark them as read-only.

Prior to this change, attempts to write into these attributes returned
an error.

Mark boolean fields in struct pmbus_limit_attr and in struct
pmbus_sensor_attr as bit fields to reduce configuration data size.
The data is scanned only while probing, so performance is not a concern.

Fixes: 6f183d33a02e6 ("hwmon: (pmbus) Add support for peak attributes")
Reviewed-by: Sanman Pradhan <psanman@juniper.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus_core.c | 48 +++++++++++++++++++++++++++++++++++-----
 1 file changed, 42 insertions(+), 6 deletions(-)

diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index be6d05def115..ecd1dddcbe0f 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -1495,8 +1495,9 @@ static int pmbus_add_label(struct pmbus_data *data,
 struct pmbus_limit_attr {
 	u16 reg;		/* Limit register */
 	u16 sbit;		/* Alarm attribute status bit */
-	bool update;		/* True if register needs updates */
-	bool low;		/* True if low limit; for limits with compare functions only */
+	bool readonly:1;	/* True if the attribute is read-only */
+	bool update:1;		/* True if register needs updates */
+	bool low:1;		/* True if low limit; for limits with compare functions only */
 	const char *attr;	/* Attribute name */
 	const char *alarm;	/* Alarm attribute name */
 };
@@ -1511,9 +1512,9 @@ struct pmbus_sensor_attr {
 	u8 nlimit;			/* # of limit registers */
 	enum pmbus_sensor_classes class;/* sensor class */
 	const char *label;		/* sensor label */
-	bool paged;			/* true if paged sensor */
-	bool update;			/* true if update needed */
-	bool compare;			/* true if compare function needed */
+	bool paged:1;			/* true if paged sensor */
+	bool update:1;			/* true if update needed */
+	bool compare:1;			/* true if compare function needed */
 	u32 func;			/* sensor mask */
 	u32 sfunc;			/* sensor status mask */
 	int sreg;			/* status register */
@@ -1544,7 +1545,7 @@ static int pmbus_add_limit_attrs(struct i2c_client *client,
 			curr = pmbus_add_sensor(data, name, l->attr, index,
 						page, 0xff, l->reg, attr->class,
 						attr->update || l->update,
-						false, true);
+						l->readonly, true);
 			if (!curr)
 				return -ENOMEM;
 			if (l->sbit && (info->func[page] & attr->sfunc)) {
@@ -1707,23 +1708,28 @@ static const struct pmbus_limit_attr vin_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_VIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VIN_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VIN_MIN,
+		.readonly = true,
 		.attr = "rated_min",
 	}, {
 		.reg = PMBUS_MFR_VIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -1776,23 +1782,28 @@ static const struct pmbus_limit_attr vout_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_VOUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VOUT_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VOUT_MIN,
+		.readonly = true,
 		.attr = "rated_min",
 	}, {
 		.reg = PMBUS_MFR_VOUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -1852,20 +1863,24 @@ static const struct pmbus_limit_attr iin_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_IIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IIN_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -1889,20 +1904,24 @@ static const struct pmbus_limit_attr iout_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_IOUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IOUT_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IOUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -1943,20 +1962,24 @@ static const struct pmbus_limit_attr pin_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "input_lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_PIN_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_PIN_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_PIN_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -1980,20 +2003,24 @@ static const struct pmbus_limit_attr pout_limit_attrs[] = {
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_AVG,
 		.update = true,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_MIN,
 		.update = true,
+		.readonly = true,
 		.attr = "input_lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_POUT_MAX,
 		.update = true,
+		.readonly = true,
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_POUT_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_POUT_MAX,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -2049,18 +2076,22 @@ static const struct pmbus_limit_attr temp_limit_attrs[] = {
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_MIN,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_AVG,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP_MAX,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_1,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -2090,18 +2121,22 @@ static const struct pmbus_limit_attr temp_limit_attrs2[] = {
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_MIN,
+		.readonly = true,
 		.attr = "lowest",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_AVG,
+		.readonly = true,
 		.attr = "average",
 	}, {
 		.reg = PMBUS_VIRT_READ_TEMP2_MAX,
+		.readonly = true,
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP2_HISTORY,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_2,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
@@ -2131,6 +2166,7 @@ static const struct pmbus_limit_attr temp_limit_attrs3[] = {
 		.sbit = PB_TEMP_OT_FAULT,
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_3,
+		.readonly = true,
 		.attr = "rated_max",
 	},
 };
-- 
cgit v1.2.3


From cd658475e7694d58e1c40dabc1dacf8431ccedb2 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Tue, 24 Mar 2026 18:54:11 -0700
Subject: hwmon: (pmbus) Introduce the concept of "write-only" attributes

Attributes intended to clear sensor history are intended to be writeable
only. Reading those attributes today results in reporting more or less
random values. To avoid ABI surprises, have those attributes explicitly
return 0 when reading.

Fixes: 787c095edaa9d ("hwmon: (pmbus/core) Add support for rated attributes")
Reviewed-by: Sanman Pradhan <psanman@juniper.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus_core.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index ecd1dddcbe0f..cbc36f0ba4bf 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -1209,6 +1209,12 @@ static ssize_t pmbus_show_boolean(struct device *dev,
 	return sysfs_emit(buf, "%d\n", val);
 }
 
+static ssize_t pmbus_show_zero(struct device *dev,
+			       struct device_attribute *devattr, char *buf)
+{
+	return sysfs_emit(buf, "0\n");
+}
+
 static ssize_t pmbus_show_sensor(struct device *dev,
 				 struct device_attribute *devattr, char *buf)
 {
@@ -1407,7 +1413,7 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data,
 					     int reg,
 					     enum pmbus_sensor_classes class,
 					     bool update, bool readonly,
-					     bool convert)
+					     bool writeonly, bool convert)
 {
 	struct pmbus_sensor *sensor;
 	struct device_attribute *a;
@@ -1436,7 +1442,8 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data,
 	sensor->data = -ENODATA;
 	pmbus_dev_attr_init(a, sensor->name,
 			    readonly ? 0444 : 0644,
-			    pmbus_show_sensor, pmbus_set_sensor);
+			    writeonly ? pmbus_show_zero : pmbus_show_sensor,
+			    pmbus_set_sensor);
 
 	if (pmbus_add_attribute(data, &a->attr))
 		return NULL;
@@ -1496,6 +1503,7 @@ struct pmbus_limit_attr {
 	u16 reg;		/* Limit register */
 	u16 sbit;		/* Alarm attribute status bit */
 	bool readonly:1;	/* True if the attribute is read-only */
+	bool writeonly:1;	/* True if the attribute is write-only */
 	bool update:1;		/* True if register needs updates */
 	bool low:1;		/* True if low limit; for limits with compare functions only */
 	const char *attr;	/* Attribute name */
@@ -1545,7 +1553,7 @@ static int pmbus_add_limit_attrs(struct i2c_client *client,
 			curr = pmbus_add_sensor(data, name, l->attr, index,
 						page, 0xff, l->reg, attr->class,
 						attr->update || l->update,
-						l->readonly, true);
+						l->readonly, l->writeonly, true);
 			if (!curr)
 				return -ENOMEM;
 			if (l->sbit && (info->func[page] & attr->sfunc)) {
@@ -1585,7 +1593,7 @@ static int pmbus_add_sensor_attrs_one(struct i2c_client *client,
 			return ret;
 	}
 	base = pmbus_add_sensor(data, name, "input", index, page, phase,
-				attr->reg, attr->class, true, true, true);
+				attr->reg, attr->class, true, true, false, true);
 	if (!base)
 		return -ENOMEM;
 	/* No limit and alarm attributes for phase specific sensors */
@@ -1722,6 +1730,7 @@ static const struct pmbus_limit_attr vin_limit_attrs[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VIN_MIN,
@@ -1796,6 +1805,7 @@ static const struct pmbus_limit_attr vout_limit_attrs[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_VOUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_VOUT_MIN,
@@ -1877,6 +1887,7 @@ static const struct pmbus_limit_attr iin_limit_attrs[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IIN_MAX,
@@ -1918,6 +1929,7 @@ static const struct pmbus_limit_attr iout_limit_attrs[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_IOUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_IOUT_MAX,
@@ -1976,6 +1988,7 @@ static const struct pmbus_limit_attr pin_limit_attrs[] = {
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_PIN_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_PIN_MAX,
@@ -2017,6 +2030,7 @@ static const struct pmbus_limit_attr pout_limit_attrs[] = {
 		.attr = "input_highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_POUT_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_POUT_MAX,
@@ -2088,6 +2102,7 @@ static const struct pmbus_limit_attr temp_limit_attrs[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_1,
@@ -2133,6 +2148,7 @@ static const struct pmbus_limit_attr temp_limit_attrs2[] = {
 		.attr = "highest",
 	}, {
 		.reg = PMBUS_VIRT_RESET_TEMP2_HISTORY,
+		.writeonly = true,
 		.attr = "reset_history",
 	}, {
 		.reg = PMBUS_MFR_MAX_TEMP_2,
@@ -2250,7 +2266,7 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client,
 
 	sensor = pmbus_add_sensor(data, "fan", "target", index, page,
 				  0xff, PMBUS_VIRT_FAN_TARGET_1 + id, PSC_FAN,
-				  false, false, true);
+				  false, false, false, true);
 
 	if (!sensor)
 		return -ENOMEM;
@@ -2261,14 +2277,14 @@ static int pmbus_add_fan_ctrl(struct i2c_client *client,
 
 	sensor = pmbus_add_sensor(data, "pwm", NULL, index, page,
 				  0xff, PMBUS_VIRT_PWM_1 + id, PSC_PWM,
-				  false, false, true);
+				  false, false, false, true);
 
 	if (!sensor)
 		return -ENOMEM;
 
 	sensor = pmbus_add_sensor(data, "pwm", "enable", index, page,
 				  0xff, PMBUS_VIRT_PWM_ENABLE_1 + id, PSC_PWM,
-				  true, false, false);
+				  true, false, false, false);
 
 	if (!sensor)
 		return -ENOMEM;
@@ -2310,7 +2326,7 @@ static int pmbus_add_fan_attributes(struct i2c_client *client,
 
 			if (pmbus_add_sensor(data, "fan", "input", index,
 					     page, 0xff, pmbus_fan_registers[f],
-					     PSC_FAN, true, true, true) == NULL)
+					     PSC_FAN, true, true, false, true) == NULL)
 				return -ENOMEM;
 
 			/* Fan control */
-- 
cgit v1.2.3


From 754bd2b4a084b90b5e7b630e1f423061a9b9b761 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 22 Mar 2026 09:12:33 -0700
Subject: hwmon: (pmbus/core) Protect regulator operations with mutex

The regulator operations pmbus_regulator_get_voltage(),
pmbus_regulator_set_voltage(), and pmbus_regulator_list_voltage()
access PMBus registers and shared data but were not protected by
the update_lock mutex. This could lead to race conditions.

However, adding mutex protection directly to these functions causes
a deadlock because pmbus_regulator_notify() (which calls
regulator_notifier_call_chain()) is often called with the mutex
already held (e.g., from pmbus_fault_handler()). If a regulator
callback then calls one of the now-protected voltage functions,
it will attempt to acquire the same mutex.

Rework pmbus_regulator_notify() to utilize a worker function to
send notifications outside of the mutex protection. Events are
stored as atomics in a per-page bitmask and processed by the worker.

Initialize the worker and its associated data during regulator
registration, and ensure it is cancelled on device removal using
devm_add_action_or_reset().

While at it, remove the unnecessary include of linux/of.h.

Cc: Sanman Pradhan <psanman@juniper.net>
Fixes: ddbb4db4ced1b ("hwmon: (pmbus) Add regulator support")
Reviewed-by: Sanman Pradhan <psanman@juniper.net>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus_core.c | 114 ++++++++++++++++++++++++++++++---------
 1 file changed, 89 insertions(+), 25 deletions(-)

diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index cbc36f0ba4bf..572be3ebc03d 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2012 Guenter Roeck
  */
 
+#include <linux/atomic.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/dcache.h>
@@ -21,8 +22,8 @@
 #include <linux/pmbus.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#include <linux/of.h>
 #include <linux/thermal.h>
+#include <linux/workqueue.h>
 #include "pmbus.h"
 
 /*
@@ -112,6 +113,11 @@ struct pmbus_data {
 
 	struct mutex update_lock;
 
+#if IS_ENABLED(CONFIG_REGULATOR)
+	atomic_t regulator_events[PMBUS_PAGES];
+	struct work_struct regulator_notify_work;
+#endif
+
 	bool has_status_word;		/* device uses STATUS_WORD register */
 	int (*read_status)(struct i2c_client *client, int page);
 
@@ -3228,12 +3234,19 @@ static int pmbus_regulator_get_voltage(struct regulator_dev *rdev)
 		.class = PSC_VOLTAGE_OUT,
 		.convert = true,
 	};
+	int ret;
 
+	mutex_lock(&data->update_lock);
 	s.data = _pmbus_read_word_data(client, s.page, 0xff, PMBUS_READ_VOUT);
-	if (s.data < 0)
-		return s.data;
+	if (s.data < 0) {
+		ret = s.data;
+		goto unlock;
+	}
 
-	return (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */
+	ret = (int)pmbus_reg2data(data, &s) * 1000; /* unit is uV */
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv,
@@ -3250,16 +3263,22 @@ static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv,
 	};
 	int val = DIV_ROUND_CLOSEST(min_uv, 1000); /* convert to mV */
 	int low, high;
+	int ret;
 
 	*selector = 0;
 
+	mutex_lock(&data->update_lock);
 	low = pmbus_regulator_get_low_margin(client, s.page);
-	if (low < 0)
-		return low;
+	if (low < 0) {
+		ret = low;
+		goto unlock;
+	}
 
 	high = pmbus_regulator_get_high_margin(client, s.page);
-	if (high < 0)
-		return high;
+	if (high < 0) {
+		ret = high;
+		goto unlock;
+	}
 
 	/* Make sure we are within margins */
 	if (low > val)
@@ -3269,7 +3288,10 @@ static int pmbus_regulator_set_voltage(struct regulator_dev *rdev, int min_uv,
 
 	val = pmbus_data2reg(data, &s, val);
 
-	return _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val);
+	ret = _pmbus_write_word_data(client, s.page, PMBUS_VOUT_COMMAND, (u16)val);
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 static int pmbus_regulator_list_voltage(struct regulator_dev *rdev,
@@ -3279,6 +3301,7 @@ static int pmbus_regulator_list_voltage(struct regulator_dev *rdev,
 	struct i2c_client *client = to_i2c_client(dev->parent);
 	struct pmbus_data *data = i2c_get_clientdata(client);
 	int val, low, high;
+	int ret;
 
 	if (data->flags & PMBUS_VOUT_PROTECTED)
 		return 0;
@@ -3291,18 +3314,29 @@ static int pmbus_regulator_list_voltage(struct regulator_dev *rdev,
 	val = DIV_ROUND_CLOSEST(rdev->desc->min_uV +
 				(rdev->desc->uV_step * selector), 1000); /* convert to mV */
 
+	mutex_lock(&data->update_lock);
+
 	low = pmbus_regulator_get_low_margin(client, rdev_get_id(rdev));
-	if (low < 0)
-		return low;
+	if (low < 0) {
+		ret = low;
+		goto unlock;
+	}
 
 	high = pmbus_regulator_get_high_margin(client, rdev_get_id(rdev));
-	if (high < 0)
-		return high;
+	if (high < 0) {
+		ret = high;
+		goto unlock;
+	}
 
-	if (val >= low && val <= high)
-		return val * 1000; /* unit is uV */
+	if (val >= low && val <= high) {
+		ret = val * 1000; /* unit is uV */
+		goto unlock;
+	}
 
-	return 0;
+	ret = 0;
+unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 const struct regulator_ops pmbus_regulator_ops = {
@@ -3333,12 +3367,42 @@ int pmbus_regulator_init_cb(struct regulator_dev *rdev,
 }
 EXPORT_SYMBOL_NS_GPL(pmbus_regulator_init_cb, "PMBUS");
 
+static void pmbus_regulator_notify_work_cancel(void *data)
+{
+	struct pmbus_data *pdata = data;
+
+	cancel_work_sync(&pdata->regulator_notify_work);
+}
+
+static void pmbus_regulator_notify_worker(struct work_struct *work)
+{
+	struct pmbus_data *data =
+		container_of(work, struct pmbus_data, regulator_notify_work);
+	int i, j;
+
+	for (i = 0; i < data->info->pages; i++) {
+		int event;
+
+		event = atomic_xchg(&data->regulator_events[i], 0);
+		if (!event)
+			continue;
+
+		for (j = 0; j < data->info->num_regulators; j++) {
+			if (i == rdev_get_id(data->rdevs[j])) {
+				regulator_notifier_call_chain(data->rdevs[j],
+							      event, NULL);
+				break;
+			}
+		}
+	}
+}
+
 static int pmbus_regulator_register(struct pmbus_data *data)
 {
 	struct device *dev = data->dev;
 	const struct pmbus_driver_info *info = data->info;
 	const struct pmbus_platform_data *pdata = dev_get_platdata(dev);
-	int i;
+	int i, ret;
 
 	data->rdevs = devm_kzalloc(dev, sizeof(struct regulator_dev *) * info->num_regulators,
 				   GFP_KERNEL);
@@ -3362,19 +3426,19 @@ static int pmbus_regulator_register(struct pmbus_data *data)
 					     info->reg_desc[i].name);
 	}
 
+	INIT_WORK(&data->regulator_notify_work, pmbus_regulator_notify_worker);
+
+	ret = devm_add_action_or_reset(dev, pmbus_regulator_notify_work_cancel, data);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
 static void pmbus_regulator_notify(struct pmbus_data *data, int page, int event)
 {
-	int j;
-
-	for (j = 0; j < data->info->num_regulators; j++) {
-		if (page == rdev_get_id(data->rdevs[j])) {
-			regulator_notifier_call_chain(data->rdevs[j], event, NULL);
-			break;
-		}
-	}
+	atomic_or(event, &data->regulator_events[page]);
+	schedule_work(&data->regulator_notify_work);
 }
 #else
 static int pmbus_regulator_register(struct pmbus_data *data)
-- 
cgit v1.2.3


From d3c0037ffe1273fa1961e779ff6906234d6cf53c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 25 Mar 2026 14:10:55 +0100
Subject: netfilter: nft_set_pipapo_avx2: don't return non-matching entry on
 expiry

New test case fails unexpectedly when avx2 matching functions are used.

The test first loads a ranomly generated pipapo set
with 'ipv4 . port' key, i.e.  nft -f foo.

This works.  Then, it reloads the set after a flush:
(echo flush set t s; cat foo) | nft -f -

This is expected to work, because its the same set after all and it was
already loaded once.

But with avx2, this fails: nft reports a clashing element.

The reported clash is of following form:

    We successfully re-inserted
      a . b
      c . d

Then we try to insert a . d

avx2 finds the already existing a . d, which (due to 'flush set') is marked
as invalid in the new generation.  It skips the element and moves to next.

Due to incorrect masking, the skip-step finds the next matching
element *only considering the first field*,

i.e. we return the already reinserted "a . b", even though the
last field is different and the entry should not have been matched.

No such error is reported for the generic c implementation (no avx2) or when
the last field has to use the 'nft_pipapo_avx2_lookup_slow' fallback.

Bisection points to
7711f4bb4b36 ("netfilter: nft_set_pipapo: fix range overlap detection")
but that fix merely uncovers this bug.

Before this commit, the wrong element is returned, but erronously
reported as a full, identical duplicate.

The root-cause is too early return in the avx2 match functions.
When we process the last field, we should continue to process data
until the entire input size has been consumed to make sure no stale
bits remain in the map.

Link: https://lore.kernel.org/netfilter-devel/20260321152506.037f68c0@elisabeth/
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_pipapo_avx2.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 7ff90325c97f..6395982e4d95 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -242,7 +242,7 @@ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -319,7 +319,7 @@ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -414,7 +414,7 @@ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -505,7 +505,7 @@ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -641,7 +641,7 @@ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -699,7 +699,7 @@ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -764,7 +764,7 @@ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -839,7 +839,7 @@ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -925,7 +925,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
@@ -1019,7 +1019,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
 
 		b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last);
 		if (last)
-			return b;
+			ret = b;
 
 		if (unlikely(ret == -1))
 			ret = b / XSAVE_YMM_SIZE;
-- 
cgit v1.2.3


From 6caefcd9491c408a4d161f7b60c8bb3d956526dd Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 25 Mar 2026 14:10:56 +0100
Subject: selftests: netfilter: nft_concat_range.sh: add check for flush+reload
 bug

This test will fail without
the preceding commit ("netfilter: nft_set_pipapo_avx2: fix match retart if found element is expired"):

  reject overlapping range on add       0s                              [ OK ]
  reload with flush                 /dev/stdin:59:32-52: Error: Could not process rule: File exists
add element inet filter test { 10.0.0.29 . 10.0.2.29 }

Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 .../selftests/net/netfilter/nft_concat_range.sh    | 70 +++++++++++++++++++++-
 1 file changed, 69 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 394166f224a4..ffdc6ccc6511 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -29,7 +29,8 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
        net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate insert_overlap"
+BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch doublecreate
+      insert_overlap load_flush_load4 load_flush_load8"
 
 # List of possible paths to pktgen script from kernel tree for performance tests
 PKTGEN_SCRIPT_PATHS="
@@ -432,6 +433,30 @@ race_repeat	0
 perf_duration	0
 "
 
+TYPE_load_flush_load4="
+display		reload with flush, 4bit groups
+type_spec	ipv4_addr . ipv4_addr
+chain_spec	ip saddr . ip daddr
+dst		addr4
+proto		icmp
+
+race_repeat	0
+
+perf_duration	0
+"
+
+TYPE_load_flush_load8="
+display		reload with flush, 8bit groups
+type_spec	ipv4_addr . ipv4_addr
+chain_spec	ip saddr . ip daddr
+dst		addr4
+proto		icmp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 # Set template for all tests, types and rules are filled in depending on test
 set_template='
 flush ruleset
@@ -1997,6 +2022,49 @@ test_bug_insert_overlap()
 	return 0
 }
 
+test_bug_load_flush_load4()
+{
+	local i
+
+	setup veth send_"${proto}" set || return ${ksft_skip}
+
+	for i in $(seq 0 255); do
+		local addelem="add element inet filter test"
+		local j
+
+		for j in $(seq 0 20); do
+			echo "$addelem { 10.$j.0.$i . 10.$j.1.$i }"
+			echo "$addelem { 10.$j.0.$i . 10.$j.2.$i }"
+		done
+	done > "$tmp"
+
+	nft -f "$tmp" || return 1
+
+	( echo "flush set inet filter test";cat "$tmp") | nft -f -
+	[ $? -eq 0 ] || return 1
+
+	return 0
+}
+
+test_bug_load_flush_load8()
+{
+	local i
+
+	setup veth send_"${proto}" set || return ${ksft_skip}
+
+	for i in $(seq 1 100); do
+		echo "add element inet filter test { 10.0.0.$i . 10.0.1.$i }"
+		echo "add element inet filter test { 10.0.0.$i . 10.0.2.$i }"
+	done > "$tmp"
+
+	nft -f "$tmp" || return 1
+
+	( echo "flush set inet filter test";cat "$tmp") | nft -f -
+	[ $? -eq 0 ] || return 1
+
+	return 0
+}
+
 test_reported_issues() {
 	eval test_bug_"${subtest}"
 }
-- 
cgit v1.2.3


From beef2634f81f1c086208191f7228bce1d366493d Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Thu, 19 Mar 2026 21:00:02 +0900
Subject: ksmbd: fix potencial OOB in get_file_all_info() for compound requests

When a compound request consists of QUERY_DIRECTORY + QUERY_INFO
(FILE_ALL_INFORMATION) and the first command consumes nearly the entire
max_trans_size, get_file_all_info() would blindly call smbConvertToUTF16()
with PATH_MAX, causing out-of-bounds write beyond the response buffer.
In get_file_all_info(), there was a missing validation check for
the client-provided OutputBufferLength before copying the filename into
FileName field of the smb2_file_all_info structure.
If the filename length exceeds the available buffer space, it could lead to
potential buffer overflows or memory corruption during smbConvertToUTF16
conversion. This calculating the actual free buffer size using
smb2_calc_max_out_buf_len() and returning -EINVAL if the buffer is
insufficient and updating smbConvertToUTF16 to use the actual filename
length (clamped by PATH_MAX) to ensure a safe copy operation.

Cc: stable@vger.kernel.org
Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound")
Reported-by: Asim Viladi Oglu Manizada <manizada@pm.me>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index f5f1bf5f642e..6fb7a795ff5d 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4940,7 +4940,8 @@ static int get_file_all_info(struct ksmbd_work *work,
 	int conv_len;
 	char *filename;
 	u64 time;
-	int ret;
+	int ret, buf_free_len, filename_len;
+	struct smb2_query_info_req *req = ksmbd_req_buf_next(work);
 
 	if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) {
 		ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n",
@@ -4952,6 +4953,16 @@ static int get_file_all_info(struct ksmbd_work *work,
 	if (IS_ERR(filename))
 		return PTR_ERR(filename);
 
+	filename_len = strlen(filename);
+	buf_free_len = smb2_calc_max_out_buf_len(work,
+			offsetof(struct smb2_query_info_rsp, Buffer) +
+			offsetof(struct smb2_file_all_info, FileName),
+			le32_to_cpu(req->OutputBufferLength));
+	if (buf_free_len < (filename_len + 1) * 2) {
+		kfree(filename);
+		return -EINVAL;
+	}
+
 	ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS,
 			  AT_STATX_SYNC_AS_STAT);
 	if (ret) {
@@ -4995,7 +5006,8 @@ static int get_file_all_info(struct ksmbd_work *work,
 	file_info->Mode = fp->coption;
 	file_info->AlignmentRequirement = 0;
 	conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename,
-				     PATH_MAX, conn->local_nls, 0);
+				     min(filename_len, PATH_MAX),
+				     conn->local_nls, 0);
 	conv_len *= 2;
 	file_info->FileNameLength = cpu_to_le32(conv_len);
 	rsp->OutputBufferLength =
-- 
cgit v1.2.3


From 4c56a8ac6869855866de0bb368a4189739e1d24f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 25 Mar 2026 07:23:48 -1000
Subject: cgroup: Fix cgroup_drain_dying() testing the wrong condition

cgroup_drain_dying() was using cgroup_is_populated() to test whether there are
dying tasks to wait for. cgroup_is_populated() tests nr_populated_csets,
nr_populated_domain_children and nr_populated_threaded_children, but
cgroup_drain_dying() only needs to care about this cgroup's own tasks - whether
there are children is cgroup_destroy_locked()'s concern.

This caused hangs during shutdown. When systemd tried to rmdir a cgroup that had
no direct tasks but had a populated child, cgroup_drain_dying() would enter its
wait loop because cgroup_is_populated() was true from
nr_populated_domain_children. The task iterator found nothing to wait for, yet
the populated state never cleared because it was driven by live tasks in the
child cgroup.

Fix it by using cgroup_has_tasks() which only tests nr_populated_csets.

v3: Fix cgroup_is_populated() -> cgroup_has_tasks() (Sebastian).

v2: https://lore.kernel.org/r/20260323200205.1063629-1-tj@kernel.org

Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Fixes: 1b164b876c36 ("cgroup: Wait for dying tasks to leave on rmdir")
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 kernel/cgroup/cgroup.c | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 2163054e1aa6..4ca3cb993da2 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6229,20 +6229,22 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
  * cgroup_drain_dying - wait for dying tasks to leave before rmdir
  * @cgrp: the cgroup being removed
  *
- * The PF_EXITING filter in css_task_iter_advance() hides exiting tasks from
- * cgroup.procs so that userspace (e.g. systemd) doesn't see tasks that have
- * already been reaped via waitpid(). However, the populated counter
- * (nr_populated_csets) is only decremented when the task later passes through
+ * cgroup.procs and cgroup.threads use css_task_iter which filters out
+ * PF_EXITING tasks so that userspace doesn't see tasks that have already been
+ * reaped via waitpid(). However, cgroup_has_tasks() - which tests whether the
+ * cgroup has non-empty css_sets - is only updated when dying tasks pass through
  * cgroup_task_dead() in finish_task_switch(). This creates a window where
- * cgroup.procs appears empty but cgroup_is_populated() is still true, causing
- * rmdir to fail with -EBUSY.
+ * cgroup.procs reads empty but cgroup_has_tasks() is still true, making rmdir
+ * fail with -EBUSY from cgroup_destroy_locked() even though userspace sees no
+ * tasks.
+ *
+ * This function aligns cgroup_has_tasks() with what userspace can observe. If
+ * cgroup_has_tasks() but the task iterator sees nothing (all remaining tasks are
+ * PF_EXITING), we wait for cgroup_task_dead() to finish processing them. As the
+ * window between PF_EXITING and cgroup_task_dead() is short, the wait is brief.
  *
- * This function bridges that gap. If the cgroup is populated but all remaining
- * tasks have PF_EXITING set, we wait for cgroup_task_dead() to process them.
- * Tasks are removed from the cgroup's css_set in cgroup_task_dead() called from
- * finish_task_switch(). As the window between PF_EXITING and cgroup_task_dead()
- * is short, the number of PF_EXITING tasks on the list is small and the wait
- * is brief.
+ * This function only concerns itself with this cgroup's own dying tasks.
+ * Whether the cgroup has children is cgroup_destroy_locked()'s problem.
  *
  * Each cgroup_task_dead() kicks the waitqueue via cset->cgrp_links, and we
  * retry the full check from scratch.
@@ -6258,7 +6260,7 @@ static int cgroup_drain_dying(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 retry:
-	if (!cgroup_is_populated(cgrp))
+	if (!cgroup_has_tasks(cgrp))
 		return 0;
 
 	/* Same iterator as cgroup.threads - if any task is visible, it's busy */
@@ -6273,15 +6275,15 @@ retry:
 	 * All remaining tasks are PF_EXITING and will pass through
 	 * cgroup_task_dead() shortly. Wait for a kick and retry.
 	 *
-	 * cgroup_is_populated() can't transition from false to true while
-	 * we're holding cgroup_mutex, but the true to false transition
-	 * happens under css_set_lock (via cgroup_task_dead()). We must
-	 * retest and prepare_to_wait() under css_set_lock. Otherwise, the
-	 * transition can happen between our first test and
-	 * prepare_to_wait(), and we sleep with no one to wake us.
+	 * cgroup_has_tasks() can't transition from false to true while we're
+	 * holding cgroup_mutex, but the true to false transition happens
+	 * under css_set_lock (via cgroup_task_dead()). We must retest and
+	 * prepare_to_wait() under css_set_lock. Otherwise, the transition
+	 * can happen between our first test and prepare_to_wait(), and we
+	 * sleep with no one to wake us.
 	 */
 	spin_lock_irq(&css_set_lock);
-	if (!cgroup_is_populated(cgrp)) {
+	if (!cgroup_has_tasks(cgrp)) {
 		spin_unlock_irq(&css_set_lock);
 		return 0;
 	}
-- 
cgit v1.2.3


From 3a28daa9b7d7c2ddf2c722e9e95d7e0928bf0cd1 Mon Sep 17 00:00:00 2001
From: Li Jun <lijun01@kylinos.cn>
Date: Thu, 26 Mar 2026 14:29:08 +0800
Subject: LoongArch: Fix missing NULL checks for kstrdup()

1. Replace "of_find_node_by_path("/")" with "of_root" to avoid multiple
calls to "of_node_put()".

2. Fix a potential kernel oops during early boot when memory allocation
fails while parsing CPU model from device tree.

Cc: stable@vger.kernel.org
Signed-off-by: Li Jun <lijun01@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/env.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 841206fde3ab..652456768b55 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -42,16 +42,15 @@ static int __init init_cpu_fullname(void)
 	int cpu, ret;
 	char *cpuname;
 	const char *model;
-	struct device_node *root;
 
 	/* Parsing cpuname from DTS model property */
-	root = of_find_node_by_path("/");
-	ret = of_property_read_string(root, "model", &model);
+	ret = of_property_read_string(of_root, "model", &model);
 	if (ret == 0) {
 		cpuname = kstrdup(model, GFP_KERNEL);
+		if (!cpuname)
+			return -ENOMEM;
 		loongson_sysconf.cpuname = strsep(&cpuname, " ");
 	}
-	of_node_put(root);
 
 	if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) {
 		for (cpu = 0; cpu < NR_CPUS; cpu++)
-- 
cgit v1.2.3


From 95db0c9f526d583634cddb2e5914718570fbac87 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Thu, 26 Mar 2026 14:29:09 +0800
Subject: LoongArch: Workaround LS2K/LS7A GPU DMA hang bug

1. Hardware limitation: GPU, DC and VPU are typically PCI device 06.0,
06.1 and 06.2. They share some hardware resources, so when configure the
PCI 06.0 device BAR1, DMA memory access cannot be performed through this
BAR, otherwise it will cause hardware abnormalities.

2. In typical scenarios of reboot or S3/S4, DC access to memory through
BAR is not prohibited, resulting in GPU DMA hangs.

3. Workaround method: When configuring the 06.0 device BAR1, turn off
the memory access of DC, GPU and VPU (via DC's CRTC registers).

Cc: stable@vger.kernel.org
Signed-off-by: Qianhai Wu <wuqianhai@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/pci/pci.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 80 insertions(+)

diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c
index d923295ab8c6..d233ea2218fe 100644
--- a/arch/loongarch/pci/pci.c
+++ b/arch/loongarch/pci/pci.c
@@ -5,9 +5,11 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/vgaarb.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/cacheflush.h>
 #include <asm/loongson.h>
 
@@ -15,6 +17,9 @@
 #define PCI_DEVICE_ID_LOONGSON_DC1      0x7a06
 #define PCI_DEVICE_ID_LOONGSON_DC2      0x7a36
 #define PCI_DEVICE_ID_LOONGSON_DC3      0x7a46
+#define PCI_DEVICE_ID_LOONGSON_GPU1     0x7a15
+#define PCI_DEVICE_ID_LOONGSON_GPU2     0x7a25
+#define PCI_DEVICE_ID_LOONGSON_GPU3     0x7a35
 
 int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val)
@@ -99,3 +104,78 @@ static void pci_fixup_vgadev(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC1, pci_fixup_vgadev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC2, pci_fixup_vgadev);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_DC3, pci_fixup_vgadev);
+
+#define CRTC_NUM_MAX		2
+#define CRTC_OUTPUT_ENABLE	0x100
+
+static void loongson_gpu_fixup_dma_hang(struct pci_dev *pdev, bool on)
+{
+	u32 i, val, count, crtc_offset, device;
+	void __iomem *crtc_reg, *base, *regbase;
+	static u32 crtc_status[CRTC_NUM_MAX] = { 0 };
+
+	base = pdev->bus->ops->map_bus(pdev->bus, pdev->devfn + 1, 0);
+	device = readw(base + PCI_DEVICE_ID);
+
+	regbase = ioremap(readq(base + PCI_BASE_ADDRESS_0) & ~0xffull, SZ_64K);
+	if (!regbase) {
+		pci_err(pdev, "Failed to ioremap()\n");
+		return;
+	}
+
+	switch (device) {
+	case PCI_DEVICE_ID_LOONGSON_DC2:
+		crtc_reg = regbase + 0x1240;
+		crtc_offset = 0x10;
+		break;
+	case PCI_DEVICE_ID_LOONGSON_DC3:
+		crtc_reg = regbase;
+		crtc_offset = 0x400;
+		break;
+	}
+
+	for (i = 0; i < CRTC_NUM_MAX; i++, crtc_reg += crtc_offset) {
+		val = readl(crtc_reg);
+
+		if (!on)
+			crtc_status[i] = val;
+
+		/* No need to fixup if the status is off at startup. */
+		if (!(crtc_status[i] & CRTC_OUTPUT_ENABLE))
+			continue;
+
+		if (on)
+			val |= CRTC_OUTPUT_ENABLE;
+		else
+			val &= ~CRTC_OUTPUT_ENABLE;
+
+		mb();
+		writel(val, crtc_reg);
+
+		for (count = 0; count < 40; count++) {
+			val = readl(crtc_reg) & CRTC_OUTPUT_ENABLE;
+			if ((on && val) || (!on && !val))
+				break;
+			udelay(1000);
+		}
+
+		pci_info(pdev, "DMA hang fixup at reg[0x%lx]: 0x%x\n",
+				(unsigned long)crtc_reg & 0xffff, readl(crtc_reg));
+	}
+
+	iounmap(regbase);
+}
+
+static void pci_fixup_dma_hang_early(struct pci_dev *pdev)
+{
+	loongson_gpu_fixup_dma_hang(pdev, false);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_early);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_early);
+
+static void pci_fixup_dma_hang_final(struct pci_dev *pdev)
+{
+	loongson_gpu_fixup_dma_hang(pdev, true);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU2, pci_fixup_dma_hang_final);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, PCI_DEVICE_ID_LOONGSON_GPU3, pci_fixup_dma_hang_final);
-- 
cgit v1.2.3


From e4878c37f6679fdea91b27a0f4e60a871f0b7bad Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Thu, 26 Mar 2026 14:29:09 +0800
Subject: LoongArch: vDSO: Emit GNU_EH_FRAME correctly

With -fno-asynchronous-unwind-tables and --no-eh-frame-hdr (the default
of the linker), the GNU_EH_FRAME segment (specified by vdso.lds.S) is
empty.  This is not valid, as the current DWARF specification mandates
the first byte of the EH frame to be the version number 1.  It causes
some unwinders to complain, for example the ClickHouse query profiler
spams the log with messages:

    clickhouse-server[365854]: libunwind: unsupported .eh_frame_hdr
    version: 127 at 7ffffffb0000

Here "127" is just the byte located at the p_vaddr (0, i.e. the
beginning of the vDSO) of the empty GNU_EH_FRAME segment. Cross-
checking with /proc/365854/maps has also proven 7ffffffb0000 is the
start of vDSO in the process VM image.

In LoongArch the -fno-asynchronous-unwind-tables option seems just a
MIPS legacy, and MIPS only uses this option to satisfy the MIPS-specific
"genvdso" program, per the commit cfd75c2db17e ("MIPS: VDSO: Explicitly
use -fno-asynchronous-unwind-tables").  IIRC it indicates some inherent
limitation of the MIPS ELF ABI and has nothing to do with LoongArch.  So
we can simply flip it over to -fasynchronous-unwind-tables and pass
--eh-frame-hdr for linking the vDSO, allowing the profilers to unwind the
stack for statistics even if the sample point is taken when the PC is in
the vDSO.

However simply adjusting the options above would exploit an issue: when
the libgcc unwinder saw the invalid GNU_EH_FRAME segment, it silently
falled back to a machine-specific routine to match the code pattern of
rt_sigreturn() and extract the registers saved in the sigframe if the
code pattern is matched.  As unwinding from signal handlers is vital for
libgcc to support pthread cancellation etc., the fall-back routine had
been silently keeping the LoongArch Linux systems functioning since
Linux 5.19.  But when we start to emit GNU_EH_FRAME with the correct
format, fall-back routine will no longer be used and libgcc will fail
to unwind the sigframe, and unwinding from signal handlers will no
longer work, causing dozens of glibc test failures.  To make it possible
to unwind from signal handlers again, it's necessary to code the unwind
info in __vdso_rt_sigreturn via .cfi_* directives.

The offsets in the .cfi_* directives depend on the layout of struct
sigframe, notably the offset of sigcontext in the sigframe.  To use the
offset in the assembly file, factor out struct sigframe into a header to
allow asm-offsets.c to output the offset for assembly.

To work around a long-term issue in the libgcc unwinder (the pc is
unconditionally substracted by 1: doing so is technically incorrect for
a signal frame), a nop instruction is included with the two real
instructions in __vdso_rt_sigreturn in the same FDE PC range.  The same
hack has been used on x86 for a long time.

Cc: stable@vger.kernel.org
Fixes: c6b99bed6b8f ("LoongArch: Add VDSO and VSYSCALL support")
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/linkage.h  | 36 +++++++++++++++++++++++++++++++++++
 arch/loongarch/include/asm/sigframe.h |  9 +++++++++
 arch/loongarch/kernel/asm-offsets.c   |  2 ++
 arch/loongarch/kernel/signal.c        |  6 +-----
 arch/loongarch/vdso/Makefile          |  4 ++--
 arch/loongarch/vdso/sigreturn.S       |  6 +++---
 6 files changed, 53 insertions(+), 10 deletions(-)
 create mode 100644 arch/loongarch/include/asm/sigframe.h

diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h
index e2eca1a25b4e..a1bd6a3ee03a 100644
--- a/arch/loongarch/include/asm/linkage.h
+++ b/arch/loongarch/include/asm/linkage.h
@@ -41,4 +41,40 @@
 	.cfi_endproc;					\
 	SYM_END(name, SYM_T_NONE)
 
+/*
+ * This is for the signal handler trampoline, which is used as the return
+ * address of the signal handlers in userspace instead of called normally.
+ * The long standing libgcc bug https://gcc.gnu.org/PR124050 requires a
+ * nop between .cfi_startproc and the actual address of the trampoline, so
+ * we cannot simply use SYM_FUNC_START.
+ *
+ * This wrapper also contains all the .cfi_* directives for recovering
+ * the content of the GPRs and the "return address" (where the rt_sigreturn
+ * syscall will jump to), assuming there is a struct rt_sigframe (where
+ * a struct sigcontext containing those information we need to recover) at
+ * $sp.  The "DWARF for the LoongArch(TM) Architecture" manual states
+ * column 0 is for $zero, but it does not make too much sense to
+ * save/restore the hardware zero register.  Repurpose this column here
+ * for the return address (here it's not the content of $ra we cannot use
+ * the default column 3).
+ */
+#define SYM_SIGFUNC_START(name)				\
+	.cfi_startproc;					\
+	.cfi_signal_frame;				\
+	.cfi_def_cfa 3, RT_SIGFRAME_SC;			\
+	.cfi_return_column 0;				\
+	.cfi_offset 0, SC_PC;				\
+							\
+	.irp num, 1,  2,  3,  4,  5,  6,  7,  8, 	\
+		  9,  10, 11, 12, 13, 14, 15, 16,	\
+		  17, 18, 19, 20, 21, 22, 23, 24,	\
+		  25, 26, 27, 28, 29, 30, 31;		\
+	.cfi_offset \num, SC_REGS + \num * SZREG;	\
+	.endr;						\
+							\
+	nop;						\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+
+#define SYM_SIGFUNC_END(name) SYM_FUNC_END(name)
+
 #endif
diff --git a/arch/loongarch/include/asm/sigframe.h b/arch/loongarch/include/asm/sigframe.h
new file mode 100644
index 000000000000..109298b8d7e0
--- /dev/null
+++ b/arch/loongarch/include/asm/sigframe.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#include <asm/siginfo.h>
+#include <asm/ucontext.h>
+
+struct rt_sigframe {
+	struct siginfo rs_info;
+	struct ucontext rs_uctx;
+};
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 3017c7157600..2cc953f113ac 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/ftrace.h>
+#include <asm/sigframe.h>
 #include <vdso/datapage.h>
 
 static void __used output_ptreg_defines(void)
@@ -220,6 +221,7 @@ static void __used output_sc_defines(void)
 	COMMENT("Linux sigcontext offsets.");
 	OFFSET(SC_REGS, sigcontext, sc_regs);
 	OFFSET(SC_PC, sigcontext, sc_pc);
+	OFFSET(RT_SIGFRAME_SC, rt_sigframe, rs_uctx.uc_mcontext);
 	BLANK();
 }
 
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index c9f7ca778364..d4151d2fb82e 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -35,6 +35,7 @@
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
 #include <asm/lbt.h>
+#include <asm/sigframe.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
 
@@ -51,11 +52,6 @@
 #define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
-struct rt_sigframe {
-	struct siginfo rs_info;
-	struct ucontext rs_uctx;
-};
-
 struct _ctx_layout {
 	struct sctx_info *addr;
 	unsigned int size;
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index 520f1513f07d..294c16b9517f 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -26,7 +26,7 @@ cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-std=gnu11 -fms-extensions -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
 	-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
-	$(call cc-option, -fno-asynchronous-unwind-tables) \
+	$(call cc-option, -fasynchronous-unwind-tables) \
 	$(call cc-option, -fno-stack-protector)
 aflags-vdso := $(ccflags-vdso) \
 	-D__ASSEMBLY__ -Wa,-gdwarf-2
@@ -41,7 +41,7 @@ endif
 
 # VDSO linker flags.
 ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
-	$(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id -T
+	$(filter -E%,$(KBUILD_CFLAGS)) -shared --build-id --eh-frame-hdr -T
 
 #
 # Shared build commands.
diff --git a/arch/loongarch/vdso/sigreturn.S b/arch/loongarch/vdso/sigreturn.S
index 9cb3c58fad03..59f940d928de 100644
--- a/arch/loongarch/vdso/sigreturn.S
+++ b/arch/loongarch/vdso/sigreturn.S
@@ -12,13 +12,13 @@
 
 #include <asm/regdef.h>
 #include <asm/asm.h>
+#include <asm/asm-offsets.h>
 
 	.section	.text
-	.cfi_sections	.debug_frame
 
-SYM_FUNC_START(__vdso_rt_sigreturn)
+SYM_SIGFUNC_START(__vdso_rt_sigreturn)
 
 	li.w	a7, __NR_rt_sigreturn
 	syscall	0
 
-SYM_FUNC_END(__vdso_rt_sigreturn)
+SYM_SIGFUNC_END(__vdso_rt_sigreturn)
-- 
cgit v1.2.3


From 2db06c15d8c7a0ccb6108524e16cd9163753f354 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Thu, 26 Mar 2026 14:29:09 +0800
Subject: LoongArch: KVM: Make kvm_get_vcpu_by_cpuid() more robust

kvm_get_vcpu_by_cpuid() takes a cpuid parameter whose type is int, so
cpuid can be negative. Let kvm_get_vcpu_by_cpuid() return NULL for this
case so as to make it more robust.

This fix an out-of-bounds access to kvm_arch::phyid_map::phys_map[].

Cc: <stable@vger.kernel.org>
Fixes: 73516e9da512adc ("LoongArch: KVM: Add vcpu mapping from physical cpuid")
Reported-by: Aurelien Jarno <aurel32@debian.org>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1131431
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/vcpu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 8ffd50a470e6..831f381a8fd1 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -588,6 +588,9 @@ struct kvm_vcpu *kvm_get_vcpu_by_cpuid(struct kvm *kvm, int cpuid)
 {
 	struct kvm_phyid_map *map;
 
+	if (cpuid < 0)
+		return NULL;
+
 	if (cpuid >= KVM_MAX_PHYID)
 		return NULL;
 
-- 
cgit v1.2.3


From b97bd69eb0f67b5f961b304d28e9ba45e202d841 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Thu, 26 Mar 2026 14:29:09 +0800
Subject: LoongArch: KVM: Handle the case that EIOINTC's coremap is empty

EIOINTC's coremap in eiointc_update_sw_coremap() can be empty, currently
we get a cpuid with -1 in this case, but we actually need 0 because it's
similar as the case that cpuid >= 4.

This fix an out-of-bounds access to kvm_arch::phyid_map::phys_map[].

Cc: <stable@vger.kernel.org>
Fixes: 3956a52bc05bd81 ("LoongArch: KVM: Add EIOINTC read and write functions")
Reported-by: Aurelien Jarno <aurel32@debian.org>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1131431
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index d2acb4d09e73..c7badc813923 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -83,7 +83,7 @@ static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s,
 
 		if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) {
 			cpuid = ffs(cpuid) - 1;
-			cpuid = (cpuid >= 4) ? 0 : cpuid;
+			cpuid = ((cpuid < 0) || (cpuid >= 4)) ? 0 : cpuid;
 		}
 
 		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
-- 
cgit v1.2.3


From 6bcfb7f46d667b04bd1a1169ccedf5fb699c60df Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Thu, 26 Mar 2026 14:29:09 +0800
Subject: LoongArch: KVM: Fix base address calculation in
 kvm_eiointc_regs_access()

In function kvm_eiointc_regs_access(), the register base address is
caculated from array base address plus offset, the offset is absolute
value from the base address. The data type of array base address is
u64, it should be converted into the "void *" type and then plus the
offset.

Cc: <stable@vger.kernel.org>
Fixes: d3e43a1f34ac ("LoongArch: KVM: Use 64-bit register definition for EIOINTC").
Reported-by: Aurelien Jarno <aurel32@debian.org>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1131431
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index c7badc813923..003bd773e11c 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -472,34 +472,34 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 	switch (addr) {
 	case EIOINTC_NODETYPE_START ... EIOINTC_NODETYPE_END:
 		offset = (addr - EIOINTC_NODETYPE_START) / 4;
-		p = s->nodetype + offset * 4;
+		p = (void *)s->nodetype + offset * 4;
 		break;
 	case EIOINTC_IPMAP_START ... EIOINTC_IPMAP_END:
 		offset = (addr - EIOINTC_IPMAP_START) / 4;
-		p = &s->ipmap + offset * 4;
+		p = (void *)&s->ipmap + offset * 4;
 		break;
 	case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END:
 		offset = (addr - EIOINTC_ENABLE_START) / 4;
-		p = s->enable + offset * 4;
+		p = (void *)s->enable + offset * 4;
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
 		offset = (addr - EIOINTC_BOUNCE_START) / 4;
-		p = s->bounce + offset * 4;
+		p = (void *)s->bounce + offset * 4;
 		break;
 	case EIOINTC_ISR_START ... EIOINTC_ISR_END:
 		offset = (addr - EIOINTC_ISR_START) / 4;
-		p = s->isr + offset * 4;
+		p = (void *)s->isr + offset * 4;
 		break;
 	case EIOINTC_COREISR_START ... EIOINTC_COREISR_END:
 		if (cpu >= s->num_cpu)
 			return -EINVAL;
 
 		offset = (addr - EIOINTC_COREISR_START) / 4;
-		p = s->coreisr[cpu] + offset * 4;
+		p = (void *)s->coreisr[cpu] + offset * 4;
 		break;
 	case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END:
 		offset = (addr - EIOINTC_COREMAP_START) / 4;
-		p = s->coremap + offset * 4;
+		p = (void *)s->coremap + offset * 4;
 		break;
 	default:
 		kvm_err("%s: unknown eiointc register, addr = %d\n", __func__, addr);
-- 
cgit v1.2.3


From cd7e1fef5a1ca1c4fcd232211962ac2395601636 Mon Sep 17 00:00:00 2001
From: GuoHan Zhao <zhaoguohan@kylinos.cn>
Date: Wed, 25 Mar 2026 20:02:46 +0800
Subject: xen/privcmd: unregister xenstore notifier on module exit

Commit 453b8fb68f36 ("xen/privcmd: restrict usage in
unprivileged domU") added a xenstore notifier to defer setting the
restriction target until Xenstore is ready.

XEN_PRIVCMD can be built as a module, but privcmd_exit() leaves that
notifier behind. Balance the notifier lifecycle by unregistering it on
module exit.

This is harmless even if xenstore was already ready at registration
time and the notifier was never queued on the chain.

Fixes: 453b8fb68f3641fe ("xen/privcmd: restrict usage in unprivileged domU")
Signed-off-by: GuoHan Zhao <zhaoguohan@kylinos.cn>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20260325120246.252899-1-zhaoguohan@kylinos.cn>
---
 drivers/xen/privcmd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index bbf9ee21306c..15ba592236e8 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1765,6 +1765,9 @@ err_privcmdbuf:
 
 static void __exit privcmd_exit(void)
 {
+	if (!xen_initial_domain())
+		unregister_xenstore_notifier(&xenstore_notifier);
+
 	privcmd_ioeventfd_exit();
 	privcmd_irqfd_exit();
 	misc_deregister(&privcmd_dev);
-- 
cgit v1.2.3


From d0b224cf9ab12e86a4d1ca55c760dfaa5c19cbe7 Mon Sep 17 00:00:00 2001
From: Aldo Conte <aldocontelk@gmail.com>
Date: Wed, 25 Mar 2026 12:32:16 +0100
Subject: iio: light: veml6070: fix veml6070_read() return value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

veml6070_read() computes the sensor value in ret but
returns 0 instead of the actual result. This causes
veml6070_read_raw() to always report 0.

Return the computed value instead of 0.

Running make W=1 returns no errors. I was unable
to test the patch because I do not have the hardware.
Found by code inspection.

Fixes: fc38525135dd ("iio: light: veml6070: use guard to handle mutex")
Signed-off-by: Aldo Conte <aldocontelk@gmail.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/veml6070.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/iio/light/veml6070.c b/drivers/iio/light/veml6070.c
index 6d4483c85f30..74d7246e5225 100644
--- a/drivers/iio/light/veml6070.c
+++ b/drivers/iio/light/veml6070.c
@@ -134,9 +134,7 @@ static int veml6070_read(struct veml6070_data *data)
 	if (ret < 0)
 		return ret;
 
-	ret = (msb << 8) | lsb;
-
-	return 0;
+	return (msb << 8) | lsb;
 }
 
 static const struct iio_chan_spec veml6070_channels[] = {
-- 
cgit v1.2.3


From f63a9df7e3f9f842945d292a19d9938924f066f9 Mon Sep 17 00:00:00 2001
From: Marc Buerg <buermarc@googlemail.com>
Date: Wed, 25 Mar 2026 23:29:50 +0100
Subject: sysctl: fix uninitialized variable in proc_do_large_bitmap

proc_do_large_bitmap() does not initialize variable c, which is expected
to be set to a trailing character by proc_get_long().

However, proc_get_long() only sets c when the input buffer contains a
trailing character after the parsed value.

If c is not initialized it may happen to contain a '-'. If this is the
case proc_do_large_bitmap() expects to be able to parse a second part of
the input buffer. If there is no second part an unjustified -EINVAL will
be returned.

Initialize c to 0 to prevent returning -EINVAL on valid input.

Fixes: 9f977fb7ae9d ("sysctl: add proc_do_large_bitmap")
Signed-off-by: Marc Buerg <buermarc@googlemail.com>
Reviewed-by: Joel Granados <joel.granados@kernel.org>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 kernel/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9d3a666ffde1..c9efb17cc255 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1118,7 +1118,7 @@ int proc_do_large_bitmap(const struct ctl_table *table, int dir,
 	unsigned long bitmap_len = table->maxlen;
 	unsigned long *bitmap = *(unsigned long **) table->data;
 	unsigned long *tmp_bitmap = NULL;
-	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
+	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c = 0;
 
 	if (!bitmap || !bitmap_len || !left || (*ppos && SYSCTL_KERN_TO_USER(dir))) {
 		*lenp = 0;
-- 
cgit v1.2.3


From c720fb57d56274213d027b3c5ab99080cf62a306 Mon Sep 17 00:00:00 2001
From: Shenwei Wang <shenwei.wang@nxp.com>
Date: Tue, 24 Mar 2026 14:21:29 -0500
Subject: gpio: mxc: map Both Edge pad wakeup to Rising Edge

Suspend may fail on i.MX8QM when Falling Edge is used as a pad wakeup
trigger due to a hardware bug in the detection logic. Since the hardware
does not support Both Edge wakeup, remap requests for Both Edge to Rising
Edge by default to avoid hitting this issue.

A warning is emitted when Falling Edge is selected on i.MX8QM.

Fixes: f60c9eac54af ("gpio: mxc: enable pad wakeup on i.MX8x platforms")
cc: stable@vger.kernel.org
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Shenwei Wang <shenwei.wang@nxp.com>
Link: https://patch.msgid.link/20260324192129.2797237-1-shenwei.wang@nxp.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpio-mxc.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index d7666fe9dbf8..647b6f4861b7 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -584,12 +584,13 @@ static bool mxc_gpio_set_pad_wakeup(struct mxc_gpio_port *port, bool enable)
 	unsigned long config;
 	bool ret = false;
 	int i, type;
+	bool is_imx8qm = of_device_is_compatible(port->dev->of_node, "fsl,imx8qm-gpio");
 
 	static const u32 pad_type_map[] = {
 		IMX_SCU_WAKEUP_OFF,		/* 0 */
 		IMX_SCU_WAKEUP_RISE_EDGE,	/* IRQ_TYPE_EDGE_RISING */
 		IMX_SCU_WAKEUP_FALL_EDGE,	/* IRQ_TYPE_EDGE_FALLING */
-		IMX_SCU_WAKEUP_FALL_EDGE,	/* IRQ_TYPE_EDGE_BOTH */
+		IMX_SCU_WAKEUP_RISE_EDGE,	/* IRQ_TYPE_EDGE_BOTH */
 		IMX_SCU_WAKEUP_HIGH_LVL,	/* IRQ_TYPE_LEVEL_HIGH */
 		IMX_SCU_WAKEUP_OFF,		/* 5 */
 		IMX_SCU_WAKEUP_OFF,		/* 6 */
@@ -604,6 +605,13 @@ static bool mxc_gpio_set_pad_wakeup(struct mxc_gpio_port *port, bool enable)
 				config = pad_type_map[type];
 			else
 				config = IMX_SCU_WAKEUP_OFF;
+
+			if (is_imx8qm && config == IMX_SCU_WAKEUP_FALL_EDGE) {
+				dev_warn_once(port->dev,
+					      "No falling-edge support for wakeup on i.MX8QM\n");
+				config = IMX_SCU_WAKEUP_OFF;
+			}
+
 			ret |= mxc_gpio_generic_config(port, i, config);
 		}
 	}
-- 
cgit v1.2.3


From 84a8335d8300576f1b377ae24abca1d9f197807f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 24 Mar 2026 08:53:23 -0400
Subject: tls: Purge async_hold in tls_decrypt_async_wait()

The async_hold queue pins encrypted input skbs while
the AEAD engine references their scatterlist data. Once
tls_decrypt_async_wait() returns, every AEAD operation
has completed and the engine no longer references those
skbs, so they can be freed unconditionally.

A subsequent patch adds batch async decryption to
tls_sw_read_sock(), introducing a new call site that
must drain pending AEAD operations and release held
skbs. Move __skb_queue_purge(&ctx->async_hold) into
tls_decrypt_async_wait() so the purge is centralized
and every caller -- recvmsg's drain path, the -EBUSY
fallback in tls_do_decryption(), and the new read_sock
batch path -- releases held skbs on synchronization
without each site managing the purge independently.

This fixes a leak when tls_strp_msg_hold() fails part-way through,
after having added some cloned skbs to the async_hold
queue. tls_decrypt_sg() will then call tls_decrypt_async_wait() to
process all pending decrypts, and drop back to synchronous mode, but
tls_sw_recvmsg() only flushes the async_hold queue when one record has
been processed in "fully-async" mode, which may not be the case here.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Fixes: b8a6ff84abbc ("tls: wait for pending async decryptions if tls_strp_msg_hold fails")
Link: https://patch.msgid.link/20260324-tls-read-sock-v5-1-5408befe5774@oracle.com
[pabeni@redhat.com: added leak comment]
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5fe07f110fe8..dd9dda759bbb 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -246,6 +246,7 @@ static int tls_decrypt_async_wait(struct tls_sw_context_rx *ctx)
 		crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
 	atomic_inc(&ctx->decrypt_pending);
 
+	__skb_queue_purge(&ctx->async_hold);
 	return ctx->async_wait.err;
 }
 
@@ -2225,7 +2226,6 @@ recv_end:
 
 		/* Wait for all previously submitted records to be decrypted */
 		ret = tls_decrypt_async_wait(ctx);
-		__skb_queue_purge(&ctx->async_hold);
 
 		if (ret) {
 			if (err >= 0 || err == -EINPROGRESS)
-- 
cgit v1.2.3


From 4b56770d345524fc2acc143a2b85539cf7d74bc1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 16 Mar 2026 13:21:19 -0700
Subject: crypto: tegra - Add missing CRYPTO_ALG_ASYNC

The tegra crypto driver failed to set the CRYPTO_ALG_ASYNC on its
asynchronous algorithms, causing the crypto API to select them for users
that request only synchronous algorithms.  This causes crashes (at
least).  Fix this by adding the flag like what the other drivers do.
Also remove the unnecessary CRYPTO_ALG_TYPE_* flags, since those just
get ignored and overridden by the registration function anyway.

Reported-by: Zorro Lang <zlang@redhat.com>
Closes: https://lore.kernel.org/r/20260314080937.pghb4aa7d4je3mhh@dell-per750-06-vm-08.rhts.eng.pek2.redhat.com
Fixes: 0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Cc: stable@vger.kernel.org
Cc: Akhil R <akhilrajeev@nvidia.com>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/tegra/tegra-se-aes.c  | 11 +++++++----
 drivers/crypto/tegra/tegra-se-hash.c | 30 +++++++++++++++++-------------
 2 files changed, 24 insertions(+), 17 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index 0e07d0523291..9210cceb4b7b 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -529,7 +529,7 @@ static struct tegra_se_alg tegra_aes_algs[] = {
 				.cra_name = "cbc(aes)",
 				.cra_driver_name = "cbc-aes-tegra",
 				.cra_priority = 500,
-				.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_aes_ctx),
 				.cra_alignmask = 0xf,
@@ -550,7 +550,7 @@ static struct tegra_se_alg tegra_aes_algs[] = {
 				.cra_name = "ecb(aes)",
 				.cra_driver_name = "ecb-aes-tegra",
 				.cra_priority = 500,
-				.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_aes_ctx),
 				.cra_alignmask = 0xf,
@@ -572,7 +572,7 @@ static struct tegra_se_alg tegra_aes_algs[] = {
 				.cra_name = "ctr(aes)",
 				.cra_driver_name = "ctr-aes-tegra",
 				.cra_priority = 500,
-				.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = 1,
 				.cra_ctxsize = sizeof(struct tegra_aes_ctx),
 				.cra_alignmask = 0xf,
@@ -594,6 +594,7 @@ static struct tegra_se_alg tegra_aes_algs[] = {
 				.cra_name = "xts(aes)",
 				.cra_driver_name = "xts-aes-tegra",
 				.cra_priority = 500,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_ctxsize	   = sizeof(struct tegra_aes_ctx),
 				.cra_alignmask	   = (__alignof__(u64) - 1),
@@ -1922,6 +1923,7 @@ static struct tegra_se_alg tegra_aead_algs[] = {
 				.cra_name = "gcm(aes)",
 				.cra_driver_name = "gcm-aes-tegra",
 				.cra_priority = 500,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = 1,
 				.cra_ctxsize = sizeof(struct tegra_aead_ctx),
 				.cra_alignmask = 0xf,
@@ -1944,6 +1946,7 @@ static struct tegra_se_alg tegra_aead_algs[] = {
 				.cra_name = "ccm(aes)",
 				.cra_driver_name = "ccm-aes-tegra",
 				.cra_priority = 500,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = 1,
 				.cra_ctxsize = sizeof(struct tegra_aead_ctx),
 				.cra_alignmask = 0xf,
@@ -1971,7 +1974,7 @@ static struct tegra_se_alg tegra_cmac_algs[] = {
 				.cra_name = "cmac(aes)",
 				.cra_driver_name = "tegra-se-cmac",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = AES_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_cmac_ctx),
 				.cra_alignmask = 0,
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index 4a298ace6e9f..06bb5bf0fa33 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -761,7 +761,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha1",
 				.cra_driver_name = "tegra-se-sha1",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -786,7 +786,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha224",
 				.cra_driver_name = "tegra-se-sha224",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -811,7 +811,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha256",
 				.cra_driver_name = "tegra-se-sha256",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -836,7 +836,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha384",
 				.cra_driver_name = "tegra-se-sha384",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA384_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -861,7 +861,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha512",
 				.cra_driver_name = "tegra-se-sha512",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA512_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -886,7 +886,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha3-224",
 				.cra_driver_name = "tegra-se-sha3-224",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA3_224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -911,7 +911,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha3-256",
 				.cra_driver_name = "tegra-se-sha3-256",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA3_256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -936,7 +936,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha3-384",
 				.cra_driver_name = "tegra-se-sha3-384",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA3_384_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -961,7 +961,7 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "sha3-512",
 				.cra_driver_name = "tegra-se-sha3-512",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA3_512_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -988,7 +988,8 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "tegra-se-hmac-sha224",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -1015,7 +1016,8 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "tegra-se-hmac-sha256",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -1042,7 +1044,8 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "hmac(sha384)",
 				.cra_driver_name = "tegra-se-hmac-sha384",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK,
 				.cra_blocksize = SHA384_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
@@ -1069,7 +1072,8 @@ static struct tegra_se_alg tegra_hash_algs[] = {
 				.cra_name = "hmac(sha512)",
 				.cra_driver_name = "tegra-se-hmac-sha512",
 				.cra_priority = 300,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_NEED_FALLBACK,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_NEED_FALLBACK,
 				.cra_blocksize = SHA512_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct tegra_sha_ctx),
 				.cra_alignmask = 0,
-- 
cgit v1.2.3


From 5ddfdcbe10dc5f97afc4e46ca22be2be717e8caf Mon Sep 17 00:00:00 2001
From: Horia Geantă <horia.geanta@nxp.com>
Date: Tue, 17 Mar 2026 12:25:13 +0200
Subject: crypto: caam - fix DMA corruption on long hmac keys
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a key longer than block size is supplied, it is copied and then
hashed into the real key.  The memory allocated for the copy needs to
be rounded to DMA cache alignment, as otherwise the hashed key may
corrupt neighbouring memory.

The rounding was performed, but never actually used for the allocation.
Fix this by replacing kmemdup with kmalloc for a larger buffer,
followed by memcpy.

Fixes: 199354d7fb6e ("crypto: caam - Remove GFP_DMA and add DMA alignment padding")
Reported-by: Paul Bunyan <pbunyan@redhat.com>
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/caam/caamhash.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 628c43a7efc4..44122208f70c 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -441,9 +441,10 @@ static int ahash_setkey(struct crypto_ahash *ahash,
 		if (aligned_len < keylen)
 			return -EOVERFLOW;
 
-		hashed_key = kmemdup(key, keylen, GFP_KERNEL);
+		hashed_key = kmalloc(aligned_len, GFP_KERNEL);
 		if (!hashed_key)
 			return -ENOMEM;
+		memcpy(hashed_key, key, keylen);
 		ret = hash_digest_key(ctx, &keylen, hashed_key, digestsize);
 		if (ret)
 			goto bad_free_key;
-- 
cgit v1.2.3


From 80688afb9c35b3934ce2d6be9973758915e2e0ef Mon Sep 17 00:00:00 2001
From: Horia Geantă <horia.geanta@nxp.com>
Date: Tue, 17 Mar 2026 12:25:14 +0200
Subject: crypto: caam - fix overflow on long hmac keys
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When a key longer than block size is supplied, it is copied and then
hashed into the real key.  The memory allocated for the copy needs to
be rounded to DMA cache alignment, as otherwise the hashed key may
corrupt neighbouring memory.

The copying is performed using kmemdup, however this leads to an overflow:
reading more bytes (aligned_len - keylen) from the keylen source buffer.
Fix this by replacing kmemdup with kmalloc, followed by memcpy.

Fixes: 199354d7fb6e ("crypto: caam - Remove GFP_DMA and add DMA alignment padding")
Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/caam/caamalg_qi2.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index 167372936ca7..78964e1712e5 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -3326,9 +3326,10 @@ static int ahash_setkey(struct crypto_ahash *ahash, const u8 *key,
 		if (aligned_len < keylen)
 			return -EOVERFLOW;
 
-		hashed_key = kmemdup(key, aligned_len, GFP_KERNEL);
+		hashed_key = kmalloc(aligned_len, GFP_KERNEL);
 		if (!hashed_key)
 			return -ENOMEM;
+		memcpy(hashed_key, key, keylen);
 		ret = hash_digest_key(ctx, &keylen, hashed_key, digestsize);
 		if (ret)
 			goto bad_free_key;
-- 
cgit v1.2.3


From 6d89f743e57cb34e233a8217b394c7ee09abf225 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 25 Mar 2026 16:31:38 +0100
Subject: crypto: deflate - fix spurious -ENOSPC

The code in deflate_decompress_one may erroneously return -ENOSPC even if
it didn't run out of output space. The error happens under this
condition:

- Suppose that there are two input pages, the compressed data fits into
  the first page and the zlib checksum is placed in the second page.

- The code iterates over the first page, decompresses the data and fully
  fills the destination buffer, zlib_inflate returns Z_OK becuse zlib
  hasn't seen the checksum yet.

- The outer do-while loop is iterated again, acomp_walk_next_src sets the
  input parameters to the second page containing the checksum.

- We go into the inner do-while loop, execute "dcur =
  acomp_walk_next_dst(&walk);". "dcur" is zero, so we break out of the
  loop and return -ENOSPC, despite the fact that the decompressed data
  fit into the destination buffer.

In order to fix this bug, this commit changes the logic when to report
the -ENOSPC error. We report the error if the destination buffer is empty
*and* if zlib_inflate didn't make any progress consuming the input
buffer. If zlib_inflate consumes the trailing checksum, we see that it
made progress and we will not return -ENOSPC.

Fixes: 08cabc7d3c86 ("crypto: deflate - Convert to acomp")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/deflate.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/crypto/deflate.c b/crypto/deflate.c
index 46fc7def8d4c..710ebba7ce85 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -164,18 +164,21 @@ static int deflate_decompress_one(struct acomp_req *req,
 
 		do {
 			unsigned int dcur;
+			unsigned long avail_in;
 
 			dcur = acomp_walk_next_dst(&walk);
-			if (!dcur) {
-				out_of_space = true;
-				break;
-			}
 
 			stream->avail_out = dcur;
 			stream->next_out = walk.dst.virt.addr;
+			avail_in = stream->avail_in;
 
 			ret = zlib_inflate(stream, Z_NO_FLUSH);
 
+			if (!dcur && avail_in == stream->avail_in) {
+				out_of_space = true;
+				break;
+			}
+
 			dcur -= stream->avail_out;
 			acomp_walk_done_dst(&walk, dcur);
 		} while (ret == Z_OK && stream->avail_in);
-- 
cgit v1.2.3


From 62397b493e14107ae82d8b80938f293d95425bcb Mon Sep 17 00:00:00 2001
From: Norbert Szetei <norbert@doyensec.com>
Date: Wed, 25 Mar 2026 18:26:13 +0100
Subject: crypto: af-alg - fix NULL pointer dereference in scatterwalk

The AF_ALG interface fails to unmark the end of a Scatter/Gather List (SGL)
when chaining a new af_alg_tsgl structure. If a sendmsg() fills an SGL
exactly to MAX_SGL_ENTS, the last entry is marked as the end. A subsequent
sendmsg() allocates a new SGL and chains it, but fails to clear the end
marker on the previous SGL's last data entry.

This causes the crypto scatterwalk to hit a premature end, returning NULL
on sg_next() and leading to a kernel panic during dereference.

Fix this by explicitly unmarking the end of the previous SGL when
performing sg_chain() in af_alg_alloc_tsgl().

Fixes: 8ff590903d5f ("crypto: algif_skcipher - User-space interface for skcipher operations")
Signed-off-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 0bb609fbec7d..c2fd9cd86c5e 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -623,8 +623,10 @@ static int af_alg_alloc_tsgl(struct sock *sk)
 		sg_init_table(sgl->sg, MAX_SGL_ENTS + 1);
 		sgl->cur = 0;
 
-		if (sg)
+		if (sg) {
+			sg_unmark_end(sg + MAX_SGL_ENTS - 1);
 			sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
+		}
 
 		list_add_tail(&sgl->list, &ctx->tsgl_list);
 	}
-- 
cgit v1.2.3


From 326fe8104a4020d30080d37ac8b6b43893cdebca Mon Sep 17 00:00:00 2001
From: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Date: Wed, 25 Mar 2026 22:07:03 +0100
Subject: ASoC: adau1372: Fix unchecked clk_prepare_enable() return value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

adau1372_set_power() calls clk_prepare_enable() but discards the return
value. If the clock enable fails, the driver proceeds to access registers
on unpowered hardware, potentially causing silent corruption.

Make adau1372_set_power() return int and propagate the error from
clk_prepare_enable(). Update adau1372_set_bias_level() to return the
error directly for the STANDBY and OFF cases.

Signed-off-by: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Fixes: 6cd4c6459e47 ("ASoC: Add ADAU1372 audio CODEC support")
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20260325210704.76847-2-jihed.chaibi.dev@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/adau1372.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/sound/soc/codecs/adau1372.c b/sound/soc/codecs/adau1372.c
index fdee689cae53..6345342218d6 100644
--- a/sound/soc/codecs/adau1372.c
+++ b/sound/soc/codecs/adau1372.c
@@ -782,15 +782,18 @@ static void adau1372_enable_pll(struct adau1372 *adau1372)
 		dev_err(adau1372->dev, "Failed to lock PLL\n");
 }
 
-static void adau1372_set_power(struct adau1372 *adau1372, bool enable)
+static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 {
 	if (adau1372->enabled == enable)
-		return;
+		return 0;
 
 	if (enable) {
 		unsigned int clk_ctrl = ADAU1372_CLK_CTRL_MCLK_EN;
+		int ret;
 
-		clk_prepare_enable(adau1372->mclk);
+		ret = clk_prepare_enable(adau1372->mclk);
+		if (ret)
+			return ret;
 		if (adau1372->pd_gpio)
 			gpiod_set_value(adau1372->pd_gpio, 0);
 
@@ -829,6 +832,8 @@ static void adau1372_set_power(struct adau1372 *adau1372, bool enable)
 	}
 
 	adau1372->enabled = enable;
+
+	return 0;
 }
 
 static int adau1372_set_bias_level(struct snd_soc_component *component,
@@ -842,11 +847,9 @@ static int adau1372_set_bias_level(struct snd_soc_component *component,
 	case SND_SOC_BIAS_PREPARE:
 		break;
 	case SND_SOC_BIAS_STANDBY:
-		adau1372_set_power(adau1372, true);
-		break;
+		return adau1372_set_power(adau1372, true);
 	case SND_SOC_BIAS_OFF:
-		adau1372_set_power(adau1372, false);
-		break;
+		return adau1372_set_power(adau1372, false);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From bfe6a264effcb6fe99ad7ceaf9e8c7439fc9555b Mon Sep 17 00:00:00 2001
From: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Date: Wed, 25 Mar 2026 22:07:04 +0100
Subject: ASoC: adau1372: Fix clock leak on PLL lock failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

adau1372_enable_pll() was a void function that logged a dev_err() on
PLL lock timeout but did not propagate the error. As a result,
adau1372_set_power() would continue with adau1372->enabled set to true
despite the PLL being unlocked, and the mclk left enabled with no
corresponding disable on the error path.

Convert adau1372_enable_pll() to return int, using -ETIMEDOUT on lock
timeout and propagating regmap errors directly. In adau1372_set_power(),
check the return value and unwind in reverse order: restore regcache to
cache-only mode, reassert GPIO power-down, and disable the clock before
returning the error.

Signed-off-by: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Fixes: 6cd4c6459e47 ("ASoC: Add ADAU1372 audio CODEC support")
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20260325210704.76847-3-jihed.chaibi.dev@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/adau1372.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/adau1372.c b/sound/soc/codecs/adau1372.c
index 6345342218d6..d7363f9d53bb 100644
--- a/sound/soc/codecs/adau1372.c
+++ b/sound/soc/codecs/adau1372.c
@@ -762,7 +762,7 @@ static int adau1372_startup(struct snd_pcm_substream *substream, struct snd_soc_
 	return 0;
 }
 
-static void adau1372_enable_pll(struct adau1372 *adau1372)
+static int adau1372_enable_pll(struct adau1372 *adau1372)
 {
 	unsigned int val, timeout = 0;
 	int ret;
@@ -778,8 +778,12 @@ static void adau1372_enable_pll(struct adau1372 *adau1372)
 		timeout++;
 	} while (!(val & 1) && timeout < 3);
 
-	if (ret < 0 || !(val & 1))
+	if (ret < 0 || !(val & 1)) {
 		dev_err(adau1372->dev, "Failed to lock PLL\n");
+		return ret < 0 ? ret : -ETIMEDOUT;
+	}
+
+	return 0;
 }
 
 static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
@@ -807,7 +811,14 @@ static int adau1372_set_power(struct adau1372 *adau1372, bool enable)
 		 * accessed.
 		 */
 		if (adau1372->use_pll) {
-			adau1372_enable_pll(adau1372);
+			ret = adau1372_enable_pll(adau1372);
+			if (ret) {
+				regcache_cache_only(adau1372->regmap, true);
+				if (adau1372->pd_gpio)
+					gpiod_set_value(adau1372->pd_gpio, 1);
+				clk_disable_unprepare(adau1372->mclk);
+				return ret;
+			}
 			clk_ctrl |= ADAU1372_CLK_CTRL_CLKSRC;
 		}
 
-- 
cgit v1.2.3


From 8d2e0cb3224c89275c5471c92850e7f74df80c20 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 25 Mar 2026 15:53:19 +0100
Subject: spi: fix use-after-free on managed registration failure

The SPI API is asymmetric and the controller is freed as part of
deregistration (unless it has been allocated using
devm_spi_alloc_host/target()).

A recent change converting the managed registration function to use
devm_add_action_or_reset() inadvertently introduced a (mostly
theoretical) regression where a non-devres managed controller could be
freed as part of failed registration. This in turn would lead to
use-after-free in controller driver error paths.

Fix this by taking another reference before calling
devm_add_action_or_reset() and not releasing it on errors for
non-devres allocated controllers.

An alternative would be a partial revert of the offending commit, but
it is better to handle this explicitly until the API has been fixed
(e.g. see 5e844cc37a5c ("spi: Introduce device-managed SPI controller
allocation")).

Fixes: b6376dbed8e1 ("spi: Simplify devm_spi_*_controller()")
Reported-by: Felix Gu <ustc.gu@gmail.com>
Link: https://lore.kernel.org/all/20260324145548.139952-1-ustc.gu@gmail.com/
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20260325145319.1132072-1-johan@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 4101c2803eb3..9b1125556d29 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3534,8 +3534,19 @@ int devm_spi_register_controller(struct device *dev,
 	if (ret)
 		return ret;
 
-	return devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr);
+	/*
+	 * Prevent controller from being freed by spi_unregister_controller()
+	 * if devm_add_action_or_reset() fails for a non-devres allocated
+	 * controller.
+	 */
+	spi_controller_get(ctlr);
+
+	ret = devm_add_action_or_reset(dev, devm_spi_unregister_controller, ctlr);
 
+	if (ret == 0 || ctlr->devm_allocated)
+		spi_controller_put(ctlr);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 
-- 
cgit v1.2.3


From c7596f9001e2b83293e3658e4e1addde69bb335d Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Tue, 3 Mar 2026 11:24:06 +0000
Subject: firmware: microchip: fail auto-update probe if no flash found

There's no point letting the driver probe if there is no flash, as
trying to do a firmware upload will fail. Move the code that attempts
to get the flash from firmware upload to probe, and let it emit a
message to users stating why auto-update is not supported.
The code currently could have a problem if there's a flash in
devicetree, but the system controller driver fails to get a pointer to
it from the mtd subsystem, which will cause
mpfs_sys_controller_get_flash() to return an error. Check for errors and
null, instead of just null, in the new clause.

CC: stable@vger.kernel.org
Fixes: ec5b0f1193ad4 ("firmware: microchip: add PolarFire SoC Auto Update support")
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/firmware/microchip/mpfs-auto-update.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
index e194f7acb2a9..8fc3749d4a70 100644
--- a/drivers/firmware/microchip/mpfs-auto-update.c
+++ b/drivers/firmware/microchip/mpfs-auto-update.c
@@ -113,10 +113,6 @@ static enum fw_upload_err mpfs_auto_update_prepare(struct fw_upload *fw_uploader
 	 * be added here.
 	 */
 
-	priv->flash = mpfs_sys_controller_get_flash(priv->sys_controller);
-	if (!priv->flash)
-		return FW_UPLOAD_ERR_HW_ERROR;
-
 	erase_size = round_up(erase_size, (u64)priv->flash->erasesize);
 
 	/*
@@ -427,6 +423,12 @@ static int mpfs_auto_update_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, PTR_ERR(priv->sys_controller),
 				     "Could not register as a sub device of the system controller\n");
 
+	priv->flash = mpfs_sys_controller_get_flash(priv->sys_controller);
+	if (IS_ERR_OR_NULL(priv->flash)) {
+		dev_dbg(dev, "No flash connected to the system controller, auto-update not supported\n");
+		return -ENODEV;
+	}
+
 	priv->dev = dev;
 	platform_set_drvdata(pdev, priv);
 
-- 
cgit v1.2.3


From d40a198e2b7821197c5c77b89d0130cc90f400f5 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 26 Mar 2026 09:56:18 +0200
Subject: ASoC: SOF: ipc4-topology: Allow bytes controls without initial
 payload

It is unexpected, but allowed to have no initial payload for a bytes
control and the code is prepared to handle this case, but the size check
missed this corner case.

Update the check for minimal size to allow the initial size to be 0.

Cc: stable@vger.kernel.org
Fixes: a653820700b8 ("ASoC: SOF: ipc4-topology: Correct the allocation size for bytes controls")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Reviewed-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://patch.msgid.link/20260326075618.1603-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/ipc4-topology.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index db077e9d5644..c12ffdcfe4e3 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -2950,7 +2950,7 @@ static int sof_ipc4_control_load_bytes(struct snd_sof_dev *sdev, struct snd_sof_
 		return -EINVAL;
 	}
 
-	if (scontrol->priv_size < sizeof(struct sof_abi_hdr)) {
+	if (scontrol->priv_size && scontrol->priv_size < sizeof(struct sof_abi_hdr)) {
 		dev_err(sdev->dev,
 			"bytes control %s initial data size %zu is insufficient.\n",
 			scontrol->name, scontrol->priv_size);
-- 
cgit v1.2.3


From 7c39f48568e0aec9bf6988cdbf833fdf8af19901 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Fri, 20 Mar 2026 07:49:10 +0000
Subject: media: uvcvideo: Fix bug in error path of uvc_alloc_urb_buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Recent cleanup introduced a bug in the error path of
uvc_alloc_urb_buffers(). If there is not enough memory for the
allocation the following error will be triggered:

[  739.196672] UBSAN: shift-out-of-bounds in mm/page_alloc.c:1403:22
[  739.196710] shift exponent 52 is too large for 32-bit type 'int'

Resulting in:
[  740.464422] BUG: unable to handle page fault for address: fffffac1c0800000

The reason for the bug is that usb_free_noncoherent is called with an
invalid size (0) instead of the actual size of the urb.

This patch takes care of that.

Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Closes: https://lore.kernel.org/linux-media/abycbXzYupZpGkvR@hyeyoo/T/#t
Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Fixes: c824345288d1 ("media: uvcvideo: Pass allocation size directly to uvc_alloc_urb_buffer")
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patch.msgid.link/20260320-uvc-urb-free-error-v1-1-b12cc3762a19@chromium.org
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/usb/uvc/uvc_video.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 40c76c051da2..f6c8e3223796 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1751,7 +1751,8 @@ static void uvc_video_complete(struct urb *urb)
 /*
  * Free transfer buffers.
  */
-static void uvc_free_urb_buffers(struct uvc_streaming *stream)
+static void uvc_free_urb_buffers(struct uvc_streaming *stream,
+				 unsigned int size)
 {
 	struct usb_device *udev = stream->dev->udev;
 	struct uvc_urb *uvc_urb;
@@ -1760,7 +1761,7 @@ static void uvc_free_urb_buffers(struct uvc_streaming *stream)
 		if (!uvc_urb->buffer)
 			continue;
 
-		usb_free_noncoherent(udev, stream->urb_size, uvc_urb->buffer,
+		usb_free_noncoherent(udev, size, uvc_urb->buffer,
 				     uvc_stream_dir(stream), uvc_urb->sgt);
 		uvc_urb->buffer = NULL;
 		uvc_urb->sgt = NULL;
@@ -1820,7 +1821,7 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream,
 
 			if (!uvc_alloc_urb_buffer(stream, uvc_urb, urb_size,
 						  gfp_flags)) {
-				uvc_free_urb_buffers(stream);
+				uvc_free_urb_buffers(stream, urb_size);
 				break;
 			}
 
@@ -1868,7 +1869,7 @@ static void uvc_video_stop_transfer(struct uvc_streaming *stream,
 	}
 
 	if (free_buffers)
-		uvc_free_urb_buffers(stream);
+		uvc_free_urb_buffers(stream, stream->urb_size);
 }
 
 /*
-- 
cgit v1.2.3


From 7587fbf5adc23d180a5ea9aa6944292c22328703 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Sat, 21 Mar 2026 23:21:44 +0200
Subject: media: ccs: Avoid deadlock in ccs_init_state()

The sub-device state lock has been already acquired when ccs_init_state()
is called. Do not try to acquire it again.

Reported-by: David Heidelberg <david@ixit.cz>
Fixes: a88883d1209c ("media: ccs: Rely on sub-device state locking")
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/i2c/ccs/ccs-core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c
index aa4dd7e7cf5a..8e25f970fd12 100644
--- a/drivers/media/i2c/ccs/ccs-core.c
+++ b/drivers/media/i2c/ccs/ccs-core.c
@@ -3080,8 +3080,6 @@ static int ccs_init_state(struct v4l2_subdev *sd,
 	struct v4l2_rect *crop =
 		v4l2_subdev_state_get_crop(sd_state, pad);
 
-	guard(mutex)(&sensor->mutex);
-
 	ccs_get_native_size(ssd, crop);
 
 	fmt->width = crop->width;
-- 
cgit v1.2.3


From 52025ebaa29f4eb4ed8bf92ce83a68f24ab7fdf7 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 25 Mar 2026 14:10:58 +0100
Subject: netfilter: nfnetlink_log: fix uninitialized padding leak in
 NFULA_PAYLOAD

__build_packet_message() manually constructs the NFULA_PAYLOAD netlink
attribute using skb_put() and skb_copy_bits(), bypassing the standard
nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes
are allocated (including NLA alignment padding), only data_len bytes
of actual packet data are copied. The trailing nla_padlen(data_len)
bytes (1-3 when data_len is not 4-byte aligned) are never initialized,
leaking stale heap contents to userspace via the NFLOG netlink socket.

Replace the manual attribute construction with nla_reserve(), which
handles the tailroom check, header setup, and padding zeroing via
__nla_reserve(). The subsequent skb_copy_bits() fills in the payload
data on top of the properly initialized attribute.

Fixes: df6fb868d611 ("[NETFILTER]: nfnetlink: convert to generic netlink attribute functions")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_log.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index b35a90955e2e..fcbe54940b2e 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -647,15 +647,11 @@ __build_packet_message(struct nfnl_log_net *log,
 
 	if (data_len) {
 		struct nlattr *nla;
-		int size = nla_attr_size(data_len);
 
-		if (skb_tailroom(inst->skb) < nla_total_size(data_len))
+		nla = nla_reserve(inst->skb, NFULA_PAYLOAD, data_len);
+		if (!nla)
 			goto nla_put_failure;
 
-		nla = skb_put(inst->skb, nla_total_size(data_len));
-		nla->nla_type = NFULA_PAYLOAD;
-		nla->nla_len = size;
-
 		if (skb_copy_bits(skb, 0, nla_data(nla), data_len))
 			BUG();
 	}
-- 
cgit v1.2.3


From 9d3f027327c2fa265f7f85ead41294792c3296ed Mon Sep 17 00:00:00 2001
From: Ren Wei <n05ec@lzu.edu.cn>
Date: Wed, 25 Mar 2026 14:11:00 +0100
Subject: netfilter: ip6t_rt: reject oversized addrnr in rt_mt6_check()

Reject rt match rules whose addrnr exceeds IP6T_RT_HOPS.

rt_mt6() expects addrnr to stay within the bounds of rtinfo->addrs[].
Validate addrnr during rule installation so malformed rules are rejected
before the match logic can use an out-of-range value.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Yuhang Zheng <z1652074432@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv6/netfilter/ip6t_rt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index 4ad8b2032f1f..5561bd9cea81 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -157,6 +157,10 @@ static int rt_mt6_check(const struct xt_mtchk_param *par)
 		pr_debug("unknown flags %X\n", rtinfo->invflags);
 		return -EINVAL;
 	}
+	if (rtinfo->addrnr > IP6T_RT_HOPS) {
+		pr_debug("too many addresses specified\n");
+		return -EINVAL;
+	}
 	if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) &&
 	    (!(rtinfo->flags & IP6T_RT_TYP) ||
 	     (rtinfo->rt_type != 0) ||
-- 
cgit v1.2.3


From fafdd92b9e30fe057740c5bb5cd4f92ecea9bf26 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 14:11:01 +0100
Subject: netfilter: nft_set_rbtree: revisit array resize logic

Chris Arges reports high memory consumption with thousands of
containers, this patch revisits the array allocation logic.

For anonymous sets, start by 16 slots (which takes 256 bytes on x86_64).
Expand it by x2 until threshold of 512 slots is reached, over that
threshold, expand it by x1.5.

For non-anonymous set, start by 1024 slots in the array (which takes 16
Kbytes initially on x86_64). Expand it by x1.5.

Use set->ndeact to subtract deactivated elements when calculating the
number of the slots in the array, otherwise the array size array gets
increased artifically. Add special case shrink logic to deal with flush
set too.

The shrink logic is skipped by anonymous sets.

Use check_add_overflow() to calculate the new array size.

Add a WARN_ON_ONCE check to make sure elements fit into the new array
size.

Reported-by: Chris Arges <carges@cloudflare.com>
Fixes: 7e43e0a1141d ("netfilter: nft_set_rbtree: translate rbtree to array for binary search")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_set_rbtree.c | 92 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 75 insertions(+), 17 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index fe8bd497d74a..737c339decd0 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -572,14 +572,12 @@ static struct nft_array *nft_array_alloc(u32 max_intervals)
 	return array;
 }
 
-#define NFT_ARRAY_EXTRA_SIZE	10240
-
 /* Similar to nft_rbtree_{u,k}size to hide details to userspace, but consider
  * packed representation coming from userspace for anonymous sets too.
  */
 static u32 nft_array_elems(const struct nft_set *set)
 {
-	u32 nelems = atomic_read(&set->nelems);
+	u32 nelems = atomic_read(&set->nelems) - set->ndeact;
 
 	/* Adjacent intervals are represented with a single start element in
 	 * anonymous sets, use the current element counter as is.
@@ -595,27 +593,87 @@ static u32 nft_array_elems(const struct nft_set *set)
 	return (nelems / 2) + 2;
 }
 
-static int nft_array_may_resize(const struct nft_set *set)
+#define NFT_ARRAY_INITIAL_SIZE		1024
+#define NFT_ARRAY_INITIAL_ANON_SIZE	16
+#define NFT_ARRAY_INITIAL_ANON_THRESH	(8192U / sizeof(struct nft_array_interval))
+
+static int nft_array_may_resize(const struct nft_set *set, bool flush)
 {
-	u32 nelems = nft_array_elems(set), new_max_intervals;
+	u32 initial_intervals, max_intervals, new_max_intervals, delta;
+	u32 shrinked_max_intervals, nelems = nft_array_elems(set);
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_array *array;
 
-	if (!priv->array_next) {
-		array = nft_array_alloc(nelems + NFT_ARRAY_EXTRA_SIZE);
-		if (!array)
-			return -ENOMEM;
+	if (nft_set_is_anonymous(set))
+		initial_intervals = NFT_ARRAY_INITIAL_ANON_SIZE;
+	else
+		initial_intervals = NFT_ARRAY_INITIAL_SIZE;
+
+	if (priv->array_next) {
+		max_intervals = priv->array_next->max_intervals;
+		new_max_intervals = priv->array_next->max_intervals;
+	} else {
+		if (priv->array) {
+			max_intervals = priv->array->max_intervals;
+			new_max_intervals = priv->array->max_intervals;
+		} else {
+			max_intervals = 0;
+			new_max_intervals = initial_intervals;
+		}
+	}
 
-		priv->array_next = array;
+	if (nft_set_is_anonymous(set))
+		goto maybe_grow;
+
+	if (flush) {
+		/* Set flush just started, nelems still report elements.*/
+		nelems = 0;
+		new_max_intervals = NFT_ARRAY_INITIAL_SIZE;
+		goto realloc_array;
 	}
 
-	if (nelems < priv->array_next->max_intervals)
-		return 0;
+	if (check_add_overflow(new_max_intervals, new_max_intervals,
+			       &shrinked_max_intervals))
+		return -EOVERFLOW;
+
+	shrinked_max_intervals = DIV_ROUND_UP(shrinked_max_intervals, 3);
 
-	new_max_intervals = priv->array_next->max_intervals + NFT_ARRAY_EXTRA_SIZE;
-	if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0)
+	if (shrinked_max_intervals > NFT_ARRAY_INITIAL_SIZE &&
+	    nelems < shrinked_max_intervals) {
+		new_max_intervals = shrinked_max_intervals;
+		goto realloc_array;
+	}
+maybe_grow:
+	if (nelems > new_max_intervals) {
+		if (nft_set_is_anonymous(set) &&
+		    new_max_intervals < NFT_ARRAY_INITIAL_ANON_THRESH) {
+			new_max_intervals <<= 1;
+		} else {
+			delta = new_max_intervals >> 1;
+			if (check_add_overflow(new_max_intervals, delta,
+					       &new_max_intervals))
+				return -EOVERFLOW;
+		}
+	}
+
+realloc_array:
+	if (WARN_ON_ONCE(nelems > new_max_intervals))
 		return -ENOMEM;
 
+	if (priv->array_next) {
+		if (max_intervals == new_max_intervals)
+			return 0;
+
+		if (nft_array_intervals_alloc(priv->array_next, new_max_intervals) < 0)
+			return -ENOMEM;
+	} else {
+		array = nft_array_alloc(new_max_intervals);
+		if (!array)
+			return -ENOMEM;
+
+		priv->array_next = array;
+	}
+
 	return 0;
 }
 
@@ -630,7 +688,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 
 	nft_rbtree_maybe_reset_start_cookie(priv, tstamp);
 
-	if (nft_array_may_resize(set) < 0)
+	if (nft_array_may_resize(set, false) < 0)
 		return -ENOMEM;
 
 	do {
@@ -741,7 +799,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
 	    nft_rbtree_interval_null(set, this))
 		priv->start_rbe_cookie = 0;
 
-	if (nft_array_may_resize(set) < 0)
+	if (nft_array_may_resize(set, false) < 0)
 		return NULL;
 
 	while (parent != NULL) {
@@ -811,7 +869,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 	switch (iter->type) {
 	case NFT_ITER_UPDATE_CLONE:
-		if (nft_array_may_resize(set) < 0) {
+		if (nft_array_may_resize(set, true) < 0) {
 			iter->err = -ENOMEM;
 			break;
 		}
-- 
cgit v1.2.3


From 9c42bc9db90a154bc61ae337a070465f3393485a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 14:11:02 +0100
Subject: netfilter: nf_conntrack_expect: honor expectation helper field

The expectation helper field is mostly unused. As a result, the
netfilter codebase relies on accessing the helper through exp->master.

Always set on the expectation helper field so it can be used to reach
the helper.

nf_ct_expect_init() is called from packet path where the skb owns
the ct object, therefore accessing exp->master for the newly created
expectation is safe. This saves a lot of updates in all callsites
to pass the ct object as parameter to nf_ct_expect_init().

This is a preparation patches for follow up fixes.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_expect.h |  2 +-
 net/netfilter/nf_conntrack_broadcast.c      |  2 +-
 net/netfilter/nf_conntrack_expect.c         | 14 +++++++++++++-
 net/netfilter/nf_conntrack_h323_main.c      | 12 ++++++------
 net/netfilter/nf_conntrack_helper.c         |  7 ++++++-
 net/netfilter/nf_conntrack_netlink.c        |  2 +-
 net/netfilter/nf_conntrack_sip.c            |  2 +-
 7 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 165e7a03b8e9..1b01400b10bd 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -40,7 +40,7 @@ struct nf_conntrack_expect {
 			 struct nf_conntrack_expect *this);
 
 	/* Helper to assign to new connection */
-	struct nf_conntrack_helper *helper;
+	struct nf_conntrack_helper __rcu *helper;
 
 	/* The conntrack of the master connection */
 	struct nf_conn *master;
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index a7552a46d6ac..1964c596c646 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -70,7 +70,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	exp->expectfn             = NULL;
 	exp->flags                = NF_CT_EXPECT_PERMANENT;
 	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
-	exp->helper               = NULL;
+	rcu_assign_pointer(exp->helper, helper);
 
 	nf_ct_expect_related(exp, 0);
 	nf_ct_expect_put(exp);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index cfc2daa3fc7f..841e316240da 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -309,12 +309,19 @@ struct nf_conntrack_expect *nf_ct_expect_alloc(struct nf_conn *me)
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_alloc);
 
+/* This function can only be used from packet path, where accessing
+ * master's helper is safe, because the packet holds a reference on
+ * the conntrack object. Never use it from control plane.
+ */
 void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 		       u_int8_t family,
 		       const union nf_inet_addr *saddr,
 		       const union nf_inet_addr *daddr,
 		       u_int8_t proto, const __be16 *src, const __be16 *dst)
 {
+	struct nf_conntrack_helper *helper = NULL;
+	struct nf_conn *ct = exp->master;
+	struct nf_conn_help *help;
 	int len;
 
 	if (family == AF_INET)
@@ -325,7 +332,12 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 	exp->flags = 0;
 	exp->class = class;
 	exp->expectfn = NULL;
-	exp->helper = NULL;
+
+	help = nfct_help(ct);
+	if (help)
+		helper = rcu_dereference(help->helper);
+
+	rcu_assign_pointer(exp->helper, helper);
 	exp->tuple.src.l3num = family;
 	exp->tuple.dst.protonum = proto;
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index a2a0e22ccee1..3f5c50455b71 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -643,7 +643,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	exp->helper = &nf_conntrack_helper_h245;
+	rcu_assign_pointer(exp->helper, &nf_conntrack_helper_h245);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -767,7 +767,7 @@ static int expect_callforwarding(struct sk_buff *skb,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
-	exp->helper = nf_conntrack_helper_q931;
+	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
 	if (memcmp(&ct->tuplehash[dir].tuple.src.u3,
@@ -1234,7 +1234,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct,
 				&ct->tuplehash[!dir].tuple.src.u3 : NULL,
 			  &ct->tuplehash[!dir].tuple.dst.u3,
 			  IPPROTO_TCP, NULL, &port);
-	exp->helper = nf_conntrack_helper_q931;
+	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
 	exp->flags = NF_CT_EXPECT_PERMANENT;	/* Accept multiple calls */
 
 	nathook = rcu_dereference(nfct_h323_nat_hook);
@@ -1306,7 +1306,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct,
 	nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT, nf_ct_l3num(ct),
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_UDP, NULL, &port);
-	exp->helper = nf_conntrack_helper_ras;
+	rcu_assign_pointer(exp->helper, nf_conntrack_helper_ras);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect RAS ");
@@ -1523,7 +1523,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	exp->helper = nf_conntrack_helper_q931;
+	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
@@ -1577,7 +1577,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct,
 			  &ct->tuplehash[!dir].tuple.src.u3, &addr,
 			  IPPROTO_TCP, NULL, &port);
 	exp->flags = NF_CT_EXPECT_PERMANENT;
-	exp->helper = nf_conntrack_helper_q931;
+	rcu_assign_pointer(exp->helper, nf_conntrack_helper_q931);
 
 	if (nf_ct_expect_related(exp, 0) == 0) {
 		pr_debug("nf_ct_ras: expect Q.931 ");
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index ceb48c3ca0a4..294a6ffcbccd 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -399,7 +399,7 @@ static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
 	const struct nf_conntrack_helper *me = data;
 	const struct nf_conntrack_helper *this;
 
-	if (exp->helper == me)
+	if (rcu_access_pointer(exp->helper) == me)
 		return true;
 
 	this = rcu_dereference_protected(help->helper,
@@ -421,6 +421,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 
 	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
 	nf_ct_iterate_destroy(unhelp, me);
+
+	/* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as
+	 * last step, this ensures rcu readers of exp->helper are done.
+	 * No need for another synchronize_rcu() here.
+	 */
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c156574e1273..a42d14290786 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3573,7 +3573,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 
 	exp->class = class;
 	exp->master = ct;
-	exp->helper = helper;
+	rcu_assign_pointer(exp->helper, helper);
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
 	exp->mask.src.u.all = mask->src.u.all;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 4ab5ef71d96d..106b2f419e19 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1297,7 +1297,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff,
 	nf_ct_expect_init(exp, SIP_EXPECT_SIGNALLING, nf_ct_l3num(ct),
 			  saddr, &daddr, proto, NULL, &port);
 	exp->timeout.expires = sip_timeout * HZ;
-	exp->helper = helper;
+	rcu_assign_pointer(exp->helper, helper);
 	exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE;
 
 	hooks = rcu_dereference(nf_nat_sip_hooks);
-- 
cgit v1.2.3


From f01794106042ee27e54af6fdf5b319a2fe3df94d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 14:11:03 +0100
Subject: netfilter: nf_conntrack_expect: use expect->helper

Use expect->helper in ctnetlink and /proc to dump the helper name.
Using nfct_help() without holding a reference to the master conntrack
is unsafe.

Use exp->master->helper in ctnetlink path if userspace does not provide
an explicit helper when creating an expectation to retain the existing
behaviour. The ctnetlink expectation path holds the reference on the
master conntrack and nf_conntrack_expect lock and the nfnetlink glue
path refers to the master ct that is attached to the skb.

Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_expect.c  |  2 +-
 net/netfilter/nf_conntrack_helper.c  |  6 +-----
 net/netfilter/nf_conntrack_netlink.c | 24 ++++++++++--------------
 net/netfilter/nf_conntrack_sip.c     |  2 +-
 4 files changed, 13 insertions(+), 21 deletions(-)

diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 841e316240da..64977db12b1d 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -666,7 +666,7 @@ static int exp_seq_show(struct seq_file *s, void *v)
 	if (expect->flags & NF_CT_EXPECT_USERSPACE)
 		seq_printf(s, "%sUSERSPACE", delim);
 
-	helper = rcu_dereference(nfct_help(expect->master)->helper);
+	helper = rcu_dereference(expect->helper);
 	if (helper) {
 		seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name);
 		if (helper->expect_policy[expect->class].name[0])
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 294a6ffcbccd..1b330ba6613b 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -395,14 +395,10 @@ EXPORT_SYMBOL_GPL(nf_conntrack_helper_register);
 
 static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data)
 {
-	struct nf_conn_help *help = nfct_help(exp->master);
 	const struct nf_conntrack_helper *me = data;
 	const struct nf_conntrack_helper *this;
 
-	if (rcu_access_pointer(exp->helper) == me)
-		return true;
-
-	this = rcu_dereference_protected(help->helper,
+	this = rcu_dereference_protected(exp->helper,
 					 lockdep_is_held(&nf_conntrack_expect_lock));
 	return this == me;
 }
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index a42d14290786..8477c3736432 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3012,7 +3012,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 {
 	struct nf_conn *master = exp->master;
 	long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
-	struct nf_conn_help *help;
+	struct nf_conntrack_helper *helper;
 #if IS_ENABLED(CONFIG_NF_NAT)
 	struct nlattr *nest_parms;
 	struct nf_conntrack_tuple nat_tuple = {};
@@ -3057,15 +3057,12 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	    nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
 	    nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
 		goto nla_put_failure;
-	help = nfct_help(master);
-	if (help) {
-		struct nf_conntrack_helper *helper;
 
-		helper = rcu_dereference(help->helper);
-		if (helper &&
-		    nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name))
-			goto nla_put_failure;
-	}
+	helper = rcu_dereference(exp->helper);
+	if (helper &&
+	    nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name))
+		goto nla_put_failure;
+
 	expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn);
 	if (expfn != NULL &&
 	    nla_put_string(skb, CTA_EXPECT_FN, expfn->name))
@@ -3394,12 +3391,9 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data)
 {
 	struct nf_conntrack_helper *helper;
-	const struct nf_conn_help *m_help;
 	const char *name = data;
 
-	m_help = nfct_help(exp->master);
-
-	helper = rcu_dereference(m_help->helper);
+	helper = rcu_dereference(exp->helper);
 	if (!helper)
 		return false;
 
@@ -3534,9 +3528,9 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
-	u_int32_t class = 0;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn_help *help;
+	u32 class = 0;
 	int err;
 
 	help = nfct_help(ct);
@@ -3573,6 +3567,8 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 
 	exp->class = class;
 	exp->master = ct;
+	if (!helper)
+		helper = rcu_dereference(help->helper);
 	rcu_assign_pointer(exp->helper, helper);
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 106b2f419e19..20e57cf5c83a 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -924,7 +924,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		exp = __nf_ct_expect_find(net, nf_ct_zone(ct), &tuple);
 
 		if (!exp || exp->master == ct ||
-		    nfct_help(exp->master)->helper != nfct_help(ct)->helper ||
+		    exp->helper != nfct_help(ct)->helper ||
 		    exp->class != class)
 			break;
 #if IS_ENABLED(CONFIG_NF_NAT)
-- 
cgit v1.2.3


From bffcaad9afdfe45d7fc777397d3b83c1e3ebffe5 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 14:11:04 +0100
Subject: netfilter: ctnetlink: ensure safe access to master conntrack

Holding reference on the expectation is not sufficient, the master
conntrack object can just go away, making exp->master invalid.

To access exp->master safely:

- Grab the nf_conntrack_expect_lock, this gets serialized with
  clean_from_lists() which also holds this lock when the master
  conntrack goes away.

- Hold reference on master conntrack via nf_conntrack_find_get().
  Not so easy since the master tuple to look up for the master conntrack
  is not available in the existing problematic paths.

This patch goes for extending the nf_conntrack_expect_lock section
to address this issue for simplicity, in the cases that are described
below this is just slightly extending the lock section.

The add expectation command already holds a reference to the master
conntrack from ctnetlink_create_expect().

However, the delete expectation command needs to grab the spinlock
before looking up for the expectation. Expand the existing spinlock
section to address this to cover the expectation lookup. Note that,
the nf_ct_expect_iterate_net() calls already grabs the spinlock while
iterating over the expectation table, which is correct.

The get expectation command needs to grab the spinlock to ensure master
conntrack does not go away. This also expands the existing spinlock
section to cover the expectation lookup too. I needed to move the
netlink skb allocation out of the spinlock to keep it GFP_KERNEL.

For the expectation events, the IPEXP_DESTROY event is already delivered
under the spinlock, just move the delivery of IPEXP_NEW under the
spinlock too because the master conntrack event cache is reached through
exp->master.

While at it, add lockdep notations to help identify what codepaths need
to grab the spinlock.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_core.h |  5 +++++
 net/netfilter/nf_conntrack_ecache.c       |  2 ++
 net/netfilter/nf_conntrack_expect.c       | 10 +++++++++-
 net/netfilter/nf_conntrack_netlink.c      | 28 +++++++++++++++++++---------
 4 files changed, 35 insertions(+), 10 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 3384859a8921..8883575adcc1 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -83,6 +83,11 @@ void nf_conntrack_lock(spinlock_t *lock);
 
 extern spinlock_t nf_conntrack_expect_lock;
 
+static inline void lockdep_nfct_expect_lock_held(void)
+{
+	lockdep_assert_held(&nf_conntrack_expect_lock);
+}
+
 /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
 
 static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout)
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 81baf2082604..9df159448b89 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -247,6 +247,8 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
+	lockdep_nfct_expect_lock_held();
+
 	rcu_read_lock();
 	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (!notify)
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 64977db12b1d..1cbe5f1108c2 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -51,6 +51,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
 	struct net *net = nf_ct_exp_net(exp);
 	struct nf_conntrack_net *cnet;
 
+	lockdep_nfct_expect_lock_held();
 	WARN_ON(!master_help);
 	WARN_ON(timer_pending(&exp->timeout));
 
@@ -118,6 +119,8 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
 
 bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
 {
+	lockdep_nfct_expect_lock_held();
+
 	if (timer_delete(&exp->timeout)) {
 		nf_ct_unlink_expect(exp);
 		nf_ct_expect_put(exp);
@@ -177,6 +180,8 @@ nf_ct_find_expectation(struct net *net,
 	struct nf_conntrack_expect *i, *exp = NULL;
 	unsigned int h;
 
+	lockdep_nfct_expect_lock_held();
+
 	if (!cnet->expect_count)
 		return NULL;
 
@@ -454,6 +459,8 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
 	unsigned int h;
 	int ret = 0;
 
+	lockdep_nfct_expect_lock_held();
+
 	if (!master_help) {
 		ret = -ESHUTDOWN;
 		goto out;
@@ -510,8 +517,9 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
 
 	nf_ct_expect_insert(expect);
 
-	spin_unlock_bh(&nf_conntrack_expect_lock);
 	nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
+
 	return 0;
 out:
 	spin_unlock_bh(&nf_conntrack_expect_lock);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 8477c3736432..89540112d165 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3355,31 +3355,37 @@ static int ctnetlink_get_expect(struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb2)
+		return -ENOMEM;
+
+	spin_lock_bh(&nf_conntrack_expect_lock);
 	exp = nf_ct_expect_find_get(info->net, &zone, &tuple);
-	if (!exp)
+	if (!exp) {
+		spin_unlock_bh(&nf_conntrack_expect_lock);
+		kfree_skb(skb2);
 		return -ENOENT;
+	}
 
 	if (cda[CTA_EXPECT_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
 
 		if (id != nf_expect_get_id(exp)) {
 			nf_ct_expect_put(exp);
+			spin_unlock_bh(&nf_conntrack_expect_lock);
+			kfree_skb(skb2);
 			return -ENOENT;
 		}
 	}
 
-	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!skb2) {
-		nf_ct_expect_put(exp);
-		return -ENOMEM;
-	}
-
 	rcu_read_lock();
 	err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid,
 				      info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW,
 				      exp);
 	rcu_read_unlock();
 	nf_ct_expect_put(exp);
+	spin_unlock_bh(&nf_conntrack_expect_lock);
+
 	if (err <= 0) {
 		kfree_skb(skb2);
 		return -ENOMEM;
@@ -3426,22 +3432,26 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
 		if (err < 0)
 			return err;
 
+		spin_lock_bh(&nf_conntrack_expect_lock);
+
 		/* bump usage count to 2 */
 		exp = nf_ct_expect_find_get(info->net, &zone, &tuple);
-		if (!exp)
+		if (!exp) {
+			spin_unlock_bh(&nf_conntrack_expect_lock);
 			return -ENOENT;
+		}
 
 		if (cda[CTA_EXPECT_ID]) {
 			__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
 
 			if (id != nf_expect_get_id(exp)) {
 				nf_ct_expect_put(exp);
+				spin_unlock_bh(&nf_conntrack_expect_lock);
 				return -ENOENT;
 			}
 		}
 
 		/* after list removal, usage count == 1 */
-		spin_lock_bh(&nf_conntrack_expect_lock);
 		if (timer_delete(&exp->timeout)) {
 			nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid,
 						   nlmsg_report(info->nlh));
-- 
cgit v1.2.3


From 02a3231b6d82efe750da6554ebf280e4a6f78756 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 22:39:55 +0100
Subject: netfilter: nf_conntrack_expect: store netns and zone in expectation

__nf_ct_expect_find() and nf_ct_expect_find_get() are called under
rcu_read_lock() but they dereference the master conntrack via
exp->master.

Since the expectation does not hold a reference on the master conntrack,
this could be dying conntrack or different recycled conntrack than the
real master due to SLAB_TYPESAFE_RCU.

Store the netns, the master_tuple and the zone in struct
nf_conntrack_expect as a safety measure.

This patch is required by the follow up fix not to dump expectations
that do not belong to this netns.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_expect.h | 18 +++++++++++++++++-
 net/netfilter/nf_conntrack_broadcast.c      |  6 +++++-
 net/netfilter/nf_conntrack_expect.c         |  9 +++++++--
 net/netfilter/nf_conntrack_netlink.c        |  5 +++++
 4 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 1b01400b10bd..e9a8350e7ccf 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -22,10 +22,16 @@ struct nf_conntrack_expect {
 	/* Hash member */
 	struct hlist_node hnode;
 
+	/* Network namespace */
+	possible_net_t net;
+
 	/* We expect this tuple, with the following mask */
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_mask mask;
 
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	struct nf_conntrack_zone zone;
+#endif
 	/* Usage count. */
 	refcount_t use;
 
@@ -62,7 +68,17 @@ struct nf_conntrack_expect {
 
 static inline struct net *nf_ct_exp_net(struct nf_conntrack_expect *exp)
 {
-	return nf_ct_net(exp->master);
+	return read_pnet(&exp->net);
+}
+
+static inline bool nf_ct_exp_zone_equal_any(const struct nf_conntrack_expect *a,
+					    const struct nf_conntrack_zone *b)
+{
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	return a->zone.id == b->id;
+#else
+	return true;
+#endif
 }
 
 #define NF_CT_EXP_POLICY_NAME_LEN	16
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index 1964c596c646..4f39bf7c843f 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -21,6 +21,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 				unsigned int timeout)
 {
 	const struct nf_conntrack_helper *helper;
+	struct net *net = read_pnet(&ct->ct_net);
 	struct nf_conntrack_expect *exp;
 	struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt = skb_rtable(skb);
@@ -71,7 +72,10 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	exp->flags                = NF_CT_EXPECT_PERMANENT;
 	exp->class		  = NF_CT_EXPECT_CLASS_DEFAULT;
 	rcu_assign_pointer(exp->helper, helper);
-
+	write_pnet(&exp->net, net);
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	exp->zone = ct->zone;
+#endif
 	nf_ct_expect_related(exp, 0);
 	nf_ct_expect_put(exp);
 
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 1cbe5f1108c2..db28801b1688 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -113,8 +113,8 @@ nf_ct_exp_equal(const struct nf_conntrack_tuple *tuple,
 		const struct net *net)
 {
 	return nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
-	       net_eq(net, nf_ct_net(i->master)) &&
-	       nf_ct_zone_equal_any(i->master, zone);
+	       net_eq(net, read_pnet(&i->net)) &&
+	       nf_ct_exp_zone_equal_any(i, zone);
 }
 
 bool nf_ct_remove_expect(struct nf_conntrack_expect *exp)
@@ -326,6 +326,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 {
 	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conn *ct = exp->master;
+	struct net *net = read_pnet(&ct->ct_net);
 	struct nf_conn_help *help;
 	int len;
 
@@ -343,6 +344,10 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 		helper = rcu_dereference(help->helper);
 
 	rcu_assign_pointer(exp->helper, helper);
+	write_pnet(&exp->net, net);
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	exp->zone = ct->zone;
+#endif
 	exp->tuple.src.l3num = family;
 	exp->tuple.dst.protonum = proto;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 89540112d165..6e6aeb0ab0a1 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3538,6 +3538,7 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
+	struct net *net = read_pnet(&ct->ct_net);
 	struct nf_conntrack_expect *exp;
 	struct nf_conn_help *help;
 	u32 class = 0;
@@ -3577,6 +3578,10 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 
 	exp->class = class;
 	exp->master = ct;
+	write_pnet(&exp->net, net);
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	exp->zone = ct->zone;
+#endif
 	if (!helper)
 		helper = rcu_dereference(help->helper);
 	rcu_assign_pointer(exp->helper, helper);
-- 
cgit v1.2.3


From b341c1176f2e001b3adf0b47154fc31589f7410e Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 19 Mar 2026 19:38:12 +0100
Subject: spi: spi-fsl-lpspi: fix teardown order issue (UAF)

There is a teardown order issue in the driver. The SPI controller is
registered using devm_spi_register_controller(), which delays
unregistration of the SPI controller until after the fsl_lpspi_remove()
function returns.

As the fsl_lpspi_remove() function synchronously tears down the DMA
channels, a running SPI transfer triggers the following NULL pointer
dereference due to use after free:

| fsl_lpspi 42550000.spi: I/O Error in DMA RX
| Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[...]
| Call trace:
|  fsl_lpspi_dma_transfer+0x260/0x340 [spi_fsl_lpspi]
|  fsl_lpspi_transfer_one+0x198/0x448 [spi_fsl_lpspi]
|  spi_transfer_one_message+0x49c/0x7c8
|  __spi_pump_transfer_message+0x120/0x420
|  __spi_sync+0x2c4/0x520
|  spi_sync+0x34/0x60
|  spidev_message+0x20c/0x378 [spidev]
|  spidev_ioctl+0x398/0x750 [spidev]
[...]

Switch from devm_spi_register_controller() to spi_register_controller() in
fsl_lpspi_probe() and add the corresponding spi_unregister_controller() in
fsl_lpspi_remove().

Fixes: 5314987de5e5 ("spi: imx: add lpspi bus driver")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20260319-spi-fsl-lpspi-fixes-v1-1-b433e435b2d8@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index b361c1bb3e43..45390e9b8cae 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -1009,7 +1009,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 		enable_irq(irq);
 	}
 
-	ret = devm_spi_register_controller(&pdev->dev, controller);
+	ret = spi_register_controller(controller);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "spi_register_controller error\n");
 		goto free_dma;
@@ -1035,6 +1035,7 @@ static void fsl_lpspi_remove(struct platform_device *pdev)
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(controller);
 
+	spi_unregister_controller(controller);
 	fsl_lpspi_dma_exit(controller);
 
 	pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);
-- 
cgit v1.2.3


From 3db5647984de03d9cae0dcddb509b058351f0ee4 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 25 Mar 2026 14:11:06 +0100
Subject: netfilter: nf_conntrack_expect: skip expectations in other netns via
 proc

Skip expectations that do not reside in this netns.

Similar to e77e6ff502ea ("netfilter: conntrack: do not dump other netns's
conntrack entries via proc").

Fixes: 9b03f38d0487 ("netfilter: netns nf_conntrack: per-netns expectations")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_expect.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index db28801b1688..24d0576d84b7 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -652,11 +652,15 @@ static int exp_seq_show(struct seq_file *s, void *v)
 {
 	struct nf_conntrack_expect *expect;
 	struct nf_conntrack_helper *helper;
+	struct net *net = seq_file_net(s);
 	struct hlist_node *n = v;
 	char *delim = "";
 
 	expect = hlist_entry(n, struct nf_conntrack_expect, hnode);
 
+	if (!net_eq(nf_ct_exp_net(expect), net))
+		return 0;
+
 	if (expect->timeout.function)
 		seq_printf(s, "%ld ", timer_pending(&expect->timeout)
 			   ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
-- 
cgit v1.2.3


From 6a2b724460cb67caed500c508c2ae5cf012e4db4 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 25 Mar 2026 14:11:07 +0100
Subject: netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in
 process_sdp

process_sdp() declares union nf_inet_addr rtp_addr on the stack and
passes it to the nf_nat_sip sdp_session hook after walking the SDP
media descriptions. However rtp_addr is only initialized inside the
media loop when a recognized media type with a non-zero port is found.

If the SDP body contains no m= lines, only inactive media sections
(m=audio 0 ...) or only unrecognized media types, rtp_addr is never
assigned. Despite that, the function still calls hooks->sdp_session()
with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack
value as an IP address and rewrite the SDP session owner and connection
lines with it.

With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this
results in the session-level o= and c= addresses being rewritten to
0.0.0.0 for inactive SDP sessions. Without stack auto-init the
rewritten address is whatever happened to be on the stack.

Fix this by pre-initializing rtp_addr from the session-level connection
address (caddr) when available, and tracking via a have_rtp_addr flag
whether any valid address was established. Skip the sdp_session hook
entirely when no valid address exists.

Fixes: 4ab9e64e5e3c ("[NETFILTER]: nf_nat_sip: split up SDP mangling")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_sip.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 20e57cf5c83a..939502ff7c87 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -1040,6 +1040,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 	unsigned int port;
 	const struct sdp_media_type *t;
 	int ret = NF_ACCEPT;
+	bool have_rtp_addr = false;
 
 	hooks = rcu_dereference(nf_nat_sip_hooks);
 
@@ -1056,8 +1057,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 	caddr_len = 0;
 	if (ct_sip_parse_sdp_addr(ct, *dptr, sdpoff, *datalen,
 				  SDP_HDR_CONNECTION, SDP_HDR_MEDIA,
-				  &matchoff, &matchlen, &caddr) > 0)
+				  &matchoff, &matchlen, &caddr) > 0) {
 		caddr_len = matchlen;
+		memcpy(&rtp_addr, &caddr, sizeof(rtp_addr));
+		have_rtp_addr = true;
+	}
 
 	mediaoff = sdpoff;
 	for (i = 0; i < ARRAY_SIZE(sdp_media_types); ) {
@@ -1091,9 +1095,11 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 					  &matchoff, &matchlen, &maddr) > 0) {
 			maddr_len = matchlen;
 			memcpy(&rtp_addr, &maddr, sizeof(rtp_addr));
-		} else if (caddr_len)
+			have_rtp_addr = true;
+		} else if (caddr_len) {
 			memcpy(&rtp_addr, &caddr, sizeof(rtp_addr));
-		else {
+			have_rtp_addr = true;
+		} else {
 			nf_ct_helper_log(skb, ct, "cannot parse SDP message");
 			return NF_DROP;
 		}
@@ -1125,7 +1131,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff,
 
 	/* Update session connection and owner addresses */
 	hooks = rcu_dereference(nf_nat_sip_hooks);
-	if (hooks && ct->status & IPS_NAT_MASK)
+	if (hooks && ct->status & IPS_NAT_MASK && have_rtp_addr)
 		ret = hooks->sdp_session(skb, protoff, dataoff,
 					 dptr, datalen, sdpoff,
 					 &rtp_addr);
-- 
cgit v1.2.3


From 8f15b5071b4548b0aafc03b366eb45c9c6566704 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Wed, 25 Mar 2026 14:11:08 +0100
Subject: netfilter: ctnetlink: use netlink policy range checks

Replace manual range and mask validations with netlink policy
annotations in ctnetlink code paths, so that the netlink core rejects
invalid values early and can generate extack errors.

- CTA_PROTOINFO_TCP_STATE: reject values > TCP_CONNTRACK_SYN_SENT2 at
  policy level, removing the manual >= TCP_CONNTRACK_MAX check.
- CTA_PROTOINFO_TCP_WSCALE_ORIGINAL/REPLY: reject values > TCP_MAX_WSCALE
  (14). The normal TCP option parsing path already clamps to this value,
  but the ctnetlink path accepted 0-255, causing undefined behavior when
  used as a u32 shift count.
- CTA_FILTER_ORIG_FLAGS/REPLY_FLAGS: use NLA_POLICY_MASK with
  CTA_FILTER_F_ALL, removing the manual mask checks.
- CTA_EXPECT_FLAGS: use NLA_POLICY_MASK with NF_CT_EXPECT_MASK, adding
  a new mask define grouping all valid expect flags.

Extracted from a broader nf-next patch by Florian Westphal, scoped to
ctnetlink for the fixes tree.

Fixes: c8e2078cfe41 ("[NETFILTER]: ctnetlink: add support for internal tcp connection tracking flags handling")
Signed-off-by: David Carlier <devnexen@gmail.com>
Co-developed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_conntrack_common.h |  4 ++++
 net/netfilter/nf_conntrack_netlink.c               | 16 +++++-----------
 net/netfilter/nf_conntrack_proto_tcp.c             | 10 +++-------
 3 files changed, 12 insertions(+), 18 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 26071021e986..56b6b60a814f 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -159,5 +159,9 @@ enum ip_conntrack_expect_events {
 #define NF_CT_EXPECT_INACTIVE		0x2
 #define NF_CT_EXPECT_USERSPACE		0x4
 
+#ifdef __KERNEL__
+#define NF_CT_EXPECT_MASK	(NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE | \
+				 NF_CT_EXPECT_USERSPACE)
+#endif
 
 #endif /* _UAPI_NF_CONNTRACK_COMMON_H */
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 6e6aeb0ab0a1..3f408f3713bb 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -910,8 +910,8 @@ struct ctnetlink_filter {
 };
 
 static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = {
-	[CTA_FILTER_ORIG_FLAGS]		= { .type = NLA_U32 },
-	[CTA_FILTER_REPLY_FLAGS]	= { .type = NLA_U32 },
+	[CTA_FILTER_ORIG_FLAGS]		= NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL),
+	[CTA_FILTER_REPLY_FLAGS]	= NLA_POLICY_MASK(NLA_U32, CTA_FILTER_F_ALL),
 };
 
 static int ctnetlink_parse_filter(const struct nlattr *attr,
@@ -925,17 +925,11 @@ static int ctnetlink_parse_filter(const struct nlattr *attr,
 	if (ret)
 		return ret;
 
-	if (tb[CTA_FILTER_ORIG_FLAGS]) {
+	if (tb[CTA_FILTER_ORIG_FLAGS])
 		filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]);
-		if (filter->orig_flags & ~CTA_FILTER_F_ALL)
-			return -EOPNOTSUPP;
-	}
 
-	if (tb[CTA_FILTER_REPLY_FLAGS]) {
+	if (tb[CTA_FILTER_REPLY_FLAGS])
 		filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]);
-		if (filter->reply_flags & ~CTA_FILTER_F_ALL)
-			return -EOPNOTSUPP;
-	}
 
 	return 0;
 }
@@ -2634,7 +2628,7 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
 	[CTA_EXPECT_HELP_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = NF_CT_HELPER_NAME_LEN - 1 },
 	[CTA_EXPECT_ZONE]	= { .type = NLA_U16 },
-	[CTA_EXPECT_FLAGS]	= { .type = NLA_U32 },
+	[CTA_EXPECT_FLAGS]	= NLA_POLICY_MASK(NLA_BE32, NF_CT_EXPECT_MASK),
 	[CTA_EXPECT_CLASS]	= { .type = NLA_U32 },
 	[CTA_EXPECT_NAT]	= { .type = NLA_NESTED },
 	[CTA_EXPECT_FN]		= { .type = NLA_NUL_STRING },
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 0c1d086e96cb..b67426c2189b 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1385,9 +1385,9 @@ nla_put_failure:
 }
 
 static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = {
-	[CTA_PROTOINFO_TCP_STATE]	    = { .type = NLA_U8 },
-	[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 },
-	[CTA_PROTOINFO_TCP_WSCALE_REPLY]    = { .type = NLA_U8 },
+	[CTA_PROTOINFO_TCP_STATE]	    = NLA_POLICY_MAX(NLA_U8, TCP_CONNTRACK_SYN_SENT2),
+	[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE),
+	[CTA_PROTOINFO_TCP_WSCALE_REPLY]    = NLA_POLICY_MAX(NLA_U8, TCP_MAX_WSCALE),
 	[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]  = { .len = sizeof(struct nf_ct_tcp_flags) },
 	[CTA_PROTOINFO_TCP_FLAGS_REPLY]	    = { .len = sizeof(struct nf_ct_tcp_flags) },
 };
@@ -1414,10 +1414,6 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
 	if (err < 0)
 		return err;
 
-	if (tb[CTA_PROTOINFO_TCP_STATE] &&
-	    nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX)
-		return -EINVAL;
-
 	spin_lock_bh(&ct->lock);
 	if (tb[CTA_PROTOINFO_TCP_STATE])
 		ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]);
-- 
cgit v1.2.3


From e98137f0a874ab36d0946de4707aa48cb7137d1c Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@nvidia.com>
Date: Mon, 23 Mar 2026 15:56:58 -0600
Subject: vfio/pci: Fix double free in dma-buf feature

The error path through vfio_pci_core_feature_dma_buf() ignores its
own advice to only use dma_buf_put() after dma_buf_export(), instead
falling through the entire unwind chain.  In the unlikely event that
we encounter file descriptor exhaustion, this can result in an
unbalanced refcount on the vfio device and double free of allocated
objects.

Avoid this by moving the "put" directly into the error path and return
the errno rather than entering the unwind chain.

Reported-by: Renato Marziano <renato@marziano.top>
Fixes: 5d74781ebc86 ("vfio/pci: Add dma-buf export support for MMIO regions")
Cc: stable@vger.kernel.org
Acked-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@nvidia.com>
Link: https://lore.kernel.org/r/20260323215659.2108191-3-alex.williamson@nvidia.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Alex Williamson <alex@shazbot.org>
---
 drivers/vfio/pci/vfio_pci_dmabuf.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 478beafc6ac3..b1d658b8f7b5 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -301,11 +301,10 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 	 */
 	ret = dma_buf_fd(priv->dmabuf, get_dma_buf.open_flags);
 	if (ret < 0)
-		goto err_dma_buf;
+		dma_buf_put(priv->dmabuf);
+
 	return ret;
 
-err_dma_buf:
-	dma_buf_put(priv->dmabuf);
 err_dev_put:
 	vfio_device_put_registration(&vdev->vdev);
 err_free_phys:
-- 
cgit v1.2.3


From 72d96e4e24bbefdcfbc68bdb9341a05d8f5cb6e5 Mon Sep 17 00:00:00 2001
From: Paolo Valerio <pvalerio@redhat.com>
Date: Mon, 23 Mar 2026 20:16:34 +0100
Subject: net: macb: use the current queue number for stats

There's a potential mismatch between the memory reserved for statistics
and the amount of memory written.

gem_get_sset_count() correctly computes the number of stats based on the
active queues, whereas gem_get_ethtool_stats() indiscriminately copies
data using the maximum number of queues, and in the case the number of
active queues is less than MACB_MAX_QUEUES, this results in a OOB write
as observed in the KASAN splat.

==================================================================
BUG: KASAN: vmalloc-out-of-bounds in gem_get_ethtool_stats+0x54/0x78
  [macb]
Write of size 760 at addr ffff80008080b000 by task ethtool/1027

CPU: [...]
Tainted: [E]=UNSIGNED_MODULE
Hardware name: raspberrypi rpi/rpi, BIOS 2025.10 10/01/2025
Call trace:
 show_stack+0x20/0x38 (C)
 dump_stack_lvl+0x80/0xf8
 print_report+0x384/0x5e0
 kasan_report+0xa0/0xf0
 kasan_check_range+0xe8/0x190
 __asan_memcpy+0x54/0x98
 gem_get_ethtool_stats+0x54/0x78 [macb
   926c13f3af83b0c6fe64badb21ec87d5e93fcf65]
 dev_ethtool+0x1220/0x38c0
 dev_ioctl+0x4ac/0xca8
 sock_do_ioctl+0x170/0x1d8
 sock_ioctl+0x484/0x5d8
 __arm64_sys_ioctl+0x12c/0x1b8
 invoke_syscall+0xd4/0x258
 el0_svc_common.constprop.0+0xb4/0x240
 do_el0_svc+0x48/0x68
 el0_svc+0x40/0xf8
 el0t_64_sync_handler+0xa0/0xe8
 el0t_64_sync+0x1b0/0x1b8

The buggy address belongs to a 1-page vmalloc region starting at
  0xffff80008080b000 allocated at dev_ethtool+0x11f0/0x38c0
The buggy address belongs to the physical page:
page: refcount:1 mapcount:0 mapping:0000000000000000
  index:0xffff00000a333000 pfn:0xa333
flags: 0x7fffc000000000(node=0|zone=0|lastcpupid=0x1ffff)
raw: 007fffc000000000 0000000000000000 dead000000000122 0000000000000000
raw: ffff00000a333000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff80008080b080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff80008080b100: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
>ffff80008080b180: 00 00 00 00 00 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
                                  ^
 ffff80008080b200: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
 ffff80008080b280: f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8 f8
==================================================================

Fix it by making sure the copied size only considers the active number of
queues.

Fixes: 512286bbd4b7 ("net: macb: Added some queue statistics")
Signed-off-by: Paolo Valerio <pvalerio@redhat.com>
Reviewed-by: Nicolai Buchwitz <nb@tipi-net.de>
Link: https://patch.msgid.link/20260323191634.2185840-1-pvalerio@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index fc4dd0757646..99e7d5cf3786 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3224,7 +3224,7 @@ static void gem_get_ethtool_stats(struct net_device *dev,
 	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
-			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+			* (GEM_STATS_LEN + QUEUE_STATS_LEN * bp->num_queues));
 	spin_unlock_irq(&bp->stats_lock);
 }
 
-- 
cgit v1.2.3


From b59efde9e6c122207c16169d3d0deb623956eae9 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 26 Mar 2026 07:02:53 -0600
Subject: io_uring/fdinfo: fix SQE_MIXED SQE displaying

When displaying pending SQEs for a MIXED ring, each 128-byte SQE
increments sq_head to skip the second slot, but the loop counter is not
adjusted. This can cause the loop to read past sq_tail by one entry for
each 128-byte SQE encountered, displaying SQEs that haven't been made
consumable yet by the application.

Match the kernel's own consumption logic in io_init_req() which
decrements what's left when consuming the extra slot.

Fixes: 1cba30bf9fdd ("io_uring: add support for IORING_SETUP_SQE_MIXED")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/fdinfo.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 80178b69e05a..25c92ace18bd 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -125,6 +125,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 					sq_idx);
 				break;
 			}
+			i++;
 			sqe128 = true;
 		}
 		seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, "
-- 
cgit v1.2.3


From 70685c291ef82269180758130394ecdc4496b52c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 23 Mar 2026 14:01:57 -0700
Subject: xfs: don't irele after failing to iget in xfs_attri_recover_work

xlog_recovery_iget* never set @ip to a valid pointer if they return
an error, so this irele will walk off a dangling pointer.  Fix that.

Cc: stable@vger.kernel.org # v6.10
Fixes: ae673f534a3097 ("xfs: record inode generation in xattr update log intent items")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Long Li <leo.lilong@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_attr_item.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index 82324f42537b..deab14f31b38 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -653,7 +653,6 @@ xfs_attri_recover_work(
 		break;
 	}
 	if (error) {
-		xfs_irele(ip);
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attrp,
 				sizeof(*attrp));
 		return ERR_PTR(-EFSCORRUPTED);
-- 
cgit v1.2.3


From e31c53a8060e134111ed095783fee0aa0c43b080 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 23 Mar 2026 14:04:33 -0700
Subject: xfs: remove file_path tracepoint data

The xfile/xmbuf shmem file descriptions are no longer as detailed as
they were when online fsck was first merged, because moving to static
strings in commit 60382993a2e180 ("xfs: get rid of the
xchk_xfile_*_descr calls") removed a memory allocation and hence a
source of failure.

However this makes encoding the description in the tracepoints sort of a
waste of memory.  David Laight also points out that file_path doesn't
zero the whole buffer which causes exposure of stale trace bytes, and
Steven Rostedt wonders why we're not using a dynamic array for the file
path.

I don't think this is worth fixing, so let's just rip it out.

Cc: rostedt@goodmis.org
Cc: david.laight.linux@gmail.com
Link: https://lore.kernel.org/linux-xfs/20260323172204.work.979-kees@kernel.org/
Cc: stable@vger.kernel.org # v6.11
Fixes: 19ebc8f84ea12e ("xfs: fix file_path handling in tracepoints")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/scrub/trace.h | 12 ++----------
 fs/xfs/xfs_trace.h   | 11 ++---------
 2 files changed, 4 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 39ea651cbb75..286c5f5e0544 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -972,20 +972,12 @@ TRACE_EVENT(xfile_create,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		*path;
-
 		__entry->ino = file_inode(xf->file)->i_ino;
-		path = file_path(xf->file, __entry->pathname, MAXNAMELEN);
-		if (IS_ERR(path))
-			strncpy(__entry->pathname, "(unknown)",
-					sizeof(__entry->pathname));
 	),
-	TP_printk("xfino 0x%lx path '%s'",
-		  __entry->ino,
-		  __entry->pathname)
+	TP_printk("xfino 0x%lx",
+		  __entry->ino)
 );
 
 TRACE_EVENT(xfile_destroy,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 0e994b3f768f..5e8190fe2be9 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -5119,23 +5119,16 @@ TRACE_EVENT(xmbuf_create,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(unsigned long, ino)
-		__array(char, pathname, MAXNAMELEN)
 	),
 	TP_fast_assign(
-		char		*path;
 		struct file	*file = btp->bt_file;
 
 		__entry->dev = btp->bt_mount->m_super->s_dev;
 		__entry->ino = file_inode(file)->i_ino;
-		path = file_path(file, __entry->pathname, MAXNAMELEN);
-		if (IS_ERR(path))
-			strncpy(__entry->pathname, "(unknown)",
-					sizeof(__entry->pathname));
 	),
-	TP_printk("dev %d:%d xmino 0x%lx path '%s'",
+	TP_printk("dev %d:%d xmino 0x%lx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->pathname)
+		  __entry->ino)
 );
 
 TRACE_EVENT(xmbuf_free,
-- 
cgit v1.2.3


From 0e764b9d46071668969410ec5429be0e2f38c6d3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 25 Mar 2026 08:20:17 +0000
Subject: netfs: Fix the handling of stream->front by removing it

The netfs_io_stream::front member is meant to point to the subrequest
currently being collected on a stream, but it isn't actually used this way
by direct write (which mostly ignores it).  However, there's a tracepoint
which looks at it.  Further, stream->front is actually redundant with
stream->subrequests.next.

Fix the potential problem in the direct code by just removing the member
and using stream->subrequests.next instead, thereby also simplifying the
code.

Fixes: a0b4c7a49137 ("netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence")
Reported-by: Paulo Alcantara <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/4158599.1774426817@warthog.procyon.org.uk
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_read.c     | 3 +--
 fs/netfs/direct_read.c       | 3 +--
 fs/netfs/direct_write.c      | 1 -
 fs/netfs/read_collect.c      | 4 ++--
 fs/netfs/read_single.c       | 1 -
 fs/netfs/write_collect.c     | 4 ++--
 fs/netfs/write_issue.c       | 3 +--
 include/linux/netfs.h        | 1 -
 include/trace/events/netfs.h | 8 ++++----
 9 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 88a0d801525f..a8c0d86118c5 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -171,9 +171,8 @@ static void netfs_queue_read(struct netfs_io_request *rreq,
 	spin_lock(&rreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-		stream->front = subreq;
 		if (!stream->active) {
-			stream->collected_to = stream->front->start;
+			stream->collected_to = subreq->start;
 			/* Store list pointers before active flag */
 			smp_store_release(&stream->active, true);
 		}
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
index a498ee8d6674..f72e6da88cca 100644
--- a/fs/netfs/direct_read.c
+++ b/fs/netfs/direct_read.c
@@ -71,9 +71,8 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 		spin_lock(&rreq->lock);
 		list_add_tail(&subreq->rreq_link, &stream->subrequests);
 		if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-			stream->front = subreq;
 			if (!stream->active) {
-				stream->collected_to = stream->front->start;
+				stream->collected_to = subreq->start;
 				/* Store list pointers before active flag */
 				smp_store_release(&stream->active, true);
 			}
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 4d9760e36c11..f9ab69de3e29 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -111,7 +111,6 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq)
 			netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred);
 			subreq = stream->construct;
 			stream->construct = NULL;
-			stream->front = NULL;
 		}
 
 		/* Check if (re-)preparation failed. */
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index 137f0e28a44c..e5f6665b3341 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -205,7 +205,8 @@ reassess:
 	 * in progress.  The issuer thread may be adding stuff to the tail
 	 * whilst we're doing this.
 	 */
-	front = READ_ONCE(stream->front);
+	front = list_first_entry_or_null(&stream->subrequests,
+					 struct netfs_io_subrequest, rreq_link);
 	while (front) {
 		size_t transferred;
 
@@ -301,7 +302,6 @@ reassess:
 		list_del_init(&front->rreq_link);
 		front = list_first_entry_or_null(&stream->subrequests,
 						 struct netfs_io_subrequest, rreq_link);
-		stream->front = front;
 		spin_unlock(&rreq->lock);
 		netfs_put_subrequest(remove,
 				     notes & ABANDON_SREQ ?
diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c
index 8e6264f62a8f..d0e23bc42445 100644
--- a/fs/netfs/read_single.c
+++ b/fs/netfs/read_single.c
@@ -107,7 +107,6 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 	spin_lock(&rreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	trace_netfs_sreq(subreq, netfs_sreq_trace_added);
-	stream->front = subreq;
 	/* Store list pointers before active flag */
 	smp_store_release(&stream->active, true);
 	spin_unlock(&rreq->lock);
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 83eb3dc1adf8..b194447f4b11 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -228,7 +228,8 @@ reassess_streams:
 		if (!smp_load_acquire(&stream->active))
 			continue;
 
-		front = stream->front;
+		front = list_first_entry_or_null(&stream->subrequests,
+						 struct netfs_io_subrequest, rreq_link);
 		while (front) {
 			trace_netfs_collect_sreq(wreq, front);
 			//_debug("sreq [%x] %llx %zx/%zx",
@@ -279,7 +280,6 @@ reassess_streams:
 			list_del_init(&front->rreq_link);
 			front = list_first_entry_or_null(&stream->subrequests,
 							 struct netfs_io_subrequest, rreq_link);
-			stream->front = front;
 			spin_unlock(&wreq->lock);
 			netfs_put_subrequest(remove,
 					     notes & SAW_FAILURE ?
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 437268f65640..2db688f94125 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -206,9 +206,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq,
 	spin_lock(&wreq->lock);
 	list_add_tail(&subreq->rreq_link, &stream->subrequests);
 	if (list_is_first(&subreq->rreq_link, &stream->subrequests)) {
-		stream->front = subreq;
 		if (!stream->active) {
-			stream->collected_to = stream->front->start;
+			stream->collected_to = subreq->start;
 			/* Write list pointers before active flag */
 			smp_store_release(&stream->active, true);
 		}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 72ee7d210a74..ba17ac5bf356 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -140,7 +140,6 @@ struct netfs_io_stream {
 	void (*issue_write)(struct netfs_io_subrequest *subreq);
 	/* Collection tracking */
 	struct list_head	subrequests;	/* Contributory I/O operations */
-	struct netfs_io_subrequest *front;	/* Op being collected */
 	unsigned long long	collected_to;	/* Position we've collected results to */
 	size_t			transferred;	/* The amount transferred from this stream */
 	unsigned short		error;		/* Aggregate error for the stream */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 2d366be46a1c..cbe28211106c 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -740,19 +740,19 @@ TRACE_EVENT(netfs_collect_stream,
 		    __field(unsigned int,	wreq)
 		    __field(unsigned char,	stream)
 		    __field(unsigned long long,	collected_to)
-		    __field(unsigned long long,	front)
+		    __field(unsigned long long,	issued_to)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->wreq	= wreq->debug_id;
 		    __entry->stream	= stream->stream_nr;
 		    __entry->collected_to = stream->collected_to;
-		    __entry->front	= stream->front ? stream->front->start : UINT_MAX;
+		    __entry->issued_to	= atomic64_read(&wreq->issued_to);
 			   ),
 
-	    TP_printk("R=%08x[%x:] cto=%llx frn=%llx",
+	    TP_printk("R=%08x[%x:] cto=%llx ito=%llx",
 		      __entry->wreq, __entry->stream,
-		      __entry->collected_to, __entry->front)
+		      __entry->collected_to, __entry->issued_to)
 	    );
 
 TRACE_EVENT(netfs_folioq,
-- 
cgit v1.2.3


From cfe02147e86307a17057ee4e3604f5f5919571d2 Mon Sep 17 00:00:00 2001
From: Jassi Brar <jassisinghbrar@gmail.com>
Date: Sun, 22 Mar 2026 12:15:33 -0500
Subject: irqchip/qcom-mpm: Add missing mailbox TX done acknowledgment

The mbox_client for qcom-mpm sends NULL doorbell messages via
mbox_send_message() but never signals TX completion.

Set knows_txdone=true and call mbox_client_txdone() after a successful
send, matching the pattern used by other Qualcomm mailbox clients (smp2p,
smsm, qcom_aoss etc).

Fixes: a6199bb514d8a6 "irqchip: Add Qualcomm MPM controller driver"
Signed-off-by: Jassi Brar <jassisinghbrar@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260322171533.608436-1-jassisinghbrar@gmail.com
---
 drivers/irqchip/irq-qcom-mpm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c
index 83f31ea657b7..181320528a47 100644
--- a/drivers/irqchip/irq-qcom-mpm.c
+++ b/drivers/irqchip/irq-qcom-mpm.c
@@ -306,6 +306,8 @@ static int mpm_pd_power_off(struct generic_pm_domain *genpd)
 	if (ret < 0)
 		return ret;
 
+	mbox_client_txdone(priv->mbox_chan, 0);
+
 	return 0;
 }
 
@@ -434,6 +436,7 @@ static int qcom_mpm_probe(struct platform_device *pdev, struct device_node *pare
 	}
 
 	priv->mbox_client.dev = dev;
+	priv->mbox_client.knows_txdone = true;
 	priv->mbox_chan = mbox_request_channel(&priv->mbox_client, 0);
 	if (IS_ERR(priv->mbox_chan)) {
 		ret = PTR_ERR(priv->mbox_chan);
-- 
cgit v1.2.3


From 0f54755343f56ac108cfd55173bc1b5c5376384d Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:10 +0100
Subject: KVM: s390: vsie: Fix dat_split_ste()

If the guest misbehaves and puts the page tables for its nested guest
inside the memory of the nested guest itself, and the guest and nested
guest are being mapped with large pages, the shadow mapping will
lose synchronization with the actual mapping, since this will cause the
large page with the vsie notification bit to be split, but the
vsie notification bit will not be propagated to the resulting small
pages.

Fix this by propagating the vsie_notif bit from large pages to normal
pages when splitting a large page.

Fixes: 2db149a0a6c5 ("KVM: s390: KVM page table management functions: walks")
Reviewed-by: Christoph Schlameuss <schlameuss@linux.ibm.com>
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/dat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index 670404d4fa44..48b5f2bcf172 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -292,6 +292,7 @@ static int dat_split_ste(struct kvm_s390_mmu_cache *mc, union pmd *pmdp, gfn_t g
 				pt->ptes[i].val = init.val | i * PAGE_SIZE;
 			/* No need to take locks as the page table is not installed yet. */
 			pgste_init.prefix_notif = old.s.fc1.prefix_notif;
+			pgste_init.vsie_notif = old.s.fc1.vsie_notif;
 			pgste_init.pcl = uses_skeys && init.h.i;
 			dat_init_pgstes(pt, pgste_init.val);
 		} else {
-- 
cgit v1.2.3


From 897cf98926429c8671a9009442883c2f62deae96 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Mon, 23 Mar 2026 12:49:14 +0000
Subject: irqchip/renesas-rzv2h: Fix error path in rzv2h_icu_probe_common()

Replace pm_runtime_put() with pm_runtime_put_sync() when
irq_domain_create_hierarchy() fails to ensure the device suspends
synchronously before devres cleanup disables runtime PM via
pm_runtime_disable().

Fixes: 5ec8cabc3b86 ("irqchip/renesas-rzv2h: Use devm_pm_runtime_enable()")
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260323124917.41602-1-biju.das.jz@bp.renesas.com
---
 drivers/irqchip/irq-renesas-rzv2h.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-renesas-rzv2h.c b/drivers/irqchip/irq-renesas-rzv2h.c
index da2bc43a0e12..03e93b061edd 100644
--- a/drivers/irqchip/irq-renesas-rzv2h.c
+++ b/drivers/irqchip/irq-renesas-rzv2h.c
@@ -621,7 +621,7 @@ static int rzv2h_icu_probe_common(struct platform_device *pdev, struct device_no
 	return 0;
 
 pm_put:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 
 	return ret;
 }
-- 
cgit v1.2.3


From b827ef02f409bd42c7e7fb82663b84753c0e5d14 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:11 +0100
Subject: KVM: s390: Remove non-atomic dat_crstep_xchg()

In practice dat_crstep_xchg() is racy and hard to use correctly. Simply
remove it and replace its uses with dat_crstep_xchg_atomic().

This solves some actual races that lead to system hangs / crashes.

Opportunistically fix an alignment issue in _gmap_crstep_xchg_atomic().

Fixes: 589071eaaa8f ("KVM: s390: KVM page table management functions: clear and replace")
Fixes: 94fd9b16cc67 ("KVM: s390: KVM page table management functions: lifecycle management")
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/dat.c     | 51 +++++++++---------------------
 arch/s390/kvm/dat.h     |  9 ++++--
 arch/s390/kvm/gaccess.c | 26 +++++++++-------
 arch/s390/kvm/gmap.c    | 82 +++++++++++++++++++++++++++++--------------------
 arch/s390/kvm/gmap.h    | 29 +++++++++--------
 5 files changed, 100 insertions(+), 97 deletions(-)

diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index 48b5f2bcf172..4d44c0f9ad45 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -134,32 +134,6 @@ int dat_set_asce_limit(struct kvm_s390_mmu_cache *mc, union asce *asce, int newt
 	return 0;
 }
 
-/**
- * dat_crstep_xchg() - Exchange a gmap CRSTE with another.
- * @crstep: Pointer to the CRST entry
- * @new: Replacement entry.
- * @gfn: The affected guest address.
- * @asce: The ASCE of the address space.
- *
- * Context: This function is assumed to be called with kvm->mmu_lock held.
- */
-void dat_crstep_xchg(union crste *crstep, union crste new, gfn_t gfn, union asce asce)
-{
-	if (crstep->h.i) {
-		WRITE_ONCE(*crstep, new);
-		return;
-	} else if (cpu_has_edat2()) {
-		crdte_crste(crstep, *crstep, new, gfn, asce);
-		return;
-	}
-
-	if (machine_has_tlb_guest())
-		idte_crste(crstep, gfn, IDTE_GUEST_ASCE, asce, IDTE_GLOBAL);
-	else
-		idte_crste(crstep, gfn, 0, NULL_ASCE, IDTE_GLOBAL);
-	WRITE_ONCE(*crstep, new);
-}
-
 /**
  * dat_crstep_xchg_atomic() - Atomically exchange a gmap CRSTE with another.
  * @crstep: Pointer to the CRST entry.
@@ -175,8 +149,8 @@ void dat_crstep_xchg(union crste *crstep, union crste new, gfn_t gfn, union asce
  *
  * Return: %true if the exchange was successful.
  */
-bool dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new, gfn_t gfn,
-			    union asce asce)
+bool __must_check dat_crstep_xchg_atomic(union crste *crstep, union crste old, union crste new,
+					 gfn_t gfn, union asce asce)
 {
 	if (old.h.i)
 		return arch_try_cmpxchg((long *)crstep, &old.val, new.val);
@@ -894,7 +868,8 @@ static long _dat_slot_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct d
 
 	/* This table entry needs to be updated. */
 	if (walk->start <= gfn && walk->end >= next) {
-		dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce);
+		if (!dat_crstep_xchg_atomic(crstep, crste, new_crste, gfn, walk->asce))
+			return -EINVAL;
 		/* A lower level table was present, needs to be freed. */
 		if (!crste.h.fc && !crste.h.i) {
 			if (is_pmd(crste))
@@ -1072,17 +1047,19 @@ int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level,
 
 static long dat_set_pn_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
 {
-	union crste crste = READ_ONCE(*crstep);
+	union crste newcrste, oldcrste;
 	int *n = walk->priv;
 
-	if (!crste.h.fc || crste.h.i || crste.h.p)
-		return 0;
-
+	do {
+		oldcrste = READ_ONCE(*crstep);
+		if (!oldcrste.h.fc || oldcrste.h.i || oldcrste.h.p)
+			return 0;
+		if (oldcrste.s.fc1.prefix_notif)
+			break;
+		newcrste = oldcrste;
+		newcrste.s.fc1.prefix_notif = 1;
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, walk->asce));
 	*n = 2;
-	if (crste.s.fc1.prefix_notif)
-		return 0;
-	crste.s.fc1.prefix_notif = 1;
-	dat_crstep_xchg(crstep, crste, gfn, walk->asce);
 	return 0;
 }
 
diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h
index 123e11dcd70d..22dafc775335 100644
--- a/arch/s390/kvm/dat.h
+++ b/arch/s390/kvm/dat.h
@@ -938,11 +938,14 @@ static inline bool dat_pudp_xchg_atomic(union pud *pudp, union pud old, union pu
 	return dat_crstep_xchg_atomic(_CRSTEP(pudp), _CRSTE(old), _CRSTE(new), gfn, asce);
 }
 
-static inline void dat_crstep_clear(union crste *crstep, gfn_t gfn, union asce asce)
+static inline union crste dat_crstep_clear_atomic(union crste *crstep, gfn_t gfn, union asce asce)
 {
-	union crste newcrste = _CRSTE_EMPTY(crstep->h.tt);
+	union crste oldcrste, empty = _CRSTE_EMPTY(crstep->h.tt);
 
-	dat_crstep_xchg(crstep, newcrste, gfn, asce);
+	do {
+		oldcrste = READ_ONCE(*crstep);
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, empty, gfn, asce));
+	return oldcrste;
 }
 
 static inline int get_level(union crste *crstep, union pte *ptep)
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a9da9390867d..4ee862424ca0 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1456,7 +1456,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, union crste *table,
 			    struct guest_fault *f, bool p)
 {
-	union crste newcrste;
+	union crste newcrste, oldcrste;
 	gfn_t gfn;
 	int rc;
 
@@ -1469,16 +1469,20 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 	if (rc)
 		return rc;
 
-	newcrste = _crste_fc1(f->pfn, host->h.tt, f->writable, !p);
-	newcrste.s.fc1.d |= host->s.fc1.d;
-	newcrste.s.fc1.sd |= host->s.fc1.sd;
-	newcrste.h.p &= host->h.p;
-	newcrste.s.fc1.vsie_notif = 1;
-	newcrste.s.fc1.prefix_notif = host->s.fc1.prefix_notif;
-	_gmap_crstep_xchg(sg->parent, host, newcrste, f->gfn, false);
-
-	newcrste = _crste_fc1(f->pfn, host->h.tt, 0, !p);
-	dat_crstep_xchg(table, newcrste, gpa_to_gfn(raddr), sg->asce);
+	do {
+		oldcrste = READ_ONCE(*host);
+		newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, f->writable, !p);
+		newcrste.s.fc1.d |= oldcrste.s.fc1.d;
+		newcrste.s.fc1.sd |= oldcrste.s.fc1.sd;
+		newcrste.h.p &= oldcrste.h.p;
+		newcrste.s.fc1.vsie_notif = 1;
+		newcrste.s.fc1.prefix_notif = oldcrste.s.fc1.prefix_notif;
+	} while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false));
+
+	newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p);
+	gfn = gpa_to_gfn(raddr);
+	while (!dat_crstep_xchg_atomic(table, READ_ONCE(*table), newcrste, gfn, sg->asce))
+		;
 	return 0;
 }
 
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index ef0c6ebfdde2..956be4c01797 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -313,13 +313,16 @@ static long gmap_clear_young_crste(union crste *crstep, gfn_t gfn, gfn_t end, st
 	struct clear_young_pte_priv *priv = walk->priv;
 	union crste crste, new;
 
-	crste = READ_ONCE(*crstep);
+	do {
+		crste = READ_ONCE(*crstep);
+
+		if (!crste.h.fc)
+			return 0;
+		if (!crste.s.fc1.y && crste.h.i)
+			return 0;
+		if (crste_prefix(crste) && !gmap_mkold_prefix(priv->gmap, gfn, end))
+			break;
 
-	if (!crste.h.fc)
-		return 0;
-	if (!crste.s.fc1.y && crste.h.i)
-		return 0;
-	if (!crste_prefix(crste) || gmap_mkold_prefix(priv->gmap, gfn, end)) {
 		new = crste;
 		new.h.i = 1;
 		new.s.fc1.y = 0;
@@ -328,8 +331,8 @@ static long gmap_clear_young_crste(union crste *crstep, gfn_t gfn, gfn_t end, st
 			folio_set_dirty(phys_to_folio(crste_origin_large(crste)));
 		new.s.fc1.d = 0;
 		new.h.p = 1;
-		dat_crstep_xchg(crstep, new, gfn, walk->asce);
-	}
+	} while (!dat_crstep_xchg_atomic(crstep, crste, new, gfn, walk->asce));
+
 	priv->young = 1;
 	return 0;
 }
@@ -391,14 +394,18 @@ static long _gmap_unmap_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct
 {
 	struct gmap_unmap_priv *priv = walk->priv;
 	struct folio *folio = NULL;
+	union crste old = *crstep;
 
-	if (crstep->h.fc) {
-		if (crstep->s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags))
-			folio = phys_to_folio(crste_origin_large(*crstep));
-		gmap_crstep_xchg(priv->gmap, crstep, _CRSTE_EMPTY(crstep->h.tt), gfn);
-		if (folio)
-			uv_convert_from_secure_folio(folio);
-	}
+	if (!old.h.fc)
+		return 0;
+
+	if (old.s.fc1.pr && test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &priv->gmap->flags))
+		folio = phys_to_folio(crste_origin_large(old));
+	/* No races should happen because kvm->mmu_lock is held in write mode */
+	KVM_BUG_ON(!gmap_crstep_xchg_atomic(priv->gmap, crstep, old, _CRSTE_EMPTY(old.h.tt), gfn),
+		   priv->gmap->kvm);
+	if (folio)
+		uv_convert_from_secure_folio(folio);
 
 	return 0;
 }
@@ -474,23 +481,24 @@ static long _crste_test_and_clear_softdirty(union crste *table, gfn_t gfn, gfn_t
 
 	if (fatal_signal_pending(current))
 		return 1;
-	crste = READ_ONCE(*table);
-	if (!crste.h.fc)
-		return 0;
-	if (crste.h.p && !crste.s.fc1.sd)
-		return 0;
+	do {
+		crste = READ_ONCE(*table);
+		if (!crste.h.fc)
+			return 0;
+		if (crste.h.p && !crste.s.fc1.sd)
+			return 0;
 
-	/*
-	 * If this large page contains one or more prefixes of vCPUs that are
-	 * currently running, do not reset the protection, leave it marked as
-	 * dirty.
-	 */
-	if (!crste.s.fc1.prefix_notif || gmap_mkold_prefix(gmap, gfn, end)) {
+		/*
+		 * If this large page contains one or more prefixes of vCPUs that are
+		 * currently running, do not reset the protection, leave it marked as
+		 * dirty.
+		 */
+		if (crste.s.fc1.prefix_notif && !gmap_mkold_prefix(gmap, gfn, end))
+			break;
 		new = crste;
 		new.h.p = 1;
 		new.s.fc1.sd = 0;
-		gmap_crstep_xchg(gmap, table, new, gfn);
-	}
+	} while (!gmap_crstep_xchg_atomic(gmap, table, crste, new, gfn));
 
 	for ( ; gfn < end; gfn++)
 		mark_page_dirty(gmap->kvm, gfn);
@@ -646,8 +654,8 @@ int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fau
 static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap,
 			     gfn_t p_gfn, gfn_t c_gfn, bool force_alloc)
 {
+	union crste newcrste, oldcrste;
 	struct page_table *pt;
-	union crste newcrste;
 	union crste *crstep;
 	union pte *ptep;
 	int rc;
@@ -673,7 +681,11 @@ static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap,
 			    &crstep, &ptep);
 	if (rc)
 		return rc;
-	dat_crstep_xchg(crstep, newcrste, c_gfn, gmap->asce);
+	do {
+		oldcrste = READ_ONCE(*crstep);
+		if (oldcrste.val == newcrste.val)
+			break;
+	} while (!dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, c_gfn, gmap->asce));
 	return 0;
 }
 
@@ -777,8 +789,10 @@ static void gmap_ucas_unmap_one(struct gmap *gmap, gfn_t c_gfn)
 	int rc;
 
 	rc = dat_entry_walk(NULL, c_gfn, gmap->asce, 0, TABLE_TYPE_SEGMENT, &crstep, &ptep);
-	if (!rc)
-		dat_crstep_xchg(crstep, _PMD_EMPTY, c_gfn, gmap->asce);
+	if (rc)
+		return;
+	while (!dat_crstep_xchg_atomic(crstep, READ_ONCE(*crstep), _PMD_EMPTY, c_gfn, gmap->asce))
+		;
 }
 
 void gmap_ucas_unmap(struct gmap *gmap, gfn_t c_gfn, unsigned long count)
@@ -1017,8 +1031,8 @@ static void gmap_unshadow_level(struct gmap *sg, gfn_t r_gfn, int level)
 			dat_ptep_xchg(ptep, _PTE_EMPTY, r_gfn, sg->asce, uses_skeys(sg));
 		return;
 	}
-	crste = READ_ONCE(*crstep);
-	dat_crstep_clear(crstep, r_gfn, sg->asce);
+
+	crste = dat_crstep_clear_atomic(crstep, r_gfn, sg->asce);
 	if (crste_leaf(crste) || crste.h.i)
 		return;
 	if (is_pmd(crste))
diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h
index ccb5cd751e31..150e91e15ee0 100644
--- a/arch/s390/kvm/gmap.h
+++ b/arch/s390/kvm/gmap.h
@@ -194,35 +194,40 @@ static inline union pgste gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, uni
 	return _gmap_ptep_xchg(gmap, ptep, newpte, pgste, gfn, true);
 }
 
-static inline void _gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne,
-				     gfn_t gfn, bool needs_lock)
+static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep,
+							 union crste oldcrste, union crste newcrste,
+							 gfn_t gfn, bool needs_lock)
 {
-	unsigned long align = 8 + (is_pmd(*crstep) ? 0 : 11);
+	unsigned long align = is_pmd(newcrste) ? _PAGE_ENTRIES : _PAGE_ENTRIES * _CRST_ENTRIES;
+
+	if (KVM_BUG_ON(crstep->h.tt != oldcrste.h.tt || newcrste.h.tt != oldcrste.h.tt, gmap->kvm))
+		return true;
 
 	lockdep_assert_held(&gmap->kvm->mmu_lock);
 	if (!needs_lock)
 		lockdep_assert_held(&gmap->children_lock);
 
 	gfn = ALIGN_DOWN(gfn, align);
-	if (crste_prefix(*crstep) && (ne.h.p || ne.h.i || !crste_prefix(ne))) {
-		ne.s.fc1.prefix_notif = 0;
+	if (crste_prefix(oldcrste) && (newcrste.h.p || newcrste.h.i || !crste_prefix(newcrste))) {
+		newcrste.s.fc1.prefix_notif = 0;
 		gmap_unmap_prefix(gmap, gfn, gfn + align);
 	}
-	if (crste_leaf(*crstep) && crstep->s.fc1.vsie_notif &&
-	    (ne.h.p || ne.h.i || !ne.s.fc1.vsie_notif)) {
-		ne.s.fc1.vsie_notif = 0;
+	if (crste_leaf(oldcrste) && oldcrste.s.fc1.vsie_notif &&
+	    (newcrste.h.p || newcrste.h.i || !newcrste.s.fc1.vsie_notif)) {
+		newcrste.s.fc1.vsie_notif = 0;
 		if (needs_lock)
 			gmap_handle_vsie_unshadow_event(gmap, gfn);
 		else
 			_gmap_handle_vsie_unshadow_event(gmap, gfn);
 	}
-	dat_crstep_xchg(crstep, ne, gfn, gmap->asce);
+	return dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, gmap->asce);
 }
 
-static inline void gmap_crstep_xchg(struct gmap *gmap, union crste *crstep, union crste ne,
-				    gfn_t gfn)
+static inline bool __must_check gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep,
+							union crste oldcrste, union crste newcrste,
+							gfn_t gfn)
 {
-	return _gmap_crstep_xchg(gmap, crstep, ne, gfn, true);
+	return _gmap_crstep_xchg_atomic(gmap, crstep, oldcrste, newcrste, gfn, true);
 }
 
 /**
-- 
cgit v1.2.3


From 6f93d1ed6f46b7b0be288cc45250d67bceb28982 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:12 +0100
Subject: KVM: s390: vsie: Fix check for pre-existing shadow mapping

When shadowing a nested guest, a check is performed and no shadowing is
attempted if the nested guest is already shadowed.

The existing check was incomplete; fix it by also checking whether the
leaf DAT table entry in the existing shadow gmap has the same protection
as the one specified in the guest DAT entry.

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 4ee862424ca0..8fd690255e1b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1506,8 +1506,9 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 	if (rc)
 		return rc;
 
-	/* A race occourred. The shadow mapping is already valid, nothing to do */
-	if ((ptep && !ptep->h.i) || (!ptep && crste_leaf(*table)))
+	/* A race occurred. The shadow mapping is already valid, nothing to do */
+	if ((ptep && !ptep->h.i && ptep->h.p == w->p) ||
+	    (!ptep && crste_leaf(*table) && !table->h.i && table->h.p == w->p))
 		return 0;
 
 	gl = get_level(table, ptep);
-- 
cgit v1.2.3


From 45921d0212d4a335680854c89a14efd01eae911a Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:13 +0100
Subject: KVM: s390: Fix gmap_link()

The slow path of the fault handler ultimately called gmap_link(), which
assumed the fault was a major fault, and blindly called dat_link().

In case of minor faults, things were not always handled properly; in
particular the prefix and vsie marker bits were ignored.

Move dat_link() into gmap.c, renaming it accordingly. Once moved, the
new _gmap_link() function will be able to correctly honour the prefix
and vsie markers.

This will cause spurious unshadows in some uncommon cases.

Fixes: 94fd9b16cc67 ("KVM: s390: KVM page table management functions: lifecycle management")
Fixes: a2c17f9270cc ("KVM: s390: New gmap code")
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/dat.c  | 48 --------------------------------------------
 arch/s390/kvm/dat.h  |  2 --
 arch/s390/kvm/gmap.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 52 insertions(+), 54 deletions(-)

diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index 4d44c0f9ad45..7b8d70fe406d 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -997,54 +997,6 @@ bool dat_test_age_gfn(union asce asce, gfn_t start, gfn_t end)
 	return _dat_walk_gfn_range(start, end, asce, &test_age_ops, 0, NULL) > 0;
 }
 
-int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level,
-	     bool uses_skeys, struct guest_fault *f)
-{
-	union crste oldval, newval;
-	union pte newpte, oldpte;
-	union pgste pgste;
-	int rc = 0;
-
-	rc = dat_entry_walk(mc, f->gfn, asce, DAT_WALK_ALLOC_CONTINUE, level, &f->crstep, &f->ptep);
-	if (rc == -EINVAL || rc == -ENOMEM)
-		return rc;
-	if (rc)
-		return -EAGAIN;
-
-	if (WARN_ON_ONCE(unlikely(get_level(f->crstep, f->ptep) > level)))
-		return -EINVAL;
-
-	if (f->ptep) {
-		pgste = pgste_get_lock(f->ptep);
-		oldpte = *f->ptep;
-		newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page);
-		newpte.s.sd = oldpte.s.sd;
-		oldpte.s.sd = 0;
-		if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) {
-			pgste = __dat_ptep_xchg(f->ptep, pgste, newpte, f->gfn, asce, uses_skeys);
-			if (f->callback)
-				f->callback(f);
-		} else {
-			rc = -EAGAIN;
-		}
-		pgste_set_unlock(f->ptep, pgste);
-	} else {
-		oldval = READ_ONCE(*f->crstep);
-		newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable,
-				    f->write_attempt | oldval.s.fc1.d);
-		newval.s.fc1.sd = oldval.s.fc1.sd;
-		if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
-		    crste_origin_large(oldval) != crste_origin_large(newval))
-			return -EAGAIN;
-		if (!dat_crstep_xchg_atomic(f->crstep, oldval, newval, f->gfn, asce))
-			return -EAGAIN;
-		if (f->callback)
-			f->callback(f);
-	}
-
-	return rc;
-}
-
 static long dat_set_pn_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
 {
 	union crste newcrste, oldcrste;
diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h
index 22dafc775335..efedcf96110c 100644
--- a/arch/s390/kvm/dat.h
+++ b/arch/s390/kvm/dat.h
@@ -540,8 +540,6 @@ int dat_set_slot(struct kvm_s390_mmu_cache *mc, union asce asce, gfn_t start, gf
 		 u16 type, u16 param);
 int dat_set_prefix_notif_bit(union asce asce, gfn_t gfn);
 bool dat_test_age_gfn(union asce asce, gfn_t start, gfn_t end);
-int dat_link(struct kvm_s390_mmu_cache *mc, union asce asce, int level,
-	     bool uses_skeys, struct guest_fault *f);
 
 int dat_perform_essa(union asce asce, gfn_t gfn, int orc, union essa_state *state, bool *dirty);
 long dat_reset_cmma(union asce asce, gfn_t start_gfn);
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 956be4c01797..03e15b5e0b9a 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -631,10 +631,60 @@ static inline bool gmap_1m_allowed(struct gmap *gmap, gfn_t gfn)
 	return test_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &gmap->flags);
 }
 
+static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int level,
+		      struct guest_fault *f)
+{
+	union crste oldval, newval;
+	union pte newpte, oldpte;
+	union pgste pgste;
+	int rc = 0;
+
+	rc = dat_entry_walk(mc, f->gfn, gmap->asce, DAT_WALK_ALLOC_CONTINUE, level,
+			    &f->crstep, &f->ptep);
+	if (rc == -ENOMEM)
+		return rc;
+	if (KVM_BUG_ON(rc == -EINVAL, gmap->kvm))
+		return rc;
+	if (rc)
+		return -EAGAIN;
+	if (KVM_BUG_ON(get_level(f->crstep, f->ptep) > level, gmap->kvm))
+		return -EINVAL;
+
+	if (f->ptep) {
+		pgste = pgste_get_lock(f->ptep);
+		oldpte = *f->ptep;
+		newpte = _pte(f->pfn, f->writable, f->write_attempt | oldpte.s.d, !f->page);
+		newpte.s.sd = oldpte.s.sd;
+		oldpte.s.sd = 0;
+		if (oldpte.val == _PTE_EMPTY.val || oldpte.h.pfra == f->pfn) {
+			pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, pgste, f->gfn);
+			if (f->callback)
+				f->callback(f);
+		} else {
+			rc = -EAGAIN;
+		}
+		pgste_set_unlock(f->ptep, pgste);
+	} else {
+		do {
+			oldval = READ_ONCE(*f->crstep);
+			newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable,
+					    f->write_attempt | oldval.s.fc1.d);
+			newval.s.fc1.sd = oldval.s.fc1.sd;
+			if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
+			    crste_origin_large(oldval) != crste_origin_large(newval))
+				return -EAGAIN;
+		} while (!gmap_crstep_xchg_atomic(gmap, f->crstep, oldval, newval, f->gfn));
+		if (f->callback)
+			f->callback(f);
+	}
+
+	return rc;
+}
+
 int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fault *f)
 {
 	unsigned int order;
-	int rc, level;
+	int level;
 
 	lockdep_assert_held(&gmap->kvm->mmu_lock);
 
@@ -646,9 +696,7 @@ int gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, struct guest_fau
 		else if (order >= get_order(_SEGMENT_SIZE) && gmap_1m_allowed(gmap, f->gfn))
 			level = TABLE_TYPE_SEGMENT;
 	}
-	rc = dat_link(mc, gmap->asce, level, uses_skeys(gmap), f);
-	KVM_BUG_ON(rc == -EINVAL, gmap->kvm);
-	return rc;
+	return _gmap_link(mc, gmap, level, f);
 }
 
 static int gmap_ucas_map_one(struct kvm_s390_mmu_cache *mc, struct gmap *gmap,
-- 
cgit v1.2.3


From 0f2b760a17126cb7940d410c99edfa14e928554c Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:14 +0100
Subject: KVM: s390: Correctly handle guest mappings without struct page

Introduce a new special softbit for large pages, like already presend
for normal pages, and use it to mark guest mappings that do not have
struct pages.

Whenever a leaf DAT entry becomes dirty, check the special softbit and
only call SetPageDirty() if there is an actual struct page.

Move the logic to mark pages dirty inside _gmap_ptep_xchg() and
_gmap_crstep_xchg_atomic(), to avoid needlessly duplicating the code.

Fixes: 5a74e3d93417 ("KVM: s390: KVM-specific bitfields and helper functions")
Fixes: a2c17f9270cc ("KVM: s390: New gmap code")
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/dat.h  | 12 ++++++------
 arch/s390/kvm/gmap.c | 11 ++++-------
 arch/s390/kvm/gmap.h |  4 ++++
 3 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h
index efedcf96110c..874cc962e196 100644
--- a/arch/s390/kvm/dat.h
+++ b/arch/s390/kvm/dat.h
@@ -160,14 +160,14 @@ union pmd {
 			unsigned long              :44; /* HW */
 			unsigned long              : 3; /* Unused */
 			unsigned long              : 1; /* HW */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable soft-bit */
 			unsigned long r            : 1; /* Readable soft-bit */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1; /* Unused */
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
@@ -183,14 +183,14 @@ union pud {
 			unsigned long              :33; /* HW */
 			unsigned long              :14; /* Unused */
 			unsigned long              : 1; /* HW */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable soft-bit */
 			unsigned long r            : 1; /* Readable soft-bit */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1; /* Unused */
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
@@ -254,14 +254,14 @@ union crste {
 		struct {
 			unsigned long              :47;
 			unsigned long              : 1; /* HW (should be 0) */
+			unsigned long s            : 1; /* Special */
 			unsigned long w            : 1; /* Writable */
 			unsigned long r            : 1; /* Readable */
 			unsigned long d            : 1; /* Dirty */
 			unsigned long y            : 1; /* Young */
-			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long              : 3; /* HW */
+			unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */
 			unsigned long vsie_notif   : 1; /* Referenced in a shadow table */
-			unsigned long              : 1;
 			unsigned long              : 4; /* HW */
 			unsigned long sd           : 1; /* Soft-Dirty */
 			unsigned long pr           : 1; /* Present */
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 03e15b5e0b9a..c8b79ad04ac9 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -519,7 +519,7 @@ void gmap_sync_dirty_log(struct gmap *gmap, gfn_t start, gfn_t end)
 	_dat_walk_gfn_range(start, end, gmap->asce, &walk_ops, 0, gmap);
 }
 
-static int gmap_handle_minor_crste_fault(union asce asce, struct guest_fault *f)
+static int gmap_handle_minor_crste_fault(struct gmap *gmap, struct guest_fault *f)
 {
 	union crste newcrste, oldcrste = READ_ONCE(*f->crstep);
 
@@ -544,10 +544,8 @@ static int gmap_handle_minor_crste_fault(union asce asce, struct guest_fault *f)
 			newcrste.s.fc1.d = 1;
 			newcrste.s.fc1.sd = 1;
 		}
-		if (!oldcrste.s.fc1.d && newcrste.s.fc1.d)
-			SetPageDirty(phys_to_page(crste_origin_large(newcrste)));
 		/* In case of races, let the slow path deal with it. */
-		return !dat_crstep_xchg_atomic(f->crstep, oldcrste, newcrste, f->gfn, asce);
+		return !gmap_crstep_xchg_atomic(gmap, f->crstep, oldcrste, newcrste, f->gfn);
 	}
 	/* Trying to write on a read-only page, let the slow path deal with it. */
 	return 1;
@@ -576,8 +574,6 @@ static int _gmap_handle_minor_pte_fault(struct gmap *gmap, union pgste *pgste,
 		newpte.s.d = 1;
 		newpte.s.sd = 1;
 	}
-	if (!oldpte.s.d && newpte.s.d)
-		SetPageDirty(pfn_to_page(newpte.h.pfra));
 	*pgste = gmap_ptep_xchg(gmap, f->ptep, newpte, *pgste, f->gfn);
 
 	return 0;
@@ -614,7 +610,7 @@ int gmap_try_fixup_minor(struct gmap *gmap, struct guest_fault *fault)
 			fault->callback(fault);
 		pgste_set_unlock(fault->ptep, pgste);
 	} else {
-		rc = gmap_handle_minor_crste_fault(gmap->asce, fault);
+		rc = gmap_handle_minor_crste_fault(gmap, fault);
 		if (!rc && fault->callback)
 			fault->callback(fault);
 	}
@@ -669,6 +665,7 @@ static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int leve
 			oldval = READ_ONCE(*f->crstep);
 			newval = _crste_fc1(f->pfn, oldval.h.tt, f->writable,
 					    f->write_attempt | oldval.s.fc1.d);
+			newval.s.fc1.s = !f->page;
 			newval.s.fc1.sd = oldval.s.fc1.sd;
 			if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val &&
 			    crste_origin_large(oldval) != crste_origin_large(newval))
diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h
index 150e91e15ee0..579399ef5480 100644
--- a/arch/s390/kvm/gmap.h
+++ b/arch/s390/kvm/gmap.h
@@ -185,6 +185,8 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un
 		else
 			_gmap_handle_vsie_unshadow_event(gmap, gfn);
 	}
+	if (!ptep->s.d && newpte.s.d && !newpte.s.s)
+		SetPageDirty(pfn_to_page(newpte.h.pfra));
 	return __dat_ptep_xchg(ptep, pgste, newpte, gfn, gmap->asce, uses_skeys(gmap));
 }
 
@@ -220,6 +222,8 @@ static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, unio
 		else
 			_gmap_handle_vsie_unshadow_event(gmap, gfn);
 	}
+	if (!oldcrste.s.fc1.d && newcrste.s.fc1.d && !newcrste.s.fc1.s)
+		SetPageDirty(phys_to_page(crste_origin_large(newcrste)));
 	return dat_crstep_xchg_atomic(crstep, oldcrste, newcrste, gfn, gmap->asce);
 }
 
-- 
cgit v1.2.3


From fd7bc612cf27f7c98764e86e2fba3511610fff20 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:15 +0100
Subject: KVM: s390: vsie: Fix nested guest memory shadowing

Fix _do_shadow_pte() to use the correct pointer (guest pte instead of
nested guest) to set up the new pte.

Add a check to return -EOPNOTSUPP if the mapping for the nested guest
is writeable but the same page in the guest is only read-only.

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 8fd690255e1b..6bc30f678921 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1436,13 +1436,19 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 
 	if (!pgste_get_trylock(ptep_h, &pgste))
 		return -EAGAIN;
-	newpte = _pte(f->pfn, f->writable, !p, 0);
-	newpte.s.d |= ptep->s.d;
-	newpte.s.sd |= ptep->s.sd;
-	newpte.h.p &= ptep->h.p;
-	pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false);
-	pgste.vsie_notif = 1;
+	newpte = _pte(f->pfn, f->writable, !p, ptep_h->s.s);
+	newpte.s.d |= ptep_h->s.d;
+	newpte.s.sd |= ptep_h->s.sd;
+	newpte.h.p &= ptep_h->h.p;
+	if (!newpte.h.p && !f->writable) {
+		rc = -EOPNOTSUPP;
+	} else {
+		pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false);
+		pgste.vsie_notif = 1;
+	}
 	pgste_set_unlock(ptep_h, pgste);
+	if (rc)
+		return rc;
 
 	newpte = _pte(f->pfn, 0, !p, 0);
 	if (!pgste_get_trylock(ptep, &pgste))
@@ -1477,6 +1483,9 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 		newcrste.h.p &= oldcrste.h.p;
 		newcrste.s.fc1.vsie_notif = 1;
 		newcrste.s.fc1.prefix_notif = oldcrste.s.fc1.prefix_notif;
+		newcrste.s.fc1.s = oldcrste.s.fc1.s;
+		if (!newcrste.h.p && !f->writable)
+			return -EOPNOTSUPP;
 	} while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false));
 
 	newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p);
-- 
cgit v1.2.3


From 0ec456b8a53d78644af7363a225c182494c1dacf Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:16 +0100
Subject: KVM: s390: vsie: Fix refcount overflow for shadow gmaps

In most cases gmap_put() was not called when it should have.

Add the missing gmap_put() in vsie_run().

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/vsie.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 0330829b4046..72895dddc39a 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1328,7 +1328,7 @@ static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
 static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	struct gmap *sg;
+	struct gmap *sg = NULL;
 	int rc = 0;
 
 	while (1) {
@@ -1368,6 +1368,8 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			sg = gmap_put(sg);
 		cond_resched();
 	}
+	if (sg)
+		sg = gmap_put(sg);
 
 	if (rc == -EFAULT) {
 		/*
-- 
cgit v1.2.3


From 19d6c5b8044366c88c1b1f6e831c0661ff1ddd20 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:17 +0100
Subject: KVM: s390: vsie: Fix unshadowing while shadowing

If shadowing causes the shadow gmap to get unshadowed, exit early to
prevent an attempt to dereference the parent pointer, which at this
point is NULL.

Opportunistically add some more checks to prevent NULL parents.

Fixes: a2c17f9270cc ("KVM: s390: New gmap code")
Fixes: e5f98a6899bd ("KVM: s390: Add some helper functions needed for vSIE")
Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c |  9 +++++++++
 arch/s390/kvm/gmap.c    | 11 ++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 6bc30f678921..8d99667e7d34 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1449,6 +1449,8 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 	pgste_set_unlock(ptep_h, pgste);
 	if (rc)
 		return rc;
+	if (!sg->parent)
+		return -EAGAIN;
 
 	newpte = _pte(f->pfn, 0, !p, 0);
 	if (!pgste_get_trylock(ptep, &pgste))
@@ -1476,6 +1478,9 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 		return rc;
 
 	do {
+		/* _gmap_crstep_xchg_atomic() could have unshadowed this shadow gmap */
+		if (!sg->parent)
+			return -EAGAIN;
 		oldcrste = READ_ONCE(*host);
 		newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, f->writable, !p);
 		newcrste.s.fc1.d |= oldcrste.s.fc1.d;
@@ -1487,6 +1492,8 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 		if (!newcrste.h.p && !f->writable)
 			return -EOPNOTSUPP;
 	} while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false));
+	if (!sg->parent)
+		return -EAGAIN;
 
 	newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p);
 	gfn = gpa_to_gfn(raddr);
@@ -1531,6 +1538,8 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 				       entries[i - 1].pfn, i, entries[i - 1].writable);
 		if (rc)
 			return rc;
+		if (!sg->parent)
+			return -EAGAIN;
 	}
 
 	rc = dat_entry_walk(NULL, entries[LEVEL_MEM].gfn, sg->parent->asce, DAT_WALK_LEAF,
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index c8b79ad04ac9..645c32c767d2 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -1160,6 +1160,7 @@ struct gmap_protect_asce_top_level {
 static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 						struct gmap_protect_asce_top_level *context)
 {
+	struct gmap *parent;
 	int rc, i;
 
 	guard(write_lock)(&sg->kvm->mmu_lock);
@@ -1167,7 +1168,12 @@ static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, s
 	if (kvm_s390_array_needs_retry_safe(sg->kvm, context->seq, context->f))
 		return -EAGAIN;
 
-	scoped_guard(spinlock, &sg->parent->children_lock) {
+	parent = READ_ONCE(sg->parent);
+	if (!parent)
+		return -EAGAIN;
+	scoped_guard(spinlock, &parent->children_lock) {
+		if (READ_ONCE(sg->parent) != parent)
+			return -EAGAIN;
 		for (i = 0; i < CRST_TABLE_PAGES; i++) {
 			if (!context->f[i].valid)
 				continue;
@@ -1250,6 +1256,9 @@ struct gmap *gmap_create_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *pare
 	struct gmap *sg, *new;
 	int rc;
 
+	if (WARN_ON(!parent))
+		return ERR_PTR(-EINVAL);
+
 	scoped_guard(spinlock, &parent->children_lock) {
 		sg = gmap_find_shadow(parent, asce, edat_level);
 		if (sg) {
-- 
cgit v1.2.3


From a12cc7e3d6a62f26262c1940a526f0682fefa3ba Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:18 +0100
Subject: KVM: s390: vsie: Fix guest page tables protection

When shadowing, the guest page tables are write-protected, in order to
trap changes and properly unshadow the shadow mapping for the nested
guest. Already shadowed levels are skipped, so that only the needed
levels are write protected.

Currently the levels that get write protected are exactly one level too
deep: the last level (nested guest memory) gets protected in the wrong
way, and will be protected again correctly a few lines afterwards; most
importantly, the highest non-shadowed level does *not* get write
protected.

Moreover, if the nested guest is running in a real address space, there
are no DAT tables to shadow.

Write protect the correct levels, so that all the levels that need to
be protected are protected, and avoid double protecting the last level;
skip attempting to shadow the DAT tables when the nested guest is
running in a real address space.

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Tested-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 8d99667e7d34..53a8550e7102 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1529,13 +1529,20 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 
 	gl = get_level(table, ptep);
 
+	/* In case of a real address space */
+	if (w->level <= LEVEL_MEM) {
+		l = TABLE_TYPE_PAGE_TABLE;
+		hl = TABLE_TYPE_REGION1;
+		goto real_address_space;
+	}
+
 	/*
 	 * Skip levels that are already protected. For each level, protect
 	 * only the page containing the entry, not the whole table.
 	 */
 	for (i = gl ; i >= w->level; i--) {
-		rc = gmap_protect_rmap(mc, sg, entries[i - 1].gfn, gpa_to_gfn(saddr),
-				       entries[i - 1].pfn, i, entries[i - 1].writable);
+		rc = gmap_protect_rmap(mc, sg, entries[i].gfn, gpa_to_gfn(saddr),
+				       entries[i].pfn, i + 1, entries[i].writable);
 		if (rc)
 			return rc;
 		if (!sg->parent)
@@ -1551,6 +1558,7 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 	/* Get the smallest granularity */
 	l = min3(gl, hl, w->level);
 
+real_address_space:
 	flags = DAT_WALK_SPLIT_ALLOC | (uses_skeys(sg->parent) ? DAT_WALK_USES_SKEYS : 0);
 	/* If necessary, create the shadow mapping */
 	if (l < gl) {
-- 
cgit v1.2.3


From 0a28e06575b3f3b30c1e99fc08fa0907956f35a4 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:17:19 +0100
Subject: KVM: s390: Fix KVM_S390_VCPU_FAULT ioctl

A previous commit changed the behaviour of the KVM_S390_VCPU_FAULT
ioctl. The current (wrong) implementation will trigger a guest
addressing exception if the requested address lies outside of a
memslot, unless the VM is UCONTROL.

Restore the previous behaviour by open coding the fault-in logic.

Fixes: 3762e905ec2e ("KVM: s390: use __kvm_faultin_pfn()")
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Steffen Eiden <seiden@linux.ibm.com>
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b2c01fa7b852..d7838334a338 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -5520,9 +5520,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 #endif
 	case KVM_S390_VCPU_FAULT: {
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = vcpu_dat_fault_handler(vcpu, arg, 0);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		gpa_t gaddr = arg;
+
+		scoped_guard(srcu, &vcpu->kvm->srcu) {
+			r = vcpu_ucontrol_translate(vcpu, &gaddr);
+			if (r)
+				break;
+
+			r = kvm_s390_faultin_gfn_simple(vcpu, NULL, gpa_to_gfn(gaddr), false);
+			if (r == PGM_ADDRESSING)
+				r = -EFAULT;
+			if (r <= 0)
+				break;
+			r = -EIO;
+			KVM_BUG_ON(r, vcpu->kvm);
+		}
 		break;
 	}
 	case KVM_ENABLE_CAP:
-- 
cgit v1.2.3


From 19f94b39058681dec64a10ebeb6f23fe7fc3f77a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 26 Mar 2026 13:35:53 +0100
Subject: futex: Require sys_futex_requeue() to have identical flags

Nicholas reported that his LLM found it was possible to create a UaF
when sys_futex_requeue() is used with different flags. The initial
motivation for allowing different flags was the variable sized futex,
but since that hasn't been merged (yet), simply mandate the flags are
identical, as is the case for the old style sys_futex() requeue
operations.

Fixes: 0f4b5f972216 ("futex: Add sys_futex_requeue()")
Reported-by: Nicholas Carlini <npc@anthropic.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/futex/syscalls.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c
index 743c7a728237..77ad9691f6a6 100644
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -459,6 +459,14 @@ SYSCALL_DEFINE4(futex_requeue,
 	if (ret)
 		return ret;
 
+	/*
+	 * For now mandate both flags are identical, like the sys_futex()
+	 * interface has. If/when we merge the variable sized futex support,
+	 * that patch can modify this test to allow a difference in size.
+	 */
+	if (futexes[0].w.flags != futexes[1].w.flags)
+		return -EINVAL;
+
 	cmpval = futexes[0].w.val;
 
 	return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
-- 
cgit v1.2.3


From 190a8c48ff623c3d67cb295b4536a660db2012aa Mon Sep 17 00:00:00 2001
From: Hao-Yu Yang <naup96721@gmail.com>
Date: Fri, 13 Mar 2026 20:47:56 +0800
Subject: futex: Fix UaF between futex_key_to_node_opt() and
 vma_replace_policy()

During futex_key_to_node_opt() execution, vma->vm_policy is read under
speculative mmap lock and RCU. Concurrently, mbind() may call
vma_replace_policy() which frees the old mempolicy immediately via
kmem_cache_free().

This creates a race where __futex_key_to_node() dereferences a freed
mempolicy pointer, causing a use-after-free read of mpol->mode.

[  151.412631] BUG: KASAN: slab-use-after-free in __futex_key_to_node (kernel/futex/core.c:349)
[  151.414046] Read of size 2 at addr ffff888001c49634 by task e/87

[  151.415969] Call Trace:

[  151.416732]  __asan_load2 (mm/kasan/generic.c:271)
[  151.416777]  __futex_key_to_node (kernel/futex/core.c:349)
[  151.416822]  get_futex_key (kernel/futex/core.c:374 kernel/futex/core.c:386 kernel/futex/core.c:593)

Fix by adding rcu to __mpol_put().

Fixes: c042c505210d ("futex: Implement FUTEX2_MPOL")
Reported-by: Hao-Yu Yang <naup96721@gmail.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Hao-Yu Yang <naup96721@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Link: https://patch.msgid.link/20260324174418.GB1850007@noisy.programming.kicks-ass.net
---
 include/linux/mempolicy.h |  1 +
 kernel/futex/core.c       |  2 +-
 mm/mempolicy.c            | 10 ++++++++--
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 0fe96f3ab3ef..65c732d440d2 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -55,6 +55,7 @@ struct mempolicy {
 		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
 		nodemask_t user_nodemask;	/* nodemask passed by user */
 	} w;
+	struct rcu_head rcu;
 };
 
 /*
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index cf7e610eac42..31e83a09789e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -342,7 +342,7 @@ static int __futex_key_to_node(struct mm_struct *mm, unsigned long addr)
 	if (!vma)
 		return FUTEX_NO_NODE;
 
-	mpol = vma_policy(vma);
+	mpol = READ_ONCE(vma->vm_policy);
 	if (!mpol)
 		return FUTEX_NO_NODE;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0e5175f1c767..cf92bd6a8226 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -487,7 +487,13 @@ void __mpol_put(struct mempolicy *pol)
 {
 	if (!atomic_dec_and_test(&pol->refcnt))
 		return;
-	kmem_cache_free(policy_cache, pol);
+	/*
+	 * Required to allow mmap_lock_speculative*() access, see for example
+	 * futex_key_to_node_opt(). All accesses are serialized by mmap_lock,
+	 * however the speculative lock section unbound by the normal lock
+	 * boundaries, requiring RCU freeing.
+	 */
+	kfree_rcu(pol, rcu);
 }
 EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm");
 
@@ -1020,7 +1026,7 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	}
 
 	old = vma->vm_policy;
-	vma->vm_policy = new; /* protected by mmap_lock */
+	WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */
 	mpol_put(old);
 
 	return 0;
-- 
cgit v1.2.3


From 88bdac5443e5269bb39c4968d5ee0becbffe3f82 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Date: Wed, 25 Mar 2026 13:22:10 +0100
Subject: dt-bindings: display/msm: qcm2290-mdss: Fix missing ranges in example

Device node has children with MMIO addressing, so must have ranges:

  msm/qcom,qcm2290-mdss.example.dtb: display-subsystem@5e00000 (qcom,qcm2290-mdss): 'ranges' is a required property

Fixes: 966a08c293cb ("dt-bindings: display: msm: qcm2290-mdss: Fix iommus property")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Reviewed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260325122209.147128-2-krzysztof.kozlowski@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
index 2772cdec7e42..bb09ecd1a5b4 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
@@ -108,6 +108,7 @@ examples:
                              "cpu-cfg";
 
         iommus = <&apps_smmu 0x420 0x2>;
+        ranges;
 
         display-controller@5e01000 {
             compatible = "qcom,qcm2290-dpu";
-- 
cgit v1.2.3


From 629ec78ef8608d955ce217880cdc3e1873af3a15 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Tue, 24 Mar 2026 00:25:57 +0100
Subject: mpls: add seqcount to protect the platform_label{,s} pair

The RCU-protected codepaths (mpls_forward, mpls_dump_routes) can have
an inconsistent view of platform_labels vs platform_label in case of a
concurrent resize (resize_platform_label_table, under
platform_mutex). This can lead to OOB accesses.

This patch adds a seqcount, so that we get a consistent snapshot.

Note that mpls_label_ok is also susceptible to this, so the check
against RTA_DST in rtm_to_route_config, done outside platform_mutex,
is not sufficient. This value gets passed to mpls_label_ok once more
in both mpls_route_add and mpls_route_del, so there is no issue, but
that additional check must not be removed.

Reported-by: Yuan Tan <tanyuan98@outlook.com>
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Reported-by: Xin Liu <bird@lzu.edu.cn>
Fixes: 7720c01f3f590 ("mpls: Add a sysctl to control the size of the mpls label table")
Fixes: dde1b38e873c ("mpls: Convert mpls_dump_routes() to RCU.")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/cd8fca15e3eb7e212b094064cd83652e20fd9d31.1774284088.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netns/mpls.h |  1 +
 net/mpls/af_mpls.c       | 29 +++++++++++++++++++++++++----
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h
index 6682e51513ef..2073cbac2afb 100644
--- a/include/net/netns/mpls.h
+++ b/include/net/netns/mpls.h
@@ -17,6 +17,7 @@ struct netns_mpls {
 	size_t platform_labels;
 	struct mpls_route __rcu * __rcu *platform_label;
 	struct mutex platform_mutex;
+	seqcount_mutex_t platform_label_seq;
 
 	struct ctl_table_header *ctl;
 };
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index d5417688f69e..18d3da8ab384 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -83,14 +83,30 @@ static struct mpls_route *mpls_route_input(struct net *net, unsigned int index)
 	return mpls_dereference(net, platform_label[index]);
 }
 
+static struct mpls_route __rcu **mpls_platform_label_rcu(struct net *net, size_t *platform_labels)
+{
+	struct mpls_route __rcu **platform_label;
+	unsigned int sequence;
+
+	do {
+		sequence = read_seqcount_begin(&net->mpls.platform_label_seq);
+		platform_label = rcu_dereference(net->mpls.platform_label);
+		*platform_labels = net->mpls.platform_labels;
+	} while (read_seqcount_retry(&net->mpls.platform_label_seq, sequence));
+
+	return platform_label;
+}
+
 static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned int index)
 {
 	struct mpls_route __rcu **platform_label;
+	size_t platform_labels;
+
+	platform_label = mpls_platform_label_rcu(net, &platform_labels);
 
-	if (index >= net->mpls.platform_labels)
+	if (index >= platform_labels)
 		return NULL;
 
-	platform_label = rcu_dereference(net->mpls.platform_label);
 	return rcu_dereference(platform_label[index]);
 }
 
@@ -2240,8 +2256,7 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb)
 	if (index < MPLS_LABEL_FIRST_UNRESERVED)
 		index = MPLS_LABEL_FIRST_UNRESERVED;
 
-	platform_label = rcu_dereference(net->mpls.platform_label);
-	platform_labels = net->mpls.platform_labels;
+	platform_label = mpls_platform_label_rcu(net, &platform_labels);
 
 	if (filter.filter_set)
 		flags |= NLM_F_DUMP_FILTERED;
@@ -2645,8 +2660,12 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 	}
 
 	/* Update the global pointers */
+	local_bh_disable();
+	write_seqcount_begin(&net->mpls.platform_label_seq);
 	net->mpls.platform_labels = limit;
 	rcu_assign_pointer(net->mpls.platform_label, labels);
+	write_seqcount_end(&net->mpls.platform_label_seq);
+	local_bh_enable();
 
 	mutex_unlock(&net->mpls.platform_mutex);
 
@@ -2728,6 +2747,8 @@ static __net_init int mpls_net_init(struct net *net)
 	int i;
 
 	mutex_init(&net->mpls.platform_mutex);
+	seqcount_mutex_init(&net->mpls.platform_label_seq, &net->mpls.platform_mutex);
+
 	net->mpls.platform_labels = 0;
 	net->mpls.platform_label = NULL;
 	net->mpls.ip_ttl_propagate = 1;
-- 
cgit v1.2.3


From f73896b4197ed53cf0894657c899265ef7c86b7a Mon Sep 17 00:00:00 2001
From: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Date: Tue, 24 Mar 2026 11:14:28 -0700
Subject: net: mana: Fix RX skb truesize accounting

MANA passes rxq->alloc_size to napi_build_skb() for all RX buffers.
It is correct for fragment-backed RX buffers, where alloc_size matches
the actual backing allocation used for each packet buffer. However, in
the non-fragment RX path mana allocates a full page, or a higher-order
page, per RX buffer. In that case alloc_size only reflects the usable
packet area and not the actual backing memory.

This causes napi_build_skb() to underestimate the skb backing allocation
in the single-buffer RX path, so skb->truesize is derived from a value
smaller than the real RX buffer allocation.

Fix this by updating alloc_size in the non-fragment RX path to the
actual backing allocation size before it is passed to napi_build_skb().

Fixes: 730ff06d3f5c ("net: mana: Use page pool fragments for RX buffers instead of full pages to improve memory efficiency.")
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/acLUhLpLum6qrD/N@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index dca62fb9a3a9..09a53c977545 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -766,6 +766,13 @@ static void mana_get_rxbuf_cfg(struct mana_port_context *apc,
 		}
 
 		*frag_count = 1;
+
+		/* In the single-buffer path, napi_build_skb() must see the
+		 * actual backing allocation size so skb->truesize reflects
+		 * the full page (or higher-order page), not just the usable
+		 * packet area.
+		 */
+		*alloc_size = PAGE_SIZE << get_order(*alloc_size);
 		return;
 	}
 
-- 
cgit v1.2.3


From 976ff48c2ac6e6b25b01428c9d7997bcd0fb2949 Mon Sep 17 00:00:00 2001
From: "Sven Eckelmann (Plasma Cloud)" <se@simonwunderlich.de>
Date: Tue, 24 Mar 2026 09:36:01 +0100
Subject: net: ethernet: mtk_ppe: avoid NULL deref when gmac0 is disabled

If the gmac0 is disabled, the precheck for a valid ingress device will
cause a NULL pointer deref and crash the system. This happens because
eth->netdev[0] will be NULL but the code will directly try to access
netdev_ops.

Instead of just checking for the first net_device, it must be checked if
any of the mtk_eth net_devices is matching the netdev_ops of the ingress
device.

Cc: stable@vger.kernel.org
Fixes: 73cfd947dbdb ("net: ethernet: mtk_eth_soc: ppe: prevent ppe update for non-mtk devices")
Signed-off-by: Sven Eckelmann (Plasma Cloud) <se@simonwunderlich.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324-wed-crash-gmac0-disabled-v1-1-3bc388aee565@simonwunderlich.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index cb30108f2bf6..cc8c4ef8038f 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -244,6 +244,25 @@ out:
 	return 0;
 }
 
+static bool
+mtk_flow_is_valid_idev(const struct mtk_eth *eth, const struct net_device *idev)
+{
+	size_t i;
+
+	if (!idev)
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(eth->netdev); i++) {
+		if (!eth->netdev[i])
+			continue;
+
+		if (idev->netdev_ops == eth->netdev[i]->netdev_ops)
+			return true;
+	}
+
+	return false;
+}
+
 static int
 mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 			 int ppe_index)
@@ -270,7 +289,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		flow_rule_match_meta(rule, &match);
 		if (mtk_is_netsys_v2_or_greater(eth)) {
 			idev = __dev_get_by_index(&init_net, match.key->ingress_ifindex);
-			if (idev && idev->netdev_ops == eth->netdev[0]->netdev_ops) {
+			if (mtk_flow_is_valid_idev(eth, idev)) {
 				struct mtk_mac *mac = netdev_priv(idev);
 
 				if (WARN_ON(mac->ppe_idx >= eth->soc->ppe_num))
-- 
cgit v1.2.3


From 5170efd9c344c68a8075dcb8ed38d3f8a60e7ed4 Mon Sep 17 00:00:00 2001
From: Nicholas Carlini <nicholas@carlini.com>
Date: Fri, 27 Mar 2026 02:18:23 +0000
Subject: io_uring/fdinfo: fix OOB read in SQE_MIXED wrap check

__io_uring_show_fdinfo() iterates over pending SQEs and, for 128-byte
SQEs on an IORING_SETUP_SQE_MIXED ring, needs to detect when the second
half of the SQE would be past the end of the sq_sqes array. The current
check tests (++sq_head & sq_mask) == 0, but sq_head is only incremented
when a 128-byte SQE is encountered, not on every iteration. The actual
array index is sq_idx = (i + sq_head) & sq_mask, which can be sq_mask
(the last slot) while the wrap check passes.

Fix by checking sq_idx directly. Keep the sq_head increment so the loop
still skips the second half of the 128-byte SQE on the next iteration.

Fixes: 1cba30bf9fdd ("io_uring: add support for IORING_SETUP_SQE_MIXED")
Signed-off-by: Nicholas Carlini <nicholas@carlini.com>
Link: https://patch.msgid.link/20260327021823.3138396-1-nicholas@carlini.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/fdinfo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 25c92ace18bd..c2d3e45544bb 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -119,12 +119,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 					sq_idx);
 				break;
 			}
-			if ((++sq_head & sq_mask) == 0) {
+			if (sq_idx == sq_mask) {
 				seq_printf(m,
 					"%5u: corrupted sqe, wrapping 128B entry\n",
 					sq_idx);
 				break;
 			}
+			sq_head++;
 			i++;
 			sqe128 = true;
 		}
-- 
cgit v1.2.3


From 57a04a13aac1f247d171c3f3aef93efc69e6979e Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Tue, 24 Mar 2026 22:08:56 +0800
Subject: netdevsim: fix build if SKB_EXTENSIONS=n

__skb_ext_put() is not declared if SKB_EXTENSIONS is not enabled, which
causes a build error:

drivers/net/netdevsim/netdev.c: In function 'nsim_forward_skb':
drivers/net/netdevsim/netdev.c:114:25: error: implicit declaration of function '__skb_ext_put'; did you mean 'skb_ext_put'? [-Werror=implicit-function-declaration]
  114 |                         __skb_ext_put(psp_ext);
      |                         ^~~~~~~~~~~~~
      |                         skb_ext_put
cc1: some warnings being treated as errors

Add a stub to fix the build.

Fixes: 7d9351435ebb ("netdevsim: drop PSP ext ref on forward failure")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Link: https://patch.msgid.link/20260324140857.783-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index daa4e4944ce3..2f278ce376b7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5097,6 +5097,7 @@ static inline bool skb_has_extensions(struct sk_buff *skb)
 	return unlikely(skb->active_extensions);
 }
 #else
+static inline void __skb_ext_put(struct skb_ext *ext) {}
 static inline void skb_ext_put(struct sk_buff *skb) {}
 static inline void skb_ext_reset(struct sk_buff *skb) {}
 static inline void skb_ext_del(struct sk_buff *skb, int unused) {}
-- 
cgit v1.2.3


From e8e44c98f789dee45cfd24ffb9d4936e0606d7c6 Mon Sep 17 00:00:00 2001
From: Buday Csaba <buday.csaba@prolan.hu>
Date: Tue, 24 Mar 2026 14:32:30 +0100
Subject: net: fec: fix the PTP periodic output sysfs interface

When the PPS channel configuration was implemented, the channel
index for the periodic outputs was configured as the hardware
channel number.

The sysfs interface uses a logical channel index, and rejects numbers
greater than `n_per_out` (see period_store() in ptp_sysfs.c).
That property was left at 1, since the driver implements channel
selection, not simultaneous operation of multiple PTP hardware timer
channels.

A second check in fec_ptp_enable() returns -EOPNOTSUPP when the two
channel numbers disagree, making channels 1..3 unusable from sysfs.

Fix by removing this redundant check in the FEC PTP driver.

Fixes: 566c2d83887f ("net: fec: make PPS channel configurable")
Signed-off-by: Buday Csaba <buday.csaba@prolan.hu>
Link: https://patch.msgid.link/8ec2afe88423c2231f9cf8044d212ce57846670e.1774359059.git.buday.csaba@prolan.hu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 4b7bad9a485d..56801c2009d5 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -545,9 +545,6 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp,
 		if (rq->perout.flags)
 			return -EOPNOTSUPP;
 
-		if (rq->perout.index != fep->pps_channel)
-			return -EOPNOTSUPP;
-
 		period.tv_sec = rq->perout.period.sec;
 		period.tv_nsec = rq->perout.period.nsec;
 		period_ns = timespec64_to_ns(&period);
-- 
cgit v1.2.3


From 0239fd701d33475a39428daa3dc627407cd417a6 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 24 Mar 2026 14:21:19 +0800
Subject: net: enetc: reset PIR and CIR if they are not equal when initializing
 TX ring

Currently the driver does not reset the producer index register (PIR) and
consumer index register (CIR) when initializing a TX BD ring. The driver
only reads the PIR and CIR and initializes the software indexes. If the
TX BD ring is reinitialized when it still contains unsent frames, its PIR
and CIR will not be equal after the reinitialization. However, the BDs
between CIR and PIR have been freed and become invalid and this can lead
to a hardware malfunction, causing the TX BD ring will not work properly.

For ENETC v4, it supports software to set the PIR and CIR, so the driver
can reset these two registers if they are not equal when reinitializing
the TX BD ring. Therefore, add this solution for ENETC v4. Note that this
patch does not work for ENETC v1 because it does not support software to
set the PIR and CIR.

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324062121.2745033-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index a146ceaf2ed6..aa8a87124b10 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2578,6 +2578,7 @@ EXPORT_SYMBOL_GPL(enetc_free_si_resources);
 
 static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
 {
+	struct enetc_si *si = container_of(hw, struct enetc_si, hw);
 	int idx = tx_ring->index;
 	u32 tbmr;
 
@@ -2591,10 +2592,20 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
 	enetc_txbdr_wr(hw, idx, ENETC_TBLENR,
 		       ENETC_RTBLENR_LEN(tx_ring->bd_count));
 
-	/* clearing PI/CI registers for Tx not supported, adjust sw indexes */
+	/* For ENETC v1, clearing PI/CI registers for Tx not supported,
+	 * adjust sw indexes
+	 */
 	tx_ring->next_to_use = enetc_txbdr_rd(hw, idx, ENETC_TBPIR);
 	tx_ring->next_to_clean = enetc_txbdr_rd(hw, idx, ENETC_TBCIR);
 
+	if (tx_ring->next_to_use != tx_ring->next_to_clean &&
+	    !is_enetc_rev1(si)) {
+		tx_ring->next_to_use = 0;
+		tx_ring->next_to_clean = 0;
+		enetc_txbdr_wr(hw, idx, ENETC_TBPIR, 0);
+		enetc_txbdr_wr(hw, idx, ENETC_TBCIR, 0);
+	}
+
 	/* enable Tx ints by setting pkt thr to 1 */
 	enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1);
 
-- 
cgit v1.2.3


From 2725d84efe2582c0a4b907e74a689d26b2dbd382 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 24 Mar 2026 14:21:20 +0800
Subject: net: enetc: add graceful stop to safely reinitialize the TX Ring

For ENETC v4, the PIR and CIR will be reset if they are not equal when
reinitializing the TX BD ring. However, resetting the PIR and CIR alone
is insufficient. When a link-down event occurs while the TX BD ring is
transmitting frames, subsequent reinitialization of the TX BD ring may
cause it to malfunction. For example, the below steps can reproduce the
problem.

1. Unplug the cable when the TX BD ring is busy transmitting frames.
2. Disable the network interface (ifconfig eth0 down).
3. Re-enable the network interface (ifconfig eth0 up).
4. Plug in the cable, the TX BD ring may fail to transmit packets.

When the link-down event occurs, enetc4_pl_mac_link_down() only clears
PMa_COMMAND_CONFIG[TX_EN] to disable MAC transmit data path. It doesn't
set PORT[TXDIS] to 1 to flush the TX BD ring. Therefore, reinitializing
the TX BD ring at this point is unsafe. To safely reinitialize the TX BD
ring after a link-down event, we checked with the NETC IP team, a proper
Ethernet MAC graceful stop is necessary. Therefore, add the Ethernet MAC
graceful stop to the link-down event handler enetc4_pl_mac_link_down().

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324062121.2745033-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_hw.h |  11 +++
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 111 ++++++++++++++++++++---
 2 files changed, 108 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 3ed0f7a02767..719c88ceb801 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -134,6 +134,12 @@
 
 /* Port operational register */
 #define ENETC4_POR			0x4100
+#define  POR_TXDIS			BIT(0)
+#define  POR_RXDIS			BIT(1)
+
+/* Port status register */
+#define ENETC4_PSR			0x4104
+#define  PSR_RX_BUSY			BIT(1)
 
 /* Port traffic class a transmit maximum SDU register */
 #define ENETC4_PTCTMSDUR(a)		((a) * 0x20 + 0x4208)
@@ -173,6 +179,11 @@
 /* Port internal MDIO base address, use to access PCS */
 #define ENETC4_PM_IMDIO_BASE		0x5030
 
+/* Port MAC 0/1 Interrupt Event Register */
+#define ENETC4_PM_IEVENT(mac)		(0x5040 + (mac) * 0x400)
+#define  PM_IEVENT_TX_EMPTY		BIT(5)
+#define  PM_IEVENT_RX_EMPTY		BIT(6)
+
 /* Port MAC 0/1 Pause Quanta Register */
 #define ENETC4_PM_PAUSE_QUANTA(mac)	(0x5054 + (mac) * 0x400)
 
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 689b9f13c5eb..53cecbb23a97 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -444,20 +444,11 @@ static void enetc4_set_trx_frame_size(struct enetc_pf *pf)
 	enetc4_pf_reset_tc_msdu(&si->hw);
 }
 
-static void enetc4_enable_trx(struct enetc_pf *pf)
-{
-	struct enetc_hw *hw = &pf->si->hw;
-
-	/* Enable port transmit/receive */
-	enetc_port_wr(hw, ENETC4_POR, 0);
-}
-
 static void enetc4_configure_port(struct enetc_pf *pf)
 {
 	enetc4_configure_port_si(pf);
 	enetc4_set_trx_frame_size(pf);
 	enetc_set_default_rss_key(pf);
-	enetc4_enable_trx(pf);
 }
 
 static int enetc4_init_ntmp_user(struct enetc_si *si)
@@ -801,15 +792,105 @@ static void enetc4_set_tx_pause(struct enetc_pf *pf, int num_rxbdr, bool tx_paus
 	enetc_port_wr(hw, ENETC4_PPAUOFFTR, pause_off_thresh);
 }
 
-static void enetc4_enable_mac(struct enetc_pf *pf, bool en)
+static void enetc4_mac_wait_tx_empty(struct enetc_si *si, int mac)
+{
+	u32 val;
+
+	if (read_poll_timeout(enetc_port_rd, val,
+			      val & PM_IEVENT_TX_EMPTY,
+			      100, 10000, false, &si->hw,
+			      ENETC4_PM_IEVENT(mac)))
+		dev_warn(&si->pdev->dev,
+			 "MAC %d TX is not empty\n", mac);
+}
+
+static void enetc4_mac_tx_graceful_stop(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val |= POR_TXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+
+	enetc4_mac_wait_tx_empty(si, 0);
+	if (si->hw_features & ENETC_SI_F_QBU)
+		enetc4_mac_wait_tx_empty(si, 1);
+
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val &= ~PM_CMD_CFG_TX_EN;
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+}
+
+static void enetc4_mac_tx_enable(struct enetc_pf *pf)
 {
+	struct enetc_hw *hw = &pf->si->hw;
 	struct enetc_si *si = pf->si;
 	u32 val;
 
 	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
-	val &= ~(PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN);
-	val |= en ? (PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN) : 0;
+	val |= PM_CMD_CFG_TX_EN;
+	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val &= ~POR_TXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+}
+
+static void enetc4_mac_wait_rx_empty(struct enetc_si *si, int mac)
+{
+	u32 val;
+
+	if (read_poll_timeout(enetc_port_rd, val,
+			      val & PM_IEVENT_RX_EMPTY,
+			      100, 10000, false, &si->hw,
+			      ENETC4_PM_IEVENT(mac)))
+		dev_warn(&si->pdev->dev,
+			 "MAC %d RX is not empty\n", mac);
+}
+
+static void enetc4_mac_rx_graceful_stop(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	if (si->hw_features & ENETC_SI_F_QBU) {
+		val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(1));
+		val &= ~PM_CMD_CFG_RX_EN;
+		enetc_port_wr(hw, ENETC4_PM_CMD_CFG(1), val);
+		enetc4_mac_wait_rx_empty(si, 1);
+	}
+
+	val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(0));
+	val &= ~PM_CMD_CFG_RX_EN;
+	enetc_port_wr(hw, ENETC4_PM_CMD_CFG(0), val);
+	enetc4_mac_wait_rx_empty(si, 0);
+
+	if (read_poll_timeout(enetc_port_rd, val,
+			      !(val & PSR_RX_BUSY),
+			      100, 10000, false, hw,
+			      ENETC4_PSR))
+		dev_warn(&si->pdev->dev, "Port RX busy\n");
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val |= POR_RXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
+}
+
+static void enetc4_mac_rx_enable(struct enetc_pf *pf)
+{
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_si *si = pf->si;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC4_POR);
+	val &= ~POR_RXDIS;
+	enetc_port_wr(hw, ENETC4_POR, val);
 
+	val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0));
+	val |= PM_CMD_CFG_RX_EN;
 	enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val);
 }
 
@@ -853,7 +934,8 @@ static void enetc4_pl_mac_link_up(struct phylink_config *config,
 	enetc4_set_hd_flow_control(pf, hd_fc);
 	enetc4_set_tx_pause(pf, priv->num_rx_rings, tx_pause);
 	enetc4_set_rx_pause(pf, rx_pause);
-	enetc4_enable_mac(pf, true);
+	enetc4_mac_tx_enable(pf);
+	enetc4_mac_rx_enable(pf);
 }
 
 static void enetc4_pl_mac_link_down(struct phylink_config *config,
@@ -862,7 +944,8 @@ static void enetc4_pl_mac_link_down(struct phylink_config *config,
 {
 	struct enetc_pf *pf = phylink_to_enetc_pf(config);
 
-	enetc4_enable_mac(pf, false);
+	enetc4_mac_rx_graceful_stop(pf);
+	enetc4_mac_tx_graceful_stop(pf);
 }
 
 static const struct phylink_mac_ops enetc_pl_mac_ops = {
-- 
cgit v1.2.3


From f2df9567b123145a07ee4ea7440e233f5d0232cc Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 24 Mar 2026 14:21:21 +0800
Subject: net: enetc: do not access non-existent registers on pseudo MAC

The ENETC4_PM_IEVENT and ENETC4_PM_CMD_CFG registers do not exist on the
ENETC pseudo MAC, so the driver should prevent from accessing them.

Fixes: 5175c1e4adca ("net: enetc: add basic support for the ENETC with pseudo MAC for i.MX94")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Tested-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324062121.2745033-4-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 53cecbb23a97..56899f2254aa 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -814,6 +814,9 @@ static void enetc4_mac_tx_graceful_stop(struct enetc_pf *pf)
 	val |= POR_TXDIS;
 	enetc_port_wr(hw, ENETC4_POR, val);
 
+	if (enetc_is_pseudo_mac(si))
+		return;
+
 	enetc4_mac_wait_tx_empty(si, 0);
 	if (si->hw_features & ENETC_SI_F_QBU)
 		enetc4_mac_wait_tx_empty(si, 1);
@@ -856,6 +859,9 @@ static void enetc4_mac_rx_graceful_stop(struct enetc_pf *pf)
 	struct enetc_si *si = pf->si;
 	u32 val;
 
+	if (enetc_is_pseudo_mac(si))
+		goto check_rx_busy;
+
 	if (si->hw_features & ENETC_SI_F_QBU) {
 		val = enetc_port_rd(hw, ENETC4_PM_CMD_CFG(1));
 		val &= ~PM_CMD_CFG_RX_EN;
@@ -868,6 +874,7 @@ static void enetc4_mac_rx_graceful_stop(struct enetc_pf *pf)
 	enetc_port_wr(hw, ENETC4_PM_CMD_CFG(0), val);
 	enetc4_mac_wait_rx_empty(si, 0);
 
+check_rx_busy:
 	if (read_poll_timeout(enetc_port_rd, val,
 			      !(val & PSR_RX_BUSY),
 			      100, 10000, false, hw,
-- 
cgit v1.2.3


From 2428083101f6883f979cceffa76cd8440751ffe6 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Tue, 24 Mar 2026 16:06:44 +0800
Subject: net: qrtr: replace qrtr_tx_flow radix_tree with xarray to fix memory
 leak
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

__radix_tree_create() allocates and links intermediate nodes into the
tree one by one. If a subsequent allocation fails, the already-linked
nodes remain in the tree with no corresponding leaf entry. These orphaned
internal nodes are never reclaimed because radix_tree_for_each_slot()
only visits slots containing leaf values.

The radix_tree API is deprecated in favor of xarray. As suggested by
Matthew Wilcox, migrate qrtr_tx_flow from radix_tree to xarray instead
of fixing the radix_tree itself [1]. xarray properly handles cleanup of
internal nodes — xa_destroy() frees all internal xarray nodes when the
qrtr_node is released, preventing the leak.

[1] https://lore.kernel.org/all/20260225071623.41275-1-jiayuan.chen@linux.dev/T/
Reported-by: syzbot+006987d1be3586e13555@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/000000000000bfba3a060bf4ffcf@google.com/T/
Fixes: 5fdeb0d372ab ("net: qrtr: Implement outgoing flow control")
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324080645.290197-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/qrtr/af_qrtr.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
index 55fd2dd37588..d77e9c8212da 100644
--- a/net/qrtr/af_qrtr.c
+++ b/net/qrtr/af_qrtr.c
@@ -118,7 +118,7 @@ static DEFINE_XARRAY_ALLOC(qrtr_ports);
  * @ep: endpoint
  * @ref: reference count for node
  * @nid: node id
- * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port
+ * @qrtr_tx_flow: xarray of qrtr_tx_flow, keyed by node << 32 | port
  * @qrtr_tx_lock: lock for qrtr_tx_flow inserts
  * @rx_queue: receive queue
  * @item: list item for broadcast list
@@ -129,7 +129,7 @@ struct qrtr_node {
 	struct kref ref;
 	unsigned int nid;
 
-	struct radix_tree_root qrtr_tx_flow;
+	struct xarray qrtr_tx_flow;
 	struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */
 
 	struct sk_buff_head rx_queue;
@@ -172,6 +172,7 @@ static void __qrtr_node_release(struct kref *kref)
 	struct qrtr_tx_flow *flow;
 	unsigned long flags;
 	void __rcu **slot;
+	unsigned long index;
 
 	spin_lock_irqsave(&qrtr_nodes_lock, flags);
 	/* If the node is a bridge for other nodes, there are possibly
@@ -189,11 +190,9 @@ static void __qrtr_node_release(struct kref *kref)
 	skb_queue_purge(&node->rx_queue);
 
 	/* Free tx flow counters */
-	radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
-		flow = *slot;
-		radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot);
+	xa_for_each(&node->qrtr_tx_flow, index, flow)
 		kfree(flow);
-	}
+	xa_destroy(&node->qrtr_tx_flow);
 	kfree(node);
 }
 
@@ -228,9 +227,7 @@ static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb)
 
 	key = remote_node << 32 | remote_port;
 
-	rcu_read_lock();
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
-	rcu_read_unlock();
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (flow) {
 		spin_lock(&flow->resume_tx.lock);
 		flow->pending = 0;
@@ -269,12 +266,13 @@ static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port,
 		return 0;
 
 	mutex_lock(&node->qrtr_tx_lock);
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (!flow) {
 		flow = kzalloc_obj(*flow);
 		if (flow) {
 			init_waitqueue_head(&flow->resume_tx);
-			if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) {
+			if (xa_err(xa_store(&node->qrtr_tx_flow, key, flow,
+					    GFP_KERNEL))) {
 				kfree(flow);
 				flow = NULL;
 			}
@@ -326,9 +324,7 @@ static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node,
 	unsigned long key = (u64)dest_node << 32 | dest_port;
 	struct qrtr_tx_flow *flow;
 
-	rcu_read_lock();
-	flow = radix_tree_lookup(&node->qrtr_tx_flow, key);
-	rcu_read_unlock();
+	flow = xa_load(&node->qrtr_tx_flow, key);
 	if (flow) {
 		spin_lock_irq(&flow->resume_tx.lock);
 		flow->tx_failed = 1;
@@ -599,7 +595,7 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid)
 	node->nid = QRTR_EP_NID_AUTO;
 	node->ep = ep;
 
-	INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL);
+	xa_init(&node->qrtr_tx_flow);
 	mutex_init(&node->qrtr_tx_lock);
 
 	qrtr_node_assign(node, nid);
@@ -627,6 +623,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 	struct qrtr_tx_flow *flow;
 	struct sk_buff *skb;
 	unsigned long flags;
+	unsigned long index;
 	void __rcu **slot;
 
 	mutex_lock(&node->ep_lock);
@@ -649,10 +646,8 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 
 	/* Wake up any transmitters waiting for resume-tx from the node */
 	mutex_lock(&node->qrtr_tx_lock);
-	radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) {
-		flow = *slot;
+	xa_for_each(&node->qrtr_tx_flow, index, flow)
 		wake_up_interruptible_all(&flow->resume_tx);
-	}
 	mutex_unlock(&node->qrtr_tx_lock);
 
 	qrtr_node_release(node);
-- 
cgit v1.2.3


From ae05340ccaa9d347fe85415609e075545bec589f Mon Sep 17 00:00:00 2001
From: Yochai Eisenrich <echelonh@gmail.com>
Date: Wed, 25 Mar 2026 00:49:25 +0200
Subject: net: ipv6: ndisc: fix ndisc_ra_useropt to initialize nduseropt_padX
 fields to zero to prevent an info-leak

When processing Router Advertisements with user options the kernel
builds an RTM_NEWNDUSEROPT netlink message. The nduseroptmsg struct
has three padding fields that are never zeroed and can leak kernel data

The fix is simple, just zeroes the padding fields.

Fixes: 31910575a9de ("[IPv6]: Export userland ND options through netlink (RDNSS support)")
Signed-off-by: Yochai Eisenrich <echelonh@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260324224925.2437775-1-echelonh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ndisc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index f6a5d8c73af9..186e60c79214 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1209,6 +1209,9 @@ static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
 	ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type;
 	ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code;
 	ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3;
+	ndmsg->nduseropt_pad1 = 0;
+	ndmsg->nduseropt_pad2 = 0;
+	ndmsg->nduseropt_pad3 = 0;
 
 	memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3);
 
-- 
cgit v1.2.3


From 90c5def10bea574b101b7a520c015ca81742183f Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 2 Mar 2026 18:22:52 -0400
Subject: iommu: Do not call drivers for empty gathers

An empty gather is coded with start=U64_MAX, end=0 and several drivers go
on to convert that to a size with:

 end - start + 1

Which gives 2 for an empty gather. This then causes Weird Stuff to
happen (for example an UBSAN splat in VT-d) that is hopefully harmless,
but maybe not.

Prevent drivers from being called right in iommu_iotlb_sync().

Auditing shows that AMD, Intel, Mediatek and RSIC-V drivers all do things
on these empty gathers.

Further, there are several callers that can trigger empty gathers,
especially in unusual conditions. For example iommu_map_nosync() will call
a 0 size unmap on some error paths. Also in VFIO, iommupt and other
places.

Cc: stable@vger.kernel.org
Reported-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Closes: https://lore.kernel.org/r/11145826.aFP6jjVeTY@jkrzyszt-mobl2.ger.corp.intel.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 include/linux/iommu.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 54b8b48c762e..555597b54083 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -980,7 +980,8 @@ static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
-	if (domain->ops->iotlb_sync)
+	if (domain->ops->iotlb_sync &&
+	    likely(iotlb_gather->start < iotlb_gather->end))
 		domain->ops->iotlb_sync(domain, iotlb_gather);
 
 	iommu_iotlb_gather_init(iotlb_gather);
-- 
cgit v1.2.3


From ee6e69d032550687a3422504bfca3f834c7b5061 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 2 Mar 2026 18:22:53 -0400
Subject: iommupt: Fix short gather if the unmap goes into a large mapping

unmap has the odd behavior that it can unmap more than requested if the
ending point lands within the middle of a large or contiguous IOPTE.

In this case the gather should flush everything unmapped which can be
larger than what was requested to be unmapped. The gather was only
flushing the range requested to be unmapped, not extending to the extra
range, resulting in a short invalidation if the caller hits this special
condition.

This was found by the new invalidation/gather test I am adding in
preparation for ARMv8. Claude deduced the root cause.

As far as I remember nothing relies on unmapping a large entry, so this is
likely not a triggerable bug.

Cc: stable@vger.kernel.org
Fixes: 7c53f4238aa8 ("iommupt: Add unmap_pages op")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/generic_pt/iommu_pt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
index 3e33fe64feab..7e7a6e7abdee 100644
--- a/drivers/iommu/generic_pt/iommu_pt.h
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -1057,7 +1057,7 @@ size_t DOMAIN_NS(unmap_pages)(struct iommu_domain *domain, unsigned long iova,
 
 	pt_walk_range(&range, __unmap_range, &unmap);
 
-	gather_range_pages(iotlb_gather, iommu_table, iova, len,
+	gather_range_pages(iotlb_gather, iommu_table, iova, unmap.unmapped,
 			   &unmap.free_list);
 
 	return unmap.unmapped;
-- 
cgit v1.2.3


From 8b72aa5704c77380742346d4ac755b074b7f9eaa Mon Sep 17 00:00:00 2001
From: Sherry Yang <sherry.yang@oracle.com>
Date: Thu, 26 Mar 2026 09:17:19 -0700
Subject: iommupt/amdv1: mark amdv1pt_install_leaf_entry as __always_inline
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After enabling CONFIG_GCOV_KERNEL and CONFIG_GCOV_PROFILE_ALL, following
build failure is observed under GCC 14.2.1:

In function 'amdv1pt_install_leaf_entry',
    inlined from '__do_map_single_page' at drivers/iommu/generic_pt/fmt/../iommu_pt.h:650:3,
    inlined from '__map_single_page0' at drivers/iommu/generic_pt/fmt/../iommu_pt.h:661:1,
    inlined from 'pt_descend' at drivers/iommu/generic_pt/fmt/../pt_iter.h:391:9,
    inlined from '__do_map_single_page' at drivers/iommu/generic_pt/fmt/../iommu_pt.h:657:10,
    inlined from '__map_single_page1.constprop' at drivers/iommu/generic_pt/fmt/../iommu_pt.h:661:1:
././include/linux/compiler_types.h:706:45: error: call to '__compiletime_assert_71' declared with attribute error: FIELD_PREP: value too large for the field
  706 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
      |

......

drivers/iommu/generic_pt/fmt/amdv1.h:220:26: note: in expansion of macro 'FIELD_PREP'
  220 |                          FIELD_PREP(AMDV1PT_FMT_OA,
      |                          ^~~~~~~~~~

In the path '__do_map_single_page()', level 0 always invokes
'pt_install_leaf_entry(&pts, map->oa, PAGE_SHIFT, …)'. At runtime that
lands in the 'if (oasz_lg2 == isz_lg2)' arm of 'amdv1pt_install_leaf_entry()';
the contiguous-only 'else' block is unreachable for 4 KiB pages.

With CONFIG_GCOV_KERNEL + CONFIG_GCOV_PROFILE_ALL, the extra
instrumentation changes GCC's inlining so that the "dead" 'else' branch
still gets instantiated. The compiler constant-folds the contiguous OA
expression, runs the 'FIELD_PREP()' compile-time check, and produces:

    FIELD_PREP: value too large for the field

gcov-enabled builds therefore fail even though the code path never executes.

Fix this by marking amdv1pt_install_leaf_entry as __always_inline.

Fixes: dcd6a011a8d5 ("iommupt: Add map_pages op")
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sherry Yang <sherry.yang@oracle.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/generic_pt/fmt/amdv1.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/generic_pt/fmt/amdv1.h b/drivers/iommu/generic_pt/fmt/amdv1.h
index 3b2c41d9654d..8d11b08291d7 100644
--- a/drivers/iommu/generic_pt/fmt/amdv1.h
+++ b/drivers/iommu/generic_pt/fmt/amdv1.h
@@ -191,7 +191,7 @@ static inline enum pt_entry_type amdv1pt_load_entry_raw(struct pt_state *pts)
 }
 #define pt_load_entry_raw amdv1pt_load_entry_raw
 
-static inline void
+static __always_inline void
 amdv1pt_install_leaf_entry(struct pt_state *pts, pt_oaddr_t oa,
 			   unsigned int oasz_lg2,
 			   const struct pt_write_attrs *attrs)
-- 
cgit v1.2.3


From 7f138de156b20d9f9da6f72f90b63c01941d97d3 Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Fri, 27 Mar 2026 01:14:12 +0800
Subject: auxdisplay: line-display: fix NULL dereference in linedisp_release

linedisp_release() currently retrieves the enclosing struct linedisp via
to_linedisp(). That lookup depends on the attachment list, but the
attachment may already have been removed before put_device() invokes the
release callback. This can happen in linedisp_unregister(), and can also
be reached from some linedisp_register() error paths.

In that case, to_linedisp() returns NULL and linedisp_release()
dereferences it while freeing the display resources.

The struct device released here is the embedded linedisp->dev used by
linedisp_register(), so retrieve the enclosing object directly with
container_of() instead.

Fixes: 66c93809487e ("auxdisplay: linedisp: encapsulate container_of usage within to_linedisp")
Cc: stable@vger.kernel.org
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/auxdisplay/line-display.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/auxdisplay/line-display.c b/drivers/auxdisplay/line-display.c
index 81b4aac65807..fb6d9294140d 100644
--- a/drivers/auxdisplay/line-display.c
+++ b/drivers/auxdisplay/line-display.c
@@ -365,7 +365,7 @@ static DEFINE_IDA(linedisp_id);
 
 static void linedisp_release(struct device *dev)
 {
-	struct linedisp *linedisp = to_linedisp(dev);
+	struct linedisp *linedisp = container_of(dev, struct linedisp, dev);
 
 	kfree(linedisp->map);
 	kfree(linedisp->message);
-- 
cgit v1.2.3


From d3be95efc6a1e03230ef646b498050152efe2888 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Thu, 19 Mar 2026 15:49:46 +0800
Subject: ALSA: hda/realtek - Fixed Speaker Mute LED for HP EliteBoard G1a
 platform

On the HP EliteBoard G1a platform (models without a headphone jack).
the speaker mute LED failed to function. The Sysfs ctl-led info showed
empty values because the standard LED registration couldn't correctly
bind to the master switch.
Adding this patch will fix and enable the speaker mute LED feature.

Tested-by: Chris Chiu <chris.chiu@canonical.com>
Signed-off-by: Kailang Yang <kailang@realtek.com>
Link: https://lore.kernel.org/279e929e884849df84687dbd67f20037@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 327f4dc1b09f..9106498eb19f 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -3725,22 +3725,42 @@ static void alc245_tas2781_spi_hp_fixup_muteled(struct hda_codec *codec,
 	alc_fixup_hp_gpio_led(codec, action, 0x04, 0x0);
 	alc285_fixup_hp_coef_micmute_led(codec, fix, action);
 }
+
+static void alc245_hp_spk_mute_led_update(void *private_data, int enabled)
+{
+	struct hda_codec *codec = private_data;
+	unsigned int val;
+
+	val = enabled ? 0x08 : 0x04; /* 0x08 led on, 0x04 led off */
+	alc_update_coef_idx(codec, 0x0b, 0x0c, val);
+}
+
 /* JD2: mute led GPIO3: micmute led */
 static void alc245_tas2781_i2c_hp_fixup_muteled(struct hda_codec *codec,
 					  const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
 	static const hda_nid_t conn[] = { 0x02 };
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
+		if (!hp_pin) {
+			spec->gen.vmaster_mute.hook = alc245_hp_spk_mute_led_update;
+			spec->gen.vmaster_mute_led = 1;
+		}
 		spec->gen.auto_mute_via_amp = 1;
 		snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
 		break;
+	case HDA_FIXUP_ACT_INIT:
+		if (!hp_pin)
+			alc245_hp_spk_mute_led_update(codec, !spec->gen.master_mute);
+		break;
 	}
 
 	tas2781_fixup_txnw_i2c(codec, fix, action);
-	alc245_fixup_hp_mute_led_coefbit(codec, fix, action);
+	if (hp_pin)
+		alc245_fixup_hp_mute_led_coefbit(codec, fix, action);
 	alc285_fixup_hp_coef_micmute_led(codec, fix, action);
 }
 /*
-- 
cgit v1.2.3


From 2f388b4e8fdd6b0f27cafd281658daacfd85807e Mon Sep 17 00:00:00 2001
From: César Montoya <sprit152009@gmail.com>
Date: Sat, 21 Mar 2026 10:36:03 -0500
Subject: ALSA: hda/realtek: Add mute LED quirk for HP Pavilion 15-eg0xxx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Pavilion 15-eg0xxx with subsystem ID 0x103c87cb uses a Realtek
ALC287 codec with a mute LED wired to GPIO pin 4 (mask 0x10). The
existing ALC287_FIXUP_HP_GPIO_LED fixup already handles this correctly,
but the subsystem ID was missing from the quirk table.

GPIO pin confirmed via manual hda-verb testing:
  hda-verb SET_GPIO_MASK 0x10
  hda-verb SET_GPIO_DIRECTION 0x10
  hda-verb SET_GPIO_DATA 0x10

Signed-off-by: César Montoya <sprit152009@gmail.com>
Link: https://patch.msgid.link/20260321153603.12771-1-sprit152009@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 9106498eb19f..a72149d6fc90 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6914,6 +6914,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8788, "HP OMEN 15", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x87b7, "HP Laptop 14-fq0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x87cb, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87cc, "HP Pavilion 15-eg0xxx", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87d3, "HP Laptop 15-gw0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x87df, "HP ProBook 430 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
-- 
cgit v1.2.3


From 990a8b0732cf899d4a0f847b0a67efeb9a384c82 Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Mon, 23 Mar 2026 21:59:21 +1030
Subject: ALSA: usb-audio: Exclude Scarlett 2i4 1st Gen from SKIP_IFACE_SETUP

Same issue that the Scarlett 2i2 1st Gen had:
QUIRK_FLAG_SKIP_IFACE_SETUP causes distorted/flanging audio on the
Scarlett 2i4 1st Gen (1235:800a).

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Reported-by: dcferreira [https://github.com/geoffreybennett/linux-fcp/issues/54]
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://patch.msgid.link/acEkEbftzyNe8W7C@m.b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index cd3a9fe8edf2..125230464ab5 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2430,6 +2430,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	VENDOR_FLG(0x07fd, /* MOTU */
 		   QUIRK_FLAG_VALIDATE_RATES),
 	DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */
+	DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),
-- 
cgit v1.2.3


From faceb5cf5d7a08f4a40335d22d833bb75f05d99e Mon Sep 17 00:00:00 2001
From: Kshamendra Kumar Mishra <kshamendrakumarmishra@gmail.com>
Date: Mon, 23 Mar 2026 22:07:50 +0530
Subject: ALSA: hda/realtek: add HP Laptop 15-fd0xxx mute LED quirk

HP Laptop 15-fd0xxx with ALC236 codec does not handle the toggling of
the mute LED.
This patch adds a quirk entry for subsystem ID 0x8dd7 using
ALC236_FIXUP_HP_MUTE_LED_COEFBIT2 fixup, enabling correct mute LED
behavior.

Signed-off-by: Kshamendra Kumar Mishra <kshamendrakumarmishra@gmail.com>
Link: https://patch.msgid.link/DHAB51ISUM96.2K9SZIABIDEQ0@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index a72149d6fc90..b6a58852752a 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7146,6 +7146,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
+	SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8de9, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
 	SND_PCI_QUIRK(0x103c, 0x8dec, "HP EliteBook 640 G12", ALC236_FIXUP_HP_GPIO_LED),
-- 
cgit v1.2.3


From ee6c551a7d84fde084e10cc02fa8c7d03e6438f9 Mon Sep 17 00:00:00 2001
From: Lianqin Hu <hulianqin@vivo.com>
Date: Wed, 25 Mar 2026 06:26:48 +0000
Subject: ALSA: usb-audio: Add iface reset and delay quirk for AB17X USB Audio

Setting up the interface when suspended/resumeing fail on this card.
Adding a reset and delay quirk will eliminate this problem.

usb 1-1: new full-speed USB device number 2 using xhci-hcd
usb 1-1: New USB device found, idVendor=001f, idProduct=0b23
usb 1-1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
usb 1-1: Product: AB17X USB Audio
usb 1-1: Manufacturer: Generic
usb 1-1: SerialNumber: 20241228172028

Signed-off-by: Lianqin Hu <hulianqin@vivo.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/PUZPR06MB6224CA59AD2B26054120B276D249A@PUZPR06MB6224.apcprd06.prod.outlook.com
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 125230464ab5..1f82e9e02d4b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2148,6 +2148,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 	/* Device matches */
 	DEVICE_FLG(0x001f, 0x0b21, /* AB13X USB Audio */
 		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
+	DEVICE_FLG(0x001f, 0x0b23, /* AB17X USB Audio */
+		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x0020, 0x0b21, /* GHW-123P */
 		   QUIRK_FLAG_FORCE_IFACE_RESET | QUIRK_FLAG_IFACE_DELAY),
 	DEVICE_FLG(0x03f0, 0x654a, /* HP 320 FHD Webcam */
-- 
cgit v1.2.3


From ed4da361bf943b9041fc63e5cb6af01b3c0de978 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 26 Mar 2026 14:05:38 -0500
Subject: Revert "ALSA: hda/intel: Add MSI X870E Tomahawk to denylist"

commit 30b3211aa2416 ("ALSA: hda/intel: Add MSI X870E Tomahawk
to denylist") was added to silence a warning, but this effectively
reintroduced commit df42ee7e22f03 ("ALSA: hda: Add ASRock
X670E Taichi to denylist") which was already reported to cause
problems and reverted in commit ee8f1613596ad ("Revert "ALSA: hda:
Add ASRock X670E Taichi to denylist"")

Revert it yet again.

Cc: stable@vger.kernel.org
Reported-by: Juhyun Song <juju6985@outlook.kr>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221274
Cc: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patch.msgid.link/20260326190542.524515-1-mario.limonciello@amd.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/controllers/intel.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c
index 3f434994c18d..2edbcab597c8 100644
--- a/sound/hda/controllers/intel.c
+++ b/sound/hda/controllers/intel.c
@@ -2077,7 +2077,6 @@ static const struct pci_device_id driver_denylist[] = {
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */
 	{ PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */
-	{ PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */
 	{}
 };
 
-- 
cgit v1.2.3


From d802d848308b35220f21a8025352f0c0aba15c12 Mon Sep 17 00:00:00 2001
From: Benoît Sevens <bsevens@google.com>
Date: Mon, 23 Mar 2026 16:11:07 +0000
Subject: HID: roccat: fix use-after-free in roccat_report_event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

roccat_report_event() iterates over the device->readers list without
holding the readers_lock. This allows a concurrent roccat_release() to
remove and free a reader while it's still being accessed, leading to a
use-after-free.

Protect the readers list traversal with the readers_lock mutex.

Signed-off-by: Benoît Sevens <bsevens@google.com>
Reviewed-by: Silvan Jegen <s.jegen@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-roccat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c
index c7f7562e22e5..e413662f7508 100644
--- a/drivers/hid/hid-roccat.c
+++ b/drivers/hid/hid-roccat.c
@@ -257,6 +257,7 @@ int roccat_report_event(int minor, u8 const *data)
 	if (!new_value)
 		return -ENOMEM;
 
+	mutex_lock(&device->readers_lock);
 	mutex_lock(&device->cbuf_lock);
 
 	report = &device->cbuf[device->cbuf_end];
@@ -279,6 +280,7 @@ int roccat_report_event(int minor, u8 const *data)
 	}
 
 	mutex_unlock(&device->cbuf_lock);
+	mutex_unlock(&device->readers_lock);
 
 	wake_up_interruptible(&device->wait);
 	return 0;
-- 
cgit v1.2.3


From 532743944324a873bbaf8620fcabcd0e69e30c36 Mon Sep 17 00:00:00 2001
From: leo vriska <leo@60228.dev>
Date: Wed, 4 Mar 2026 13:36:59 -0500
Subject: HID: quirks: add HID_QUIRK_ALWAYS_POLL for 8BitDo Pro 3

According to a mailing list report [1], this controller's predecessor
has the same issue. However, it uses the xpad driver instead of HID, so
this quirk wouldn't apply.

[1]: https://lore.kernel.org/linux-input/unufo3$det$1@ciao.gmane.io/

Signed-off-by: leo vriska <leo@60228.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h    | 3 +++
 drivers/hid/hid-quirks.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index afcee13bad61..e432cc0df680 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -22,6 +22,9 @@
 #define USB_DEVICE_ID_3M2256		0x0502
 #define USB_DEVICE_ID_3M3266		0x0506
 
+#define USB_VENDOR_ID_8BITDO		0x2dc8
+#define USB_DEVICE_ID_8BITDO_PRO_3	0x6009
+
 #define USB_VENDOR_ID_A4TECH		0x09da
 #define USB_DEVICE_ID_A4TECH_WCP32PU	0x0006
 #define USB_DEVICE_ID_A4TECH_X5_005D	0x000a
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 3217e436c052..f6be3ffee023 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -25,6 +25,7 @@
  */
 
 static const struct hid_device_id hid_quirks[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_8BITDO, USB_DEVICE_ID_8BITDO_PRO_3), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL },
-- 
cgit v1.2.3


From e1415b9418eb22b4a7a1ef4b4aec9dd0a49e3fa7 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 25 Mar 2026 12:26:38 -0700
Subject: platform/x86: ISST: Reset core count to 0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on feature revision, number of buckets can be less than the
TRL_MAX_BUCKETS. In that case core counts in the remaining buckets
can be set to some invalid values.

Hence reset core count to 0 for all buckets before assigning correct
values.

Fixes: 885d1c2a30b7 ("platform/x86: ISST: Support SST-TF revision 2")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260325192638.3417281-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index e238c3105c78..63f08d66703a 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -1461,6 +1461,8 @@ static int isst_if_get_turbo_freq_info(void __user *argp)
 					    SST_MUL_FACTOR_FREQ)
 	}
 
+	memset(turbo_freq.bucket_core_counts, 0, sizeof(turbo_freq.bucket_core_counts));
+
 	if (feature_rev >= 2) {
 		bool has_tf_info_8 = false;
 
-- 
cgit v1.2.3


From 4ab604b3f3aa8dcccc7505f5d310016682a99d5f Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 25 Mar 2026 12:29:09 -0700
Subject: platform/x86/intel-uncore-freq: Handle autonomous UFS status bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the AUTONOMOUS_UFS_DISABLED bit is set in the header, the ELC
(Efficiency Latency Control) feature is non-functional. Hence, return
error for read or write to ELC attributes.

Fixes: bb516dc79c4a ("platform/x86/intel-uncore-freq: Add support for efficiency latency control")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260325192909.3417322-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c   | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 1237d9570886..4c7e64db478c 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -537,6 +537,7 @@ static void set_cdie_id(int domain_id, struct tpmi_uncore_cluster_info *cluster_
 #define UNCORE_VERSION_MASK			GENMASK_ULL(7, 0)
 #define UNCORE_LOCAL_FABRIC_CLUSTER_ID_MASK	GENMASK_ULL(15, 8)
 #define UNCORE_CLUSTER_OFF_MASK			GENMASK_ULL(7, 0)
+#define UNCORE_AUTONOMOUS_UFS_DISABLED		BIT(32)
 #define UNCORE_MAX_CLUSTER_PER_DOMAIN		8
 
 static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
@@ -598,6 +599,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 
 	for (i = 0; i < num_resources; ++i) {
 		struct tpmi_uncore_power_domain_info *pd_info;
+		bool auto_ufs_enabled;
 		struct resource *res;
 		u64 cluster_offset;
 		u8 cluster_mask;
@@ -647,6 +649,8 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 			continue;
 		}
 
+		auto_ufs_enabled = !(header & UNCORE_AUTONOMOUS_UFS_DISABLED);
+
 		/* Find out number of clusters in this resource */
 		pd_info->cluster_count = hweight8(cluster_mask);
 
@@ -689,7 +693,9 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 
 			cluster_info->uncore_root = tpmi_uncore;
 
-			if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) >= UNCORE_ELC_SUPPORTED_VERSION)
+			if ((TPMI_MINOR_VERSION(pd_info->ufs_header_ver) >=
+			     UNCORE_ELC_SUPPORTED_VERSION) &&
+			    auto_ufs_enabled)
 				cluster_info->elc_supported = true;
 
 			ret = uncore_freq_add_entry(&cluster_info->uncore_data, 0);
-- 
cgit v1.2.3


From ba7d46e0a384398c58eee34579986f830260d37b Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 25 Mar 2026 12:31:57 -0700
Subject: platform/x86: ISST: Increase minor version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current implementation doesn't require any changes to support minor
version 3, hence increment it to avoid "Unsupported minor version:3"
message.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260325193158.3417382-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 63f08d66703a..b804cb753f94 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -36,7 +36,7 @@
 
 /* Supported SST hardware version by this driver */
 #define ISST_MAJOR_VERSION	0
-#define ISST_MINOR_VERSION	2
+#define ISST_MINOR_VERSION	3
 
 /*
  * Used to indicate if value read from MMIO needs to get multiplied
-- 
cgit v1.2.3


From b7f4e7babc122426e8802dffdd8ff1501db6adf4 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 25 Mar 2026 12:31:58 -0700
Subject: platform/x86/intel-uncore-freq: Increase minor version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current implementation doesn't require any changes to support minor
version 3, hence increment it to avoid "Unsupported minor version:3"
message.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://patch.msgid.link/20260325193158.3417382-2-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 4c7e64db478c..88015a2c6a0d 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -31,7 +31,7 @@
 #include "uncore-frequency-common.h"
 
 #define	UNCORE_MAJOR_VERSION		0
-#define	UNCORE_MINOR_VERSION		2
+#define	UNCORE_MINOR_VERSION		3
 #define UNCORE_ELC_SUPPORTED_VERSION	2
 #define UNCORE_HEADER_INDEX		0
 #define UNCORE_FABRIC_CLUSTER_OFFSET	8
-- 
cgit v1.2.3


From 1a9452c428a6b76f0b797bae21daa454fccef1a2 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 24 Mar 2026 16:16:41 -0500
Subject: platform/x86/amd: pmc: Add Thinkpad L14 Gen3 to quirk_s2idle_bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This platform is a similar vintage of platforms that had a BIOS bug
leading to a 10s delay at resume from s0i3.

Add a quirk for it.

Reported-by: Imrane <ihalim.me@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221273
Tested-by: Imrane <ihalim.me@gmail.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patch.msgid.link/20260324211647.357924-1-mario.limonciello@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmc/pmc-quirks.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index ed285afaf9b0..24506e342943 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -203,6 +203,15 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "82XQ"),
 		}
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=221273 */
+	{
+		.ident = "Thinkpad L14 Gen3",
+		.driver_data = &quirk_s2idle_bug,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21C6"),
+		}
+	},
 	/* https://gitlab.freedesktop.org/drm/amd/-/issues/4434 */
 	{
 		.ident = "Lenovo Yoga 6 13ALC6",
-- 
cgit v1.2.3


From 1f6ee9be92f8df85a8c9a5a78c20fd39c0c21a95 Mon Sep 17 00:00:00 2001
From: Fei Lv <feilv@asrmicro.com>
Date: Mon, 22 Jul 2024 18:14:43 +0800
Subject: ovl: make fsync after metadata copy-up opt-in mount option

Commit 7d6899fb69d25 ("ovl: fsync after metadata copy-up") was done to
fix durability of overlayfs copy up on an upper filesystem which does
not enforce ordering on storing of metadata changes (e.g. ubifs).

In an earlier revision of the regressing commit by Lei Lv, the metadata
fsync behavior was opt-in via a new "fsync=strict" mount option.
We were hoping that the opt-in mount option could be avoided, so the
change was only made to depend on metacopy=off, in the hope of not
hurting performance of metadata heavy workloads, which are more likely
to be using metacopy=on.

This hope was proven wrong by a performance regression report from Google
COS workload after upgrade to kernel 6.12.

This is an adaptation of Lei's original "fsync=strict" mount option
to the existing upstream code.

The new mount option is mutually exclusive with the "volatile" mount
option, so the latter is now an alias to the "fsync=volatile" mount
option.

Reported-by: Chenglong Tang <chenglongtang@google.com>
Closes: https://lore.kernel.org/linux-unionfs/CAOdxtTadAFH01Vui1FvWfcmQ8jH1O45owTzUcpYbNvBxnLeM7Q@mail.gmail.com/
Link: https://lore.kernel.org/linux-unionfs/CAOQ4uxgKC1SgjMWre=fUb00v8rxtd6sQi-S+dxR8oDzAuiGu8g@mail.gmail.com/
Fixes: 7d6899fb69d25 ("ovl: fsync after metadata copy-up")
Depends: 50e638beb67e0 ("ovl: Use str_on_off() helper in ovl_show_options()")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Fei Lv <feilv@asrmicro.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 Documentation/filesystems/overlayfs.rst | 50 +++++++++++++++++++++++++++++++++
 fs/overlayfs/copy_up.c                  |  6 ++--
 fs/overlayfs/overlayfs.h                | 21 ++++++++++++++
 fs/overlayfs/ovl_entry.h                |  7 +----
 fs/overlayfs/params.c                   | 33 ++++++++++++++++++----
 fs/overlayfs/super.c                    |  2 +-
 6 files changed, 104 insertions(+), 15 deletions(-)

diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index af5a69f87da4..eb846518e6ac 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -783,6 +783,56 @@ controlled by the "uuid" mount option, which supports these values:
     mounted with "uuid=on".
 
 
+Durability and copy up
+----------------------
+
+The fsync(2) system call ensures that the data and metadata of a file
+are safely written to the backing storage, which is expected to
+guarantee the existence of the information post system crash.
+
+Without an fsync(2) call, there is no guarantee that the observed
+data after a system crash will be either the old or the new data, but
+in practice, the observed data after crash is often the old or new data
+or a mix of both.
+
+When an overlayfs file is modified for the first time, copy up will
+create a copy of the lower file and its parent directories in the upper
+layer.  Since the Linux filesystem API does not enforce any particular
+ordering on storing changes without explicit fsync(2) calls, in case
+of a system crash, the upper file could end up with no data at all
+(i.e. zeros), which would be an unusual outcome.  To avoid this
+experience, overlayfs calls fsync(2) on the upper file before completing
+data copy up with rename(2) or link(2) to make the copy up "atomic".
+
+By default, overlayfs does not explicitly call fsync(2) on copied up
+directories or on metadata-only copy up, so it provides no guarantee to
+persist the user's modification unless the user calls fsync(2).
+The fsync during copy up only guarantees that if a copy up is observed
+after a crash, the observed data is not zeroes or intermediate values
+from the copy up staging area.
+
+On traditional local filesystems with a single journal (e.g. ext4, xfs),
+fsync on a file also persists the parent directory changes, because they
+are usually modified in the same transaction, so metadata durability during
+data copy up effectively comes for free.  Overlayfs further limits risk by
+disallowing network filesystems as upper layer.
+
+Overlayfs can be tuned to prefer performance or durability when storing
+to the underlying upper layer.  This is controlled by the "fsync" mount
+option, which supports these values:
+
+- "auto": (default)
+    Call fsync(2) on upper file before completion of data copy up.
+    No explicit fsync(2) on directory or metadata-only copy up.
+- "strict":
+    Call fsync(2) on upper file and directories before completion of any
+    copy up.
+- "volatile": [*]
+    Prefer performance over durability (see `Volatile mount`_)
+
+[*] The mount option "volatile" is an alias to "fsync=volatile".
+
+
 Volatile mount
 --------------
 
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 758611ee4475..13cb60b52bd6 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -1146,15 +1146,15 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 		return -EOVERFLOW;
 
 	/*
-	 * With metacopy disabled, we fsync after final metadata copyup, for
+	 * With "fsync=strict", we fsync after final metadata copyup, for
 	 * both regular files and directories to get atomic copyup semantics
 	 * on filesystems that do not use strict metadata ordering (e.g. ubifs).
 	 *
-	 * With metacopy enabled we want to avoid fsync on all meta copyup
+	 * By default, we want to avoid fsync on all meta copyup, because
 	 * that will hurt performance of workloads such as chown -R, so we
 	 * only fsync on data copyup as legacy behavior.
 	 */
-	ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy &&
+	ctx.metadata_fsync = ovl_should_sync_metadata(OVL_FS(dentry->d_sb)) &&
 			     (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode));
 	ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index cad2055ebf18..63b299bf12f7 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -99,6 +99,12 @@ enum {
 	OVL_VERITY_REQUIRE,
 };
 
+enum {
+	OVL_FSYNC_VOLATILE,
+	OVL_FSYNC_AUTO,
+	OVL_FSYNC_STRICT,
+};
+
 /*
  * The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
  * where:
@@ -656,6 +662,21 @@ static inline bool ovl_xino_warn(struct ovl_fs *ofs)
 	return ofs->config.xino == OVL_XINO_ON;
 }
 
+static inline bool ovl_should_sync(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode != OVL_FSYNC_VOLATILE;
+}
+
+static inline bool ovl_should_sync_metadata(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode == OVL_FSYNC_STRICT;
+}
+
+static inline bool ovl_is_volatile(struct ovl_config *config)
+{
+	return config->fsync_mode == OVL_FSYNC_VOLATILE;
+}
+
 /*
  * To avoid regressions in existing setups with overlay lower offline changes,
  * we allow lower changes only if none of the new features are used.
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 1d4828dbcf7a..80cad4ea96a3 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -18,7 +18,7 @@ struct ovl_config {
 	int xino;
 	bool metacopy;
 	bool userxattr;
-	bool ovl_volatile;
+	int fsync_mode;
 };
 
 struct ovl_sb {
@@ -120,11 +120,6 @@ static inline struct ovl_fs *OVL_FS(struct super_block *sb)
 	return (struct ovl_fs *)sb->s_fs_info;
 }
 
-static inline bool ovl_should_sync(struct ovl_fs *ofs)
-{
-	return !ofs->config.ovl_volatile;
-}
-
 static inline unsigned int ovl_numlower(struct ovl_entry *oe)
 {
 	return oe ? oe->__numlower : 0;
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 8111b437ae5d..c93fcaa45d4a 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -58,6 +58,7 @@ enum ovl_opt {
 	Opt_xino,
 	Opt_metacopy,
 	Opt_verity,
+	Opt_fsync,
 	Opt_volatile,
 	Opt_override_creds,
 };
@@ -140,6 +141,23 @@ static int ovl_verity_mode_def(void)
 	return OVL_VERITY_OFF;
 }
 
+static const struct constant_table ovl_parameter_fsync[] = {
+	{ "volatile",	OVL_FSYNC_VOLATILE },
+	{ "auto",	OVL_FSYNC_AUTO     },
+	{ "strict",	OVL_FSYNC_STRICT   },
+	{}
+};
+
+static const char *ovl_fsync_mode(struct ovl_config *config)
+{
+	return ovl_parameter_fsync[config->fsync_mode].name;
+}
+
+static int ovl_fsync_mode_def(void)
+{
+	return OVL_FSYNC_AUTO;
+}
+
 const struct fs_parameter_spec ovl_parameter_spec[] = {
 	fsparam_string_empty("lowerdir",    Opt_lowerdir),
 	fsparam_file_or_string("lowerdir+", Opt_lowerdir_add),
@@ -155,6 +173,7 @@ const struct fs_parameter_spec ovl_parameter_spec[] = {
 	fsparam_enum("xino",                Opt_xino, ovl_parameter_xino),
 	fsparam_enum("metacopy",            Opt_metacopy, ovl_parameter_bool),
 	fsparam_enum("verity",              Opt_verity, ovl_parameter_verity),
+	fsparam_enum("fsync",               Opt_fsync, ovl_parameter_fsync),
 	fsparam_flag("volatile",            Opt_volatile),
 	fsparam_flag_no("override_creds",   Opt_override_creds),
 	{}
@@ -665,8 +684,11 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case Opt_verity:
 		config->verity_mode = result.uint_32;
 		break;
+	case Opt_fsync:
+		config->fsync_mode = result.uint_32;
+		break;
 	case Opt_volatile:
-		config->ovl_volatile = true;
+		config->fsync_mode = OVL_FSYNC_VOLATILE;
 		break;
 	case Opt_userxattr:
 		config->userxattr = true;
@@ -800,6 +822,7 @@ int ovl_init_fs_context(struct fs_context *fc)
 	ofs->config.nfs_export		= ovl_nfs_export_def;
 	ofs->config.xino		= ovl_xino_def();
 	ofs->config.metacopy		= ovl_metacopy_def;
+	ofs->config.fsync_mode		= ovl_fsync_mode_def();
 
 	fc->s_fs_info		= ofs;
 	fc->fs_private		= ctx;
@@ -870,9 +893,9 @@ int ovl_fs_params_verify(const struct ovl_fs_context *ctx,
 		config->index = false;
 	}
 
-	if (!config->upperdir && config->ovl_volatile) {
+	if (!config->upperdir && ovl_is_volatile(config)) {
 		pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n");
-		config->ovl_volatile = false;
+		config->fsync_mode = ovl_fsync_mode_def();
 	}
 
 	if (!config->upperdir && config->uuid == OVL_UUID_ON) {
@@ -1070,8 +1093,8 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 		seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config));
 	if (ofs->config.metacopy != ovl_metacopy_def)
 		seq_printf(m, ",metacopy=%s", str_on_off(ofs->config.metacopy));
-	if (ofs->config.ovl_volatile)
-		seq_puts(m, ",volatile");
+	if (ofs->config.fsync_mode != ovl_fsync_mode_def())
+		seq_printf(m, ",fsync=%s", ovl_fsync_mode(&ofs->config));
 	if (ofs->config.userxattr)
 		seq_puts(m, ",userxattr");
 	if (ofs->config.verity_mode != ovl_verity_mode_def())
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index d4c12feec039..0822987cfb51 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -776,7 +776,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	 * For volatile mount, create a incompat/volatile/dirty file to keep
 	 * track of it.
 	 */
-	if (ofs->config.ovl_volatile) {
+	if (ovl_is_volatile(&ofs->config)) {
 		err = ovl_create_volatile_dirty(ofs);
 		if (err < 0) {
 			pr_err("Failed to create volatile/dirty file.\n");
-- 
cgit v1.2.3


From 5e67ba9bb531e1ec6599a82a065dea9040b9ce50 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Wed, 25 Mar 2026 15:41:52 +0800
Subject: net/ipv6: ioam6: prevent schema length wraparound in trace fill

ioam6_fill_trace_data() stores the schema contribution to the trace
length in a u8. With bit 22 enabled and the largest schema payload,
sclen becomes 1 + 1020 / 4, wraps from 256 to 0, and bypasses the
remaining-space check. __ioam6_fill_trace_data() then positions the
write cursor without reserving the schema area but still copies the
4-byte schema header and the full schema payload, overrunning the trace
buffer.

Keep sclen in an unsigned int so the remaining-space check and the write
cursor calculation both see the full schema length.

Fixes: 8c6f6fa67726 ("ipv6: ioam: IOAM Generic Netlink API")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Reviewed-by: Justin Iurman <justin.iurman@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ioam6.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c
index b76f89d92e7b..3978773bec42 100644
--- a/net/ipv6/ioam6.c
+++ b/net/ipv6/ioam6.c
@@ -708,7 +708,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 				    struct ioam6_namespace *ns,
 				    struct ioam6_trace_hdr *trace,
 				    struct ioam6_schema *sc,
-				    u8 sclen, bool is_input)
+				    unsigned int sclen, bool is_input)
 {
 	struct net_device *dev = skb_dst_dev(skb);
 	struct timespec64 ts;
@@ -939,7 +939,7 @@ void ioam6_fill_trace_data(struct sk_buff *skb,
 			   bool is_input)
 {
 	struct ioam6_schema *sc;
-	u8 sclen = 0;
+	unsigned int sclen = 0;
 
 	/* Skip if Overflow flag is set
 	 */
-- 
cgit v1.2.3


From bb417456c7814d1493d98b7dd9c040bf3ce3b4ed Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Wed, 25 Mar 2026 12:20:53 +0100
Subject: tg3: Fix race for querying speed/duplex

When driver signals carrier up via netif_carrier_on() its internal
link_up state isn't updated immediately. This leads to inconsistent
speed/duplex in /proc/net/bonding/bondX where the speed and duplex
is shown as unknown while ethtool shows correct values. Fix this by
using netif_carrier_ok() for link checking in get_ksettings function.

Fixes: 84421b99cedc ("tg3: Update link_up flag for phylib devices")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 21a5dd342724..73a4b569b03e 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12299,7 +12299,7 @@ static int tg3_get_link_ksettings(struct net_device *dev,
 	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
 						advertising);
 
-	if (netif_running(dev) && tp->link_up) {
+	if (netif_running(dev) && netif_carrier_ok(dev)) {
 		cmd->base.speed = tp->link_config.active_speed;
 		cmd->base.duplex = tp->link_config.active_duplex;
 		ethtool_convert_legacy_u32_to_link_mode(
-- 
cgit v1.2.3


From 5597dd284ff8c556c0b00f6a34473677426e3f81 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Wed, 25 Mar 2026 12:51:30 +0000
Subject: net: ti: icssg-prueth: fix missing data copy and wrong recycle in ZC
 RX dispatch

emac_dispatch_skb_zc() allocates a new skb via napi_alloc_skb() but
never copies the packet data from the XDP buffer into it. The skb is
passed up the stack containing uninitialized heap memory instead of
the actual received packet, leaking kernel heap contents to userspace.

Copy the received packet data from the XDP buffer into the skb using
skb_copy_to_linear_data().

Additionally, remove the skb_mark_for_recycle() call since the skb is
backed by the NAPI page frag allocator, not page_pool. Marking a
non-page_pool skb for recycle causes the free path to return pages to
a page_pool that does not own them, corrupting page_pool state.

The non-ZC path (emac_rx_packet) does not have these issues because it
uses napi_build_skb() to wrap the existing page_pool page directly,
requiring no copy, and correctly marks for recycle since the page comes
from page_pool_dev_alloc_pages().

Fixes: 7a64bb388df3 ("net: ti: icssg-prueth: Add AF_XDP zero copy for RX")
Signed-off-by: David Carlier <devnexen@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index fd4e7622f123..a28a608f9bf4 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -902,6 +902,7 @@ static void emac_dispatch_skb_zc(struct prueth_emac *emac, struct xdp_buff *xdp,
 
 	skb_reserve(skb, headroom);
 	skb_put(skb, pkt_len);
+	skb_copy_to_linear_data(skb, xdp->data, pkt_len);
 	skb->dev = ndev;
 
 	/* RX HW timestamp */
@@ -912,7 +913,6 @@ static void emac_dispatch_skb_zc(struct prueth_emac *emac, struct xdp_buff *xdp,
 		skb->offload_fwd_mark = emac->offload_fwd_mark;
 	skb->protocol = eth_type_trans(skb, ndev);
 
-	skb_mark_for_recycle(skb);
 	napi_gro_receive(&emac->napi_rx, skb);
 	ndev->stats.rx_bytes += pkt_len;
 	ndev->stats.rx_packets++;
-- 
cgit v1.2.3


From f88e2e748a1fc3cb4b8d163a9be790812f578850 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Wed, 18 Feb 2026 16:08:49 +0100
Subject: i2c: imx: fix i2c issue when reading multiple messages

When reading multiple messages, meaning a repeated start is required,
polling the bus busy bit must be avoided. This must only be done for
the last message. Otherwise, the driver will timeout.

Here an example of such a sequence that fails with an error:
i2ctransfer -y -a 0 w1@0x00 0x02 r1 w1@0x00 0x02 r1
Error: Sending messages failed: Connection timed out

Fixes: 5f5c2d4579ca ("i2c: imx: prevent rescheduling in non dma mode")
Cc: stable@vger.kernel.org # v6.13+
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260218150940.131354-2-eichest@gmail.com
---
 drivers/i2c/busses/i2c-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 85f554044cf1..56e2a14495a9 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1522,7 +1522,7 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs,
 		dev_err(&i2c_imx->adapter.dev, "<%s> read timedout\n", __func__);
 		return -ETIMEDOUT;
 	}
-	if (!i2c_imx->stopped)
+	if (i2c_imx->is_lastmsg && !i2c_imx->stopped)
 		return i2c_imx_bus_busy(i2c_imx, 0, false);
 
 	return 0;
-- 
cgit v1.2.3


From 13101db735bdb29c5f60e95fb578690bd178b30f Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Wed, 18 Feb 2026 16:08:50 +0100
Subject: i2c: imx: ensure no clock is generated after last read

When reading from the I2DR register, right after releasing the bus by
clearing MSTA and MTX, the I2C controller might still generate an
additional clock cycle which can cause devices to misbehave. Ensure to
only read from I2DR after the bus is not busy anymore. Because this
requires polling, the read of the last byte is moved outside of the
interrupt handler.

An example for such a failing transfer is this:
i2ctransfer -y -a 0 w1@0x00 0x02 r1
Error: Sending messages failed: Connection timed out
It does not happen with every device because not all devices react to
the additional clock cycle.

Fixes: 5f5c2d4579ca ("i2c: imx: prevent rescheduling in non dma mode")
Cc: stable@vger.kernel.org # v6.13+
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260218150940.131354-3-eichest@gmail.com
---
 drivers/i2c/busses/i2c-imx.c | 51 +++++++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 56e2a14495a9..452d120a210b 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1018,8 +1018,9 @@ static inline int i2c_imx_isr_read(struct imx_i2c_struct *i2c_imx)
 	return 0;
 }
 
-static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
+static inline enum imx_i2c_state i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
 {
+	enum imx_i2c_state next_state = IMX_I2C_STATE_READ_CONTINUE;
 	unsigned int temp;
 
 	if ((i2c_imx->msg->len - 1) == i2c_imx->msg_buf_idx) {
@@ -1033,18 +1034,20 @@ static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
 				i2c_imx->stopped =  1;
 			temp &= ~(I2CR_MSTA | I2CR_MTX);
 			imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
-		} else {
-			/*
-			 * For i2c master receiver repeat restart operation like:
-			 * read -> repeat MSTA -> read/write
-			 * The controller must set MTX before read the last byte in
-			 * the first read operation, otherwise the first read cost
-			 * one extra clock cycle.
-			 */
-			temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
-			temp |= I2CR_MTX;
-			imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
+
+			return IMX_I2C_STATE_DONE;
 		}
+		/*
+		 * For i2c master receiver repeat restart operation like:
+		 * read -> repeat MSTA -> read/write
+		 * The controller must set MTX before read the last byte in
+		 * the first read operation, otherwise the first read cost
+		 * one extra clock cycle.
+		 */
+		temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
+		temp |= I2CR_MTX;
+		imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
+		next_state = IMX_I2C_STATE_DONE;
 	} else if (i2c_imx->msg_buf_idx == (i2c_imx->msg->len - 2)) {
 		temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
 		temp |= I2CR_TXAK;
@@ -1052,6 +1055,7 @@ static inline void i2c_imx_isr_read_continue(struct imx_i2c_struct *i2c_imx)
 	}
 
 	i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2DR);
+	return next_state;
 }
 
 static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_imx)
@@ -1088,11 +1092,9 @@ static irqreturn_t i2c_imx_master_isr(struct imx_i2c_struct *i2c_imx, unsigned i
 		break;
 
 	case IMX_I2C_STATE_READ_CONTINUE:
-		i2c_imx_isr_read_continue(i2c_imx);
-		if (i2c_imx->msg_buf_idx == i2c_imx->msg->len) {
-			i2c_imx->state = IMX_I2C_STATE_DONE;
+		i2c_imx->state = i2c_imx_isr_read_continue(i2c_imx);
+		if (i2c_imx->state == IMX_I2C_STATE_DONE)
 			wake_up(&i2c_imx->queue);
-		}
 		break;
 
 	case IMX_I2C_STATE_READ_BLOCK_DATA:
@@ -1490,6 +1492,7 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs,
 			bool is_lastmsg)
 {
 	int block_data = msgs->flags & I2C_M_RECV_LEN;
+	int ret = 0;
 
 	dev_dbg(&i2c_imx->adapter.dev,
 		"<%s> write slave address: addr=0x%x\n",
@@ -1522,10 +1525,20 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs,
 		dev_err(&i2c_imx->adapter.dev, "<%s> read timedout\n", __func__);
 		return -ETIMEDOUT;
 	}
-	if (i2c_imx->is_lastmsg && !i2c_imx->stopped)
-		return i2c_imx_bus_busy(i2c_imx, 0, false);
+	if (i2c_imx->is_lastmsg) {
+		if (!i2c_imx->stopped)
+			ret = i2c_imx_bus_busy(i2c_imx, 0, false);
+		/*
+		 * Only read the last byte of the last message after the bus is
+		 * not busy. Else the controller generates another clock which
+		 * might confuse devices.
+		 */
+		if (!ret)
+			i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = imx_i2c_read_reg(i2c_imx,
+										     IMX_I2C_I2DR);
+	}
 
-	return 0;
+	return ret;
 }
 
 static int i2c_imx_xfer_common(struct i2c_adapter *adapter,
-- 
cgit v1.2.3


From e2f1ada8e089dd5a331bcd8b88125ae2af8d188f Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Fri, 20 Mar 2026 16:12:22 -0400
Subject: i2c: designware: amdisp: Fix resume-probe race condition issue

Identified resume-probe race condition in kernel v7.0 with the commit
38fa29b01a6a ("i2c: designware: Combine the init functions"),but this
issue existed from the beginning though not detected.

The amdisp i2c device requires ISP to be in power-on state for probe
to succeed. To meet this requirement, this device is added to genpd
to control ISP power using runtime PM. The pm_runtime_get_sync() called
before i2c_dw_probe() triggers PM resume, which powers on ISP and also
invokes the amdisp i2c runtime resume before the probe completes resulting
in this race condition and a NULL dereferencing issue in v7.0

Fix this race condition by using the genpd APIs directly during probe:
  - Call dev_pm_genpd_resume() to Power ON ISP before probe
  - Call dev_pm_genpd_suspend() to Power OFF ISP after probe
  - Set the device to suspended state with pm_runtime_set_suspended()
  - Enable runtime PM only after the device is fully initialized

Fixes: d6263c468a761 ("i2c: amd-isp: Add ISP i2c-designware driver")
Co-developed-by: Bin Du <bin.du@amd.com>
Signed-off-by: Bin Du <bin.du@amd.com>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Cc: <stable@vger.kernel.org> # v6.16+
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260320201302.3490570-1-pratap.nirujogi@amd.com
---
 drivers/i2c/busses/i2c-designware-amdisp.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/i2c/busses/i2c-designware-amdisp.c b/drivers/i2c/busses/i2c-designware-amdisp.c
index c48728ad9f6f..9f0ec0fae6f2 100644
--- a/drivers/i2c/busses/i2c-designware-amdisp.c
+++ b/drivers/i2c/busses/i2c-designware-amdisp.c
@@ -7,6 +7,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/soc/amd/isp4_misc.h>
 
@@ -76,22 +77,20 @@ static int amd_isp_dw_i2c_plat_probe(struct platform_device *pdev)
 
 	device_enable_async_suspend(&pdev->dev);
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
-
+	dev_pm_genpd_resume(&pdev->dev);
 	ret = i2c_dw_probe(isp_i2c_dev);
 	if (ret) {
 		dev_err_probe(&pdev->dev, ret, "i2c_dw_probe failed\n");
 		goto error_release_rpm;
 	}
-
-	pm_runtime_put_sync(&pdev->dev);
+	dev_pm_genpd_suspend(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 
 	return 0;
 
 error_release_rpm:
 	amd_isp_dw_i2c_plat_pm_cleanup(isp_i2c_dev);
-	pm_runtime_put_sync(&pdev->dev);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 743677a8cb30b09f16a7f167f497c2c927891b5a Mon Sep 17 00:00:00 2001
From: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Date: Wed, 4 Mar 2026 09:25:22 +0100
Subject: HID: amd_sfh: don't log error when device discovery fails with
 -EOPNOTSUPP

When sensor discovery fails on systems without AMD SFH sensors, the
code already emits a warning via dev_warn() in amd_sfh_hid_client_init().
The subsequent dev_err() in sfh_init_work() for the same -EOPNOTSUPP
return value is redundant and causes unnecessary alarm.

Suppress the dev_err() for -EOPNOTSUPP to avoid confusing users who
have no AMD SFH sensors.

Fixes: 2105e8e00da4 ("HID: amd_sfh: Improve boot time when SFH is available")
Reported-by: Casey Croy <ccroy@bugzilla.kernel.org>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221099
Signed-off-by: Maximilian Pezzullo <maximilianpezzullo@gmail.com>
Acked-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 1d9f955573aa..4b81cebdc335 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -413,7 +413,8 @@ static void sfh_init_work(struct work_struct *work)
 	rc = amd_sfh_hid_client_init(mp2);
 	if (rc) {
 		amd_sfh_clear_intr(mp2);
-		dev_err(&pdev->dev, "amd_sfh_hid_client_init failed err %d\n", rc);
+		if (rc != -EOPNOTSUPP)
+			dev_err(&pdev->dev, "amd_sfh_hid_client_init failed err %d\n", rc);
 		return;
 	}
 
-- 
cgit v1.2.3


From 1a2d30aa73140e008e62dc5898e4c2c3b59b35e4 Mon Sep 17 00:00:00 2001
From: Lode Willems <me@lodewillems.com>
Date: Tue, 24 Mar 2026 21:43:06 +0100
Subject: HID: Kysona: Add support for VXE Dragonfly R1 Pro

Apparently this same protocol is used by more mice from different brands.

This patch adds support for the VXE Dragonfly R1 Pro.

Tested-by: Dominykas Svetikas <dominykas@svetikas.lt>
Signed-off-by: Lode Willems <me@lodewillems.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h    | 4 ++++
 drivers/hid/hid-kysona.c | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index e432cc0df680..c1e4a6ce9631 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -1474,6 +1474,10 @@
 #define USB_VENDOR_ID_VTL		0x0306
 #define USB_DEVICE_ID_VTL_MULTITOUCH_FF3F	0xff3f
 
+#define USB_VENDOR_ID_VXE		0x3554
+#define USB_DEVICE_ID_VXE_DRAGONFLY_R1_PRO_DONGLE	0xf58a
+#define USB_DEVICE_ID_VXE_DRAGONFLY_R1_PRO_WIRED	0xf58c
+
 #define USB_VENDOR_ID_WACOM		0x056a
 #define USB_DEVICE_ID_WACOM_GRAPHIRE_BLUETOOTH	0x81
 #define USB_DEVICE_ID_WACOM_INTUOS4_BLUETOOTH   0x00BD
diff --git a/drivers/hid/hid-kysona.c b/drivers/hid/hid-kysona.c
index 09bfe30d02cb..ccbd8380064e 100644
--- a/drivers/hid/hid-kysona.c
+++ b/drivers/hid/hid-kysona.c
@@ -272,6 +272,8 @@ static void kysona_remove(struct hid_device *hdev)
 static const struct hid_device_id kysona_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYSONA, USB_DEVICE_ID_KYSONA_M600_DONGLE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYSONA, USB_DEVICE_ID_KYSONA_M600_WIRED) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_VXE, USB_DEVICE_ID_VXE_DRAGONFLY_R1_PRO_DONGLE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_VXE, USB_DEVICE_ID_VXE_DRAGONFLY_R1_PRO_WIRED) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, kysona_devices);
-- 
cgit v1.2.3


From 73ff3916d803f7ca3a4325af649e46ff89d6c3a7 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Fri, 27 Mar 2026 18:12:15 +0800
Subject: ALSA: hda/realtek: change quirk for HP OmniBook 7 Laptop 16-bh0xxx

HP OmniBook 7 Laptop 16-bh0xxx has the same PCI subsystem ID 0x103c8e60,
and the ALC245 on it needs this quirk to control the mute LED.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221214
Cc: <stable@vger.kernel.org>
Tested-by: Artem S. Tashkinov <aros@gmx.com>
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260327101215.481108-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index b6a58852752a..6787e54fcfe6 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -4122,6 +4122,7 @@ enum {
 	ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY,
 	ALC245_FIXUP_BASS_HP_DAC,
 	ALC245_FIXUP_ACER_MICMUTE_LED,
+	ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -6651,6 +6652,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.v.func = alc285_fixup_hp_coef_micmute_led,
 		.chained = true,
 		.chain_id = ALC2XX_FIXUP_HEADSET_MIC,
+	},
+	[ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc245_fixup_hp_mute_led_coefbit,
+		.chained = true,
+		.chain_id = ALC287_FIXUP_CS35L41_I2C_2,
 	}
 };
 
@@ -7177,7 +7184,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2),
-	SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8e60, "HP OmniBook 7 Laptop 16-bh0xxx", ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e8a, "HP NexusX", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED),
-- 
cgit v1.2.3


From fffca572f9ca51607f180a37d0c898404c8f9112 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 26 Mar 2026 15:06:31 +0100
Subject: mpage: Provide variant of mpage_writepages() with own optional folio
 handler

Some filesystems need to treat some folios specially (for example for
inodes with inline data). Doing the handling in their .writepages method
in a race-free manner results in duplicating some of the writeback
internals. So provide generalized version of mpage_writepages() that
allows filesystem to provide a handler called for each folio which can
handle the folio in a special way.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260326140635.15895-3-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/mpage.c            | 30 ++++++++++++++++++++++++------
 include/linux/mpage.h | 11 +++++++++--
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/fs/mpage.c b/fs/mpage.c
index 7dae5afc2b9e..b3d9f231a04a 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -646,17 +646,24 @@ out:
 }
 
 /**
- * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
+ * __mpage_writepages - walk the list of dirty pages of the given address space
+ * 			& writepage() all of them
  * @mapping: address space structure to write
  * @wbc: subtract the number of written pages from *@wbc->nr_to_write
  * @get_block: the filesystem's block mapper function.
+ * @write_folio: handler to call for each folio before calling
+ *		 mpage_write_folio()
  *
  * This is a library function, which implements the writepages()
- * address_space_operation.
+ * address_space_operation. It calls @write_folio handler for each folio. If
+ * the handler returns value > 0, it calls mpage_write_folio() to do the
+ * folio writeback.
  */
 int
-mpage_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, get_block_t get_block)
+__mpage_writepages(struct address_space *mapping,
+		   struct writeback_control *wbc, get_block_t get_block,
+		   int (*write_folio)(struct folio *folio,
+				      struct writeback_control *wbc))
 {
 	struct mpage_data mpd = {
 		.get_block	= get_block,
@@ -666,11 +673,22 @@ mpage_writepages(struct address_space *mapping,
 	int error;
 
 	blk_start_plug(&plug);
-	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
+	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
+		if (write_folio) {
+			error = write_folio(folio, wbc);
+			/*
+			 * == 0 means folio is handled, < 0 means error. In
+			 * both cases hand back control to writeback_iter()
+			 */
+			if (error <= 0)
+				continue;
+			/* Let mpage_write_folio() handle the folio. */
+		}
 		error = mpage_write_folio(wbc, folio, &mpd);
+	}
 	if (mpd.bio)
 		mpage_bio_submit_write(mpd.bio);
 	blk_finish_plug(&plug);
 	return error;
 }
-EXPORT_SYMBOL(mpage_writepages);
+EXPORT_SYMBOL(__mpage_writepages);
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 1bdc39daac0a..358946990bfa 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -17,7 +17,14 @@ struct readahead_control;
 
 void mpage_readahead(struct readahead_control *, get_block_t get_block);
 int mpage_read_folio(struct folio *folio, get_block_t get_block);
-int mpage_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, get_block_t get_block);
+int __mpage_writepages(struct address_space *mapping,
+		struct writeback_control *wbc, get_block_t get_block,
+		int (*write_folio)(struct folio *folio,
+				   struct writeback_control *wbc));
+static inline int mpage_writepages(struct address_space *mapping,
+		struct writeback_control *wbc, get_block_t get_block)
+{
+	return __mpage_writepages(mapping, wbc, get_block, NULL);
+}
 
 #endif
-- 
cgit v1.2.3


From 102e57d56f81fa5c5ed78f576101d1bf1b3e6fe2 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 26 Mar 2026 15:06:32 +0100
Subject: udf: Fix race between file type conversion and writeback

udf_setsize() can race with udf_writepages() as follows:

udf_setsize()			udf_writepages()
				  if (iinfo->i_alloc_type ==
						ICBTAG_FLAG_AD_IN_ICB)
  err = udf_expand_file_adinicb(inode);
  err = udf_extend_file(inode, newsize);
				    udf_adinicb_writepages()
				      memcpy_from_file_folio() - crash
					because inode size is too big.

Fix the problem by checking the file type under folio lock in
udf_handle_page_wb() handler called from __mpage_writepages() which
properly serializes with udf_expand_file_adinicb().

Reported-by: Jianzhou Zhao <luckd0g@163.com>
Link: https://lore.kernel.org/all/f622c01.67ac.19cdbdd777d.Coremail.luckd0g@163.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260326140635.15895-4-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/udf/inode.c | 33 +++++++++++++++------------------
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 7fae8002344a..23e894092dab 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -181,22 +181,23 @@ static void udf_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int udf_adinicb_writepages(struct address_space *mapping,
-		      struct writeback_control *wbc)
+static int udf_handle_page_wb(struct folio *folio,
+			      struct writeback_control *wbc)
 {
-	struct inode *inode = mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct udf_inode_info *iinfo = UDF_I(inode);
-	struct folio *folio = NULL;
-	int error = 0;
 
-	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
-		BUG_ON(!folio_test_locked(folio));
-		BUG_ON(folio->index != 0);
-		memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio,
-				0, i_size_read(inode));
-		folio_unlock(folio);
-	}
+	/*
+	 * Inodes in the normal format are handled by the generic code. This
+	 * check is race-free as the folio lock protects us from inode type
+	 * conversion.
+	 */
+	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB)
+		return 1;
 
+	memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio,
+				0, i_size_read(inode));
+	folio_unlock(folio);
 	mark_inode_dirty(inode);
 	return 0;
 }
@@ -204,12 +205,8 @@ static int udf_adinicb_writepages(struct address_space *mapping,
 static int udf_writepages(struct address_space *mapping,
 			  struct writeback_control *wbc)
 {
-	struct inode *inode = mapping->host;
-	struct udf_inode_info *iinfo = UDF_I(inode);
-
-	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB)
-		return udf_adinicb_writepages(mapping, wbc);
-	return mpage_writepages(mapping, wbc, udf_get_block_wb);
+	return __mpage_writepages(mapping, wbc, udf_get_block_wb,
+				  udf_handle_page_wb);
 }
 
 static void udf_adinicb_read_folio(struct folio *folio)
-- 
cgit v1.2.3


From 1f9885732248d22f788e4992c739a98c88ab8a55 Mon Sep 17 00:00:00 2001
From: Luo Haiyang <luo.haiyang@zte.com.cn>
Date: Thu, 26 Mar 2026 14:19:53 +0800
Subject: tracing: Fix potential deadlock in cpu hotplug with osnoise

The following sequence may leads deadlock in cpu hotplug:

    task1        task2        task3
    -----        -----        -----

 mutex_lock(&interface_lock)

            [CPU GOING OFFLINE]

            cpus_write_lock();
            osnoise_cpu_die();
              kthread_stop(task3);
                wait_for_completion();

                      osnoise_sleep();
                        mutex_lock(&interface_lock);

 cpus_read_lock();

 [DEAD LOCK]

Fix by swap the order of cpus_read_lock() and mutex_lock(&interface_lock).

Cc: stable@vger.kernel.org
Cc: <mathieu.desnoyers@efficios.com>
Cc: <zhang.run@zte.com.cn>
Cc: <yang.tao172@zte.com.cn>
Cc: <ran.xiaokai@zte.com.cn>
Fixes: bce29ac9ce0bb ("trace: Add osnoise tracer")
Link: https://patch.msgid.link/20260326141953414bVSj33dAYktqp9Oiyizq8@zte.com.cn
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Luo Haiyang <luo.haiyang@zte.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index dee610e465b9..be6cf0bb3c03 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2073,8 +2073,8 @@ static void osnoise_hotplug_workfn(struct work_struct *dummy)
 	if (!osnoise_has_registered_instances())
 		return;
 
-	guard(mutex)(&interface_lock);
 	guard(cpus_read_lock)();
+	guard(mutex)(&interface_lock);
 
 	if (!cpu_online(cpu))
 		return;
@@ -2237,11 +2237,11 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf,
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * avoid CPU hotplug operations that might read options.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	retval = cnt;
 
@@ -2257,8 +2257,8 @@ static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf,
 			clear_bit(option, &osnoise_options);
 	}
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();
@@ -2345,16 +2345,16 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	if (running)
 		stop_per_cpu_kthreads();
 
-	mutex_lock(&interface_lock);
 	/*
 	 * osnoise_cpumask is read by CPU hotplug operations.
 	 */
 	cpus_read_lock();
+	mutex_lock(&interface_lock);
 
 	cpumask_copy(&osnoise_cpumask, osnoise_cpumask_new);
 
-	cpus_read_unlock();
 	mutex_unlock(&interface_lock);
+	cpus_read_unlock();
 
 	if (running)
 		start_per_cpu_kthreads();
-- 
cgit v1.2.3


From e5046823f8fa3677341b541a25af2fcb99a5b1e0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Wed, 25 Mar 2026 20:29:20 -0700
Subject: lib/crypto: chacha: Zeroize permuted_state before it leaves scope

Since the ChaCha permutation is invertible, the local variable
'permuted_state' is sufficient to compute the original 'state', and thus
the key, even after the permutation has been done.

While the kernel is quite inconsistent about zeroizing secrets on the
stack (and some prominent userspace crypto libraries don't bother at all
since it's not guaranteed to work anyway), the kernel does try to do it
as a best practice, especially in cases involving the RNG.

Thus, explicitly zeroize 'permuted_state' before it goes out of scope.

Fixes: c08d0e647305 ("crypto: chacha20 - Add a generic ChaCha20 stream cipher implementation")
Cc: stable@vger.kernel.org
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20260326032920.39408-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/chacha-block-generic.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lib/crypto/chacha-block-generic.c b/lib/crypto/chacha-block-generic.c
index 77f68de71066..4a6d627580cb 100644
--- a/lib/crypto/chacha-block-generic.c
+++ b/lib/crypto/chacha-block-generic.c
@@ -87,6 +87,8 @@ void chacha_block_generic(struct chacha_state *state,
 				   &out[i * sizeof(u32)]);
 
 	state->x[12]++;
+
+	chacha_zeroize_state(&permuted_state);
 }
 EXPORT_SYMBOL(chacha_block_generic);
 
@@ -110,5 +112,7 @@ void hchacha_block_generic(const struct chacha_state *state,
 
 	memcpy(&out[0], &permuted_state.x[0], 16);
 	memcpy(&out[4], &permuted_state.x[12], 16);
+
+	chacha_zeroize_state(&permuted_state);
 }
 EXPORT_SYMBOL(hchacha_block_generic);
-- 
cgit v1.2.3


From aad885e774966e97b675dfe928da164214a71605 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 5 Mar 2026 17:28:04 -0800
Subject: KVM: x86/mmu: Drop/zap existing present SPTE even when creating an
 MMIO SPTE

When installing an emulated MMIO SPTE, do so *after* dropping/zapping the
existing SPTE (if it's shadow-present).  While commit a54aa15c6bda3 was
right about it being impossible to convert a shadow-present SPTE to an
MMIO SPTE due to a _guest_ write, it failed to account for writes to guest
memory that are outside the scope of KVM.

E.g. if host userspace modifies a shadowed gPTE to switch from a memslot
to emulted MMIO and then the guest hits a relevant page fault, KVM will
install the MMIO SPTE without first zapping the shadow-present SPTE.

  ------------[ cut here ]------------
  is_shadow_present_pte(*sptep)
  WARNING: arch/x86/kvm/mmu/mmu.c:484 at mark_mmio_spte+0xb2/0xc0 [kvm], CPU#0: vmx_ept_stale_r/4292
  Modules linked in: kvm_intel kvm irqbypass
  CPU: 0 UID: 1000 PID: 4292 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:mark_mmio_spte+0xb2/0xc0 [kvm]
  Call Trace:
   <TASK>
   mmu_set_spte+0x237/0x440 [kvm]
   ept_page_fault+0x535/0x7f0 [kvm]
   kvm_mmu_do_page_fault+0xee/0x1f0 [kvm]
   kvm_mmu_page_fault+0x8d/0x620 [kvm]
   vmx_handle_exit+0x18c/0x5a0 [kvm_intel]
   kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm]
   kvm_vcpu_ioctl+0x2d5/0x980 [kvm]
   __x64_sys_ioctl+0x8a/0xd0
   do_syscall_64+0xb5/0x730
   entry_SYSCALL_64_after_hwframe+0x4b/0x53
  RIP: 0033:0x47fa3f
   </TASK>
  ---[ end trace 0000000000000000 ]---

Reported-by: Alexander Bulekov <bkov@amazon.com>
Debugged-by: Alexander Bulekov <bkov@amazon.com>
Suggested-by: Fred Griffoul <fgriffo@amazon.co.uk>
Fixes: a54aa15c6bda3 ("KVM: x86/mmu: Handle MMIO SPTEs directly in mmu_set_spte()")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b922a8b00057..98406d6aa2d6 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3044,12 +3044,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	bool prefetch = !fault || fault->prefetch;
 	bool write_fault = fault && fault->write;
 
-	if (unlikely(is_noslot_pfn(pfn))) {
-		vcpu->stat.pf_mmio_spte_created++;
-		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
-		return RET_PF_EMULATE;
-	}
-
 	if (is_shadow_present_pte(*sptep)) {
 		if (prefetch && is_last_spte(*sptep, level) &&
 		    pfn == spte_to_pfn(*sptep))
@@ -3073,6 +3067,14 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			was_rmapped = 1;
 	}
 
+	if (unlikely(is_noslot_pfn(pfn))) {
+		vcpu->stat.pf_mmio_spte_created++;
+		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
+		if (flush)
+			kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
+		return RET_PF_EMULATE;
+	}
+
 	wrprot = make_spte(vcpu, sp, slot, pte_access, gfn, pfn, *sptep, prefetch,
 			   false, host_writable, &spte);
 
-- 
cgit v1.2.3


From df83746075778958954aa0460cca55f4b3fc9c02 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 5 Mar 2026 17:42:14 -0800
Subject: KVM: x86/mmu: Only WARN in direct MMUs when overwriting
 shadow-present SPTE

Adjust KVM's sanity check against overwriting a shadow-present SPTE with a
another SPTE with a different target PFN to only apply to direct MMUs,
i.e. only to MMUs without shadowed gPTEs.  While it's impossible for KVM
to overwrite a shadow-present SPTE in response to a guest write, writes
from outside the scope of KVM, e.g. from host userspace, aren't detected
by KVM's write tracking and so can break KVM's shadow paging rules.

  ------------[ cut here ]------------
  pfn != spte_to_pfn(*sptep)
  WARNING: arch/x86/kvm/mmu/mmu.c:3069 at mmu_set_spte+0x1e4/0x440 [kvm], CPU#0: vmx_ept_stale_r/872
  Modules linked in: kvm_intel kvm irqbypass
  CPU: 0 UID: 1000 PID: 872 Comm: vmx_ept_stale_r Not tainted 7.0.0-rc2-eafebd2d2ab0-sink-vm #319 PREEMPT
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015
  RIP: 0010:mmu_set_spte+0x1e4/0x440 [kvm]
  Call Trace:
   <TASK>
   ept_page_fault+0x535/0x7f0 [kvm]
   kvm_mmu_do_page_fault+0xee/0x1f0 [kvm]
   kvm_mmu_page_fault+0x8d/0x620 [kvm]
   vmx_handle_exit+0x18c/0x5a0 [kvm_intel]
   kvm_arch_vcpu_ioctl_run+0xc55/0x1c20 [kvm]
   kvm_vcpu_ioctl+0x2d5/0x980 [kvm]
   __x64_sys_ioctl+0x8a/0xd0
   do_syscall_64+0xb5/0x730
   entry_SYSCALL_64_after_hwframe+0x4b/0x53
   </TASK>
  ---[ end trace 0000000000000000 ]---

Fixes: 11d45175111d ("KVM: x86/mmu: Warn if PFN changes on shadow-present SPTE in shadow MMU")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 98406d6aa2d6..dd06453d5b72 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3060,7 +3060,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			child = spte_to_child_sp(pte);
 			drop_parent_pte(vcpu->kvm, child, sptep);
 			flush = true;
-		} else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) {
+		} else if (pfn != spte_to_pfn(*sptep)) {
+			WARN_ON_ONCE(vcpu->arch.mmu->root_role.direct);
 			drop_spte(vcpu->kvm, sptep);
 			flush = true;
 		} else
-- 
cgit v1.2.3


From c5c0a268b38adffbb2e70e6957017537ff54c157 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 26 Mar 2026 14:38:44 +0100
Subject: s390/barrier: Make array_index_mask_nospec() __always_inline

Mark array_index_mask_nospec() as __always_inline to guarantee the
mitigation is emitted inline regardless of compiler inlining decisions.

Fixes: e2dd833389cc ("s390: add optimized array_index_mask_nospec")
Cc: stable@kernel.org
Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/barrier.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index f3184073e754..dad02f5b3c8d 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -62,8 +62,8 @@ do {									\
  * @size: number of elements in array
  */
 #define array_index_mask_nospec array_index_mask_nospec
-static inline unsigned long array_index_mask_nospec(unsigned long index,
-						    unsigned long size)
+static __always_inline unsigned long array_index_mask_nospec(unsigned long index,
+							     unsigned long size)
 {
 	unsigned long mask;
 
-- 
cgit v1.2.3


From 48b8814e25d073dd84daf990a879a820bad2bcbd Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 24 Mar 2026 17:34:05 +0100
Subject: s390/syscalls: Add spectre boundary for syscall dispatch table

The s390 syscall number is directly controlled by userspace, but does
not have an array_index_nospec() boundary to prevent access past the
syscall function pointer tables.

Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Fixes: 56e62a737028 ("s390: convert to generic entry")
Cc: stable@kernel.org
Assisted-by: gkh_clanker_2000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/2026032404-sterling-swoosh-43e6@gregkh
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/syscall.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c
index 795b6cca74c9..d103c853e120 100644
--- a/arch/s390/kernel/syscall.c
+++ b/arch/s390/kernel/syscall.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/cpufeature.h>
+#include <linux/nospec.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
@@ -131,8 +132,10 @@ void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
 	if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
 		goto out;
 	regs->gprs[2] = -ENOSYS;
-	if (likely(nr < NR_syscalls))
+	if (likely(nr < NR_syscalls)) {
+		nr = array_index_nospec(nr, NR_syscalls);
 		regs->gprs[2] = sys_call_table[nr](regs);
+	}
 out:
 	syscall_exit_to_user_mode(regs);
 }
-- 
cgit v1.2.3


From 0738d395aab8fae3b5a3ad3fc640630c91693c27 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 26 Mar 2026 19:50:14 +0100
Subject: s390/entry: Scrub r12 register on kernel entry

Before commit f33f2d4c7c80 ("s390/bp: remove TIF_ISOLATE_BP"),
all entry handlers loaded r12 with the current task pointer
(lg %r12,__LC_CURRENT) for use by the BPENTER/BPEXIT macros. That
commit removed TIF_ISOLATE_BP, dropping both the branch prediction
macros and the r12 load, but did not add r12 to the register clearing
sequence.

Add the missing xgr %r12,%r12 to make the register scrub consistent
across all entry points.

Fixes: f33f2d4c7c80 ("s390/bp: remove TIF_ISOLATE_BP")
Cc: stable@kernel.org
Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/entry.S | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 4873fe9d891b..689d253e1afc 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -271,6 +271,7 @@ SYM_CODE_START(system_call)
 	xgr	%r9,%r9
 	xgr	%r10,%r10
 	xgr	%r11,%r11
+	xgr	%r12,%r12
 	la	%r2,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 	mvc	__PT_R8(64,%r2),__LC_SAVE_AREA(%r13)
 	MBEAR	%r2,%r13
@@ -407,6 +408,7 @@ SYM_CODE_START(\name)
 	xgr	%r6,%r6
 	xgr	%r7,%r7
 	xgr	%r10,%r10
+	xgr	%r12,%r12
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA(%r13)
 	MBEAR	%r11,%r13
@@ -496,6 +498,7 @@ SYM_CODE_START(mcck_int_handler)
 	xgr	%r6,%r6
 	xgr	%r7,%r7
 	xgr	%r10,%r10
+	xgr	%r12,%r12
 	stmg	%r8,%r9,__PT_PSW(%r11)
 	xc	__PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-- 
cgit v1.2.3


From 82c4f23d2757c2fc6751a5805c1feecdd4c430fb Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 19 Feb 2026 10:22:18 -0500
Subject: Update MAINTAINERS file to add reviewers for ext4

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
---
 MAINTAINERS | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 96ea84948d76..bf2a5ef7aaeb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9611,7 +9611,12 @@ F:	include/linux/ext2*
 
 EXT4 FILE SYSTEM
 M:	"Theodore Ts'o" <tytso@mit.edu>
-M:	Andreas Dilger <adilger.kernel@dilger.ca>
+R:	Andreas Dilger <adilger.kernel@dilger.ca>
+R:	Baokun Li <libaokun@linux.alibaba.com>
+R:	Jan Kara <jack@suse.cz>
+R:	Ojaswin Mujoo <ojaswin@linux.ibm.com>
+R:	Ritesh Harjani (IBM) <ritesh.list@gmail.com>
+R:	Zhang Yi <yi.zhang@huawei.com>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 W:	http://ext4.wiki.kernel.org
-- 
cgit v1.2.3


From 84e21e3fb8fd99ea460eb7274584750d11cf3e9f Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Sat, 31 Jan 2026 17:11:56 +0800
Subject: ext4: do not check fast symlink during orphan recovery

Commit '5f920d5d6083 ("ext4: verify fast symlink length")' causes the
generic/475 test to fail during orphan cleanup of zero-length symlinks.

  generic/475  84s ... _check_generic_filesystem: filesystem on /dev/vde is inconsistent

The fsck reports are provided below:

  Deleted inode 9686 has zero dtime.
  Deleted inode 158230 has zero dtime.
  ...
  Inode bitmap differences:  -9686 -158230
  Orphan file (inode 12) block 13 is not clean.
  Failed to initialize orphan file.

In ext4_symlink(), a newly created symlink can be added to the orphan
list due to ENOSPC. Its data has not been initialized, and its size is
zero. Therefore, we need to disregard the length check of the symbolic
link when cleaning up orphan inodes. Instead, we should ensure that the
nlink count is zero.

Fixes: 5f920d5d6083 ("ext4: verify fast symlink length")
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260131091156.1733648-1-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/inode.c | 40 +++++++++++++++++++++++++++++-----------
 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 396dc3a5d16b..af6d1759c8de 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5401,18 +5401,36 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 			inode->i_op = &ext4_encrypted_symlink_inode_operations;
 		} else if (ext4_inode_is_fast_symlink(inode)) {
 			inode->i_op = &ext4_fast_symlink_inode_operations;
-			if (inode->i_size == 0 ||
-			    inode->i_size >= sizeof(ei->i_data) ||
-			    strnlen((char *)ei->i_data, inode->i_size + 1) !=
-								inode->i_size) {
-				ext4_error_inode(inode, function, line, 0,
-					"invalid fast symlink length %llu",
-					 (unsigned long long)inode->i_size);
-				ret = -EFSCORRUPTED;
-				goto bad_inode;
+
+			/*
+			 * Orphan cleanup can see inodes with i_size == 0
+			 * and i_data uninitialized. Skip size checks in
+			 * that case. This is safe because the first thing
+			 * ext4_evict_inode() does for fast symlinks is
+			 * clearing of i_data and i_size.
+			 */
+			if ((EXT4_SB(sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+				if (inode->i_nlink != 0) {
+					ext4_error_inode(inode, function, line, 0,
+						"invalid orphan symlink nlink %d",
+						inode->i_nlink);
+					ret = -EFSCORRUPTED;
+					goto bad_inode;
+				}
+			} else {
+				if (inode->i_size == 0 ||
+				    inode->i_size >= sizeof(ei->i_data) ||
+				    strnlen((char *)ei->i_data, inode->i_size + 1) !=
+						inode->i_size) {
+					ext4_error_inode(inode, function, line, 0,
+						"invalid fast symlink length %llu",
+						(unsigned long long)inode->i_size);
+					ret = -EFSCORRUPTED;
+					goto bad_inode;
+				}
+				inode_set_cached_link(inode, (char *)ei->i_data,
+						      inode->i_size);
 			}
-			inode_set_cached_link(inode, (char *)ei->i_data,
-					      inode->i_size);
 		} else {
 			inode->i_op = &ext4_symlink_inode_operations;
 		}
-- 
cgit v1.2.3


From 86ab3e55673a7a49a841838776f1ab18d23a67b5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Mar 2026 20:26:08 +0000
Subject: ipv6: icmp: clear skb2->cb[] in ip6_err_gen_icmpv6_unreach()

Sashiko AI-review observed:

  In ip6_err_gen_icmpv6_unreach(), the skb is an outer IPv4 ICMP error packet
  where its cb contains an IPv4 inet_skb_parm. When skb is cloned into skb2
  and passed to icmp6_send(), it uses IP6CB(skb2).

  IP6CB interprets the IPv4 inet_skb_parm as an inet6_skb_parm. The cipso
  offset in inet_skb_parm.opt directly overlaps with dsthao in inet6_skb_parm
  at offset 18.

  If an attacker sends a forged ICMPv4 error with a CIPSO IP option, dsthao
  would be a non-zero offset. Inside icmp6_send(), mip6_addr_swap() is called
  and uses ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO).

  This would scan the inner, attacker-controlled IPv6 packet starting at that
  offset, potentially returning a fake TLV without checking if the remaining
  packet length can hold the full 18-byte struct ipv6_destopt_hao.

  Could mip6_addr_swap() then perform a 16-byte swap that extends past the end
  of the packet data into skb_shared_info?

  Should the cb array also be cleared in ip6_err_gen_icmpv6_unreach() and
  ip6ip6_err() to prevent this?

This patch implements the first suggestion.

I am not sure if ip6ip6_err() needs to be changed.
A separate patch would be better anyway.

Fixes: ca15a078bd90 ("sit: generate icmpv6 error when receiving icmpv4 error")
Reported-by: Ido Schimmel <idosch@nvidia.com>
Closes: https://sashiko.dev/#/patchset/20260326155138.2429480-1-edumazet%40google.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Oskar Kjos <oskar.kjos@hotmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260326202608.2976021-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/icmp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 813d2e9edb8b..d5d23a9296ea 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -875,6 +875,9 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
 	if (!skb2)
 		return 1;
 
+	/* Remove debris left by IPv4 stack. */
+	memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2)));
+
 	skb_dst_drop(skb2);
 	skb_pull(skb2, nhs);
 	skb_reset_network_header(skb2);
-- 
cgit v1.2.3


From 2edfa31769a4add828a7e604b21cb82aaaa05925 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Mar 2026 15:51:38 +0000
Subject: ip6_tunnel: clear skb2->cb[] in ip4ip6_err()

Oskar Kjos reported the following problem.

ip4ip6_err() calls icmp_send() on a cloned skb whose cb[] was written
by the IPv6 receive path as struct inet6_skb_parm. icmp_send() passes
IPCB(skb2) to __ip_options_echo(), which interprets that cb[] region
as struct inet_skb_parm (IPv4). The layouts differ: inet6_skb_parm.nhoff
at offset 14 overlaps inet_skb_parm.opt.rr, producing a non-zero rr
value. __ip_options_echo() then reads optlen from attacker-controlled
packet data at sptr[rr+1] and copies that many bytes into dopt->__data,
a fixed 40-byte stack buffer (IP_OPTIONS_DATA_FIXED_SIZE).

To fix this we clear skb2->cb[], as suggested by Oskar Kjos.

Also add minimal IPv4 header validation (version == 4, ihl >= 5).

Fixes: c4d3efafcc93 ("[IPV6] IP6TUNNEL: Add support to IPv4 over IPv6 tunnel.")
Reported-by: Oskar Kjos <oskar.kjos@hotmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260326155138.2429480-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_tunnel.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 4c29aa94e86e..0b53488a9229 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -601,11 +601,16 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!skb2)
 		return 0;
 
+	/* Remove debris left by IPv6 stack. */
+	memset(IPCB(skb2), 0, sizeof(*IPCB(skb2)));
+
 	skb_dst_drop(skb2);
 
 	skb_pull(skb2, offset);
 	skb_reset_network_header(skb2);
 	eiph = ip_hdr(skb2);
+	if (eiph->version != 4 || eiph->ihl < 5)
+		goto out;
 
 	/* Try to guess incoming interface */
 	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,
-- 
cgit v1.2.3


From f4a2b42e78914ff15630e71289adc589c3a8eb45 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 5 Feb 2026 10:22:24 +0100
Subject: ext4: fix stale xarray tags after writeback

There are cases where ext4_bio_write_page() gets called for a page which
has no buffers to submit. This happens e.g. when the part of the file is
actually a hole, when we cannot allocate blocks due to being called from
jbd2, or in data=journal mode when checkpointing writes the buffers
earlier. In these cases we just return from ext4_bio_write_page()
however if the page didn't need redirtying, we will leave stale DIRTY
and/or TOWRITE tags in xarray because those get cleared only in
__folio_start_writeback(). As a result we can leave these tags set in
mappings even after a final sync on filesystem that's getting remounted
read-only or that's being frozen. Various assertions can then get upset
when writeback is started on such filesystems (Gerald reported assertion
in ext4_journal_check_start() firing).

Fix the problem by cycling the page through writeback state even if we
decide nothing needs to be written for it so that xarray tags get
properly updated. This is slightly silly (we could update the xarray
tags directly) but I don't think a special helper messing with xarray
tags is really worth it in this relatively rare corner case.

Reported-by: Gerald Yang <gerald.yang@canonical.com>
Link: https://lore.kernel.org/all/20260128074515.2028982-1-gerald.yang@canonical.com
Fixes: dff4ac75eeee ("ext4: move keep_towrite handling to ext4_bio_write_page()")
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260205092223.21287-2-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/page-io.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index a8c95eee91b7..39fe50b3c662 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -524,9 +524,15 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
 		nr_to_submit++;
 	} while ((bh = bh->b_this_page) != head);
 
-	/* Nothing to submit? Just unlock the folio... */
-	if (!nr_to_submit)
+	if (!nr_to_submit) {
+		/*
+		 * We have nothing to submit. Just cycle the folio through
+		 * writeback state to properly update xarray tags.
+		 */
+		__folio_start_writeback(folio, keep_towrite);
+		folio_end_writeback(folio);
 		return 0;
+	}
 
 	bh = head = folio_buffers(folio);
 
-- 
cgit v1.2.3


From ed9356a30e59c7cc3198e7fc46cfedf3767b9b17 Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Sat, 7 Feb 2026 10:06:07 +0530
Subject: ext4: convert inline data to extents when truncate exceeds inline
 size

Add a check in ext4_setattr() to convert files from inline data storage
to extent-based storage when truncate() grows the file size beyond the
inline capacity. This prevents the filesystem from entering an
inconsistent state where the inline data flag is set but the file size
exceeds what can be stored inline.

Without this fix, the following sequence causes a kernel BUG_ON():

1. Mount filesystem with inode that has inline flag set and small size
2. truncate(file, 50MB) - grows size but inline flag remains set
3. sendfile() attempts to write data
4. ext4_write_inline_data() hits BUG_ON(write_size > inline_capacity)

The crash occurs because ext4_write_inline_data() expects inline storage
to accommodate the write, but the actual inline capacity (~60 bytes for
i_block + ~96 bytes for xattrs) is far smaller than the file size and
write request.

The fix checks if the new size from setattr exceeds the inode's actual
inline capacity (EXT4_I(inode)->i_inline_size) and converts the file to
extent-based storage before proceeding with the size change.

This addresses the root cause by ensuring the inline data flag and file
size remain consistent during truncate operations.

Reported-by: syzbot+7de5fe447862fc37576f@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7de5fe447862fc37576f
Tested-by: syzbot+7de5fe447862fc37576f@syzkaller.appspotmail.com
Signed-off-by: Deepanshu Kartikey <Kartikey406@gmail.com>
Link: https://patch.msgid.link/20260207043607.1175976-1-kartikey406@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/inode.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index af6d1759c8de..252191632f56 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5867,6 +5867,18 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (attr->ia_size == inode->i_size)
 			inc_ivers = false;
 
+		/*
+		 * If file has inline data but new size exceeds inline capacity,
+		 * convert to extent-based storage first to prevent inconsistent
+		 * state (inline flag set but size exceeds inline capacity).
+		 */
+		if (ext4_has_inline_data(inode) &&
+		    attr->ia_size > EXT4_I(inode)->i_inline_size) {
+			error = ext4_convert_inline_data(inode);
+			if (error)
+				goto err_out;
+		}
+
 		if (shrink) {
 			if (ext4_should_order_data(inode)) {
 				error = ext4_begin_ordered_truncate(inode,
-- 
cgit v1.2.3


From b38c55320bf85a84a4f04803c57b261fc87e9b4b Mon Sep 17 00:00:00 2001
From: Dimitri Daskalakis <daskald@meta.com>
Date: Tue, 24 Mar 2026 12:51:22 -0700
Subject: eth: fbnic: Account for page fragments when updating BDQ tail

FBNIC supports fixed size buffers of 4K. When PAGE_SIZE > 4K, we
fragment the page across multiple descriptors (FBNIC_BD_FRAG_COUNT).
When refilling the BDQ, the correct number of entries are populated,
but tail was only incremented by one. So on a system with 64K pages,
HW would get one descriptor refilled for every 16 we populate.

Additionally, we program the ring size in the HW when enabling the BDQ.
This was not accounting for page fragments, so on systems with 64K pages,
the HW used 1/16th of the ring.

Fixes: 0cb4c0a13723 ("eth: fbnic: Implement Rx queue alloc/start/stop/free")
Signed-off-by: Dimitri Daskalakis <daskald@meta.com>
Link: https://patch.msgid.link/20260324195123.3486219-2-dimitri.daskalakis1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 9fb91d4f3971..9cd85a0d0c3a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -927,7 +927,7 @@ static void fbnic_fill_bdq(struct fbnic_ring *bdq)
 		/* Force DMA writes to flush before writing to tail */
 		dma_wmb();
 
-		writel(i, bdq->doorbell);
+		writel(i * FBNIC_BD_FRAG_COUNT, bdq->doorbell);
 	}
 }
 
@@ -2564,7 +2564,7 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq)
 	hpq->tail = 0;
 	hpq->head = 0;
 
-	log_size = fls(hpq->size_mask);
+	log_size = fls(hpq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT);
 
 	/* Store descriptor ring address and size */
 	fbnic_ring_wr32(hpq, FBNIC_QUEUE_BDQ_HPQ_BAL, lower_32_bits(hpq->dma));
@@ -2576,7 +2576,7 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq)
 	if (!ppq->size_mask)
 		goto write_ctl;
 
-	log_size = fls(ppq->size_mask);
+	log_size = fls(ppq->size_mask) + ilog2(FBNIC_BD_FRAG_COUNT);
 
 	/* Add enabling of PPQ to BDQ control */
 	bdq_ctl |= FBNIC_QUEUE_BDQ_CTL_PPQ_ENABLE;
-- 
cgit v1.2.3


From f3567dd428b264b3f06f881e5e85a738c7c910df Mon Sep 17 00:00:00 2001
From: Dimitri Daskalakis <daskald@meta.com>
Date: Tue, 24 Mar 2026 12:51:23 -0700
Subject: eth: fbnic: Fix debugfs output for BDQ's with page frags

The rings size_mask represents the number of pages, so we need to
determine the number of page frags when dumping the descriptors.

Fixes: df04373b0dab ("eth fbnic: Add debugfs hooks for tx/rx rings")
Signed-off-by: Dimitri Daskalakis <daskald@meta.com>
Link: https://patch.msgid.link/20260324195123.3486219-3-dimitri.daskalakis1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index 08270db2dee8..3c4563c8f403 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -197,7 +197,7 @@ static int fbnic_dbg_bdq_desc_seq_show(struct seq_file *s, void *v)
 		return 0;
 	}
 
-	for (i = 0; i <= ring->size_mask; i++) {
+	for (i = 0; i < (ring->size_mask + 1) * FBNIC_BD_FRAG_COUNT; i++) {
 		u64 bd = le64_to_cpu(ring->desc[i]);
 
 		seq_printf(s, "%04x %#04llx %#014llx\n", i,
-- 
cgit v1.2.3


From b1d682f1990c19fb1d5b97d13266210457092bcd Mon Sep 17 00:00:00 2001
From: Simon Weber <simon.weber.39@gmail.com>
Date: Sat, 7 Feb 2026 10:53:03 +0100
Subject: ext4: fix journal credit check when setting fscrypt context

Fix an issue arising when ext4 features has_journal, ea_inode, and encrypt
are activated simultaneously, leading to ENOSPC when creating an encrypted
file.

Fix by passing XATTR_CREATE flag to xattr_set_handle function if a handle
is specified, i.e., when the function is called in the control flow of
creating a new inode. This aligns the number of jbd2 credits set_handle
checks for with the number allocated for creating a new inode.

ext4_set_context must not be called with a non-null handle (fs_data) if
fscrypt context xattr is not guaranteed to not exist yet. The only other
usage of this function currently is when handling the ioctl
FS_IOC_SET_ENCRYPTION_POLICY, which calls it with fs_data=NULL.

Fixes: c1a5d5f6ab21eb7e ("ext4: improve journal credit handling in set xattr paths")

Co-developed-by: Anthony Durrer <anthonydev@fastmail.com>
Signed-off-by: Anthony Durrer <anthonydev@fastmail.com>
Signed-off-by: Simon Weber <simon.weber.39@gmail.com>
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Link: https://patch.msgid.link/20260207100148.724275-4-simon.weber.39@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/crypto.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index cf0a0970c095..f41f320f4437 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -163,10 +163,17 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 	 */
 
 	if (handle) {
+		/*
+		 * Since the inode is new it is ok to pass the
+		 * XATTR_CREATE flag. This is necessary to match the
+		 * remaining journal credits check in the set_handle
+		 * function with the credits allocated for the new
+		 * inode.
+		 */
 		res = ext4_xattr_set_handle(handle, inode,
 					    EXT4_XATTR_INDEX_ENCRYPTION,
 					    EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
-					    ctx, len, 0);
+					    ctx, len, XATTR_CREATE);
 		if (!res) {
 			ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT);
 			ext4_clear_inode_state(inode,
-- 
cgit v1.2.3


From bd060afa7cc3e0ad30afa9ecc544a78638498555 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 16 Feb 2026 17:48:43 +0100
Subject: ext4: make recently_deleted() properly work with lazy itable
 initialization

recently_deleted() checks whether inode has been used in the near past.
However this can give false positive result when inode table is not
initialized yet and we are in fact comparing to random garbage (or stale
itable block of a filesystem before mkfs). Ultimately this results in
uninitialized inodes being skipped during inode allocation and possibly
they are never initialized and thus e2fsck complains.  Verify if the
inode has been initialized before checking for dtime.

Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://patch.msgid.link/20260216164848.3074-3-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/ialloc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index b20a1bf866ab..b1bc1950c9f0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -686,6 +686,12 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
 	if (unlikely(!gdp))
 		return 0;
 
+	/* Inode was never used in this filesystem? */
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT) ||
+	     ino >= EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp)))
+		return 0;
+
 	bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) +
 		       (ino / inodes_per_block));
 	if (!bh || !buffer_uptodate(bh))
-- 
cgit v1.2.3


From 1308255bbf8452762f89f44f7447ce137ecdbcff Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 16 Feb 2026 17:48:44 +0100
Subject: ext4: fix fsync(2) for nojournal mode

When inode metadata is changed, we sometimes just call
ext4_mark_inode_dirty() to track modified metadata. This copies inode
metadata into block buffer which is enough when we are journalling
metadata. However when we are running in nojournal mode we currently
fail to write the dirtied inode buffer during fsync(2) because the inode
is not marked as dirty. Use explicit ext4_write_inode() call to make
sure the inode table buffer is written to the disk. This is a band aid
solution but proper solution requires a much larger rewrite including
changes in metadata bh tracking infrastructure.

Reported-by: Free Ekanayaka <free.ekanayaka@gmail.com>
Link: https://lore.kernel.org/all/87il8nhxdm.fsf@x1.mail-host-address-is-not-set/
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://patch.msgid.link/20260216164848.3074-4-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/fsync.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index e476c6de3074..bd8f230fa507 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -83,11 +83,23 @@ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
 				int datasync, bool *needs_barrier)
 {
 	struct inode *inode = file->f_inode;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = 0,
+	};
 	int ret;
 
 	ret = generic_buffers_fsync_noflush(file, start, end, datasync);
-	if (!ret)
-		ret = ext4_sync_parent(inode);
+	if (ret)
+		return ret;
+
+	/* Force writeout of inode table buffer to disk */
+	ret = ext4_write_inode(inode, &wbc);
+	if (ret)
+		return ret;
+
+	ret = ext4_sync_parent(inode);
+
 	if (test_opt(inode->i_sb, BARRIER))
 		*needs_barrier = true;
 
-- 
cgit v1.2.3


From 356227096eb66e41b23caf7045e6304877322edf Mon Sep 17 00:00:00 2001
From: Yuto Ohnuki <ytohnuki@amazon.com>
Date: Mon, 23 Feb 2026 12:33:46 +0000
Subject: ext4: replace BUG_ON with proper error handling in
 ext4_read_inline_folio

Replace BUG_ON() with proper error handling when inline data size
exceeds PAGE_SIZE. This prevents kernel panic and allows the system to
continue running while properly reporting the filesystem corruption.

The error is logged via ext4_error_inode(), the buffer head is released
to prevent memory leak, and -EFSCORRUPTED is returned to indicate
filesystem corruption.

Signed-off-by: Yuto Ohnuki <ytohnuki@amazon.com>
Link: https://patch.msgid.link/20260223123345.14838-2-ytohnuki@amazon.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/inline.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 1f6bc05593df..408677fa8196 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -522,7 +522,15 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio)
 		goto out;
 
 	len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
-	BUG_ON(len > PAGE_SIZE);
+
+	if (len > PAGE_SIZE) {
+		ext4_error_inode(inode, __func__, __LINE__, 0,
+				 "inline size %zu exceeds PAGE_SIZE", len);
+		ret = -EFSCORRUPTED;
+		brelse(iloc.bh);
+		goto out;
+	}
+
 	kaddr = kmap_local_folio(folio, 0);
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
 	kaddr = folio_zero_tail(folio, len, kaddr + len);
-- 
cgit v1.2.3


From 1aec30021edd410b986c156f195f3d23959a9d11 Mon Sep 17 00:00:00 2001
From: Li Chen <me@linux.beauty>
Date: Wed, 25 Feb 2026 16:26:16 +0800
Subject: ext4: publish jinode after initialization

ext4_inode_attach_jinode() publishes ei->jinode to concurrent users.
It used to set ei->jinode before jbd2_journal_init_jbd_inode(),
allowing a reader to observe a non-NULL jinode with i_vfs_inode
still unset.

The fast commit flush path can then pass this jinode to
jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and
may crash.

Below is the crash I observe:
```
BUG: unable to handle page fault for address: 000000010beb47f4
PGD 110e51067 P4D 110e51067 PUD 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014
RIP: 0010:xas_find_marked+0x3d/0x2e0
Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02
RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246
RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003
RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10
RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec
R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000
R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88
FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0
PKRU: 55555554
Call Trace:
<TASK>
filemap_get_folios_tag+0x87/0x2a0
__filemap_fdatawait_range+0x5f/0xd0
? srso_alias_return_thunk+0x5/0xfbef5
? __schedule+0x3e7/0x10c0
? srso_alias_return_thunk+0x5/0xfbef5
? srso_alias_return_thunk+0x5/0xfbef5
? srso_alias_return_thunk+0x5/0xfbef5
? preempt_count_sub+0x5f/0x80
? srso_alias_return_thunk+0x5/0xfbef5
? cap_safe_nice+0x37/0x70
? srso_alias_return_thunk+0x5/0xfbef5
? preempt_count_sub+0x5f/0x80
? srso_alias_return_thunk+0x5/0xfbef5
filemap_fdatawait_range_keep_errors+0x12/0x40
ext4_fc_commit+0x697/0x8b0
? ext4_file_write_iter+0x64b/0x950
? srso_alias_return_thunk+0x5/0xfbef5
? preempt_count_sub+0x5f/0x80
? srso_alias_return_thunk+0x5/0xfbef5
? vfs_write+0x356/0x480
? srso_alias_return_thunk+0x5/0xfbef5
? preempt_count_sub+0x5f/0x80
ext4_sync_file+0xf7/0x370
do_fsync+0x3b/0x80
? syscall_trace_enter+0x108/0x1d0
__x64_sys_fdatasync+0x16/0x20
do_syscall_64+0x62/0x2c0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
...
```

Fix this by initializing the jbd2_inode first.
Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after
initialization. Readers use READ_ONCE() to fetch the pointer.

Fixes: a361293f5fede ("jbd2: Fix oops in jbd2_journal_file_inode()")
Cc: stable@vger.kernel.org
Signed-off-by: Li Chen <me@linux.beauty>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260225082617.147957-1-me@linux.beauty
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/fast_commit.c |  4 ++--
 fs/ext4/inode.c       | 15 +++++++++++----
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f575751f1cae..6e949c21842d 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -975,13 +975,13 @@ static int ext4_fc_flush_data(journal_t *journal)
 	int ret = 0;
 
 	list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
-		ret = jbd2_submit_inode_data(journal, ei->jinode);
+		ret = jbd2_submit_inode_data(journal, READ_ONCE(ei->jinode));
 		if (ret)
 			return ret;
 	}
 
 	list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
-		ret = jbd2_wait_inode_data(journal, ei->jinode);
+		ret = jbd2_wait_inode_data(journal, READ_ONCE(ei->jinode));
 		if (ret)
 			return ret;
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 252191632f56..ac5f3446c731 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -128,6 +128,8 @@ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
+	struct jbd2_inode *jinode = READ_ONCE(EXT4_I(inode)->jinode);
+
 	trace_ext4_begin_ordered_truncate(inode, new_size);
 	/*
 	 * If jinode is zero, then we never opened the file for
@@ -135,10 +137,10 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode,
 	 * jbd2_journal_begin_ordered_truncate() since there's no
 	 * outstanding writes we need to flush.
 	 */
-	if (!EXT4_I(inode)->jinode)
+	if (!jinode)
 		return 0;
 	return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
-						   EXT4_I(inode)->jinode,
+						   jinode,
 						   new_size);
 }
 
@@ -4451,8 +4453,13 @@ int ext4_inode_attach_jinode(struct inode *inode)
 			spin_unlock(&inode->i_lock);
 			return -ENOMEM;
 		}
-		ei->jinode = jinode;
-		jbd2_journal_init_jbd_inode(ei->jinode, inode);
+		jbd2_journal_init_jbd_inode(jinode, inode);
+		/*
+		 * Publish ->jinode only after it is fully initialized so that
+		 * readers never observe a partially initialized jbd2_inode.
+		 */
+		smp_wmb();
+		WRITE_ONCE(ei->jinode, jinode);
 		jinode = NULL;
 	}
 	spin_unlock(&inode->i_lock);
-- 
cgit v1.2.3


From afe376d2c1fa78c8a1063a357c6971bba3f6da91 Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Sun, 1 Mar 2026 21:44:26 +0530
Subject: ext4: kunit: extents-test: lix percpu_counters list corruption

commit 82f80e2e3b23 ("ext4: add extent status cache support to kunit tests"),
added ext4_es_register_shrinker() in extents_kunit_init() function but
failed to add the unregister shrinker routine in extents_kunit_exit().

This could cause the following percpu_counters list corruption bug.

         ok 1 split unwrit extent to 2 extents and convert 1st half writ
  slab kmalloc-4k start c0000002007ff000 pointer offset 1448 size 4096
 list_add corruption. next->prev should be prev (c000000004bc9e60), but was 0000000000000000. (next=c0000002007ff5a8).
 ------------[ cut here ]------------
 kernel BUG at lib/list_debug.c:29!
cpu 0x2: Vector: 700 (Program Check) at [c000000241927a30]
    pc: c000000000f26ed0: __list_add_valid_or_report+0x120/0x164
    lr: c000000000f26ecc: __list_add_valid_or_report+0x11c/0x164
    sp: c000000241927cd0
   msr: 800000000282b033
  current = 0xc000000241215200
  paca    = 0xc0000003fffff300   irqmask: 0x03   irq_happened: 0x09
    pid   = 258, comm = kunit_try_catch
kernel BUG at lib/list_debug.c:29!
enter ? for help
 __percpu_counter_init_many+0x148/0x184
 ext4_es_register_shrinker+0x74/0x23c
 extents_kunit_init+0x100/0x308
 kunit_try_run_case+0x78/0x1f8
 kunit_generic_run_threadfn_adapter+0x40/0x70
 kthread+0x190/0x1a0
 start_kernel_thread+0x14/0x18
2:mon>

This happens because:

extents_kunit_init(test N):
  ext4_es_register_shrinker(sbi)
    percpu_counters_init() x 4; // this adds 4 list nodes to global percpu_counters list
      list_add(&fbc->list, &percpu_counters);
    shrinker_register();

extents_kunit_exit(test N):
  kfree(sbi);			// frees sbi w/o removing those 4 list nodes.
  				// So, those list node now becomes dangling pointers

extents_kunit_init(test N+1):
  kzalloc_obj(ext4_sb_info)	// allocator returns same page, but zeroed.
  ext4_es_register_shrinker(sbi)
    percpu_counters_init()
      list_add(&fbc->list, &percpu_counters);
        __list_add_valid(new, prev, next);
	next->prev != prev 		// list corruption bug detected, since next->prev = NULL

Fixes: 82f80e2e3b23 ("ext4: add extent status cache support to kunit tests")
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Link: https://patch.msgid.link/5bb9041471dab8ce870c191c19cbe4df57473be8.1772381213.git.ritesh.list@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/extents-test.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c
index 7c4690eb7dad..a6b3e6b592a5 100644
--- a/fs/ext4/extents-test.c
+++ b/fs/ext4/extents-test.c
@@ -142,8 +142,10 @@ static struct file_system_type ext_fs_type = {
 
 static void extents_kunit_exit(struct kunit *test)
 {
-	struct ext4_sb_info *sbi = k_ctx.k_ei->vfs_inode.i_sb->s_fs_info;
+	struct super_block *sb = k_ctx.k_ei->vfs_inode.i_sb;
+	struct ext4_sb_info *sbi = sb->s_fs_info;
 
+	ext4_es_unregister_shrinker(sbi);
 	kfree(sbi);
 	kfree(k_ctx.k_ei);
 	kfree(k_ctx.k_data);
-- 
cgit v1.2.3


From 46066e3a06647c5b186cc6334409722622d05c44 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Mon, 2 Mar 2026 21:46:19 +0800
Subject: ext4: avoid allocate block from corrupted group in
 ext4_mb_find_by_goal()

There's issue as follows:
...
EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 206 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2243 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): Delayed block allocation failed for inode 2239 at logical offset 0 with max blocks 1 with error 117
EXT4-fs (mmcblk0p1): This should not happen!! Data will be lost

EXT4-fs (mmcblk0p1): error count since last fsck: 1
EXT4-fs (mmcblk0p1): initial error at time 1765597433: ext4_mb_generate_buddy:760
EXT4-fs (mmcblk0p1): last error at time 1765597433: ext4_mb_generate_buddy:760
...

According to the log analysis, blocks are always requested from the
corrupted block group. This may happen as follows:
ext4_mb_find_by_goal
  ext4_mb_load_buddy
   ext4_mb_load_buddy_gfp
     ext4_mb_init_cache
      ext4_read_block_bitmap_nowait
      ext4_wait_block_bitmap
       ext4_validate_block_bitmap
        if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
         return -EFSCORRUPTED; // There's no logs.
 if (err)
  return err;  // Will return error
ext4_lock_group(ac->ac_sb, group);
  if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) // Unreachable
   goto out;

After commit 9008a58e5dce ("ext4: make the bitmap read routines return
real error codes") merged, Commit 163a203ddb36 ("ext4: mark block group
as corrupt on block bitmap error") is no real solution for allocating
blocks from corrupted block groups. This is because if
'EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)' is true, then
'ext4_mb_load_buddy()' may return an error. This means that the block
allocation will fail.
Therefore, check block group if corrupted when ext4_mb_load_buddy()
returns error.

Fixes: 163a203ddb36 ("ext4: mark block group as corrupt on block bitmap error")
Fixes: 9008a58e5dce ("ext4: make the bitmap read routines return real error codes")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260302134619.3145520-1-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/mballoc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 20e9fdaf4301..705a879f13d3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2443,8 +2443,12 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 		return 0;
 
 	err = ext4_mb_load_buddy(ac->ac_sb, group, e4b);
-	if (err)
+	if (err) {
+		if (EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info) &&
+		    !(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
+			return 0;
 		return err;
+	}
 
 	ext4_lock_group(ac->ac_sb, group);
 	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
-- 
cgit v1.2.3


From c4a48e9eeefd610ae0d26e9ff085277f751c8e53 Mon Sep 17 00:00:00 2001
From: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Date: Mon, 2 Mar 2026 20:08:11 +0530
Subject: ext4: minor fix for ext4_split_extent_zeroout()

We missed storing the error which triggerd smatch warning:

	fs/ext4/extents.c:3369 ext4_split_extent_zeroout()
	warn: duplicate zero check 'err' (previous on line 3363)

fs/ext4/extents.c
    3361
    3362         err = ext4_ext_get_access(handle, inode, path + depth);
    3363         if (err)
    3364                 return err;
    3365
    3366         ext4_ext_mark_initialized(ex);
    3367
    3368         ext4_ext_dirty(handle, inode, path + depth);
--> 3369         if (err)
    3370                 return err;
    3371
    3372         return 0;
    3373 }

Fix it by correctly storing the err value from ext4_ext_dirty().

Link: https://lore.kernel.org/all/aYXvVgPnKltX79KE@stanley.mountain/
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: a985e07c26455 ("ext4: refactor zeroout path and handle all cases")
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Baokun Li <libaokun@linux.alibaba.com>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://patch.msgid.link/20260302143811.605174-1-ojaswin@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/extents.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ae3804f36535..b41a44dc245c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3363,7 +3363,7 @@ static int ext4_split_extent_zeroout(handle_t *handle, struct inode *inode,
 
 	ext4_ext_mark_initialized(ex);
 
-	ext4_ext_dirty(handle, inode, path + depth);
+	err = ext4_ext_dirty(handle, inode, path + depth);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 73bf12adbea10b13647864cd1c62410d19e21086 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Tue, 3 Mar 2026 09:22:42 +0800
Subject: ext4: test if inode's all dirty pages are submitted to disk

The commit aa373cf55099 ("writeback: stop background/kupdate works from
livelocking other works") introduced an issue where unmounting a filesystem
in a multi-logical-partition scenario could lead to batch file data loss.
This problem was not fixed until the commit d92109891f21 ("fs/writeback:
bail out if there is no more inodes for IO and queued once"). It took
considerable time to identify the root cause. Additionally, in actual
production environments, we frequently encountered file data loss after
normal system reboots. Therefore, we are adding a check in the inode
release flow to verify whether all dirty pages have been flushed to disk,
in order to determine whether the data loss is caused by a logic issue in
the filesystem code.

Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260303012242.3206465-1-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/inode.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ac5f3446c731..1123d995494b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -186,6 +186,14 @@ void ext4_evict_inode(struct inode *inode)
 	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
 		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
+		/*
+		 * If there's dirty page will lead to data loss, user
+		 * could see stale data.
+		 */
+		if (unlikely(!ext4_emergency_state(inode->i_sb) &&
+		    mapping_tagged(&inode->i_data, PAGECACHE_TAG_DIRTY)))
+			ext4_warning_inode(inode, "data will be lost");
+
 		truncate_inode_pages_final(&inode->i_data);
 
 		goto no_delete;
-- 
cgit v1.2.3


From 2acb5c12ebd860f30e4faf67e6cc8c44ddfe5fe8 Mon Sep 17 00:00:00 2001
From: Tejas Bharambe <tejas.bharambe@outlook.com>
Date: Tue, 3 Mar 2026 23:14:34 -0800
Subject: ext4: validate p_idx bounds in ext4_ext_correct_indexes

ext4_ext_correct_indexes() walks up the extent tree correcting
index entries when the first extent in a leaf is modified. Before
accessing path[k].p_idx->ei_block, there is no validation that
p_idx falls within the valid range of index entries for that
level.

If the on-disk extent header contains a corrupted or crafted
eh_entries value, p_idx can point past the end of the allocated
buffer, causing a slab-out-of-bounds read.

Fix this by validating path[k].p_idx against EXT_LAST_INDEX() at
both access sites: before the while loop and inside it. Return
-EFSCORRUPTED if the index pointer is out of range, consistent
with how other bounds violations are handled in the ext4 extent
tree code.

Reported-by: syzbot+04c4e65cab786a2e5b7e@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=04c4e65cab786a2e5b7e
Signed-off-by: Tejas Bharambe <tejas.bharambe@outlook.com>
Link: https://patch.msgid.link/JH0PR06MB66326016F9B6AD24097D232B897CA@JH0PR06MB6632.apcprd06.prod.outlook.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/extents.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b41a44dc245c..c99e0802d700 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1736,6 +1736,13 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
 	err = ext4_ext_get_access(handle, inode, path + k);
 	if (err)
 		return err;
+	if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) {
+		EXT4_ERROR_INODE(inode,
+				 "path[%d].p_idx %p > EXT_LAST_INDEX %p",
+				 k, path[k].p_idx,
+				 EXT_LAST_INDEX(path[k].p_hdr));
+		return -EFSCORRUPTED;
+	}
 	path[k].p_idx->ei_block = border;
 	err = ext4_ext_dirty(handle, inode, path + k);
 	if (err)
@@ -1748,6 +1755,14 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
 		err = ext4_ext_get_access(handle, inode, path + k);
 		if (err)
 			goto clean;
+		if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) {
+			EXT4_ERROR_INODE(inode,
+					 "path[%d].p_idx %p > EXT_LAST_INDEX %p",
+					 k, path[k].p_idx,
+					 EXT_LAST_INDEX(path[k].p_hdr));
+			err = -EFSCORRUPTED;
+			goto clean;
+		}
 		path[k].p_idx->ei_block = border;
 		err = ext4_ext_dirty(handle, inode, path + k);
 		if (err)
-- 
cgit v1.2.3


From 5422fe71d26d42af6c454ca9527faaad4e677d6c Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Fri, 6 Mar 2026 09:31:58 +0800
Subject: ext4: avoid infinite loops caused by residual data

On the mkdir/mknod path, when mapping logical blocks to physical blocks,
if inserting a new extent into the extent tree fails (in this example,
because the file system disabled the huge file feature when marking the
inode as dirty), ext4_ext_map_blocks() only calls ext4_free_blocks() to
reclaim the physical block without deleting the corresponding data in
the extent tree. This causes subsequent mkdir operations to reference
the previously reclaimed physical block number again, even though this
physical block is already being used by the xattr block. Therefore, a
situation arises where both the directory and xattr are using the same
buffer head block in memory simultaneously.

The above causes ext4_xattr_block_set() to enter an infinite loop about
"inserted" and cannot release the inode lock, ultimately leading to the
143s blocking problem mentioned in [1].

If the metadata is corrupted, then trying to remove some extent space
can do even more harm. Also in case EXT4_GET_BLOCKS_DELALLOC_RESERVE
was passed, remove space wrongly update quota information.
Jan Kara suggests distinguishing between two cases:

1) The error is ENOSPC or EDQUOT - in this case the filesystem is fully
consistent and we must maintain its consistency including all the
accounting. However these errors can happen only early before we've
inserted the extent into the extent tree. So current code works correctly
for this case.

2) Some other error - this means metadata is corrupted. We should strive to
do as few modifications as possible to limit damage. So I'd just skip
freeing of allocated blocks.

[1]
INFO: task syz.0.17:5995 blocked for more than 143 seconds.
Call Trace:
 inode_lock_nested include/linux/fs.h:1073 [inline]
 __start_dirop fs/namei.c:2923 [inline]
 start_dirop fs/namei.c:2934 [inline]

Reported-by: syzbot+512459401510e2a9a39f@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1659aaaaa8d9d11265d7
Tested-by: syzbot+1659aaaaa8d9d11265d7@syzkaller.appspotmail.com
Reported-by: syzbot+1659aaaaa8d9d11265d7@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=512459401510e2a9a39f
Tested-by: syzbot+1659aaaaa8d9d11265d7@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Tested-by: syzbot+512459401510e2a9a39f@syzkaller.appspotmail.com
Link: https://patch.msgid.link/tencent_43696283A68450B761D76866C6F360E36705@qq.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/extents.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c99e0802d700..8744d3845577 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4472,9 +4472,13 @@ got_allocated_blocks:
 	path = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (IS_ERR(path)) {
 		err = PTR_ERR(path);
-		if (allocated_clusters) {
+		/*
+		 * Gracefully handle out of space conditions. If the filesystem
+		 * is inconsistent, we'll just leak allocated blocks to avoid
+		 * causing even more damage.
+		 */
+		if (allocated_clusters && (err == -EDQUOT || err == -ENOSPC)) {
 			int fb_flags = 0;
-
 			/*
 			 * free data blocks we just allocated.
 			 * not a good idea to call discard here directly,
-- 
cgit v1.2.3


From bac3190a8e79beff6ed221975e0c9b1b5f2a21da Mon Sep 17 00:00:00 2001
From: Milos Nikic <nikic.milos@gmail.com>
Date: Tue, 10 Mar 2026 21:15:48 -0700
Subject: jbd2: gracefully abort on checkpointing state corruptions

This patch targets two internal state machine invariants in checkpoint.c
residing inside functions that natively return integer error codes.

- In jbd2_cleanup_journal_tail(): A blocknr of 0 indicates a severely
corrupted journal superblock. Replaced the J_ASSERT with a WARN_ON_ONCE
and a graceful journal abort, returning -EFSCORRUPTED.

- In jbd2_log_do_checkpoint(): Replaced the J_ASSERT_BH checking for
an unexpected buffer_jwrite state. If the warning triggers, we
explicitly drop the just-taken get_bh() reference and call __flush_batch()
to safely clean up any previously queued buffers in the j_chkpt_bhs array,
preventing a memory leak before returning -EFSCORRUPTED.

Signed-off-by: Milos Nikic <nikic.milos@gmail.com>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Baokun Li <libaokun@linux.alibaba.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260311041548.159424-1-nikic.milos@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/jbd2/checkpoint.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index de89c5bef607..1508e2f54462 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -267,7 +267,15 @@ restart:
 			 */
 			BUFFER_TRACE(bh, "queue");
 			get_bh(bh);
-			J_ASSERT_BH(bh, !buffer_jwrite(bh));
+			if (WARN_ON_ONCE(buffer_jwrite(bh))) {
+				put_bh(bh); /* drop the ref we just took */
+				spin_unlock(&journal->j_list_lock);
+				/* Clean up any previously batched buffers */
+				if (batch_count)
+					__flush_batch(journal, &batch_count);
+				jbd2_journal_abort(journal, -EFSCORRUPTED);
+				return -EFSCORRUPTED;
+			}
 			journal->j_chkpt_bhs[batch_count++] = bh;
 			transaction->t_chp_stats.cs_written++;
 			transaction->t_checkpoint_list = jh->b_cpnext;
@@ -325,7 +333,10 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 
 	if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr))
 		return 1;
-	J_ASSERT(blocknr != 0);
+	if (WARN_ON_ONCE(blocknr == 0)) {
+		jbd2_journal_abort(journal, -EFSCORRUPTED);
+		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * We need to make sure that any blocks that were recently written out
-- 
cgit v1.2.3


From 49504a512587147dd6da3b4b08832ccc157b97dc Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Sat, 14 Mar 2026 15:52:56 +0800
Subject: ext4: introduce EXPORT_SYMBOL_FOR_EXT4_TEST() helper

Introduce EXPORT_SYMBOL_FOR_EXT4_TEST() helper for kuint test.

Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260314075258.1317579-2-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 293f698b7042..c579f68b3c11 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3944,6 +3944,11 @@ static inline bool ext4_inode_can_atomic_write(struct inode *inode)
 extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
 				  loff_t pos, unsigned len,
 				  get_block_t *get_block);
+
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+#define EXPORT_SYMBOL_FOR_EXT4_TEST(sym) \
+	EXPORT_SYMBOL_FOR_MODULES(sym, "ext4-test")
+#endif
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */
-- 
cgit v1.2.3


From 519b76ac0b31d86b45784735d4ef964e8efdc56b Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Sat, 14 Mar 2026 15:52:57 +0800
Subject: ext4: fix mballoc-test.c is not compiled when EXT4_KUNIT_TESTS=M

Now, only EXT4_KUNIT_TESTS=Y testcase will be compiled in 'mballoc.c'.
To solve this issue, the ext4 test code needs to be decoupled. The ext4
test module is compiled into a separate module.

Reported-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Closes: https://patchwork.kernel.org/project/cifs-client/patch/20260118091313.1988168-2-chenxiaosong.chenxiaosong@linux.dev/
Fixes: 7c9fa399a369 ("ext4: add first unit test for ext4_mb_new_blocks_simple in mballoc")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260314075258.1317579-3-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/Makefile       |   4 +-
 fs/ext4/mballoc-test.c |  81 ++++++++++++++++++++-------------------
 fs/ext4/mballoc.c      | 102 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ext4/mballoc.h      |  30 +++++++++++++++
 4 files changed, 172 insertions(+), 45 deletions(-)

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 72206a292676..d836c3fe311b 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -14,7 +14,7 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
-ext4-inode-test-objs			+= inode-test.o
-obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-inode-test.o
+ext4-test-objs				+= inode-test.o mballoc-test.o
+obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-test.o
 ext4-$(CONFIG_FS_VERITY)		+= verity.o
 ext4-$(CONFIG_FS_ENCRYPTION)		+= crypto.o
diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c
index 9fbdf6a09489..6f5bfbb0e8a4 100644
--- a/fs/ext4/mballoc-test.c
+++ b/fs/ext4/mballoc-test.c
@@ -8,6 +8,7 @@
 #include <linux/random.h>
 
 #include "ext4.h"
+#include "mballoc.h"
 
 struct mbt_grp_ctx {
 	struct buffer_head bitmap_bh;
@@ -336,7 +337,7 @@ ext4_mb_mark_context_stub(handle_t *handle, struct super_block *sb, bool state,
 	if (state)
 		mb_set_bits(bitmap_bh->b_data, blkoff, len);
 	else
-		mb_clear_bits(bitmap_bh->b_data, blkoff, len);
+		mb_clear_bits_test(bitmap_bh->b_data, blkoff, len);
 
 	return 0;
 }
@@ -413,14 +414,14 @@ static void test_new_blocks_simple(struct kunit *test)
 
 	/* get block at goal */
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test, ar.goal, found,
 		"failed to alloc block at goal, expected %llu found %llu",
 		ar.goal, found);
 
 	/* get block after goal in goal group */
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found,
 		"failed to alloc block after goal in goal group, expected %llu found %llu",
 		ar.goal + 1, found);
@@ -428,7 +429,7 @@ static void test_new_blocks_simple(struct kunit *test)
 	/* get block after goal group */
 	mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test,
 		ext4_group_first_block_no(sb, goal_group + 1), found,
 		"failed to alloc block after goal group, expected %llu found %llu",
@@ -438,7 +439,7 @@ static void test_new_blocks_simple(struct kunit *test)
 	for (i = goal_group; i < ext4_get_groups_count(sb); i++)
 		mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_EQ_MSG(test,
 		ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found,
 		"failed to alloc block before goal group, expected %llu found %llu",
@@ -448,7 +449,7 @@ static void test_new_blocks_simple(struct kunit *test)
 	for (i = 0; i < ext4_get_groups_count(sb); i++)
 		mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 	ar.goal = ext4_group_first_block_no(sb, goal_group);
-	found = ext4_mb_new_blocks_simple(&ar, &err);
+	found = ext4_mb_new_blocks_simple_test(&ar, &err);
 	KUNIT_ASSERT_NE_MSG(test, err, 0,
 		"unexpectedly get block when no block is available");
 }
@@ -492,16 +493,16 @@ validate_free_blocks_simple(struct kunit *test, struct super_block *sb,
 			continue;
 
 		bitmap = mbt_ctx_bitmap(sb, i);
-		bit = mb_find_next_zero_bit(bitmap, max, 0);
+		bit = mb_find_next_zero_bit_test(bitmap, max, 0);
 		KUNIT_ASSERT_EQ_MSG(test, bit, max,
 				    "free block on unexpected group %d", i);
 	}
 
 	bitmap = mbt_ctx_bitmap(sb, goal_group);
-	bit = mb_find_next_zero_bit(bitmap, max, 0);
+	bit = mb_find_next_zero_bit_test(bitmap, max, 0);
 	KUNIT_ASSERT_EQ(test, bit, start);
 
-	bit = mb_find_next_bit(bitmap, max, bit + 1);
+	bit = mb_find_next_bit_test(bitmap, max, bit + 1);
 	KUNIT_ASSERT_EQ(test, bit, start + len);
 }
 
@@ -524,7 +525,7 @@ test_free_blocks_simple_range(struct kunit *test, ext4_group_t goal_group,
 
 	block = ext4_group_first_block_no(sb, goal_group) +
 		EXT4_C2B(sbi, start);
-	ext4_free_blocks_simple(inode, block, len);
+	ext4_free_blocks_simple_test(inode, block, len);
 	validate_free_blocks_simple(test, sb, goal_group, start, len);
 	mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb));
 }
@@ -566,15 +567,15 @@ test_mark_diskspace_used_range(struct kunit *test,
 
 	bitmap = mbt_ctx_bitmap(sb, TEST_GOAL_GROUP);
 	memset(bitmap, 0, sb->s_blocksize);
-	ret = ext4_mb_mark_diskspace_used(ac, NULL);
+	ret = ext4_mb_mark_diskspace_used_test(ac, NULL);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
-	i = mb_find_next_bit(bitmap, max, 0);
+	i = mb_find_next_bit_test(bitmap, max, 0);
 	KUNIT_ASSERT_EQ(test, i, start);
-	i = mb_find_next_zero_bit(bitmap, max, i + 1);
+	i = mb_find_next_zero_bit_test(bitmap, max, i + 1);
 	KUNIT_ASSERT_EQ(test, i, start + len);
-	i = mb_find_next_bit(bitmap, max, i + 1);
+	i = mb_find_next_bit_test(bitmap, max, i + 1);
 	KUNIT_ASSERT_EQ(test, max, i);
 }
 
@@ -617,54 +618,54 @@ static void mbt_generate_buddy(struct super_block *sb, void *buddy,
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
 	bb_h = buddy + sbi->s_mb_offsets[1];
 
-	off = mb_find_next_zero_bit(bb, max, 0);
+	off = mb_find_next_zero_bit_test(bb, max, 0);
 	grp->bb_first_free = off;
 	while (off < max) {
 		grp->bb_counters[0]++;
 		grp->bb_free++;
 
-		if (!(off & 1) && !mb_test_bit(off + 1, bb)) {
+		if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) {
 			grp->bb_free++;
 			grp->bb_counters[0]--;
-			mb_clear_bit(off >> 1, bb_h);
+			mb_clear_bit_test(off >> 1, bb_h);
 			grp->bb_counters[1]++;
 			grp->bb_largest_free_order = 1;
 			off++;
 		}
 
-		off = mb_find_next_zero_bit(bb, max, off + 1);
+		off = mb_find_next_zero_bit_test(bb, max, off + 1);
 	}
 
 	for (order = 1; order < MB_NUM_ORDERS(sb) - 1; order++) {
 		bb = buddy + sbi->s_mb_offsets[order];
 		bb_h = buddy + sbi->s_mb_offsets[order + 1];
 		max = max >> 1;
-		off = mb_find_next_zero_bit(bb, max, 0);
+		off = mb_find_next_zero_bit_test(bb, max, 0);
 
 		while (off < max) {
-			if (!(off & 1) && !mb_test_bit(off + 1, bb)) {
+			if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) {
 				mb_set_bits(bb, off, 2);
 				grp->bb_counters[order] -= 2;
-				mb_clear_bit(off >> 1, bb_h);
+				mb_clear_bit_test(off >> 1, bb_h);
 				grp->bb_counters[order + 1]++;
 				grp->bb_largest_free_order = order + 1;
 				off++;
 			}
 
-			off = mb_find_next_zero_bit(bb, max, off + 1);
+			off = mb_find_next_zero_bit_test(bb, max, off + 1);
 		}
 	}
 
 	max = EXT4_CLUSTERS_PER_GROUP(sb);
-	off = mb_find_next_zero_bit(bitmap, max, 0);
+	off = mb_find_next_zero_bit_test(bitmap, max, 0);
 	while (off < max) {
 		grp->bb_fragments++;
 
-		off = mb_find_next_bit(bitmap, max, off + 1);
+		off = mb_find_next_bit_test(bitmap, max, off + 1);
 		if (off + 1 >= max)
 			break;
 
-		off = mb_find_next_zero_bit(bitmap, max, off + 1);
+		off = mb_find_next_zero_bit_test(bitmap, max, off + 1);
 	}
 }
 
@@ -706,7 +707,7 @@ do_test_generate_buddy(struct kunit *test, struct super_block *sb, void *bitmap,
 	/* needed by validation in ext4_mb_generate_buddy */
 	ext4_grp->bb_free = mbt_grp->bb_free;
 	memset(ext4_buddy, 0xff, sb->s_blocksize);
-	ext4_mb_generate_buddy(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP,
+	ext4_mb_generate_buddy_test(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP,
 			       ext4_grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(mbt_buddy, ext4_buddy, sb->s_blocksize),
@@ -760,7 +761,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b,
 	ex.fe_group = TEST_GOAL_GROUP;
 
 	ext4_lock_group(sb, TEST_GOAL_GROUP);
-	mb_mark_used(e4b, &ex);
+	mb_mark_used_test(e4b, &ex);
 	ext4_unlock_group(sb, TEST_GOAL_GROUP);
 
 	mb_set_bits(bitmap, start, len);
@@ -769,7 +770,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b,
 	memset(buddy, 0xff, sb->s_blocksize);
 	for (i = 0; i < MB_NUM_ORDERS(sb); i++)
 		grp->bb_counters[i] = 0;
-	ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp);
+	ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize),
 			0);
@@ -798,7 +799,7 @@ static void test_mb_mark_used(struct kunit *test)
 				bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp);
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	grp->bb_free = EXT4_CLUSTERS_PER_GROUP(sb);
@@ -809,7 +810,7 @@ static void test_mb_mark_used(struct kunit *test)
 		test_mb_mark_used_range(test, &e4b, ranges[i].start,
 					ranges[i].len, bitmap, buddy, grp);
 
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 static void
@@ -825,16 +826,16 @@ test_mb_free_blocks_range(struct kunit *test, struct ext4_buddy *e4b,
 		return;
 
 	ext4_lock_group(sb, e4b->bd_group);
-	mb_free_blocks(NULL, e4b, start, len);
+	mb_free_blocks_test(NULL, e4b, start, len);
 	ext4_unlock_group(sb, e4b->bd_group);
 
-	mb_clear_bits(bitmap, start, len);
+	mb_clear_bits_test(bitmap, start, len);
 	/* bypass bb_free validatoin in ext4_mb_generate_buddy */
 	grp->bb_free += len;
 	memset(buddy, 0xff, sb->s_blocksize);
 	for (i = 0; i < MB_NUM_ORDERS(sb); i++)
 		grp->bb_counters[i] = 0;
-	ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp);
+	ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp);
 
 	KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize),
 			0);
@@ -865,7 +866,7 @@ static void test_mb_free_blocks(struct kunit *test)
 				bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp);
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	ex.fe_start = 0;
@@ -873,7 +874,7 @@ static void test_mb_free_blocks(struct kunit *test)
 	ex.fe_group = TEST_GOAL_GROUP;
 
 	ext4_lock_group(sb, TEST_GOAL_GROUP);
-	mb_mark_used(&e4b, &ex);
+	mb_mark_used_test(&e4b, &ex);
 	ext4_unlock_group(sb, TEST_GOAL_GROUP);
 
 	grp->bb_free = 0;
@@ -886,7 +887,7 @@ static void test_mb_free_blocks(struct kunit *test)
 		test_mb_free_blocks_range(test, &e4b, ranges[i].start,
 					  ranges[i].len, bitmap, buddy, grp);
 
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 #define COUNT_FOR_ESTIMATE 100000
@@ -904,7 +905,7 @@ static void test_mb_mark_used_cost(struct kunit *test)
 	if (sb->s_blocksize > PAGE_SIZE)
 		kunit_skip(test, "blocksize exceeds pagesize");
 
-	ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b);
+	ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	ex.fe_group = TEST_GOAL_GROUP;
@@ -918,7 +919,7 @@ static void test_mb_mark_used_cost(struct kunit *test)
 			ex.fe_start = ranges[i].start;
 			ex.fe_len = ranges[i].len;
 			ext4_lock_group(sb, TEST_GOAL_GROUP);
-			mb_mark_used(&e4b, &ex);
+			mb_mark_used_test(&e4b, &ex);
 			ext4_unlock_group(sb, TEST_GOAL_GROUP);
 		}
 		end = jiffies;
@@ -929,14 +930,14 @@ static void test_mb_mark_used_cost(struct kunit *test)
 				continue;
 
 			ext4_lock_group(sb, TEST_GOAL_GROUP);
-			mb_free_blocks(NULL, &e4b, ranges[i].start,
+			mb_free_blocks_test(NULL, &e4b, ranges[i].start,
 				       ranges[i].len);
 			ext4_unlock_group(sb, TEST_GOAL_GROUP);
 		}
 	}
 
 	kunit_info(test, "costed jiffies %lu\n", all);
-	ext4_mb_unload_buddy(&e4b);
+	ext4_mb_unload_buddy_test(&e4b);
 }
 
 static const struct mbt_ext4_block_layout mbt_test_layouts[] = {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 705a879f13d3..93d37f6cf9c3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4088,7 +4088,7 @@ void ext4_exit_mballoc(void)
 
 #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001
 #define EXT4_MB_SYNC_UPDATE 0x0002
-static int
+int
 ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state,
 		     ext4_group_t group, ext4_grpblk_t blkoff,
 		     ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed)
@@ -7192,6 +7192,102 @@ out_unload:
 	return error;
 }
 
-#ifdef CONFIG_EXT4_KUNIT_TESTS
-#include "mballoc-test.c"
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+void mb_clear_bits_test(void *bm, int cur, int len)
+{
+	 mb_clear_bits(bm, cur, len);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bits_test);
+
+ext4_fsblk_t
+ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar,
+			       int *errp)
+{
+	return ext4_mb_new_blocks_simple(ar, errp);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_new_blocks_simple_test);
+
+int mb_find_next_zero_bit_test(void *addr, int max, int start)
+{
+	return mb_find_next_zero_bit(addr, max, start);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_zero_bit_test);
+
+int mb_find_next_bit_test(void *addr, int max, int start)
+{
+	return mb_find_next_bit(addr, max, start);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_bit_test);
+
+void mb_clear_bit_test(int bit, void *addr)
+{
+	mb_clear_bit(bit, addr);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bit_test);
+
+int mb_test_bit_test(int bit, void *addr)
+{
+	return mb_test_bit(bit, addr);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_test_bit_test);
+
+int ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac,
+				     handle_t *handle)
+{
+	return ext4_mb_mark_diskspace_used(ac, handle);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_diskspace_used_test);
+
+int mb_mark_used_test(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
+{
+	return mb_mark_used(e4b, ex);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_mark_used_test);
+
+void ext4_mb_generate_buddy_test(struct super_block *sb, void *buddy,
+				 void *bitmap, ext4_group_t group,
+				 struct ext4_group_info *grp)
+{
+	ext4_mb_generate_buddy(sb, buddy, bitmap, group, grp);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_generate_buddy_test);
+
+int ext4_mb_load_buddy_test(struct super_block *sb, ext4_group_t group,
+			    struct ext4_buddy *e4b)
+{
+	return ext4_mb_load_buddy(sb, group, e4b);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_load_buddy_test);
+
+void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b)
+{
+	ext4_mb_unload_buddy(e4b);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_unload_buddy_test);
+
+void mb_free_blocks_test(struct inode *inode, struct ext4_buddy *e4b,
+			 int first, int count)
+{
+	mb_free_blocks(inode, e4b, first, count);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_free_blocks_test);
+
+void ext4_free_blocks_simple_test(struct inode *inode, ext4_fsblk_t block,
+				  unsigned long count)
+{
+	return ext4_free_blocks_simple(inode, block, count);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_blocks_simple_test);
+
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_wait_block_bitmap);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_init);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_desc);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_count_free_clusters);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_info);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_group_clusters_set);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_release);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_read_block_bitmap_nowait);
+EXPORT_SYMBOL_FOR_EXT4_TEST(mb_set_bits);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_fc_init_inode);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_context);
 #endif
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 15a049f05d04..39333ce72cbd 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -270,4 +270,34 @@ ext4_mballoc_query_range(
 	ext4_mballoc_query_range_fn	formatter,
 	void				*priv);
 
+extern int ext4_mb_mark_context(handle_t *handle,
+		struct super_block *sb, bool state,
+		ext4_group_t group, ext4_grpblk_t blkoff,
+		ext4_grpblk_t len, int flags,
+		ext4_grpblk_t *ret_changed);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern void mb_clear_bits_test(void *bm, int cur, int len);
+extern ext4_fsblk_t
+ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar,
+			       int *errp);
+extern int mb_find_next_zero_bit_test(void *addr, int max, int start);
+extern int mb_find_next_bit_test(void *addr, int max, int start);
+extern void mb_clear_bit_test(int bit, void *addr);
+extern int mb_test_bit_test(int bit, void *addr);
+extern int
+ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac,
+				 handle_t *handle);
+extern int mb_mark_used_test(struct ext4_buddy *e4b,
+			     struct ext4_free_extent *ex);
+extern void ext4_mb_generate_buddy_test(struct super_block *sb,
+		void *buddy, void *bitmap, ext4_group_t group,
+		struct ext4_group_info *grp);
+extern int ext4_mb_load_buddy_test(struct super_block *sb,
+		ext4_group_t group, struct ext4_buddy *e4b);
+extern void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b);
+extern void mb_free_blocks_test(struct inode *inode,
+		struct ext4_buddy *e4b, int first, int count);
+extern void ext4_free_blocks_simple_test(struct inode *inode,
+		ext4_fsblk_t block, unsigned long count);
+#endif
 #endif
-- 
cgit v1.2.3


From 9e1b14320b154094bb2c1bee6d8c6cb851fc3215 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Sat, 14 Mar 2026 15:52:58 +0800
Subject: ext4: fix extents-test.c is not compiled when EXT4_KUNIT_TESTS=M

Now, only EXT4_KUNIT_TESTS=Y testcase will be compiled in 'extents.c'.
To solve this issue, the ext4 test code needs to be decoupled. The
'extents-test' module is compiled into 'ext4-test' module.

Fixes: cb1e0c1d1fad ("ext4: kunit tests for extent splitting and conversion")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260314075258.1317579-4-yebin@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/Makefile       |  3 ++-
 fs/ext4/ext4_extents.h | 12 ++++++++++++
 fs/ext4/extents-test.c |  8 ++++----
 fs/ext4/extents.c      | 39 +++++++++++++++++++++++++++++++++------
 4 files changed, 51 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index d836c3fe311b..3baee4e7c1cf 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -14,7 +14,8 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
-ext4-test-objs				+= inode-test.o mballoc-test.o
+ext4-test-objs				+= inode-test.o mballoc-test.o \
+					   extents-test.o
 obj-$(CONFIG_EXT4_KUNIT_TESTS)		+= ext4-test.o
 ext4-$(CONFIG_FS_VERITY)		+= verity.o
 ext4-$(CONFIG_FS_ENCRYPTION)		+= crypto.o
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index c484125d963f..ebaf7cc42430 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -264,5 +264,17 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
 				     0xffff);
 }
 
+extern int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path);
+extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern int ext4_ext_space_root_idx_test(struct inode *inode, int check);
+extern struct ext4_ext_path *ext4_split_convert_extents_test(
+				handle_t *handle, struct inode *inode,
+				struct ext4_map_blocks *map,
+				struct ext4_ext_path *path,
+				int flags, unsigned int *allocated);
+#endif
 #endif /* _EXT4_EXTENTS */
 
diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c
index a6b3e6b592a5..5496b2c8e2cd 100644
--- a/fs/ext4/extents-test.c
+++ b/fs/ext4/extents-test.c
@@ -282,8 +282,8 @@ static int extents_kunit_init(struct kunit *test)
 	eh->eh_depth = 0;
 	eh->eh_entries = cpu_to_le16(1);
 	eh->eh_magic = EXT4_EXT_MAGIC;
-	eh->eh_max =
-		cpu_to_le16(ext4_ext_space_root_idx(&k_ctx.k_ei->vfs_inode, 0));
+	eh->eh_max = cpu_to_le16(ext4_ext_space_root_idx_test(
+					&k_ctx.k_ei->vfs_inode, 0));
 	eh->eh_generation = 0;
 
 	/*
@@ -386,8 +386,8 @@ static void test_split_convert(struct kunit *test)
 
 	switch (param->type) {
 	case TEST_SPLIT_CONVERT:
-		path = ext4_split_convert_extents(NULL, inode, &map, path,
-						  param->split_flags, NULL);
+		path = ext4_split_convert_extents_test(NULL, inode, &map,
+					path, param->split_flags, NULL);
 		break;
 	case TEST_CREATE_BLOCKS:
 		ext4_map_create_blocks_helper(test, inode, &map, param->split_flags);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 8744d3845577..da78eb23aaa6 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -184,9 +184,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
  *  - ENOMEM
  *  - EIO
  */
-static int __ext4_ext_dirty(const char *where, unsigned int line,
-			    handle_t *handle, struct inode *inode,
-			    struct ext4_ext_path *path)
+int __ext4_ext_dirty(const char *where, unsigned int line,
+		     handle_t *handle, struct inode *inode,
+		     struct ext4_ext_path *path)
 {
 	int err;
 
@@ -3159,7 +3159,7 @@ static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
 }
 
 /* FIXME!! we need to try to merge to left or right after zero-out  */
-static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
+int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 {
 	ext4_fsblk_t ee_pblock;
 	unsigned int ee_len;
@@ -6257,6 +6257,33 @@ out:
 	return 0;
 }
 
-#ifdef CONFIG_EXT4_KUNIT_TESTS
-#include "extents-test.c"
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+int ext4_ext_space_root_idx_test(struct inode *inode, int check)
+{
+	return ext4_ext_space_root_idx(inode, check);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_space_root_idx_test);
+
+struct ext4_ext_path *ext4_split_convert_extents_test(handle_t *handle,
+			struct inode *inode, struct ext4_map_blocks *map,
+			struct ext4_ext_path *path, int flags,
+			unsigned int *allocated)
+{
+	return ext4_split_convert_extents(handle, inode, map, path,
+					  flags, allocated);
+}
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_split_convert_extents_test);
+
+EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_insert_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_insert_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_find_extent);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_issue_zeroout);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_query_blocks);
 #endif
-- 
cgit v1.2.3


From 3822743dc20386d9897e999dbb990befa3a5b3f8 Mon Sep 17 00:00:00 2001
From: Helen Koike <koike@igalia.com>
Date: Tue, 17 Mar 2026 11:23:10 -0300
Subject: ext4: reject mount if bigalloc with s_first_data_block != 0

bigalloc with s_first_data_block != 0 is not supported, reject mounting
it.

Signed-off-by: Helen Koike <koike@igalia.com>
Suggested-by: Theodore Ts'o <tytso@mit.edu>
Reported-by: syzbot+b73703b873a33d8eb8f6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b73703b873a33d8eb8f6
Link: https://patch.msgid.link/20260317142325.135074-1-koike@igalia.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/super.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 43f680c750ae..152c58fe8e01 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3633,6 +3633,13 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly)
 			 "extents feature\n");
 		return 0;
 	}
+	if (ext4_has_feature_bigalloc(sb) &&
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+		ext4_msg(sb, KERN_WARNING,
+			 "bad geometry: bigalloc file system with non-zero "
+			 "first_data_block\n");
+		return 0;
+	}
 
 #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
 	if (!readonly && (ext4_has_feature_quota(sb) ||
-- 
cgit v1.2.3


From 496bb99b7e66f48b178126626f47e9ba79e2d0fa Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@linux.dev>
Date: Thu, 19 Mar 2026 17:45:45 +0800
Subject: ext4: fix the might_sleep() warnings in kvfree()

Use the kvfree() in the RCU read critical section can trigger
the following warnings:

EXT4-fs (vdb): unmounting filesystem cd983e5b-3c83-4f5a-a136-17b00eb9d018.

WARNING: suspicious RCU usage

./include/linux/rcupdate.h:409 Illegal context switch in RCU read-side critical section!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1

Call Trace:
 <TASK>
 dump_stack_lvl+0xbb/0xd0
 dump_stack+0x14/0x20
 lockdep_rcu_suspicious+0x15a/0x1b0
 __might_resched+0x375/0x4d0
 ? put_object.part.0+0x2c/0x50
 __might_sleep+0x108/0x160
 vfree+0x58/0x910
 ? ext4_group_desc_free+0x27/0x270
 kvfree+0x23/0x40
 ext4_group_desc_free+0x111/0x270
 ext4_put_super+0x3c8/0xd40
 generic_shutdown_super+0x14c/0x4a0
 ? __pfx_shrinker_free+0x10/0x10
 kill_block_super+0x40/0x90
 ext4_kill_sb+0x6d/0xb0
 deactivate_locked_super+0xb4/0x180
 deactivate_super+0x7e/0xa0
 cleanup_mnt+0x296/0x3e0
 __cleanup_mnt+0x16/0x20
 task_work_run+0x157/0x250
 ? __pfx_task_work_run+0x10/0x10
 ? exit_to_user_mode_loop+0x6a/0x550
 exit_to_user_mode_loop+0x102/0x550
 do_syscall_64+0x44a/0x500
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

BUG: sleeping function called from invalid context at mm/vmalloc.c:3441
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 556, name: umount
preempt_count: 1, expected: 0
CPU: 3 UID: 0 PID: 556 Comm: umount
Call Trace:
 <TASK>
 dump_stack_lvl+0xbb/0xd0
 dump_stack+0x14/0x20
 __might_resched+0x275/0x4d0
 ? put_object.part.0+0x2c/0x50
 __might_sleep+0x108/0x160
 vfree+0x58/0x910
 ? ext4_group_desc_free+0x27/0x270
 kvfree+0x23/0x40
 ext4_group_desc_free+0x111/0x270
 ext4_put_super+0x3c8/0xd40
 generic_shutdown_super+0x14c/0x4a0
 ? __pfx_shrinker_free+0x10/0x10
 kill_block_super+0x40/0x90
 ext4_kill_sb+0x6d/0xb0
 deactivate_locked_super+0xb4/0x180
 deactivate_super+0x7e/0xa0
 cleanup_mnt+0x296/0x3e0
 __cleanup_mnt+0x16/0x20
 task_work_run+0x157/0x250
 ? __pfx_task_work_run+0x10/0x10
 ? exit_to_user_mode_loop+0x6a/0x550
 exit_to_user_mode_loop+0x102/0x550
 do_syscall_64+0x44a/0x500
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The above scenarios occur in initialization failures and teardown
paths, there are no parallel operations on the resources released
by kvfree(), this commit therefore remove rcu_read_lock/unlock() and
use rcu_access_pointer() instead of rcu_dereference() operations.

Fixes: 7c990728b99e ("ext4: fix potential race between s_flex_groups online resizing and access")
Fixes: df3da4ea5a0f ("ext4: fix potential race between s_group_info online resizing and access")
Signed-off-by: Zqiang <qiang.zhang@linux.dev>
Reviewed-by: Baokun Li <libaokun@linux.alibaba.com>
Link: https://patch.msgid.link/20260319094545.19291-1-qiang.zhang@linux.dev
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/mballoc.c | 10 +++-------
 fs/ext4/super.c   |  8 ++------
 2 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 93d37f6cf9c3..bb6faebf9b6d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3584,9 +3584,7 @@ err_freebuddy:
 	rcu_read_unlock();
 	iput(sbi->s_buddy_cache);
 err_freesgi:
-	rcu_read_lock();
-	kvfree(rcu_dereference(sbi->s_group_info));
-	rcu_read_unlock();
+	kvfree(rcu_access_pointer(sbi->s_group_info));
 	return -ENOMEM;
 }
 
@@ -3901,7 +3899,8 @@ void ext4_mb_release(struct super_block *sb)
 		WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
 	}
 
-	if (sbi->s_group_info) {
+	group_info = rcu_access_pointer(sbi->s_group_info);
+	if (group_info) {
 		for (i = 0; i < ngroups; i++) {
 			cond_resched();
 			grinfo = ext4_get_group_info(sb, i);
@@ -3919,12 +3918,9 @@ void ext4_mb_release(struct super_block *sb)
 		num_meta_group_infos = (ngroups +
 				EXT4_DESC_PER_BLOCK(sb) - 1) >>
 			EXT4_DESC_PER_BLOCK_BITS(sb);
-		rcu_read_lock();
-		group_info = rcu_dereference(sbi->s_group_info);
 		for (i = 0; i < num_meta_group_infos; i++)
 			kfree(group_info[i]);
 		kvfree(group_info);
-		rcu_read_unlock();
 	}
 	ext4_mb_avg_fragment_size_destroy(sbi);
 	ext4_mb_largest_free_orders_destroy(sbi);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 152c58fe8e01..baa067eb8cf4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1254,12 +1254,10 @@ static void ext4_group_desc_free(struct ext4_sb_info *sbi)
 	struct buffer_head **group_desc;
 	int i;
 
-	rcu_read_lock();
-	group_desc = rcu_dereference(sbi->s_group_desc);
+	group_desc = rcu_access_pointer(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(group_desc[i]);
 	kvfree(group_desc);
-	rcu_read_unlock();
 }
 
 static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
@@ -1267,14 +1265,12 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
 	struct flex_groups **flex_groups;
 	int i;
 
-	rcu_read_lock();
-	flex_groups = rcu_dereference(sbi->s_flex_groups);
+	flex_groups = rcu_access_pointer(sbi->s_flex_groups);
 	if (flex_groups) {
 		for (i = 0; i < sbi->s_flex_groups_allocated; i++)
 			kvfree(flex_groups[i]);
 		kvfree(flex_groups);
 	}
-	rcu_read_unlock();
 }
 
 static void ext4_put_super(struct super_block *sb)
-- 
cgit v1.2.3


From a01aee7cafc575bb82f5529e8734e7052f9b16ea Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Thu, 26 Mar 2026 03:44:39 +0000
Subject: bridge: br_nd_send: linearize skb before parsing ND options

br_nd_send() parses neighbour discovery options from ns->opt[] and
assumes that these options are in the linear part of request.

Its callers only guarantee that the ICMPv6 header and target address
are available, so the option area can still be non-linear. Parsing
ns->opt[] in that case can access data past the linear buffer.

Linearize request before option parsing and derive ns from the linear
network header.

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Tested-by: Ao Zhou <n05ec@lzu.edu.cn>
Co-developed-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260326034441.2037420-2-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_arp_nd_proxy.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 1e2b51769eec..af3d1e33f50b 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -251,12 +251,12 @@ struct nd_msg *br_is_nd_neigh_msg(const struct sk_buff *skb, struct nd_msg *msg)
 
 static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 		       struct sk_buff *request, struct neighbour *n,
-		       __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns)
+		       __be16 vlan_proto, u16 vlan_tci)
 {
 	struct net_device *dev = request->dev;
 	struct net_bridge_vlan_group *vg;
+	struct nd_msg *na, *ns;
 	struct sk_buff *reply;
-	struct nd_msg *na;
 	struct ipv6hdr *pip6;
 	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
 	int ns_olen;
@@ -264,7 +264,7 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	u8 *daddr;
 	u16 pvid;
 
-	if (!dev)
+	if (!dev || skb_linearize(request))
 		return;
 
 	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
@@ -281,6 +281,8 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	skb_set_mac_header(reply, 0);
 
 	daddr = eth_hdr(request)->h_source;
+	ns = (struct nd_msg *)(skb_network_header(request) +
+			       sizeof(struct ipv6hdr));
 
 	/* Do we need option processing ? */
 	ns_olen = request->len - (skb_network_offset(request) +
@@ -472,9 +474,9 @@ void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br,
 				if (vid != 0)
 					br_nd_send(br, p, skb, n,
 						   skb->vlan_proto,
-						   skb_vlan_tag_get(skb), msg);
+						   skb_vlan_tag_get(skb));
 				else
-					br_nd_send(br, p, skb, n, 0, 0, msg);
+					br_nd_send(br, p, skb, n, 0, 0);
 				replied = true;
 			}
 
-- 
cgit v1.2.3


From 850837965af15707fd3142c1cf3c5bfaf022299b Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Thu, 26 Mar 2026 03:44:40 +0000
Subject: bridge: br_nd_send: validate ND option lengths

br_nd_send() walks ND options according to option-provided lengths.
A malformed option can make the parser advance beyond the computed
option span or use a too-short source LLADDR option payload.

Validate option lengths against the remaining NS option area before
advancing, and only read source LLADDR when the option is large enough
for an Ethernet address.

Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports")
Cc: stable@vger.kernel.org
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Tested-by: Ao Zhou <n05ec@lzu.edu.cn>
Co-developed-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260326034441.2037420-3-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_arp_nd_proxy.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index af3d1e33f50b..6b5595868a39 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -288,12 +288,14 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p,
 	ns_olen = request->len - (skb_network_offset(request) +
 				  sizeof(struct ipv6hdr)) - sizeof(*ns);
 	for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) {
-		if (!ns->opt[i + 1]) {
+		if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) {
 			kfree_skb(reply);
 			return;
 		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
-			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			if ((ns->opt[i + 1] << 3) >=
+			    sizeof(struct nd_opt_hdr) + ETH_ALEN)
+				daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
 		}
 	}
-- 
cgit v1.2.3


From afa9a05e6c4971bd5586f1b304e14d61fb3d9385 Mon Sep 17 00:00:00 2001
From: Yang Yang <n05ec@lzu.edu.cn>
Date: Thu, 26 Mar 2026 03:44:41 +0000
Subject: vxlan: validate ND option lengths in vxlan_na_create

vxlan_na_create() walks ND options according to option-provided
lengths. A malformed option can make the parser advance beyond the
computed option span or use a too-short source LLADDR option payload.

Validate option lengths against the remaining NS option area before
advancing, and only read source LLADDR when the option is large enough
for an Ethernet address.

Fixes: 4b29dba9c085 ("vxlan: fix nonfunctional neigh_reduce()")
Cc: stable@vger.kernel.org
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Tested-by: Ao Zhou <n05ec@lzu.edu.cn>
Co-developed-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260326034441.2037420-4-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 17c941aac32d..a94ac82a6136 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1965,12 +1965,14 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
-		if (!ns->opt[i + 1]) {
+		if (!ns->opt[i + 1] || i + (ns->opt[i + 1] << 3) > ns_olen) {
 			kfree_skb(reply);
 			return NULL;
 		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
-			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+			if ((ns->opt[i + 1] << 3) >=
+			    sizeof(struct nd_opt_hdr) + ETH_ALEN)
+				daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
 		}
 	}
-- 
cgit v1.2.3


From d15e4b0a418537aafa56b2cb80d44add83e83697 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@shopee.com>
Date: Thu, 19 Mar 2026 20:03:35 +0800
Subject: ext4: fix use-after-free in update_super_work when racing with umount

Commit b98535d09179 ("ext4: fix bug_on in start_this_handle during umount
filesystem") moved ext4_unregister_sysfs() before flushing s_sb_upd_work
to prevent new error work from being queued via /proc/fs/ext4/xx/mb_groups
reads during unmount. However, this introduced a use-after-free because
update_super_work calls ext4_notify_error_sysfs() -> sysfs_notify() which
accesses the kobject's kernfs_node after it has been freed by kobject_del()
in ext4_unregister_sysfs():

  update_super_work                ext4_put_super
  -----------------                --------------
                                   ext4_unregister_sysfs(sb)
                                     kobject_del(&sbi->s_kobj)
                                       __kobject_del()
                                         sysfs_remove_dir()
                                           kobj->sd = NULL
                                         sysfs_put(sd)
                                           kernfs_put()  // RCU free
  ext4_notify_error_sysfs(sbi)
    sysfs_notify(&sbi->s_kobj)
      kn = kobj->sd              // stale pointer
      kernfs_get(kn)             // UAF on freed kernfs_node
                                   ext4_journal_destroy()
                                     flush_work(&sbi->s_sb_upd_work)

Instead of reordering the teardown sequence, fix this by making
ext4_notify_error_sysfs() detect that sysfs has already been torn down
by checking s_kobj.state_in_sysfs, and skipping the sysfs_notify() call
in that case. A dedicated mutex (s_error_notify_mutex) serializes
ext4_notify_error_sysfs() against kobject_del() in ext4_unregister_sysfs()
to prevent TOCTOU races where the kobject could be deleted between the
state_in_sysfs check and the sysfs_notify() call.

Fixes: b98535d09179 ("ext4: fix bug_on in start_this_handle during umount filesystem")
Cc: Jiayuan Chen <jiayuan.chen@linux.dev>
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jiayuan Chen <jiayuan.chen@shopee.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260319120336.157873-1-jiayuan.chen@linux.dev
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/ext4.h  |  1 +
 fs/ext4/super.c |  1 +
 fs/ext4/sysfs.c | 10 +++++++++-
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c579f68b3c11..7617e2d454ea 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1570,6 +1570,7 @@ struct ext4_sb_info {
 	struct proc_dir_entry *s_proc;
 	struct kobject s_kobj;
 	struct completion s_kobj_unregister;
+	struct mutex s_error_notify_mutex; /* protects sysfs_notify vs kobject_del */
 	struct super_block *s_sb;
 	struct buffer_head *s_mmp_bh;
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index baa067eb8cf4..cb69a9b38b7c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5406,6 +5406,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 	spin_lock_init(&sbi->s_error_lock);
+	mutex_init(&sbi->s_error_notify_mutex);
 	INIT_WORK(&sbi->s_sb_upd_work, update_super_work);
 
 	err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed);
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index b87d7bdab06a..923b375e017f 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -597,7 +597,10 @@ static const struct kobj_type ext4_feat_ktype = {
 
 void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
 {
-	sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+	mutex_lock(&sbi->s_error_notify_mutex);
+	if (sbi->s_kobj.state_in_sysfs)
+		sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+	mutex_unlock(&sbi->s_error_notify_mutex);
 }
 
 static struct kobject *ext4_root;
@@ -610,8 +613,10 @@ int ext4_register_sysfs(struct super_block *sb)
 	int err;
 
 	init_completion(&sbi->s_kobj_unregister);
+	mutex_lock(&sbi->s_error_notify_mutex);
 	err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root,
 				   "%s", sb->s_id);
+	mutex_unlock(&sbi->s_error_notify_mutex);
 	if (err) {
 		kobject_put(&sbi->s_kobj);
 		wait_for_completion(&sbi->s_kobj_unregister);
@@ -644,7 +649,10 @@ void ext4_unregister_sysfs(struct super_block *sb)
 
 	if (sbi->s_proc)
 		remove_proc_subtree(sb->s_id, ext4_proc_root);
+
+	mutex_lock(&sbi->s_error_notify_mutex);
 	kobject_del(&sbi->s_kobj);
+	mutex_unlock(&sbi->s_error_notify_mutex);
 }
 
 int __init ext4_init_sysfs(void)
-- 
cgit v1.2.3


From 0c90eed1b95335eba4f546e6742a8e4503d79349 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 20 Mar 2026 10:04:29 +0100
Subject: ext4: fix deadlock on inode reallocation

Currently there is a race in ext4 when reallocating freed inode
resulting in a deadlock:

Task1					Task2
ext4_evict_inode()
  handle = ext4_journal_start();
  ...
  if (IS_SYNC(inode))
    handle->h_sync = 1;
  ext4_free_inode()
					ext4_new_inode()
					  handle = ext4_journal_start()
					  finds the bit in inode bitmap
					    already clear
					  insert_inode_locked()
					    waits for inode to be
					      removed from the hash.
  ext4_journal_stop(handle)
    jbd2_journal_stop(handle)
      jbd2_log_wait_commit(journal, tid);
        - deadlocks waiting for transaction handle Task2 holds

Fix the problem by removing inode from the hash already in
ext4_clear_inode() by which time all IO for the inode is done so reuse
is already fine but we are still before possibly blocking on transaction
commit.

Reported-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Link: https://lore.kernel.org/all/abNvb2PcrKj1FBeC@ly-workstation
Fixes: 88ec797c4680 ("fs: make insert_inode_locked() wait for inode destruction")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260320090428.24899-2-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/super.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cb69a9b38b7c..a34efb44e73d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1523,6 +1523,27 @@ void ext4_clear_inode(struct inode *inode)
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
+	/*
+	 * We must remove the inode from the hash before ext4_free_inode()
+	 * clears the bit in inode bitmap as otherwise another process reusing
+	 * the inode will block in insert_inode_hash() waiting for inode
+	 * eviction to complete while holding transaction handle open, but
+	 * ext4_evict_inode() still running for that inode could block waiting
+	 * for transaction commit if the inode is marked as IS_SYNC => deadlock.
+	 *
+	 * Removing the inode from the hash here is safe. There are two cases
+	 * to consider:
+	 * 1) The inode still has references to it (i_nlink > 0). In that case
+	 * we are keeping the inode and once we remove the inode from the hash,
+	 * iget() can create the new inode structure for the same inode number
+	 * and we are fine with that as all IO on behalf of the inode is
+	 * finished.
+	 * 2) We are deleting the inode (i_nlink == 0). In that case inode
+	 * number cannot be reused until ext4_free_inode() clears the bit in
+	 * the inode bitmap, at which point all IO is done and reuse is fine
+	 * again.
+	 */
+	remove_inode_hash(inode);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
-- 
cgit v1.2.3


From ec0a7500d8eace5b4f305fa0c594dd148f0e8d29 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun@linux.alibaba.com>
Date: Mon, 23 Mar 2026 14:08:36 +0800
Subject: ext4: fix iloc.bh leak in ext4_fc_replay_inode() error paths

During code review, Joseph found that ext4_fc_replay_inode() calls
ext4_get_fc_inode_loc() to get the inode location, which holds a
reference to iloc.bh that must be released via brelse().

However, several error paths jump to the 'out' label without
releasing iloc.bh:

 - ext4_handle_dirty_metadata() failure
 - sync_dirty_buffer() failure
 - ext4_mark_inode_used() failure
 - ext4_iget() failure

Fix this by introducing an 'out_brelse' label placed just before
the existing 'out' label to ensure iloc.bh is always released.

Additionally, make ext4_fc_replay_inode() propagate errors
properly instead of always returning 0.

Reported-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Fixes: 8016e29f4362 ("ext4: fast commit recovery path")
Signed-off-by: Baokun Li <libaokun@linux.alibaba.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260323060836.3452660-1-libaokun@linux.alibaba.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/fast_commit.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 6e949c21842d..2f0057e04934 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1613,19 +1613,21 @@ static int ext4_fc_replay_inode(struct super_block *sb,
 	/* Immediately update the inode on disk. */
 	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
 	if (ret)
-		goto out;
+		goto out_brelse;
 	ret = sync_dirty_buffer(iloc.bh);
 	if (ret)
-		goto out;
+		goto out_brelse;
 	ret = ext4_mark_inode_used(sb, ino);
 	if (ret)
-		goto out;
+		goto out_brelse;
 
 	/* Given that we just wrote the inode on disk, this SHOULD succeed. */
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
 	if (IS_ERR(inode)) {
 		ext4_debug("Inode not found.");
-		return -EFSCORRUPTED;
+		inode = NULL;
+		ret = -EFSCORRUPTED;
+		goto out_brelse;
 	}
 
 	/*
@@ -1642,13 +1644,14 @@ static int ext4_fc_replay_inode(struct super_block *sb,
 	ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode));
 	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
 	sync_dirty_buffer(iloc.bh);
+out_brelse:
 	brelse(iloc.bh);
 out:
 	iput(inode);
 	if (!ret)
 		blkdev_issue_flush(sb->s_bdev);
 
-	return 0;
+	return ret;
 }
 
 /*
-- 
cgit v1.2.3


From 3ceda17325fc2600f66fd85b526592bc8a9dfb9d Mon Sep 17 00:00:00 2001
From: hongao <hongao@uniontech.com>
Date: Tue, 24 Mar 2026 09:58:15 +0800
Subject: ext4: skip split extent recovery on corruption

ext4_split_extent_at() retries after ext4_ext_insert_extent() fails by
refinding the original extent and restoring its length. That recovery is
only safe for transient resource failures such as -ENOSPC, -EDQUOT, and
-ENOMEM.

When ext4_ext_insert_extent() fails because the extent tree is already
corrupted, ext4_find_extent() can return a leaf path without p_ext.
ext4_split_extent_at() then dereferences path[depth].p_ext while trying to
fix up the original extent length, causing a NULL pointer dereference while
handling a pre-existing filesystem corruption.

Do not enter the recovery path for corruption errors, and validate p_ext
after refinding the extent before touching it. This keeps the recovery path
limited to cases it can actually repair and turns the syzbot-triggered crash
into a proper corruption report.

Fixes: 716b9c23b862 ("ext4: refactor split and convert extents")
Reported-by: syzbot+1ffa5d865557e51cb604@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1ffa5d865557e51cb604
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Signed-off-by: hongao <hongao@uniontech.com>
Link: https://patch.msgid.link/EF77870F23FF9C90+20260324015815.35248-1-hongao@uniontech.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/extents.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index da78eb23aaa6..8cce1479be6d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3254,6 +3254,9 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle,
 
 	insert_err = PTR_ERR(path);
 	err = 0;
+	if (insert_err != -ENOSPC && insert_err != -EDQUOT &&
+	    insert_err != -ENOMEM)
+		goto out_path;
 
 	/*
 	 * Get a new path to try to zeroout or fix the extent length.
@@ -3270,13 +3273,20 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle,
 		goto out_path;
 	}
 
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	if (!ex) {
+		EXT4_ERROR_INODE(inode,
+				 "bad extent address lblock: %lu, depth: %d pblock %llu",
+				 (unsigned long)ee_block, depth, path[depth].p_block);
+		err = -EFSCORRUPTED;
+		goto out;
+	}
+
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
 
-	depth = ext_depth(inode);
-	ex = path[depth].p_ext;
-
 fix_extent_len:
 	ex->ee_len = orig_ex.ee_len;
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-- 
cgit v1.2.3


From bb81702370fad22c06ca12b6e1648754dbc37e0f Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 26 Mar 2026 00:58:34 -0400
Subject: ext4: handle wraparound when searching for blocks for indirect mapped
 blocks

Commit 4865c768b563 ("ext4: always allocate blocks only from groups
inode can use") restricts what blocks will be allocated for indirect
block based files to block numbers that fit within 32-bit block
numbers.

However, when using a review bot running on the latest Gemini LLM to
check this commit when backporting into an LTS based kernel, it raised
this concern:

   If ac->ac_g_ex.fe_group is >= ngroups (for instance, if the goal
   group was populated via stream allocation from s_mb_last_groups),
   then start will be >= ngroups.

   Does this allow allocating blocks beyond the 32-bit limit for
   indirect block mapped files? The commit message mentions that
   ext4_mb_scan_groups_linear() takes care to not select unsupported
   groups. However, its loop uses group = *start, and the very first
   iteration will call ext4_mb_scan_group() with this unsupported
   group because next_linear_group() is only called at the end of the
   iteration.

After reviewing the code paths involved and considering the LLM
review, I determined that this can happen when there is a file system
where some files/directories are extent-mapped and others are
indirect-block mapped.  To address this, add a safety clamp in
ext4_mb_scan_groups().

Fixes: 4865c768b563 ("ext4: always allocate blocks only from groups inode can use")
Cc: Jan Kara <jack@suse.cz>
Reviewed-by: Baokun Li <libaokun@linux.alibaba.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Link: https://patch.msgid.link/20260326045834.1175822-1-tytso@mit.edu
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/mballoc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index bb6faebf9b6d..cb2bd87c355c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1199,6 +1199,8 @@ static int ext4_mb_scan_groups(struct ext4_allocation_context *ac)
 
 	/* searching for the right group start from the goal value specified */
 	start = ac->ac_g_ex.fe_group;
+	if (start >= ngroups)
+		start = 0;
 	ac->ac_prefetch_grp = start;
 	ac->ac_prefetch_nr = 0;
 
-- 
cgit v1.2.3


From 9ee29d20aab228adfb02ca93f87fb53c56c2f3af Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Fri, 27 Mar 2026 02:13:15 -0400
Subject: ext4: always drain queued discard work in ext4_mb_release()

While reviewing recent ext4 patch[1], Sashiko raised the following
concern[2]:

> If the filesystem is initially mounted with the discard option,
> deleting files will populate sbi->s_discard_list and queue
> s_discard_work. If it is then remounted with nodiscard, the
> EXT4_MOUNT_DISCARD flag is cleared, but the pending s_discard_work is
> neither cancelled nor flushed.

[1] https://lore.kernel.org/r/20260319094545.19291-1-qiang.zhang@linux.dev/
[2] https://sashiko.dev/#/patchset/20260319094545.19291-1-qiang.zhang%40linux.dev

The concern was valid, but it had nothing to do with the patch[1].
One of the problems with Sashiko in its current (early) form is that
it will detect pre-existing issues and report it as a problem with the
patch that it is reviewing.

In practice, it would be hard to hit deliberately (unless you are a
malicious syzkaller fuzzer), since it would involve mounting the file
system with -o discard, and then deleting a large number of files,
remounting the file system with -o nodiscard, and then immediately
unmounting the file system before the queued discard work has a change
to drain on its own.

Fix it because it's a real bug, and to avoid Sashiko from raising this
concern when analyzing future patches to mballoc.c.

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Fixes: 55cdd0af2bc5 ("ext4: get discard out of jbd2 commit kthread contex")
Cc: stable@kernel.org
---
 fs/ext4/mballoc.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cb2bd87c355c..bb58eafb87bc 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3893,13 +3893,11 @@ void ext4_mb_release(struct super_block *sb)
 	struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits);
 	int count;
 
-	if (test_opt(sb, DISCARD)) {
-		/*
-		 * wait the discard work to drain all of ext4_free_data
-		 */
-		flush_work(&sbi->s_discard_work);
-		WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
-	}
+	/*
+	 * wait the discard work to drain all of ext4_free_data
+	 */
+	flush_work(&sbi->s_discard_work);
+	WARN_ON_ONCE(!list_empty(&sbi->s_discard_list));
 
 	group_info = rcu_access_pointer(sbi->s_group_info);
 	if (group_info) {
-- 
cgit v1.2.3


From 4576100b8cd03118267513cafacde164b498b322 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Thu, 26 Mar 2026 13:43:09 -0700
Subject: net/sched: sch_hfsc: fix divide-by-zero in rtsc_min()

m2sm() converts a u32 slope to a u64 scaled value.  For large inputs
(e.g. m1=4000000000), the result can reach 2^32.  rtsc_min() stores
the difference of two such u64 values in a u32 variable `dsm` and
uses it as a divisor.  When the difference is exactly 2^32 the
truncation yields zero, causing a divide-by-zero oops in the
concave-curve intersection path:

  Oops: divide error: 0000
  RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601)
  Call Trace:
   init_ed (net/sched/sch_hfsc.c:629)
   hfsc_enqueue (net/sched/sch_hfsc.c:1569)
   [...]

Widen `dsm` to u64 and replace do_div() with div64_u64() so the full
difference is preserved.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260326204310.1549327-1-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_hfsc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index b5657ffbbf84..83b2ca2e37fc 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -555,7 +555,7 @@ static void
 rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y)
 {
 	u64 y1, y2, dx, dy;
-	u32 dsm;
+	u64 dsm;
 
 	if (isc->sm1 <= isc->sm2) {
 		/* service curve is convex */
@@ -598,7 +598,7 @@ rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y)
 	 */
 	dx = (y1 - y) << SM_SHIFT;
 	dsm = isc->sm1 - isc->sm2;
-	do_div(dx, dsm);
+	dx = div64_u64(dx, dsm);
 	/*
 	 * check if (x, y1) belongs to the 1st segment of rtsc.
 	 * if so, add the offset.
-- 
cgit v1.2.3


From 5d17af9eb2dd3de6846ed344c883de7812e6cc09 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Thu, 26 Mar 2026 13:43:10 -0700
Subject: selftests/tc-testing: add test for HFSC divide-by-zero in rtsc_min()

Add a regression test for the divide-by-zero in rtsc_min() triggered
when m2sm() converts a large m1 value (e.g. 32gbit) to a u64 scaled
slope reaching 2^32. rtsc_min() stores the difference of two such u64
values (sm1 - sm2) in a u32 variable `dsm`, truncating 2^32 to zero
and causing a divide-by-zero oops in the concave-curve intersection
path. The test configures an HFSC class with m1=32gbit d=1ms m2=0bit,
sends a packet to activate the class, waits for it to drain and go
idle, then sends another packet to trigger reactivation through
rtsc_min().

Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260326204310.1549327-2-xmei5@asu.edu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/infra/qdiscs.json          | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 6a39640aa2a8..1e5efb2a31eb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -1111,5 +1111,30 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1:"
         ]
+    },
+    {
+        "id": "a3d7",
+        "name": "HFSC with large m1 - no divide-by-zero on class reactivation",
+        "category": [
+            "qdisc",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc replace dev $DUMMY root handle 1: hfsc default 1",
+            "$TC class replace dev $DUMMY parent 1: classid 1:1 hfsc rt m1 32gbit d 1ms m2 0bit ls m1 32gbit d 1ms m2 0bit",
+            "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+            "sleep 1"
+        ],
+        "cmdUnderTest": "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 4c5e7f0fcd592801c9cc18f29f80fbee84eb8669 Mon Sep 17 00:00:00 2001
From: Jinjiang Tu <tujinjiang@huawei.com>
Date: Thu, 19 Mar 2026 09:25:41 +0800
Subject: mm/huge_memory: fix folio isn't locked in softleaf_to_folio()

On arm64 server, we found folio that get from migration entry isn't locked
in softleaf_to_folio().  This issue triggers when mTHP splitting and
zap_nonpresent_ptes() races, and the root cause is lack of memory barrier
in softleaf_to_folio().  The race is as follows:

	CPU0                                             CPU1

deferred_split_scan()                              zap_nonpresent_ptes()
  lock folio
  split_folio()
    unmap_folio()
      change ptes to migration entries
    __split_folio_to_order()                         softleaf_to_folio()
      set flags(including PG_locked) for tail pages    folio = pfn_folio(softleaf_to_pfn(entry))
      smp_wmb()                                        VM_WARN_ON_ONCE(!folio_test_locked(folio))
      prep_compound_page() for tail pages

In __split_folio_to_order(), smp_wmb() guarantees page flags of tail pages
are visible before the tail page becomes non-compound.  smp_wmb() should
be paired with smp_rmb() in softleaf_to_folio(), which is missed.  As a
result, if zap_nonpresent_ptes() accesses migration entry that stores tail
pfn, softleaf_to_folio() may see the updated compound_head of tail page
before page->flags.

This issue will trigger VM_WARN_ON_ONCE() in pfn_swap_entry_folio()
because of the race between folio split and zap_nonpresent_ptes()
leading to a folio incorrectly undergoing modification without a folio
lock being held.

This is a BUG_ON() before commit 93976a20345b ("mm: eliminate further
swapops predicates"), which in merged in v6.19-rc1.

To fix it, add missing smp_rmb() if the softleaf entry is migration entry
in softleaf_to_folio() and softleaf_to_page().

[tujinjiang@huawei.com: update function name and comments]
  Link: https://lkml.kernel.org/r/20260321075214.3305564-1-tujinjiang@huawei.com
Link: https://lkml.kernel.org/r/20260319012541.4158561-1-tujinjiang@huawei.com
Fixes: e9b61f19858a ("thp: reintroduce split_huge_page()")
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Barry Song <baohua@kernel.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/leafops.h | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/include/linux/leafops.h b/include/linux/leafops.h
index a9ff94b744f2..05673d3529e7 100644
--- a/include/linux/leafops.h
+++ b/include/linux/leafops.h
@@ -363,6 +363,23 @@ static inline unsigned long softleaf_to_pfn(softleaf_t entry)
 	return swp_offset(entry) & SWP_PFN_MASK;
 }
 
+static inline void softleaf_migration_sync(softleaf_t entry,
+		struct folio *folio)
+{
+	/*
+	 * Ensure we do not race with split, which might alter tail pages into new
+	 * folios and thus result in observing an unlocked folio.
+	 * This matches the write barrier in __split_folio_to_order().
+	 */
+	smp_rmb();
+
+	/*
+	 * Any use of migration entries may only occur while the
+	 * corresponding page is locked
+	 */
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+}
+
 /**
  * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry.
  * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
@@ -374,11 +391,8 @@ static inline struct page *softleaf_to_page(softleaf_t entry)
 	struct page *page = pfn_to_page(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding page is locked
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, page_folio(page));
 
 	return page;
 }
@@ -394,12 +408,8 @@ static inline struct folio *softleaf_to_folio(softleaf_t entry)
 	struct folio *folio = pfn_folio(softleaf_to_pfn(entry));
 
 	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
-	/*
-	 * Any use of migration entries may only occur while the
-	 * corresponding folio is locked.
-	 */
-	VM_WARN_ON_ONCE(softleaf_is_migration(entry) &&
-			!folio_test_locked(folio));
+	if (softleaf_is_migration(entry))
+		softleaf_migration_sync(entry, folio);
 
 	return folio;
 }
-- 
cgit v1.2.3


From 26d3dca201f3662e51d25022cfce0f642a150a90 Mon Sep 17 00:00:00 2001
From: "Harry Yoo (Oracle)" <harry@kernel.org>
Date: Fri, 20 Mar 2026 21:59:25 +0900
Subject: MAINTAINERS, mailmap: update email address for Harry Yoo

Update my email address to harry@kernel.org.

Link: https://lkml.kernel.org/r/20260320125925.2259998-1-harry@kernel.org
Signed-off-by: Harry Yoo (Oracle) <harry@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/.mailmap b/.mailmap
index 7d14504daf24..2d04aeba68b4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -316,6 +316,7 @@ Hans Verkuil <hverkuil@kernel.org> <hverkuil-cisco@xs4all.nl>
 Hans Verkuil <hverkuil@kernel.org> <hansverk@cisco.com>
 Hao Ge <hao.ge@linux.dev> <gehao@kylinos.cn>
 Harry Yoo <harry.yoo@oracle.com> <42.hyeyoo@gmail.com>
+Harry Yoo <harry@kernel.org> <harry.yoo@oracle.com>
 Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com>
 Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com>
 Heiko Stuebner <heiko@sntech.de> <heiko.stuebner@bqreaders.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 7d10988cbc62..915f074c3577 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16877,7 +16877,7 @@ M:	Lorenzo Stoakes <ljs@kernel.org>
 R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@kernel.org>
-R:	Harry Yoo <harry.yoo@oracle.com>
+R:	Harry Yoo <harry@kernel.org>
 R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -24343,7 +24343,7 @@ F:	drivers/nvmem/layouts/sl28vpd.c
 
 SLAB ALLOCATOR
 M:	Vlastimil Babka <vbabka@kernel.org>
-M:	Harry Yoo <harry.yoo@oracle.com>
+M:	Harry Yoo <harry@kernel.org>
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Hao Li <hao.li@linux.dev>
 R:	Christoph Lameter <cl@gentwo.org>
-- 
cgit v1.2.3


From 9e0d0ddfbc0e3491da7e2db73faa08d8d4f322b2 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alex@ghiti.fr>
Date: Fri, 20 Mar 2026 06:05:59 +0100
Subject: mm/swap: fix swap cache memcg accounting

The swap readahead path was recently refactored and while doing this, the
order between the charging of the folio in the memcg and the addition of
the folio in the swap cache was inverted.

Since the accounting of the folio is done while adding the folio to the
swap cache and the folio is not charged in the memcg yet, the accounting
is then done at the node level, which is wrong.

Fix this by charging the folio in the memcg before adding it to the swap cache.

Link: https://lkml.kernel.org/r/20260320050601.1833108-1-alex@ghiti.fr
Fixes: 2732acda82c9 ("mm, swap: use swap cache as the swap in synchronize layer")
Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
Acked-by: Kairui Song <kasong@tencent.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Chris Li <chrisl@kernel.org>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Baoquan He <bhe@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swap_state.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/mm/swap_state.c b/mm/swap_state.c
index 6d0eef7470be..48aff2c917c0 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -494,6 +494,10 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry,
 
 	__folio_set_locked(folio);
 	__folio_set_swapbacked(folio);
+
+	if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry))
+		goto failed;
+
 	for (;;) {
 		ret = swap_cache_add_folio(folio, entry, &shadow);
 		if (!ret)
@@ -514,11 +518,6 @@ static struct folio *__swap_cache_prepare_and_add(swp_entry_t entry,
 			goto failed;
 	}
 
-	if (!charged && mem_cgroup_swapin_charge_folio(folio, NULL, gfp, entry)) {
-		swap_cache_del_folio(folio);
-		goto failed;
-	}
-
 	memcg1_swapin(entry, folio_nr_pages(folio));
 	if (shadow)
 		workingset_refault(folio, shadow);
-- 
cgit v1.2.3


From 7fe000eb32904758a85e62f6ea9483f89d5dabfc Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Sat, 21 Mar 2026 10:54:24 -0700
Subject: mm/damon/sysfs: fix param_ctx leak on damon_sysfs_new_test_ctx()
 failure

Patch series "mm/damon/sysfs: fix memory leak and NULL dereference
issues", v4.

DAMON_SYSFS can leak memory under allocation failure, and do NULL pointer
dereference when a privileged user make wrong sequences of control.  Fix
those.


This patch (of 3):

When damon_sysfs_new_test_ctx() fails in damon_sysfs_commit_input(),
param_ctx is leaked because the early return skips the cleanup at the out
label.  Destroy param_ctx before returning.

Link: https://lkml.kernel.org/r/20260321175427.86000-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20260321175427.86000-2-sj@kernel.org
Fixes: f0c5118ebb0e ("mm/damon/sysfs: catch commit test ctx alloc failure")
Signed-off-by: Josh Law <objecting@objecting.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 576d1ddd736b..b573b9d60784 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1524,8 +1524,10 @@ static int damon_sysfs_commit_input(void *data)
 	if (IS_ERR(param_ctx))
 		return PTR_ERR(param_ctx);
 	test_ctx = damon_sysfs_new_test_ctx(kdamond->damon_ctx);
-	if (!test_ctx)
+	if (!test_ctx) {
+		damon_destroy_ctx(param_ctx);
 		return -ENOMEM;
+	}
 	err = damon_commit_ctx(test_ctx, param_ctx);
 	if (err)
 		goto out;
-- 
cgit v1.2.3


From 1bfe9fb5ed2667fb075682408b776b5273162615 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Sat, 21 Mar 2026 10:54:25 -0700
Subject: mm/damon/sysfs: check contexts->nr before accessing contexts_arr[0]

Multiple sysfs command paths dereference contexts_arr[0] without first
verifying that kdamond->contexts->nr == 1.  A user can set nr_contexts to
0 via sysfs while DAMON is running, causing NULL pointer dereferences.

In more detail, the issue can be triggered by privileged users like
below.

First, start DAMON and make contexts directory empty
(kdamond->contexts->nr == 0).

    # damo start
    # cd /sys/kernel/mm/damon/admin/kdamonds/0
    # echo 0 > contexts/nr_contexts

Then, each of below commands will cause the NULL pointer dereference.

    # echo update_schemes_stats > state
    # echo update_schemes_tried_regions > state
    # echo update_schemes_tried_bytes > state
    # echo update_schemes_effective_quotas > state
    # echo update_tuned_intervals > state

Guard all commands (except OFF) at the entry point of
damon_sysfs_handle_cmd().

Link: https://lkml.kernel.org/r/20260321175427.86000-3-sj@kernel.org
Fixes: 0ac32b8affb5 ("mm/damon/sysfs: support DAMOS stats")
Signed-off-by: Josh Law <objecting@objecting.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[5.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index b573b9d60784..ddc30586c0e6 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1749,6 +1749,9 @@ static int damon_sysfs_update_schemes_tried_regions(
 static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd,
 		struct damon_sysfs_kdamond *kdamond)
 {
+	if (cmd != DAMON_SYSFS_CMD_OFF && kdamond->contexts->nr != 1)
+		return -EINVAL;
+
 	switch (cmd) {
 	case DAMON_SYSFS_CMD_ON:
 		return damon_sysfs_turn_damon_on(kdamond);
-- 
cgit v1.2.3


From 6557004a8b59c7701e695f02be03c7e20ed1cc15 Mon Sep 17 00:00:00 2001
From: Josh Law <objecting@objecting.org>
Date: Sat, 21 Mar 2026 10:54:26 -0700
Subject: mm/damon/sysfs: check contexts->nr in repeat_call_fn

damon_sysfs_repeat_call_fn() calls damon_sysfs_upd_tuned_intervals(),
damon_sysfs_upd_schemes_stats(), and
damon_sysfs_upd_schemes_effective_quotas() without checking contexts->nr.
If nr_contexts is set to 0 via sysfs while DAMON is running, these
functions dereference contexts_arr[0] and cause a NULL pointer
dereference.  Add the missing check.

For example, the issue can be reproduced using DAMON sysfs interface and
DAMON user-space tool (damo) [1] like below.

    $ sudo damo start --refresh_interval 1s
    $ echo 0 | sudo tee \
            /sys/kernel/mm/damon/admin/kdamonds/0/contexts/nr_contexts

Link: https://patch.msgid.link/20260320163559.178101-3-objecting@objecting.org
Link: https://lkml.kernel.org/r/20260321175427.86000-4-sj@kernel.org
Link: https://github.com/damonitor/damo [1]
Fixes: d809a7c64ba8 ("mm/damon/sysfs: implement refresh_ms file internal work")
Signed-off-by: Josh Law <objecting@objecting.org>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.17+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index ddc30586c0e6..6a44a2f3d8fc 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1620,9 +1620,12 @@ static int damon_sysfs_repeat_call_fn(void *data)
 
 	if (!mutex_trylock(&damon_sysfs_lock))
 		return 0;
+	if (sysfs_kdamond->contexts->nr != 1)
+		goto out;
 	damon_sysfs_upd_tuned_intervals(sysfs_kdamond);
 	damon_sysfs_upd_schemes_stats(sysfs_kdamond);
 	damon_sysfs_upd_schemes_effective_quotas(sysfs_kdamond);
+out:
 	mutex_unlock(&damon_sysfs_lock);
 	return 0;
 }
-- 
cgit v1.2.3


From ffef67b93aa352b34e6aeba3d52c19a63885409a Mon Sep 17 00:00:00 2001
From: "David Hildenbrand (Arm)" <david@kernel.org>
Date: Mon, 23 Mar 2026 21:20:18 +0100
Subject: mm/memory: fix PMD/PUD checks in follow_pfnmap_start()

follow_pfnmap_start() suffers from two problems:

(1) We are not re-fetching the pmd/pud after taking the PTL

Therefore, we are not properly stabilizing what the lock actually
protects.  If there is concurrent zapping, we would indicate to the
caller that we found an entry, however, that entry might already have
been invalidated, or contain a different PFN after taking the lock.

Properly use pmdp_get() / pudp_get() after taking the lock.

(2) pmd_leaf() / pud_leaf() are not well defined on non-present entries

pmd_leaf()/pud_leaf() could wrongly trigger on non-present entries.

There is no real guarantee that pmd_leaf()/pud_leaf() returns something
reasonable on non-present entries.  Most architectures indeed either
perform a present check or make it work by smart use of flags.

However, for example loongarch checks the _PAGE_HUGE flag in pmd_leaf(),
and always sets the _PAGE_HUGE flag in __swp_entry_to_pmd().  Whereby
pmd_trans_huge() explicitly checks pmd_present(), pmd_leaf() does not do
that.

Let's check pmd_present()/pud_present() before assuming "the is a present
PMD leaf" when spotting pmd_leaf()/pud_leaf(), like other page table
handling code that traverses user page tables does.

Given that non-present PMD entries are likely rare in VM_IO|VM_PFNMAP, (1)
is likely more relevant than (2).  It is questionable how often (1) would
actually trigger, but let's CC stable to be sure.

This was found by code inspection.

Link: https://lkml.kernel.org/r/20260323-follow_pfnmap_fix-v1-1-5b0ec10872b3@kernel.org
Fixes: 6da8e9634bb7 ("mm: new follow_pfnmap API")
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 2f815a34d924..c65e82c86fed 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6815,11 +6815,16 @@ retry:
 
 	pudp = pud_offset(p4dp, address);
 	pud = pudp_get(pudp);
-	if (pud_none(pud))
+	if (!pud_present(pud))
 		goto out;
 	if (pud_leaf(pud)) {
 		lock = pud_lock(mm, pudp);
-		if (!unlikely(pud_leaf(pud))) {
+		pud = pudp_get(pudp);
+
+		if (unlikely(!pud_present(pud))) {
+			spin_unlock(lock);
+			goto out;
+		} else if (unlikely(!pud_leaf(pud))) {
 			spin_unlock(lock);
 			goto retry;
 		}
@@ -6831,9 +6836,16 @@ retry:
 
 	pmdp = pmd_offset(pudp, address);
 	pmd = pmdp_get_lockless(pmdp);
+	if (!pmd_present(pmd))
+		goto out;
 	if (pmd_leaf(pmd)) {
 		lock = pmd_lock(mm, pmdp);
-		if (!unlikely(pmd_leaf(pmd))) {
+		pmd = pmdp_get(pmdp);
+
+		if (unlikely(!pmd_present(pmd))) {
+			spin_unlock(lock);
+			goto out;
+		} else if (unlikely(!pmd_leaf(pmd))) {
 			spin_unlock(lock);
 			goto retry;
 		}
-- 
cgit v1.2.3


From 3b89863c3fa482912911cd65a12a3aeef662c250 Mon Sep 17 00:00:00 2001
From: Max Boone <mboone@akamai.com>
Date: Wed, 25 Mar 2026 10:59:16 +0100
Subject: mm/pagewalk: fix race between concurrent split and refault

The splitting of a PUD entry in walk_pud_range() can race with a
concurrent thread refaulting the PUD leaf entry causing it to try walking
a PMD range that has disappeared.

An example and reproduction of this is to try reading numa_maps of a
process while VFIO-PCI is setting up DMA (specifically the
vfio_pin_pages_remote call) on a large BAR for that process.

This will trigger a kernel BUG:
vfio-pci 0000:03:00.0: enabling device (0000 -> 0002)
BUG: unable to handle page fault for address: ffffa23980000000
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP NOPTI
...
RIP: 0010:walk_pgd_range+0x3b5/0x7a0
Code: 8d 43 ff 48 89 44 24 28 4d 89 ce 4d 8d a7 00 00 20 00 48 8b 4c 24
28 49 81 e4 00 00 e0 ff 49 8d 44 24 ff 48 39 c8 4c 0f 43 e3 <49> f7 06
   9f ff ff ff 75 3b 48 8b 44 24 20 48 8b 40 28 48 85 c0 74
RSP: 0018:ffffac23e1ecf808 EFLAGS: 00010287
RAX: 00007f44c01fffff RBX: 00007f4500000000 RCX: 00007f44ffffffff
RDX: 0000000000000000 RSI: 000ffffffffff000 RDI: ffffffff93378fe0
RBP: ffffac23e1ecf918 R08: 0000000000000004 R09: ffffa23980000000
R10: 0000000000000020 R11: 0000000000000004 R12: 00007f44c0200000
R13: 00007f44c0000000 R14: ffffa23980000000 R15: 00007f44c0000000
FS:  00007fe884739580(0000) GS:ffff9b7d7a9c0000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffa23980000000 CR3: 000000c0650e2005 CR4: 0000000000770ef0
PKRU: 55555554
Call Trace:
 <TASK>
 __walk_page_range+0x195/0x1b0
 walk_page_vma+0x62/0xc0
 show_numa_map+0x12b/0x3b0
 seq_read_iter+0x297/0x440
 seq_read+0x11d/0x140
 vfs_read+0xc2/0x340
 ksys_read+0x5f/0xe0
 do_syscall_64+0x68/0x130
 ? get_page_from_freelist+0x5c2/0x17e0
 ? mas_store_prealloc+0x17e/0x360
 ? vma_set_page_prot+0x4c/0xa0
 ? __alloc_pages_noprof+0x14e/0x2d0
 ? __mod_memcg_lruvec_state+0x8d/0x140
 ? __lruvec_stat_mod_folio+0x76/0xb0
 ? __folio_mod_stat+0x26/0x80
 ? do_anonymous_page+0x705/0x900
 ? __handle_mm_fault+0xa8d/0x1000
 ? __count_memcg_events+0x53/0xf0
 ? handle_mm_fault+0xa5/0x360
 ? do_user_addr_fault+0x342/0x640
 ? arch_exit_to_user_mode_prepare.constprop.0+0x16/0xa0
 ? irqentry_exit_to_user_mode+0x24/0x100
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7fe88464f47e
Code: c0 e9 b6 fe ff ff 50 48 8d 3d be 07 0b 00 e8 69 01 02 00 66 0f 1f
84 00 00 00 00 00 64 8b 04 25 18 00 00 00 85 c0 75 14 0f 05 <48> 3d 00
   f0 ff ff 77 5a c3 66 0f 1f 84 00 00 00 00 00 48 83 ec 28
RSP: 002b:00007ffe6cd9a9b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007fe88464f47e
RDX: 0000000000020000 RSI: 00007fe884543000 RDI: 0000000000000003
RBP: 00007fe884543000 R08: 00007fe884542010 R09: 0000000000000000
R10: fffffffffffffbc5 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000
 </TASK>

Fix this by validating the PUD entry in walk_pmd_range() using a stable
snapshot (pudp_get()).  If the PUD is not present or is a leaf, retry the
walk via ACTION_AGAIN instead of descending further.  This mirrors the
retry logic in walk_pte_range(), which lets walk_pmd_range() retry if the
PTE is not being got by pte_offset_map_lock().

Link: https://lkml.kernel.org/r/20260325-pagewalk-check-pmd-refault-v2-1-707bff33bc60@akamai.com
Fixes: f9e54c3a2f5b ("vfio/pci: implement huge_fault support")
Co-developed-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Signed-off-by: Max Boone <mboone@akamai.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/pagewalk.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index a94c401ab2cf..4e7bcd975c54 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -97,6 +97,7 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
 {
+	pud_t pudval = pudp_get(pud);
 	pmd_t *pmd;
 	unsigned long next;
 	const struct mm_walk_ops *ops = walk->ops;
@@ -105,6 +106,24 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	int err = 0;
 	int depth = real_depth(3);
 
+	/*
+	 * For PTE handling, pte_offset_map_lock() takes care of checking
+	 * whether there actually is a page table. But it also has to be
+	 * very careful about concurrent page table reclaim.
+	 *
+	 * Similarly, we have to be careful here - a PUD entry that points
+	 * to a PMD table cannot go away, so we can just walk it. But if
+	 * it's something else, we need to ensure we didn't race something,
+	 * so need to retry.
+	 *
+	 * A pertinent example of this is a PUD refault after PUD split -
+	 * we will need to split again or risk accessing invalid memory.
+	 */
+	if (!pud_present(pudval) || pud_leaf(pudval)) {
+		walk->action = ACTION_AGAIN;
+		return 0;
+	}
+
 	pmd = pmd_offset(pud, addr);
 	do {
 again:
@@ -218,12 +237,12 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 		else if (pud_leaf(*pud) || !pud_present(*pud))
 			continue; /* Nothing to do. */
 
-		if (pud_none(*pud))
-			goto again;
-
 		err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
+
+		if (walk->action == ACTION_AGAIN)
+			goto again;
 	} while (pud++, addr = next, addr != end);
 
 	return err;
-- 
cgit v1.2.3


From 2598ab9d63f41160c7081998857fef409182933d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 23 Mar 2026 21:55:16 +0100
Subject: bug: avoid format attribute warning for clang as well

Like gcc, clang-22 now also warns about a function that it incorrectly
identifies as a printf-style format:

lib/bug.c:190:22: error: diagnostic behavior may be improved by adding the 'format(printf, 1, 0)' attribute to the declaration of '__warn_printf' [-Werror,-Wmissing-format-attribute]
  179 | static void __warn_printf(const char *fmt, struct pt_regs *regs)
      | __attribute__((format(printf, 1, 0)))
  180 | {
  181 |         if (!fmt)
  182 |                 return;
  183 |
  184 | #ifdef HAVE_ARCH_BUG_FORMAT_ARGS
  185 |         if (regs) {
  186 |                 struct arch_va_list _args;
  187 |                 va_list *args = __warn_args(&_args, regs);
  188 |
  189 |                 if (args) {
  190 |                         vprintk(fmt, *args);
      |                                           ^

Revert the change that added a gcc-specific workaround, and instead add
the generic annotation that avoid the warning.

Link: https://lkml.kernel.org/r/20260323205534.1284284-1-arnd@kernel.org
Fixes: d36067d6ea00 ("bug: Hush suggest-attribute=format for __warn_printf()")
Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Suggested-by: Brendan Jackman <jackmanb@google.com>
Link: https://lore.kernel.org/all/20251208141618.2805983-1-andriy.shevchenko@linux.intel.com/T/#u
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Brendan Jackman <jackmanb@google.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Justin Stitt <justinstitt@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/bug.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/lib/bug.c b/lib/bug.c
index 623c467a8b76..aab9e6a40c5f 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -173,10 +173,8 @@ struct bug_entry *find_bug(unsigned long bugaddr)
 	return module_find_bug(bugaddr);
 }
 
-__diag_push();
-__diag_ignore(GCC, all, "-Wsuggest-attribute=format",
-	      "Not a valid __printf() conversion candidate.");
-static void __warn_printf(const char *fmt, struct pt_regs *regs)
+static __printf(1, 0)
+void __warn_printf(const char *fmt, struct pt_regs *regs)
 {
 	if (!fmt)
 		return;
@@ -195,7 +193,6 @@ static void __warn_printf(const char *fmt, struct pt_regs *regs)
 
 	printk("%s", fmt);
 }
-__diag_pop();
 
 static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long bugaddr, struct pt_regs *regs)
 {
-- 
cgit v1.2.3


From 2697dd8ae721db4f6a53d4f4cbd438212a80f8dc Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Date: Fri, 27 Mar 2026 17:31:04 +0000
Subject: mm/mseal: update VMA end correctly on merge

Previously we stored the end of the current VMA in curr_end, and then upon
iterating to the next VMA updated curr_start to curr_end to advance to the
next VMA.

However, this doesn't take into account the fact that a VMA might be
updated due to a merge by vma_modify_flags(), which can result in curr_end
being stale and thus, upon setting curr_start to curr_end, ending up with
an incorrect curr_start on the next iteration.

Resolve the issue by setting curr_end to vma->vm_end unconditionally to
ensure this value remains updated should this occur.

While we're here, eliminate this entire class of bug by simply setting
const curr_[start/end] to be clamped to the input range and VMAs, which
also happens to simplify the logic.

Link: https://lkml.kernel.org/r/20260327173104.322405-1-ljs@kernel.org
Fixes: 6c2da14ae1e0 ("mm/mseal: rework mseal apply logic")
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reported-by: Antonius <antonius@bluedragonsec.com>
Closes: https://lore.kernel.org/linux-mm/CAK8a0jwWGj9-SgFk0yKFh7i8jMkwKm5b0ao9=kmXWjO54veX2g@mail.gmail.com/
Suggested-by: David Hildenbrand (ARM) <david@kernel.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mseal.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/mseal.c b/mm/mseal.c
index 316b5e1dec78..ac58643181f7 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -56,7 +56,6 @@ static int mseal_apply(struct mm_struct *mm,
 		unsigned long start, unsigned long end)
 {
 	struct vm_area_struct *vma, *prev;
-	unsigned long curr_start = start;
 	VMA_ITERATOR(vmi, mm, start);
 
 	/* We know there are no gaps so this will be non-NULL. */
@@ -66,6 +65,7 @@ static int mseal_apply(struct mm_struct *mm,
 		prev = vma;
 
 	for_each_vma_range(vmi, vma, end) {
+		const unsigned long curr_start = MAX(vma->vm_start, start);
 		const unsigned long curr_end = MIN(vma->vm_end, end);
 
 		if (!(vma->vm_flags & VM_SEALED)) {
@@ -79,7 +79,6 @@ static int mseal_apply(struct mm_struct *mm,
 		}
 
 		prev = vma;
-		curr_start = curr_end;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From eeee5a710f26ce57807024ef330fe5a850eaecd8 Mon Sep 17 00:00:00 2001
From: Marek Behún <kabel@kernel.org>
Date: Thu, 26 Mar 2026 13:20:38 +0100
Subject: net: sfp: Fix Ubiquiti U-Fiber Instant SFP module on mvneta
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In commit 8110633db49d7de2 ("net: sfp-bus: allow SFP quirks to override
Autoneg and pause bits") we moved the setting of Autoneg and pause bits
before the call to SFP quirk when parsing SFP module support.

Since the quirk for Ubiquiti U-Fiber Instant SFP module zeroes the
support bits and sets 1000baseX_Full only, the above mentioned commit
changed the overall computed support from
  1000baseX_Full, Autoneg, Pause, Asym_Pause
to just
  1000baseX_Full.

This broke the SFP module for mvneta, which requires Autoneg for
1000baseX since commit c762b7fac1b249a9 ("net: mvneta: deny disabling
autoneg for 802.3z modes").

Fix this by setting back the Autoneg, Pause and Asym_Pause bits in the
quirk.

Fixes: 8110633db49d7de2 ("net: sfp-bus: allow SFP quirks to override Autoneg and pause bits")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20260326122038.2489589-1-kabel@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 5db841377199..ce8924613363 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -480,11 +480,16 @@ static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id,
 {
 	/* Ubiquiti U-Fiber Instant module claims that support all transceiver
 	 * types including 10G Ethernet which is not truth. So clear all claimed
-	 * modes and set only one mode which module supports: 1000baseX_Full.
+	 * modes and set only one mode which module supports: 1000baseX_Full,
+	 * along with the Autoneg and pause bits.
 	 */
 	linkmode_zero(caps->link_modes);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
 			 caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, caps->link_modes);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, caps->link_modes);
+
 	phy_interface_zero(caps->interfaces);
 	__set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces);
 }
-- 
cgit v1.2.3


From d389954a6cae7bf76b7b082ac3511d177b77ef2d Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 26 Mar 2026 15:52:32 +0800
Subject: net: enetc: check whether the RSS algorithm is Toeplitz

Both ENETC v1 and v4 only provide Toeplitz RSS support. This patch adds
a validation check to reject attempts to configure other RSS algorithms,
avoiding misleading configuration options for users.

Fixes: d382563f541b ("enetc: Add RFS and RSS support")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20260326075233.3628047-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 2fe140ddebb2..a393647e6062 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -795,6 +795,10 @@ static int enetc_set_rxfh(struct net_device *ndev,
 	struct enetc_si *si = priv->si;
 	int err = 0;
 
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
 	/* set hash key, if PF */
 	if (rxfh->key && enetc_si_is_pf(si))
 		enetc_set_rss_key(si, rxfh->key);
-- 
cgit v1.2.3


From a142d139168cce8d5776245b5494c7f7f5d7fb7d Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 26 Mar 2026 15:52:33 +0800
Subject: net: enetc: do not allow VF to configure the RSS key

VFs do not have privilege to configure the RSS key because the registers
are owned by the PF. Currently, if VF attempts to configure the RSS key,
enetc_set_rxfh() simply skips the configuration and does not generate a
warning, which may mislead users into thinking the feature is supported.
To improve this situation, add a check to reject RSS key configuration
on VFs.

Fixes: d382563f541b ("enetc: Add RFS and RSS support")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Clark Wang <xiaoning.wang@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20260326075233.3628047-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index a393647e6062..7c17acaf7a38 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -800,8 +800,12 @@ static int enetc_set_rxfh(struct net_device *ndev,
 		return -EOPNOTSUPP;
 
 	/* set hash key, if PF */
-	if (rxfh->key && enetc_si_is_pf(si))
+	if (rxfh->key) {
+		if (!enetc_si_is_pf(si))
+			return -EOPNOTSUPP;
+
 		enetc_set_rss_key(si, rxfh->key);
+	}
 
 	/* set RSS table */
 	if (rxfh->indir)
-- 
cgit v1.2.3


From bc5b4e5ae1a67700a618328217b6a3bd0f296e97 Mon Sep 17 00:00:00 2001
From: Phil Willoughby <willerz@gmail.com>
Date: Sat, 28 Mar 2026 08:07:34 +0000
Subject: ALSA: usb-audio: Fix quirk flags for NeuralDSP Quad Cortex

The NeuralDSP Quad Cortex does not support DSD playback. We need
this product-specific entry with zero quirks because otherwise it
falls through to the vendor-specific entry which marks it as
supporting DSD playback.

Cc: Yue Wang <yuleopen@gmail.com>
Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Takashi Iwai <tiwai@suse.com>
Signed-off-by: Phil Willoughby <willerz@gmail.com>
Link: https://patch.msgid.link/20260328080921.3310-1-willerz@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 1f82e9e02d4b..6e40c18c37f9 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2305,6 +2305,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_PLAYBACK_FIRST | QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x13e5, 0x0001, /* Serato Phono */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
+	DEVICE_FLG(0x152a, 0x880a, /* NeuralDSP Quad Cortex */
+		   0), /* Doesn't have the vendor quirk which would otherwise apply */
 	DEVICE_FLG(0x154e, 0x1002, /* Denon DCD-1500RE */
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x154e, 0x1003, /* Denon DA-300USB */
-- 
cgit v1.2.3


From bac1e57adf08c9ee33e95fb09cd032f330294e70 Mon Sep 17 00:00:00 2001
From: "Dustin L. Howett" <dustin@howett.net>
Date: Fri, 27 Mar 2026 10:54:40 -0500
Subject: ALSA: hda/realtek: add quirk for Framework F111:000F

Similar to commit 7b509910b3ad ("ALSA hda/realtek: Add quirk for
Framework F111:000C") and previous quirks for Framework systems with
Realtek codecs.

000F is another new platform with an ALC285 which needs the same quirk.

Signed-off-by: Dustin L. Howett <dustin@howett.net>
Link: https://patch.msgid.link/20260327-framework-alsa-000f-v1-1-74013aba1c00@howett.net
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 6787e54fcfe6..393910857e89 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7757,6 +7757,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0xf111, 0x000f, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
 
 #if 0
 	/* Below is a quirk table taken from the old code.
-- 
cgit v1.2.3


From 696b0a9bd2e4b4c7082369202fe9406345a6d11e Mon Sep 17 00:00:00 2001
From: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Date: Fri, 27 Mar 2026 15:57:36 +0000
Subject: ALSA: hda/intel: Add MSI X870E Tomahawk to denylist by DMI ID

This motherboard uses USB audio instead, causing this driver to complain
about "no codecs found!".
Add it to the denylist to silence the warning.

The first attempt only matched on the PCI device, but this caused issues
for some laptops, so DMI match against the board as well.

Signed-off-by: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Link: https://patch.msgid.link/20260327155737.21818-2-stuart.a.hayhurst@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/controllers/intel.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c
index 2edbcab597c8..8a7bd49e411f 100644
--- a/sound/hda/controllers/intel.c
+++ b/sound/hda/controllers/intel.c
@@ -2085,6 +2085,11 @@ static struct pci_device_id driver_denylist_ideapad_z570[] = {
 	{}
 };
 
+static struct pci_device_id driver_denylist_msi_x870e[] = {
+	{ PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1462, 0xee59) }, /* MSI X870E Tomahawk WiFi */
+	{}
+};
+
 /* DMI-based denylist, to be used when:
  *  - PCI subsystem IDs are zero, impossible to distinguish from valid sound cards.
  *  - Different modifications of the same laptop use different GPU models.
@@ -2098,6 +2103,14 @@ static const struct dmi_system_id driver_denylist_dmi[] = {
 		},
 		.driver_data = &driver_denylist_ideapad_z570,
 	},
+	{
+		/* PCI device matching alone incorrectly matches some laptops */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_BOARD_NAME, "MAG X870E TOMAHAWK WIFI (MS-7E59)"),
+		},
+		.driver_data = &driver_denylist_msi_x870e,
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 1fbf85dbf02c96c318e056fb5b8fc614758fee3c Mon Sep 17 00:00:00 2001
From: Sourav Nayak <nonameblank007@gmail.com>
Date: Fri, 27 Mar 2026 19:58:05 +0530
Subject: ALSA: hda/realtek: add quirk for HP Victus 15-fb0xxx

This adds a mute led quirck for HP Victus 15-fb0xxx (103c:8a3d) model

- As it used 0x8(full bright)/0x7f(little dim) for mute led on and other
  values as 0ff (0x0, 0x4, ...)

- So, use ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT insted for safer approach

Cc: <stable@vger.kernel.org>
Signed-off-by: Sourav Nayak <nonameblank007@gmail.com>
Link: https://patch.msgid.link/20260327142805.17139-1-nonameblank007@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 393910857e89..78ab0e86621b 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7009,6 +7009,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8a30, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8a31, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8a34, "HP Pavilion x360 2-in-1 Laptop 14-ek0xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
+	SND_PCI_QUIRK(0x103c, 0x8a3d, "HP Victus 15-fb0xxx (MB 8A3D)", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4),
 	SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
-- 
cgit v1.2.3


From 250ab25391edeeab8462b68be42e4904506c409c Mon Sep 17 00:00:00 2001
From: Wesley Atwell <atwellwea@gmail.com>
Date: Tue, 24 Mar 2026 16:13:26 -0600
Subject: tracing: Drain deferred trigger frees if kthread creation fails

Boot-time trigger registration can fail before the trigger-data cleanup
kthread exists. Deferring those frees until late init is fine, but the
post-boot fallback must still drain the deferred list if kthread
creation never succeeds.

Otherwise, boot-deferred nodes can accumulate on
trigger_data_free_list, later frees fall back to synchronously freeing
only the current object, and the older queued entries are leaked
forever.

To trigger this, add the following to the kernel command line:

  trace_event=sched_switch trace_trigger=sched_switch.traceon,sched_switch.traceon

The second traceon trigger will fail and be freed. This triggers a NULL
pointer dereference and crashes the kernel.

Keep the deferred boot-time behavior, but when kthread creation fails,
drain the whole queued list synchronously. Do the same in the late-init
drain path so queued entries are not stranded there either.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260324221326.1395799-3-atwellwea@gmail.com
Fixes: 61d445af0a7c ("tracing: Add bulk garbage collection of freeing event_trigger_data")
Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_trigger.c | 79 +++++++++++++++++++++++++++++++------
 1 file changed, 66 insertions(+), 13 deletions(-)

diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d5230b759a2d..655db2e82513 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -22,6 +22,39 @@ static struct task_struct *trigger_kthread;
 static struct llist_head trigger_data_free_list;
 static DEFINE_MUTEX(trigger_data_kthread_mutex);
 
+static int trigger_kthread_fn(void *ignore);
+
+static void trigger_create_kthread_locked(void)
+{
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	if (!trigger_kthread) {
+		struct task_struct *kthread;
+
+		kthread = kthread_create(trigger_kthread_fn, NULL,
+					 "trigger_data_free");
+		if (!IS_ERR(kthread))
+			WRITE_ONCE(trigger_kthread, kthread);
+	}
+}
+
+static void trigger_data_free_queued_locked(void)
+{
+	struct event_trigger_data *data, *tmp;
+	struct llist_node *llnodes;
+
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	llnodes = llist_del_all(&trigger_data_free_list);
+	if (!llnodes)
+		return;
+
+	tracepoint_synchronize_unregister();
+
+	llist_for_each_entry_safe(data, tmp, llnodes, llist)
+		kfree(data);
+}
+
 /* Bulk garbage collection of event_trigger_data elements */
 static int trigger_kthread_fn(void *ignore)
 {
@@ -56,30 +89,50 @@ void trigger_data_free(struct event_trigger_data *data)
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 
+	/*
+	 * Boot-time trigger registration can fail before kthread creation
+	 * works. Keep the deferred-free semantics during boot and let late
+	 * init start the kthread to drain the list.
+	 */
+	if (system_state == SYSTEM_BOOTING && !trigger_kthread) {
+		llist_add(&data->llist, &trigger_data_free_list);
+		return;
+	}
+
 	if (unlikely(!trigger_kthread)) {
 		guard(mutex)(&trigger_data_kthread_mutex);
+
+		trigger_create_kthread_locked();
 		/* Check again after taking mutex */
 		if (!trigger_kthread) {
-			struct task_struct *kthread;
-
-			kthread = kthread_create(trigger_kthread_fn, NULL,
-						 "trigger_data_free");
-			if (!IS_ERR(kthread))
-				WRITE_ONCE(trigger_kthread, kthread);
+			llist_add(&data->llist, &trigger_data_free_list);
+			/* Drain the queued frees synchronously if creation failed. */
+			trigger_data_free_queued_locked();
+			return;
 		}
 	}
 
-	if (!trigger_kthread) {
-		/* Do it the slow way */
-		tracepoint_synchronize_unregister();
-		kfree(data);
-		return;
-	}
-
 	llist_add(&data->llist, &trigger_data_free_list);
 	wake_up_process(trigger_kthread);
 }
 
+static int __init trigger_data_free_init(void)
+{
+	guard(mutex)(&trigger_data_kthread_mutex);
+
+	if (llist_empty(&trigger_data_free_list))
+		return 0;
+
+	trigger_create_kthread_locked();
+	if (trigger_kthread)
+		wake_up_process(trigger_kthread);
+	else
+		trigger_data_free_queued_locked();
+
+	return 0;
+}
+late_initcall(trigger_data_free_init);
+
 static inline void data_ops_trigger(struct event_trigger_data *data,
 				    struct trace_buffer *buffer,  void *rec,
 				    struct ring_buffer_event *event)
-- 
cgit v1.2.3


From 210d36d892de5195e6766c45519dfb1e65f3eb83 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Wed, 25 Mar 2026 17:17:59 -0700
Subject: futex: Clear stale exiting pointer in futex_lock_pi() retry path

Fuzzying/stressing futexes triggered:

    WARNING: kernel/futex/core.c:825 at wait_for_owner_exiting+0x7a/0x80, CPU#11: futex_lock_pi_s/524

When futex_lock_pi_atomic() sees the owner is exiting, it returns -EBUSY
and stores a refcounted task pointer in 'exiting'.

After wait_for_owner_exiting() consumes that reference, the local pointer
is never reset to nil. Upon a retry, if futex_lock_pi_atomic() returns a
different error, the bogus pointer is passed to wait_for_owner_exiting().

  CPU0			     CPU1		       CPU2
  futex_lock_pi(uaddr)
  // acquires the PI futex
  exit()
    futex_cleanup_begin()
      futex_state = EXITING;
			     futex_lock_pi(uaddr)
			       futex_lock_pi_atomic()
				 attach_to_pi_owner()
				   // observes EXITING
				   *exiting = owner;  // takes ref
				   return -EBUSY
			       wait_for_owner_exiting(-EBUSY, owner)
				 put_task_struct();   // drops ref
			       // exiting still points to owner
			       goto retry;
			       futex_lock_pi_atomic()
				 lock_pi_update_atomic()
				   cmpxchg(uaddr)
					*uaddr ^= WAITERS // whatever
				   // value changed
				 return -EAGAIN;
			       wait_for_owner_exiting(-EAGAIN, exiting) // stale
				 WARN_ON_ONCE(exiting)

Fix this by resetting upon retry, essentially aligning it with requeue_pi.

Fixes: 3ef240eaff36 ("futex: Prevent exit livelock")
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260326001759.4129680-1-dave@stgolabs.net
---
 kernel/futex/pi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index bc1f7e83a37e..7808068fa59e 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -918,7 +918,7 @@ int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct task_struct *exiting = NULL;
+	struct task_struct *exiting;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_q q = futex_q_init;
 	DEFINE_WAKE_Q(wake_q);
@@ -933,6 +933,7 @@ int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int tryl
 	to = futex_setup_timer(time, &timeout, flags, 0);
 
 retry:
+	exiting = NULL;
 	ret = get_futex_key(uaddr, flags, &q.key, FUTEX_WRITE);
 	if (unlikely(ret != 0))
 		goto out;
-- 
cgit v1.2.3


From b0faf733fc1cf7f198c299dcc1638571d7cfd0f7 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 27 Mar 2026 16:18:24 +0100
Subject: MAINTAINERS: drop outdated I2C website

As stated on the website: "This wiki has been archived and the content
is no longer updated." No need to reference it.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 7d10988cbc62..6593e5c7d821 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12009,7 +12009,6 @@ I2C SUBSYSTEM
 M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
-W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
 F:	Documentation/i2c/
@@ -12035,7 +12034,6 @@ I2C SUBSYSTEM HOST DRIVERS
 M:	Andi Shyti <andi.shyti@kernel.org>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
-W:	https://i2c.wiki.kernel.org/
 Q:	https://patchwork.ozlabs.org/project/linux-i2c/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux.git
 F:	Documentation/devicetree/bindings/i2c/
-- 
cgit v1.2.3


From b045ab3dff97edae6d538eeff900a34c098761f8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sun, 29 Mar 2026 11:12:37 +0200
Subject: ALSA: ctxfi: Fix missing SPDIFI1 index handling

SPDIF1 DAIO type isn't properly handled in daio_device_index() for
hw20k2, and it returned -EINVAL, which ended up with the out-of-bounds
array access.  Follow the hw20k1 pattern and return the proper index
for this type, too.

Reported-and-tested-by: Karsten Hohmeier <linux@hohmatik.de>
Closes: https://lore.kernel.org/20260315155004.15633-1-linux@hohmatik.de
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20260329091240.420194-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/ctdaio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index b8bde27f3a1d..19faa81d5400 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -118,6 +118,7 @@ static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw)
 		switch (type) {
 		case SPDIFOO:	return 0;
 		case SPDIFIO:	return 0;
+		case SPDIFI1:	return 1;
 		case LINEO1:	return 4;
 		case LINEO2:	return 7;
 		case LINEO3:	return 5;
-- 
cgit v1.2.3


From 277c6960d4ddb94d16198afd70c92c3d4593d131 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sun, 29 Mar 2026 11:12:38 +0200
Subject: ALSA: ctxfi: Check the error for index mapping

The ctxfi driver blindly assumed a proper value returned from
daio_device_index(), but it's not always true.  Add a proper error
check to deal with the error from the function.

Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/87cy149n6k.wl-tiwai@suse.de
Link: https://patch.msgid.link/20260329091240.420194-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/ctdaio.c | 85 +++++++++++++++++++++++++++++-------------------
 1 file changed, 52 insertions(+), 33 deletions(-)

diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index 19faa81d5400..4dbb1dd7af32 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -99,7 +99,7 @@ static const struct rsc_ops daio_in_rsc_ops_20k2 = {
 	.output_slot	= daio_index,
 };
 
-static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw)
+static int daio_device_index(enum DAIOTYP type, struct hw *hw)
 {
 	switch (hw->chip_type) {
 	case ATC20K1:
@@ -112,7 +112,9 @@ static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw)
 		case LINEO3:	return 5;
 		case LINEO4:	return 6;
 		case LINEIM:	return 7;
-		default:	return -EINVAL;
+		default:
+			pr_err("ctxfi: Invalid type %d for hw20k1\n", type);
+			return -EINVAL;
 		}
 	case ATC20K2:
 		switch (type) {
@@ -126,9 +128,12 @@ static unsigned int daio_device_index(enum DAIOTYP type, struct hw *hw)
 		case LINEIM:	return 4;
 		case MIC:	return 5;
 		case RCA:	return 3;
-		default:	return -EINVAL;
+		default:
+			pr_err("ctxfi: Invalid type %d for hw20k2\n", type);
+			return -EINVAL;
 		}
 	default:
+		pr_err("ctxfi: Invalid chip type %d\n", hw->chip_type);
 		return -EINVAL;
 	}
 }
@@ -149,8 +154,11 @@ static int dao_spdif_set_spos(struct dao *dao, unsigned int spos)
 
 static int dao_commit_write(struct dao *dao)
 {
-	dao->hw->dao_commit_write(dao->hw,
-		daio_device_index(dao->daio.type, dao->hw), dao->ctrl_blk);
+	int idx = daio_device_index(dao->daio.type, dao->hw);
+
+	if (idx < 0)
+		return idx;
+	dao->hw->dao_commit_write(dao->hw, idx, dao->ctrl_blk);
 	return 0;
 }
 
@@ -288,8 +296,11 @@ static int dai_set_enb_srt(struct dai *dai, unsigned int enb)
 
 static int dai_commit_write(struct dai *dai)
 {
-	dai->hw->dai_commit_write(dai->hw,
-		daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk);
+	int idx = daio_device_index(dai->daio.type, dai->hw);
+
+	if (idx < 0)
+		return idx;
+	dai->hw->dai_commit_write(dai->hw, idx, dai->ctrl_blk);
 	return 0;
 }
 
@@ -368,7 +379,7 @@ static int dao_rsc_init(struct dao *dao,
 {
 	struct hw *hw = mgr->mgr.hw;
 	unsigned int conf;
-	int err;
+	int idx, err;
 
 	err = daio_rsc_init(&dao->daio, desc, mgr->mgr.hw);
 	if (err)
@@ -387,15 +398,18 @@ static int dao_rsc_init(struct dao *dao,
 	if (err)
 		goto error2;
 
-	hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw));
+	idx = daio_device_index(dao->daio.type, hw);
+	if (idx < 0) {
+		err = idx;
+		goto error2;
+	}
+
+	hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx);
 	hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk);
 
 	conf = (desc->msr & 0x7) | (desc->passthru << 3);
-	hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw), conf);
-	hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk,
-			daio_device_index(dao->daio.type, hw));
+	hw->daio_mgr_dao_init(hw, mgr->mgr.ctrl_blk, idx, conf);
+	hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx);
 	hw->daio_mgr_commit_write(hw, mgr->mgr.ctrl_blk);
 
 	return 0;
@@ -444,7 +458,7 @@ static int dai_rsc_init(struct dai *dai,
 			const struct daio_desc *desc,
 			struct daio_mgr *mgr)
 {
-	int err;
+	int idx, err;
 	struct hw *hw = mgr->mgr.hw;
 	unsigned int rsr, msr;
 
@@ -458,6 +472,12 @@ static int dai_rsc_init(struct dai *dai,
 	if (err)
 		goto error1;
 
+	idx = daio_device_index(dai->daio.type, dai->hw);
+	if (idx < 0) {
+		err = idx;
+		goto error1;
+	}
+
 	for (rsr = 0, msr = desc->msr; msr > 1; msr >>= 1)
 		rsr++;
 
@@ -466,8 +486,7 @@ static int dai_rsc_init(struct dai *dai,
 	/* default to disabling control of a SRC */
 	hw->dai_srt_set_ec(dai->ctrl_blk, 0);
 	hw->dai_srt_set_et(dai->ctrl_blk, 0); /* default to disabling SRT */
-	hw->dai_commit_write(hw,
-		daio_device_index(dai->daio.type, dai->hw), dai->ctrl_blk);
+	hw->dai_commit_write(hw, idx, dai->ctrl_blk);
 
 	return 0;
 
@@ -582,28 +601,28 @@ static int put_daio_rsc(struct daio_mgr *mgr, struct daio *daio)
 static int daio_mgr_enb_daio(struct daio_mgr *mgr, struct daio *daio)
 {
 	struct hw *hw = mgr->mgr.hw;
-
-	if (daio->output) {
-		hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	} else {
-		hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	}
+	int idx = daio_device_index(daio->type, hw);
+
+	if (idx < 0)
+		return idx;
+	if (daio->output)
+		hw->daio_mgr_enb_dao(mgr->mgr.ctrl_blk, idx);
+	else
+		hw->daio_mgr_enb_dai(mgr->mgr.ctrl_blk, idx);
 	return 0;
 }
 
 static int daio_mgr_dsb_daio(struct daio_mgr *mgr, struct daio *daio)
 {
 	struct hw *hw = mgr->mgr.hw;
-
-	if (daio->output) {
-		hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	} else {
-		hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk,
-				daio_device_index(daio->type, hw));
-	}
+	int idx = daio_device_index(daio->type, hw);
+
+	if (idx < 0)
+		return idx;
+	if (daio->output)
+		hw->daio_mgr_dsb_dao(mgr->mgr.ctrl_blk, idx);
+	else
+		hw->daio_mgr_dsb_dai(mgr->mgr.ctrl_blk, idx);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 45065a5095c7773fb98c35d60c20c3b513540597 Mon Sep 17 00:00:00 2001
From: Akshai Murari <akshaim@google.com>
Date: Fri, 27 Mar 2026 06:54:45 +0000
Subject: Input: add keycodes for contextual AI usages (HUTRR119)

HUTRR119 introduces new usages for keys intended to invoke AI agents
based on the current context. These are useful with the increasing
number of operating systems with integrated Large Language Models

Add new key definitions for KEY_ACTION_ON_SELECTION,
KEY_CONTEXTUAL_INSERT and KEY_CONTEXTUAL_QUERY

Signed-off-by: Akshai Murari <akshaim@google.com>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-debug.c                | 6 ++++++
 drivers/hid/hid-input.c                | 3 +++
 include/uapi/linux/input-event-codes.h | 4 ++++
 3 files changed, 13 insertions(+)

diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index c5865b0d2aaa..a8d2b36a7852 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -990,6 +990,9 @@ static const struct hid_usage_entry hid_usage_table[] = {
 		{ 0x0c, 0x01c9, "ALContactSync" },
 		{ 0x0c, 0x01ca, "ALNavigation" },
 		{ 0x0c, 0x01cb, "ALContextawareDesktopAssistant" },
+		{ 0x0c, 0x01cc, "ALActionOnSelection" },
+		{ 0x0c, 0x01cd, "ALContextualInsertion" },
+		{ 0x0c, 0x01ce, "ALContextualQuery" },
 		{ 0x0c, 0x0200, "GenericGUIApplicationControls" },
 		{ 0x0c, 0x0201, "ACNew" },
 		{ 0x0c, 0x0202, "ACOpen" },
@@ -3375,6 +3378,9 @@ static const char *keys[KEY_MAX + 1] = {
 	[KEY_BRIGHTNESS_MIN] = "BrightnessMin",
 	[KEY_BRIGHTNESS_MAX] = "BrightnessMax",
 	[KEY_BRIGHTNESS_AUTO] = "BrightnessAuto",
+	[KEY_ACTION_ON_SELECTION] = "ActionOnSelection",
+	[KEY_CONTEXTUAL_INSERT] = "ContextualInsert",
+	[KEY_CONTEXTUAL_QUERY] = "ContextualQuery",
 	[KEY_KBDINPUTASSIST_PREV] = "KbdInputAssistPrev",
 	[KEY_KBDINPUTASSIST_NEXT] = "KbdInputAssistNext",
 	[KEY_KBDINPUTASSIST_PREVGROUP] = "KbdInputAssistPrevGroup",
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 8fc20df99b97..ce9c3251287d 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1227,6 +1227,9 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x1bc: map_key_clear(KEY_MESSENGER);	break;
 		case 0x1bd: map_key_clear(KEY_INFO);		break;
 		case 0x1cb: map_key_clear(KEY_ASSISTANT);	break;
+		case 0x1cc: map_key_clear(KEY_ACTION_ON_SELECTION);	break;
+		case 0x1cd: map_key_clear(KEY_CONTEXTUAL_INSERT);	break;
+		case 0x1ce: map_key_clear(KEY_CONTEXTUAL_QUERY);	break;
 		case 0x201: map_key_clear(KEY_NEW);		break;
 		case 0x202: map_key_clear(KEY_OPEN);		break;
 		case 0x203: map_key_clear(KEY_CLOSE);		break;
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 4bdb6a165987..3528168f7c6d 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -643,6 +643,10 @@
 #define KEY_EPRIVACY_SCREEN_ON		0x252
 #define KEY_EPRIVACY_SCREEN_OFF		0x253
 
+#define KEY_ACTION_ON_SELECTION		0x254	/* AL Action on Selection (HUTRR119) */
+#define KEY_CONTEXTUAL_INSERT		0x255	/* AL Contextual Insertion (HUTRR119) */
+#define KEY_CONTEXTUAL_QUERY		0x256	/* AL Contextual Query (HUTRR119) */
+
 #define KEY_KBDINPUTASSIST_PREV		0x260
 #define KEY_KBDINPUTASSIST_NEXT		0x261
 #define KEY_KBDINPUTASSIST_PREVGROUP		0x262
-- 
cgit v1.2.3


From b948f9d5d3057b01188e36664e7c7604d1c8ecb5 Mon Sep 17 00:00:00 2001
From: Junxi Qian <qjx1298677004@gmail.com>
Date: Sun, 29 Mar 2026 23:39:09 +0800
Subject: io_uring/net: fix slab-out-of-bounds read in io_bundle_nbufs()

sqe->len is __u32 but gets stored into sr->len which is int. When
userspace passes sqe->len values exceeding INT_MAX (e.g. 0xFFFFFFFF),
sr->len overflows to a negative value. This negative value propagates
through the bundle recv/send path:

  1. io_recv(): sel.val = sr->len (ssize_t gets -1)
  2. io_recv_buf_select(): arg.max_len = sel->val (size_t gets
     0xFFFFFFFFFFFFFFFF)
  3. io_ring_buffers_peek(): buf->len is not clamped because max_len
     is astronomically large
  4. iov[].iov_len = 0xFFFFFFFF flows into io_bundle_nbufs()
  5. io_bundle_nbufs(): min_t(int, 0xFFFFFFFF, ret) yields -1,
     causing ret to increase instead of decrease, creating an
     infinite loop that reads past the allocated iov[] array

This results in a slab-out-of-bounds read in io_bundle_nbufs() from
the kmalloc-64 slab, as nbufs increments past the allocated iovec
entries.

  BUG: KASAN: slab-out-of-bounds in io_bundle_nbufs+0x128/0x160
  Read of size 8 at addr ffff888100ae05c8 by task exp/145
  Call Trace:
   io_bundle_nbufs+0x128/0x160
   io_recv_finish+0x117/0xe20
   io_recv+0x2db/0x1160

Fix this by rejecting negative sr->len values early in both
io_sendmsg_prep() and io_recvmsg_prep(). Since sqe->len is __u32,
any value > INT_MAX indicates overflow and is not a valid length.

Fixes: a05d1f625c7a ("io_uring/net: support bundles for send")
Cc: stable@vger.kernel.org
Signed-off-by: Junxi Qian <qjx1298677004@gmail.com>
Link: https://patch.msgid.link/20260329153909.279046-1-qjx1298677004@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/io_uring/net.c b/io_uring/net.c
index d27adbe3f20b..8885d944130a 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -421,6 +421,8 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	sr->done_io = 0;
 	sr->len = READ_ONCE(sqe->len);
+	if (unlikely(sr->len < 0))
+		return -EINVAL;
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~SENDMSG_FLAGS)
 		return -EINVAL;
@@ -791,6 +793,8 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 	sr->len = READ_ONCE(sqe->len);
+	if (unlikely(sr->len < 0))
+		return -EINVAL;
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~RECVMSG_FLAGS)
 		return -EINVAL;
-- 
cgit v1.2.3


From 111a12b422a8cfa93deabaef26fec48237163214 Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Mon, 30 Mar 2026 00:49:36 +0800
Subject: io_uring/rsrc: reject zero-length fixed buffer import

validate_fixed_range() admits buf_addr at the exact end of the
registered region when len is zero, because the check uses strict
greater-than (buf_end > imu->ubuf + imu->len).  io_import_fixed()
then computes offset == imu->len, which causes the bvec skip logic
to advance past the last bio_vec entry and read bv_offset from
out-of-bounds slab memory.

Return early from io_import_fixed() when len is zero.  A zero-length
import has no data to transfer and should not walk the bvec array
at all.

  BUG: KASAN: slab-out-of-bounds in io_import_reg_buf+0x697/0x7f0
  Read of size 4 at addr ffff888002bcc254 by task poc/103
  Call Trace:
   io_import_reg_buf+0x697/0x7f0
   io_write_fixed+0xd9/0x250
   __io_issue_sqe+0xad/0x710
   io_issue_sqe+0x7d/0x1100
   io_submit_sqes+0x86a/0x23c0
   __do_sys_io_uring_enter+0xa98/0x1590
  Allocated by task 103:
  The buggy address is located 12 bytes to the right of
   allocated 584-byte region [ffff888002bcc000, ffff888002bcc248)

Fixes: 8622b20f23ed ("io_uring: add validate_fixed_range() for validate fixed buffer")
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Link: https://patch.msgid.link/20260329164936.240871-1-tpluszz77@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 842e231c8a7c..3f82ed7dd11e 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1062,6 +1062,10 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 		return ret;
 	if (!(imu->dir & (1 << ddir)))
 		return -EFAULT;
+	if (unlikely(!len)) {
+		iov_iter_bvec(iter, ddir, NULL, 0, 0);
+		return 0;
+	}
 
 	offset = buf_addr - imu->ubuf;
 
-- 
cgit v1.2.3


From 7aaa8047eafd0bd628065b15757d9b48c5f9c07d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 29 Mar 2026 15:40:00 -0700
Subject: Linux 7.0-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index e1279c4d5b24..6b1d9fb1a6b4 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 0e211f6aaa6a00fd0ee0c1eea5498f168c6725e6 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Sun, 29 Mar 2026 17:09:40 +0000
Subject: hwmon: (tps53679) Fix array access with zero-length block read

i2c_smbus_read_block_data() can return 0, indicating a zero-length
read. When this happens, tps53679_identify_chip() accesses buf[ret - 1]
which is buf[-1], reading one byte before the buffer on the stack.

Fix by changing the check from "ret < 0" to "ret <= 0", treating a
zero-length read as an error (-EIO), which prevents the out-of-bounds
array access.

Also fix a typo in the adjacent comment: "if present" instead of
duplicate "if".

Fixes: 75ca1e5875fe ("hwmon: (pmbus/tps53679) Add support for TPS53685")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260329170925.34581-2-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/tps53679.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hwmon/pmbus/tps53679.c b/drivers/hwmon/pmbus/tps53679.c
index ca2bfa25eb04..3bca543817a6 100644
--- a/drivers/hwmon/pmbus/tps53679.c
+++ b/drivers/hwmon/pmbus/tps53679.c
@@ -103,10 +103,10 @@ static int tps53679_identify_chip(struct i2c_client *client,
 	}
 
 	ret = i2c_smbus_read_block_data(client, PMBUS_IC_DEVICE_ID, buf);
-	if (ret < 0)
-		return ret;
+	if (ret <= 0)
+		return ret < 0 ? ret : -EIO;
 
-	/* Adjust length if null terminator if present */
+	/* Adjust length if null terminator is present */
 	buf_len = (buf[ret - 1] != '\x00' ? ret : ret - 1);
 
 	id_len = strlen(id);
-- 
cgit v1.2.3


From ccf70c41e562b29d1c05d1bbf53391785e09c6fb Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Sun, 29 Mar 2026 17:09:48 +0000
Subject: hwmon: (pxe1610) Check return value of page-select write in probe

pxe1610_probe() writes PMBUS_PAGE to select page 0 but does not check
the return value. If the write fails, subsequent register reads operate
on an indeterminate page, leading to silent misconfiguration.

Check the return value and propagate the error using dev_err_probe(),
which also handles -EPROBE_DEFER correctly without log spam.

Fixes: 344757bac526 ("hwmon: (pmbus) Add Infineon PXE1610 VR driver")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260329170925.34581-4-sanman.pradhan@hpe.com
[groeck: Fix "Fixes" SHA]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pxe1610.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/pmbus/pxe1610.c b/drivers/hwmon/pmbus/pxe1610.c
index 6a4a978eca7e..24c1f961c766 100644
--- a/drivers/hwmon/pmbus/pxe1610.c
+++ b/drivers/hwmon/pmbus/pxe1610.c
@@ -104,7 +104,10 @@ static int pxe1610_probe(struct i2c_client *client)
 	 * By default this device doesn't boot to page 0, so set page 0
 	 * to access all pmbus registers.
 	 */
-	i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0);
+	ret = i2c_smbus_write_byte_data(client, PMBUS_PAGE, 0);
+	if (ret < 0)
+		return dev_err_probe(&client->dev, ret,
+				     "Failed to set page 0\n");
 
 	/* Read Manufacturer id */
 	ret = i2c_smbus_read_block_data(client, PMBUS_MFR_ID, buf);
-- 
cgit v1.2.3


From a9d2fbd3ad0e6ac588386e699beeccfe7516755f Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Sun, 29 Mar 2026 17:09:53 +0000
Subject: hwmon: (ltc4286) Add missing MODULE_IMPORT_NS("PMBUS")

ltc4286.c uses PMBus core symbols exported in the PMBUS namespace,
such as pmbus_do_probe(), but does not declare MODULE_IMPORT_NS("PMBUS").

Add the missing namespace import to avoid modpost warnings.

Fixes: 0c459759ca97 ("hwmon: (pmbus) Add ltc4286 driver")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260329170925.34581-5-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/ltc4286.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hwmon/pmbus/ltc4286.c b/drivers/hwmon/pmbus/ltc4286.c
index aabd0bcdfeee..8715d380784a 100644
--- a/drivers/hwmon/pmbus/ltc4286.c
+++ b/drivers/hwmon/pmbus/ltc4286.c
@@ -173,3 +173,4 @@ module_i2c_driver(ltc4286_driver);
 MODULE_AUTHOR("Delphine CC Chiu <Delphine_CC_Chiu@wiwynn.com>");
 MODULE_DESCRIPTION("PMBUS driver for LTC4286 and compatibles");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("PMBUS");
-- 
cgit v1.2.3


From fda9522ed6afaec45cabc198d8492270c394c7bc Mon Sep 17 00:00:00 2001
From: Asim Viladi Oglu Manizada <manizada@pm.me>
Date: Wed, 25 Mar 2026 09:14:22 +0900
Subject: ksmbd: fix OOB write in QUERY_INFO for compound requests

When a compound request such as READ + QUERY_INFO(Security) is received,
and the first command (READ) consumes most of the response buffer,
ksmbd could write beyond the allocated buffer while building a security
descriptor.

The root cause was that smb2_get_info_sec() checked buffer space using
ppntsd_size from xattr, while build_sec_desc() often synthesized a
significantly larger descriptor from POSIX ACLs.

This patch introduces smb_acl_sec_desc_scratch_len() to accurately
compute the final descriptor size beforehand, performs proper buffer
checking with smb2_calc_max_out_buf_len(), and uses exact-sized
allocation + iov pinning.

Cc: stable@vger.kernel.org
Fixes: e2b76ab8b5c9 ("ksmbd: add support for read compound")
Signed-off-by: Asim Viladi Oglu Manizada <manizada@pm.me>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 121 +++++++++++++++++++++++++++++++++++-------------
 fs/smb/server/smbacl.c  |  43 +++++++++++++++++
 fs/smb/server/smbacl.h  |   2 +
 3 files changed, 134 insertions(+), 32 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 6fb7a795ff5d..8e4cfdc0ba02 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -3402,20 +3402,24 @@ int smb2_open(struct ksmbd_work *work)
 							   KSMBD_SHARE_FLAG_ACL_XATTR)) {
 					struct smb_fattr fattr;
 					struct smb_ntsd *pntsd;
-					int pntsd_size, ace_num = 0;
+					int pntsd_size;
+					size_t scratch_len;
 
 					ksmbd_acls_fattr(&fattr, idmap, inode);
-					if (fattr.cf_acls)
-						ace_num = fattr.cf_acls->a_count;
-					if (fattr.cf_dacls)
-						ace_num += fattr.cf_dacls->a_count;
-
-					pntsd = kmalloc(sizeof(struct smb_ntsd) +
-							sizeof(struct smb_sid) * 3 +
-							sizeof(struct smb_acl) +
-							sizeof(struct smb_ace) * ace_num * 2,
-							KSMBD_DEFAULT_GFP);
+					scratch_len = smb_acl_sec_desc_scratch_len(&fattr,
+							NULL, 0,
+							OWNER_SECINFO | GROUP_SECINFO |
+							DACL_SECINFO);
+					if (!scratch_len || scratch_len == SIZE_MAX) {
+						rc = -EFBIG;
+						posix_acl_release(fattr.cf_acls);
+						posix_acl_release(fattr.cf_dacls);
+						goto err_out;
+					}
+
+					pntsd = kvzalloc(scratch_len, KSMBD_DEFAULT_GFP);
 					if (!pntsd) {
+						rc = -ENOMEM;
 						posix_acl_release(fattr.cf_acls);
 						posix_acl_release(fattr.cf_dacls);
 						goto err_out;
@@ -3430,7 +3434,7 @@ int smb2_open(struct ksmbd_work *work)
 					posix_acl_release(fattr.cf_acls);
 					posix_acl_release(fattr.cf_dacls);
 					if (rc) {
-						kfree(pntsd);
+						kvfree(pntsd);
 						goto err_out;
 					}
 
@@ -3440,7 +3444,7 @@ int smb2_open(struct ksmbd_work *work)
 								    pntsd,
 								    pntsd_size,
 								    false);
-					kfree(pntsd);
+					kvfree(pntsd);
 					if (rc)
 						pr_err("failed to store ntacl in xattr : %d\n",
 						       rc);
@@ -5372,8 +5376,9 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 	if (test_share_config_flag(work->tcon->share_conf,
 				   KSMBD_SHARE_FLAG_PIPE)) {
 		/* smb2 info file called for pipe */
-		return smb2_get_info_file_pipe(work->sess, req, rsp,
+		rc = smb2_get_info_file_pipe(work->sess, req, rsp,
 					       work->response_buf);
+		goto iov_pin_out;
 	}
 
 	if (work->next_smb2_rcv_hdr_off) {
@@ -5473,6 +5478,12 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 		rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
 				      rsp, work->response_buf);
 	ksmbd_fd_put(work, fp);
+
+iov_pin_out:
+	if (!rc)
+		rc = ksmbd_iov_pin_rsp(work, (void *)rsp,
+				offsetof(struct smb2_query_info_rsp, Buffer) +
+				le32_to_cpu(rsp->OutputBufferLength));
 	return rc;
 }
 
@@ -5699,6 +5710,11 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 	rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
 			      rsp, work->response_buf);
 	path_put(&path);
+
+	if (!rc)
+		rc = ksmbd_iov_pin_rsp(work, (void *)rsp,
+				offsetof(struct smb2_query_info_rsp, Buffer) +
+				le32_to_cpu(rsp->OutputBufferLength));
 	return rc;
 }
 
@@ -5708,13 +5724,14 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 {
 	struct ksmbd_file *fp;
 	struct mnt_idmap *idmap;
-	struct smb_ntsd *pntsd = (struct smb_ntsd *)rsp->Buffer, *ppntsd = NULL;
+	struct smb_ntsd *pntsd = NULL, *ppntsd = NULL;
 	struct smb_fattr fattr = {{0}};
 	struct inode *inode;
 	__u32 secdesclen = 0;
 	unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID;
 	int addition_info = le32_to_cpu(req->AdditionalInformation);
-	int rc = 0, ppntsd_size = 0;
+	int rc = 0, ppntsd_size = 0, max_len;
+	size_t scratch_len = 0;
 
 	if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO |
 			      PROTECTED_DACL_SECINFO |
@@ -5722,6 +5739,11 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 		ksmbd_debug(SMB, "Unsupported addition info: 0x%x)\n",
 		       addition_info);
 
+		pntsd = kzalloc(ALIGN(sizeof(struct smb_ntsd), 8),
+				KSMBD_DEFAULT_GFP);
+		if (!pntsd)
+			return -ENOMEM;
+
 		pntsd->revision = cpu_to_le16(1);
 		pntsd->type = cpu_to_le16(SELF_RELATIVE | DACL_PROTECTED);
 		pntsd->osidoffset = 0;
@@ -5730,9 +5752,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 		pntsd->dacloffset = 0;
 
 		secdesclen = sizeof(struct smb_ntsd);
-		rsp->OutputBufferLength = cpu_to_le32(secdesclen);
-
-		return 0;
+		goto iov_pin;
 	}
 
 	if (work->next_smb2_rcv_hdr_off) {
@@ -5764,18 +5784,58 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 						     &ppntsd);
 
 	/* Check if sd buffer size exceeds response buffer size */
-	if (smb2_resp_buf_len(work, 8) > ppntsd_size)
-		rc = build_sec_desc(idmap, pntsd, ppntsd, ppntsd_size,
-				    addition_info, &secdesclen, &fattr);
+	max_len = smb2_calc_max_out_buf_len(work,
+			offsetof(struct smb2_query_info_rsp, Buffer),
+			le32_to_cpu(req->OutputBufferLength));
+	if (max_len < 0) {
+		rc = -EINVAL;
+		goto release_acl;
+	}
+
+	scratch_len = smb_acl_sec_desc_scratch_len(&fattr, ppntsd,
+			ppntsd_size, addition_info);
+	if (!scratch_len || scratch_len == SIZE_MAX) {
+		rc = -EFBIG;
+		goto release_acl;
+	}
+
+	pntsd = kvzalloc(scratch_len, KSMBD_DEFAULT_GFP);
+	if (!pntsd) {
+		rc = -ENOMEM;
+		goto release_acl;
+	}
+
+	rc = build_sec_desc(idmap, pntsd, ppntsd, ppntsd_size,
+			addition_info, &secdesclen, &fattr);
+
+release_acl:
 	posix_acl_release(fattr.cf_acls);
 	posix_acl_release(fattr.cf_dacls);
 	kfree(ppntsd);
 	ksmbd_fd_put(work, fp);
+
+	if (!rc && ALIGN(secdesclen, 8) > scratch_len)
+		rc = -EFBIG;
 	if (rc)
-		return rc;
+		goto err_out;
 
+iov_pin:
 	rsp->OutputBufferLength = cpu_to_le32(secdesclen);
-	return 0;
+	rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
+			      rsp, work->response_buf);
+	if (rc)
+		goto err_out;
+
+	rc = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
+			offsetof(struct smb2_query_info_rsp, Buffer),
+			pntsd, secdesclen);
+err_out:
+	if (rc) {
+		rsp->OutputBufferLength = 0;
+		kvfree(pntsd);
+	}
+
+	return rc;
 }
 
 /**
@@ -5799,6 +5859,9 @@ int smb2_query_info(struct ksmbd_work *work)
 		goto err_out;
 	}
 
+	rsp->StructureSize = cpu_to_le16(9);
+	rsp->OutputBufferOffset = cpu_to_le16(72);
+
 	switch (req->InfoType) {
 	case SMB2_O_INFO_FILE:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");
@@ -5819,14 +5882,6 @@ int smb2_query_info(struct ksmbd_work *work)
 	}
 	ksmbd_revert_fsids(work);
 
-	if (!rc) {
-		rsp->StructureSize = cpu_to_le16(9);
-		rsp->OutputBufferOffset = cpu_to_le16(72);
-		rc = ksmbd_iov_pin_rsp(work, (void *)rsp,
-				       offsetof(struct smb2_query_info_rsp, Buffer) +
-					le32_to_cpu(rsp->OutputBufferLength));
-	}
-
 err_out:
 	if (rc < 0) {
 		if (rc == -EACCES)
@@ -5837,6 +5892,8 @@ err_out:
 			rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR;
 		else if (rc == -ENOMEM)
 			rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES;
+		else if (rc == -EINVAL && rsp->hdr.Status == 0)
+			rsp->hdr.Status = STATUS_INVALID_PARAMETER;
 		else if (rc == -EOPNOTSUPP || rsp->hdr.Status == 0)
 			rsp->hdr.Status = STATUS_INVALID_INFO_CLASS;
 		smb2_set_err_rsp(work);
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 49c2abb29bf5..c30d01877c41 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -915,6 +915,49 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 	return 0;
 }
 
+size_t smb_acl_sec_desc_scratch_len(struct smb_fattr *fattr,
+		struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info)
+{
+	size_t len = sizeof(struct smb_ntsd);
+	size_t tmp;
+
+	if (addition_info & OWNER_SECINFO)
+		len += sizeof(struct smb_sid);
+	if (addition_info & GROUP_SECINFO)
+		len += sizeof(struct smb_sid);
+	if (!(addition_info & DACL_SECINFO))
+		return len;
+
+	len += sizeof(struct smb_acl);
+	if (ppntsd && ppntsd_size > 0) {
+		unsigned int dacl_offset = le32_to_cpu(ppntsd->dacloffset);
+
+		if (dacl_offset < ppntsd_size &&
+		    check_add_overflow(len, ppntsd_size - dacl_offset, &len))
+			return 0;
+	}
+
+	if (fattr->cf_acls) {
+		if (check_mul_overflow((size_t)fattr->cf_acls->a_count,
+					2 * sizeof(struct smb_ace), &tmp) ||
+		    check_add_overflow(len, tmp, &len))
+			return 0;
+	} else {
+		/* default/minimum DACL */
+		if (check_add_overflow(len, 5 * sizeof(struct smb_ace), &len))
+			return 0;
+	}
+
+	if (fattr->cf_dacls) {
+		if (check_mul_overflow((size_t)fattr->cf_dacls->a_count,
+					sizeof(struct smb_ace), &tmp) ||
+		    check_add_overflow(len, tmp, &len))
+			return 0;
+	}
+
+	return len;
+}
+
 /* Convert permission bits from mode to equivalent CIFS ACL */
 int build_sec_desc(struct mnt_idmap *idmap,
 		   struct smb_ntsd *pntsd, struct smb_ntsd *ppntsd,
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 355adaee39b8..ab21ba2cd4df 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -101,6 +101,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon,
 		 bool type_check, bool get_write);
 void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid);
 void ksmbd_init_domain(u32 *sub_auth);
+size_t smb_acl_sec_desc_scratch_len(struct smb_fattr *fattr,
+		struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info);
 
 static inline uid_t posix_acl_uid_translate(struct mnt_idmap *idmap,
 					    struct posix_acl_entry *pace)
-- 
cgit v1.2.3


From 742de64b62b690a368dbeb846499eb8ac8ceedb9 Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Fri, 27 Mar 2026 09:30:29 +0100
Subject: kbuild: modules-cpio-pkg: Respect INSTALL_MOD_PATH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The modules-cpio-pkg target added in commit 2a9c8c0b59d3 ("kbuild: add
target to build a cpio containing modules") is incompatible with
initramfs with merged /lib and /usr/lib directories [1]. "/lib" cannot
be a link and directory at the same time.
Respect a non-empty INSTALL_MOD_PATH in the modules-cpio-pkg target so
that `make INSTALL_MOD_PATH=/usr modules-cpio-pkg` results in the same
module install location as `make INSTALL_MOD_PATH=/usr modules_install`.

Tested with Fedora distribution initramfs produced by dracut.

Link: https://systemd.io/THE_CASE_FOR_THE_USR_MERGE/ [1]
Fixes: 2a9c8c0b59d3 ("kbuild: add target to build a cpio containing modules")
Cc: stable@vger.kernel.org
Reviewed-by: Simon Glass <sjg@chromium.org>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Janne Grunau <j@jannau.net>
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Tested-by: Nicolas Schier <nsc@kernel.org>
Reviewed-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Link: https://patch.msgid.link/20260327-kbuild-modules-cpio-pkg-usr-merge-v3-1-ef507dfa006c@jannau.net
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/Makefile.package | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scripts/Makefile.package b/scripts/Makefile.package
index 0ec946f9b905..6d36786ba31c 100644
--- a/scripts/Makefile.package
+++ b/scripts/Makefile.package
@@ -195,7 +195,7 @@ tar%-pkg: linux-$(KERNELRELEASE)-$(ARCH).tar.% FORCE
 .tmp_modules_cpio: FORCE
 	$(Q)$(MAKE) -f $(srctree)/Makefile
 	$(Q)rm -rf $@
-	$(Q)$(MAKE) -f $(srctree)/Makefile INSTALL_MOD_PATH=$@ modules_install
+	$(Q)$(MAKE) -f $(srctree)/Makefile INSTALL_MOD_PATH=$@/$(INSTALL_MOD_PATH) modules_install
 
 quiet_cmd_cpio = CPIO    $@
       cmd_cpio = $(CONFIG_SHELL) $(srctree)/usr/gen_initramfs.sh -o $@ $<
@@ -264,6 +264,7 @@ help:
 	@echo '  tarxz-pkg           - Build the kernel as a xz compressed tarball'
 	@echo '  tarzst-pkg          - Build the kernel as a zstd compressed tarball'
 	@echo '  modules-cpio-pkg    - Build the kernel modules as cpio archive'
+	@echo '                        (uses INSTALL_MOD_PATH inside the archive)'
 	@echo '  perf-tar-src-pkg    - Build the perf source tarball with no compression'
 	@echo '  perf-targz-src-pkg  - Build the perf source tarball with gzip compression'
 	@echo '  perf-tarbz2-src-pkg - Build the perf source tarball with bz2 compression'
-- 
cgit v1.2.3


From deb4605671cfae3b2803cfbbf4739e7245248398 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 25 Mar 2026 18:20:30 -0700
Subject: modpost: Declare extra_warn with unused attribute

A recent strengthening of -Wunused-but-set-variable (enabled with -Wall)
in clang under a new subwarning, -Wunused-but-set-global, points out an
unused static global variable in scripts/mod/modpost.c:

  scripts/mod/modpost.c:59:13: error: variable 'extra_warn' set but not used [-Werror,-Wunused-but-set-global]
     59 | static bool extra_warn;
        |             ^

This variable has been unused since commit 6c6c1fc09de3 ("modpost:
require a MODULE_DESCRIPTION()") but that is expected, as there are
currently no extra warnings at W=1 right now. Declare the variable with
the unused attribute to make it clear to the compiler that this variable
may be unused.

Cc: stable@vger.kernel.org
Fixes: 6c6c1fc09de3 ("modpost: require a MODULE_DESCRIPTION()")
Link: https://patch.msgid.link/20260325-modpost-extra_warn-unused-but-set-global-v1-1-2e84003b7e81@kernel.org
Reviewed-by: Nicolas Schier <nsc@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
---
 scripts/mod/modpost.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 0c25b5ad497b..c3bc801d8b2d 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -56,7 +56,7 @@ static bool allow_missing_ns_imports;
 
 static bool error_occurred;
 
-static bool extra_warn;
+static bool extra_warn __attribute__((unused));
 
 bool target_is_big_endian;
 bool host_is_big_endian;
-- 
cgit v1.2.3


From 71a98248c63c535eaa4d4c22f099b68d902006d0 Mon Sep 17 00:00:00 2001
From: Yasuaki Torimaru <yasuakitorimaru@gmail.com>
Date: Thu, 26 Mar 2026 14:58:00 +0900
Subject: xfrm: clear trailing padding in build_polexpire()

build_expire() clears the trailing padding bytes of struct
xfrm_user_expire after setting the hard field via memset_after(),
but the analogous function build_polexpire() does not do this for
struct xfrm_user_polexpire.

The padding bytes after the __u8 hard field are left
uninitialized from the heap allocation, and are then sent to
userspace via netlink multicast to XFRMNLGRP_EXPIRE listeners,
leaking kernel heap memory contents.

Add the missing memset_after() call, matching build_expire().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Yasuaki Torimaru <yasuakitorimaru@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 1656b487f833..5d59c11fc01e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3960,6 +3960,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
 		return err;
 	}
 	upe->hard = !!hard;
+	/* clear the padding bytes */
+	memset_after(upe, 0, hard);
 
 	nlmsg_end(skb, nlh);
 	return 0;
-- 
cgit v1.2.3


From 7081d46d32312f1a31f0e0e99c6835a394037599 Mon Sep 17 00:00:00 2001
From: Keenan Dong <keenanat2000@gmail.com>
Date: Thu, 26 Mar 2026 20:36:39 +0800
Subject: xfrm: account XFRMA_IF_ID in aevent size calculation

xfrm_get_ae() allocates the reply skb with xfrm_aevent_msgsize(), then
build_aevent() appends attributes including XFRMA_IF_ID when x->if_id is
set.

xfrm_aevent_msgsize() does not include space for XFRMA_IF_ID. For states
with if_id, build_aevent() can fail with -EMSGSIZE and hit BUG_ON(err < 0)
in xfrm_get_ae(), turning a malformed netlink interaction into a kernel
panic.

Account XFRMA_IF_ID in the size calculation unconditionally and replace
the BUG_ON with normal error unwinding.

Fixes: 7e6526404ade ("xfrm: Add a new lookup key to match xfrm interfaces.")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 5d59c11fc01e..a779590c985a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2677,7 +2677,8 @@ static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x)
 	       + nla_total_size(4) /* XFRM_AE_RTHR */
 	       + nla_total_size(4) /* XFRM_AE_ETHR */
 	       + nla_total_size(sizeof(x->dir)) /* XFRMA_SA_DIR */
-	       + nla_total_size(4); /* XFRMA_SA_PCPU */
+	       + nla_total_size(4) /* XFRMA_SA_PCPU */
+	       + nla_total_size(sizeof(x->if_id)); /* XFRMA_IF_ID */
 }
 
 static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
@@ -2789,7 +2790,12 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 	c.portid = nlh->nlmsg_pid;
 
 	err = build_aevent(r_skb, x, &c);
-	BUG_ON(err < 0);
+	if (err < 0) {
+		spin_unlock_bh(&x->lock);
+		xfrm_state_put(x);
+		kfree_skb(r_skb);
+		return err;
+	}
 
 	err = nlmsg_unicast(xfrm_net_nlsk(net, skb), r_skb, NETLINK_CB(skb).portid);
 	spin_unlock_bh(&x->lock);
-- 
cgit v1.2.3


From 4dfce79e098915d8e5fc2b9e1d980bc3251dd32c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 26 Mar 2026 13:18:10 +0200
Subject: drm/i915/dsi: Don't do DSC horizontal timing adjustments in command
 mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Stop adjusting the horizontal timing values based on the
compression ratio in command mode. Bspec seems to be telling
us to do this only in video mode, and this is also how the
Windows driver does things.

This should also fix a div-by-zero on some machines because
the adjusted htotal ends up being so small that we end up with
line_time_us==0 when trying to determine the vtotal value in
command mode.

Note that this doesn't actually make the display on the
Huawei Matebook E work, but at least the kernel no longer
explodes when the driver loads.

Cc: stable@vger.kernel.org
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12045
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260326111814.9800-2-ville.syrjala@linux.intel.com
Fixes: 53693f02d80e ("drm/i915/dsi: account for DSC in horizontal timings")
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 0b475e91ecc2313207196c6d7fd5c53e1a878525)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index fc265f71d72b..298b3a48197c 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -889,7 +889,7 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	 * non-compressed link speeds, and simplifies down to the ratio between
 	 * compressed and non-compressed bpp.
 	 */
-	if (crtc_state->dsc.compression_enable) {
+	if (is_vid_mode(intel_dsi) && crtc_state->dsc.compression_enable) {
 		mul = fxp_q4_to_int(crtc_state->dsc.compressed_bpp_x16);
 		div = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	}
@@ -1503,7 +1503,7 @@ static void gen11_dsi_get_timings(struct intel_encoder *encoder,
 	struct drm_display_mode *adjusted_mode =
 					&pipe_config->hw.adjusted_mode;
 
-	if (pipe_config->dsc.compressed_bpp_x16) {
+	if (is_vid_mode(intel_dsi) && pipe_config->dsc.compressed_bpp_x16) {
 		int div = fxp_q4_to_int(pipe_config->dsc.compressed_bpp_x16);
 		int mul = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 
-- 
cgit v1.2.3


From 45424e871abf2a152e247a9cff78359f18dd95c0 Mon Sep 17 00:00:00 2001
From: Berk Cem Goksel <berkcgoksel@gmail.com>
Date: Sun, 29 Mar 2026 16:38:25 +0300
Subject: ALSA: caiaq: fix stack out-of-bounds read in init_card

The loop creates a whitespace-stripped copy of the card shortname
where `len < sizeof(card->id)` is used for the bounds check. Since
sizeof(card->id) is 16 and the local id buffer is also 16 bytes,
writing 16 non-space characters fills the entire buffer,
overwriting the terminating nullbyte.

When this non-null-terminated string is later passed to
snd_card_set_id() -> copy_valid_id_string(), the function scans
forward with `while (*nid && ...)` and reads past the end of the
stack buffer, reading the contents of the stack.

A USB device with a product name containing many non-ASCII, non-space
characters (e.g. multibyte UTF-8) will reliably trigger this as follows:

  BUG: KASAN: stack-out-of-bounds in copy_valid_id_string
       sound/core/init.c:696 [inline]
  BUG: KASAN: stack-out-of-bounds in snd_card_set_id_no_lock+0x698/0x74c
       sound/core/init.c:718

The off-by-one has been present since commit bafeee5b1f8d ("ALSA:
snd_usb_caiaq: give better shortname") from June 2009 (v2.6.31-rc1),
which first introduced this whitespace-stripping loop. The original
code never accounted for the null terminator when bounding the copy.

Fix this by changing the loop bound to `sizeof(card->id) - 1`,
ensuring at least one byte remains as the null terminator.

Fixes: bafeee5b1f8d ("ALSA: snd_usb_caiaq: give better shortname")
Cc: stable@vger.kernel.org
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Reported-by: Berk Cem Goksel <berkcgoksel@gmail.com>
Signed-off-by: Berk Cem Goksel <berkcgoksel@gmail.com>
Link: https://patch.msgid.link/20260329133825.581585-1-berkcgoksel@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/caiaq/device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c
index dfd820483849..3a71bab8a477 100644
--- a/sound/usb/caiaq/device.c
+++ b/sound/usb/caiaq/device.c
@@ -488,7 +488,7 @@ static int init_card(struct snd_usb_caiaqdev *cdev)
 		memset(id, 0, sizeof(id));
 
 		for (c = card->shortname, len = 0;
-			*c && len < sizeof(card->id); c++)
+			*c && len < sizeof(card->id) - 1; c++)
 			if (*c != ' ')
 				id[len++] = *c;
 
-- 
cgit v1.2.3


From f025ac8c698ac7d29eb3b5025bcdaf7ad675785d Mon Sep 17 00:00:00 2001
From: Dag Smedberg <dag@dsmedberg.se>
Date: Sun, 29 Mar 2026 19:04:20 +0200
Subject: ALSA: usb-audio: Exclude Scarlett Solo 1st Gen from SKIP_IFACE_SETUP

Same issue that the Scarlett 2i2 1st Gen had:
QUIRK_FLAG_SKIP_IFACE_SETUP causes distorted audio on the
Scarlett Solo 1st Gen (1235:801c).

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Reported-by: Dag Smedberg <dag@dsmedberg.se>
Tested-by: Dag Smedberg <dag@dsmedberg.se>
Signed-off-by: Dag Smedberg <dag@dsmedberg.se>
Link: https://patch.msgid.link/20260329170420.4122-1-dag@dsmedberg.se
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 6e40c18c37f9..116da076a194 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2435,6 +2435,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_VALIDATE_RATES),
 	DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */
 	DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */
+	DEVICE_FLG(0x1235, 0x801c, 0), /* Focusrite Scarlett Solo 1st Gen */
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
 		   QUIRK_FLAG_SKIP_IFACE_SETUP),
-- 
cgit v1.2.3


From 3d48c9fd78dd0b1809669ec49c4d0997b8127512 Mon Sep 17 00:00:00 2001
From: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Date: Fri, 27 Mar 2026 17:41:56 +0500
Subject: dma-debug: suppress cacheline overlap warning when arch has no DMA
 alignment requirement

When CONFIG_DMA_API_DEBUG is enabled, the DMA debug infrastructure
tracks active mappings per cacheline and warns if two different DMA
mappings share the same cacheline ("cacheline tracking EEXIST,
overlapping mappings aren't supported").

On x86_64, ARCH_KMALLOC_MINALIGN defaults to 8, so small kmalloc
allocations (e.g. the 8-byte hub->buffer and hub->status in the USB
hub driver) frequently land in the same 64-byte cacheline.  When both
are DMA-mapped, this triggers a false positive warning.

This has been reported repeatedly since v5.14 (when the EEXIST check
was added) across various USB host controllers and devices including
xhci_hcd with USB hubs, USB audio devices, and USB ethernet adapters.

The cacheline overlap is only a real concern on architectures that
require DMA buffer alignment to cacheline boundaries (i.e. where
ARCH_DMA_MINALIGN >= L1_CACHE_BYTES).  On architectures like x86_64
where dma_get_cache_alignment() returns 1, the hardware is
cache-coherent and overlapping cacheline mappings are harmless.

Suppress the EEXIST warning when dma_get_cache_alignment() is less
than L1_CACHE_BYTES, indicating the architecture does not require
cacheline-aligned DMA buffers.

Verified with a kernel module reproducer that performs two kmalloc(8)
allocations back-to-back and DMA-maps both:

  Before: allocations share a cacheline, EEXIST fires within ~50 pairs
  After:  same cacheline pair found, but no warning emitted

Fixes: 2b4bbc6231d7 ("dma-debug: report -EEXIST errors in add_dma_entry")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215740
Suggested-by: Harry Yoo <harry@kernel.org>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260327124156.24820-1-mikhail.v.gavrilov@gmail.com
---
 kernel/dma/debug.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 0677918f06a8..1a725edbbbf6 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -615,6 +615,7 @@ static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
 	} else if (rc == -EEXIST &&
 		   !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 		   !(entry->is_cache_clean && overlap_cache_clean) &&
+		   dma_get_cache_alignment() >= L1_CACHE_BYTES &&
 		   !(IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) &&
 		     is_swiotlb_active(entry->dev))) {
 		err_printk(entry->dev, entry,
-- 
cgit v1.2.3


From 310a4a9cbb17037668ea440f6a3964d00705b400 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Date: Wed, 25 Mar 2026 12:06:38 +0100
Subject: gpio: shared: shorten the critical section in gpiochip_setup_shared()

Commit 710abda58055 ("gpio: shared: call gpio_chip::of_xlate() if set")
introduced a critical section around the adjustmenet of entry->offset.
However this may cause a deadlock if we create the auxiliary shared
proxy devices with this lock taken. We only need to protect
entry->offset while it's read/written so shorten the critical section
and release the lock before creating the proxy device as the field in
question is no longer accessed at this point.

Fixes: 710abda58055 ("gpio: shared: call gpio_chip::of_xlate() if set")
Reported-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://patch.msgid.link/20260325-gpio-shared-deadlock-v1-1-e4e7a5319e95@oss.qualcomm.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpiolib-shared.c | 56 +++++++++++++++++++++----------------------
 1 file changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c
index e257212fa5e3..e02d6b93a4ab 100644
--- a/drivers/gpio/gpiolib-shared.c
+++ b/drivers/gpio/gpiolib-shared.c
@@ -533,48 +533,48 @@ int gpiochip_setup_shared(struct gpio_chip *gc)
 	 * exposing shared pins. Find them and create the proxy devices.
 	 */
 	list_for_each_entry(entry, &gpio_shared_list, list) {
-		guard(mutex)(&entry->lock);
-
 		if (!device_match_fwnode(&gdev->dev, entry->fwnode))
 			continue;
 
 		if (list_count_nodes(&entry->refs) <= 1)
 			continue;
 
+		scoped_guard(mutex, &entry->lock) {
 #if IS_ENABLED(CONFIG_OF)
-		if (is_of_node(entry->fwnode) && gc->of_xlate) {
-			/*
-			 * This is the earliest that we can tranlate the
-			 * devicetree offset to the chip offset.
-			 */
-			struct of_phandle_args gpiospec = { };
+			if (is_of_node(entry->fwnode) && gc->of_xlate) {
+				/*
+				 * This is the earliest that we can tranlate the
+				 * devicetree offset to the chip offset.
+				 */
+				struct of_phandle_args gpiospec = { };
 
-			gpiospec.np = to_of_node(entry->fwnode);
-			gpiospec.args_count = 2;
-			gpiospec.args[0] = entry->offset;
+				gpiospec.np = to_of_node(entry->fwnode);
+				gpiospec.args_count = 2;
+				gpiospec.args[0] = entry->offset;
 
-			ret = gc->of_xlate(gc, &gpiospec, NULL);
-			if (ret < 0)
-				return ret;
+				ret = gc->of_xlate(gc, &gpiospec, NULL);
+				if (ret < 0)
+					return ret;
 
-			entry->offset = ret;
-		}
+				entry->offset = ret;
+			}
 #endif /* CONFIG_OF */
 
-		desc = &gdev->descs[entry->offset];
+			desc = &gdev->descs[entry->offset];
 
-		__set_bit(GPIOD_FLAG_SHARED, &desc->flags);
-		/*
-		 * Shared GPIOs are not requested via the normal path. Make
-		 * them inaccessible to anyone even before we register the
-		 * chip.
-		 */
-		ret = gpiod_request_commit(desc, "shared");
-		if (ret)
-			return ret;
+			__set_bit(GPIOD_FLAG_SHARED, &desc->flags);
+			/*
+			 * Shared GPIOs are not requested via the normal path. Make
+			 * them inaccessible to anyone even before we register the
+			 * chip.
+			 */
+			ret = gpiod_request_commit(desc, "shared");
+			if (ret)
+				return ret;
 
-		pr_debug("GPIO %u owned by %s is shared by multiple consumers\n",
-			 entry->offset, gpio_device_get_label(gdev));
+			pr_debug("GPIO %u owned by %s is shared by multiple consumers\n",
+				 entry->offset, gpio_device_get_label(gdev));
+		}
 
 		list_for_each_entry(ref, &entry->refs, list) {
 			pr_debug("Setting up a shared GPIO entry for %s (con_id: '%s')\n",
-- 
cgit v1.2.3


From 6b5ef8c88854b343b733b574ea8754c9dab61f41 Mon Sep 17 00:00:00 2001
From: Jamie Gibbons <jamie.gibbons@microchip.com>
Date: Thu, 26 Mar 2026 17:02:34 +0000
Subject: dt-bindings: gpio: fix microchip #interrupt-cells

The GPIO controller on PolarFire SoC supports more than one type of
interrupt and needs two interrupt cells.

Fixes: 735806d8a68e9 ("dt-bindings: gpio: add bindings for microchip mpfs gpio")
Signed-off-by: Jamie Gibbons <jamie.gibbons@microchip.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://patch.msgid.link/20260326-wise-gumdrop-49217723a72a@spud
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml b/Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml
index 184432d24ea1..f42c54653d52 100644
--- a/Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml
+++ b/Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml
@@ -37,7 +37,7 @@ properties:
     const: 2
 
   "#interrupt-cells":
-    const: 1
+    const: 2
 
   ngpios:
     description:
@@ -86,7 +86,7 @@ examples:
         gpio-controller;
         #gpio-cells = <2>;
         interrupt-controller;
-        #interrupt-cells = <1>;
+        #interrupt-cells = <2>;
         interrupts = <53>, <53>, <53>, <53>,
                      <53>, <53>, <53>, <53>,
                      <53>, <53>, <53>, <53>,
-- 
cgit v1.2.3


From f1af71d568e55536d9297bfa7907ad497108cf30 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 30 Mar 2026 15:53:34 +0800
Subject: ALSA: hda/realtek: Add quirk for ASUS ROG Strix SCAR 15

ASUS ROG Strix SCAR 15, like the Strix G15, requires the
ALC285_FIXUP_ASUS_G533Z_PINS quirk to work properly.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221247
Cc: <stable@vger.kernel.org>
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260330075334.50962-2-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 78ab0e86621b..c14046e09aa4 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7269,6 +7269,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301VV/VQ/VU/VJ/VA/VC/VE/VVC/VQC/VUC/VJC/VEC/VCC", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1584, "ASUS UM3406GA ", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1602, "ASUS ROG Strix SCAR 15", ALC285_FIXUP_ASUS_G533Z_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1652, "ASUS ROG Zephyrus Do 15 SE", ALC289_FIXUP_ASUS_ZEPHYRUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZI/ZJ/ZQ/ZU/ZV", ALC285_FIXUP_ASUS_HEADSET_MIC),
-- 
cgit v1.2.3


From 917e3ad3321e75ca0223d5ccf26ceda116aa51e1 Mon Sep 17 00:00:00 2001
From: Aleksandr Nogikh <nogikh@google.com>
Date: Wed, 25 Mar 2026 16:48:24 +0100
Subject: x86/kexec: Disable KCOV instrumentation after load_segments()

The load_segments() function changes segment registers, invalidating GS base
(which KCOV relies on for per-cpu data). When CONFIG_KCOV is enabled, any
subsequent instrumented C code call (e.g. native_gdt_invalidate()) begins
crashing the kernel in an endless loop.

To reproduce the problem, it's sufficient to do kexec on a KCOV-instrumented
kernel:

  $ kexec -l /boot/otherKernel
  $ kexec -e

The real-world context for this problem is enabling crash dump collection in
syzkaller. For this, the tool loads a panic kernel before fuzzing and then
calls makedumpfile after the panic. This workflow requires both CONFIG_KEXEC
and CONFIG_KCOV to be enabled simultaneously.

Adding safeguards directly to the KCOV fast-path (__sanitizer_cov_trace_pc())
is also undesirable as it would introduce an extra performance overhead.

Disabling instrumentation for the individual functions would be too fragile,
so disable KCOV instrumentation for the entire machine_kexec_64.c and
physaddr.c. If coverage-guided fuzzing ever needs these components in the
future, other approaches should be considered.

The problem is not relevant for 32 bit kernels as CONFIG_KCOV is not supported
there.

  [ bp: Space out comment for better readability. ]

Fixes: 0d345996e4cb ("x86/kernel: increase kcov coverage under arch/x86/kernel folder")
Signed-off-by: Aleksandr Nogikh <nogikh@google.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260325154825.551191-1-nogikh@google.com
---
 arch/x86/kernel/Makefile | 14 ++++++++++++++
 arch/x86/mm/Makefile     |  2 ++
 2 files changed, 16 insertions(+)

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e9aeeeafad17..47a32f583930 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,20 @@ KCOV_INSTRUMENT_unwind_orc.o				:= n
 KCOV_INSTRUMENT_unwind_frame.o				:= n
 KCOV_INSTRUMENT_unwind_guess.o				:= n
 
+# Disable KCOV to prevent crashes during kexec: load_segments() invalidates
+# the GS base, which KCOV relies on for per-CPU data.
+#
+# As KCOV and KEXEC compatibility should be preserved (e.g. syzkaller is
+# using it to collect crash dumps during kernel fuzzing), disabling
+# KCOV for KEXEC kernels is not an option. Selectively disabling KCOV
+# instrumentation for individual affected functions can be fragile, while
+# adding more checks to KCOV would slow it down.
+#
+# As a compromise solution, disable KCOV instrumentation for the whole
+# source code file. If its coverage is ever needed, other approaches
+# should be considered.
+KCOV_INSTRUMENT_machine_kexec_64.o			:= n
+
 CFLAGS_head32.o := -fno-stack-protector
 CFLAGS_head64.o := -fno-stack-protector
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 5b9908f13dcf..3a5364853eab 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -4,6 +4,8 @@ KCOV_INSTRUMENT_tlb.o			:= n
 KCOV_INSTRUMENT_mem_encrypt.o		:= n
 KCOV_INSTRUMENT_mem_encrypt_amd.o	:= n
 KCOV_INSTRUMENT_pgprot.o		:= n
+# See the "Disable KCOV" comment in arch/x86/kernel/Makefile.
+KCOV_INSTRUMENT_physaddr.o		:= n
 
 KASAN_SANITIZE_mem_encrypt.o		:= n
 KASAN_SANITIZE_mem_encrypt_amd.o	:= n
-- 
cgit v1.2.3


From 73cd1f97946ae3796544448ff12c07f399bb2881 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 29 Mar 2026 19:14:05 +0800
Subject: spi: stm32-ospi: Fix resource leak in remove() callback

The remove() callback returned early if pm_runtime_resume_and_get()
failed, skipping the cleanup of spi controller and other resources.

Remove the early return so cleanup completes regardless of PM resume
result.

Fixes: 79b8a705e26c ("spi: stm32: Add OSPI driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Patrice Chotard <patrice.chotard@foss.st.com>
Link: https://patch.msgid.link/20260329-ospi-v1-1-cc8cf1c82c4a@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32-ospi.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index c98afe02a1b6..2baf651c0a6d 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -989,11 +989,8 @@ err_pm_enable:
 static void stm32_ospi_remove(struct platform_device *pdev)
 {
 	struct stm32_ospi *ospi = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pm_runtime_resume_and_get(ospi->dev);
-	if (ret < 0)
-		return;
+	pm_runtime_resume_and_get(ospi->dev);
 
 	spi_unregister_controller(ospi->ctrl);
 	/* Disable ospi */
-- 
cgit v1.2.3


From 5a570c8d6e55689253f6fcc4a198c56cca7e39d6 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 29 Mar 2026 00:07:06 +0800
Subject: spi: stm32-ospi: Fix reset control leak on probe error

When spi_register_controller() fails after reset_control_acquire()
succeeds, the reset control is never released. This causes a resource
leak in the error path.

Add the missing reset_control_release() call in the error path.

Fixes: cf2c3eceb757 ("spi: stm32-ospi: Make usage of reset_control_acquire/release() API")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Patrice Chotard <patrice.chotard@foss.st.com>
Link: https://patch.msgid.link/20260329-stm32-ospi-v1-1-142122466412@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32-ospi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 2baf651c0a6d..c9f92e85253f 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -965,13 +965,15 @@ static int stm32_ospi_probe(struct platform_device *pdev)
 	if (ret) {
 		/* Disable ospi */
 		writel_relaxed(0, ospi->regs_base + OSPI_CR);
-		goto err_pm_resume;
+		goto err_reset_control;
 	}
 
 	pm_runtime_put_autosuspend(ospi->dev);
 
 	return 0;
 
+err_reset_control:
+	reset_control_release(ospi->rstc);
 err_pm_resume:
 	pm_runtime_put_sync_suspend(ospi->dev);
 
-- 
cgit v1.2.3


From 534025950c9fe4dfbe476b3938d73a26814047d1 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 29 Mar 2026 00:07:07 +0800
Subject: spi: stm32-ospi: Fix DMA channel leak on stm32_ospi_dma_setup()
 failure

When stm32_ospi_dma_setup() fails, the DMA channels allocated by
stm32_ospi_get_resources() were never released. Add proper cleanup
in the error path.

Fixes: e35a7607e05d ("spi: stm32-ospi: Set DMA maxburst dynamically")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Patrice Chotard <patrice.chotard@foss.st.com>
Link: https://patch.msgid.link/20260329-stm32-ospi-v1-2-142122466412@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32-ospi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index c9f92e85253f..38405f8f547f 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -928,7 +928,7 @@ static int stm32_ospi_probe(struct platform_device *pdev)
 	dma_cfg.dst_addr = ospi->regs_phys_base + OSPI_DR;
 	ret = stm32_ospi_dma_setup(ospi, &dma_cfg);
 	if (ret)
-		return ret;
+		goto err_dma_free;
 
 	mutex_init(&ospi->lock);
 
@@ -980,6 +980,7 @@ err_pm_resume:
 err_pm_enable:
 	pm_runtime_force_suspend(ospi->dev);
 	mutex_destroy(&ospi->lock);
+err_dma_free:
 	if (ospi->dma_chtx)
 		dma_release_channel(ospi->dma_chtx);
 	if (ospi->dma_chrx)
-- 
cgit v1.2.3


From 6d192b4f2d644d15d9a9f1d33dab05af936f6540 Mon Sep 17 00:00:00 2001
From: Jonathan Cavitt <jonathan.cavitt@intel.com>
Date: Tue, 24 Mar 2026 15:29:37 +0000
Subject: drm/xe/xe_pagefault: Disallow writes to read-only VMAs

The page fault handler should reject write/atomic access to read only
VMAs.  Add code to handle this in xe_pagefault_service after the VMA
lookup.

v2:
- Apply max line length (Matthew)

Fixes: fb544b844508 ("drm/xe: Implement xe_pagefault_queue_work")
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260324152935.72444-7-jonathan.cavitt@intel.com
(cherry picked from commit 714ee6754ac5fa3dc078856a196a6b124cd797a0)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pagefault.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
index 6bee53d6ffc3..922a4f3344b1 100644
--- a/drivers/gpu/drm/xe/xe_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_pagefault.c
@@ -187,6 +187,12 @@ static int xe_pagefault_service(struct xe_pagefault *pf)
 		goto unlock_vm;
 	}
 
+	if (xe_vma_read_only(vma) &&
+	    pf->consumer.access_type != XE_PAGEFAULT_ACCESS_TYPE_READ) {
+		err = -EPERM;
+		goto unlock_vm;
+	}
+
 	atomic = xe_pagefault_access_is_atomic(pf->consumer.access_type);
 
 	if (xe_vma_is_cpu_addr_mirror(vma))
-- 
cgit v1.2.3


From 7b9a3a910e96f20b101b0df6b1f5c77b023a4097 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav@intel.com>
Date: Thu, 26 Mar 2026 18:38:38 +0530
Subject: drm/xe/madvise: Accept canonical GPU addresses in xe_vm_madvise_ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userspace passes canonical (sign-extended) GPU addresses where bits 63:48
mirror bit 47. The internal GPUVM uses non-canonical form (upper bits
zeroed), so passing raw canonical addresses into GPUVM lookups causes
mismatches for addresses above 128TiB.

Strip the sign extension with xe_device_uncanonicalize_addr() at the
top of xe_vm_madvise_ioctl(). Non-canonical addresses are unaffected.

Fixes: ada7486c5668 ("drm/xe: Implement madvise ioctl for xe")
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Arvind Yadav <arvind.yadav@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260326130843.3545241-13-arvind.yadav@intel.com
(cherry picked from commit 05c8b1cdc54036465ea457a0501a8c2f9409fce7)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index bc39a9a9790c..b4086129a364 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -408,8 +408,15 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	struct xe_device *xe = to_xe_device(dev);
 	struct xe_file *xef = to_xe_file(file);
 	struct drm_xe_madvise *args = data;
-	struct xe_vmas_in_madvise_range madvise_range = {.addr = args->start,
-							 .range =  args->range, };
+	struct xe_vmas_in_madvise_range madvise_range = {
+		/*
+		 * Userspace may pass canonical (sign-extended) addresses.
+		 * Strip the sign extension to get the internal non-canonical
+		 * form used by the GPUVM, matching xe_vm_bind_ioctl() behavior.
+		 */
+		.addr = xe_device_uncanonicalize_addr(xe, args->start),
+		.range = args->range,
+	};
 	struct xe_madvise_details details;
 	struct xe_vm *vm;
 	struct drm_exec exec;
@@ -439,7 +446,7 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	if (err)
 		goto unlock_vm;
 
-	err = xe_vm_alloc_madvise_vma(vm, args->start, args->range);
+	err = xe_vm_alloc_madvise_vma(vm, madvise_range.addr, args->range);
 	if (err)
 		goto madv_fini;
 
@@ -482,7 +489,8 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 	madvise_funcs[attr_type](xe, vm, madvise_range.vmas, madvise_range.num_vmas, args,
 				 &details);
 
-	err = xe_vm_invalidate_madvise_range(vm, args->start, args->start + args->range);
+	err = xe_vm_invalidate_madvise_range(vm, madvise_range.addr,
+					     madvise_range.addr + args->range);
 
 	if (madvise_range.has_svm_userptr_vmas)
 		xe_svm_notifier_unlock(vm);
-- 
cgit v1.2.3


From e2628e670bb0923fcdc00828bfcd67b26a7df020 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 24 Mar 2026 08:37:20 -0700
Subject: drm/xe/pxp: Clean up termination status on failure

If the PXP HW termination fails during PXP start, the normal completion
code won't be called, so the termination will remain uncomplete. To avoid
unnecessary waits, mark the termination as completed from the error path.
Note that we already do this if the termination fails when handling a
termination irq from the HW.

Fixes: f8caa80154c4 ("drm/xe/pxp: Add PXP queue tracking and session start")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn Teres Alexis <alan.previn.teres.alexis@intel.com>
Cc: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Julia Filipchuk <julia.filipchuk@intel.com>
Link: https://patch.msgid.link/20260324153718.3155504-7-daniele.ceraolospurio@intel.com
(cherry picked from commit 5d9e708d2a69ab1f64a17aec810cd7c70c5b9fab)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pxp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c
index d61446bf9c19..782281dbe9e0 100644
--- a/drivers/gpu/drm/xe/xe_pxp.c
+++ b/drivers/gpu/drm/xe/xe_pxp.c
@@ -583,6 +583,7 @@ wait_for_idle:
 			drm_err(&pxp->xe->drm, "PXP termination failed before start\n");
 			mutex_lock(&pxp->mutex);
 			pxp->status = XE_PXP_ERROR;
+			complete_all(&pxp->termination);
 
 			goto out_unlock;
 		}
-- 
cgit v1.2.3


From 4fed244954c2dc9aafa333d08f66b14345225e03 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 24 Mar 2026 08:37:21 -0700
Subject: drm/xe/pxp: Remove incorrect handling of impossible state during
 suspend

The default case of the PXP suspend switch is incorrectly exiting
without releasing the lock. However, this case is impossible to hit
because we're switching on an enum and all the valid enum values have
their own cases. Therefore, we can just get rid of the default case
and rely on the compiler to warn us if a new enum value is added and
we forget to add it to the switch.

Fixes: 51462211f4a9 ("drm/xe/pxp: add PXP PM support")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Alan Previn Teres Alexis <alan.previn.teres.alexis@intel.com>
Cc: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Julia Filipchuk <julia.filipchuk@intel.com>
Link: https://patch.msgid.link/20260324153718.3155504-8-daniele.ceraolospurio@intel.com
(cherry picked from commit f1b5a77fc9b6a90cd9a5e3db9d4c73ae1edfcfac)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pxp.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c
index 782281dbe9e0..fa82d606953e 100644
--- a/drivers/gpu/drm/xe/xe_pxp.c
+++ b/drivers/gpu/drm/xe/xe_pxp.c
@@ -871,11 +871,6 @@ wait_for_activation:
 		pxp->key_instance++;
 		needs_queue_inval = true;
 		break;
-	default:
-		drm_err(&pxp->xe->drm, "unexpected state during PXP suspend: %u",
-			pxp->status);
-		ret = -EIO;
-		goto out;
 	}
 
 	/*
@@ -900,7 +895,6 @@ wait_for_activation:
 
 	pxp->last_suspend_key_instance = pxp->key_instance;
 
-out:
 	return ret;
 }
 
-- 
cgit v1.2.3


From 76903b2057c8677c2c006e87fede15f496555dc0 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 24 Mar 2026 08:37:22 -0700
Subject: drm/xe/pxp: Clear restart flag in pxp_start after jumping back

If we don't clear the flag we'll keep jumping back at the beginning of
the function once we reach the end.

Fixes: ccd3c6820a90 ("drm/xe/pxp: Decouple queue addition from PXP start")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Julia Filipchuk <julia.filipchuk@intel.com>
Link: https://patch.msgid.link/20260324153718.3155504-9-daniele.ceraolospurio@intel.com
(cherry picked from commit 0850ec7bb2459602351639dccf7a68a03c9d1ee0)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pxp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c
index fa82d606953e..088a1ab75f70 100644
--- a/drivers/gpu/drm/xe/xe_pxp.c
+++ b/drivers/gpu/drm/xe/xe_pxp.c
@@ -512,7 +512,7 @@ static int __exec_queue_add(struct xe_pxp *pxp, struct xe_exec_queue *q)
 static int pxp_start(struct xe_pxp *pxp, u8 type)
 {
 	int ret = 0;
-	bool restart = false;
+	bool restart;
 
 	if (!xe_pxp_is_enabled(pxp))
 		return -ENODEV;
@@ -541,6 +541,8 @@ wait_for_idle:
 					 msecs_to_jiffies(PXP_ACTIVATION_TIMEOUT_MS)))
 		return -ETIMEDOUT;
 
+	restart = false;
+
 	mutex_lock(&pxp->mutex);
 
 	/* If PXP is not already active, turn it on */
-- 
cgit v1.2.3


From e3fb579872a8d9cf264c52710d5839de3afa6fc1 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 24 Mar 2026 08:37:23 -0700
Subject: drm/xe/pxp: Don't allow PXP on older PTL GSC FWs

On PTL, older GSC FWs have a bug that can cause them to crash during
PXP invalidation events, which leads to a complete loss of power
management on the media GT. Therefore, we can't use PXP on FWs that
have this bug, which was fixed in PTL GSC build 1396.

Fixes: b1dcec9bd8a1 ("drm/xe/ptl: Enable PXP for PTL")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Julia Filipchuk <julia.filipchuk@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patch.msgid.link/20260324153718.3155504-10-daniele.ceraolospurio@intel.com
(cherry picked from commit 6eb04caaa972934c9b6cea0e0c29e466bf9a346f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pxp.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_pxp.c b/drivers/gpu/drm/xe/xe_pxp.c
index 088a1ab75f70..872217f30375 100644
--- a/drivers/gpu/drm/xe/xe_pxp.c
+++ b/drivers/gpu/drm/xe/xe_pxp.c
@@ -380,6 +380,18 @@ int xe_pxp_init(struct xe_device *xe)
 		return 0;
 	}
 
+	/*
+	 * On PTL, older GSC FWs have a bug that can cause them to crash during
+	 * PXP invalidation events, which leads to a complete loss of power
+	 * management on the media GT. Therefore, we can't use PXP on FWs that
+	 * have this bug, which was fixed in PTL GSC build 1396.
+	 */
+	if (xe->info.platform == XE_PANTHERLAKE &&
+	    gt->uc.gsc.fw.versions.found[XE_UC_FW_VER_RELEASE].build < 1396) {
+		drm_info(&xe->drm, "PXP requires PTL GSC build 1396 or newer\n");
+		return 0;
+	}
+
 	pxp = drmm_kzalloc(&xe->drm, sizeof(struct xe_pxp), GFP_KERNEL);
 	if (!pxp) {
 		err = -ENOMEM;
-- 
cgit v1.2.3


From bce7cd6db2386e7a2b49ad3c09df0beabddfa3c4 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 26 Feb 2026 17:52:25 -0800
Subject: drm/xe: Disable garbage collector work item on SVM close
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When an SVM is closed, the garbage collector work item must be stopped
synchronously and any future queuing must be prevented. Replace
flush_work() with disable_work_sync() to ensure both conditions are
met.

Fixes: 63f6e480d115 ("drm/xe: Add SVM garbage collector")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/20260227015225.3081787-1-matthew.brost@intel.com
(cherry picked from commit 2247feb9badca5a4774df9a437bfc44fba4f22de)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index ca67d0bdbfac..c6b92d4ea6f4 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -903,7 +903,7 @@ int xe_svm_init(struct xe_vm *vm)
 void xe_svm_close(struct xe_vm *vm)
 {
 	xe_assert(vm->xe, xe_vm_is_closed(vm));
-	flush_work(&vm->svm.garbage_collector.work);
+	disable_work_sync(&vm->svm.garbage_collector.work);
 	xe_svm_put_pagemaps(vm);
 	drm_pagemap_release_owner(&vm->svm.peer);
 }
-- 
cgit v1.2.3


From 56b7432b7e8e6ae1b289cb405d16db4150ef193b Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 26 Mar 2026 14:01:15 -0700
Subject: drm/xe: Avoid memory allocations in xe_device_declare_wedged()

xe_device_declare_wedged() runs in the DMA-fence signaling path, where
GFP_KERNEL memory allocations are not allowed. However, registering
xe_device_wedged_fini via drmm_add_action_or_reset() triggers a
GFP_KERNEL allocation.

Fix this by deferring the registration of xe_device_wedged_fini until
late in the driver load sequence. Additionally, drop the wedged PM
reference only if the device is actually wedged in
xe_device_wedged_fini.

Fixes: 452bca0edbd0 ("drm/xe: Don't suspend device upon wedge")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patch.msgid.link/20260326210116.202585-2-matthew.brost@intel.com
(cherry picked from commit b08ceb443866808b881b12d4183008d214d816c1)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 27 +++++++++++++--------------
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 52ee24e9cd3a..3eb06b27db7e 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -837,6 +837,14 @@ static void detect_preproduction_hw(struct xe_device *xe)
 	}
 }
 
+static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
+{
+	struct xe_device *xe = arg;
+
+	if (atomic_read(&xe->wedged.flag))
+		xe_pm_runtime_put(xe);
+}
+
 int xe_device_probe(struct xe_device *xe)
 {
 	struct xe_tile *tile;
@@ -1013,6 +1021,10 @@ int xe_device_probe(struct xe_device *xe)
 
 	detect_preproduction_hw(xe);
 
+	err = drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe);
+	if (err)
+		goto err_unregister_display;
+
 	return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe);
 
 err_unregister_display:
@@ -1216,13 +1228,6 @@ u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address)
 	return address & GENMASK_ULL(xe->info.va_bits - 1, 0);
 }
 
-static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
-{
-	struct xe_device *xe = arg;
-
-	xe_pm_runtime_put(xe);
-}
-
 /**
  * DOC: Xe Device Wedging
  *
@@ -1300,15 +1305,9 @@ void xe_device_declare_wedged(struct xe_device *xe)
 		return;
 	}
 
-	xe_pm_runtime_get_noresume(xe);
-
-	if (drmm_add_action_or_reset(&xe->drm, xe_device_wedged_fini, xe)) {
-		drm_err(&xe->drm, "Failed to register xe_device_wedged_fini clean-up. Although device is wedged.\n");
-		return;
-	}
-
 	if (!atomic_xchg(&xe->wedged.flag, 1)) {
 		xe->needs_flr_on_fini = true;
+		xe_pm_runtime_get_noresume(xe);
 		drm_err(&xe->drm,
 			"CRITICAL: Xe has declared device %s as wedged.\n"
 			"IOCTLs and executions are blocked. Only a rebind may clear the failure\n"
-- 
cgit v1.2.3


From 11b72b1ca9891c77bc876ef9fc39d6825847ffee Mon Sep 17 00:00:00 2001
From: Ziyue Zhang <ziyue.zhang@oss.qualcomm.com>
Date: Mon, 30 Mar 2026 10:09:34 +0800
Subject: arm64: dts: qcom: hamoa: Fix incomplete Root Port property migration

Historically, the Qualcomm PCIe controller node (Host bridge) described
all Root Port properties, such as PHY, PERST#, and WAKE#. But to provide
a more accurate hardware description and to support future multi-Root Port
controllers, these properties were moved to the Root Port node in the
devicetree bindings.

Commit 960609b22be5 ("arm64: dts: qcom: hamoa: Move PHY, PERST, and Wake
GPIOs to PCIe port nodes and add port Nodes for all PCIe ports")
initiated this transition for the Hamoa platform by moving the PHY
property to the Root Port node in hamoa.dtsi. However, it only updated
some platform specific DTS files for PERST# and WAKE#, leaving others in
a "mixed" binding state.

While the PCIe controller driver supports both legacy and Root Port
bindings, It cannot correctly handle a mix of both. In these cases, the
driver parses the PHY from the Root Port node, but fails to find the
PERST# property (which it then assumes is not present, as it is optional).
Consequently, the controller probe succeeds, but PERST# remains
uncontrolled, preventing PCIe endpoints from functioning.

So, fix the incomplete migration by moving the PERST# and WAKE# properties
from the controller node to the Root Port node in all remaining Hamoa
platform DTS files.

Fixes: 960609b22be5 ("arm64: dts: qcom: hamoa: Move PHY, PERST, and Wake GPIOs to PCIe port nodes and add port Nodes for all PCIe ports")
Signed-off-by: Ziyue Zhang <ziyue.zhang@oss.qualcomm.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20260330020934.3501247-1-ziyue.zhang@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/x1-asus-zenbook-a14.dtsi  | 16 +++++++++------
 arch/arm64/boot/dts/qcom/x1-crd.dtsi               | 24 ++++++++++++++--------
 arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi        | 14 +++++++------
 arch/arm64/boot/dts/qcom/x1-hp-omnibook-x14.dtsi   | 14 +++++++------
 arch/arm64/boot/dts/qcom/x1-microsoft-denali.dtsi  |  8 +++++---
 .../boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts  |  6 +++---
 .../dts/qcom/x1e80100-medion-sprchrgd-14-s1.dts    | 15 +++++++-------
 .../boot/dts/qcom/x1p42100-lenovo-thinkbook-16.dts | 14 +++++++------
 8 files changed, 65 insertions(+), 46 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/x1-asus-zenbook-a14.dtsi b/arch/arm64/boot/dts/qcom/x1-asus-zenbook-a14.dtsi
index 8e5c5575a532..0a382cc9e643 100644
--- a/arch/arm64/boot/dts/qcom/x1-asus-zenbook-a14.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1-asus-zenbook-a14.dtsi
@@ -1032,9 +1032,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1048,10 +1045,12 @@
 	status = "okay";
 };
 
-&pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+&pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+};
 
+&pcie6a {
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -1067,6 +1066,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pm8550_gpios {
 	rtmr0_default: rtmr0-reset-n-active-state {
 		pins = "gpio10";
diff --git a/arch/arm64/boot/dts/qcom/x1-crd.dtsi b/arch/arm64/boot/dts/qcom/x1-crd.dtsi
index ded96fb43489..2fbf9ec66fb8 100644
--- a/arch/arm64/boot/dts/qcom/x1-crd.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1-crd.dtsi
@@ -1216,15 +1216,17 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
 	status = "okay";
 };
 
+&pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+};
+
 &pcie4_phy {
 	vdda-phy-supply = <&vreg_l3i_0p8>;
 	vdda-pll-supply = <&vreg_l3e_1p2>;
@@ -1233,9 +1235,6 @@
 };
 
 &pcie5 {
-	perst-gpios = <&tlmm 149 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 151 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_wwan>;
 
 	pinctrl-0 = <&pcie5_default>;
@@ -1251,10 +1250,12 @@
 	status = "okay";
 };
 
-&pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+&pcie5_port0 {
+	reset-gpios = <&tlmm 149 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 151 GPIO_ACTIVE_LOW>;
+};
 
+&pcie6a {
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-names = "default";
@@ -1270,6 +1271,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pm8550_gpios {
 	kypd_vol_up_n: kypd-vol-up-n-state {
 		pins = "gpio6";
diff --git a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi
index bf04a12b16bc..217ca8c7d81d 100644
--- a/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1-dell-thena.dtsi
@@ -1081,9 +1081,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1098,6 +1095,9 @@
 };
 
 &pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
 	wifi@0 {
 		compatible = "pci17cb,1107";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
@@ -1115,9 +1115,6 @@
 };
 
 &pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -1126,6 +1123,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pcie6a_phy {
 	vdda-phy-supply = <&vreg_l1d_0p8>;
 	vdda-pll-supply = <&vreg_l2j_1p2>;
diff --git a/arch/arm64/boot/dts/qcom/x1-hp-omnibook-x14.dtsi b/arch/arm64/boot/dts/qcom/x1-hp-omnibook-x14.dtsi
index a4075434162a..41063948c583 100644
--- a/arch/arm64/boot/dts/qcom/x1-hp-omnibook-x14.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1-hp-omnibook-x14.dtsi
@@ -1065,9 +1065,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1082,6 +1079,9 @@
 };
 
 &pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
 	wifi@0 {
 		compatible = "pci17cb,1107";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
@@ -1099,9 +1099,6 @@
 };
 
 &pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -1110,6 +1107,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pcie6a_phy {
 	vdda-phy-supply = <&vreg_l1d_0p8>;
 	vdda-pll-supply = <&vreg_l2j_1p2>;
diff --git a/arch/arm64/boot/dts/qcom/x1-microsoft-denali.dtsi b/arch/arm64/boot/dts/qcom/x1-microsoft-denali.dtsi
index d77be02848b5..ba6b7b5a9191 100644
--- a/arch/arm64/boot/dts/qcom/x1-microsoft-denali.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1-microsoft-denali.dtsi
@@ -964,9 +964,6 @@
 };
 
 &pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -982,6 +979,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pm8550_gpios {
 	rtmr0_default: rtmr0-reset-n-active-state {
 		pins = "gpio10";
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
index d6472e5a3f9f..d7938d349205 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
@@ -1126,9 +1126,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1143,6 +1140,9 @@
 };
 
 &pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
 	wifi@0 {
 		compatible = "pci17cb,1107";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-medion-sprchrgd-14-s1.dts b/arch/arm64/boot/dts/qcom/x1e80100-medion-sprchrgd-14-s1.dts
index 20a33e6f27ee..eec5f2f1f75d 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-medion-sprchrgd-14-s1.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-medion-sprchrgd-14-s1.dts
@@ -1033,9 +1033,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1050,6 +1047,9 @@
 };
 
 &pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
 	wifi@0 {
 		compatible = "pci17cb,1107";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
@@ -1067,10 +1067,6 @@
 };
 
 &pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -1086,6 +1082,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pm8550_gpios {
 	rtmr0_default: rtmr0-reset-n-active-state {
 		pins = "gpio10";
diff --git a/arch/arm64/boot/dts/qcom/x1p42100-lenovo-thinkbook-16.dts b/arch/arm64/boot/dts/qcom/x1p42100-lenovo-thinkbook-16.dts
index 1e5eb8c5dc98..06747b54a38e 100644
--- a/arch/arm64/boot/dts/qcom/x1p42100-lenovo-thinkbook-16.dts
+++ b/arch/arm64/boot/dts/qcom/x1p42100-lenovo-thinkbook-16.dts
@@ -1131,9 +1131,6 @@
 };
 
 &pcie4 {
-	perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
-
 	pinctrl-0 = <&pcie4_default>;
 	pinctrl-names = "default";
 
@@ -1148,6 +1145,9 @@
 };
 
 &pcie4_port0 {
+	reset-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
+
 	wifi@0 {
 		compatible = "pci17cb,1107";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
@@ -1165,9 +1165,6 @@
 };
 
 &pcie6a {
-	perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
-	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
-
 	vddpe-3v3-supply = <&vreg_nvme>;
 
 	pinctrl-0 = <&pcie6a_default>;
@@ -1183,6 +1180,11 @@
 	status = "okay";
 };
 
+&pcie6a_port0 {
+	reset-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
+	wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
+};
+
 &pm8550_pwm {
 	status = "okay";
 };
-- 
cgit v1.2.3


From 27c299698464c515c5cd97b4fcf1a0e38600b2ac Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Mon, 30 Mar 2026 17:51:33 +0800
Subject: ASoC: amd: yc: Add DMI quirk for ASUS Vivobook Pro 16X OLED M7601RM

Add a DMI quirk for the ASUS Vivobook Pro 16X OLED M7601RM fixing the
issue where the internal microphone was not detected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221288
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260330095133.81786-1-zhangheng@kylinos.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 6f1c105ca77e..87d6aeb78807 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -731,6 +731,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Thin A15 B7VE"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "M7601RM"),
+		}
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 8ec017cf31299c4b6287ebe27afe81c986aeef88 Mon Sep 17 00:00:00 2001
From: Gilson Marquato Júnior <gilsonmandalogo@hotmail.com>
Date: Mon, 30 Mar 2026 02:43:48 +0100
Subject: ASoC: amd: yc: Add DMI entry for HP Laptop 15-fc0xxx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The HP Laptop 15-fc0xxx (subsystem ID 0x103c8dc9) has an internal
DMIC connected to the AMD ACP6x audio coprocessor. Add a DMI quirk
entry so the internal microphone is properly detected on this model.

Tested on HP Laptop 15-fc0237ns with Fedora 43 (kernel 6.19.9).

Signed-off-by: Gilson Marquato Júnior <gilsonmandalogo@hotmail.com>
Link: https://patch.msgid.link/20260330-hp-15-fc0xxx-dmic-v2-v1-1-6dd6f53a1917@hotmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 87d6aeb78807..aa6200933182 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -45,6 +45,13 @@ static struct snd_soc_card acp6x_card = {
 };
 
 static const struct dmi_system_id yc_acp_quirk_table[] = {
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15-fc0xxx"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
-- 
cgit v1.2.3


From 679b771ea05ad0f8eeae83e14a91b8f4f39510c4 Mon Sep 17 00:00:00 2001
From: Justin Chen <justin.chen@broadcom.com>
Date: Wed, 18 Mar 2026 11:57:07 -0700
Subject: usb: ehci-brcm: fix sleep during atomic

echi_brcm_wait_for_sof() gets called after disabling interrupts
in ehci_brcm_hub_control(). Use the atomic version of poll_timeout
to fix the warning.

Fixes: 9df231511bd6 ("usb: ehci: Add new EHCI driver for Broadcom STB SoC's")
Cc: stable <stable@kernel.org>
Signed-off-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20260318185707.2588431-1-justin.chen@broadcom.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/ehci-brcm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/ehci-brcm.c b/drivers/usb/host/ehci-brcm.c
index 888e8f6670d2..5e3156f94cc6 100644
--- a/drivers/usb/host/ehci-brcm.c
+++ b/drivers/usb/host/ehci-brcm.c
@@ -31,8 +31,8 @@ static inline void ehci_brcm_wait_for_sof(struct ehci_hcd *ehci, u32 delay)
 	int res;
 
 	/* Wait for next microframe (every 125 usecs) */
-	res = readl_relaxed_poll_timeout(&ehci->regs->frame_index, val,
-					 val != frame_idx, 1, 130);
+	res = readl_relaxed_poll_timeout_atomic(&ehci->regs->frame_index,
+						val, val != frame_idx, 1, 130);
 	if (res)
 		ehci_err(ehci, "Error waiting for SOF\n");
 	udelay(delay);
-- 
cgit v1.2.3


From dd36014ec6042f424ef51b923e607772f7502ee7 Mon Sep 17 00:00:00 2001
From: Miao Li <limiao@kylinos.cn>
Date: Thu, 19 Mar 2026 13:39:27 +0800
Subject: usb: quirks: add DELAY_INIT quirk for another Silicon Motion flash
 drive

Another Silicon Motion flash drive also randomly work incorrectly
(lsusb does not list the device) on Huawei hisi platforms during
500 reboot cycles, and the DELAY_INIT quirk fixes this issue.

Signed-off-by: Miao Li <limiao@kylinos.cn>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260319053927.264840-1-limiao870622@163.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 5523a8e29021..26fed25da26e 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -401,6 +401,7 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	/* Silicon Motion Flash Drive */
 	{ USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x090c, 0x2000), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Sound Devices USBPre2 */
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
-- 
cgit v1.2.3


From eba2936bbe6b752a31725a9eb5c674ecbf21ee7d Mon Sep 17 00:00:00 2001
From: Jimmy Hu <hhhuuu@google.com>
Date: Fri, 20 Mar 2026 14:54:27 +0800
Subject: usb: gadget: uvc: fix NULL pointer dereference during unbind race

Commit b81ac4395bbe ("usb: gadget: uvc: allow for application to cleanly
shutdown") introduced two stages of synchronization waits totaling 1500ms
in uvc_function_unbind() to prevent several types of kernel panics.
However, this timing-based approach is insufficient during power
management (PM) transitions.

When the PM subsystem starts freezing user space processes, the
wait_event_interruptible_timeout() is aborted early, which allows the
unbind thread to proceed and nullify the gadget pointer
(cdev->gadget = NULL):

[  814.123447][  T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind()
[  814.178583][ T3173] PM: suspend entry (deep)
[  814.192487][ T3173] Freezing user space processes
[  814.197668][  T947] configfs-gadget.g1 gadget.0: uvc: uvc_function_unbind no clean disconnect, wait for release

When the PM subsystem resumes or aborts the suspend and tasks are
restarted, the V4L2 release path is executed and attempts to access the
already nullified gadget pointer, triggering a kernel panic:

[  814.292597][    C0] PM: pm_system_irq_wakeup: 479 triggered dhdpcie_host_wake
[  814.386727][ T3173] Restarting tasks ...
[  814.403522][ T4558] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000030
[  814.404021][ T4558] pc : usb_gadget_deactivate+0x14/0xf4
[  814.404031][ T4558] lr : usb_function_deactivate+0x54/0x94
[  814.404078][ T4558] Call trace:
[  814.404080][ T4558]  usb_gadget_deactivate+0x14/0xf4
[  814.404083][ T4558]  usb_function_deactivate+0x54/0x94
[  814.404087][ T4558]  uvc_function_disconnect+0x1c/0x5c
[  814.404092][ T4558]  uvc_v4l2_release+0x44/0xac
[  814.404095][ T4558]  v4l2_release+0xcc/0x130

Address the race condition and NULL pointer dereference by:

1. State Synchronization (flag + mutex)
Introduce a 'func_unbound' flag in struct uvc_device. This allows
uvc_function_disconnect() to safely skip accessing the nullified
cdev->gadget pointer. As suggested by Alan Stern, this flag is protected
by a new mutex (uvc->lock) to ensure proper memory ordering and prevent
instruction reordering or speculative loads. This mutex is also used to
protect 'func_connected' for consistent state management.

2. Explicit Synchronization (completion)
Use a completion to synchronize uvc_function_unbind() with the
uvc_vdev_release() callback. This prevents Use-After-Free (UAF) by
ensuring struct uvc_device is freed after all video device resources
are released.

Fixes: b81ac4395bbe ("usb: gadget: uvc: allow for application to cleanly shutdown")
Cc: stable <stable@kernel.org>
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jimmy Hu <hhhuuu@google.com>
Link: https://patch.msgid.link/20260320065427.1374555-1-hhhuuu@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uvc.c    | 39 +++++++++++++++++++++++++++++++---
 drivers/usb/gadget/function/uvc.h      |  3 +++
 drivers/usb/gadget/function/uvc_v4l2.c |  5 ++++-
 3 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c
index 494fdbc4e85b..8d404d88391c 100644
--- a/drivers/usb/gadget/function/f_uvc.c
+++ b/drivers/usb/gadget/function/f_uvc.c
@@ -413,6 +413,12 @@ uvc_function_disconnect(struct uvc_device *uvc)
 {
 	int ret;
 
+	guard(mutex)(&uvc->lock);
+	if (uvc->func_unbound) {
+		dev_dbg(&uvc->vdev.dev, "skipping function deactivate (unbound)\n");
+		return;
+	}
+
 	if ((ret = usb_function_deactivate(&uvc->func)) < 0)
 		uvcg_info(&uvc->func, "UVC disconnect failed with %d\n", ret);
 }
@@ -431,6 +437,15 @@ static ssize_t function_name_show(struct device *dev,
 
 static DEVICE_ATTR_RO(function_name);
 
+static void uvc_vdev_release(struct video_device *vdev)
+{
+	struct uvc_device *uvc = video_get_drvdata(vdev);
+
+	/* Signal uvc_function_unbind() that the video device has been released */
+	if (uvc->vdev_release_done)
+		complete(uvc->vdev_release_done);
+}
+
 static int
 uvc_register_video(struct uvc_device *uvc)
 {
@@ -443,7 +458,7 @@ uvc_register_video(struct uvc_device *uvc)
 	uvc->vdev.v4l2_dev->dev = &cdev->gadget->dev;
 	uvc->vdev.fops = &uvc_v4l2_fops;
 	uvc->vdev.ioctl_ops = &uvc_v4l2_ioctl_ops;
-	uvc->vdev.release = video_device_release_empty;
+	uvc->vdev.release = uvc_vdev_release;
 	uvc->vdev.vfl_dir = VFL_DIR_TX;
 	uvc->vdev.lock = &uvc->video.mutex;
 	uvc->vdev.device_caps = V4L2_CAP_VIDEO_OUTPUT | V4L2_CAP_STREAMING;
@@ -659,6 +674,8 @@ uvc_function_bind(struct usb_configuration *c, struct usb_function *f)
 	int ret = -EINVAL;
 
 	uvcg_info(f, "%s()\n", __func__);
+	scoped_guard(mutex, &uvc->lock)
+		uvc->func_unbound = false;
 
 	opts = fi_to_f_uvc_opts(f->fi);
 	/* Sanity check the streaming endpoint module parameters. */
@@ -988,12 +1005,19 @@ static void uvc_free(struct usb_function *f)
 static void uvc_function_unbind(struct usb_configuration *c,
 				struct usb_function *f)
 {
+	DECLARE_COMPLETION_ONSTACK(vdev_release_done);
 	struct usb_composite_dev *cdev = c->cdev;
 	struct uvc_device *uvc = to_uvc(f);
 	struct uvc_video *video = &uvc->video;
 	long wait_ret = 1;
+	bool connected;
 
 	uvcg_info(f, "%s()\n", __func__);
+	scoped_guard(mutex, &uvc->lock) {
+		uvc->func_unbound = true;
+		uvc->vdev_release_done = &vdev_release_done;
+		connected = uvc->func_connected;
+	}
 
 	kthread_cancel_work_sync(&video->hw_submit);
 
@@ -1006,7 +1030,7 @@ static void uvc_function_unbind(struct usb_configuration *c,
 	 * though the video device removal uevent. Allow some time for the
 	 * application to close out before things get deleted.
 	 */
-	if (uvc->func_connected) {
+	if (connected) {
 		uvcg_dbg(f, "waiting for clean disconnect\n");
 		wait_ret = wait_event_interruptible_timeout(uvc->func_connected_queue,
 				uvc->func_connected == false, msecs_to_jiffies(500));
@@ -1017,7 +1041,10 @@ static void uvc_function_unbind(struct usb_configuration *c,
 	video_unregister_device(&uvc->vdev);
 	v4l2_device_unregister(&uvc->v4l2_dev);
 
-	if (uvc->func_connected) {
+	scoped_guard(mutex, &uvc->lock)
+		connected = uvc->func_connected;
+
+	if (connected) {
 		/*
 		 * Wait for the release to occur to ensure there are no longer any
 		 * pending operations that may cause panics when resources are cleaned
@@ -1029,6 +1056,10 @@ static void uvc_function_unbind(struct usb_configuration *c,
 		uvcg_dbg(f, "done waiting for release with ret: %ld\n", wait_ret);
 	}
 
+	/* Wait for the video device to be released */
+	wait_for_completion(&vdev_release_done);
+	uvc->vdev_release_done = NULL;
+
 	usb_ep_free_request(cdev->gadget->ep0, uvc->control_req);
 	kfree(uvc->control_buf);
 
@@ -1047,6 +1078,8 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi)
 		return ERR_PTR(-ENOMEM);
 
 	mutex_init(&uvc->video.mutex);
+	mutex_init(&uvc->lock);
+	uvc->func_unbound = true;
 	uvc->state = UVC_STATE_DISCONNECTED;
 	init_waitqueue_head(&uvc->func_connected_queue);
 	opts = fi_to_f_uvc_opts(fi);
diff --git a/drivers/usb/gadget/function/uvc.h b/drivers/usb/gadget/function/uvc.h
index 676419a04976..7abfdd5e1eef 100644
--- a/drivers/usb/gadget/function/uvc.h
+++ b/drivers/usb/gadget/function/uvc.h
@@ -155,6 +155,9 @@ struct uvc_device {
 	enum uvc_state state;
 	struct usb_function func;
 	struct uvc_video video;
+	struct completion *vdev_release_done;
+	struct mutex lock;	/* protects func_unbound and func_connected */
+	bool func_unbound;
 	bool func_connected;
 	wait_queue_head_t func_connected_queue;
 
diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c
index ed48d38498fb..514e5930b9ca 100644
--- a/drivers/usb/gadget/function/uvc_v4l2.c
+++ b/drivers/usb/gadget/function/uvc_v4l2.c
@@ -574,6 +574,8 @@ uvc_v4l2_subscribe_event(struct v4l2_fh *fh,
 	if (sub->type < UVC_EVENT_FIRST || sub->type > UVC_EVENT_LAST)
 		return -EINVAL;
 
+	guard(mutex)(&uvc->lock);
+
 	if (sub->type == UVC_EVENT_SETUP && uvc->func_connected)
 		return -EBUSY;
 
@@ -595,7 +597,8 @@ static void uvc_v4l2_disable(struct uvc_device *uvc)
 	uvc_function_disconnect(uvc);
 	uvcg_video_disable(&uvc->video);
 	uvcg_free_buffers(&uvc->video.queue);
-	uvc->func_connected = false;
+	scoped_guard(mutex, &uvc->lock)
+		uvc->func_connected = false;
 	wake_up_interruptible(&uvc->func_connected_queue);
 }
 
-- 
cgit v1.2.3


From 9bb4b5ed7f8c4f95cc556bdf042b0ba2fa13557a Mon Sep 17 00:00:00 2001
From: Juno Choi <juno.choi@lge.com>
Date: Tue, 24 Mar 2026 10:49:10 +0900
Subject: usb: dwc2: gadget: Fix spin_lock/unlock mismatch in
 dwc2_hsotg_udc_stop()

dwc2_gadget_exit_clock_gating() internally calls call_gadget() macro,
which expects hsotg->lock to be held since it does spin_unlock/spin_lock
around the gadget driver callback invocation.

However, dwc2_hsotg_udc_stop() calls dwc2_gadget_exit_clock_gating()
without holding the lock. This leads to:
 - spin_unlock on a lock that is not held (undefined behavior)
 - The lock remaining held after dwc2_gadget_exit_clock_gating() returns,
   causing a deadlock when spin_lock_irqsave() is called later in the
   same function.

Fix this by acquiring hsotg->lock before calling
dwc2_gadget_exit_clock_gating() and releasing it afterwards, which
satisfies the locking requirement of the call_gadget() macro.

Fixes: af076a41f8a2 ("usb: dwc2: also exit clock_gating when stopping udc while suspended")
Cc: stable <stable@kernel.org>
Signed-off-by: Juno Choi <juno.choi@lge.com>
Link: https://patch.msgid.link/20260324014910.2798425-1-juno.choi@lge.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc2/gadget.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index d216e26c787b..c8b02c27d27d 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -4607,7 +4607,9 @@ static int dwc2_hsotg_udc_stop(struct usb_gadget *gadget)
 	/* Exit clock gating when driver is stopped. */
 	if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
 	    hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
+		spin_lock_irqsave(&hsotg->lock, flags);
 		dwc2_gadget_exit_clock_gating(hsotg, 0);
+		spin_unlock_irqrestore(&hsotg->lock, flags);
 	}
 
 	/* all endpoints should be shutdown */
-- 
cgit v1.2.3


From b65d4ca1d1059ace899170d1dfd02639ce971d2d Mon Sep 17 00:00:00 2001
From: Andrei Kuchynski <akuchynski@chromium.org>
Date: Tue, 24 Mar 2026 10:29:03 +0000
Subject: usb: typec: Remove alt->adev.dev.class assignment

The typec plug alternate mode is already registered as part of the bus.
When both class and bus are set for a device, device_add() attempts to
create the "subsystem" symlink in the device's sysfs directory twice, once
for the bus and once for the class.
This results in a duplicate filename error during registration,
causing the alternate mode registration to fail with warnings:

cannot create duplicate filename '/devices/pci0000:00/0000:00:1f.0/
  PNP0C09:00/GOOG0004:00/cros-ec-dev.1.auto/cros_ec_ucsi.3.auto/typec/
  port1/port1-cable/port1-plug0/port1-plug0.0/subsystem'
typec port0-plug0: failed to register alternate mode (-17)
cros_ec_ucsi.3.auto: failed to registers svid 0x8087 mode 1

Cc: stable <stable@kernel.org>
Fixes: 67ab45426215 ("usb: typec: Set the bus also for the port and plug altmodes")
Tested-by: Madhu M <madhu.m@intel.corp-partner.google.com>
Signed-off-by: Andrei Kuchynski <akuchynski@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Benson Leung <bleung@chromium.org>
Link: https://patch.msgid.link/20260324102903.1416210-1-akuchynski@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 831430909471..0977581ad1b6 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -686,10 +686,6 @@ typec_register_altmode(struct device *parent,
 
 	alt->adev.dev.bus = &typec_bus;
 
-	/* Plug alt modes need a class to generate udev events. */
-	if (is_typec_plug(parent))
-		alt->adev.dev.class = &typec_class;
-
 	ret = device_register(&alt->adev.dev);
 	if (ret) {
 		dev_err(parent, "failed to register alternate mode (%d)\n",
-- 
cgit v1.2.3


From 3b8ae9817686efb3ea789ca9d4efdff2ce9c1c04 Mon Sep 17 00:00:00 2001
From: Andrei Kuchynski <akuchynski@chromium.org>
Date: Tue, 24 Mar 2026 10:30:12 +0000
Subject: usb: typec: thunderbolt: Set enter_vdo during initialization

In the current implementation, if a cable's alternate mode enter operation
is not supported, the tbt->plug[TYPEC_PLUG_SOP_P] pointer is cleared by the
time tbt_enter_mode() is called. This prevents the driver from identifying
the cable's VDO.

As a result, the Thunderbolt connection falls back to the default
TBT_CABLE_USB3_PASSIVE speed, even if the cable supports higher speeds.
To ensure the correct VDO value is used during mode entry, calculate and
store the enter_vdo earlier during the initialization phase in tbt_ready().

Cc: stable <stable@kernel.org>
Fixes: 100e25738659 ("usb: typec: Add driver for Thunderbolt 3 Alternate Mode")
Tested-by: Madhu M <madhu.m@intel.corp-partner.google.com>
Signed-off-by: Andrei Kuchynski <akuchynski@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Benson Leung <bleung@chromium.org>
Link: https://patch.msgid.link/20260324103012.1417616-1-akuchynski@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/thunderbolt.c | 44 ++++++++++++++++----------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/drivers/usb/typec/altmodes/thunderbolt.c b/drivers/usb/typec/altmodes/thunderbolt.c
index c4c5da6154da..32250b94262a 100644
--- a/drivers/usb/typec/altmodes/thunderbolt.c
+++ b/drivers/usb/typec/altmodes/thunderbolt.c
@@ -39,28 +39,7 @@ static bool tbt_ready(struct typec_altmode *alt);
 
 static int tbt_enter_mode(struct tbt_altmode *tbt)
 {
-	struct typec_altmode *plug = tbt->plug[TYPEC_PLUG_SOP_P];
-	u32 vdo;
-
-	vdo = tbt->alt->vdo & (TBT_VENDOR_SPECIFIC_B0 | TBT_VENDOR_SPECIFIC_B1);
-	vdo |= tbt->alt->vdo & TBT_INTEL_SPECIFIC_B0;
-	vdo |= TBT_MODE;
-
-	if (plug) {
-		if (typec_cable_is_active(tbt->cable))
-			vdo |= TBT_ENTER_MODE_ACTIVE_CABLE;
-
-		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_SPEED(plug->vdo));
-		vdo |= plug->vdo & TBT_CABLE_ROUNDED;
-		vdo |= plug->vdo & TBT_CABLE_OPTICAL;
-		vdo |= plug->vdo & TBT_CABLE_RETIMER;
-		vdo |= plug->vdo & TBT_CABLE_LINK_TRAINING;
-	} else {
-		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_USB3_PASSIVE);
-	}
-
-	tbt->enter_vdo = vdo;
-	return typec_altmode_enter(tbt->alt, &vdo);
+	return typec_altmode_enter(tbt->alt, &tbt->enter_vdo);
 }
 
 static void tbt_altmode_work(struct work_struct *work)
@@ -337,6 +316,7 @@ static bool tbt_ready(struct typec_altmode *alt)
 {
 	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
 	struct typec_altmode *plug;
+	u32 vdo;
 
 	if (tbt->cable)
 		return true;
@@ -364,6 +344,26 @@ static bool tbt_ready(struct typec_altmode *alt)
 		tbt->plug[i] = plug;
 	}
 
+	vdo = tbt->alt->vdo & (TBT_VENDOR_SPECIFIC_B0 | TBT_VENDOR_SPECIFIC_B1);
+	vdo |= tbt->alt->vdo & TBT_INTEL_SPECIFIC_B0;
+	vdo |= TBT_MODE;
+	plug = tbt->plug[TYPEC_PLUG_SOP_P];
+
+	if (plug) {
+		if (typec_cable_is_active(tbt->cable))
+			vdo |= TBT_ENTER_MODE_ACTIVE_CABLE;
+
+		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_SPEED(plug->vdo));
+		vdo |= plug->vdo & TBT_CABLE_ROUNDED;
+		vdo |= plug->vdo & TBT_CABLE_OPTICAL;
+		vdo |= plug->vdo & TBT_CABLE_RETIMER;
+		vdo |= plug->vdo & TBT_CABLE_LINK_TRAINING;
+	} else {
+		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_USB3_PASSIVE);
+	}
+
+	tbt->enter_vdo = vdo;
+
 	return true;
 }
 
-- 
cgit v1.2.3


From 269c26464dcf8b54b0dd9c333721c30ee44ae297 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 30 Mar 2026 14:35:18 +0800
Subject: dt-bindings: connector: add pd-disable dependency

When Power Delivery is not supported, the source is unable to obtain the
current capability from the Source PDO. As a result, typec-power-opmode
needs to be added to advertise such capability.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Cc: stable <stable@kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://patch.msgid.link/20260330063518.719345-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/connector/usb-connector.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 11e40d225b9f..d97b29e49bf5 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -301,6 +301,7 @@ properties:
     maxItems: 4
 
 dependencies:
+  pd-disable: [typec-power-opmode]
   sink-vdos-v1: [ sink-vdos ]
   sink-vdos: [ sink-vdos-v1 ]
 
-- 
cgit v1.2.3


From caa27923aacd8a5869207842f2ab1657c6c0c7bc Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:44 +0800
Subject: usb: gadget: f_subset: Fix unbalanced refcnt in geth_free

geth_alloc() increments the reference count, but geth_free() fails to
decrement it. This prevents the configuration of attributes via configfs
after unlinking the function.

Decrement the reference count in geth_free() to ensure proper cleanup.

Fixes: 02832e56f88a ("usb: gadget: f_subset: add configfs support")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-1-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_subset.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/gadget/function/f_subset.c b/drivers/usb/gadget/function/f_subset.c
index 076072386e5e..74dc6da5c767 100644
--- a/drivers/usb/gadget/function/f_subset.c
+++ b/drivers/usb/gadget/function/f_subset.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2008 Nokia Corporation
  */
 
+#include <linux/cleanup.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -449,8 +450,13 @@ static struct usb_function_instance *geth_alloc_inst(void)
 static void geth_free(struct usb_function *f)
 {
 	struct f_gether *eth;
+	struct f_gether_opts *opts;
+
+	opts = container_of(f->fi, struct f_gether_opts, func_inst);
 
 	eth = func_to_geth(f);
+	scoped_guard(mutex, &opts->lock)
+		opts->refcnt--;
 	kfree(eth);
 }
 
-- 
cgit v1.2.3


From 8d8c68b1fc06ece60cf43e1306ff0f4ac121547e Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:45 +0800
Subject: usb: gadget: f_rndis: Protect RNDIS options with mutex

The class/subclass/protocol options are suspectible to race conditions
as they can be accessed concurrently through configfs.

Use existing mutex to protect these options. This issue was identified
during code inspection.

Fixes: 73517cf49bd4 ("usb: gadget: add RNDIS configfs options for class/subclass/protocol")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-2-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_rndis.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c
index 8b11d8d6d89c..521b4619d6be 100644
--- a/drivers/usb/gadget/function/f_rndis.c
+++ b/drivers/usb/gadget/function/f_rndis.c
@@ -11,6 +11,7 @@
 
 /* #define VERBOSE_DEBUG */
 
+#include <linux/cleanup.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -678,9 +679,11 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 			return -ENOMEM;
 	}
 
-	rndis_iad_descriptor.bFunctionClass = rndis_opts->class;
-	rndis_iad_descriptor.bFunctionSubClass = rndis_opts->subclass;
-	rndis_iad_descriptor.bFunctionProtocol = rndis_opts->protocol;
+	scoped_guard(mutex, &rndis_opts->lock) {
+		rndis_iad_descriptor.bFunctionClass = rndis_opts->class;
+		rndis_iad_descriptor.bFunctionSubClass = rndis_opts->subclass;
+		rndis_iad_descriptor.bFunctionProtocol = rndis_opts->protocol;
+	}
 
 	/*
 	 * in drivers/usb/gadget/configfs.c:configfs_composite_bind()
-- 
cgit v1.2.3


From 57f531df3618b26df053798a96aa5ade44e00e1a Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:46 +0800
Subject: usb: gadget: u_ncm: Add kernel-doc comments for struct f_ncm_opts

Provide kernel-doc descriptions for the fields in struct f_ncm_opts to
improve code readability and maintainability.

Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-3-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ncm.h | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ncm.h b/drivers/usb/gadget/function/u_ncm.h
index b1f3db8b68c1..ce2f6358688a 100644
--- a/drivers/usb/gadget/function/u_ncm.h
+++ b/drivers/usb/gadget/function/u_ncm.h
@@ -15,6 +15,20 @@
 
 #include <linux/usb/composite.h>
 
+/**
+ * struct f_ncm_opts - NCM function options
+ * @func_inst: USB function instance.
+ * @net: The net_device associated with the NCM function.
+ * @bind_count: Tracks the number of configurations the NCM function is
+ *              bound to, preventing double-registration of the @net device.
+ * @ncm_interf_group: ConfigFS group for NCM interface.
+ * @ncm_os_desc: USB OS descriptor for NCM.
+ * @ncm_ext_compat_id: Extended compatibility ID.
+ * @lock: Protects the data from concurrent access by configfs read/write
+ *        and create symlink/remove symlink operations.
+ * @refcnt: Reference counter for the function instance.
+ * @max_segment_size: Maximum segment size.
+ */
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
@@ -23,12 +37,7 @@ struct f_ncm_opts {
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;
 	char				ncm_ext_compat_id[16];
-	/*
-	 * Read/write access to configfs attributes is handled by configfs.
-	 *
-	 * This is to protect the data from concurrent access by read/write
-	 * and create symlink/remove symlink.
-	 */
+
 	struct mutex			lock;
 	int				refcnt;
 
-- 
cgit v1.2.3


From b2cc4fae67a51f60d81d6af2678696accb07c656 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:47 +0800
Subject: usb: gadget: f_ecm: Fix net_device lifecycle with device_move

The net_device is allocated during function instance creation and
registered during the bind phase with the gadget device as its sysfs
parent. When the function unbinds, the parent device is destroyed, but
the net_device survives, resulting in dangling sysfs symlinks:

  console:/ # ls -l /sys/class/net/usb0
  lrwxrwxrwx ... /sys/class/net/usb0 ->
  /sys/devices/platform/.../gadget.0/net/usb0
  console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0
  ls: .../gadget.0/net/usb0: No such file or directory

Use device_move() to reparent the net_device between the gadget device
tree and /sys/devices/virtual across bind and unbind cycles. During the
final unbind, calling device_move(NULL) moves the net_device to the
virtual device tree before the gadget device is destroyed. On rebinding,
device_move() reparents the device back under the new gadget, ensuring
proper sysfs topology and power management ordering.

To maintain compatibility with legacy composite drivers (e.g., multi.c),
the bound flag is used to indicate whether the network device is shared
and pre-registered during the legacy driver's bind phase.

Fixes: fee562a6450b ("usb: gadget: f_ecm: convert to new function interface with backward compatibility")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-4-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_ecm.c | 37 ++++++++++++++++++++++++-------------
 drivers/usb/gadget/function/u_ecm.h | 21 +++++++++++++++------
 2 files changed, 39 insertions(+), 19 deletions(-)

diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index e0c02121374e..e495bac4efeb 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -681,6 +681,7 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_ep		*ep;
 
 	struct f_ecm_opts	*ecm_opts;
+	struct net_device	*net __free(detach_gadget) = NULL;
 	struct usb_request	*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
@@ -688,18 +689,18 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 
 	ecm_opts = container_of(f->fi, struct f_ecm_opts, func_inst);
 
-	mutex_lock(&ecm_opts->lock);
-
-	gether_set_gadget(ecm_opts->net, cdev->gadget);
-
-	if (!ecm_opts->bound) {
-		status = gether_register_netdev(ecm_opts->net);
-		ecm_opts->bound = true;
-	}
-
-	mutex_unlock(&ecm_opts->lock);
-	if (status)
-		return status;
+	scoped_guard(mutex, &ecm_opts->lock)
+		if (ecm_opts->bind_count == 0 && !ecm_opts->bound) {
+			if (!device_is_registered(&ecm_opts->net->dev)) {
+				gether_set_gadget(ecm_opts->net, cdev->gadget);
+				status = gether_register_netdev(ecm_opts->net);
+			} else
+				status = gether_attach_gadget(ecm_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = ecm_opts->net;
+		}
 
 	ecm_string_defs[1].s = ecm->ethaddr;
 
@@ -790,6 +791,9 @@ ecm_bind(struct usb_configuration *c, struct usb_function *f)
 
 	ecm->notify_req = no_free_ptr(request);
 
+	ecm_opts->bind_count++;
+	retain_and_null_ptr(net);
+
 	DBG(cdev, "CDC Ethernet: IN/%s OUT/%s NOTIFY/%s\n",
 			ecm->port.in_ep->name, ecm->port.out_ep->name,
 			ecm->notify->name);
@@ -836,7 +840,7 @@ static void ecm_free_inst(struct usb_function_instance *f)
 	struct f_ecm_opts *opts;
 
 	opts = container_of(f, struct f_ecm_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -906,9 +910,12 @@ static void ecm_free(struct usb_function *f)
 static void ecm_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_ecm		*ecm = func_to_ecm(f);
+	struct f_ecm_opts	*ecm_opts;
 
 	DBG(c->cdev, "ecm unbind\n");
 
+	ecm_opts = container_of(f->fi, struct f_ecm_opts, func_inst);
+
 	usb_free_all_descriptors(f);
 
 	if (atomic_read(&ecm->notify_count)) {
@@ -918,6 +925,10 @@ static void ecm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ecm->notify_req->buf);
 	usb_ep_free_request(ecm->notify, ecm->notify_req);
+
+	ecm_opts->bind_count--;
+	if (ecm_opts->bind_count == 0 && !ecm_opts->bound)
+		gether_detach_gadget(ecm_opts->net);
 }
 
 static struct usb_function *ecm_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_ecm.h b/drivers/usb/gadget/function/u_ecm.h
index 77cfb89932be..7f666b9dea02 100644
--- a/drivers/usb/gadget/function/u_ecm.h
+++ b/drivers/usb/gadget/function/u_ecm.h
@@ -15,17 +15,26 @@
 
 #include <linux/usb/composite.h>
 
+/**
+ * struct f_ecm_opts - ECM function options
+ * @func_inst: USB function instance.
+ * @net: The net_device associated with the ECM function.
+ * @bound: True if the net_device is shared and pre-registered during the
+ *         legacy composite driver's bind phase (e.g., multi.c). If false,
+ *         the ECM function will register the net_device during its own
+ *         bind phase.
+ * @bind_count: Tracks the number of configurations the ECM function is
+ *              bound to, preventing double-registration of the @net device.
+ * @lock: Protects the data from concurrent access by configfs read/write
+ *        and create symlink/remove symlink operations.
+ * @refcnt: Reference counter for the function instance.
+ */
 struct f_ecm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
 	bool				bound;
+	int				bind_count;
 
-	/*
-	 * Read/write access to configfs attributes is handled by configfs.
-	 *
-	 * This is to protect the data from concurrent access by read/write
-	 * and create symlink/remove symlink.
-	 */
 	struct mutex			lock;
 	int				refcnt;
 };
-- 
cgit v1.2.3


From d9270c9a8118c1535409db926ac1e2545dc97b81 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:48 +0800
Subject: usb: gadget: f_eem: Fix net_device lifecycle with device_move

The net_device is allocated during function instance creation and
registered during the bind phase with the gadget device as its sysfs
parent. When the function unbinds, the parent device is destroyed, but
the net_device survives, resulting in dangling sysfs symlinks:

console:/ # ls -l /sys/class/net/usb0
lrwxrwxrwx ... /sys/class/net/usb0 ->
/sys/devices/platform/.../gadget.0/net/usb0
console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0
ls: .../gadget.0/net/usb0: No such file or directory

Use device_move() to reparent the net_device between the gadget device
tree and /sys/devices/virtual across bind and unbind cycles. During the
final unbind, calling device_move(NULL) moves the net_device to the
virtual device tree before the gadget device is destroyed. On rebinding,
device_move() reparents the device back under the new gadget, ensuring
proper sysfs topology and power management ordering.

To maintain compatibility with legacy composite drivers (e.g., multi.c),
the bound flag is used to indicate whether the network device is shared
and pre-registered during the legacy driver's bind phase.

Fixes: b29002a15794 ("usb: gadget: f_eem: convert to new function interface with backward compatibility")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-5-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_eem.c | 59 +++++++++++++++++++------------------
 drivers/usb/gadget/function/u_eem.h | 21 +++++++++----
 2 files changed, 46 insertions(+), 34 deletions(-)

diff --git a/drivers/usb/gadget/function/f_eem.c b/drivers/usb/gadget/function/f_eem.c
index 0142a0e487ee..ac37d7c1d168 100644
--- a/drivers/usb/gadget/function/f_eem.c
+++ b/drivers/usb/gadget/function/f_eem.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2009 EF Johnson Technologies
  */
 
+#include <linux/cleanup.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/device.h>
@@ -251,24 +252,22 @@ static int eem_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_ep		*ep;
 
 	struct f_eem_opts	*eem_opts;
+	struct net_device	*net __free(detach_gadget) = NULL;
 
 	eem_opts = container_of(f->fi, struct f_eem_opts, func_inst);
-	/*
-	 * in drivers/usb/gadget/configfs.c:configfs_composite_bind()
-	 * configurations are bound in sequence with list_for_each_entry,
-	 * in each configuration its functions are bound in sequence
-	 * with list_for_each_entry, so we assume no race condition
-	 * with regard to eem_opts->bound access
-	 */
-	if (!eem_opts->bound) {
-		mutex_lock(&eem_opts->lock);
-		gether_set_gadget(eem_opts->net, cdev->gadget);
-		status = gether_register_netdev(eem_opts->net);
-		mutex_unlock(&eem_opts->lock);
-		if (status)
-			return status;
-		eem_opts->bound = true;
-	}
+
+	scoped_guard(mutex, &eem_opts->lock)
+		if (eem_opts->bind_count == 0 && !eem_opts->bound) {
+			if (!device_is_registered(&eem_opts->net->dev)) {
+				gether_set_gadget(eem_opts->net, cdev->gadget);
+				status = gether_register_netdev(eem_opts->net);
+			} else
+				status = gether_attach_gadget(eem_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = eem_opts->net;
+		}
 
 	us = usb_gstrings_attach(cdev, eem_strings,
 				 ARRAY_SIZE(eem_string_defs));
@@ -279,21 +278,19 @@ static int eem_bind(struct usb_configuration *c, struct usb_function *f)
 	/* allocate instance-specific interface IDs */
 	status = usb_interface_id(c, f);
 	if (status < 0)
-		goto fail;
+		return status;
 	eem->ctrl_id = status;
 	eem_intf.bInterfaceNumber = status;
 
-	status = -ENODEV;
-
 	/* allocate instance-specific endpoints */
 	ep = usb_ep_autoconfig(cdev->gadget, &eem_fs_in_desc);
 	if (!ep)
-		goto fail;
+		return -ENODEV;
 	eem->port.in_ep = ep;
 
 	ep = usb_ep_autoconfig(cdev->gadget, &eem_fs_out_desc);
 	if (!ep)
-		goto fail;
+		return -ENODEV;
 	eem->port.out_ep = ep;
 
 	/* support all relevant hardware speeds... we expect that when
@@ -309,16 +306,14 @@ static int eem_bind(struct usb_configuration *c, struct usb_function *f)
 	status = usb_assign_descriptors(f, eem_fs_function, eem_hs_function,
 			eem_ss_function, eem_ss_function);
 	if (status)
-		goto fail;
+		return status;
+
+	eem_opts->bind_count++;
+	retain_and_null_ptr(net);
 
 	DBG(cdev, "CDC Ethernet (EEM): IN/%s OUT/%s\n",
 			eem->port.in_ep->name, eem->port.out_ep->name);
 	return 0;
-
-fail:
-	ERROR(cdev, "%s: can't bind, err %d\n", f->name, status);
-
-	return status;
 }
 
 static void eem_cmd_complete(struct usb_ep *ep, struct usb_request *req)
@@ -597,7 +592,7 @@ static void eem_free_inst(struct usb_function_instance *f)
 	struct f_eem_opts *opts;
 
 	opts = container_of(f, struct f_eem_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -640,9 +635,17 @@ static void eem_free(struct usb_function *f)
 
 static void eem_unbind(struct usb_configuration *c, struct usb_function *f)
 {
+	struct f_eem_opts *opts;
+
 	DBG(c->cdev, "eem unbind\n");
 
+	opts = container_of(f->fi, struct f_eem_opts, func_inst);
+
 	usb_free_all_descriptors(f);
+
+	opts->bind_count--;
+	if (opts->bind_count == 0 && !opts->bound)
+		gether_detach_gadget(opts->net);
 }
 
 static struct usb_function *eem_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_eem.h b/drivers/usb/gadget/function/u_eem.h
index 3bd85dfcd71c..78ef55815219 100644
--- a/drivers/usb/gadget/function/u_eem.h
+++ b/drivers/usb/gadget/function/u_eem.h
@@ -15,17 +15,26 @@
 
 #include <linux/usb/composite.h>
 
+/**
+ * struct f_eem_opts - EEM function options
+ * @func_inst: USB function instance.
+ * @net: The net_device associated with the EEM function.
+ * @bound: True if the net_device is shared and pre-registered during the
+ *         legacy composite driver's bind phase (e.g., multi.c). If false,
+ *         the EEM function will register the net_device during its own
+ *         bind phase.
+ * @bind_count: Tracks the number of configurations the EEM function is
+ *              bound to, preventing double-registration of the @net device.
+ * @lock: Protects the data from concurrent access by configfs read/write
+ *        and create symlink/remove symlink operations.
+ * @refcnt: Reference counter for the function instance.
+ */
 struct f_eem_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
 	bool				bound;
+	int				bind_count;
 
-	/*
-	 * Read/write access to configfs attributes is handled by configfs.
-	 *
-	 * This is to protect the data from concurrent access by read/write
-	 * and create symlink/remove symlink.
-	 */
 	struct mutex			lock;
 	int				refcnt;
 };
-- 
cgit v1.2.3


From 06524cd1c9011bee141a87e43ab878641ed3652b Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:49 +0800
Subject: usb: gadget: f_subset: Fix net_device lifecycle with device_move

The net_device is allocated during function instance creation and
registered during the bind phase with the gadget device as its sysfs
parent. When the function unbinds, the parent device is destroyed, but
the net_device survives, resulting in dangling sysfs symlinks:

  console:/ # ls -l /sys/class/net/usb0
  lrwxrwxrwx ... /sys/class/net/usb0 ->
  /sys/devices/platform/.../gadget.0/net/usb0
  console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0
  ls: .../gadget.0/net/usb0: No such file or directory

Use device_move() to reparent the net_device between the gadget device
tree and /sys/devices/virtual across bind and unbind cycles. During the
final unbind, calling device_move(NULL) moves the net_device to the
virtual device tree before the gadget device is destroyed. On rebinding,
device_move() reparents the device back under the new gadget, ensuring
proper sysfs topology and power management ordering.

To maintain compatibility with legacy composite drivers (e.g., multi.c),
the bound flag is used to indicate whether the network device is shared
and pre-registered during the legacy driver's bind phase.

Fixes: 8cedba7c73af ("usb: gadget: f_subset: convert to new function interface with backward compatibility")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-6-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_subset.c | 57 +++++++++++++++++-----------------
 drivers/usb/gadget/function/u_gether.h | 22 ++++++++-----
 2 files changed, 44 insertions(+), 35 deletions(-)

diff --git a/drivers/usb/gadget/function/f_subset.c b/drivers/usb/gadget/function/f_subset.c
index 74dc6da5c767..6e3265b8a3a0 100644
--- a/drivers/usb/gadget/function/f_subset.c
+++ b/drivers/usb/gadget/function/f_subset.c
@@ -299,25 +299,22 @@ geth_bind(struct usb_configuration *c, struct usb_function *f)
 	struct usb_ep		*ep;
 
 	struct f_gether_opts	*gether_opts;
+	struct net_device	*net __free(detach_gadget) = NULL;
 
 	gether_opts = container_of(f->fi, struct f_gether_opts, func_inst);
 
-	/*
-	 * in drivers/usb/gadget/configfs.c:configfs_composite_bind()
-	 * configurations are bound in sequence with list_for_each_entry,
-	 * in each configuration its functions are bound in sequence
-	 * with list_for_each_entry, so we assume no race condition
-	 * with regard to gether_opts->bound access
-	 */
-	if (!gether_opts->bound) {
-		mutex_lock(&gether_opts->lock);
-		gether_set_gadget(gether_opts->net, cdev->gadget);
-		status = gether_register_netdev(gether_opts->net);
-		mutex_unlock(&gether_opts->lock);
-		if (status)
-			return status;
-		gether_opts->bound = true;
-	}
+	scoped_guard(mutex, &gether_opts->lock)
+		if (gether_opts->bind_count == 0 && !gether_opts->bound) {
+			if (!device_is_registered(&gether_opts->net->dev)) {
+				gether_set_gadget(gether_opts->net, cdev->gadget);
+				status = gether_register_netdev(gether_opts->net);
+			} else
+				status = gether_attach_gadget(gether_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = gether_opts->net;
+		}
 
 	us = usb_gstrings_attach(cdev, geth_strings,
 				 ARRAY_SIZE(geth_string_defs));
@@ -330,20 +327,18 @@ geth_bind(struct usb_configuration *c, struct usb_function *f)
 	/* allocate instance-specific interface IDs */
 	status = usb_interface_id(c, f);
 	if (status < 0)
-		goto fail;
+		return status;
 	subset_data_intf.bInterfaceNumber = status;
 
-	status = -ENODEV;
-
 	/* allocate instance-specific endpoints */
 	ep = usb_ep_autoconfig(cdev->gadget, &fs_subset_in_desc);
 	if (!ep)
-		goto fail;
+		return -ENODEV;
 	geth->port.in_ep = ep;
 
 	ep = usb_ep_autoconfig(cdev->gadget, &fs_subset_out_desc);
 	if (!ep)
-		goto fail;
+		return -ENODEV;
 	geth->port.out_ep = ep;
 
 	/* support all relevant hardware speeds... we expect that when
@@ -361,21 +356,19 @@ geth_bind(struct usb_configuration *c, struct usb_function *f)
 	status = usb_assign_descriptors(f, fs_eth_function, hs_eth_function,
 			ss_eth_function, ss_eth_function);
 	if (status)
-		goto fail;
+		return status;
 
 	/* NOTE:  all that is done without knowing or caring about
 	 * the network link ... which is unavailable to this code
 	 * until we're activated via set_alt().
 	 */
 
+	gether_opts->bind_count++;
+	retain_and_null_ptr(net);
+
 	DBG(cdev, "CDC Subset: IN/%s OUT/%s\n",
 			geth->port.in_ep->name, geth->port.out_ep->name);
 	return 0;
-
-fail:
-	ERROR(cdev, "%s: can't bind, err %d\n", f->name, status);
-
-	return status;
 }
 
 static inline struct f_gether_opts *to_f_gether_opts(struct config_item *item)
@@ -418,7 +411,7 @@ static void geth_free_inst(struct usb_function_instance *f)
 	struct f_gether_opts *opts;
 
 	opts = container_of(f, struct f_gether_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -462,8 +455,16 @@ static void geth_free(struct usb_function *f)
 
 static void geth_unbind(struct usb_configuration *c, struct usb_function *f)
 {
+	struct f_gether_opts *opts;
+
+	opts = container_of(f->fi, struct f_gether_opts, func_inst);
+
 	geth_string_defs[0].id = 0;
 	usb_free_all_descriptors(f);
+
+	opts->bind_count--;
+	if (opts->bind_count == 0 && !opts->bound)
+		gether_detach_gadget(opts->net);
 }
 
 static struct usb_function *geth_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_gether.h b/drivers/usb/gadget/function/u_gether.h
index 2f7a373ed449..e7b6b51f69c1 100644
--- a/drivers/usb/gadget/function/u_gether.h
+++ b/drivers/usb/gadget/function/u_gether.h
@@ -15,17 +15,25 @@
 
 #include <linux/usb/composite.h>
 
+/**
+ * struct f_gether_opts - subset function options
+ * @func_inst: USB function instance.
+ * @net: The net_device associated with the subset function.
+ * @bound: True if the net_device is shared and pre-registered during the
+ *         legacy composite driver's bind phase (e.g., multi.c). If false,
+ *         the subset function will register the net_device during its own
+ *         bind phase.
+ * @bind_count: Tracks the number of configurations the subset function is
+ *              bound to, preventing double-registration of the @net device.
+ * @lock: Protects the data from concurrent access by configfs read/write
+ *        and create symlink/remove symlink operations.
+ * @refcnt: Reference counter for the function instance.
+ */
 struct f_gether_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
 	bool				bound;
-
-	/*
-	 * Read/write access to configfs attributes is handled by configfs.
-	 *
-	 * This is to protect the data from concurrent access by read/write
-	 * and create symlink/remove symlink.
-	 */
+	int				bind_count;
 	struct mutex			lock;
 	int				refcnt;
 };
-- 
cgit v1.2.3


From e367599529dc42578545a7f85fde517b35b3cda7 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Fri, 20 Mar 2026 16:54:50 +0800
Subject: usb: gadget: f_rndis: Fix net_device lifecycle with device_move

The net_device is allocated during function instance creation and
registered during the bind phase with the gadget device as its sysfs
parent. When the function unbinds, the parent device is destroyed, but
the net_device survives, resulting in dangling sysfs symlinks:

  console:/ # ls -l /sys/class/net/usb0
  lrwxrwxrwx ... /sys/class/net/usb0 ->
  /sys/devices/platform/.../gadget.0/net/usb0
  console:/ # ls -l /sys/devices/platform/.../gadget.0/net/usb0
  ls: .../gadget.0/net/usb0: No such file or directory

Use device_move() to reparent the net_device between the gadget device
tree and /sys/devices/virtual across bind and unbind cycles. During the
final unbind, calling device_move(NULL) moves the net_device to the
virtual device tree before the gadget device is destroyed. On rebinding,
device_move() reparents the device back under the new gadget, ensuring
proper sysfs topology and power management ordering.

To maintain compatibility with legacy composite drivers (e.g., multi.c),
the borrowed_net flag is used to indicate whether the network device is
shared and pre-registered during the legacy driver's bind phase.

Fixes: f466c6353819 ("usb: gadget: f_rndis: convert to new function interface with backward compatibility")
Cc: stable@vger.kernel.org
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://patch.msgid.link/20260320-usb-net-lifecycle-v1-7-4886b578161b@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_rndis.c | 42 +++++++++++++++++++++--------------
 drivers/usb/gadget/function/u_rndis.h | 31 +++++++++++++++++++-------
 2 files changed, 48 insertions(+), 25 deletions(-)

diff --git a/drivers/usb/gadget/function/f_rndis.c b/drivers/usb/gadget/function/f_rndis.c
index 521b4619d6be..7de1c5f8e326 100644
--- a/drivers/usb/gadget/function/f_rndis.c
+++ b/drivers/usb/gadget/function/f_rndis.c
@@ -666,6 +666,7 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 
 	struct f_rndis_opts *rndis_opts;
 	struct usb_os_desc_table        *os_desc_table __free(kfree) = NULL;
+	struct net_device		*net __free(detach_gadget) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_rndis(c))
@@ -683,21 +684,18 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 		rndis_iad_descriptor.bFunctionClass = rndis_opts->class;
 		rndis_iad_descriptor.bFunctionSubClass = rndis_opts->subclass;
 		rndis_iad_descriptor.bFunctionProtocol = rndis_opts->protocol;
-	}
 
-	/*
-	 * in drivers/usb/gadget/configfs.c:configfs_composite_bind()
-	 * configurations are bound in sequence with list_for_each_entry,
-	 * in each configuration its functions are bound in sequence
-	 * with list_for_each_entry, so we assume no race condition
-	 * with regard to rndis_opts->bound access
-	 */
-	if (!rndis_opts->bound) {
-		gether_set_gadget(rndis_opts->net, cdev->gadget);
-		status = gether_register_netdev(rndis_opts->net);
-		if (status)
-			return status;
-		rndis_opts->bound = true;
+		if (rndis_opts->bind_count == 0 && !rndis_opts->borrowed_net) {
+			if (!device_is_registered(&rndis_opts->net->dev)) {
+				gether_set_gadget(rndis_opts->net, cdev->gadget);
+				status = gether_register_netdev(rndis_opts->net);
+			} else
+				status = gether_attach_gadget(rndis_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = rndis_opts->net;
+		}
 	}
 
 	us = usb_gstrings_attach(cdev, rndis_strings,
@@ -796,6 +794,9 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 	}
 	rndis->notify_req = no_free_ptr(request);
 
+	rndis_opts->bind_count++;
+	retain_and_null_ptr(net);
+
 	/* NOTE:  all that is done without knowing or caring about
 	 * the network link ... which is unavailable to this code
 	 * until we're activated via set_alt().
@@ -812,11 +813,11 @@ void rndis_borrow_net(struct usb_function_instance *f, struct net_device *net)
 	struct f_rndis_opts *opts;
 
 	opts = container_of(f, struct f_rndis_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
-	opts->borrowed_net = opts->bound = true;
+	opts->borrowed_net = true;
 	opts->net = net;
 }
 EXPORT_SYMBOL_GPL(rndis_borrow_net);
@@ -874,7 +875,7 @@ static void rndis_free_inst(struct usb_function_instance *f)
 
 	opts = container_of(f, struct f_rndis_opts, func_inst);
 	if (!opts->borrowed_net) {
-		if (opts->bound)
+		if (device_is_registered(&opts->net->dev))
 			gether_cleanup(netdev_priv(opts->net));
 		else
 			free_netdev(opts->net);
@@ -943,6 +944,9 @@ static void rndis_free(struct usb_function *f)
 static void rndis_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_rndis		*rndis = func_to_rndis(f);
+	struct f_rndis_opts	*rndis_opts;
+
+	rndis_opts = container_of(f->fi, struct f_rndis_opts, func_inst);
 
 	kfree(f->os_desc_table);
 	f->os_desc_n = 0;
@@ -950,6 +954,10 @@ static void rndis_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(rndis->notify_req->buf);
 	usb_ep_free_request(rndis->notify, rndis->notify_req);
+
+	rndis_opts->bind_count--;
+	if (rndis_opts->bind_count == 0 && !rndis_opts->borrowed_net)
+		gether_detach_gadget(rndis_opts->net);
 }
 
 static struct usb_function *rndis_alloc(struct usb_function_instance *fi)
diff --git a/drivers/usb/gadget/function/u_rndis.h b/drivers/usb/gadget/function/u_rndis.h
index a8c409b2f52f..4e64619714dc 100644
--- a/drivers/usb/gadget/function/u_rndis.h
+++ b/drivers/usb/gadget/function/u_rndis.h
@@ -15,12 +15,34 @@
 
 #include <linux/usb/composite.h>
 
+/**
+ * struct f_rndis_opts - RNDIS function options
+ * @func_inst: USB function instance.
+ * @vendor_id: Vendor ID.
+ * @manufacturer: Manufacturer string.
+ * @net: The net_device associated with the RNDIS function.
+ * @bind_count: Tracks the number of configurations the RNDIS function is
+ *              bound to, preventing double-registration of the @net device.
+ * @borrowed_net: True if the net_device is shared and pre-registered during
+ *                the legacy composite driver's bind phase (e.g., multi.c).
+ *                If false, the RNDIS function will register the net_device
+ *                during its own bind phase.
+ * @rndis_interf_group: ConfigFS group for RNDIS interface.
+ * @rndis_os_desc: USB OS descriptor for RNDIS.
+ * @rndis_ext_compat_id: Extended compatibility ID.
+ * @class: USB class.
+ * @subclass: USB subclass.
+ * @protocol: USB protocol.
+ * @lock: Protects the data from concurrent access by configfs read/write
+ *        and create symlink/remove symlink operations.
+ * @refcnt: Reference counter for the function instance.
+ */
 struct f_rndis_opts {
 	struct usb_function_instance	func_inst;
 	u32				vendor_id;
 	const char			*manufacturer;
 	struct net_device		*net;
-	bool				bound;
+	int				bind_count;
 	bool				borrowed_net;
 
 	struct config_group		*rndis_interf_group;
@@ -30,13 +52,6 @@ struct f_rndis_opts {
 	u8				class;
 	u8				subclass;
 	u8				protocol;
-
-	/*
-	 * Read/write access to configfs attributes is handled by configfs.
-	 *
-	 * This is to protect the data from concurrent access by read/write
-	 * and create symlink/remove symlink.
-	 */
 	struct mutex			lock;
 	int				refcnt;
 };
-- 
cgit v1.2.3


From 40014493cece72a0be5672cd86763e53fb3ec613 Mon Sep 17 00:00:00 2001
From: Liav Mordouch <liavmordouch@gmail.com>
Date: Fri, 27 Mar 2026 20:02:04 +0300
Subject: vt: discard stale unicode buffer on alt screen exit after resize

When enter_alt_screen() saves vc_uni_lines into vc_saved_uni_lines and
sets vc_uni_lines to NULL, a subsequent console resize via vc_do_resize()
skips reallocating the unicode buffer because vc_uni_lines is NULL.
However, vc_saved_uni_lines still points to the old buffer allocated for
the original dimensions.

When leave_alt_screen() later restores vc_saved_uni_lines, the buffer
dimensions no longer match vc_rows/vc_cols. Any operation that iterates
over the unicode buffer using the current dimensions (e.g. csi_J clearing
the screen) will access memory out of bounds, causing a kernel oops:

  BUG: unable to handle page fault for address: 0x0000002000000020
  RIP: 0010:csi_J+0x133/0x2d0

The faulting address 0x0000002000000020 is two adjacent u32 space
characters (0x20) interpreted as a pointer, read from the row data area
past the end of the 25-entry pointer array in a buffer allocated for
80x25 but accessed with 240x67 dimensions.

Fix this by checking whether the console dimensions changed while in the
alternate screen. If they did, free the stale saved buffer instead of
restoring it. The unicode screen will be lazily rebuilt via
vc_uniscr_check() when next needed.

Fixes: 5eb608319bb5 ("vt: save/restore unicode screen buffer for alternate screen")
Cc: stable <stable@kernel.org>
Tested-by: Liav Mordouch <liavmordouch@gmail.com>
Signed-off-by: Liav Mordouch <liavmordouch@gmail.com>
Reviewed-by: Nicolas Pitre <nico@fluxnic.net>
Link: https://patch.msgid.link/20260327170204.29706-1-liavmordouch@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index e2df99e3d458..99f15b3e9544 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1901,6 +1901,7 @@ static void leave_alt_screen(struct vc_data *vc)
 	unsigned int rows = min(vc->vc_saved_rows, vc->vc_rows);
 	unsigned int cols = min(vc->vc_saved_cols, vc->vc_cols);
 	u16 *src, *dest;
+	bool uni_lines_stale;
 
 	if (vc->vc_saved_screen == NULL)
 		return; /* Not inside an alt-screen */
@@ -1909,7 +1910,18 @@ static void leave_alt_screen(struct vc_data *vc)
 		dest = ((u16 *)vc->vc_origin) + r * vc->vc_cols;
 		memcpy(dest, src, 2 * cols);
 	}
-	vc_uniscr_set(vc, vc->vc_saved_uni_lines);
+	/*
+	 * If the console was resized while in the alternate screen,
+	 * vc_saved_uni_lines was allocated for the old dimensions.
+	 * Restoring it would cause out-of-bounds accesses. Discard it
+	 * and let the unicode screen be lazily rebuilt.
+	 */
+	uni_lines_stale = vc->vc_saved_rows != vc->vc_rows ||
+			  vc->vc_saved_cols != vc->vc_cols;
+	if (uni_lines_stale)
+		vc_uniscr_free(vc->vc_saved_uni_lines);
+	else
+		vc_uniscr_set(vc, vc->vc_saved_uni_lines);
 	vc->vc_saved_uni_lines = NULL;
 	restore_cur(vc);
 	/* Update the entire screen */
-- 
cgit v1.2.3


From 3ddbea7542ae529c1a88ef9a8b1ce169126211f6 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@fluxnic.net>
Date: Fri, 27 Mar 2026 23:09:47 -0400
Subject: vt: resize saved unicode buffer on alt screen exit after resize

Instead of discarding the saved unicode buffer when the console was
resized while in the alternate screen, resize it to the current
dimensions using vc_uniscr_copy_area() to preserve its content. This
properly restores the unicode screen on alt screen exit rather than
lazily rebuilding it from a lossy reverse glyph translation.

On allocation failure the stale buffer is freed and vc_uni_lines is
set to NULL so it gets lazily rebuilt via vc_uniscr_check() when next
needed.

Fixes: 40014493cece ("vt: discard stale unicode buffer on alt screen exit after resize")
Cc: stable <stable@kernel.org>
Signed-off-by: Nicolas Pitre <nico@fluxnic.net>
Link: https://patch.msgid.link/3nsr334n-079q-125n-7807-n4nq818758ns@syhkavp.arg
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 99f15b3e9544..b4b19157f05c 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1901,7 +1901,6 @@ static void leave_alt_screen(struct vc_data *vc)
 	unsigned int rows = min(vc->vc_saved_rows, vc->vc_rows);
 	unsigned int cols = min(vc->vc_saved_cols, vc->vc_cols);
 	u16 *src, *dest;
-	bool uni_lines_stale;
 
 	if (vc->vc_saved_screen == NULL)
 		return; /* Not inside an alt-screen */
@@ -1912,16 +1911,23 @@ static void leave_alt_screen(struct vc_data *vc)
 	}
 	/*
 	 * If the console was resized while in the alternate screen,
-	 * vc_saved_uni_lines was allocated for the old dimensions.
-	 * Restoring it would cause out-of-bounds accesses. Discard it
-	 * and let the unicode screen be lazily rebuilt.
+	 * resize the saved unicode buffer to the current dimensions.
+	 * On allocation failure new_uniscr is NULL, causing the old
+	 * buffer to be freed and vc_uni_lines to be lazily rebuilt
+	 * via vc_uniscr_check() when next needed.
 	 */
-	uni_lines_stale = vc->vc_saved_rows != vc->vc_rows ||
-			  vc->vc_saved_cols != vc->vc_cols;
-	if (uni_lines_stale)
+	if (vc->vc_saved_uni_lines &&
+	    (vc->vc_saved_rows != vc->vc_rows ||
+	     vc->vc_saved_cols != vc->vc_cols)) {
+		u32 **new_uniscr = vc_uniscr_alloc(vc->vc_cols, vc->vc_rows);
+
+		if (new_uniscr)
+			vc_uniscr_copy_area(new_uniscr, vc->vc_cols, vc->vc_rows,
+					    vc->vc_saved_uni_lines, cols, 0, rows);
 		vc_uniscr_free(vc->vc_saved_uni_lines);
-	else
-		vc_uniscr_set(vc, vc->vc_saved_uni_lines);
+		vc->vc_saved_uni_lines = new_uniscr;
+	}
+	vc_uniscr_set(vc, vc->vc_saved_uni_lines);
 	vc->vc_saved_uni_lines = NULL;
 	restore_cur(vc);
 	/* Update the entire screen */
-- 
cgit v1.2.3


From ea31be8a2c8c99eac198f3b7f2dc770111f2b182 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 30 Mar 2026 18:22:20 +0200
Subject: ALSA: hda/realtek: Add quirk for Samsung Book2 Pro 360 (NP950QED)

There is another Book2 Pro model (NP950QED) that seems equipped with
the same speaker module as the non-360 model, which requires
ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS quirk.

Reported-by: Throw <zakkabj@gmail.com>
Link: https://patch.msgid.link/20260330162249.147665-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index c14046e09aa4..766d7bb2d4f5 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7409,6 +7409,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc1ac, "Samsung Galaxy Book2 Pro 360 (NP950QED)", ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP),
-- 
cgit v1.2.3


From 2e8b1a1d12ae3338efeb1c3de3eb4e9324b87a28 Mon Sep 17 00:00:00 2001
From: Tomas Glozar <tglozar@redhat.com>
Date: Mon, 30 Mar 2026 11:12:07 +0200
Subject: rtla: Fix build without libbpf header

rtla supports building without libbpf. However, BPF actions
patchset [1] adds an include of bpf/libbpf.h into timerlat_bpf.h,
which breaks build on systems that don't have libbpf headers
installed.

This is a leftover from a draft version of the patchset where
timerlat_bpf_set_action() (which takes a struct bpf_program * argument)
was defined in the header. timerlat_bpf.c already includes bpf/libbpf.h
via timerlat.skel.h when libbpf is present.

Remove the redundant include to fix build on systems without libbpf
headers.

[1] https://lore.kernel.org/linux-trace-kernel/20251126144205.331954-1-tglozar@redhat.com/T/

Cc: John Kacur <jkacur@redhat.com>
Cc: Luis Goncalves <lgoncalv@redhat.com>
Cc: Crystal Wood <crwood@redhat.com>
Cc: Costa Shulyupin <costa.shul@redhat.com>
Link: https://patch.msgid.link/20260330091207.16184-1-tglozar@redhat.com
Reported-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Closes: https://lore.kernel.org/linux-trace-kernel/20260329122202.65a8b575@robin/
Fixes: 8cd0f08ac72e ("rtla/timerlat: Support tail call from BPF program")
Signed-off-by: Tomas Glozar <tglozar@redhat.com>
Reviewed-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/tracing/rtla/src/timerlat_bpf.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h
index 169abeaf4363..f7c5675737fe 100644
--- a/tools/tracing/rtla/src/timerlat_bpf.h
+++ b/tools/tracing/rtla/src/timerlat_bpf.h
@@ -12,7 +12,6 @@ enum summary_field {
 };
 
 #ifndef __bpf__
-#include <bpf/libbpf.h>
 #ifdef HAVE_BPF_SKEL
 int timerlat_bpf_init(struct timerlat_params *params);
 int timerlat_bpf_attach(void);
-- 
cgit v1.2.3


From b9eff9732cb0f86a68c9d1592a98ceab47c01e95 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Fri, 27 Mar 2026 02:43:54 +0000
Subject: ASoC: soc-core: call missing INIT_LIST_HEAD() for card_aux_list

Component has "card_aux_list" which is added/deled in bind/unbind aux dev
function (A), and used in for_each_card_auxs() loop (B).

	static void soc_unbind_aux_dev(...)
	{
		...
		for_each_card_auxs_safe(...) {
			...
(A)			list_del(&component->card_aux_list);
		}			     ^^^^^^^^^^^^^
	}

	static int soc_bind_aux_dev(...)
	{
		...
		for_each_card_pre_auxs(...) {
			...
(A)			list_add(&component->card_aux_list, ...);
		}			     ^^^^^^^^^^^^^
		...
	}

	#define for_each_card_auxs(card, component)	\
(B)		list_for_each_entry(component, ..., card_aux_list)
						    ^^^^^^^^^^^^^

But it has been used without calling INIT_LIST_HEAD().

	> git grep card_aux_list sound/soc
	sound/soc/soc-core.c:           list_del(&component->card_aux_list);
	sound/soc/soc-core.c:           list_add(&component->card_aux_list, ...);

call missing INIT_LIST_HEAD() for it.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/87341mxa8l.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 573693e21780..ff6eb6bfc63b 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2859,6 +2859,7 @@ int snd_soc_component_initialize(struct snd_soc_component *component,
 	INIT_LIST_HEAD(&component->dobj_list);
 	INIT_LIST_HEAD(&component->card_list);
 	INIT_LIST_HEAD(&component->list);
+	INIT_LIST_HEAD(&component->card_aux_list);
 	mutex_init(&component->io_mutex);
 
 	if (!component->name) {
-- 
cgit v1.2.3


From ca34ee6d0307a0b4e52c870dfc1bb8a3c3eb956e Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Mon, 30 Mar 2026 15:56:40 +0000
Subject: hwmon: (tps53679) Fix device ID comparison and printing in
 tps53676_identify()

tps53676_identify() uses strncmp() to compare the device ID buffer
against a byte sequence containing embedded non-printable bytes
(\x53\x67\x60). strncmp() is semantically wrong for binary data
comparison; use memcmp() instead.

Additionally, the buffer from i2c_smbus_read_block_data() is not
NUL-terminated, so printing it with "%s" in the error path is
undefined behavior and may read past the buffer. Use "%*ph" to
hex-dump the actual bytes returned.

Per the datasheet, the expected device ID is the 6-byte sequence
54 49 53 67 60 00 ("TI\x53\x67\x60\x00"), so compare all 6 bytes
including the trailing NUL.

Fixes: cb3d37b59012 ("hwmon: (pmbus/tps53679) Add support for TI TPS53676")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260330155618.77403-1-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/tps53679.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/pmbus/tps53679.c b/drivers/hwmon/pmbus/tps53679.c
index 3bca543817a6..249974c13aa3 100644
--- a/drivers/hwmon/pmbus/tps53679.c
+++ b/drivers/hwmon/pmbus/tps53679.c
@@ -175,8 +175,8 @@ static int tps53676_identify(struct i2c_client *client,
 	ret = i2c_smbus_read_block_data(client, PMBUS_IC_DEVICE_ID, buf);
 	if (ret < 0)
 		return ret;
-	if (strncmp("TI\x53\x67\x60", buf, 5)) {
-		dev_err(&client->dev, "Unexpected device ID: %s\n", buf);
+	if (ret != 6 || memcmp(buf, "TI\x53\x67\x60\x00", 6)) {
+		dev_err(&client->dev, "Unexpected device ID: %*ph\n", ret, buf);
 		return -ENODEV;
 	}
 
-- 
cgit v1.2.3


From b0dc7e7c56573e7a52080f25f3179a45f3dd7e6f Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 22 Mar 2026 22:28:45 +0800
Subject: spi: amlogic: spifc-a4: unregister ECC engine on probe failure and
 remove() callback

aml_sfc_probe() registers the on-host NAND ECC engine, but teardown was
missing from both probe unwind and remove-time cleanup. Add a devm cleanup
action after successful registration so
nand_ecc_unregister_on_host_hw_engine() runs automatically on probe
failures and during device removal.

Fixes: 4670db6f32e9 ("spi: amlogic: add driver for Amlogic SPI Flash Controller")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Link: https://patch.msgid.link/20260322-spifc-a4-v1-1-2dc5ebcbe0a9@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-amlogic-spifc-a4.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/spi/spi-amlogic-spifc-a4.c b/drivers/spi/spi-amlogic-spifc-a4.c
index 1aabafa36e48..16346f50c7d9 100644
--- a/drivers/spi/spi-amlogic-spifc-a4.c
+++ b/drivers/spi/spi-amlogic-spifc-a4.c
@@ -1066,6 +1066,13 @@ static const struct nand_ecc_engine_ops aml_sfc_ecc_engine_ops = {
 	.finish_io_req = aml_sfc_ecc_finish_io_req,
 };
 
+static void aml_sfc_unregister_ecc_engine(void *data)
+{
+	struct nand_ecc_engine *eng = data;
+
+	nand_ecc_unregister_on_host_hw_engine(eng);
+}
+
 static int aml_sfc_clk_init(struct aml_sfc *sfc)
 {
 	sfc->gate_clk = devm_clk_get_enabled(sfc->dev, "gate");
@@ -1149,6 +1156,11 @@ static int aml_sfc_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "failed to register Aml host ecc engine.\n");
 
+	ret = devm_add_action_or_reset(dev, aml_sfc_unregister_ecc_engine,
+				       &sfc->ecc_eng);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to add ECC unregister action\n");
+
 	ret = of_property_read_u32(np, "amlogic,rx-adj", &val);
 	if (!ret)
 		sfc->rx_adj = val;
-- 
cgit v1.2.3


From 415cb193bb9736f0e830286c72a6fa8eb2a9cc5c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 28 Mar 2026 14:18:55 -1000
Subject: sched_ext: Fix SCX_KICK_WAIT deadlock by deferring wait to balance
 callback

SCX_KICK_WAIT busy-waits in kick_cpus_irq_workfn() using
smp_cond_load_acquire() until the target CPU's kick_sync advances. Because
the irq_work runs in hardirq context, the waiting CPU cannot reschedule and
its own kick_sync never advances. If multiple CPUs form a wait cycle, all
CPUs deadlock.

Replace the busy-wait in kick_cpus_irq_workfn() with resched_curr() to
force the CPU through do_pick_task_scx(), which queues a balance callback
to perform the wait. The balance callback drops the rq lock and enables
IRQs following the sched_core_balance() pattern, so the CPU can process
IPIs while waiting. The local CPU's kick_sync is advanced on entry to
do_pick_task_scx() and continuously during the wait, ensuring any CPU that
starts waiting for us sees the advancement and cannot form cyclic
dependencies.

Fixes: 90e55164dad4 ("sched_ext: Implement SCX_KICK_WAIT")
Cc: stable@vger.kernel.org # v6.12+
Reported-by: Christian Loehle <christian.loehle@arm.com>
Link: https://lore.kernel.org/r/20260316100249.1651641-1-christian.loehle@arm.com
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Christian Loehle <christian.loehle@arm.com>
---
 kernel/sched/ext.c   | 95 ++++++++++++++++++++++++++++++++++++++--------------
 kernel/sched/sched.h |  3 ++
 2 files changed, 73 insertions(+), 25 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 26a6ac2f8826..d5bdcdb3f700 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2404,7 +2404,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 {
 	struct scx_sched *sch = scx_root;
 
-	/* see kick_cpus_irq_workfn() */
+	/* see kick_sync_wait_bal_cb() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
 	update_curr_scx(rq);
@@ -2447,6 +2447,48 @@ switch_class:
 		switch_class(rq, next);
 }
 
+static void kick_sync_wait_bal_cb(struct rq *rq)
+{
+	struct scx_kick_syncs __rcu *ks = __this_cpu_read(scx_kick_syncs);
+	unsigned long *ksyncs = rcu_dereference_sched(ks)->syncs;
+	bool waited;
+	s32 cpu;
+
+	/*
+	 * Drop rq lock and enable IRQs while waiting. IRQs must be enabled
+	 * — a target CPU may be waiting for us to process an IPI (e.g. TLB
+	 * flush) while we wait for its kick_sync to advance.
+	 *
+	 * Also, keep advancing our own kick_sync so that new kick_sync waits
+	 * targeting us, which can start after we drop the lock, cannot form
+	 * cyclic dependencies.
+	 */
+retry:
+	waited = false;
+	for_each_cpu(cpu, rq->scx.cpus_to_sync) {
+		/*
+		 * smp_load_acquire() pairs with smp_store_release() on
+		 * kick_sync updates on the target CPUs.
+		 */
+		if (cpu == cpu_of(rq) ||
+		    smp_load_acquire(&cpu_rq(cpu)->scx.kick_sync) != ksyncs[cpu]) {
+			cpumask_clear_cpu(cpu, rq->scx.cpus_to_sync);
+			continue;
+		}
+
+		raw_spin_rq_unlock_irq(rq);
+		while (READ_ONCE(cpu_rq(cpu)->scx.kick_sync) == ksyncs[cpu]) {
+			smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
+			cpu_relax();
+		}
+		raw_spin_rq_lock_irq(rq);
+		waited = true;
+	}
+
+	if (waited)
+		goto retry;
+}
+
 static struct task_struct *first_local_task(struct rq *rq)
 {
 	return list_first_entry_or_null(&rq->scx.local_dsq.list,
@@ -2460,7 +2502,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	bool keep_prev;
 	struct task_struct *p;
 
-	/* see kick_cpus_irq_workfn() */
+	/* see kick_sync_wait_bal_cb() */
 	smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1);
 
 	rq_modified_begin(rq, &ext_sched_class);
@@ -2470,6 +2512,17 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 	rq_repin_lock(rq, rf);
 	maybe_queue_balance_callback(rq);
 
+	/*
+	 * Defer to a balance callback which can drop rq lock and enable
+	 * IRQs. Waiting directly in the pick path would deadlock against
+	 * CPUs sending us IPIs (e.g. TLB flushes) while we wait for them.
+	 */
+	if (unlikely(rq->scx.kick_sync_pending)) {
+		rq->scx.kick_sync_pending = false;
+		queue_balance_callback(rq, &rq->scx.kick_sync_bal_cb,
+				       kick_sync_wait_bal_cb);
+	}
+
 	/*
 	 * If any higher-priority sched class enqueued a runnable task on
 	 * this rq during balance_one(), abort and return RETRY_TASK, so
@@ -4713,6 +4766,9 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 		if (!cpumask_empty(rq->scx.cpus_to_wait))
 			dump_line(&ns, "  cpus_to_wait   : %*pb",
 				  cpumask_pr_args(rq->scx.cpus_to_wait));
+		if (!cpumask_empty(rq->scx.cpus_to_sync))
+			dump_line(&ns, "  cpus_to_sync   : %*pb",
+				  cpumask_pr_args(rq->scx.cpus_to_sync));
 
 		used = seq_buf_used(&ns);
 		if (SCX_HAS_OP(sch, dump_cpu)) {
@@ -5610,11 +5666,11 @@ static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *ksyncs)
 
 		if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) {
 			if (cur_class == &ext_sched_class) {
+				cpumask_set_cpu(cpu, this_scx->cpus_to_sync);
 				ksyncs[cpu] = rq->scx.kick_sync;
 				should_wait = true;
-			} else {
-				cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
 			}
+			cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
 		}
 
 		resched_curr(rq);
@@ -5669,27 +5725,15 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work)
 		cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
 	}
 
-	if (!should_wait)
-		return;
-
-	for_each_cpu(cpu, this_scx->cpus_to_wait) {
-		unsigned long *wait_kick_sync = &cpu_rq(cpu)->scx.kick_sync;
-
-		/*
-		 * Busy-wait until the task running at the time of kicking is no
-		 * longer running. This can be used to implement e.g. core
-		 * scheduling.
-		 *
-		 * smp_cond_load_acquire() pairs with store_releases in
-		 * pick_task_scx() and put_prev_task_scx(). The former breaks
-		 * the wait if SCX's scheduling path is entered even if the same
-		 * task is picked subsequently. The latter is necessary to break
-		 * the wait when $cpu is taken by a higher sched class.
-		 */
-		if (cpu != cpu_of(this_rq))
-			smp_cond_load_acquire(wait_kick_sync, VAL != ksyncs[cpu]);
-
-		cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
+	/*
+	 * Can't wait in hardirq — kick_sync can't advance, deadlocking if
+	 * CPUs wait for each other. Defer to kick_sync_wait_bal_cb().
+	 */
+	if (should_wait) {
+		raw_spin_rq_lock(this_rq);
+		this_scx->kick_sync_pending = true;
+		resched_curr(this_rq);
+		raw_spin_rq_unlock(this_rq);
 	}
 }
 
@@ -5794,6 +5838,7 @@ void __init init_sched_ext_class(void)
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_preempt, GFP_KERNEL, n));
 		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_wait, GFP_KERNEL, n));
+		BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_sync, GFP_KERNEL, n));
 		rq->scx.deferred_irq_work = IRQ_WORK_INIT_HARD(deferred_irq_workfn);
 		rq->scx.kick_cpus_irq_work = IRQ_WORK_INIT_HARD(kick_cpus_irq_workfn);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 43bbf0693cca..1ef9ba480f51 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -805,9 +805,12 @@ struct scx_rq {
 	cpumask_var_t		cpus_to_kick_if_idle;
 	cpumask_var_t		cpus_to_preempt;
 	cpumask_var_t		cpus_to_wait;
+	cpumask_var_t		cpus_to_sync;
+	bool			kick_sync_pending;
 	unsigned long		kick_sync;
 	local_t			reenq_local_deferred;
 	struct balance_callback	deferred_bal_cb;
+	struct balance_callback	kick_sync_bal_cb;
 	struct irq_work		deferred_irq_work;
 	struct irq_work		kick_cpus_irq_work;
 	struct scx_dispatch_q	bypass_dsq;
-- 
cgit v1.2.3


From 090d34f0f0285124452373225bcc520a31e305e4 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 28 Mar 2026 14:18:56 -1000
Subject: selftests/sched_ext: Add cyclic SCX_KICK_WAIT stress test

Add a test that creates a 3-CPU kick_wait cycle (A->B->C->A). A BPF
scheduler kicks the next CPU in the ring with SCX_KICK_WAIT on every
enqueue while userspace workers generate continuous scheduling churn via
sched_yield(). Without the preceding fix, this hangs the machine within seconds.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Tested-by: Christian Loehle <christian.loehle@arm.com>
---
 tools/testing/selftests/sched_ext/Makefile         |   1 +
 .../selftests/sched_ext/cyclic_kick_wait.bpf.c     |  68 ++++++++
 .../testing/selftests/sched_ext/cyclic_kick_wait.c | 194 +++++++++++++++++++++
 3 files changed, 263 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/cyclic_kick_wait.c

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 006300ac6dff..1c9ca328cca1 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -188,6 +188,7 @@ auto-test-targets :=			\
 	rt_stall			\
 	test_example			\
 	total_bw			\
+	cyclic_kick_wait		\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 
diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
new file mode 100644
index 000000000000..cb34d3335917
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock.
+ *
+ * Three CPUs are designated from userspace. Every enqueue from one of the
+ * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a
+ * persistent A -> B -> C -> A wait cycle pressure.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu_a;
+const volatile s32 test_cpu_b;
+const volatile s32 test_cpu_c;
+
+u64 nr_enqueues;
+u64 nr_wait_kicks;
+
+UEI_DEFINE(uei);
+
+static s32 target_cpu(s32 cpu)
+{
+	if (cpu == test_cpu_a)
+		return test_cpu_b;
+	if (cpu == test_cpu_b)
+		return test_cpu_c;
+	if (cpu == test_cpu_c)
+		return test_cpu_a;
+	return -1;
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 tgt;
+
+	__sync_fetch_and_add(&nr_enqueues, 1);
+
+	if (p->flags & PF_KTHREAD) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				   enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+
+	tgt = target_cpu(this_cpu);
+	if (tgt < 0 || tgt == this_cpu)
+		return;
+
+	__sync_fetch_and_add(&nr_wait_kicks, 1);
+	scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT);
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops cyclic_kick_wait_ops = {
+	.enqueue		= cyclic_kick_wait_enqueue,
+	.exit			= cyclic_kick_wait_exit,
+	.name			= "cyclic_kick_wait",
+	.timeout_ms		= 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c
new file mode 100644
index 000000000000..c2e5aa9de715
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.c
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Test SCX_KICK_WAIT forward progress under cyclic wait pressure.
+ *
+ * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path.
+ * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits
+ * for A), all CPUs deadlock unless the implementation breaks the cycle.
+ *
+ * This test creates that scenario: three CPUs are arranged in a ring. The BPF
+ * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT
+ * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling
+ * sched_yield(), generating a steady stream of enqueues and thus sustained
+ * A->B->C->A kick_wait cycle pressure. The test passes if the system remains
+ * responsive for 5 seconds without the scheduler being killed by the watchdog.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <stdint.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "scx_test.h"
+#include "cyclic_kick_wait.bpf.skel.h"
+
+#define WORKERS_PER_CPU	4
+#define NR_TEST_CPUS	3
+#define NR_WORKERS	(NR_TEST_CPUS * WORKERS_PER_CPU)
+
+struct worker_ctx {
+	pthread_t tid;
+	int cpu;
+	volatile bool stop;
+	volatile __u64 iters;
+	bool started;
+};
+
+static void *worker_fn(void *arg)
+{
+	struct worker_ctx *worker = arg;
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(worker->cpu, &mask);
+
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		return (void *)(uintptr_t)errno;
+
+	while (!worker->stop) {
+		sched_yield();
+		worker->iters++;
+	}
+
+	return NULL;
+}
+
+static int join_worker(struct worker_ctx *worker)
+{
+	void *ret;
+	struct timespec ts;
+	int err;
+
+	if (!worker->started)
+		return 0;
+
+	if (clock_gettime(CLOCK_REALTIME, &ts))
+		return -errno;
+
+	ts.tv_sec += 2;
+	err = pthread_timedjoin_np(worker->tid, &ret, &ts);
+	if (err == ETIMEDOUT)
+		pthread_detach(worker->tid);
+	if (err)
+		return -err;
+
+	if ((uintptr_t)ret)
+		return -(int)(uintptr_t)ret;
+
+	return 0;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct cyclic_kick_wait *skel;
+
+	skel = cyclic_kick_wait__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+
+	*ctx = skel;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+	struct worker_ctx workers[NR_WORKERS] = {};
+	struct bpf_link *link = NULL;
+	enum scx_test_status status = SCX_TEST_PASS;
+	int test_cpus[NR_TEST_CPUS];
+	int nr_cpus = 0;
+	cpu_set_t mask;
+	int ret, i;
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		SCX_ERR("Failed to get affinity (%d)", errno);
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &mask))
+			test_cpus[nr_cpus++] = i;
+		if (nr_cpus == NR_TEST_CPUS)
+			break;
+	}
+
+	if (nr_cpus < NR_TEST_CPUS)
+		return SCX_TEST_SKIP;
+
+	skel->rodata->test_cpu_a = test_cpus[0];
+	skel->rodata->test_cpu_b = test_cpus[1];
+	skel->rodata->test_cpu_c = test_cpus[2];
+
+	if (cyclic_kick_wait__load(skel)) {
+		SCX_ERR("Failed to load skel");
+		return SCX_TEST_FAIL;
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].cpu = test_cpus[i / WORKERS_PER_CPU];
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]);
+		if (ret) {
+			SCX_ERR("Failed to create worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+			goto out;
+		}
+		workers[i].started = true;
+	}
+
+	sleep(5);
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		status = SCX_TEST_FAIL;
+	}
+
+out:
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].stop = true;
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = join_worker(&workers[i]);
+		if (ret && status == SCX_TEST_PASS) {
+			SCX_ERR("Failed to join worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	if (link)
+		bpf_link__destroy(link);
+
+	return status;
+}
+
+static void cleanup(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+
+	cyclic_kick_wait__destroy(skel);
+}
+
+struct scx_test cyclic_kick_wait = {
+	.name = "cyclic_kick_wait",
+	.description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&cyclic_kick_wait)
-- 
cgit v1.2.3


From 622363757b2286dd2c2984b0d80255cbb35a0495 Mon Sep 17 00:00:00 2001
From: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Date: Tue, 24 Mar 2026 22:09:09 +0100
Subject: ASoC: ep93xx: Fix unchecked clk_prepare_enable() and add rollback on
 failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ep93xx_i2s_enable() calls clk_prepare_enable() on three clocks in
sequence (mclk, sclk, lrclk) without checking the return value of any
of them. If an intermediate enable fails, the clocks that were already
enabled are never rolled back, leaking them until the next disable cycle
— which may never come if the stream never started cleanly.

Change ep93xx_i2s_enable() from void to int. Add error checking after
each clk_prepare_enable() call and unwind already-enabled clocks on
failure. Propagate the error through ep93xx_i2s_startup() and
ep93xx_i2s_resume(), both of which already return int.

Signed-off-by: Jihed Chaibi <jihed.chaibi.dev@gmail.com>
Fixes: f4ff6b56bc8a ("ASoC: cirrus: i2s: Prepare clock before using it")
Link: https://patch.msgid.link/20260324210909.45494-1-jihed.chaibi.dev@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/cirrus/ep93xx-i2s.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/sound/soc/cirrus/ep93xx-i2s.c b/sound/soc/cirrus/ep93xx-i2s.c
index cca01c03f048..5dba741594fa 100644
--- a/sound/soc/cirrus/ep93xx-i2s.c
+++ b/sound/soc/cirrus/ep93xx-i2s.c
@@ -91,16 +91,28 @@ static inline unsigned ep93xx_i2s_read_reg(struct ep93xx_i2s_info *info,
 	return __raw_readl(info->regs + reg);
 }
 
-static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
+static int ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
 {
 	unsigned base_reg;
+	int err;
 
 	if ((ep93xx_i2s_read_reg(info, EP93XX_I2S_TX0EN) & 0x1) == 0 &&
 	    (ep93xx_i2s_read_reg(info, EP93XX_I2S_RX0EN) & 0x1) == 0) {
 		/* Enable clocks */
-		clk_prepare_enable(info->mclk);
-		clk_prepare_enable(info->sclk);
-		clk_prepare_enable(info->lrclk);
+		err = clk_prepare_enable(info->mclk);
+		if (err)
+			return err;
+		err = clk_prepare_enable(info->sclk);
+		if (err) {
+			clk_disable_unprepare(info->mclk);
+			return err;
+		}
+		err = clk_prepare_enable(info->lrclk);
+		if (err) {
+			clk_disable_unprepare(info->sclk);
+			clk_disable_unprepare(info->mclk);
+			return err;
+		}
 
 		/* Enable i2s */
 		ep93xx_i2s_write_reg(info, EP93XX_I2S_GLCTRL, 1);
@@ -119,6 +131,8 @@ static void ep93xx_i2s_enable(struct ep93xx_i2s_info *info, int stream)
 		ep93xx_i2s_write_reg(info, EP93XX_I2S_TXCTRL,
 				     EP93XX_I2S_TXCTRL_TXEMPTY_LVL |
 				     EP93XX_I2S_TXCTRL_TXUFIE);
+
+	return 0;
 }
 
 static void ep93xx_i2s_disable(struct ep93xx_i2s_info *info, int stream)
@@ -195,9 +209,7 @@ static int ep93xx_i2s_startup(struct snd_pcm_substream *substream,
 {
 	struct ep93xx_i2s_info *info = snd_soc_dai_get_drvdata(dai);
 
-	ep93xx_i2s_enable(info, substream->stream);
-
-	return 0;
+	return ep93xx_i2s_enable(info, substream->stream);
 }
 
 static void ep93xx_i2s_shutdown(struct snd_pcm_substream *substream,
@@ -373,14 +385,16 @@ static int ep93xx_i2s_suspend(struct snd_soc_component *component)
 static int ep93xx_i2s_resume(struct snd_soc_component *component)
 {
 	struct ep93xx_i2s_info *info = snd_soc_component_get_drvdata(component);
+	int err;
 
 	if (!snd_soc_component_active(component))
 		return 0;
 
-	ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK);
-	ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE);
+	err = ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_PLAYBACK);
+	if (err)
+		return err;
 
-	return 0;
+	return ep93xx_i2s_enable(info, SNDRV_PCM_STREAM_CAPTURE);
 }
 #else
 #define ep93xx_i2s_suspend	NULL
-- 
cgit v1.2.3


From 9badc2a84e688be1275bb740942d5f6f51746908 Mon Sep 17 00:00:00 2001
From: Changwoo Min <changwoo@igalia.com>
Date: Sun, 29 Mar 2026 16:36:15 +0900
Subject: PM: EM: Fix NULL pointer dereference when perf domain ID is not found

dev_energymodel_nl_get_perf_domains_doit() calls
em_perf_domain_get_by_id() but does not check the return value before
passing it to __em_nl_get_pd_size(). When a caller supplies a
non-existent perf domain ID, em_perf_domain_get_by_id() returns NULL,
and __em_nl_get_pd_size() immediately dereferences pd->cpus
(struct offset 0x30), causing a NULL pointer dereference.

The sister handler dev_energymodel_nl_get_perf_table_doit() already
handles this correctly via __em_nl_get_pd_table_id(), which returns
NULL and causes the caller to return -EINVAL. Add the same NULL check
in the get-perf-domains do handler.

Fixes: 380ff27af25e ("PM: EM: Add dump to get-perf-domains in the EM YNL spec")
Reported-by: Yi Lai <yi1.lai@linux.intel.com>
Closes: https://lore.kernel.org/lkml/aXiySM79UYfk+ytd@ly-workstation/
Signed-off-by: Changwoo Min <changwoo@igalia.com>
Cc: 6.19+ <stable@vger.kernel.org> # 6.19+
[ rjw: Subject and changelog edits ]
Link: https://patch.msgid.link/20260329073615.649976-1-changwoo@igalia.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/em_netlink.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/power/em_netlink.c b/kernel/power/em_netlink.c
index 5a611d3950fd..4d4fd29bd2be 100644
--- a/kernel/power/em_netlink.c
+++ b/kernel/power/em_netlink.c
@@ -109,6 +109,8 @@ int dev_energymodel_nl_get_perf_domains_doit(struct sk_buff *skb,
 
 	id = nla_get_u32(info->attrs[DEV_ENERGYMODEL_A_PERF_DOMAIN_PERF_DOMAIN_ID]);
 	pd = em_perf_domain_get_by_id(id);
+	if (!pd)
+		return -EINVAL;
 
 	__em_nl_get_pd_size(pd, &msg_sz);
 	msg = genlmsg_new(msg_sz, GFP_KERNEL);
-- 
cgit v1.2.3


From a3ffaa5b397f4df9d6ac16b10583e9df8e6fa471 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 17 Mar 2026 16:34:41 -0400
Subject: drm/amdgpu/pm: drop SMU driver if version not matched messages

It just leads to user confusion.

Cc: Yang Wang <kevinyang.wang@amd.com>
Cc: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e471627d56272a791972f25e467348b611c31713)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 1 -
 drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c | 1 -
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c | 1 -
 3 files changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 12b052d920f5..7ca8fdd23206 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -262,7 +262,6 @@ int smu_v11_0_check_fw_version(struct smu_context *smu)
 			"smu fw program = %d, version = 0x%08x (%d.%d.%d)\n",
 			smu->smc_driver_if_version, if_version,
 			smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(smu->adev->dev, "SMU driver if version not matched\n");
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
index 2c20624caca4..ac5e44dff6c9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -101,7 +101,6 @@ int smu_v12_0_check_fw_version(struct smu_context *smu)
 			"smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			smu->smc_driver_if_version, if_version,
 			smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(smu->adev->dev, "SMU driver if version not matched\n");
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index cec2df1ad0af..e38354c694c9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -284,7 +284,6 @@ int smu_v14_0_check_fw_version(struct smu_context *smu)
 			 "smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			 smu->smc_driver_if_version, if_version,
 			 smu_program, smu_version, smu_major, smu_minor, smu_debug);
-		dev_info(adev->dev, "SMU driver if version not matched\n");
 	}
 
 	return ret;
-- 
cgit v1.2.3


From a018d1819f158991b7308e4f74609c6c029b670c Mon Sep 17 00:00:00 2001
From: Junrui Luo <moonafterrain@outlook.com>
Date: Tue, 24 Mar 2026 17:39:02 +0800
Subject: drm/amdgpu: validate doorbell_offset in user queue creation

amdgpu_userq_get_doorbell_index() passes the user-provided
doorbell_offset to amdgpu_doorbell_index_on_bar() without bounds
checking. An arbitrarily large doorbell_offset can cause the
calculated doorbell index to fall outside the allocated doorbell BO,
potentially corrupting kernel doorbell space.

Validate that doorbell_offset falls within the doorbell BO before
computing the BAR index, using u64 arithmetic to prevent overflow.

Fixes: f09c1e6077ab ("drm/amdgpu: generate doorbell index for userqueue")
Reported-by: Yuhao Jiang <danisjiang@gmail.com>
Signed-off-by: Junrui Luo <moonafterrain@outlook.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit de1ef4ffd70e1d15f0bf584fd22b1f28cbd5e2ec)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 7c450350847d..0a1b93259887 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -600,6 +600,13 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 		goto unpin_bo;
 	}
 
+	/* Validate doorbell_offset is within the doorbell BO */
+	if ((u64)db_info->doorbell_offset * db_size + db_size >
+	    amdgpu_bo_size(db_obj->obj)) {
+		r = -EINVAL;
+		goto unpin_bo;
+	}
+
 	index = amdgpu_doorbell_index_on_bar(uq_mgr->adev, db_obj->obj,
 					     db_info->doorbell_offset, db_size);
 	drm_dbg_driver(adev_to_drm(uq_mgr->adev),
-- 
cgit v1.2.3


From 62f553d60a801384336f5867967c26ddf3b17038 Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Mon, 23 Mar 2026 16:07:02 +0800
Subject: drm/amdgpu: fix the idr allocation flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the IDR allocation flags by using atomic GFP
flags in non‑sleepable contexts to avoid the __might_sleep()
complaint.

  268.290239] [drm] Initialized amdgpu 3.64.0 for 0000:03:00.0 on minor 0
[  268.294900] BUG: sleeping function called from invalid context at ./include/linux/sched/mm.h:323
[  268.295355] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1744, name: modprobe
[  268.295705] preempt_count: 1, expected: 0
[  268.295886] RCU nest depth: 0, expected: 0
[  268.296072] 2 locks held by modprobe/1744:
[  268.296077]  #0: ffff8c3a44abd1b8 (&dev->mutex){....}-{4:4}, at: __driver_attach+0xe4/0x210
[  268.296100]  #1: ffffffffc1a6ea78 (amdgpu_pasid_idr_lock){+.+.}-{3:3}, at: amdgpu_pasid_alloc+0x26/0xe0 [amdgpu]
[  268.296494] CPU: 12 UID: 0 PID: 1744 Comm: modprobe Tainted: G     U     OE       6.19.0-custom #16 PREEMPT(voluntary)
[  268.296498] Tainted: [U]=USER, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
[  268.296499] Hardware name: AMD Majolica-RN/Majolica-RN, BIOS RMJ1009A 06/13/2021
[  268.296501] Call Trace:

Fixes: 8f1de51f49be ("drm/amdgpu: prevent immediate PASID reuse case")
Tested-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ea56aa2625708eaf96f310032391ff37746310ef)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index d88523568b62..569c5a89ff10 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -68,8 +68,11 @@ int amdgpu_pasid_alloc(unsigned int bits)
 		return -EINVAL;
 
 	spin_lock(&amdgpu_pasid_idr_lock);
+	/* TODO: Need to replace the idr with an xarry, and then
+	 * handle the internal locking with ATOMIC safe paths.
+	 */
 	pasid = idr_alloc_cyclic(&amdgpu_pasid_idr, NULL, 1,
-				 1U << bits, GFP_KERNEL);
+				 1U << bits, GFP_ATOMIC);
 	spin_unlock(&amdgpu_pasid_idr_lock);
 
 	if (pasid >= 0)
-- 
cgit v1.2.3


From 68484a648ade555842e0c75a392f3572b3d51998 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Mon, 23 Mar 2026 09:58:35 +0530
Subject: drm/amdkfd: Align expected_queue_size to PAGE_SIZE

The AQL queue size can be 4K, but the minimum buffer object (BO)
allocation size is PAGE_SIZE. On systems with a page size larger
than 4K, the expected queue size does not match the allocated BO
size, causing queue creation to fail.

Align the expected queue size to PAGE_SIZE so that it matches the
allocated BO size and allows queue creation to succeed.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b01cd158a2f5230b137396c5f8cda3fc780abbc2)
---
 drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index bbe869ceae3f..e1a922bb2ab7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -249,10 +249,10 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	    topo_dev->node_props.gfx_target_version < 90000)
 		/* metadata_queue_size not supported on GFX7/GFX8 */
 		expected_queue_size =
-			properties->queue_size / 2;
+			PAGE_ALIGN(properties->queue_size / 2);
 	else
 		expected_queue_size =
-			properties->queue_size + properties->metadata_queue_size;
+			PAGE_ALIGN(properties->queue_size + properties->metadata_queue_size);
 
 	vm = drm_priv_to_vm(pdd->drm_priv);
 	err = amdgpu_bo_reserve(vm->root.bo, false);
-- 
cgit v1.2.3


From 6caeace0d1471b33bb43b58893940cc90baca5b9 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Mon, 23 Mar 2026 09:58:38 +0530
Subject: drm/amd: Fix MQD and control stack alignment for non-4K
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For gfxV9, due to a hardware bug ("based on the comments in the code
here [1]"), the control stack of a user-mode compute queue must be
allocated immediately after the page boundary of its regular MQD buffer.
To handle this, we allocate an enlarged MQD buffer where the first page
is used as the MQD and the remaining pages store the control stack.
Although these regions share the same BO, they require different memory
types: the MQD must be UC (uncached), while the control stack must be
NC (non-coherent), matching the behavior when the control stack is
allocated in user space.

This logic works correctly on systems where the CPU page size matches
the GPU page size (4K). However, the current implementation aligns both
the MQD and the control stack to the CPU PAGE_SIZE. On systems with a
larger CPU page size, the entire first CPU page is marked UC—even though
that page may contain multiple GPU pages. The GPU treats the second 4K
GPU page inside that CPU page as part of the control stack, but it is
incorrectly mapped as UC.

This patch fixes the issue by aligning both the MQD and control stack
sizes to the GPU page size (4K). The first 4K page is correctly marked
as UC for the MQD, and the remaining GPU pages are marked NC for the
control stack. This ensures proper memory type assignment on systems
with larger CPU page sizes.

[1]: https://elixir.bootlin.com/linux/v6.18/source/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c#L118

Acked-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 998d6781410de1c4b787fdbf6c56e851ea7fa553)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c        | 44 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h        |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c         | 16 ++-------
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 23 ++++++++-----
 4 files changed, 64 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index e2d32c29668a..bc772ca3dab7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -403,6 +403,50 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
 	drm_dev_exit(idx);
 }
 
+/**
+ * amdgpu_gart_map_gfx9_mqd - map mqd and ctrl_stack dma_addresses into GART entries
+ *
+ * @adev: amdgpu_device pointer
+ * @offset: offset into the GPU's gart aperture
+ * @pages: number of pages to bind
+ * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
+ *
+ * Map the MQD and control stack addresses into GART entries with the correct
+ * memory types on gfxv9. The MQD occupies the first 4KB and is followed by
+ * the control stack. The MQD uses UC (uncached) memory, while the control stack
+ * uses NC (non-coherent) memory.
+ */
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags)
+{
+	uint64_t page_base;
+	unsigned int i, j, t;
+	int idx;
+	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
+	void *dst;
+
+	if (!adev->gart.ptr)
+		return;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return;
+
+	t = offset / AMDGPU_GPU_PAGE_SIZE;
+	dst = adev->gart.ptr;
+	for (i = 0; i < pages; i++) {
+		page_base = dma_addr[i];
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
+			if ((i == 0) && (j == 0))
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
+			else
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, ctrl_flags);
+			page_base += AMDGPU_GPU_PAGE_SIZE;
+		}
+	}
+	drm_dev_exit(idx);
+}
+
 /**
  * amdgpu_gart_bind - bind pages into the gart page table
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index d3118275ddae..6ebd2da32ea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -62,6 +62,8 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, dma_addr_t *dma_addr, uint64_t flags,
 		     void *dst);
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		      int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index eeaa56c8d129..0ccb31788b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -853,25 +853,15 @@ static void amdgpu_ttm_gart_bind_gfx9_mqd(struct amdgpu_device *adev,
 	int num_xcc = max(1U, adev->gfx.num_xcc_per_xcp);
 	uint64_t page_idx, pages_per_xcc;
 	int i;
-	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
 
 	pages_per_xcc = total_pages;
 	do_div(pages_per_xcc, num_xcc);
 
 	for (i = 0, page_idx = 0; i < num_xcc; i++, page_idx += pages_per_xcc) {
-		/* MQD page: use default flags */
-		amdgpu_gart_bind(adev,
+		amdgpu_gart_map_gfx9_mqd(adev,
 				gtt->offset + (page_idx << PAGE_SHIFT),
-				1, &gtt->ttm.dma_address[page_idx], flags);
-		/*
-		 * Ctrl pages - modify the memory type to NC (ctrl_flags) from
-		 * the second page of the BO onward.
-		 */
-		amdgpu_gart_bind(adev,
-				gtt->offset + ((page_idx + 1) << PAGE_SHIFT),
-				pages_per_xcc - 1,
-				&gtt->ttm.dma_address[page_idx + 1],
-				ctrl_flags);
+				pages_per_xcc, &gtt->ttm.dma_address[page_idx],
+				flags);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index d5c234f30e8d..a535f151cb5f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -42,9 +42,16 @@ static uint64_t mqd_stride_v9(struct mqd_manager *mm,
 				struct queue_properties *q)
 {
 	if (mm->dev->kfd->cwsr_enabled &&
-	    q->type == KFD_QUEUE_TYPE_COMPUTE)
-		return ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE);
+	    q->type == KFD_QUEUE_TYPE_COMPUTE) {
+
+		/* On gfxv9, the MQD resides in the first 4K page,
+		 * followed by the control stack. Align both to
+		 * AMDGPU_GPU_PAGE_SIZE to maintain the required 4K boundary.
+		 */
+
+		return ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE);
+	}
 
 	return mm->mqd_size;
 }
@@ -151,8 +158,8 @@ static struct kfd_mem_obj *allocate_mqd(struct mqd_manager *mm,
 		if (!mqd_mem_obj)
 			return NULL;
 		retval = amdgpu_amdkfd_alloc_kernel_mem(node->adev,
-			(ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE)) *
+			(ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE)) *
 			NUM_XCC(node->xcc_mask),
 			mqd_on_vram(node->adev) ? AMDGPU_GEM_DOMAIN_VRAM :
 						  AMDGPU_GEM_DOMAIN_GTT,
@@ -360,7 +367,7 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	struct kfd_context_save_area_header header;
 
 	/* Control stack is located one page after MQD. */
-	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);
 
 	m = get_mqd(mqd);
 
@@ -397,7 +404,7 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, voi
 {
 	struct v9_mqd *m;
 	/* Control stack is located one page after MQD. */
-	void *ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);
 
 	m = get_mqd(mqd);
 
@@ -443,7 +450,7 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd,
 		*gart_addr = addr;
 
 	/* Control stack is located one page after MQD. */
-	ctl_stack = (void *)((uintptr_t)*mqd + PAGE_SIZE);
+	ctl_stack = (void *)((uintptr_t)*mqd + AMDGPU_GPU_PAGE_SIZE);
 	memcpy(ctl_stack, ctl_stack_src, ctl_stack_size);
 
 	m->cp_hqd_pq_doorbell_control =
-- 
cgit v1.2.3


From ced5c30e47d1cd52d6ae40f809223a6286854086 Mon Sep 17 00:00:00 2001
From: Junrui Luo <moonafterrain@outlook.com>
Date: Sat, 14 Mar 2026 23:33:53 +0800
Subject: drm/amdgpu/userq: fix memory leak in MQD creation error paths

In mes_userq_mqd_create(), the memdup_user() allocations for
IP-specific MQD structs are not freed when subsequent VA validation
fails. The goto free_mqd label only cleans up the MQD BO object and
userq_props.

Fix by adding kfree() before each goto free_mqd on VA validation
failure in the COMPUTE, GFX, and SDMA branches.

Fixes: 9e46b8bb0539 ("drm/amdgpu: validate userq buffer virtual address and size")
Reported-by: Yuhao Jiang <danisjiang@gmail.com>
Signed-off-by: Junrui Luo <moonafterrain@outlook.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 27f5ff9e4a4150d7cf8b4085aedd3b77ddcc5d08)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mes_userqueue.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index 8c74894254f7..faac21ee5739 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -324,8 +324,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		r = amdgpu_userq_input_va_validate(adev, queue, compute_mqd->eop_va,
 						   2048);
-		if (r)
+		if (r) {
+			kfree(compute_mqd);
 			goto free_mqd;
+		}
 
 		userq_props->eop_gpu_addr = compute_mqd->eop_va;
 		userq_props->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_NORMAL;
@@ -365,12 +367,16 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->shadow_va,
 						   shadow_info.shadow_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_gfx_v11->csa_va,
 						   shadow_info.csa_size);
-		if (r)
+		if (r) {
+			kfree(mqd_gfx_v11);
 			goto free_mqd;
+		}
 
 		kfree(mqd_gfx_v11);
 	} else if (queue->queue_type == AMDGPU_HW_IP_DMA) {
@@ -390,8 +396,10 @@ static int mes_userq_mqd_create(struct amdgpu_usermode_queue *queue,
 		}
 		r = amdgpu_userq_input_va_validate(adev, queue, mqd_sdma_v11->csa_va,
 						   32);
-		if (r)
+		if (r) {
+			kfree(mqd_sdma_v11);
 			goto free_mqd;
+		}
 
 		userq_props->csa_addr = mqd_sdma_v11->csa_va;
 		kfree(mqd_sdma_v11);
-- 
cgit v1.2.3


From 4487571ef17a30d274600b3bd6965f497a881299 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Thu, 26 Mar 2026 17:51:28 +0530
Subject: drm/amdgpu: Change AMDGPU_VA_RESERVED_TRAP_SIZE to 64KB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, AMDGPU_VA_RESERVED_TRAP_SIZE is hardcoded to 8KB, while
KFD_CWSR_TBA_TMA_SIZE is defined as 2 * PAGE_SIZE. On systems with
4K pages, both values match (8KB), so allocation and reserved space
are consistent.

However, on 64K page-size systems, KFD_CWSR_TBA_TMA_SIZE becomes 128KB,
while the reserved trap area remains 8KB. This mismatch causes the
kernel to crash when running rocminfo or rccl unit tests.

Kernel attempted to read user page (2) - exploit attempt? (uid: 1001)
BUG: Kernel NULL pointer dereference on read at 0x00000002
Faulting instruction address: 0xc0000000002c8a64
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries
CPU: 34 UID: 1001 PID: 9379 Comm: rocminfo Tainted: G E
6.19.0-rc4-amdgpu-00320-gf23176405700 #56 VOLUNTARY
Tainted: [E]=UNSIGNED_MODULE
Hardware name: IBM,9105-42A POWER10 (architected) 0x800200 0xf000006
of:IBM,FW1060.30 (ML1060_896) hv:phyp pSeries
NIP:  c0000000002c8a64 LR: c00000000125dbc8 CTR: c00000000125e730
REGS: c0000001e0957580 TRAP: 0300 Tainted: G E
MSR:  8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 24008268
XER: 00000036
CFAR: c00000000125dbc4 DAR: 0000000000000002 DSISR: 40000000
IRQMASK: 1
GPR00: c00000000125d908 c0000001e0957820 c0000000016e8100
c00000013d814540
GPR04: 0000000000000002 c00000013d814550 0000000000000045
0000000000000000
GPR08: c00000013444d000 c00000013d814538 c00000013d814538
0000000084002268
GPR12: c00000000125e730 c000007e2ffd5f00 ffffffffffffffff
0000000000020000
GPR16: 0000000000000000 0000000000000002 c00000015f653000
0000000000000000
GPR20: c000000138662400 c00000013d814540 0000000000000000
c00000013d814500
GPR24: 0000000000000000 0000000000000002 c0000001e0957888
c0000001e0957878
GPR28: c00000013d814548 0000000000000000 c00000013d814540
c0000001e0957888
NIP [c0000000002c8a64] __mutex_add_waiter+0x24/0xc0
LR [c00000000125dbc8] __mutex_lock.constprop.0+0x318/0xd00
Call Trace:
0xc0000001e0957890 (unreliable)
__mutex_lock.constprop.0+0x58/0xd00
amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x6fc/0xb60 [amdgpu]
kfd_process_alloc_gpuvm+0x54/0x1f0 [amdgpu]
kfd_process_device_init_cwsr_dgpu+0xa4/0x1a0 [amdgpu]
kfd_process_device_init_vm+0xd8/0x2e0 [amdgpu]
kfd_ioctl_acquire_vm+0xd0/0x130 [amdgpu]
kfd_ioctl+0x514/0x670 [amdgpu]
sys_ioctl+0x134/0x180
system_call_exception+0x114/0x300
system_call_vectored_common+0x15c/0x2ec

This patch changes AMDGPU_VA_RESERVED_TRAP_SIZE to 64 KB and
KFD_CWSR_TBA_TMA_SIZE to the AMD GPU page size. This means we reserve
64 KB for the trap in the address space, but only allocate 8 KB within
it. With this approach, the allocation size never exceeds the reserved
area.

Fixes: 34a1de0f7935 ("drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole")
Reviewed-by: Christian König <christian.koenig@amd.com>
Suggested-by: Felix Kuehling <felix.kuehling@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 31b8de5e55666f26ea7ece5f412b83eab3f56dbb)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index bb276c0ad06d..d5b7061556ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -173,7 +173,7 @@ struct amdgpu_bo_vm;
 #define AMDGPU_VA_RESERVED_SEQ64_SIZE		(2ULL << 20)
 #define AMDGPU_VA_RESERVED_SEQ64_START(adev)	(AMDGPU_VA_RESERVED_CSA_START(adev) \
 						 - AMDGPU_VA_RESERVED_SEQ64_SIZE)
-#define AMDGPU_VA_RESERVED_TRAP_SIZE		(2ULL << 12)
+#define AMDGPU_VA_RESERVED_TRAP_SIZE		(1ULL << 16)
 #define AMDGPU_VA_RESERVED_TRAP_START(adev)	(AMDGPU_VA_RESERVED_SEQ64_START(adev) \
 						 - AMDGPU_VA_RESERVED_TRAP_SIZE)
 #define AMDGPU_VA_RESERVED_BOTTOM		(1ULL << 16)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index e5b56412931b..035687a17d89 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -102,8 +102,8 @@
  * The first chunk is the TBA used for the CWSR ISA code. The second
  * chunk is used as TMA for user-mode trap handler setup in daisy-chain mode.
  */
-#define KFD_CWSR_TBA_TMA_SIZE (PAGE_SIZE * 2)
-#define KFD_CWSR_TMA_OFFSET (PAGE_SIZE + 2048)
+#define KFD_CWSR_TBA_TMA_SIZE (AMDGPU_GPU_PAGE_SIZE * 2)
+#define KFD_CWSR_TMA_OFFSET (AMDGPU_GPU_PAGE_SIZE + 2048)
 
 #define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
 	(KFD_MAX_NUM_OF_PROCESSES *			\
-- 
cgit v1.2.3


From e927b36ae18b66b49219eaa9f46edc7b4fdbb25e Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sat, 21 Mar 2026 17:25:14 +0530
Subject: drm/amd/display: Fix NULL pointer dereference in dcn401_init_hw()

dcn401_init_hw() assumes that update_bw_bounding_box() is valid when
entering the update path. However, the existing condition:

  ((!fams2_enable && update_bw_bounding_box) || freq_changed)

does not guarantee this, as the freq_changed branch can evaluate to true
independently of the callback pointer.

This can result in calling update_bw_bounding_box() when it is NULL.

Fix this by separating the update condition from the pointer checks and
ensuring the callback, dc->clk_mgr, and bw_params are validated before
use.

Fixes the below:
../dc/hwss/dcn401/dcn401_hwseq.c:367 dcn401_init_hw() error: we previously assumed 'dc->res_pool->funcs->update_bw_bounding_box' could be null (see line 362)

Fixes: ca0fb243c3bb ("drm/amd/display: Underflow Seen on DCN401 eGPU")
Cc: Daniel Sa <Daniel.Sa@amd.com>
Cc: Alvin Lee <alvin.lee2@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 86117c5ab42f21562fedb0a64bffea3ee5fcd477)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c   | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index eb198d52a115..4dfb6c865831 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -147,6 +147,7 @@ void dcn401_init_hw(struct dc *dc)
 	int edp_num;
 	uint32_t backlight = MAX_BACKLIGHT_LEVEL;
 	uint32_t user_level = MAX_BACKLIGHT_LEVEL;
+	bool dchub_ref_freq_changed;
 	int current_dchub_ref_freq = 0;
 
 	if (dc->clk_mgr && dc->clk_mgr->funcs && dc->clk_mgr->funcs->init_clocks) {
@@ -360,14 +361,18 @@ void dcn401_init_hw(struct dc *dc)
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
 		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver > 0;
 		dc->caps.dmub_caps.fams_ver = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch_ver;
+
+		/* sw and fw FAMS versions must match for support */
 		dc->debug.fams2_config.bits.enable &=
-				dc->caps.dmub_caps.fams_ver == dc->debug.fams_version.ver; // sw & fw fams versions must match for support
-		if ((!dc->debug.fams2_config.bits.enable && dc->res_pool->funcs->update_bw_bounding_box)
-			|| res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 != current_dchub_ref_freq) {
+			dc->caps.dmub_caps.fams_ver == dc->debug.fams_version.ver;
+		dchub_ref_freq_changed =
+			res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 != current_dchub_ref_freq;
+		if ((!dc->debug.fams2_config.bits.enable || dchub_ref_freq_changed) &&
+		    dc->res_pool->funcs->update_bw_bounding_box &&
+		    dc->clk_mgr && dc->clk_mgr->bw_params) {
 			/* update bounding box if FAMS2 disabled, or if dchub clk has changed */
-			if (dc->clk_mgr)
-				dc->res_pool->funcs->update_bw_bounding_box(dc,
-									    dc->clk_mgr->bw_params);
+			dc->res_pool->funcs->update_bw_bounding_box(dc,
+								    dc->clk_mgr->bw_params);
 		}
 	}
 }
-- 
cgit v1.2.3


From 39e2a5bf970402a8530a319cf06122e216ba57b8 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Thu, 26 Mar 2026 22:45:23 +0000
Subject: hwmon: (occ) Fix division by zero in occ_show_power_1()

In occ_show_power_1() case 1, the accumulator is divided by
update_tag without checking for zero. If no samples have been
collected yet (e.g. during early boot when the sensor block is
included but hasn't been updated), update_tag is zero, causing
a kernel divide-by-zero crash.

The 2019 fix in commit 211186cae14d ("hwmon: (occ) Fix division by
zero issue") only addressed occ_get_powr_avg() used by
occ_show_power_2() and occ_show_power_a0(). This separate code
path in occ_show_power_1() was missed.

Fix this by reusing the existing occ_get_powr_avg() helper, which
already handles the zero-sample case and uses mul_u64_u32_div()
to multiply before dividing for better precision. Move the helper
above occ_show_power_1() so it is visible at the call site.

Fixes: c10e753d43eb ("hwmon (occ): Add sensor types and versions")
Cc: stable@vger.kernel.org
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260326224510.294619-2-sanman.pradhan@hpe.com
[groeck: Fix alignment problems reported by checkpatch]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/occ/common.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 89928d38831b..ec7dbb94de0b 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -420,6 +420,12 @@ static ssize_t occ_show_freq_2(struct device *dev,
 	return sysfs_emit(buf, "%u\n", val);
 }
 
+static u64 occ_get_powr_avg(u64 accum, u32 samples)
+{
+	return (samples == 0) ? 0 :
+		mul_u64_u32_div(accum, 1000000UL, samples);
+}
+
 static ssize_t occ_show_power_1(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -441,9 +447,8 @@ static ssize_t occ_show_power_1(struct device *dev,
 		val = get_unaligned_be16(&power->sensor_id);
 		break;
 	case 1:
-		val = get_unaligned_be32(&power->accumulator) /
-			get_unaligned_be32(&power->update_tag);
-		val *= 1000000ULL;
+		val = occ_get_powr_avg(get_unaligned_be32(&power->accumulator),
+				       get_unaligned_be32(&power->update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->update_tag) *
@@ -459,12 +464,6 @@ static ssize_t occ_show_power_1(struct device *dev,
 	return sysfs_emit(buf, "%llu\n", val);
 }
 
-static u64 occ_get_powr_avg(u64 accum, u32 samples)
-{
-	return (samples == 0) ? 0 :
-		mul_u64_u32_div(accum, 1000000UL, samples);
-}
-
 static ssize_t occ_show_power_2(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-- 
cgit v1.2.3


From daf470b8882b6f7f53cbfe9ec2b93a1b21528cdc Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 27 Mar 2026 14:29:17 +0530
Subject: drm/amdgpu: Fix wait after reset sequence in S4

For a mode-1 reset done at the end of S4 on PSPv11 dGPUs, only check if
TOS is unloaded.

Fixes: 32f73741d6ee ("drm/amdgpu: Wait for bootloader after PSPv11 reset")
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/4853
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2fb4883b884a437d760bd7bdf7695a7e5a60bba3)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 8 ++++++--
 drivers/gpu/drm/amd/amdgpu/psp_v11_0.c  | 3 ++-
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 95d26f086d54..c91638e65174 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2703,8 +2703,12 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	if (r)
 		return r;
 
-	if (amdgpu_acpi_should_gpu_reset(adev))
-		return amdgpu_asic_reset(adev);
+	if (amdgpu_acpi_should_gpu_reset(adev)) {
+		amdgpu_device_lock_reset_domain(adev->reset_domain);
+		r = amdgpu_asic_reset(adev);
+		amdgpu_device_unlock_reset_domain(adev->reset_domain);
+		return r;
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 9aa988982304..fb7aaf5ae05c 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -170,7 +170,8 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 	int retry_loop;
 
 	/* For a reset done at the end of S3, only wait for TOS to be unloaded */
-	if (adev->in_s3 && !(adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev))
+	if ((adev->in_s4 || adev->in_s3) && !(adev->flags & AMD_IS_APU) &&
+	    amdgpu_in_reset(adev))
 		return psp_v11_wait_for_tos_unload(psp);
 
 	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
-- 
cgit v1.2.3


From 09773978879ecf71a7990fe9a28ce4eb92bce645 Mon Sep 17 00:00:00 2001
From: Sanman Pradhan <psanman@juniper.net>
Date: Thu, 26 Mar 2026 22:45:29 +0000
Subject: hwmon: (occ) Fix missing newline in occ_show_extended()

In occ_show_extended() case 0, when the EXTN_FLAG_SENSOR_ID flag
is set, the sysfs_emit format string "%u" is missing the trailing
newline that the sysfs ABI expects. The else branch correctly uses
"%4phN\n", and all other show functions in this file include the
trailing newline.

Add the missing "\n" for consistency and correct sysfs output.

Fixes: c10e753d43eb ("hwmon (occ): Add sensor types and versions")
Signed-off-by: Sanman Pradhan <psanman@juniper.net>
Link: https://lore.kernel.org/r/20260326224510.294619-3-sanman.pradhan@hpe.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/occ/common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index ec7dbb94de0b..42cc6068bb08 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -724,7 +724,7 @@ static ssize_t occ_show_extended(struct device *dev,
 	switch (sattr->nr) {
 	case 0:
 		if (extn->flags & EXTN_FLAG_SENSOR_ID) {
-			rc = sysfs_emit(buf, "%u",
+			rc = sysfs_emit(buf, "%u\n",
 					get_unaligned_be32(&extn->sensor_id));
 		} else {
 			rc = sysfs_emit(buf, "%4phN\n", extn->name);
-- 
cgit v1.2.3


From 78746a474e92fc7aaed12219bec7c78ae1bd6156 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Mon, 23 Mar 2026 09:58:39 +0530
Subject: drm/amdkfd: Fix queue preemption/eviction failures by aligning
 control stack size to GPU page size

The control stack size is calculated based on the number of CUs and
waves, and is then aligned to PAGE_SIZE. When the resulting control
stack size is aligned to 64 KB, GPU hangs and queue preemption
failures are observed while running RCCL unit tests on systems with
more than two GPUs.

amdgpu 0048:0f:00.0: amdgpu: Queue preemption failed for queue with
doorbell_id: 80030008
amdgpu 0048:0f:00.0: amdgpu: Failed to evict process queues
amdgpu 0048:0f:00.0: amdgpu: GPU reset begin!. Source: 4
amdgpu 0048:0f:00.0: amdgpu: Queue preemption failed for queue with
doorbell_id: 80030008
amdgpu 0048:0f:00.0: amdgpu: Failed to evict process queues
amdgpu 0048:0f:00.0: amdgpu: Failed to restore process queues

This issue is observed on both 4 KB and 64 KB system page-size
configurations.

This patch fixes the issue by aligning the control stack size to
AMDGPU_GPU_PAGE_SIZE instead of PAGE_SIZE, so the control stack size
will not be 64 KB on systems with a 64 KB page size and queue
preemption works correctly.

Additionally, In the current code, wg_data_size is aligned to PAGE_SIZE,
which can waste memory if the system page size is large. In this patch,
wg_data_size is aligned to AMDGPU_GPU_PAGE_SIZE. The cwsr_size, calculated
from wg_data_size and the control stack size, is aligned to PAGE_SIZE.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a3e14436304392fbada359edd0f1d1659850c9b7)
---
 drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index e1a922bb2ab7..28354a4e5dd5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -492,10 +492,11 @@ void kfd_queue_ctx_save_restore_size(struct kfd_topology_device *dev)
 	cu_num = props->simd_count / props->simd_per_cu / NUM_XCC(dev->gpu->xcc_mask);
 	wave_num = get_num_waves(props, gfxv, cu_num);
 
-	wg_data_size = ALIGN(cu_num * WG_CONTEXT_DATA_SIZE_PER_CU(gfxv, props), PAGE_SIZE);
+	wg_data_size = ALIGN(cu_num * WG_CONTEXT_DATA_SIZE_PER_CU(gfxv, props),
+				AMDGPU_GPU_PAGE_SIZE);
 	ctl_stack_size = wave_num * CNTL_STACK_BYTES_PER_WAVE(gfxv) + 8;
 	ctl_stack_size = ALIGN(SIZEOF_HSA_USER_CONTEXT_SAVE_AREA_HEADER + ctl_stack_size,
-			       PAGE_SIZE);
+			       AMDGPU_GPU_PAGE_SIZE);
 
 	if ((gfxv / 10000 * 10000) == 100000) {
 		/* HW design limits control stack size to 0x7000.
@@ -507,7 +508,7 @@ void kfd_queue_ctx_save_restore_size(struct kfd_topology_device *dev)
 
 	props->ctl_stack_size = ctl_stack_size;
 	props->debug_memory_size = ALIGN(wave_num * DEBUGGER_BYTES_PER_WAVE, DEBUGGER_BYTES_ALIGN);
-	props->cwsr_size = ctl_stack_size + wg_data_size;
+	props->cwsr_size = ALIGN(ctl_stack_size + wg_data_size, PAGE_SIZE);
 
 	if (gfxv == 80002)	/* GFX_VERSION_TONGA */
 		props->eop_buffer_size = 0x8000;
-- 
cgit v1.2.3


From 59e1be1278f064d7172b00473b7e0c453cb1ec52 Mon Sep 17 00:00:00 2001
From: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Date: Fri, 13 Mar 2026 14:52:31 +0100
Subject: spi: cadence-qspi: Fix exec_mem_op error handling

cqspi_exec_mem_op() increments the runtime PM usage counter before all
refcount checks are performed. If one of these checks fails, the function
returns without dropping the PM reference.

Move the pm_runtime_resume_and_get() call after the refcount checks so
that runtime PM is only acquired when the operation can proceed and
drop the inflight_ops refcount if the PM resume fails.

Cc: stable@vger.kernel.org
Fixes: 7446284023e8 ("spi: cadence-quadspi: Implement refcount to handle unbind during busy")
Signed-off-by: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Link: https://patch.msgid.link/20260313135236.46642-1-ghidoliemanuele@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-quadspi.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 5fb0cb07c110..2ead419e896e 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1483,14 +1483,6 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	if (refcount_read(&cqspi->inflight_ops) == 0)
 		return -ENODEV;
 
-	if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) {
-		ret = pm_runtime_resume_and_get(dev);
-		if (ret) {
-			dev_err(&mem->spi->dev, "resume failed with %d\n", ret);
-			return ret;
-		}
-	}
-
 	if (!refcount_read(&cqspi->refcount))
 		return -EBUSY;
 
@@ -1502,6 +1494,14 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		return -EBUSY;
 	}
 
+	if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM))) {
+		ret = pm_runtime_resume_and_get(dev);
+		if (ret) {
+			dev_err(&mem->spi->dev, "resume failed with %d\n", ret);
+			goto dec_inflight_refcount;
+		}
+	}
+
 	ret = cqspi_mem_process(mem, op);
 
 	if (!(ddata && (ddata->quirks & CQSPI_DISABLE_RUNTIME_PM)))
@@ -1510,6 +1510,7 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	if (ret)
 		dev_err(&mem->spi->dev, "operation failed with %d\n", ret);
 
+dec_inflight_refcount:
 	if (refcount_read(&cqspi->inflight_ops) > 1)
 		refcount_dec(&cqspi->inflight_ops);
 
-- 
cgit v1.2.3


From fd63f185979b047fb22a0dfc6bd94d0cab6a6a70 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 27 Mar 2026 10:52:57 +0100
Subject: ipv6: prevent possible UaF in addrconf_permanent_addr()

The mentioned helper try to warn the user about an exceptional
condition, but the message is delivered too late, accessing the ipv6
after its possible deletion.

Reorder the statement to avoid the possible UaF; while at it, place the
warning outside the idev->lock as it needs no protection.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://sashiko.dev/#/patchset/8c8bfe2e1a324e501f0e15fef404a77443fd8caf.1774365668.git.pabeni%40redhat.com
Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/ef973c3a8cb4f8f1787ed469f3e5391b9fe95aa0.1774601542.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/addrconf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f4e23b543585..dd0b4d80e0f8 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3625,12 +3625,12 @@ static void addrconf_permanent_addr(struct net *net, struct net_device *dev)
 		if ((ifp->flags & IFA_F_PERMANENT) &&
 		    fixup_permanent_addr(net, idev, ifp) < 0) {
 			write_unlock_bh(&idev->lock);
-			in6_ifa_hold(ifp);
-			ipv6_del_addr(ifp);
-			write_lock_bh(&idev->lock);
 
 			net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n",
 					     idev->dev->name, &ifp->addr);
+			in6_ifa_hold(ifp);
+			ipv6_del_addr(ifp);
+			write_lock_bh(&idev->lock);
 		}
 	}
 
-- 
cgit v1.2.3


From 514aac3599879a7ed48b7dc19e31145beb6958ac Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 27 Mar 2026 10:48:21 +0100
Subject: net: airoha: Add missing cleanup bits in
 airoha_qdma_cleanup_rx_queue()

In order to properly cleanup hw rx QDMA queues and bring the device to
the initial state, reset rx DMA queue head/tail index. Moreover, reset
queued DMA descriptor fields.

Fixes: 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC")
Tested-by: Madhur Agrawal <Madhur.Agrawal@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260327-airoha_qdma_cleanup_rx_queue-fix-v1-1-369d6ab1511a@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 56cf9a926a83..c2a54dbcbb0d 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -794,18 +794,34 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
 
 static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 {
-	struct airoha_eth *eth = q->qdma->eth;
+	struct airoha_qdma *qdma = q->qdma;
+	struct airoha_eth *eth = qdma->eth;
+	int qid = q - &qdma->q_rx[0];
 
 	while (q->queued) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
+		struct airoha_qdma_desc *desc = &q->desc[q->tail];
 		struct page *page = virt_to_head_page(e->buf);
 
 		dma_sync_single_for_cpu(eth->dev, e->dma_addr, e->dma_len,
 					page_pool_get_dma_dir(q->page_pool));
 		page_pool_put_full_page(q->page_pool, page, false);
+		/* Reset DMA descriptor */
+		WRITE_ONCE(desc->ctrl, 0);
+		WRITE_ONCE(desc->addr, 0);
+		WRITE_ONCE(desc->data, 0);
+		WRITE_ONCE(desc->msg0, 0);
+		WRITE_ONCE(desc->msg1, 0);
+		WRITE_ONCE(desc->msg2, 0);
+		WRITE_ONCE(desc->msg3, 0);
+
 		q->tail = (q->tail + 1) % q->ndesc;
 		q->queued--;
 	}
+
+	q->head = q->tail;
+	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
+			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->tail));
 }
 
 static int airoha_qdma_init_rx(struct airoha_qdma *qdma)
-- 
cgit v1.2.3


From ddc748a391dd8642ba6b2e4fe22e7f2ddf84b7f0 Mon Sep 17 00:00:00 2001
From: Guoyu Su <yss2813483011xxl@gmail.com>
Date: Fri, 27 Mar 2026 23:35:07 +0800
Subject: net: use skb_header_pointer() for TCPv4 GSO frag_off check

Syzbot reported a KMSAN uninit-value warning in gso_features_check()
called from netif_skb_features() [1].

gso_features_check() reads iph->frag_off to decide whether to clear
mangleid_features. Accessing the IPv4 header via ip_hdr()/inner_ip_hdr()
can rely on skb header offsets that are not always safe for direct
dereference on packets injected from PF_PACKET paths.

Use skb_header_pointer() for the TCPv4 frag_off check so the header read
is robust whether data is already linear or needs copying.

[1] https://syzkaller.appspot.com/bug?extid=1543a7d954d9c6d00407

Link: https://lore.kernel.org/netdev/willemdebruijn.kernel.1a9f35039caab@gmail.com/
Fixes: cbc53e08a793 ("GSO: Add GSO type for fixed IPv4 ID")
Reported-by: syzbot+1543a7d954d9c6d00407@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1543a7d954d9c6d00407
Tested-by: syzbot+1543a7d954d9c6d00407@syzkaller.appspotmail.com
Signed-off-by: Guoyu Su <yss2813483011xxl@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260327153507.39742-1-yss2813483011xxl@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index fc5557062414..831129f2a69b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3821,10 +3821,15 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	 * segmentation-offloads.rst).
 	 */
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
-		struct iphdr *iph = skb->encapsulation ?
-				    inner_ip_hdr(skb) : ip_hdr(skb);
+		const struct iphdr *iph;
+		struct iphdr _iph;
+		int nhoff = skb->encapsulation ?
+			    skb_inner_network_offset(skb) :
+			    skb_network_offset(skb);
 
-		if (!(iph->frag_off & htons(IP_DF)))
+		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+
+		if (!iph || !(iph->frag_off & htons(IP_DF)))
 			features &= ~dev->mangleid_features;
 	}
 
-- 
cgit v1.2.3


From e6e3eb5ee89ac4c163d46429391c889a1bb5e404 Mon Sep 17 00:00:00 2001
From: Yochai Eisenrich <echelonh@gmail.com>
Date: Sun, 29 Mar 2026 00:14:36 +0300
Subject: net: sched: cls_api: fix tc_chain_fill_node to initialize tcm_info to
 zero to prevent an info-leak

When building netlink messages, tc_chain_fill_node() never initializes
the tcm_info field of struct tcmsg. Since the allocation is not zeroed,
kernel heap memory is leaked to userspace through this 4-byte field.

The fix simply zeroes tcm_info alongside the other fields that are
already initialized.

Fixes: 32a4f5ecd738 ("net: sched: introduce chain object to uapi")
Signed-off-by: Yochai Eisenrich <echelonh@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260328211436.1010152-1-echelonh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/cls_api.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 4829c27446e3..20f7f9ee0b35 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2969,6 +2969,7 @@ static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops,
 	tcm->tcm__pad1 = 0;
 	tcm->tcm__pad2 = 0;
 	tcm->tcm_handle = 0;
+	tcm->tcm_info = 0;
 	if (block->q) {
 		tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex;
 		tcm->tcm_parent = block->q->handle;
-- 
cgit v1.2.3


From cedc1bf327de62ec30af9743bd1f601c2de30553 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sun, 29 Mar 2026 12:32:27 +0200
Subject: net: airoha: Delay offloading until all net_devices are fully
 registered

Netfilter flowtable can theoretically try to offload flower rules as soon
as a net_device is registered while all the other ones are not
registered or initialized, triggering a possible NULL pointer dereferencing
of qdma pointer in airoha_ppe_set_cpu_port routine. Moreover, if
register_netdev() fails for a particular net_device, there is a small
race if Netfilter tries to offload flowtable rules before all the
net_devices are properly unregistered in airoha_probe() error patch,
triggering a NULL pointer dereferencing in airoha_ppe_set_cpu_port
routine. In order to avoid any possible race, delay offloading until
all net_devices are registered in the networking subsystem.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20260329-airoha-regiser-race-fix-v2-1-f4ebb139277b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 2 ++
 drivers/net/ethernet/airoha/airoha_eth.h | 1 +
 drivers/net/ethernet/airoha/airoha_ppe.c | 7 +++++++
 3 files changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index c2a54dbcbb0d..95ba99b89428 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2962,6 +2962,8 @@ static int airoha_register_gdm_devices(struct airoha_eth *eth)
 			return err;
 	}
 
+	set_bit(DEV_STATE_REGISTERED, &eth->state);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 20e602d61e61..a97903569335 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -88,6 +88,7 @@ enum {
 
 enum {
 	DEV_STATE_INITIALIZED,
+	DEV_STATE_REGISTERED,
 };
 
 enum {
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 5724f8f2defd..c2c32b6833df 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -1368,6 +1368,13 @@ int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data)
 	struct airoha_eth *eth = ppe->eth;
 	int err = 0;
 
+	/* Netfilter flowtable can try to offload flower rules while not all
+	 * the net_devices are registered or initialized. Delay offloading
+	 * until all net_devices are registered in the system.
+	 */
+	if (!test_bit(DEV_STATE_REGISTERED, &eth->state))
+		return -EBUSY;
+
 	mutex_lock(&flow_offload_mutex);
 
 	if (!eth->npu)
-- 
cgit v1.2.3


From 4ee937107d52f9e5c350e4b5e629760e328b3d9f Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Sun, 29 Mar 2026 07:43:56 +0800
Subject: bnxt_en: set backing store type from query type

bnxt_hwrm_func_backing_store_qcaps_v2() stores resp->type from the
firmware response in ctxm->type and later uses that value to index
fixed backing-store metadata arrays such as ctx_arr[] and
bnxt_bstore_to_trace[].

ctxm->type is fixed by the current backing-store query type and matches
the array index of ctx->ctx_arr. Set ctxm->type from the current loop
variable instead of depending on resp->type.

Also update the loop to advance type from next_valid_type in the for
statement, which keeps the control flow simpler for non-valid and
unchanged entries.

Fixes: 6a4d0774f02d ("bnxt_en: Add support for new backing store query firmware API")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Tested-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260328234357.43669-1-pengpeng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0751c0e4581a..7ed805713fbb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8671,7 +8671,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
 	struct hwrm_func_backing_store_qcaps_v2_output *resp;
 	struct hwrm_func_backing_store_qcaps_v2_input *req;
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
-	u16 type;
+	u16 type, next_type = 0;
 	int rc;
 
 	rc = hwrm_req_init(bp, req, HWRM_FUNC_BACKING_STORE_QCAPS_V2);
@@ -8687,7 +8687,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
 
 	resp = hwrm_req_hold(bp, req);
 
-	for (type = 0; type < BNXT_CTX_V2_MAX; ) {
+	for (type = 0; type < BNXT_CTX_V2_MAX; type = next_type) {
 		struct bnxt_ctx_mem_type *ctxm = &ctx->ctx_arr[type];
 		u8 init_val, init_off, i;
 		u32 max_entries;
@@ -8700,7 +8700,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
 		if (rc)
 			goto ctx_done;
 		flags = le32_to_cpu(resp->flags);
-		type = le16_to_cpu(resp->next_valid_type);
+		next_type = le16_to_cpu(resp->next_valid_type);
 		if (!(flags & BNXT_CTX_MEM_TYPE_VALID)) {
 			bnxt_free_one_ctx_mem(bp, ctxm, true);
 			continue;
@@ -8715,7 +8715,7 @@ static int bnxt_hwrm_func_backing_store_qcaps_v2(struct bnxt *bp)
 			else
 				continue;
 		}
-		ctxm->type = le16_to_cpu(resp->type);
+		ctxm->type = type;
 		ctxm->entry_size = entry_size;
 		ctxm->flags = flags;
 		ctxm->instance_bmap = le32_to_cpu(resp->instance_bit_map);
-- 
cgit v1.2.3


From 316fb1b3169efb081d2db910cbbfef445afa03b9 Mon Sep 17 00:00:00 2001
From: robbieko <robbieko@synology.com>
Date: Wed, 25 Mar 2026 18:18:15 +0800
Subject: btrfs: fix incorrect return value after changing leaf in
 lookup_extent_data_ref()

After commit 1618aa3c2e01 ("btrfs: simplify return variables in
lookup_extent_data_ref()"), the err and ret variables were merged into
a single ret variable. However, when btrfs_next_leaf() returns 0
(success), ret is overwritten from -ENOENT to 0. If the first key in
the next leaf does not match (different objectid or type), the function
returns 0 instead of -ENOENT, making the caller believe the lookup
succeeded when it did not. This can lead to operations on the wrong
extent tree item, potentially causing extent tree corruption.

Fix this by returning -ENOENT directly when the key does not match,
instead of relying on the ret variable.

Fixes: 1618aa3c2e01 ("btrfs: simplify return variables in lookup_extent_data_ref()")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: robbieko <robbieko@synology.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 85ee5c79759d..098e64106d02 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -495,7 +495,7 @@ again:
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 		if (key.objectid != bytenr ||
 		    key.type != BTRFS_EXTENT_DATA_REF_KEY)
-			return ret;
+			return -ENOENT;
 
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_extent_data_ref);
-- 
cgit v1.2.3


From e08e0754e690e4909cab83ac43fd2c93c6200514 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 25 Mar 2026 15:58:44 +0200
Subject: drm/i915/cdclk: Do the full CDCLK dance for min_voltage_level changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apparently I forgot about the pipe min_voltage_level when I
decoupled the CDCLK calculations from modesets. Even if the
CDCLK frequency doesn't need changing we may still need to
bump the voltage level to accommodate an increase in the
port clock frequency.

Currently, even if there is a full modeset, we won't notice the
need to go through the full CDCLK calculations/programming,
unless the set of enabled/active pipes changes, or the
pipe/dbuf min CDCLK changes.

Duplicate the same logic we use the pipe's min CDCLK frequency
to also deal with its min voltage level.

Note that the 'allow_voltage_level_decrease' stuff isn't
really useful here since the min voltage level can only
change during a full modeset. But I think sticking to the
same approach in the three similar parts (pipe min cdclk,
pipe min voltage level, dbuf min cdclk) is a good idea.

Cc: stable@vger.kernel.org
Tested-by: Mikhail Rudenko <mike.rudenko@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/15826
Fixes: ba91b9eecb47 ("drm/i915/cdclk: Decouple cdclk from state->modeset")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260325135849.12603-2-ville.syrjala@linux.intel.com
Reviewed-by: Michał Grzelak <michal.grzelak@intel.com>
(cherry picked from commit 0f21a14987ebae3c05ad1184ea872e7b7a7b8695)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 54 ++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index f5946e677c93..3d7b4b0795cd 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2971,6 +2971,53 @@ static int intel_cdclk_update_crtc_min_cdclk(struct intel_atomic_state *state,
 	return 0;
 }
 
+static int intel_cdclk_update_crtc_min_voltage_level(struct intel_atomic_state *state,
+						     struct intel_crtc *crtc,
+						     u8 old_min_voltage_level,
+						     u8 new_min_voltage_level,
+						     bool *need_cdclk_calc)
+{
+	struct intel_display *display = to_intel_display(state);
+	struct intel_cdclk_state *cdclk_state;
+	bool allow_voltage_level_decrease = intel_any_crtc_needs_modeset(state);
+	int ret;
+
+	if (new_min_voltage_level == old_min_voltage_level)
+		return 0;
+
+	if (!allow_voltage_level_decrease &&
+	    new_min_voltage_level < old_min_voltage_level)
+		return 0;
+
+	cdclk_state = intel_atomic_get_cdclk_state(state);
+	if (IS_ERR(cdclk_state))
+		return PTR_ERR(cdclk_state);
+
+	old_min_voltage_level = cdclk_state->min_voltage_level[crtc->pipe];
+
+	if (new_min_voltage_level == old_min_voltage_level)
+		return 0;
+
+	if (!allow_voltage_level_decrease &&
+	    new_min_voltage_level < old_min_voltage_level)
+		return 0;
+
+	cdclk_state->min_voltage_level[crtc->pipe] = new_min_voltage_level;
+
+	ret = intel_atomic_lock_global_state(&cdclk_state->base);
+	if (ret)
+		return ret;
+
+	*need_cdclk_calc = true;
+
+	drm_dbg_kms(display->drm,
+		    "[CRTC:%d:%s] min voltage level: %d -> %d\n",
+		    crtc->base.base.id, crtc->base.name,
+		    old_min_voltage_level, new_min_voltage_level);
+
+	return 0;
+}
+
 int intel_cdclk_update_dbuf_bw_min_cdclk(struct intel_atomic_state *state,
 					 int old_min_cdclk, int new_min_cdclk,
 					 bool *need_cdclk_calc)
@@ -3386,6 +3433,13 @@ static int intel_crtcs_calc_min_cdclk(struct intel_atomic_state *state,
 							need_cdclk_calc);
 		if (ret)
 			return ret;
+
+		ret = intel_cdclk_update_crtc_min_voltage_level(state, crtc,
+								old_crtc_state->min_voltage_level,
+								new_crtc_state->min_voltage_level,
+								need_cdclk_calc);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 9c9a57e4e337f94e23ddf69263fd0685c91155fb Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 25 Mar 2026 15:58:45 +0200
Subject: drm/i915/dp: Use crtc_state->enhanced_framing properly on ivb/hsw CPU
 eDP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Looks like I missed the drm_dp_enhanced_frame_cap() in the ivb/hsw CPU
eDP code when I introduced crtc_state->enhanced_framing. Fix it up so
that the state we program to the hardware is guaranteed to match what
we computed earlier.

Cc: stable@vger.kernel.org
Fixes: 3072a24c778a ("drm/i915: Introduce crtc_state->enhanced_framing")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patch.msgid.link/20260325135849.12603-3-ville.syrjala@linux.intel.com
Reviewed-by: Michał Grzelak <michal.grzelak@intel.com>
(cherry picked from commit 799fe8dc2af52f35c78c4ac97f8e34994dfd8760)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/g4x_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index 4cb753177fd8..c7fa014e0d50 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -137,7 +137,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 			intel_dp->DP |= DP_SYNC_VS_HIGH;
 		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 
-		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
+		if (pipe_config->enhanced_framing)
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
 		intel_dp->DP |= DP_PIPE_SEL_IVB(crtc->pipe);
-- 
cgit v1.2.3


From 720460722310c7ab35421aa81a3153ff96b6c82b Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Tue, 31 Mar 2026 09:35:36 +0800
Subject: ALSA: hda/realtek: add quirk for HP Laptop 15-fc0xxx

For the HP Laptop 15-fc0xxx with ALC236, the built-in mic 0x12 was
not set up, making it unusable; after adding it, it now works properly.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=221233
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260331013536.13778-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 766d7bb2d4f5..57ba642252b0 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -4123,6 +4123,7 @@ enum {
 	ALC245_FIXUP_BASS_HP_DAC,
 	ALC245_FIXUP_ACER_MICMUTE_LED,
 	ALC245_FIXUP_CS35L41_I2C_2_MUTE_LED,
+	ALC236_FIXUP_HP_DMIC,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -6658,6 +6659,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.v.func = alc245_fixup_hp_mute_led_coefbit,
 		.chained = true,
 		.chain_id = ALC287_FIXUP_CS35L41_I2C_2,
+	},
+	[ALC236_FIXUP_HP_DMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x12, 0x90a60160 }, /* use as internal mic */
+			{ }
+		},
 	}
 };
 
@@ -7153,6 +7161,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8da1, "HP 16 Clipper OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da7, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8da8, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8dc9, "HP Laptop 15-fc0xxx", ALC236_FIXUP_HP_DMIC),
 	SND_PCI_QUIRK(0x103c, 0x8dd4, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
 	SND_PCI_QUIRK(0x103c, 0x8dd7, "HP Laptop 15-fd0xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8de8, "HP Gemtree", ALC245_FIXUP_TAS2781_SPI_2),
-- 
cgit v1.2.3


From e6c888202297eca21860b669edb74fc600e679d9 Mon Sep 17 00:00:00 2001
From: songxiebing <songxiebing@kylinos.cn>
Date: Tue, 31 Mar 2026 11:36:50 +0800
Subject: ALSA: hda/realtek: Add quirk for Lenovo Yoga Slim 7 14AKP10

The Pin Complex 0x17 (bass/woofer speakers) is incorrectly reported as
unconnected in the BIOS (pin default 0x411111f0 = N/A). This causes the
kernel to configure speaker_outs=0, meaning only the tweeters (pin 0x14)
are used. The result is very low, tinny audio with no bass.

The existing quirk ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN (already present
in patch_realtek.c for SSID 0x17aa3801) fixes the issue completely.

Reported-by: Garcicasti <andresgarciacastilla@gmail.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=221298
Signed-off-by: songxiebing <songxiebing@kylinos.cn>
Link: https://patch.msgid.link/20260331033650.285601-1-songxiebing@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 57ba642252b0..fa5f08cd2c65 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7676,6 +7676,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
+	SND_PCI_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TXNW2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3929, "Thinkbook 13x Gen 5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
-- 
cgit v1.2.3


From b981e9e94c687b7b19ae8820963f005b842cb2f2 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 29 Mar 2026 19:27:48 -0700
Subject: x86/platform/geode: Fix on-stack property data use-after-return bug

The PROPERTY_ENTRY_GPIO macro (and by extension PROPERTY_ENTRY_REF)
creates a temporary software_node_ref_args structure on the stack
when used in a runtime assignment. This results in the property
pointing to data that is invalid once the function returns.

Fix this by ensuring the GPIO reference data is not stored on stack and
using PROPERTY_ENTRY_REF_ARRAY_LEN() to point directly to the persistent
reference data.

Fixes: 298c9babadb8 ("x86/platform/geode: switch GPIO buttons and LEDs to software properties")
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Daniel Scally <djrscally@gmail.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Hans de Goede <hansg@kernel.org>
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: Sakari Ailus <sakari.ailus@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260329-property-gpio-fix-v2-1-3cca5ba136d8@gmail.com
---
 arch/x86/platform/geode/geode-common.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/x86/platform/geode/geode-common.c b/arch/x86/platform/geode/geode-common.c
index 05189c5f7d2a..1843ae385e2d 100644
--- a/arch/x86/platform/geode/geode-common.c
+++ b/arch/x86/platform/geode/geode-common.c
@@ -28,8 +28,10 @@ static const struct software_node geode_gpio_keys_node = {
 	.properties = geode_gpio_keys_props,
 };
 
-static struct property_entry geode_restart_key_props[] = {
-	{ /* Placeholder for GPIO property */ },
+static struct software_node_ref_args geode_restart_gpio_ref;
+
+static const struct property_entry geode_restart_key_props[] = {
+	PROPERTY_ENTRY_REF_ARRAY_LEN("gpios", &geode_restart_gpio_ref, 1),
 	PROPERTY_ENTRY_U32("linux,code", KEY_RESTART),
 	PROPERTY_ENTRY_STRING("label", "Reset button"),
 	PROPERTY_ENTRY_U32("debounce-interval", 100),
@@ -64,8 +66,7 @@ int __init geode_create_restart_key(unsigned int pin)
 	struct platform_device *pd;
 	int err;
 
-	geode_restart_key_props[0] = PROPERTY_ENTRY_GPIO("gpios",
-							 &geode_gpiochip_node,
+	geode_restart_gpio_ref = SOFTWARE_NODE_REFERENCE(&geode_gpiochip_node,
 							 pin, GPIO_ACTIVE_LOW);
 
 	err = software_node_register_node_group(geode_gpio_keys_swnodes);
@@ -99,6 +100,7 @@ int __init geode_create_leds(const char *label, const struct geode_led *leds,
 	const struct software_node *group[MAX_LEDS + 2] = { 0 };
 	struct software_node *swnodes;
 	struct property_entry *props;
+	struct software_node_ref_args *gpio_refs;
 	struct platform_device_info led_info = {
 		.name	= "leds-gpio",
 		.id	= PLATFORM_DEVID_NONE,
@@ -127,6 +129,12 @@ int __init geode_create_leds(const char *label, const struct geode_led *leds,
 		goto err_free_swnodes;
 	}
 
+	gpio_refs = kzalloc_objs(*gpio_refs, n_leds);
+	if (!gpio_refs) {
+		err = -ENOMEM;
+		goto err_free_props;
+	}
+
 	group[0] = &geode_gpio_leds_node;
 	for (i = 0; i < n_leds; i++) {
 		node_name = kasprintf(GFP_KERNEL, "%s:%d", label, i);
@@ -135,9 +143,11 @@ int __init geode_create_leds(const char *label, const struct geode_led *leds,
 			goto err_free_names;
 		}
 
+		gpio_refs[i] = SOFTWARE_NODE_REFERENCE(&geode_gpiochip_node,
+						       leds[i].pin,
+						       GPIO_ACTIVE_LOW);
 		props[i * 3 + 0] =
-			PROPERTY_ENTRY_GPIO("gpios", &geode_gpiochip_node,
-					    leds[i].pin, GPIO_ACTIVE_LOW);
+			PROPERTY_ENTRY_REF_ARRAY_LEN("gpios", &gpio_refs[i], 1);
 		props[i * 3 + 1] =
 			PROPERTY_ENTRY_STRING("linux,default-trigger",
 					      leds[i].default_on ?
@@ -171,6 +181,8 @@ err_unregister_group:
 err_free_names:
 	while (--i >= 0)
 		kfree(swnodes[i].name);
+	kfree(gpio_refs);
+err_free_props:
 	kfree(props);
 err_free_swnodes:
 	kfree(swnodes);
-- 
cgit v1.2.3


From af416cd9b3fb9d17ac7f4cfa12d1ea83dfd0e4be Mon Sep 17 00:00:00 2001
From: Jessica Liu <liu.xuemei1@zte.com.cn>
Date: Tue, 31 Mar 2026 09:30:29 +0800
Subject: irqchip/riscv-aplic: Restrict genpd notifier to device tree only
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ACPI systems, the aplic's pm_domain is set to acpi_general_pm_domain,
which provides its own power management callbacks (e.g., runtime_suspend
via acpi_subsys_runtime_suspend).

aplic_pm_add() unconditionally calls dev_pm_genpd_add_notifier() when
dev->pm_domain is non‑NULL, leading to a comparison between runtime_suspend
and genpd_runtime_suspend. This results in the following errors when ACPI
is enabled:

  riscv-aplic RSCV0002:00: failed to create APLIC context
  riscv-aplic RSCV0002:00: error -ENODEV: failed to setup APLIC in MSI mode

Fix this by checking for dev->of_node before adding or removing the genpd
notifier, ensuring it is only used for device tree based systems.

Fixes: 95a8ddde3660 ("irqchip/riscv-aplic: Preserve APLIC states across suspend/resume")
Signed-off-by: Jessica Liu <liu.xuemei1@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Link: https://patch.msgid.link/20260331093029749vRpdH-0qoEqjS0Wnn9M4x@zte.com.cn
---
 drivers/irqchip/irq-riscv-aplic-main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
index 9f53979b6962..d9afb6ae98cf 100644
--- a/drivers/irqchip/irq-riscv-aplic-main.c
+++ b/drivers/irqchip/irq-riscv-aplic-main.c
@@ -150,7 +150,7 @@ static void aplic_pm_remove(void *data)
 	struct device *dev = priv->dev;
 
 	list_del(&priv->head);
-	if (dev->pm_domain)
+	if (dev->pm_domain && dev->of_node)
 		dev_pm_genpd_remove_notifier(dev);
 }
 
@@ -165,7 +165,7 @@ static int aplic_pm_add(struct device *dev, struct aplic_priv *priv)
 
 	priv->saved_hw_regs.srcs = srcs;
 	list_add(&priv->head, &aplics);
-	if (dev->pm_domain) {
+	if (dev->pm_domain && dev->of_node) {
 		priv->genpd_nb.notifier_call = aplic_pm_notifier;
 		ret = dev_pm_genpd_add_notifier(dev, &priv->genpd_nb);
 		if (ret)
-- 
cgit v1.2.3


From a664bf3d603dc3bdcf9ae47cc21e0daec706d7a5 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 26 Mar 2026 15:30:20 +0900
Subject: crypto: algif_aead - Revert to operating out-of-place

This mostly reverts commit 72548b093ee3 except for the copying of
the associated data.

There is no benefit in operating in-place in algif_aead since the
source and destination come from different mappings.  Get rid of
all the complexity added for in-place operation and just copy the
AD directly.

Fixes: 72548b093ee3 ("crypto: algif_aead - copy AAD from src to dst")
Reported-by: Taeyang Lee <0wn@theori.io>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c         |  49 +++++-------------------
 crypto/algif_aead.c     | 100 +++++++++---------------------------------------
 crypto/algif_skcipher.c |   6 +--
 include/crypto/if_alg.h |   5 +--
 4 files changed, 34 insertions(+), 126 deletions(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index c2fd9cd86c5e..8e0199394984 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -637,15 +637,13 @@ static int af_alg_alloc_tsgl(struct sock *sk)
 /**
  * af_alg_count_tsgl - Count number of TX SG entries
  *
- * The counting starts from the beginning of the SGL to @bytes. If
- * an @offset is provided, the counting of the SG entries starts at the @offset.
+ * The counting starts from the beginning of the SGL to @bytes.
  *
  * @sk: socket of connection to user space
  * @bytes: Count the number of SG entries holding given number of bytes.
- * @offset: Start the counting of SG entries from the given offset.
  * Return: Number of TX SG entries found given the constraints
  */
-unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset)
+unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes)
 {
 	const struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_ctx *ctx = ask->private;
@@ -660,25 +658,11 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset)
 		const struct scatterlist *sg = sgl->sg;
 
 		for (i = 0; i < sgl->cur; i++) {
-			size_t bytes_count;
-
-			/* Skip offset */
-			if (offset >= sg[i].length) {
-				offset -= sg[i].length;
-				bytes -= sg[i].length;
-				continue;
-			}
-
-			bytes_count = sg[i].length - offset;
-
-			offset = 0;
 			sgl_count++;
-
-			/* If we have seen requested number of bytes, stop */
-			if (bytes_count >= bytes)
+			if (sg[i].length >= bytes)
 				return sgl_count;
 
-			bytes -= bytes_count;
+			bytes -= sg[i].length;
 		}
 	}
 
@@ -690,19 +674,14 @@ EXPORT_SYMBOL_GPL(af_alg_count_tsgl);
  * af_alg_pull_tsgl - Release the specified buffers from TX SGL
  *
  * If @dst is non-null, reassign the pages to @dst. The caller must release
- * the pages. If @dst_offset is given only reassign the pages to @dst starting
- * at the @dst_offset (byte). The caller must ensure that @dst is large
- * enough (e.g. by using af_alg_count_tsgl with the same offset).
+ * the pages.
  *
  * @sk: socket of connection to user space
  * @used: Number of bytes to pull from TX SGL
  * @dst: If non-NULL, buffer is reassigned to dst SGL instead of releasing. The
  *	 caller must release the buffers in dst.
- * @dst_offset: Reassign the TX SGL from given offset. All buffers before
- *	        reaching the offset is released.
  */
-void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
-		      size_t dst_offset)
+void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	struct af_alg_ctx *ctx = ask->private;
@@ -727,18 +706,10 @@ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
 			 * SG entries in dst.
 			 */
 			if (dst) {
-				if (dst_offset >= plen) {
-					/* discard page before offset */
-					dst_offset -= plen;
-				} else {
-					/* reassign page to dst after offset */
-					get_page(page);
-					sg_set_page(dst + j, page,
-						    plen - dst_offset,
-						    sg[i].offset + dst_offset);
-					dst_offset = 0;
-					j++;
-				}
+				/* reassign page to dst after offset */
+				get_page(page);
+				sg_set_page(dst + j, page, plen, sg[i].offset);
+				j++;
 			}
 
 			sg[i].length -= plen;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 79b016a899a1..dda15bb05e89 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -26,7 +26,6 @@
 #include <crypto/internal/aead.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/if_alg.h>
-#include <crypto/skcipher.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
@@ -72,9 +71,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct alg_sock *pask = alg_sk(psk);
 	struct af_alg_ctx *ctx = ask->private;
 	struct crypto_aead *tfm = pask->private;
-	unsigned int i, as = crypto_aead_authsize(tfm);
+	unsigned int as = crypto_aead_authsize(tfm);
 	struct af_alg_async_req *areq;
-	struct af_alg_tsgl *tsgl, *tmp;
 	struct scatterlist *rsgl_src, *tsgl_src = NULL;
 	int err = 0;
 	size_t used = 0;		/* [in]  TX bufs to be en/decrypted */
@@ -154,23 +152,24 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 		outlen -= less;
 	}
 
+	/*
+	 * Create a per request TX SGL for this request which tracks the
+	 * SG entries from the global TX SGL.
+	 */
 	processed = used + ctx->aead_assoclen;
-	list_for_each_entry_safe(tsgl, tmp, &ctx->tsgl_list, list) {
-		for (i = 0; i < tsgl->cur; i++) {
-			struct scatterlist *process_sg = tsgl->sg + i;
-
-			if (!(process_sg->length) || !sg_page(process_sg))
-				continue;
-			tsgl_src = process_sg;
-			break;
-		}
-		if (tsgl_src)
-			break;
-	}
-	if (processed && !tsgl_src) {
-		err = -EFAULT;
+	areq->tsgl_entries = af_alg_count_tsgl(sk, processed);
+	if (!areq->tsgl_entries)
+		areq->tsgl_entries = 1;
+	areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl),
+					         areq->tsgl_entries),
+				  GFP_KERNEL);
+	if (!areq->tsgl) {
+		err = -ENOMEM;
 		goto free;
 	}
+	sg_init_table(areq->tsgl, areq->tsgl_entries);
+	af_alg_pull_tsgl(sk, processed, areq->tsgl);
+	tsgl_src = areq->tsgl;
 
 	/*
 	 * Copy of AAD from source to destination
@@ -179,76 +178,15 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * when user space uses an in-place cipher operation, the kernel
 	 * will copy the data as it does not see whether such in-place operation
 	 * is initiated.
-	 *
-	 * To ensure efficiency, the following implementation ensure that the
-	 * ciphers are invoked to perform a crypto operation in-place. This
-	 * is achieved by memory management specified as follows.
 	 */
 
 	/* Use the RX SGL as source (and destination) for crypto op. */
 	rsgl_src = areq->first_rsgl.sgl.sgt.sgl;
 
-	if (ctx->enc) {
-		/*
-		 * Encryption operation - The in-place cipher operation is
-		 * achieved by the following operation:
-		 *
-		 * TX SGL: AAD || PT
-		 *	    |	   |
-		 *	    | copy |
-		 *	    v	   v
-		 * RX SGL: AAD || PT || Tag
-		 */
-		memcpy_sglist(areq->first_rsgl.sgl.sgt.sgl, tsgl_src,
-			      processed);
-		af_alg_pull_tsgl(sk, processed, NULL, 0);
-	} else {
-		/*
-		 * Decryption operation - To achieve an in-place cipher
-		 * operation, the following  SGL structure is used:
-		 *
-		 * TX SGL: AAD || CT || Tag
-		 *	    |	   |	 ^
-		 *	    | copy |	 | Create SGL link.
-		 *	    v	   v	 |
-		 * RX SGL: AAD || CT ----+
-		 */
-
-		/* Copy AAD || CT to RX SGL buffer for in-place operation. */
-		memcpy_sglist(areq->first_rsgl.sgl.sgt.sgl, tsgl_src, outlen);
-
-		/* Create TX SGL for tag and chain it to RX SGL. */
-		areq->tsgl_entries = af_alg_count_tsgl(sk, processed,
-						       processed - as);
-		if (!areq->tsgl_entries)
-			areq->tsgl_entries = 1;
-		areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl),
-							 areq->tsgl_entries),
-					  GFP_KERNEL);
-		if (!areq->tsgl) {
-			err = -ENOMEM;
-			goto free;
-		}
-		sg_init_table(areq->tsgl, areq->tsgl_entries);
-
-		/* Release TX SGL, except for tag data and reassign tag data. */
-		af_alg_pull_tsgl(sk, processed, areq->tsgl, processed - as);
-
-		/* chain the areq TX SGL holding the tag with RX SGL */
-		if (usedpages) {
-			/* RX SGL present */
-			struct af_alg_sgl *sgl_prev = &areq->last_rsgl->sgl;
-			struct scatterlist *sg = sgl_prev->sgt.sgl;
-
-			sg_unmark_end(sg + sgl_prev->sgt.nents - 1);
-			sg_chain(sg, sgl_prev->sgt.nents + 1, areq->tsgl);
-		} else
-			/* no RX SGL present (e.g. authentication only) */
-			rsgl_src = areq->tsgl;
-	}
+	memcpy_sglist(rsgl_src, tsgl_src, ctx->aead_assoclen);
 
 	/* Initialize the crypto operation */
-	aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src,
+	aead_request_set_crypt(&areq->cra_u.aead_req, tsgl_src,
 			       areq->first_rsgl.sgl.sgt.sgl, used, ctx->iv);
 	aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen);
 	aead_request_set_tfm(&areq->cra_u.aead_req, tfm);
@@ -450,7 +388,7 @@ static void aead_sock_destruct(struct sock *sk)
 	struct crypto_aead *tfm = pask->private;
 	unsigned int ivlen = crypto_aead_ivsize(tfm);
 
-	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
+	af_alg_pull_tsgl(sk, ctx->used, NULL);
 	sock_kzfree_s(sk, ctx->iv, ivlen);
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 125d395c5e00..82735e51be10 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -138,7 +138,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * Create a per request TX SGL for this request which tracks the
 	 * SG entries from the global TX SGL.
 	 */
-	areq->tsgl_entries = af_alg_count_tsgl(sk, len, 0);
+	areq->tsgl_entries = af_alg_count_tsgl(sk, len);
 	if (!areq->tsgl_entries)
 		areq->tsgl_entries = 1;
 	areq->tsgl = sock_kmalloc(sk, array_size(sizeof(*areq->tsgl),
@@ -149,7 +149,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		goto free;
 	}
 	sg_init_table(areq->tsgl, areq->tsgl_entries);
-	af_alg_pull_tsgl(sk, len, areq->tsgl, 0);
+	af_alg_pull_tsgl(sk, len, areq->tsgl);
 
 	/* Initialize the crypto operation */
 	skcipher_request_set_tfm(&areq->cra_u.skcipher_req, tfm);
@@ -363,7 +363,7 @@ static void skcipher_sock_destruct(struct sock *sk)
 	struct alg_sock *pask = alg_sk(psk);
 	struct crypto_skcipher *tfm = pask->private;
 
-	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
+	af_alg_pull_tsgl(sk, ctx->used, NULL);
 	sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm));
 	if (ctx->state)
 		sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm));
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 107b797c33ec..0cc8fa749f68 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -230,9 +230,8 @@ static inline bool af_alg_readable(struct sock *sk)
 	return PAGE_SIZE <= af_alg_rcvbuf(sk);
 }
 
-unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset);
-void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
-		      size_t dst_offset);
+unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes);
+void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst);
 void af_alg_wmem_wakeup(struct sock *sk);
 int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min);
 int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
-- 
cgit v1.2.3


From e02494114ebf7c8b42777c6cd6982f113bfdbec7 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 27 Mar 2026 15:04:17 +0900
Subject: crypto: authencesn - Do not place hiseq at end of dst for
 out-of-place decryption

When decrypting data that is not in-place (src != dst), there is
no need to save the high-order sequence bits in dst as it could
simply be re-copied from the source.

However, the data to be hashed need to be rearranged accordingly.

Reported-by: Taeyang Lee <0wn@theori.io>
Fixes: 104880a6b470 ("crypto: authencesn - Convert to new AEAD interface")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Thanks,

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/authencesn.c | 48 +++++++++++++++++++++++++++++-------------------
 1 file changed, 29 insertions(+), 19 deletions(-)

diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 542a978663b9..c0a01d738d9b 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -207,6 +207,7 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	u8 *ohash = areq_ctx->tail;
 	unsigned int cryptlen = req->cryptlen - authsize;
 	unsigned int assoclen = req->assoclen;
+	struct scatterlist *src = req->src;
 	struct scatterlist *dst = req->dst;
 	u8 *ihash = ohash + crypto_ahash_digestsize(auth);
 	u32 tmp[2];
@@ -214,23 +215,27 @@ static int crypto_authenc_esn_decrypt_tail(struct aead_request *req,
 	if (!authsize)
 		goto decrypt;
 
-	/* Move high-order bits of sequence number back. */
-	scatterwalk_map_and_copy(tmp, dst, 4, 4, 0);
-	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0);
-	scatterwalk_map_and_copy(tmp, dst, 0, 8, 1);
+	if (src == dst) {
+		/* Move high-order bits of sequence number back. */
+		scatterwalk_map_and_copy(tmp, dst, 4, 4, 0);
+		scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 0);
+		scatterwalk_map_and_copy(tmp, dst, 0, 8, 1);
+	} else
+		memcpy_sglist(dst, src, assoclen);
 
 	if (crypto_memneq(ihash, ohash, authsize))
 		return -EBADMSG;
 
 decrypt:
 
-	sg_init_table(areq_ctx->dst, 2);
+	if (src != dst)
+		src = scatterwalk_ffwd(areq_ctx->src, src, assoclen);
 	dst = scatterwalk_ffwd(areq_ctx->dst, dst, assoclen);
 
 	skcipher_request_set_tfm(skreq, ctx->enc);
 	skcipher_request_set_callback(skreq, flags,
 				      req->base.complete, req->base.data);
-	skcipher_request_set_crypt(skreq, dst, dst, cryptlen, req->iv);
+	skcipher_request_set_crypt(skreq, src, dst, cryptlen, req->iv);
 
 	return crypto_skcipher_decrypt(skreq);
 }
@@ -255,6 +260,7 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req)
 	unsigned int assoclen = req->assoclen;
 	unsigned int cryptlen = req->cryptlen;
 	u8 *ihash = ohash + crypto_ahash_digestsize(auth);
+	struct scatterlist *src = req->src;
 	struct scatterlist *dst = req->dst;
 	u32 tmp[2];
 	int err;
@@ -262,24 +268,28 @@ static int crypto_authenc_esn_decrypt(struct aead_request *req)
 	if (assoclen < 8)
 		return -EINVAL;
 
-	cryptlen -= authsize;
-
-	if (req->src != dst)
-		memcpy_sglist(dst, req->src, assoclen + cryptlen);
+	if (!authsize)
+		goto tail;
 
+	cryptlen -= authsize;
 	scatterwalk_map_and_copy(ihash, req->src, assoclen + cryptlen,
 				 authsize, 0);
 
-	if (!authsize)
-		goto tail;
-
 	/* Move high-order bits of sequence number to the end. */
-	scatterwalk_map_and_copy(tmp, dst, 0, 8, 0);
-	scatterwalk_map_and_copy(tmp, dst, 4, 4, 1);
-	scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1);
-
-	sg_init_table(areq_ctx->dst, 2);
-	dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4);
+	scatterwalk_map_and_copy(tmp, src, 0, 8, 0);
+	if (src == dst) {
+		scatterwalk_map_and_copy(tmp, dst, 4, 4, 1);
+		scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen, 4, 1);
+		dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4);
+	} else {
+		scatterwalk_map_and_copy(tmp, dst, 0, 4, 1);
+		scatterwalk_map_and_copy(tmp + 1, dst, assoclen + cryptlen - 4, 4, 1);
+
+		src = scatterwalk_ffwd(areq_ctx->src, src, 8);
+		dst = scatterwalk_ffwd(areq_ctx->dst, dst, 4);
+		memcpy_sglist(dst, src, assoclen + cryptlen - 8);
+		dst = req->dst;
+	}
 
 	ahash_request_set_tfm(ahreq, auth);
 	ahash_request_set_crypt(ahreq, dst, ohash, assoclen + cryptlen);
-- 
cgit v1.2.3


From 75dc1980cf48826287e43dc7a49e310c6691f97e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 31 Mar 2026 10:12:17 +0200
Subject: ALSA: ctxfi: Don't enumerate SPDIF1 at DAIO initialization

The recent refactoring of xfi driver changed the assignment of
atc->daios[] at atc_get_resources(); now it loops over all enum
DAIOTYP entries while it looped formerly only a part of them.
The problem is that the last entry, SPDIF1, is a special type that
is used only for hw20k1 CTSB073X model (as a replacement of SPDIFIO),
and there is no corresponding definition for hw20k2.  Due to the lack
of the info, it caused a kernel crash on hw20k2, which was already
worked around by the commit b045ab3dff97 ("ALSA: ctxfi: Fix missing
SPDIFI1 index handling").

This patch addresses the root cause of the regression above properly,
simply by skipping the incorrect SPDIF1 type in the parser loop.

For making the change clearer, the code is slightly arranged, too.

Fixes: a2dbaeb5c61e ("ALSA: ctxfi: Refactor resource alloc for sparse mappings")
Cc: <stable@vger.kernel.org>
Link: https://bugzilla.suse.com/show_bug.cgi?id=1259925
Link: https://patch.msgid.link/20260331081227.216134-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/ctatc.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/sound/pci/ctxfi/ctatc.c b/sound/pci/ctxfi/ctatc.c
index f122e396bc55..da2667cb2489 100644
--- a/sound/pci/ctxfi/ctatc.c
+++ b/sound/pci/ctxfi/ctatc.c
@@ -1427,10 +1427,14 @@ static int atc_get_resources(struct ct_atc *atc)
 	daio_mgr = (struct daio_mgr *)atc->rsc_mgrs[DAIO];
 	da_desc.msr = atc->msr;
 	for (i = 0; i < NUM_DAIOTYP; i++) {
-		if (((i == MIC) && !cap.dedicated_mic) || ((i == RCA) && !cap.dedicated_rca))
+		if (((i == MIC) && !cap.dedicated_mic) ||
+		    ((i == RCA) && !cap.dedicated_rca) ||
+		    i == SPDIFI1)
 			continue;
-		da_desc.type = (atc->model != CTSB073X) ? i :
-			     ((i == SPDIFIO) ? SPDIFI1 : i);
+		if (atc->model == CTSB073X && i == SPDIFIO)
+			da_desc.type = SPDIFI1;
+		else
+			da_desc.type = i;
 		da_desc.output = (i < LINEIM) || (i == RCA);
 		err = daio_mgr->get_daio(daio_mgr, &da_desc,
 					(struct daio **)&atc->daios[i]);
-- 
cgit v1.2.3


From 2884bf72fb8f03409e423397319205de48adca16 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Thu, 26 Mar 2026 00:55:53 -0700
Subject: net: bonding: fix use-after-free in bond_xmit_broadcast()

bond_xmit_broadcast() reuses the original skb for the last slave
(determined by bond_is_last_slave()) and clones it for others.
Concurrent slave enslave/release can mutate the slave list during
RCU-protected iteration, changing which slave is "last" mid-loop.
This causes the original skb to be double-consumed (double-freed).

Replace the racy bond_is_last_slave() check with a simple index
comparison (i + 1 == slaves_count) against the pre-snapshot slave
count taken via READ_ONCE() before the loop.  This preserves the
zero-copy optimization for the last slave while making the "last"
determination stable against concurrent list mutations.

The UAF can trigger the following crash:

==================================================================
BUG: KASAN: slab-use-after-free in skb_clone
Read of size 8 at addr ffff888100ef8d40 by task exploit/147

CPU: 1 UID: 0 PID: 147 Comm: exploit Not tainted 7.0.0-rc3+ #4 PREEMPTLAZY
Call Trace:
 <TASK>
 dump_stack_lvl (lib/dump_stack.c:123)
 print_report (mm/kasan/report.c:379 mm/kasan/report.c:482)
 kasan_report (mm/kasan/report.c:597)
 skb_clone (include/linux/skbuff.h:1724 include/linux/skbuff.h:1792 include/linux/skbuff.h:3396 net/core/skbuff.c:2108)
 bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5334)
 bond_start_xmit (drivers/net/bonding/bond_main.c:5567 drivers/net/bonding/bond_main.c:5593)
 dev_hard_start_xmit (include/linux/netdevice.h:5325 include/linux/netdevice.h:5334 net/core/dev.c:3871 net/core/dev.c:3887)
 __dev_queue_xmit (include/linux/netdevice.h:3601 net/core/dev.c:4838)
 ip6_finish_output2 (include/net/neighbour.h:540 include/net/neighbour.h:554 net/ipv6/ip6_output.c:136)
 ip6_finish_output (net/ipv6/ip6_output.c:208 net/ipv6/ip6_output.c:219)
 ip6_output (net/ipv6/ip6_output.c:250)
 ip6_send_skb (net/ipv6/ip6_output.c:1985)
 udp_v6_send_skb (net/ipv6/udp.c:1442)
 udpv6_sendmsg (net/ipv6/udp.c:1733)
 __sys_sendto (net/socket.c:730 net/socket.c:742 net/socket.c:2206)
 __x64_sys_sendto (net/socket.c:2209)
 do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
 </TASK>

Allocated by task 147:

Freed by task 147:

The buggy address belongs to the object at ffff888100ef8c80
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 192 bytes inside of
 freed 224-byte region [ffff888100ef8c80, ffff888100ef8d60)

Memory state around the buggy address:
 ffff888100ef8c00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
 ffff888100ef8c80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100ef8d00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
                                                    ^
 ffff888100ef8d80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
 ffff888100ef8e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: 4e5bd03ae346 ("net: bonding: fix bond_xmit_broadcast return value error bug")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Link: https://patch.msgid.link/20260326075553.3960562-1-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 33f414d03ab9..a5484d11553d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5326,7 +5326,7 @@ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
 		if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
 			continue;
 
-		if (bond_is_last_slave(bond, slave)) {
+		if (i + 1 == slaves_count) {
 			skb2 = skb;
 			skb_used = true;
 		} else {
-- 
cgit v1.2.3


From 30fe3f5f6494f827d812ff179f295a8e532709d6 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Thu, 26 Mar 2026 22:20:33 +0800
Subject: NFC: pn533: bound the UART receive buffer

pn532_receive_buf() appends every incoming byte to dev->recv_skb and
only resets the buffer after pn532_uart_rx_is_frame() recognizes a
complete frame. A continuous stream of bytes without a valid PN532 frame
header therefore keeps growing the skb until skb_put_u8() hits the tail
limit.

Drop the accumulated partial frame once the fixed receive buffer is full
so malformed UART traffic cannot grow the skb past
PN532_UART_SKB_BUFF_LEN.

Fixes: c656aa4c27b1 ("nfc: pn533: add UART phy driver")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Link: https://patch.msgid.link/20260326142033.82297-1-pengpeng@iscas.ac.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/nfc/pn533/uart.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index 6d2f520a5bc8..1b82b7b2a5fa 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -211,6 +211,9 @@ static size_t pn532_receive_buf(struct serdev_device *serdev,
 
 	timer_delete(&dev->cmd_timeout);
 	for (i = 0; i < count; i++) {
+		if (unlikely(!skb_tailroom(dev->recv_skb)))
+			skb_trim(dev->recv_skb, 0);
+
 		skb_put_u8(dev->recv_skb, *data++);
 		if (!pn532_uart_rx_is_frame(dev->recv_skb))
 			continue;
-- 
cgit v1.2.3


From 1635c2acdde86c4f555b627aec873c8677c421ed Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@ownmail.net>
Date: Fri, 27 Mar 2026 09:18:21 +1100
Subject: cachefiles: fix incorrect dentry refcount in cachefiles_cull()

The patch mentioned below changed cachefiles_bury_object() to expect 2
references to the 'rep' dentry.  Three of the callers were changed to
use start_removing_dentry() which takes an extra reference so in those
cases the call gets the expected references.

However there is another call to cachefiles_bury_object() in
cachefiles_cull() which did not need to be changed to use
start_removing_dentry() and so was not properly considered.
It still passed the dentry with just one reference so the net result is
that a reference is lost.

To meet the expectations of cachefiles_bury_object(), cachefiles_cull()
must take an extra reference before the call.  It will be dropped by
cachefiles_bury_object().

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Fixes: 7bb1eb45e43c ("VFS: introduce start_removing_dentry()")
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://patch.msgid.link/177456350181.1851489.16359967086642190170@noble.neil.brown.name
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/cachefiles/namei.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index e5ec90dccc27..eb9eb7683e3c 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -810,6 +810,11 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
 	if (ret < 0)
 		goto error_unlock;
 
+	/*
+	 * cachefiles_bury_object() expects 2 references to 'victim',
+	 * and drops one.
+	 */
+	dget(victim);
 	ret = cachefiles_bury_object(cache, NULL, dir, victim,
 				     FSCACHE_OBJECT_WAS_CULLED);
 	dput(victim);
-- 
cgit v1.2.3


From 393e0b4f178ec7fce1141dacc3304e3607a92ee9 Mon Sep 17 00:00:00 2001
From: Suraj Gupta <suraj.gupta2@amd.com>
Date: Fri, 27 Mar 2026 13:02:37 +0530
Subject: net: xilinx: axienet: Correct BD length masks to match AXIDMA IP spec

The XAXIDMA_BD_CTRL_LENGTH_MASK and XAXIDMA_BD_STS_ACTUAL_LEN_MASK
macros were defined as 0x007FFFFF (23 bits), but the AXI DMA IP
product guide (PG021) specifies the buffer length field as bits 25:0
(26 bits). Update both masks to match the IP documentation.

In practice this had no functional impact, since Ethernet frames are
far smaller than 2^23 bytes and the extra bits were always zero, but
the masks should still reflect the hardware specification.

Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
Signed-off-by: Suraj Gupta <suraj.gupta2@amd.com>
Reviewed-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20260327073238.134948-2-suraj.gupta2@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 5ff742103beb..fcd3aaef27fc 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -105,7 +105,7 @@
 #define XAXIDMA_BD_HAS_DRE_MASK		0xF00 /* Whether has DRE mask */
 #define XAXIDMA_BD_WORDLEN_MASK		0xFF /* Whether has DRE mask */
 
-#define XAXIDMA_BD_CTRL_LENGTH_MASK	0x007FFFFF /* Requested len */
+#define XAXIDMA_BD_CTRL_LENGTH_MASK	GENMASK(25, 0) /* Requested len */
 #define XAXIDMA_BD_CTRL_TXSOF_MASK	0x08000000 /* First tx packet */
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
 #define XAXIDMA_BD_CTRL_ALL_MASK	0x0C000000 /* All control bits */
@@ -130,7 +130,7 @@
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
 #define XAXIDMA_BD_CTRL_ALL_MASK	0x0C000000 /* All control bits */
 
-#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK	0x007FFFFF /* Actual len */
+#define XAXIDMA_BD_STS_ACTUAL_LEN_MASK	GENMASK(25, 0) /* Actual len */
 #define XAXIDMA_BD_STS_COMPLETE_MASK	0x80000000 /* Completed */
 #define XAXIDMA_BD_STS_DEC_ERR_MASK	0x40000000 /* Decode error */
 #define XAXIDMA_BD_STS_SLV_ERR_MASK	0x20000000 /* Slave error */
-- 
cgit v1.2.3


From d1978d03e86785872871bff9c2623174b10740de Mon Sep 17 00:00:00 2001
From: Suraj Gupta <suraj.gupta2@amd.com>
Date: Fri, 27 Mar 2026 13:02:38 +0530
Subject: net: xilinx: axienet: Fix BQL accounting for multi-BD TX packets

When a TX packet spans multiple buffer descriptors (scatter-gather),
axienet_free_tx_chain sums the per-BD actual length from descriptor
status into a caller-provided accumulator. That sum is reset on each
NAPI poll. If the BDs for a single packet complete across different
polls, the earlier bytes are lost and never credited to BQL. This
causes BQL to think bytes are permanently in-flight, eventually
stalling the TX queue.

The SKB pointer is stored only on the last BD of a packet. When that
BD completes, use skb->len for the byte count instead of summing
per-BD status lengths. This matches netdev_sent_queue(), which debits
skb->len, and naturally survives across polls because no partial
packet contributes to the accumulator.

Fixes: c900e49d58eb ("net: xilinx: axienet: Implement BQL")
Signed-off-by: Suraj Gupta <suraj.gupta2@amd.com>
Reviewed-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20260327073238.134948-3-suraj.gupta2@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b06e4c37ff61..263c4b67fd5a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -770,8 +770,8 @@ static int axienet_device_reset(struct net_device *ndev)
  * @first_bd:	Index of first descriptor to clean up
  * @nr_bds:	Max number of descriptors to clean up
  * @force:	Whether to clean descriptors even if not complete
- * @sizep:	Pointer to a u32 filled with the total sum of all bytes
- *		in all cleaned-up descriptors. Ignored if NULL.
+ * @sizep:	Pointer to a u32 accumulating the total byte count of
+ *		completed packets (using skb->len). Ignored if NULL.
  * @budget:	NAPI budget (use 0 when not called from NAPI poll)
  *
  * Would either be called after a successful transmit operation, or after
@@ -805,6 +805,8 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 DMA_TO_DEVICE);
 
 		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
+			if (sizep)
+				*sizep += cur_p->skb->len;
 			napi_consume_skb(cur_p->skb, budget);
 			packets++;
 		}
@@ -818,9 +820,6 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 		wmb();
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
-
-		if (sizep)
-			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
 	if (!force) {
-- 
cgit v1.2.3


From dff34ef879c5e73298443956a8b391311ba78d57 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 27 Mar 2026 11:52:05 +0100
Subject: mmc: vub300: fix NULL-deref on disconnect

Make sure to deregister the controller before dropping the reference to
the driver data on disconnect to avoid NULL-pointer dereferences or
use-after-free.

Fixes: 88095e7b473a ("mmc: Add new VUB300 USB-to-SD/SDIO/MMC driver")
Cc: stable@vger.kernel.org # 3.0+
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/vub300.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index ff49d0770506..f173c7cf4e1a 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -2365,8 +2365,8 @@ static void vub300_disconnect(struct usb_interface *interface)
 			usb_set_intfdata(interface, NULL);
 			/* prevent more I/O from starting */
 			vub300->interface = NULL;
-			kref_put(&vub300->kref, vub300_delete);
 			mmc_remove_host(mmc);
+			kref_put(&vub300->kref, vub300_delete);
 			pr_info("USB vub300 remote SDIO host controller[%d]"
 				" now disconnected", ifnum);
 			return;
-- 
cgit v1.2.3


From 8f4d20a710225ec7a565f6a0459862d3b1f32330 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 27 Mar 2026 11:52:06 +0100
Subject: mmc: vub300: fix use-after-free on disconnect

The vub300 driver maintains an explicit reference count for the
controller and its driver data and the last reference can in theory be
dropped after the driver has been unbound.

This specifically means that the controller allocation must not be
device managed as that can lead to use-after-free.

Note that the lifetime is currently also incorrectly tied the parent USB
device rather than interface, which can lead to memory leaks if the
driver is unbound without its device being physically disconnected (e.g.
on probe deferral).

Fix both issues by reverting to non-managed allocation of the controller.

Fixes: dcfdd698dc52 ("mmc: vub300: Use devm_mmc_alloc_host() helper")
Cc: stable@vger.kernel.org # 6.17+
Cc: Binbin Zhou <zhoubinbin@loongson.cn>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/vub300.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index f173c7cf4e1a..3c9df27f9fa7 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -369,11 +369,14 @@ struct vub300_mmc_host {
 static void vub300_delete(struct kref *kref)
 {				/* kref callback - softirq */
 	struct vub300_mmc_host *vub300 = kref_to_vub300_mmc_host(kref);
+	struct mmc_host *mmc = vub300->mmc;
+
 	usb_free_urb(vub300->command_out_urb);
 	vub300->command_out_urb = NULL;
 	usb_free_urb(vub300->command_res_urb);
 	vub300->command_res_urb = NULL;
 	usb_put_dev(vub300->udev);
+	mmc_free_host(mmc);
 	/*
 	 * and hence also frees vub300
 	 * which is contained at the end of struct mmc
@@ -2112,7 +2115,7 @@ static int vub300_probe(struct usb_interface *interface,
 		goto error1;
 	}
 	/* this also allocates memory for our VUB300 mmc host device */
-	mmc = devm_mmc_alloc_host(&udev->dev, sizeof(*vub300));
+	mmc = mmc_alloc_host(sizeof(*vub300), &udev->dev);
 	if (!mmc) {
 		retval = -ENOMEM;
 		dev_err(&udev->dev, "not enough memory for the mmc_host\n");
@@ -2269,7 +2272,7 @@ static int vub300_probe(struct usb_interface *interface,
 		dev_err(&vub300->udev->dev,
 		    "Could not find two sets of bulk-in/out endpoint pairs\n");
 		retval = -EINVAL;
-		goto error4;
+		goto err_free_host;
 	}
 	retval =
 		usb_control_msg(vub300->udev, usb_rcvctrlpipe(vub300->udev, 0),
@@ -2278,14 +2281,14 @@ static int vub300_probe(struct usb_interface *interface,
 				0x0000, 0x0000, &vub300->hc_info,
 				sizeof(vub300->hc_info), 1000);
 	if (retval < 0)
-		goto error4;
+		goto err_free_host;
 	retval =
 		usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
 				SET_ROM_WAIT_STATES,
 				USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
 				firmware_rom_wait_states, 0x0000, NULL, 0, 1000);
 	if (retval < 0)
-		goto error4;
+		goto err_free_host;
 	dev_info(&vub300->udev->dev,
 		 "operating_mode = %s %s %d MHz %s %d byte USB packets\n",
 		 (mmc->caps & MMC_CAP_SDIO_IRQ) ? "IRQs" : "POLL",
@@ -2300,7 +2303,7 @@ static int vub300_probe(struct usb_interface *interface,
 				0x0000, 0x0000, &vub300->system_port_status,
 				sizeof(vub300->system_port_status), 1000);
 	if (retval < 0) {
-		goto error4;
+		goto err_free_host;
 	} else if (sizeof(vub300->system_port_status) == retval) {
 		vub300->card_present =
 			(0x0001 & vub300->system_port_status.port_flags) ? 1 : 0;
@@ -2308,7 +2311,7 @@ static int vub300_probe(struct usb_interface *interface,
 			(0x0010 & vub300->system_port_status.port_flags) ? 1 : 0;
 	} else {
 		retval = -EINVAL;
-		goto error4;
+		goto err_free_host;
 	}
 	usb_set_intfdata(interface, vub300);
 	INIT_DELAYED_WORK(&vub300->pollwork, vub300_pollwork_thread);
@@ -2338,6 +2341,8 @@ static int vub300_probe(struct usb_interface *interface,
 	return 0;
 error6:
 	timer_delete_sync(&vub300->inactivity_timer);
+err_free_host:
+	mmc_free_host(mmc);
 	/*
 	 * and hence also frees vub300
 	 * which is contained at the end of struct mmc
-- 
cgit v1.2.3


From 51e3eb3d074a8c7c306d447612011cf8568c8d6f Mon Sep 17 00:00:00 2001
From: Sachin Mokashi <sachin.mokashi@intel.com>
Date: Fri, 27 Mar 2026 09:14:39 -0400
Subject: ASoC: Intel: ehl_rt5660: Use the correct rtd->dev device in hw_params

In rt5660_hw_params(), the error path for snd_soc_dai_set_sysclk()
correctly uses rtd->dev as the logging device, but the error path for
snd_soc_dai_set_pll() uses codec_dai->dev instead.

These two devices are distinct:
- rtd->dev is the platform device of the PCM runtime (the Intel HDA/SSP
  controller, e.g. 0000:00:1f.3), which owns the machine driver callback.
- codec_dai->dev is the I2C device of the rt5660 codec itself
  (i2c-10EC5660:00).

Since hw_params is a machine driver operation and both calls are made
within the same function from the machine driver's context, all error
messages should be attributed to rtd->dev. Using codec_dai->dev for one
of them would suggest the error originates inside the codec driver,
which is misleading.

Align the PLL error log with the sysclk one to use rtd->dev, matching
the convention used by all other Intel board drivers in this directory.

Signed-off-by: Sachin Mokashi <sachin.mokashi@intel.com>
Link: https://patch.msgid.link/20260327131439.1330373-1-sachin.mokashi@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/ehl_rt5660.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/ehl_rt5660.c b/sound/soc/intel/boards/ehl_rt5660.c
index 5c7b218f22b7..c40cd9fb1a26 100644
--- a/sound/soc/intel/boards/ehl_rt5660.c
+++ b/sound/soc/intel/boards/ehl_rt5660.c
@@ -127,7 +127,7 @@ static int rt5660_hw_params(struct snd_pcm_substream *substream,
 				  params_rate(params) * 50,
 				  params_rate(params) * 512);
 	if (ret < 0)
-		dev_err(codec_dai->dev, "can't set codec pll: %d\n", ret);
+		dev_err(rtd->dev, "can't set codec pll: %d\n", ret);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 45b859b0728267a6199ee5002d62e6c6f3e8c89d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 27 Mar 2026 10:49:52 +0100
Subject: thermal: core: Address thermal zone removal races with resume

Since thermal_zone_pm_complete() and thermal_zone_device_resume()
re-initialize the poll_queue delayed work for the given thermal zone,
the cancel_delayed_work_sync() in thermal_zone_device_unregister()
may miss some already running work items and the thermal zone may
be freed prematurely [1].

There are two failing scenarios that both start with
running thermal_pm_notify_complete() right before invoking
thermal_zone_device_unregister() for one of the thermal zones.

In the first scenario, there is a work item already running for
the given thermal zone when thermal_pm_notify_complete() calls
thermal_zone_pm_complete() for that thermal zone and it continues to
run when thermal_zone_device_unregister() starts.  Since the poll_queue
delayed work has been re-initialized by thermal_pm_notify_complete(), the
running work item will be missed by the cancel_delayed_work_sync() in
thermal_zone_device_unregister() and if it continues to run past the
freeing of the thermal zone object, a use-after-free will occur.

In the second scenario, thermal_zone_device_resume() queued up by
thermal_pm_notify_complete() runs right after the thermal_zone_exit()
called by thermal_zone_device_unregister() has returned.  The poll_queue
delayed work is re-initialized by it before cancel_delayed_work_sync() is
called by thermal_zone_device_unregister(), so it may continue to run
after the freeing of the thermal zone object, which also leads to a
use-after-free.

Address the first failing scenario by ensuring that no thermal work
items will be running when thermal_pm_notify_complete() is called.
For this purpose, first move the cancel_delayed_work() call from
thermal_zone_pm_complete() to thermal_zone_pm_prepare() to prevent
new work from entering the workqueue going forward.  Next, switch
over to using a dedicated workqueue for thermal events and update
the code in thermal_pm_notify() to flush that workqueue after
thermal_pm_notify_prepare() has returned which will take care of
all leftover thermal work already on the workqueue (that leftover
work would do nothing useful anyway because all of the thermal zones
have been flagged as suspended).

The second failing scenario is addressed by adding a tz->state check
to thermal_zone_device_resume() to prevent it from re-initializing
the poll_queue delayed work if the thermal zone is going away.

Note that the above changes will also facilitate relocating the suspend
and resume of thermal zones closer to the suspend and resume of devices,
respectively.

Fixes: 5a5efdaffda5 ("thermal: core: Resume thermal zones asynchronously")
Reported-by: syzbot+3b3852c6031d0f30dfaf@syzkaller.appspotmail.com
Closes: https://syzbot.org/bug?extid=3b3852c6031d0f30dfaf
Reported-by: Mauricio Faria de Oliveira <mfo@igalia.com>
Closes: https://lore.kernel.org/linux-pm/20260324-thermal-core-uaf-init_delayed_work-v1-1-6611ae76a8a1@igalia.com/ [1]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mauricio Faria de Oliveira <mfo@igalia.com>
Tested-by: Mauricio Faria de Oliveira <mfo@igalia.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Cc: All applicable <stable@vger.kernel.org>
Link: https://patch.msgid.link/6267615.lOV4Wx5bFT@rafael.j.wysocki
---
 drivers/thermal/thermal_core.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index b7d706ed7ed9..5337612e484d 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -41,6 +41,8 @@ static struct thermal_governor *def_governor;
 
 static bool thermal_pm_suspended;
 
+static struct workqueue_struct *thermal_wq __ro_after_init;
+
 /*
  * Governor section: set of functions to handle thermal governors
  *
@@ -313,7 +315,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 	if (delay > HZ)
 		delay = round_jiffies_relative(delay);
 
-	mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, delay);
+	mod_delayed_work(thermal_wq, &tz->poll_queue, delay);
 }
 
 static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
@@ -1785,6 +1787,10 @@ static void thermal_zone_device_resume(struct work_struct *work)
 
 	guard(thermal_zone)(tz);
 
+	/* If the thermal zone is going away, there's nothing to do. */
+	if (tz->state & TZ_STATE_FLAG_EXIT)
+		return;
+
 	tz->state &= ~(TZ_STATE_FLAG_SUSPENDED | TZ_STATE_FLAG_RESUMING);
 
 	thermal_debug_tz_resume(tz);
@@ -1811,6 +1817,9 @@ static void thermal_zone_pm_prepare(struct thermal_zone_device *tz)
 	}
 
 	tz->state |= TZ_STATE_FLAG_SUSPENDED;
+
+	/* Prevent new work from getting to the workqueue subsequently. */
+	cancel_delayed_work(&tz->poll_queue);
 }
 
 static void thermal_pm_notify_prepare(void)
@@ -1829,8 +1838,6 @@ static void thermal_zone_pm_complete(struct thermal_zone_device *tz)
 {
 	guard(thermal_zone)(tz);
 
-	cancel_delayed_work(&tz->poll_queue);
-
 	reinit_completion(&tz->resume);
 	tz->state |= TZ_STATE_FLAG_RESUMING;
 
@@ -1840,7 +1847,7 @@ static void thermal_zone_pm_complete(struct thermal_zone_device *tz)
 	 */
 	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_resume);
 	/* Queue up the work without a delay. */
-	mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, 0);
+	mod_delayed_work(thermal_wq, &tz->poll_queue, 0);
 }
 
 static void thermal_pm_notify_complete(void)
@@ -1863,6 +1870,11 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_RESTORE_PREPARE:
 	case PM_SUSPEND_PREPARE:
 		thermal_pm_notify_prepare();
+		/*
+		 * Allow any leftover thermal work items already on the
+		 * worqueue to complete so they don't get in the way later.
+		 */
+		flush_workqueue(thermal_wq);
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_RESTORE:
@@ -1895,9 +1907,16 @@ static int __init thermal_init(void)
 	if (result)
 		goto error;
 
+	thermal_wq = alloc_workqueue("thermal_events",
+				      WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
+	if (!thermal_wq) {
+		result = -ENOMEM;
+		goto unregister_netlink;
+	}
+
 	result = thermal_register_governors();
 	if (result)
-		goto unregister_netlink;
+		goto destroy_workqueue;
 
 	thermal_class = kzalloc_obj(*thermal_class);
 	if (!thermal_class) {
@@ -1924,6 +1943,8 @@ static int __init thermal_init(void)
 
 unregister_governors:
 	thermal_unregister_governors();
+destroy_workqueue:
+	destroy_workqueue(thermal_wq);
 unregister_netlink:
 	thermal_netlink_exit();
 error:
-- 
cgit v1.2.3


From ec327abae5edd1d5b60ea9f920212970133171d2 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Sat, 14 Mar 2026 11:19:51 +0000
Subject: rust_binder: use AssertSync for BINDER_VM_OPS

When declaring an immutable global variable in Rust, the compiler checks
that it looks thread safe, because it is generally safe to access said
global variable. When using C bindings types for these globals, we don't
really want this check, because it is conservative and assumes pointers
are not thread safe.

In the case of BINDER_VM_OPS, this is a challenge when combined with the
patch 'userfaultfd: introduce vm_uffd_ops' [1], which introduces a
pointer field to vm_operations_struct. It previously only held function
pointers, which are considered thread safe.

Rust Binder should not be assuming that vm_operations_struct contains no
pointer fields, so to fix this, use AssertSync (which Rust Binder has
already declared for another similar global of type struct
file_operations with the same problem). This ensures that even if
another commit adds a pointer field to vm_operations_struct, this does
not cause problems.

Fixes: 8ef2c15aeae0 ("rust_binder: check ownership before using vma")
Cc: stable <stable@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202603121235.tpnRxFKO-lkp@intel.com/
Link: https://lore.kernel.org/r/20260306171815.3160826-8-rppt@kernel.org [1]
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260314111951.4139029-1-aliceryhl@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder/page_range.rs       | 8 +++++---
 drivers/android/binder/rust_binder_main.rs | 2 +-
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/android/binder/page_range.rs b/drivers/android/binder/page_range.rs
index 9dfc154e5dd4..b57e0c7ba3f1 100644
--- a/drivers/android/binder/page_range.rs
+++ b/drivers/android/binder/page_range.rs
@@ -13,6 +13,8 @@
 //
 // The shrinker will use trylock methods because it locks them in a different order.
 
+use crate::AssertSync;
+
 use core::{
     marker::PhantomPinned,
     mem::{size_of, size_of_val, MaybeUninit},
@@ -143,14 +145,14 @@ pub(crate) struct ShrinkablePageRange {
 }
 
 // We do not define any ops. For now, used only to check identity of vmas.
-static BINDER_VM_OPS: bindings::vm_operations_struct = pin_init::zeroed();
+static BINDER_VM_OPS: AssertSync<bindings::vm_operations_struct> = AssertSync(pin_init::zeroed());
 
 // To ensure that we do not accidentally install pages into or zap pages from the wrong vma, we
 // check its vm_ops and private data before using it.
 fn check_vma(vma: &virt::VmaRef, owner: *const ShrinkablePageRange) -> Option<&virt::VmaMixedMap> {
     // SAFETY: Just reading the vm_ops pointer of any active vma is safe.
     let vm_ops = unsafe { (*vma.as_ptr()).vm_ops };
-    if !ptr::eq(vm_ops, &BINDER_VM_OPS) {
+    if !ptr::eq(vm_ops, &BINDER_VM_OPS.0) {
         return None;
     }
 
@@ -342,7 +344,7 @@ impl ShrinkablePageRange {
 
         // SAFETY: We own the vma, and we don't use any methods on VmaNew that rely on
         // `vm_ops`.
-        unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS };
+        unsafe { (*vma.as_ptr()).vm_ops = &BINDER_VM_OPS.0 };
 
         Ok(num_pages)
     }
diff --git a/drivers/android/binder/rust_binder_main.rs b/drivers/android/binder/rust_binder_main.rs
index aa5f2a75adb4..014010662df8 100644
--- a/drivers/android/binder/rust_binder_main.rs
+++ b/drivers/android/binder/rust_binder_main.rs
@@ -306,7 +306,7 @@ impl kernel::Module for BinderModule {
 /// Makes the inner type Sync.
 #[repr(transparent)]
 pub struct AssertSync<T>(T);
-// SAFETY: Used only to insert `file_operations` into a global, which is safe.
+// SAFETY: Used only to insert C bindings types into globals, which is safe.
 unsafe impl<T> Sync for AssertSync<T> {}
 
 /// File operations that rust_binderfs.c can use.
-- 
cgit v1.2.3


From 8c27b1bce059a11a8d3c8682984e13866f0714af Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Mon, 30 Mar 2026 11:38:30 +0300
Subject: mei: me: reduce the scope on unexpected reset

After commit 2cedb296988c ("mei: me: trigger link reset if hw ready is unexpected")
some devices started to show long resume times (5-7 seconds).
This happens as mei falsely detects unready hardware,
starts parallel link reset flow and triggers link reset timeouts
in the resume callback.

Address it by performing detection of unready hardware only
when driver is in the MEI_DEV_ENABLED state instead of blacklisting
states as done in the original patch.
This eliminates active waitqueue check as in MEI_DEV_ENABLED state
there will be no active waitqueue.

Reviewed-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Reported-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221023
Tested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Fixes: 2cedb296988c ("mei: me: trigger link reset if hw ready is unexpected")
Cc: stable <stable@kernel.org>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Link: https://patch.msgid.link/20260330083830.536056-1-alexander.usyskin@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/hw-me.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index d4612c659784..1e4a41ac428f 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -1337,19 +1337,13 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	/*  check if we need to start the dev */
 	if (!mei_host_is_ready(dev)) {
 		if (mei_hw_is_ready(dev)) {
-			/* synchronized by dev mutex */
-			if (waitqueue_active(&dev->wait_hw_ready)) {
-				dev_dbg(&dev->dev, "we need to start the dev.\n");
-				dev->recvd_hw_ready = true;
-				wake_up(&dev->wait_hw_ready);
-			} else if (dev->dev_state != MEI_DEV_UNINITIALIZED &&
-				   dev->dev_state != MEI_DEV_POWERING_DOWN &&
-				   dev->dev_state != MEI_DEV_POWER_DOWN) {
+			if (dev->dev_state == MEI_DEV_ENABLED) {
 				dev_dbg(&dev->dev, "Force link reset.\n");
 				schedule_work(&dev->reset_work);
 			} else {
-				dev_dbg(&dev->dev, "Ignore this interrupt in state = %d\n",
-					dev->dev_state);
+				dev_dbg(&dev->dev, "we need to start the dev.\n");
+				dev->recvd_hw_ready = true;
+				wake_up(&dev->wait_hw_ready);
 			}
 		} else {
 			dev_dbg(&dev->dev, "Spurious Interrupt\n");
-- 
cgit v1.2.3


From 69335152910b775e7835939d5c863c580c605275 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 27 Jan 2026 20:11:05 +0100
Subject: misc/mei: INTEL_MEI should depend on X86 or DRM_XE

The Intel Management Engine Interface is only present on x86 platforms
and Intel Xe graphics cards.  Hence add a dependency on X86 or DRM_XE,
to prevent asking the user about this driver when configuring a kernel
for a non-x86 architecture and without Xe graphics support.

Fixes: 25f9b0d35155 ("misc/mei: Allow building Intel ME interface on non-x86")
Cc: stable <stable@kernel.org>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/8e2646fb71b148b3d38beb13f19b14e3634a1e1a.1769541024.git.geert+renesas@glider.be
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 5902dd1ee44b..094fb1dde0fe 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -3,6 +3,7 @@
 config INTEL_MEI
 	tristate "Intel Management Engine Interface"
 	depends on PCI
+	depends on X86 || DRM_XE!=n || COMPILE_TEST
 	default X86_64 || MATOM
 	help
 	  The Intel Management Engine (Intel ME) provides Manageability,
-- 
cgit v1.2.3


From e920c36f2073d533bdf19ba6ab690432c8173b63 Mon Sep 17 00:00:00 2001
From: Julian Braha <julianbraha@gmail.com>
Date: Wed, 25 Mar 2026 00:15:21 +0000
Subject: ASoC: Intel: boards: fix unmet dependency on PINCTRL

This reverts commit c073f0757663 ("ASoC: Intel: sof_sdw: select PINCTRL_CS42L43 and SPI_CS42L43")

Currently, SND_SOC_INTEL_SOUNDWIRE_SOF_MACH selects PINCTRL_CS42L43
without also selecting or depending on PINCTRL, despite PINCTRL_CS42L43
depending on PINCTRL.

See the following Kbuild warning:

WARNING: unmet direct dependencies detected for PINCTRL_CS42L43
  Depends on [n]: PINCTRL [=n] && MFD_CS42L43 [=m]
  Selected by [m]:
  - SND_SOC_INTEL_SOUNDWIRE_SOF_MACH [=m] && SOUND [=y] && SND [=m] && SND_SOC [=m] && SND_SOC_INTEL_MACH [=y] && (SND_SOC_SOF_INTEL_COMMON [=m] || !SND_SOC_SOF_INTEL_COMMON [=m]) && SND_SOC_SOF_INTEL_SOUNDWIRE [=m] && I2C [=y] && SPI_MASTER [=y] && ACPI [=y] && (MFD_INTEL_LPSS [=n] || COMPILE_TEST [=y]) && (SND_SOC_INTEL_USER_FRIENDLY_LONG_NAMES [=n] || COMPILE_TEST [=y]) && SOUNDWIRE [=m]

In response to v1 of this patch [1], Arnd pointed out that there is
no compile-time dependency sof_sdw and the PINCTRL_CS42L43 driver.
After testing, I can confirm that the kernel compiled with
SND_SOC_INTEL_SOUNDWIRE_SOF_MACH enabled and PINCTRL_CS42L43 disabled.

This unmet dependency was detected by kconfirm, a static analysis
tool for Kconfig.

Link: https://lore.kernel.org/all/b8aecc71-1fed-4f52-9f6c-263fbe56d493@app.fastmail.com/ [1]
Fixes: c073f0757663 ("ASoC: Intel: sof_sdw: select PINCTRL_CS42L43 and SPI_CS42L43")
Signed-off-by: Julian Braha <julianbraha@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20260325001522.1727678-1-julianbraha@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index c5942b5655d3..d53af8f7e55b 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -530,8 +530,6 @@ config SND_SOC_INTEL_SOUNDWIRE_SOF_MACH
 	select SND_SOC_CS42L43_SDW
 	select MFD_CS42L43
 	select MFD_CS42L43_SDW
-	select PINCTRL_CS42L43
-	select SPI_CS42L43
 	select SND_SOC_CS35L56_SPI
 	select SND_SOC_CS35L56_SDW
 	select SND_SOC_DMIC
-- 
cgit v1.2.3


From fa6e24963342de4370e3a3c9af41e38277b74cf3 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Fri, 27 Mar 2026 23:30:00 -0700
Subject: bridge: mrp: reject zero test interval to avoid OOM panic

br_mrp_start_test() and br_mrp_start_in_test() accept the user-supplied
interval value from netlink without validation. When interval is 0,
usecs_to_jiffies(0) yields 0, causing the delayed work
(br_mrp_test_work_expired / br_mrp_in_test_work_expired) to reschedule
itself with zero delay. This creates a tight loop on system_percpu_wq
that allocates and transmits MRP test frames at maximum rate, exhausting
all system memory and causing a kernel panic via OOM deadlock.

The same zero-interval issue applies to br_mrp_start_in_test_parse()
for interconnect test frames.

Use NLA_POLICY_MIN(NLA_U32, 1) in the nla_policy tables for both
IFLA_BRIDGE_MRP_START_TEST_INTERVAL and
IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL, so zero is rejected at the
netlink attribute parsing layer before the value ever reaches the
workqueue scheduling code. This is consistent with how other bridge
subsystems (br_fdb, br_mst) enforce range constraints on netlink
attributes.

Fixes: 20f6a05ef635 ("bridge: mrp: Rework the MRP netlink interface")
Fixes: 7ab1748e4ce6 ("bridge: mrp: Extend MRP netlink interface for configuring MRP interconnect")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260328063000.1845376-1-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/bridge/br_mrp_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c
index ce6f63c77cc0..86f0e75d6e34 100644
--- a/net/bridge/br_mrp_netlink.c
+++ b/net/bridge/br_mrp_netlink.c
@@ -196,7 +196,7 @@ static const struct nla_policy
 br_mrp_start_test_policy[IFLA_BRIDGE_MRP_START_TEST_MAX + 1] = {
 	[IFLA_BRIDGE_MRP_START_TEST_UNSPEC]	= { .type = NLA_REJECT },
 	[IFLA_BRIDGE_MRP_START_TEST_RING_ID]	= { .type = NLA_U32 },
-	[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_MRP_START_TEST_INTERVAL]	= NLA_POLICY_MIN(NLA_U32, 1),
 	[IFLA_BRIDGE_MRP_START_TEST_MAX_MISS]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_TEST_PERIOD]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_TEST_MONITOR]	= { .type = NLA_U32 },
@@ -316,7 +316,7 @@ static const struct nla_policy
 br_mrp_start_in_test_policy[IFLA_BRIDGE_MRP_START_IN_TEST_MAX + 1] = {
 	[IFLA_BRIDGE_MRP_START_IN_TEST_UNSPEC]	= { .type = NLA_REJECT },
 	[IFLA_BRIDGE_MRP_START_IN_TEST_IN_ID]	= { .type = NLA_U32 },
-	[IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_MRP_START_IN_TEST_INTERVAL]	= NLA_POLICY_MIN(NLA_U32, 1),
 	[IFLA_BRIDGE_MRP_START_IN_TEST_MAX_MISS]	= { .type = NLA_U32 },
 	[IFLA_BRIDGE_MRP_START_IN_TEST_PERIOD]	= { .type = NLA_U32 },
 };
-- 
cgit v1.2.3


From 217d5bc9f96272316ac5a3215c7cc32a5127bbf3 Mon Sep 17 00:00:00 2001
From: Alexander Savenko <alex.sav4387@gmail.com>
Date: Tue, 31 Mar 2026 11:29:28 +0300
Subject: ALSA: hda/realtek: Add quirk for Lenovo Yoga Pro 7 14IMH9

The Lenovo Yoga Pro 7 14IMH9 (DMI: 83E2) shares PCI SSID 17aa:3847
with the Legion 7 16ACHG6, but has a different codec subsystem ID
(17aa:38cf). The existing SND_PCI_QUIRK for 17aa:3847 applies
ALC287_FIXUP_LEGION_16ACHG6, which attempts to initialize an external
I2C amplifier (CLSA0100) that is not present on the Yoga Pro 7 14IMH9.

As a result, pin 0x17 (bass speakers) is connected to DAC 0x06 which
has no volume control, making hardware volume adjustment completely
non-functional. Audio is either silent or at maximum volume regardless
of the slider position.

Add a HDA_CODEC_QUIRK entry using the codec subsystem ID (17aa:38cf)
to correctly identify the Yoga Pro 7 14IMH9 and apply
ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN, which redirects pin 0x17 to
DAC 0x02 and restores proper volume control. The existing Legion entry
is preserved unchanged.

This follows the same pattern used for 17aa:386e, where Legion Y9000X
and Yoga Pro 7 14ARP8 share a PCI SSID but are distinguished via
HDA_CODEC_QUIRK.

Link: https://github.com/nomad4tech/lenovo-yoga-pro-7-linux
Tested-by: Alexander Savenko <alex.sav4387@gmail.com>
Signed-off-by: Alexander Savenko <alex.sav4387@gmail.com>
Link: https://patch.msgid.link/20260331082929.44890-1-alex.sav4387@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index fa5f08cd2c65..c6f878678986 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7614,6 +7614,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x383d, "Legion Y9000X 2019", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3843, "Lenovo Yoga 9i / Yoga Book 9i", ALC287_FIXUP_LENOVO_YOGA_BOOK_9I),
+	/* Yoga Pro 7 14IMH9 shares PCI SSID 17aa:3847 with Legion 7 16ACHG6;
+	 * use codec SSID to distinguish them
+	 */
+	HDA_CODEC_QUIRK(0x17aa, 0x38cf, "Lenovo Yoga Pro 7 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3847, "Legion 7 16ACHG6", ALC287_FIXUP_LEGION_16ACHG6),
 	SND_PCI_QUIRK(0x17aa, 0x384a, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
-- 
cgit v1.2.3


From dd9b99b822684f421f9b7e1e5a69d791ffc1d48f Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Tue, 31 Mar 2026 17:46:14 +0800
Subject: ALSA: hda/realtek: add quirk for Acer Swift SFG14-73

fix mute/micmute LEDs and headset microphone for Acer Swift SFG14-73.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220279
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Link: https://patch.msgid.link/20260331094614.186063-1-zhangheng@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index c6f878678986..6db23ce8a5fe 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6720,6 +6720,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED),
+	SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED),
 	SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2),
-- 
cgit v1.2.3


From 82cbae59263e3941a8bb79f0b25e0b0f085132d4 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Sun, 29 Mar 2026 14:46:57 +0200
Subject: platform/x86: asus-armoury: add support for GV302XU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model GV302XU.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260329124659.3967495-2-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index 569743746347..a53204c24d43 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1376,6 +1376,33 @@ static const struct dmi_system_id power_limits[] = {
 			},
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GV302XU"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 55,
+				.ppt_pl2_sppt_min = 25,
+				.ppt_pl2_sppt_max = 60,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 35,
+				.ppt_pl2_sppt_min = 25,
+				.ppt_pl2_sppt_max = 35,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GV302XV"),
-- 
cgit v1.2.3


From b4f04a6038fa97f7ceea33e99456b9838c79dde7 Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Sun, 29 Mar 2026 14:46:58 +0200
Subject: platform/x86: asus-armoury: add support for FA607NU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model FA607NU.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260329124659.3967495-3-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index a53204c24d43..ed02574139fa 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -592,6 +592,37 @@ static const struct dmi_system_id power_limits[] = {
 			},
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "FA607NU"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 15,
+				.ppt_pl1_spl_max = 80,
+				.ppt_pl2_sppt_min = 35,
+				.ppt_pl2_sppt_max = 80,
+				.ppt_pl3_fppt_min = 35,
+				.ppt_pl3_fppt_max = 80,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 25,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 25,
+				.ppt_pl1_spl_def = 45,
+				.ppt_pl1_spl_max = 65,
+				.ppt_pl2_sppt_min = 25,
+				.ppt_pl2_sppt_def = 54,
+				.ppt_pl2_sppt_max = 65,
+				.ppt_pl3_fppt_min = 25,
+				.ppt_pl3_fppt_max = 65,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "FA607P"),
-- 
cgit v1.2.3


From 5d486669b3db11ccc2d1b9f4e42c11c2766f35ba Mon Sep 17 00:00:00 2001
From: Denis Benato <denis.benato@linux.dev>
Date: Sun, 29 Mar 2026 14:46:59 +0200
Subject: platform/x86: asus-armoury: add support for GU605MU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add TDP data for laptop model GU605MU.

Signed-off-by: Denis Benato <denis.benato@linux.dev>
Link: https://patch.msgid.link/20260329124659.3967495-4-denis.benato@linux.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-armoury.h | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/platform/x86/asus-armoury.h b/drivers/platform/x86/asus-armoury.h
index ed02574139fa..c30d2b451e01 100644
--- a/drivers/platform/x86/asus-armoury.h
+++ b/drivers/platform/x86/asus-armoury.h
@@ -1340,6 +1340,34 @@ static const struct dmi_system_id power_limits[] = {
 			.requires_fan_curve = true,
 		},
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "GU605MU"),
+		},
+		.driver_data = &(struct power_data) {
+			.ac_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 28,
+				.ppt_pl1_spl_max = 90,
+				.ppt_pl2_sppt_min = 28,
+				.ppt_pl2_sppt_max = 135,
+				.nv_dynamic_boost_min = 5,
+				.nv_dynamic_boost_max = 20,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+				.nv_tgp_min = 55,
+				.nv_tgp_max = 85,
+			},
+			.dc_data = &(struct power_limits) {
+				.ppt_pl1_spl_min = 25,
+				.ppt_pl1_spl_max = 35,
+				.ppt_pl2_sppt_min = 38,
+				.ppt_pl2_sppt_max = 53,
+				.nv_temp_target_min = 75,
+				.nv_temp_target_max = 87,
+			},
+			.requires_fan_curve = true,
+		},
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GU605M"),
-- 
cgit v1.2.3


From bbe5ab8191a33572c11be8628c55b79246307125 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 31 Mar 2026 11:11:07 -0400
Subject: cgroup/cpuset: Simplify setsched decision check in task iteration
 loop of cpuset_can_attach()

Centralize the check required to run security_task_setscheduler() in
the task iteration loop of cpuset_can_attach() outside of the loop as
it has no dependency on the characteristics of the tasks themselves.

There is no functional change.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index d21868455341..58c5b7b72cca 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2988,7 +2988,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	struct cgroup_subsys_state *css;
 	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
-	bool cpus_updated, mems_updated;
+	bool setsched_check;
 	int ret;
 
 	/* used later by cpuset_attach() */
@@ -3003,20 +3003,21 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 	if (ret)
 		goto out_unlock;
 
-	cpus_updated = !cpumask_equal(cs->effective_cpus, oldcs->effective_cpus);
-	mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems);
+	/*
+	 * Skip rights over task setsched check in v2 when nothing changes,
+	 * migration permission derives from hierarchy ownership in
+	 * cgroup_procs_write_permission()).
+	 */
+	setsched_check = !cpuset_v2() ||
+		!cpumask_equal(cs->effective_cpus, oldcs->effective_cpus) ||
+		!nodes_equal(cs->effective_mems, oldcs->effective_mems);
 
 	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task);
 		if (ret)
 			goto out_unlock;
 
-		/*
-		 * Skip rights over task check in v2 when nothing changes,
-		 * migration permission derives from hierarchy ownership in
-		 * cgroup_procs_write_permission()).
-		 */
-		if (!cpuset_v2() || (cpus_updated || mems_updated)) {
+		if (setsched_check) {
 			ret = security_task_setscheduler(task);
 			if (ret)
 				goto out_unlock;
-- 
cgit v1.2.3


From 089f3fcd690c71cb3d8ca09f34027764e28920a0 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 31 Mar 2026 11:11:08 -0400
Subject: cgroup/cpuset: Skip security check for hotplug induced v1 task
 migration

When a CPU hot removal causes a v1 cpuset to lose all its CPUs, the
cpuset hotplug handler will schedule a work function to migrate tasks
in that cpuset with no CPU to its ancestor to enable those tasks to
continue running.

If a strict security policy is in place, however, the task migration
may fail when security_task_setscheduler() call in cpuset_can_attach()
returns a -EACCES error. That will mean that those tasks will have
no CPU to run on. The system administrators will have to explicitly
intervene to either add CPUs to that cpuset or move the tasks elsewhere
if they are aware of it.

This problem was found by a reported test failure in the LTP's
cpuset_hotplug_test.sh. Fix this problem by treating this special case as
an exception to skip the setsched security check in cpuset_can_attach()
when a v1 cpuset with tasks have no CPU left.

With that patch applied, the cpuset_hotplug_test.sh test can be run
successfully without failure.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58c5b7b72cca..1335e437098e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3012,6 +3012,16 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		!cpumask_equal(cs->effective_cpus, oldcs->effective_cpus) ||
 		!nodes_equal(cs->effective_mems, oldcs->effective_mems);
 
+	/*
+	 * A v1 cpuset with tasks will have no CPU left only when CPU hotplug
+	 * brings the last online CPU offline as users are not allowed to empty
+	 * cpuset.cpus when there are active tasks inside. When that happens,
+	 * we should allow tasks to migrate out without security check to make
+	 * sure they will be able to run after migration.
+	 */
+	if (!is_in_v2_mode() && cpumask_empty(oldcs->effective_cpus))
+		setsched_check = false;
+
 	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task);
 		if (ret)
-- 
cgit v1.2.3


From a8502a79e832b861e99218cbd2d8f4312d62e225 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Tue, 31 Mar 2026 13:42:28 -0700
Subject: bpf: Fix regsafe() for pointers to packet

In case rold->reg->range == BEYOND_PKT_END && rcur->reg->range == N
regsafe() may return true which may lead to current state with
valid packet range not being explored. Fix the bug.

Fixes: 6d94e741a8ff ("bpf: Support for pointers beyond pkt_end.")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20260331204228.26726-1-alexei.starovoitov@gmail.com
---
 kernel/bpf/verifier.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f108c01ff6d0..a3388cb8fcbd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19915,8 +19915,13 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
 		 * since someone could have accessed through (ptr - k), or
 		 * even done ptr -= k in a register, to get a safe access.
 		 */
-		if (rold->range > rcur->range)
+		if (rold->range < 0 || rcur->range < 0) {
+			/* special case for [BEYOND|AT]_PKT_END */
+			if (rold->range != rcur->range)
+				return false;
+		} else if (rold->range > rcur->range) {
 			return false;
+		}
 		/* If the offsets don't match, we can't trust our alignment;
 		 * nor can we be sure that we won't fall out of range.
 		 */
-- 
cgit v1.2.3


From 9ca562bb8e66978b53028fa32b1a190708e6a091 Mon Sep 17 00:00:00 2001
From: Zhengchuan Liang <zcliangcn@gmail.com>
Date: Mon, 30 Mar 2026 16:46:24 +0800
Subject: net: ipv6: flowlabel: defer exclusive option free until RCU teardown

`ip6fl_seq_show()` walks the global flowlabel hash under the seq-file
RCU read-side lock and prints `fl->opt->opt_nflen` when an option block
is present.

Exclusive flowlabels currently free `fl->opt` as soon as `fl->users`
drops to zero in `fl_release()`. However, the surrounding
`struct ip6_flowlabel` remains visible in the global hash table until
later garbage collection removes it and `fl_free_rcu()` finally tears it
down.

A concurrent `/proc/net/ip6_flowlabel` reader can therefore race that
early `kfree()` and dereference freed option state, triggering a crash
in `ip6fl_seq_show()`.

Fix this by keeping `fl->opt` alive until `fl_free_rcu()`. That matches
the lifetime already required for the enclosing flowlabel while readers
can still reach it under RCU.

Fixes: d3aedd5ebd4b ("ipv6 flowlabel: Convert hash list to RCU.")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Zhengchuan Liang <zcliangcn@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/07351f0ec47bcee289576f39f9354f4a64add6e4.1774855883.git.zcliangcn@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_flowlabel.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 7c12bf75beed..c92f98c6f6ec 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -133,11 +133,6 @@ static void fl_release(struct ip6_flowlabel *fl)
 		if (time_after(ttd, fl->expires))
 			fl->expires = ttd;
 		ttd = fl->expires;
-		if (fl->opt && fl->share == IPV6_FL_S_EXCL) {
-			struct ipv6_txoptions *opt = fl->opt;
-			fl->opt = NULL;
-			kfree(opt);
-		}
 		if (!timer_pending(&ip6_fl_gc_timer) ||
 		    time_after(ip6_fl_gc_timer.expires, ttd))
 			mod_timer(&ip6_fl_gc_timer, ttd);
-- 
cgit v1.2.3


From c76fef7dcd9372e3476d4df5e0a72ed5919a814b Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 31 Mar 2026 23:10:20 +0200
Subject: bpf: Fix grace period wait for tracepoint bpf_link

Recently, tracepoints were switched from using disabled preemption
(which acts as RCU read section) to SRCU-fast when they are not
faultable. This means that to do a proper grace period wait for programs
running in such tracepoints, we must use SRCU's grace period wait.
This is only for non-faultable tracepoints, faultable ones continue
using RCU Tasks Trace.

However, bpf_link_free() currently does call_rcu() for all cases when
the link is non-sleepable (hence, for tracepoints, non-faultable). Fix
this by doing a call_srcu() grace period wait.

As far RCU Tasks Trace gp -> RCU gp chaining is concerned, it is deemed
unnecessary for tracepoint programs. The link and program are either
accessed under RCU Tasks Trace protection, or SRCU-fast protection now.

The earlier logic of chaining both RCU Tasks Trace and RCU gp waits was
to generalize the logic, even if it conceded an extra RCU gp wait,
however that is unnecessary for tracepoints even before this change.
In practice no cost was paid since rcu_trace_implies_rcu_gp() was always
true. Hence we need not chaining any RCU gp after the SRCU gp.

For instance, in the non-faultable raw tracepoint, the RCU read section
of the program in __bpf_trace_run() is enclosed in the SRCU gp, likewise
for faultable raw tracepoint, the program is under the RCU Tasks Trace
protection. Hence, the outermost scope can be waited upon to ensure
correctness.

Also, sleepable programs cannot be attached to non-faultable
tracepoints, so whenever program or link is sleepable, only RCU Tasks
Trace protection is being used for the link and prog.

Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast")
Reviewed-by: Sun Jian <sun.jian.kdev@gmail.com>
Reviewed-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20260331211021.1632902-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h        |  4 ++++
 include/linux/tracepoint.h | 20 ++++++++++++++++++++
 kernel/bpf/syscall.c       | 25 +++++++++++++++++++++++--
 3 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 05b34a6355b0..35b1e25bd104 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1854,6 +1854,10 @@ struct bpf_link_ops {
 	 * target hook is sleepable, we'll go through tasks trace RCU GP and
 	 * then "classic" RCU GP; this need for chaining tasks trace and
 	 * classic RCU GPs is designated by setting bpf_link->sleepable flag
+	 *
+	 * For non-sleepable tracepoint links we go through SRCU gp instead,
+	 * since RCU is not used in that case. Sleepable tracepoints still
+	 * follow the scheme above.
 	 */
 	void (*dealloc_deferred)(struct bpf_link *link);
 	int (*detach)(struct bpf_link *link);
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 22ca1c8b54f3..1d7f29f5e901 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -122,6 +122,22 @@ static inline bool tracepoint_is_faultable(struct tracepoint *tp)
 {
 	return tp->ext && tp->ext->faultable;
 }
+/*
+ * Run RCU callback with the appropriate grace period wait for non-faultable
+ * tracepoints, e.g., those used in atomic context.
+ */
+static inline void call_tracepoint_unregister_atomic(struct rcu_head *rcu, rcu_callback_t func)
+{
+	call_srcu(&tracepoint_srcu, rcu, func);
+}
+/*
+ * Run RCU callback with the appropriate grace period wait for faultable
+ * tracepoints, e.g., those used in syscall context.
+ */
+static inline void call_tracepoint_unregister_syscall(struct rcu_head *rcu, rcu_callback_t func)
+{
+	call_rcu_tasks_trace(rcu, func);
+}
 #else
 static inline void tracepoint_synchronize_unregister(void)
 { }
@@ -129,6 +145,10 @@ static inline bool tracepoint_is_faultable(struct tracepoint *tp)
 {
 	return false;
 }
+static inline void call_tracepoint_unregister_atomic(struct rcu_head *rcu, rcu_callback_t func)
+{  }
+static inline void call_tracepoint_unregister_syscall(struct rcu_head *rcu, rcu_callback_t func)
+{  }
 #endif
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 274039e36465..700938782bed 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3261,6 +3261,18 @@ static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
 	bpf_link_dealloc(link);
 }
 
+static bool bpf_link_is_tracepoint(struct bpf_link *link)
+{
+	/*
+	 * Only these combinations support a tracepoint bpf_link.
+	 * BPF_LINK_TYPE_TRACING raw_tp progs are hardcoded to use
+	 * bpf_raw_tp_link_lops and thus dealloc_deferred(), see
+	 * bpf_raw_tp_link_attach().
+	 */
+	return link->type == BPF_LINK_TYPE_RAW_TRACEPOINT ||
+	       (link->type == BPF_LINK_TYPE_TRACING && link->attach_type == BPF_TRACE_RAW_TP);
+}
+
 static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
 {
 	if (rcu_trace_implies_rcu_gp())
@@ -3279,16 +3291,25 @@ static void bpf_link_free(struct bpf_link *link)
 	if (link->prog)
 		ops->release(link);
 	if (ops->dealloc_deferred) {
-		/* Schedule BPF link deallocation, which will only then
+		/*
+		 * Schedule BPF link deallocation, which will only then
 		 * trigger putting BPF program refcount.
 		 * If underlying BPF program is sleepable or BPF link's target
 		 * attach hookpoint is sleepable or otherwise requires RCU GPs
 		 * to ensure link and its underlying BPF program is not
 		 * reachable anymore, we need to first wait for RCU tasks
-		 * trace sync, and then go through "classic" RCU grace period
+		 * trace sync, and then go through "classic" RCU grace period.
+		 *
+		 * For tracepoint BPF links, we need to go through SRCU grace
+		 * period wait instead when non-faultable tracepoint is used. We
+		 * don't need to chain SRCU grace period waits, however, for the
+		 * faultable case, since it exclusively uses RCU Tasks Trace.
 		 */
 		if (link->sleepable || (link->prog && link->prog->sleepable))
 			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+		/* We need to do a SRCU grace period wait for non-faultable tracepoint BPF links. */
+		else if (bpf_link_is_tracepoint(link))
+			call_tracepoint_unregister_atomic(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
 		else
 			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
 	} else if (ops->dealloc) {
-- 
cgit v1.2.3


From 78ec5bf2f589ec7fd8f169394bfeca541b077317 Mon Sep 17 00:00:00 2001
From: Fredric Cover <FredTheDude@proton.me>
Date: Mon, 30 Mar 2026 13:11:27 -0700
Subject: fs/smb/client: fix out-of-bounds read in cifs_sanitize_prepath

When cifs_sanitize_prepath is called with an empty string or a string
containing only delimiters (e.g., "/"), the current logic attempts to
check *(cursor2 - 1) before cursor2 has advanced. This results in an
out-of-bounds read.

This patch adds an early exit check after stripping prepended
delimiters. If no path content remains, the function returns NULL.

The bug was identified via manual audit and verified using a
standalone test case compiled with AddressSanitizer, which
triggered a SEGV on affected inputs.

Signed-off-by: Fredric Cover <FredTheDude@proton.me>
Reviewed-by: Henrique Carvalho <[2]henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index a4a7c7eee038..a46764c24710 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -588,6 +588,10 @@ char *cifs_sanitize_prepath(char *prepath, gfp_t gfp)
 	while (IS_DELIM(*cursor1))
 		cursor1++;
 
+	/* exit in case of only delimiters */
+	if (!*cursor1)
+		return NULL;
+
 	/* copy the first letter */
 	*cursor2 = *cursor1;
 
-- 
cgit v1.2.3


From 5dd8025a49c268ab6b94d978532af3ad341132a7 Mon Sep 17 00:00:00 2001
From: Li Xiasong <lixiasong1@huawei.com>
Date: Mon, 30 Mar 2026 20:03:35 +0800
Subject: mptcp: fix soft lockup in mptcp_recvmsg()

syzbot reported a soft lockup in mptcp_recvmsg() [0].

When receiving data with MSG_PEEK | MSG_WAITALL flags, the skb is not
removed from the sk_receive_queue. This causes sk_wait_data() to always
find available data and never perform actual waiting, leading to a soft
lockup.

Fix this by adding a 'last' parameter to track the last peeked skb.
This allows sk_wait_data() to make informed waiting decisions and prevent
infinite loops when MSG_PEEK is used.

[0]:
watchdog: BUG: soft lockup - CPU#2 stuck for 156s! [server:1963]
Modules linked in:
CPU: 2 UID: 0 PID: 1963 Comm: server Not tainted 6.19.0-rc8 #61 PREEMPT(none)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
RIP: 0010:sk_wait_data+0x15/0x190
Code: 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 41 56 41 55 41 54 49 89 f4 55 48 89 d5 53 48 89 fb <48> 83 ec 30 65 48 8b 05 17 a4 6b 01 48 89 44 24 28 31 c0 65 48 8b
RSP: 0018:ffffc90000603ca0 EFLAGS: 00000246
RAX: 0000000000000000 RBX: ffff888102bf0800 RCX: 0000000000000001
RDX: 0000000000000000 RSI: ffffc90000603d18 RDI: ffff888102bf0800
RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000101
R10: 0000000000000000 R11: 0000000000000075 R12: ffffc90000603d18
R13: ffff888102bf0800 R14: ffff888102bf0800 R15: 0000000000000000
FS:  00007f6e38b8c4c0(0000) GS:ffff8881b877e000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055aa7bff1680 CR3: 0000000105cbe000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 mptcp_recvmsg+0x547/0x8c0 net/mptcp/protocol.c:2329
 inet_recvmsg+0x11f/0x130 net/ipv4/af_inet.c:891
 sock_recvmsg+0x94/0xc0 net/socket.c:1100
 __sys_recvfrom+0xb2/0x130 net/socket.c:2256
 __x64_sys_recvfrom+0x1f/0x30 net/socket.c:2267
 do_syscall_64+0x59/0x2d0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e arch/x86/entry/entry_64.S:131
RIP: 0033:0x7f6e386a4a1d
Code: 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 8d 05 f1 de 2c 00 41 89 ca 8b 00 85 c0 75 20 45 31 c9 45 31 c0 b8 2d 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 6b f3 c3 66 0f 1f 84 00 00 00 00 00 41 56 41
RSP: 002b:00007ffc3c4bb078 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
RAX: ffffffffffffffda RBX: 000000000000861e RCX: 00007f6e386a4a1d
RDX: 00000000000003ff RSI: 00007ffc3c4bb150 RDI: 0000000000000004
RBP: 00007ffc3c4bb570 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000103 R11: 0000000000000246 R12: 00005605dbc00be0
R13: 00007ffc3c4bb650 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Fixes: 8e04ce45a8db ("mptcp: fix MSG_PEEK stream corruption")
Signed-off-by: Li Xiasong <lixiasong1@huawei.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260330120335.659027-1-lixiasong1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index cf1852b99963..65c3bb8016f4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2006,7 +2006,7 @@ static void mptcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 				size_t len, int flags, int copied_total,
 				struct scm_timestamping_internal *tss,
-				int *cmsg_flags)
+				int *cmsg_flags, struct sk_buff **last)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sk_buff *skb, *tmp;
@@ -2023,6 +2023,7 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 			/* skip already peeked skbs */
 			if (total_data_len + data_len <= copied_total) {
 				total_data_len += data_len;
+				*last = skb;
 				continue;
 			}
 
@@ -2058,6 +2059,8 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 			}
 
 			mptcp_eat_recv_skb(sk, skb);
+		} else {
+			*last = skb;
 		}
 
 		if (copied >= len)
@@ -2288,10 +2291,12 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		cmsg_flags = MPTCP_CMSG_INQ;
 
 	while (copied < len) {
+		struct sk_buff *last = NULL;
 		int err, bytes_read;
 
 		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags,
-						  copied, &tss, &cmsg_flags);
+						  copied, &tss, &cmsg_flags,
+						  &last);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
@@ -2343,7 +2348,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 		pr_debug("block timeout %ld\n", timeo);
 		mptcp_cleanup_rbuf(msk, copied);
-		err = sk_wait_data(sk, &timeo, NULL);
+		err = sk_wait_data(sk, &timeo, last);
 		if (err < 0) {
 			err = copied ? : err;
 			goto out_err;
-- 
cgit v1.2.3


From c0fd0fe745f5e8c568d898cd1513d0083e46204a Mon Sep 17 00:00:00 2001
From: Yufan Chen <yufan.chen@linux.dev>
Date: Sun, 29 Mar 2026 00:32:57 +0800
Subject: net: ftgmac100: fix ring allocation unwind on open failure

ftgmac100_alloc_rings() allocates rx_skbs, tx_skbs, rxdes, txdes, and
rx_scratch in stages. On intermediate failures it returned -ENOMEM
directly, leaking resources allocated earlier in the function.

Rework the failure path to use staged local unwind labels and free
allocated resources in reverse order before returning -ENOMEM. This
matches common netdev allocation cleanup style.

Fixes: d72e01a0430f ("ftgmac100: Use a scratch buffer for failed RX allocations")
Cc: stable@vger.kernel.org
Signed-off-by: Yufan Chen <yufan.chen@linux.dev>
Link: https://patch.msgid.link/20260328163257.60836-1-yufan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/faraday/ftgmac100.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 1e91e79c8134..6d2fe5c2f390 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -977,19 +977,19 @@ static int ftgmac100_alloc_rings(struct ftgmac100 *priv)
 	priv->tx_skbs = kcalloc(MAX_TX_QUEUE_ENTRIES, sizeof(void *),
 				GFP_KERNEL);
 	if (!priv->tx_skbs)
-		return -ENOMEM;
+		goto err_free_rx_skbs;
 
 	/* Allocate descriptors */
 	priv->rxdes = dma_alloc_coherent(priv->dev,
 					 MAX_RX_QUEUE_ENTRIES * sizeof(struct ftgmac100_rxdes),
 					 &priv->rxdes_dma, GFP_KERNEL);
 	if (!priv->rxdes)
-		return -ENOMEM;
+		goto err_free_tx_skbs;
 	priv->txdes = dma_alloc_coherent(priv->dev,
 					 MAX_TX_QUEUE_ENTRIES * sizeof(struct ftgmac100_txdes),
 					 &priv->txdes_dma, GFP_KERNEL);
 	if (!priv->txdes)
-		return -ENOMEM;
+		goto err_free_rxdes;
 
 	/* Allocate scratch packet buffer */
 	priv->rx_scratch = dma_alloc_coherent(priv->dev,
@@ -997,9 +997,29 @@ static int ftgmac100_alloc_rings(struct ftgmac100 *priv)
 					      &priv->rx_scratch_dma,
 					      GFP_KERNEL);
 	if (!priv->rx_scratch)
-		return -ENOMEM;
+		goto err_free_txdes;
 
 	return 0;
+
+err_free_txdes:
+	dma_free_coherent(priv->dev,
+			  MAX_TX_QUEUE_ENTRIES *
+			  sizeof(struct ftgmac100_txdes),
+			  priv->txdes, priv->txdes_dma);
+	priv->txdes = NULL;
+err_free_rxdes:
+	dma_free_coherent(priv->dev,
+			  MAX_RX_QUEUE_ENTRIES *
+			  sizeof(struct ftgmac100_rxdes),
+			  priv->rxdes, priv->rxdes_dma);
+	priv->rxdes = NULL;
+err_free_tx_skbs:
+	kfree(priv->tx_skbs);
+	priv->tx_skbs = NULL;
+err_free_rx_skbs:
+	kfree(priv->rx_skbs);
+	priv->rx_skbs = NULL;
+	return -ENOMEM;
 }
 
 static void ftgmac100_init_rings(struct ftgmac100 *priv)
-- 
cgit v1.2.3


From 48b3cd69265f346f64b93064723492da46206e9b Mon Sep 17 00:00:00 2001
From: Michal Piekos <michal.piekos@mmpsystems.pl>
Date: Sat, 28 Mar 2026 09:55:51 +0100
Subject: net: stmmac: skip VLAN restore when VLAN hash ops are missing

stmmac_vlan_restore() unconditionally calls stmmac_vlan_update() when
NETIF_F_VLAN_FEATURES is set. On platforms where priv->hw->vlan (or
->update_vlan_hash) is not provided, stmmac_update_vlan_hash() returns
-EINVAL via stmmac_do_void_callback(), resulting in a spurious
"Failed to restore VLANs" error even when no VLAN filtering is in use.

Remove not needed comment.
Remove not used return value from stmmac_vlan_restore().

Tested on Orange Pi Zero 3.

Fixes: bd7ad51253a7 ("net: stmmac: Fix VLAN HW state restore")
Signed-off-by: Michal Piekos <michal.piekos@mmpsystems.pl>
Link: https://patch.msgid.link/20260328-vlan-restore-error-v4-1-f88624c530dc@mmpsystems.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6827c99bde8c..13d3cac056be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -156,7 +156,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue);
 static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue);
 static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 					  u32 rxmode, u32 chan);
-static int stmmac_vlan_restore(struct stmmac_priv *priv);
+static void stmmac_vlan_restore(struct stmmac_priv *priv);
 
 #ifdef CONFIG_DEBUG_FS
 static const struct net_device_ops stmmac_netdev_ops;
@@ -6859,21 +6859,15 @@ del_vlan_error:
 	return ret;
 }
 
-static int stmmac_vlan_restore(struct stmmac_priv *priv)
+static void stmmac_vlan_restore(struct stmmac_priv *priv)
 {
-	int ret;
-
 	if (!(priv->dev->features & NETIF_F_VLAN_FEATURES))
-		return 0;
+		return;
 
 	if (priv->hw->num_vlan)
 		stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw);
 
-	ret = stmmac_vlan_update(priv, priv->num_double_vlans);
-	if (ret)
-		netdev_err(priv->dev, "Failed to restore VLANs\n");
-
-	return ret;
+	stmmac_vlan_update(priv, priv->num_double_vlans);
 }
 
 static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf)
-- 
cgit v1.2.3


From a0dafdbd1049a8ea661a1a471be1b840bd8aed13 Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Wed, 1 Apr 2026 16:01:27 +1030
Subject: ALSA: usb-audio: Exclude Scarlett 2i2 1st Gen (8016) from
 SKIP_IFACE_SETUP

Same issue as the other 1st Gen Scarletts: QUIRK_FLAG_SKIP_IFACE_SETUP
causes distorted audio on this revision of the Scarlett 2i2 1st Gen
(1235:8016).

Fixes: 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
Reported-by: lukas-reineke [https://github.com/geoffreybennett/linux-fcp/issues/54]
Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://patch.msgid.link/acytr8aEUba4VXmZ@m.b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 116da076a194..4cfa24c06fcd 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2435,6 +2435,7 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_VALIDATE_RATES),
 	DEVICE_FLG(0x1235, 0x8006, 0), /* Focusrite Scarlett 2i2 1st Gen */
 	DEVICE_FLG(0x1235, 0x800a, 0), /* Focusrite Scarlett 2i4 1st Gen */
+	DEVICE_FLG(0x1235, 0x8016, 0), /* Focusrite Scarlett 2i2 1st Gen */
 	DEVICE_FLG(0x1235, 0x801c, 0), /* Focusrite Scarlett Solo 1st Gen */
 	VENDOR_FLG(0x1235, /* Focusrite Novation */
 		   QUIRK_FLAG_SKIP_CLOCK_SELECTOR |
-- 
cgit v1.2.3


From 8c0ef7b56d6bbbc53f2d43d99c195144f01b0775 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 11 Mar 2026 22:14:00 -0700
Subject: lis3lv02d: fix kernel-doc warnings

Use the correct kernel-doc format to avoid kernel-doc warnings:

Warning: include/linux/lis3lv02d.h:125 struct member 'st_min_limits' not
 described in 'lis3lv02d_platform_data'
Warning: include/linux/lis3lv02d.h:125 struct member 'st_max_limits' not
 described in 'lis3lv02d_platform_data'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20260312051400.682991-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/lis3lv02d.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h
index b72b8cdba765..feb60ba4e30e 100644
--- a/include/linux/lis3lv02d.h
+++ b/include/linux/lis3lv02d.h
@@ -30,8 +30,8 @@
  * @default_rate:	Default sampling rate. 0 means reset default
  * @setup_resources:	Interrupt line setup call back function
  * @release_resources:	Interrupt line release call back function
- * @st_min_limits[3]:	Selftest acceptance minimum values
- * @st_max_limits[3]:	Selftest acceptance maximum values
+ * @st_min_limits:	Selftest acceptance minimum values (x, y, z)
+ * @st_max_limits:	Selftest acceptance maximum values (x, y, z)
  * @irq2:		Irq line 2 number
  *
  * Platform data is used to setup the sensor chip. Meaning of the different
-- 
cgit v1.2.3


From f40b1401b6ad0f4dadfca4e7a69744352a2e4f8f Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 26 Mar 2026 19:04:36 +0100
Subject: lis3lv02d: Omit IRQF_ONESHOT if no threaded handler is provided

The lis3lv02d started triggering a WARN in the IRQ code because it
passes IRQF_ONESHOT to request_threaded_irq() even when thread_fn is
NULL, which is an invalid combination.

So set the flag only if thread_fn is non-NULL.

Cc: Eric Piel <eric.piel@tremplin-utc.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://patch.msgid.link/20260326180436.14968-2-ardb@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/lis3lv02d/lis3lv02d.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c
index 9c68f8b1d5d6..21e8ad0a7444 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d.c
@@ -1230,10 +1230,12 @@ int lis3lv02d_init_device(struct lis3lv02d *lis3)
 	else
 		thread_fn = NULL;
 
+	if (thread_fn)
+		irq_flags |= IRQF_ONESHOT;
+
 	err = request_threaded_irq(lis3->irq, lis302dl_interrupt,
 				thread_fn,
-				IRQF_TRIGGER_RISING | IRQF_ONESHOT |
-				irq_flags,
+				irq_flags | IRQF_TRIGGER_RISING,
 				DRIVER_NAME, lis3);
 
 	if (err < 0) {
-- 
cgit v1.2.3


From e8d0ed37bd51da52da6225d278e330c2f18a6198 Mon Sep 17 00:00:00 2001
From: Ernestas Kulik <ernestas.k@iconn-networks.com>
Date: Tue, 24 Mar 2026 13:07:16 +0200
Subject: USB: serial: option: add MeiG Smart SRM825WN

Add support for the SDX62-based MeiG Smart SRM825WN module.

If#= 0: RNDIS
If#= 1: RNDIS
If#= 2: Diag
If#= 3: AT
If#= 4: AT
If#= 5: NMEA

T:  Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#= 19 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2dee ProdID=4d38 Rev= 5.04
S:  Manufacturer=MEIG
S:  Product=LTE-A Module
S:  SerialNumber=da47a175
C:* #Ifs= 6 Cfg#= 1 Atr=80 MxPwr=500mA
A:  FirstIf#= 0 IfCount= 2 Cls=e0(wlcon) Sub=01 Prot=03
I:* If#= 0 Alt= 0 #EPs= 1 Cls=e0(wlcon) Sub=01 Prot=03 Driver=rndis_host
E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Ernestas Kulik <ernestas.k@iconn-networks.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index d222bf2c2539..313612114db9 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2441,6 +2441,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x30) },	/* MeiG Smart SRM815 and SRM825L */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x40) },	/* MeiG Smart SRM825L */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x60) },	/* MeiG Smart SRM825L */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x30) },	/* MeiG Smart SRM825WN (Diag) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x40) },	/* MeiG Smart SRM825WN (AT) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x60) },	/* MeiG Smart SRM825WN (NMEA) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
-- 
cgit v1.2.3


From 76522fcdbc3a02b568f5d957f7e66fc194abb893 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 26 Mar 2026 00:17:09 +0100
Subject: netfilter: flowtable: strictly check for maximum number of actions

The maximum number of flowtable hardware offload actions in IPv6 is:

* ethernet mangling (4 payload actions, 2 for each ethernet address)
* SNAT (4 payload actions)
* DNAT (4 payload actions)
* Double VLAN (4 vlan actions, 2 for popping vlan, and 2 for pushing)
  for QinQ.
* Redirect (1 action)

Which makes 17, while the maximum is 16. But act_ct supports for tunnels
actions too. Note that payload action operates at 32-bit word level, so
mangling an IPv6 address takes 4 payload actions.

Update flow_action_entry_next() calls to check for the maximum number of
supported actions.

While at it, rise the maximum number of actions per flow from 16 to 24
so this works fine with IPv6 setups.

Fixes: c29f74e0df7a ("netfilter: nf_flow_table: hardware offload support")
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_offload.c | 196 ++++++++++++++++++++++------------
 1 file changed, 130 insertions(+), 66 deletions(-)

diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 9b677e116487..93d0aa7f8fcc 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -14,6 +14,8 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 
+#define NF_FLOW_RULE_ACTION_MAX	24
+
 static struct workqueue_struct *nf_flow_offload_add_wq;
 static struct workqueue_struct *nf_flow_offload_del_wq;
 static struct workqueue_struct *nf_flow_offload_stats_wq;
@@ -216,7 +218,12 @@ static void flow_offload_mangle(struct flow_action_entry *entry,
 static inline struct flow_action_entry *
 flow_action_entry_next(struct nf_flow_rule *flow_rule)
 {
-	int i = flow_rule->rule->action.num_entries++;
+	int i;
+
+	if (unlikely(flow_rule->rule->action.num_entries >= NF_FLOW_RULE_ACTION_MAX))
+		return NULL;
+
+	i = flow_rule->rule->action.num_entries++;
 
 	return &flow_rule->rule->action.entries[i];
 }
@@ -234,6 +241,9 @@ static int flow_offload_eth_src(struct net *net,
 	u32 mask, val;
 	u16 val16;
 
+	if (!entry0 || !entry1)
+		return -E2BIG;
+
 	this_tuple = &flow->tuplehash[dir].tuple;
 
 	switch (this_tuple->xmit_type) {
@@ -284,6 +294,9 @@ static int flow_offload_eth_dst(struct net *net,
 	u8 nud_state;
 	u16 val16;
 
+	if (!entry0 || !entry1)
+		return -E2BIG;
+
 	this_tuple = &flow->tuplehash[dir].tuple;
 
 	switch (this_tuple->xmit_type) {
@@ -325,16 +338,19 @@ static int flow_offload_eth_dst(struct net *net,
 	return 0;
 }
 
-static void flow_offload_ipv4_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask = ~htonl(0xffffffff);
 	__be32 addr;
 	u32 offset;
 
+	if (!entry)
+		return -E2BIG;
+
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
 		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
@@ -345,23 +361,27 @@ static void flow_offload_ipv4_snat(struct net *net,
 		offset = offsetof(struct iphdr, daddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
 			    &addr, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv4_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask = ~htonl(0xffffffff);
 	__be32 addr;
 	u32 offset;
 
+	if (!entry)
+		return -E2BIG;
+
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
 		addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
@@ -372,14 +392,15 @@ static void flow_offload_ipv4_dnat(struct net *net,
 		offset = offsetof(struct iphdr, saddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset,
 			    &addr, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
+static int flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
 				     unsigned int offset,
 				     const __be32 *addr, const __be32 *mask)
 {
@@ -388,15 +409,20 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule,
 
 	for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) {
 		entry = flow_action_entry_next(flow_rule);
+		if (!entry)
+			return -E2BIG;
+
 		flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
 				    offset + i * sizeof(u32), &addr[i], mask);
 	}
+
+	return 0;
 }
 
-static void flow_offload_ipv6_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv6_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	u32 mask = ~htonl(0xffffffff);
 	const __be32 *addr;
@@ -412,16 +438,16 @@ static void flow_offload_ipv6_snat(struct net *net,
 		offset = offsetof(struct ipv6hdr, daddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+	return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
 }
 
-static void flow_offload_ipv6_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv6_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	u32 mask = ~htonl(0xffffffff);
 	const __be32 *addr;
@@ -437,10 +463,10 @@ static void flow_offload_ipv6_dnat(struct net *net,
 		offset = offsetof(struct ipv6hdr, saddr);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
+	return flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask);
 }
 
 static int flow_offload_l4proto(const struct flow_offload *flow)
@@ -462,15 +488,18 @@ static int flow_offload_l4proto(const struct flow_offload *flow)
 	return type;
 }
 
-static void flow_offload_port_snat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_port_snat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask, port;
 	u32 offset;
 
+	if (!entry)
+		return -E2BIG;
+
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
 		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port);
@@ -485,22 +514,26 @@ static void flow_offload_port_snat(struct net *net,
 		mask = ~htonl(0xffff);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
 			    &port, &mask);
+	return 0;
 }
 
-static void flow_offload_port_dnat(struct net *net,
-				   const struct flow_offload *flow,
-				   enum flow_offload_tuple_dir dir,
-				   struct nf_flow_rule *flow_rule)
+static int flow_offload_port_dnat(struct net *net,
+				  const struct flow_offload *flow,
+				  enum flow_offload_tuple_dir dir,
+				  struct nf_flow_rule *flow_rule)
 {
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 	u32 mask, port;
 	u32 offset;
 
+	if (!entry)
+		return -E2BIG;
+
 	switch (dir) {
 	case FLOW_OFFLOAD_DIR_ORIGINAL:
 		port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port);
@@ -515,20 +548,24 @@ static void flow_offload_port_dnat(struct net *net,
 		mask = ~htonl(0xffff0000);
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	flow_offload_mangle(entry, flow_offload_l4proto(flow), offset,
 			    &port, &mask);
+	return 0;
 }
 
-static void flow_offload_ipv4_checksum(struct net *net,
-				       const struct flow_offload *flow,
-				       struct nf_flow_rule *flow_rule)
+static int flow_offload_ipv4_checksum(struct net *net,
+				      const struct flow_offload *flow,
+				      struct nf_flow_rule *flow_rule)
 {
 	u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto;
 	struct flow_action_entry *entry = flow_action_entry_next(flow_rule);
 
+	if (!entry)
+		return -E2BIG;
+
 	entry->id = FLOW_ACTION_CSUM;
 	entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR;
 
@@ -540,12 +577,14 @@ static void flow_offload_ipv4_checksum(struct net *net,
 		entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP;
 		break;
 	}
+
+	return 0;
 }
 
-static void flow_offload_redirect(struct net *net,
-				  const struct flow_offload *flow,
-				  enum flow_offload_tuple_dir dir,
-				  struct nf_flow_rule *flow_rule)
+static int flow_offload_redirect(struct net *net,
+				 const struct flow_offload *flow,
+				 enum flow_offload_tuple_dir dir,
+				 struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *this_tuple, *other_tuple;
 	struct flow_action_entry *entry;
@@ -563,21 +602,28 @@ static void flow_offload_redirect(struct net *net,
 		ifindex = other_tuple->iifidx;
 		break;
 	default:
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	dev = dev_get_by_index(net, ifindex);
 	if (!dev)
-		return;
+		return -ENODEV;
 
 	entry = flow_action_entry_next(flow_rule);
+	if (!entry) {
+		dev_put(dev);
+		return -E2BIG;
+	}
+
 	entry->id = FLOW_ACTION_REDIRECT;
 	entry->dev = dev;
+
+	return 0;
 }
 
-static void flow_offload_encap_tunnel(const struct flow_offload *flow,
-				      enum flow_offload_tuple_dir dir,
-				      struct nf_flow_rule *flow_rule)
+static int flow_offload_encap_tunnel(const struct flow_offload *flow,
+				     enum flow_offload_tuple_dir dir,
+				     struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *this_tuple;
 	struct flow_action_entry *entry;
@@ -585,7 +631,7 @@ static void flow_offload_encap_tunnel(const struct flow_offload *flow,
 
 	this_tuple = &flow->tuplehash[dir].tuple;
 	if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
-		return;
+		return 0;
 
 	dst = this_tuple->dst_cache;
 	if (dst && dst->lwtstate) {
@@ -594,15 +640,19 @@ static void flow_offload_encap_tunnel(const struct flow_offload *flow,
 		tun_info = lwt_tun_info(dst->lwtstate);
 		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -E2BIG;
 			entry->id = FLOW_ACTION_TUNNEL_ENCAP;
 			entry->tunnel = tun_info;
 		}
 	}
+
+	return 0;
 }
 
-static void flow_offload_decap_tunnel(const struct flow_offload *flow,
-				      enum flow_offload_tuple_dir dir,
-				      struct nf_flow_rule *flow_rule)
+static int flow_offload_decap_tunnel(const struct flow_offload *flow,
+				     enum flow_offload_tuple_dir dir,
+				     struct nf_flow_rule *flow_rule)
 {
 	const struct flow_offload_tuple *other_tuple;
 	struct flow_action_entry *entry;
@@ -610,7 +660,7 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow,
 
 	other_tuple = &flow->tuplehash[!dir].tuple;
 	if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT)
-		return;
+		return 0;
 
 	dst = other_tuple->dst_cache;
 	if (dst && dst->lwtstate) {
@@ -619,9 +669,13 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow,
 		tun_info = lwt_tun_info(dst->lwtstate);
 		if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -E2BIG;
 			entry->id = FLOW_ACTION_TUNNEL_DECAP;
 		}
 	}
+
+	return 0;
 }
 
 static int
@@ -633,8 +687,9 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow,
 	const struct flow_offload_tuple *tuple;
 	int i;
 
-	flow_offload_decap_tunnel(flow, dir, flow_rule);
-	flow_offload_encap_tunnel(flow, dir, flow_rule);
+	if (flow_offload_decap_tunnel(flow, dir, flow_rule) < 0 ||
+	    flow_offload_encap_tunnel(flow, dir, flow_rule) < 0)
+		return -1;
 
 	if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 ||
 	    flow_offload_eth_dst(net, flow, dir, flow_rule) < 0)
@@ -650,6 +705,8 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow,
 
 		if (tuple->encap[i].proto == htons(ETH_P_8021Q)) {
 			entry = flow_action_entry_next(flow_rule);
+			if (!entry)
+				return -1;
 			entry->id = FLOW_ACTION_VLAN_POP;
 		}
 	}
@@ -663,6 +720,8 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow,
 			continue;
 
 		entry = flow_action_entry_next(flow_rule);
+		if (!entry)
+			return -1;
 
 		switch (other_tuple->encap[i].proto) {
 		case htons(ETH_P_PPP_SES):
@@ -688,18 +747,22 @@ int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow,
 		return -1;
 
 	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
-		flow_offload_ipv4_snat(net, flow, dir, flow_rule);
-		flow_offload_port_snat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv4_snat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_snat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
-		flow_offload_ipv4_dnat(net, flow, dir, flow_rule);
-		flow_offload_port_dnat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv4_dnat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_dnat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_SNAT, &flow->flags) ||
 	    test_bit(NF_FLOW_DNAT, &flow->flags))
-		flow_offload_ipv4_checksum(net, flow, flow_rule);
+		if (flow_offload_ipv4_checksum(net, flow, flow_rule) < 0)
+			return -1;
 
-	flow_offload_redirect(net, flow, dir, flow_rule);
+	if (flow_offload_redirect(net, flow, dir, flow_rule) < 0)
+		return -1;
 
 	return 0;
 }
@@ -713,22 +776,23 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow,
 		return -1;
 
 	if (test_bit(NF_FLOW_SNAT, &flow->flags)) {
-		flow_offload_ipv6_snat(net, flow, dir, flow_rule);
-		flow_offload_port_snat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv6_snat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_snat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 	if (test_bit(NF_FLOW_DNAT, &flow->flags)) {
-		flow_offload_ipv6_dnat(net, flow, dir, flow_rule);
-		flow_offload_port_dnat(net, flow, dir, flow_rule);
+		if (flow_offload_ipv6_dnat(net, flow, dir, flow_rule) < 0 ||
+		    flow_offload_port_dnat(net, flow, dir, flow_rule) < 0)
+			return -1;
 	}
 
-	flow_offload_redirect(net, flow, dir, flow_rule);
+	if (flow_offload_redirect(net, flow, dir, flow_rule) < 0)
+		return -1;
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv6);
 
-#define NF_FLOW_RULE_ACTION_MAX	16
-
 static struct nf_flow_rule *
 nf_flow_offload_rule_alloc(struct net *net,
 			   const struct flow_offload_work *offload,
-- 
cgit v1.2.3


From 6d52a4a0520a6696bdde51caa11f2d6821cd0c01 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 26 Mar 2026 16:17:24 +0100
Subject: netfilter: nfnetlink_log: account for netlink header size

This is a followup to an old bug fix: NLMSG_DONE needs to account
for the netlink header size, not just the attribute size.

This can result in a WARN splat + drop of the netlink message,
but other than this there are no ill effects.

Fixes: 9dfa1dfe4d5e ("netfilter: nf_log: account for size of NLMSG_DONE attribute")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index fcbe54940b2e..f80978c06fa0 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -726,7 +726,7 @@ nfulnl_log_packet(struct net *net,
 		+ nla_total_size(plen)			/* prefix */
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
 		+ nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
-		+ nla_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
+		+ nlmsg_total_size(sizeof(struct nfgenmsg));	/* NLMSG_DONE */
 
 	if (in && skb_mac_header_was_set(skb)) {
 		size += nla_total_size(skb->dev->hard_header_len)
-- 
cgit v1.2.3


From a958a4f90ddd7de0800b33ca9d7b886b7d40f74e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 31 Mar 2026 23:13:36 +0200
Subject: netfilter: x_tables: ensure names are nul-terminated

Reject names that lack a \0 character before feeding them
to functions that expect c-strings.

Fixes tag is the most recent commit that needs this change.

Fixes: c38c4597e4bf ("netfilter: implement xt_cgroup cgroup2 path match")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_cgroup.c  | 6 ++++++
 net/netfilter/xt_rateest.c | 5 +++++
 2 files changed, 11 insertions(+)

diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index c437fbd59ec1..43d2ae2be628 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -65,6 +65,9 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par)
 
 	info->priv = NULL;
 	if (info->has_path) {
+		if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path))
+			return -ENAMETOOLONG;
+
 		cgrp = cgroup_get_from_path(info->path);
 		if (IS_ERR(cgrp)) {
 			pr_info_ratelimited("invalid path, errno=%ld\n",
@@ -102,6 +105,9 @@ static int cgroup_mt_check_v2(const struct xt_mtchk_param *par)
 
 	info->priv = NULL;
 	if (info->has_path) {
+		if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path))
+			return -ENAMETOOLONG;
+
 		cgrp = cgroup_get_from_path(info->path);
 		if (IS_ERR(cgrp)) {
 			pr_info_ratelimited("invalid path, errno=%ld\n",
diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c
index 72324bd976af..b1d736c15fcb 100644
--- a/net/netfilter/xt_rateest.c
+++ b/net/netfilter/xt_rateest.c
@@ -91,6 +91,11 @@ static int xt_rateest_mt_checkentry(const struct xt_mtchk_param *par)
 		goto err1;
 	}
 
+	if (strnlen(info->name1, sizeof(info->name1)) >= sizeof(info->name1))
+		return -ENAMETOOLONG;
+	if (strnlen(info->name2, sizeof(info->name2)) >= sizeof(info->name2))
+		return -ENAMETOOLONG;
+
 	ret  = -ENOENT;
 	est1 = xt_rateest_lookup(par->net, info->name1);
 	if (!est1)
-- 
cgit v1.2.3


From b7e8590987aa94c9dc51518fad0e58cb887b1db5 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 30 Mar 2026 14:16:34 +0200
Subject: netfilter: ipset: use nla_strcmp for IPSET_ATTR_NAME attr

IPSET_ATTR_NAME and IPSET_ATTR_NAMEREF are of NLA_STRING type, they
cannot be treated like a c-string.

They either have to be switched to NLA_NUL_STRING, or the compare
operations need to use the nla functions.

Fixes: f830837f0eed ("netfilter: ipset: list:set set type support")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set.h | 2 +-
 net/netfilter/ipset/ip_set_core.c      | 4 ++--
 net/netfilter/ipset/ip_set_list_set.c  | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index e9f4f845d760..b98331572ad2 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -309,7 +309,7 @@ enum {
 
 /* register and unregister set references */
 extern ip_set_id_t ip_set_get_byname(struct net *net,
-				     const char *name, struct ip_set **set);
+				     const struct nlattr *name, struct ip_set **set);
 extern void ip_set_put_byindex(struct net *net, ip_set_id_t index);
 extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name);
 extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index a2fe711cb5e3..d0c9fe59c67d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -821,7 +821,7 @@ EXPORT_SYMBOL_GPL(ip_set_del);
  *
  */
 ip_set_id_t
-ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
+ip_set_get_byname(struct net *net, const struct nlattr *name, struct ip_set **set)
 {
 	ip_set_id_t i, index = IPSET_INVALID_ID;
 	struct ip_set *s;
@@ -830,7 +830,7 @@ ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
 	rcu_read_lock();
 	for (i = 0; i < inst->ip_set_max; i++) {
 		s = rcu_dereference(inst->ip_set_list)[i];
-		if (s && STRNCMP(s->name, name)) {
+		if (s && nla_strcmp(name, s->name) == 0) {
 			__ip_set_get(s);
 			index = i;
 			*set = s;
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 98b91b34c314..1cef84f15e8c 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -367,7 +367,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 	ret = ip_set_get_extensions(set, tb, &ext);
 	if (ret)
 		return ret;
-	e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s);
+	e.id = ip_set_get_byname(map->net, tb[IPSET_ATTR_NAME], &s);
 	if (e.id == IPSET_INVALID_ID)
 		return -IPSET_ERR_NAME;
 	/* "Loop detection" */
@@ -389,7 +389,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_NAMEREF]) {
 		e.refid = ip_set_get_byname(map->net,
-					    nla_data(tb[IPSET_ATTR_NAMEREF]),
+					    tb[IPSET_ATTR_NAMEREF],
 					    &s);
 		if (e.refid == IPSET_INVALID_ID) {
 			ret = -IPSET_ERR_NAMEREF;
-- 
cgit v1.2.3


From a242a9ae58aa46ff7dae51ce64150a93957abe65 Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Mon, 30 Mar 2026 00:50:36 +0800
Subject: netfilter: nf_conntrack_helper: pass helper to expect cleanup

nf_conntrack_helper_unregister() calls nf_ct_expect_iterate_destroy()
to remove expectations belonging to the helper being unregistered.
However, it passes NULL instead of the helper pointer as the data
argument, so expect_iter_me() never matches any expectation and all
of them survive the cleanup.

After unregister returns, nfnl_cthelper_del() frees the helper
object immediately.  Subsequent expectation dumps or packet-driven
init_conntrack() calls then dereference the freed exp->helper,
causing a use-after-free.

Pass the actual helper pointer so expectations referencing it are
properly destroyed before the helper object is freed.

  BUG: KASAN: slab-use-after-free in string+0x38f/0x430
  Read of size 1 at addr ffff888003b14d20 by task poc/103
  Call Trace:
   string+0x38f/0x430
   vsnprintf+0x3cc/0x1170
   seq_printf+0x17a/0x240
   exp_seq_show+0x2e5/0x560
   seq_read_iter+0x419/0x1280
   proc_reg_read+0x1ac/0x270
   vfs_read+0x179/0x930
   ksys_read+0xef/0x1c0
  Freed by task 103:
  The buggy address is located 32 bytes inside of
   freed 192-byte region [ffff888003b14d00, ffff888003b14dc0)

Fixes: ac7b84839003 ("netfilter: expect: add and use nf_ct_expect_iterate helpers")
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Reviewed-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 1b330ba6613b..a715304a53d8 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -415,7 +415,7 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 	 */
 	synchronize_rcu();
 
-	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
+	nf_ct_expect_iterate_destroy(expect_iter_me, me);
 	nf_ct_iterate_destroy(unhelp, me);
 
 	/* nf_ct_iterate_destroy() does an unconditional synchronize_rcu() as
-- 
cgit v1.2.3


From 35177c6877134a21315f37d57a5577846225623e Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Tue, 31 Mar 2026 14:17:12 +0800
Subject: netfilter: ctnetlink: zero expect NAT fields when CTA_EXPECT_NAT
 absent

ctnetlink_alloc_expect() allocates expectations from a non-zeroing
slab cache via nf_ct_expect_alloc().  When CTA_EXPECT_NAT is not
present in the netlink message, saved_addr and saved_proto are
never initialized.  Stale data from a previous slab occupant can
then be dumped to userspace by ctnetlink_exp_dump_expect(), which
checks these fields to decide whether to emit CTA_EXPECT_NAT.

The safe sibling nf_ct_expect_init(), used by the packet path,
explicitly zeroes these fields.

Zero saved_addr, saved_proto and dir in the else branch, guarded
by IS_ENABLED(CONFIG_NF_NAT) since these fields only exist when
NAT is enabled.

Confirmed by priming the expect slab with NAT-bearing expectations,
freeing them, creating a new expectation without CTA_EXPECT_NAT,
and observing that the ctnetlink dump emits a spurious
CTA_EXPECT_NAT containing stale data from the prior allocation.

Fixes: 076a0ca02644 ("netfilter: ctnetlink: add NAT support for expectations")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 3f408f3713bb..38bd7124d9f7 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -3588,6 +3588,12 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 						 exp, nf_ct_l3num(ct));
 		if (err < 0)
 			goto err_out;
+#if IS_ENABLED(CONFIG_NF_NAT)
+	} else {
+		memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
+		memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
+		exp->dir = 0;
+#endif
 	}
 	return exp;
 err_out:
-- 
cgit v1.2.3


From 917b61fa2042f11e2af4c428e43f08199586633a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 30 Mar 2026 11:26:22 +0200
Subject: netfilter: ctnetlink: ignore explicit helper on new expectations

Use the existing master conntrack helper, anything else is not really
supported and it just makes validation more complicated, so just ignore
what helper userspace suggests for this expectation.

This was uncovered when validating CTA_EXPECT_CLASS via different helper
provided by userspace than the existing master conntrack helper:

  BUG: KASAN: slab-out-of-bounds in nf_ct_expect_related_report+0x2479/0x27c0
  Read of size 4 at addr ffff8880043fe408 by task poc/102
  Call Trace:
   nf_ct_expect_related_report+0x2479/0x27c0
   ctnetlink_create_expect+0x22b/0x3b0
   ctnetlink_new_expect+0x4bd/0x5c0
   nfnetlink_rcv_msg+0x67a/0x950
   netlink_rcv_skb+0x120/0x350

Allowing to read kernel memory bytes off the expectation boundary.

CTA_EXPECT_HELP_NAME is still used to offer the helper name to userspace
via netlink dump.

Fixes: bd0779370588 ("netfilter: nfnetlink_queue: allow to attach expectations to conntracks")
Reported-by: Qi Tang <tpluszz77@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c | 54 ++++++------------------------------
 1 file changed, 9 insertions(+), 45 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 38bd7124d9f7..a20cd82446c5 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2636,7 +2636,6 @@ static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
-		       struct nf_conntrack_helper *helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask);
 
@@ -2865,7 +2864,6 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 {
 	struct nlattr *cda[CTA_EXPECT_MAX+1];
 	struct nf_conntrack_tuple tuple, mask;
-	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conntrack_expect *exp;
 	int err;
 
@@ -2879,17 +2877,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 	if (err < 0)
 		return err;
 
-	if (cda[CTA_EXPECT_HELP_NAME]) {
-		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
-
-		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
-						    nf_ct_protonum(ct));
-		if (helper == NULL)
-			return -EOPNOTSUPP;
-	}
-
 	exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct,
-				     helper, &tuple, &mask);
+				     &tuple, &mask);
 	if (IS_ERR(exp))
 		return PTR_ERR(exp);
 
@@ -3528,11 +3517,11 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 
 static struct nf_conntrack_expect *
 ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
-		       struct nf_conntrack_helper *helper,
 		       struct nf_conntrack_tuple *tuple,
 		       struct nf_conntrack_tuple *mask)
 {
 	struct net *net = read_pnet(&ct->ct_net);
+	struct nf_conntrack_helper *helper;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn_help *help;
 	u32 class = 0;
@@ -3542,7 +3531,11 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 	if (!help)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	if (cda[CTA_EXPECT_CLASS] && helper) {
+	helper = rcu_dereference(help->helper);
+	if (!helper)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (cda[CTA_EXPECT_CLASS]) {
 		class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS]));
 		if (class > helper->expect_class_max)
 			return ERR_PTR(-EINVAL);
@@ -3576,8 +3569,6 @@ ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	exp->zone = ct->zone;
 #endif
-	if (!helper)
-		helper = rcu_dereference(help->helper);
 	rcu_assign_pointer(exp->helper, helper);
 	exp->tuple = *tuple;
 	exp->mask.src.u3 = mask->src.u3;
@@ -3609,7 +3600,6 @@ ctnetlink_create_expect(struct net *net,
 {
 	struct nf_conntrack_tuple tuple, mask, master_tuple;
 	struct nf_conntrack_tuple_hash *h = NULL;
-	struct nf_conntrack_helper *helper = NULL;
 	struct nf_conntrack_expect *exp;
 	struct nf_conn *ct;
 	int err;
@@ -3635,33 +3625,7 @@ ctnetlink_create_expect(struct net *net,
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	rcu_read_lock();
-	if (cda[CTA_EXPECT_HELP_NAME]) {
-		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
-
-		helper = __nf_conntrack_helper_find(helpname, u3,
-						    nf_ct_protonum(ct));
-		if (helper == NULL) {
-			rcu_read_unlock();
-#ifdef CONFIG_MODULES
-			if (request_module("nfct-helper-%s", helpname) < 0) {
-				err = -EOPNOTSUPP;
-				goto err_ct;
-			}
-			rcu_read_lock();
-			helper = __nf_conntrack_helper_find(helpname, u3,
-							    nf_ct_protonum(ct));
-			if (helper) {
-				err = -EAGAIN;
-				goto err_rcu;
-			}
-			rcu_read_unlock();
-#endif
-			err = -EOPNOTSUPP;
-			goto err_ct;
-		}
-	}
-
-	exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
+	exp = ctnetlink_alloc_expect(cda, ct, &tuple, &mask);
 	if (IS_ERR(exp)) {
 		err = PTR_ERR(exp);
 		goto err_rcu;
@@ -3671,8 +3635,8 @@ ctnetlink_create_expect(struct net *net,
 	nf_ct_expect_put(exp);
 err_rcu:
 	rcu_read_unlock();
-err_ct:
 	nf_ct_put(ct);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 9862ef9ab0a116c6dca98842aab7de13a252ae02 Mon Sep 17 00:00:00 2001
From: Yifan Wu <yifanwucs@gmail.com>
Date: Mon, 30 Mar 2026 14:39:24 -0700
Subject: netfilter: ipset: drop logically empty buckets in mtype_del

mtype_del() counts empty slots below n->pos in k, but it only drops the
bucket when both n->pos and k are zero. This misses buckets whose live
entries have all been removed while n->pos still points past deleted slots.

Treat a bucket as empty when all positions below n->pos are unused and
release it directly instead of shrinking it further.

Fixes: 8af1c6fbd923 ("netfilter: ipset: Fix forceadd evaluation path")
Cc: stable@vger.kernel.org
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Reported-by: Xin Liu <dstsmallbird@foxmail.com>
Signed-off-by: Yifan Wu <yifanwucs@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Reviewed-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipset/ip_set_hash_gen.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 181daa9c2019..b79e5dd2af03 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1098,7 +1098,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 			if (!test_bit(i, n->used))
 				k++;
 		}
-		if (n->pos == 0 && k == 0) {
+		if (k == n->pos) {
 			t->hregion[r].ext_size -= ext_size(n->size, dsize);
 			rcu_assign_pointer(hbucket(t, key), NULL);
 			kfree_rcu(n, rcu);
-- 
cgit v1.2.3


From 3d5d488f11776738deab9da336038add95d342d1 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 31 Mar 2026 16:41:25 +0200
Subject: netfilter: x_tables: restrict xt_check_match/xt_check_target
 extensions for NFPROTO_ARP

Weiming Shi says:

xt_match and xt_target structs registered with NFPROTO_UNSPEC can be
loaded by any protocol family through nft_compat. When such a
match/target sets .hooks to restrict which hooks it may run on, the
bitmask uses NF_INET_* constants. This is only correct for families
whose hook layout matches NF_INET_*: IPv4, IPv6, INET, and bridge
all share the same five hooks (PRE_ROUTING ... POST_ROUTING).

ARP only has three hooks (IN=0, OUT=1, FORWARD=2) with different
semantics. Because NF_ARP_OUT == 1 == NF_INET_LOCAL_IN, the .hooks
validation silently passes for the wrong reasons, allowing matches to
run on ARP chains where the hook assumptions (e.g. state->in being
set on input hooks) do not hold. This leads to NULL pointer
dereferences; xt_devgroup is one concrete example:

 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000044: 0000 [#1] SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000220-0x0000000000000227]
 RIP: 0010:devgroup_mt+0xff/0x350
 Call Trace:
  <TASK>
  nft_match_eval (net/netfilter/nft_compat.c:407)
  nft_do_chain (net/netfilter/nf_tables_core.c:285)
  nft_do_chain_arp (net/netfilter/nft_chain_filter.c:61)
  nf_hook_slow (net/netfilter/core.c:623)
  arp_xmit (net/ipv4/arp.c:666)
  </TASK>
 Kernel panic - not syncing: Fatal exception in interrupt

Fix it by restricting arptables to NFPROTO_ARP extensions only.
Note that arptables-legacy only supports:

- arpt_CLASSIFY
- arpt_mangle
- arpt_MARK

that provide explicit NFPROTO_ARP match/target declarations.

Fixes: 9291747f118d ("netfilter: xtables: add device group match")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/x_tables.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e594b3b7ad82..b39017c80548 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -501,6 +501,17 @@ int xt_check_match(struct xt_mtchk_param *par,
 				    par->match->table, par->table);
 		return -EINVAL;
 	}
+
+	/* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with
+	 * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP
+	 * support.
+	 */
+	if (par->family == NFPROTO_ARP &&
+	    par->match->family != NFPROTO_ARP) {
+		pr_info_ratelimited("%s_tables: %s match: not valid for this family\n",
+				    xt_prefix[par->family], par->match->name);
+		return -EINVAL;
+	}
 	if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) {
 		char used[64], allow[64];
 
@@ -1016,6 +1027,18 @@ int xt_check_target(struct xt_tgchk_param *par,
 				    par->target->table, par->table);
 		return -EINVAL;
 	}
+
+	/* NFPROTO_UNSPEC implies NF_INET_* hooks which do not overlap with
+	 * NF_ARP_IN,OUT,FORWARD, allow explicit extensions with NFPROTO_ARP
+	 * support.
+	 */
+	if (par->family == NFPROTO_ARP &&
+	    par->target->family != NFPROTO_ARP) {
+		pr_info_ratelimited("%s_tables: %s target: not valid for this family\n",
+				    xt_prefix[par->family], par->target->name);
+		return -EINVAL;
+	}
+
 	if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) {
 		char used[64], allow[64];
 
-- 
cgit v1.2.3


From da107398cbd4bbdb6bffecb2ce86d5c9384f4cec Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 31 Mar 2026 23:08:02 +0200
Subject: netfilter: nf_tables: reject immediate NF_QUEUE verdict

nft_queue is always used from userspace nftables to deliver the NF_QUEUE
verdict. Immediately emitting an NF_QUEUE verdict is never used by the
userspace nft tools, so reject immediate NF_QUEUE verdicts.

The arp family does not provide queue support, but such an immediate
verdict is still reachable. Globally reject NF_QUEUE immediate verdicts
to address this issue.

Fixes: f342de4e2f33 ("netfilter: nf_tables: reject QUEUE/DROP verdict parameters")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3922cff1bb3d..8c42247a176c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -11667,8 +11667,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	switch (data->verdict.code) {
 	case NF_ACCEPT:
 	case NF_DROP:
-	case NF_QUEUE:
-		break;
 	case NFT_CONTINUE:
 	case NFT_BREAK:
 	case NFT_RETURN:
@@ -11703,6 +11701,11 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 
 		data->verdict.chain = chain;
 		break;
+	case NF_QUEUE:
+		/* The nft_queue expression is used for this purpose, an
+		 * immediate NF_QUEUE verdict should not ever be seen here.
+		 */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 88c4bd90725557796c15878b7cb70066e9e6b5ab Mon Sep 17 00:00:00 2001
From: Michal Wilczynski <m.wilczynski@samsung.com>
Date: Thu, 3 Apr 2025 15:10:51 +0200
Subject: firmware: thead: Fix buffer overflow and use standard endian macros

Addresses two issues in the TH1520 AON firmware protocol driver:

1. Fix a potential buffer overflow where the code used unsafe pointer
   arithmetic to access the 'mode' field through the 'resource' pointer
   with an offset. This was flagged by Smatch static checker as:
   "buffer overflow 'data' 2 <= 3"

2. Replace custom RPC_SET_BE* and RPC_GET_BE* macros with standard
   kernel endianness conversion macros (cpu_to_be16, etc.) for better
   portability and maintainability.

The functionality was re-tested with the GPU power-up sequence,
confirming the GPU powers up correctly and the driver probes
successfully.

[   12.702370] powervr ffef400000.gpu: [drm] loaded firmware
powervr/rogue_36.52.104.182_v1.fw
[   12.711043] powervr ffef400000.gpu: [drm] FW version v1.0 (build
6645434 OS)
[   12.719787] [drm] Initialized powervr 1.0.0 for ffef400000.gpu on
minor 0

Fixes: e4b3cbd840e5 ("firmware: thead: Add AON firmware protocol driver")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/17a0ccce-060b-4b9d-a3c4-8d5d5823b1c9@stanley.mountain/
Signed-off-by: Michal Wilczynski <m.wilczynski@samsung.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Drew Fustini <fustini@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/firmware/thead,th1520-aon.c             |  7 +--
 include/linux/firmware/thead/thead,th1520-aon.h | 74 -------------------------
 2 files changed, 3 insertions(+), 78 deletions(-)

diff --git a/drivers/firmware/thead,th1520-aon.c b/drivers/firmware/thead,th1520-aon.c
index a35fd5e2a07f..d7f19b5b5f46 100644
--- a/drivers/firmware/thead,th1520-aon.c
+++ b/drivers/firmware/thead,th1520-aon.c
@@ -170,10 +170,9 @@ int th1520_aon_power_update(struct th1520_aon_chan *aon_chan, u16 rsrc,
 	hdr->func = TH1520_AON_PM_FUNC_SET_RESOURCE_POWER_MODE;
 	hdr->size = TH1520_AON_RPC_MSG_NUM;
 
-	RPC_SET_BE16(&msg.resource, 0, rsrc);
-	RPC_SET_BE16(&msg.resource, 2,
-		     (power_on ? TH1520_AON_PM_PW_MODE_ON :
-				 TH1520_AON_PM_PW_MODE_OFF));
+	msg.resource = cpu_to_be16(rsrc);
+	msg.mode = cpu_to_be16(power_on ? TH1520_AON_PM_PW_MODE_ON :
+					  TH1520_AON_PM_PW_MODE_OFF);
 
 	ret = th1520_aon_call_rpc(aon_chan, &msg);
 	if (ret)
diff --git a/include/linux/firmware/thead/thead,th1520-aon.h b/include/linux/firmware/thead/thead,th1520-aon.h
index dae132b66873..d81f5f6f5b90 100644
--- a/include/linux/firmware/thead/thead,th1520-aon.h
+++ b/include/linux/firmware/thead/thead,th1520-aon.h
@@ -97,80 +97,6 @@ struct th1520_aon_rpc_ack_common {
 #define RPC_GET_SVC_FLAG_ACK_TYPE(MESG) (((MESG)->svc & 0x40) >> 6)
 #define RPC_SET_SVC_FLAG_ACK_TYPE(MESG, ACK) ((MESG)->svc |= (ACK) << 6)
 
-#define RPC_SET_BE64(MESG, OFFSET, SET_DATA)                                \
-	do {                                                                \
-		u8 *data = (u8 *)(MESG);                                    \
-		u64 _offset = (OFFSET);                                     \
-		u64 _set_data = (SET_DATA);                                 \
-		data[_offset + 7] = _set_data & 0xFF;                       \
-		data[_offset + 6] = (_set_data & 0xFF00) >> 8;              \
-		data[_offset + 5] = (_set_data & 0xFF0000) >> 16;           \
-		data[_offset + 4] = (_set_data & 0xFF000000) >> 24;         \
-		data[_offset + 3] = (_set_data & 0xFF00000000) >> 32;       \
-		data[_offset + 2] = (_set_data & 0xFF0000000000) >> 40;     \
-		data[_offset + 1] = (_set_data & 0xFF000000000000) >> 48;   \
-		data[_offset + 0] = (_set_data & 0xFF00000000000000) >> 56; \
-	} while (0)
-
-#define RPC_SET_BE32(MESG, OFFSET, SET_DATA)			    \
-	do {							    \
-		u8 *data = (u8 *)(MESG);			    \
-		u64 _offset = (OFFSET);				    \
-		u64 _set_data = (SET_DATA);			    \
-		data[_offset + 3] = (_set_data) & 0xFF;		    \
-		data[_offset + 2] = (_set_data & 0xFF00) >> 8;	    \
-		data[_offset + 1] = (_set_data & 0xFF0000) >> 16;   \
-		data[_offset + 0] = (_set_data & 0xFF000000) >> 24; \
-	} while (0)
-
-#define RPC_SET_BE16(MESG, OFFSET, SET_DATA)		       \
-	do {						       \
-		u8 *data = (u8 *)(MESG);		       \
-		u64 _offset = (OFFSET);			       \
-		u64 _set_data = (SET_DATA);		       \
-		data[_offset + 1] = (_set_data) & 0xFF;	       \
-		data[_offset + 0] = (_set_data & 0xFF00) >> 8; \
-	} while (0)
-
-#define RPC_SET_U8(MESG, OFFSET, SET_DATA)	  \
-	do {					  \
-		u8 *data = (u8 *)(MESG);	  \
-		data[OFFSET] = (SET_DATA) & 0xFF; \
-	} while (0)
-
-#define RPC_GET_BE64(MESG, OFFSET, PTR)                                      \
-	do {                                                                 \
-		u8 *data = (u8 *)(MESG);                                     \
-		u64 _offset = (OFFSET);                                      \
-		*(u32 *)(PTR) =                                              \
-			(data[_offset + 7] | data[_offset + 6] << 8 |        \
-			 data[_offset + 5] << 16 | data[_offset + 4] << 24 | \
-			 data[_offset + 3] << 32 | data[_offset + 2] << 40 | \
-			 data[_offset + 1] << 48 | data[_offset + 0] << 56); \
-	} while (0)
-
-#define RPC_GET_BE32(MESG, OFFSET, PTR)                                      \
-	do {                                                                 \
-		u8 *data = (u8 *)(MESG);                                     \
-		u64 _offset = (OFFSET);                                      \
-		*(u32 *)(PTR) =                                              \
-			(data[_offset + 3] | data[_offset + 2] << 8 |        \
-			 data[_offset + 1] << 16 | data[_offset + 0] << 24); \
-	} while (0)
-
-#define RPC_GET_BE16(MESG, OFFSET, PTR)                                       \
-	do {                                                                  \
-		u8 *data = (u8 *)(MESG);                                      \
-		u64 _offset = (OFFSET);                                       \
-		*(u16 *)(PTR) = (data[_offset + 1] | data[_offset + 0] << 8); \
-	} while (0)
-
-#define RPC_GET_U8(MESG, OFFSET, PTR)          \
-	do {                                   \
-		u8 *data = (u8 *)(MESG);       \
-		*(u8 *)(PTR) = (data[OFFSET]); \
-	} while (0)
-
 /*
  * Defines for SC PM Power Mode
  */
-- 
cgit v1.2.3


From e91d5f94acf68618ea3ad9c92ac28614e791ae7d Mon Sep 17 00:00:00 2001
From: Jacky Bai <ping.bai@nxp.com>
Date: Fri, 20 Mar 2026 16:43:46 +0800
Subject: pmdomain: imx8mp-blk-ctrl: Keep the NOC_HDCP clock enabled

Keep the NOC_HDCP clock always enabled to fix the potential hang
caused by the NoC ADB400 port power down handshake.

Fixes: 77b0ddb42add ("soc: imx: add i.MX8MP HDMI blk ctrl HDCP/HRV_MWR")
Signed-off-by: Jacky Bai <ping.bai@nxp.com>
Cc: stable@vger.kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/imx/imx8mp-blk-ctrl.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c
index 8fc79f9723f0..3f5b9499d30a 100644
--- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c
+++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c
@@ -352,9 +352,6 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc,
 		regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12));
 		regmap_clear_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3));
 		break;
-	case IMX8MP_HDMIBLK_PD_HDCP:
-		regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(11));
-		break;
 	case IMX8MP_HDMIBLK_PD_HRV:
 		regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(3) | BIT(4) | BIT(5));
 		regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(15));
@@ -408,9 +405,6 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc,
 		regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7));
 		regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24));
 		break;
-	case IMX8MP_HDMIBLK_PD_HDCP:
-		regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(11));
-		break;
 	case IMX8MP_HDMIBLK_PD_HRV:
 		regmap_clear_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(15));
 		regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(3) | BIT(4) | BIT(5));
@@ -439,7 +433,7 @@ static int imx8mp_hdmi_power_notifier(struct notifier_block *nb,
 	regmap_write(bc->regmap, HDMI_RTX_CLK_CTL0, 0x0);
 	regmap_write(bc->regmap, HDMI_RTX_CLK_CTL1, 0x0);
 	regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0,
-			BIT(0) | BIT(1) | BIT(10));
+			BIT(0) | BIT(1) | BIT(10) | BIT(11));
 	regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(0));
 
 	/*
-- 
cgit v1.2.3


From e74c38ef6f170179c0029b5744d6a14dfd543108 Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Tue, 31 Mar 2026 13:19:16 +0000
Subject: ASoC: amd: ps: Fix missing leading zeros in subsystem_device SSID log

Ensure that subsystem_device is printed with leading zeros when combined
with subsystem_vendor to form the SSID. Without this, devices with upper
bits unset may appear to have an incorrect SSID in the debug output.

Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com>
Link: https://patch.msgid.link/20260331131916.145546-1-simont@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/ps/pci-ps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c
index 3a20cc10d61f..9751cf0784a6 100644
--- a/sound/soc/amd/ps/pci-ps.c
+++ b/sound/soc/amd/ps/pci-ps.c
@@ -339,7 +339,7 @@ static struct snd_soc_acpi_mach *acp63_sdw_machine_select(struct device *dev)
 			mach->mach_params.subsystem_device = acp_data->subsystem_device;
 			mach->mach_params.subsystem_id_set = true;
 
-			dev_dbg(dev, "SSID %x%x\n", mach->mach_params.subsystem_vendor,
+			dev_dbg(dev, "SSID %x%04x\n", mach->mach_params.subsystem_vendor,
 				mach->mach_params.subsystem_device);
 			return mach;
 		}
-- 
cgit v1.2.3


From 6dcf9d0064ce2f3e3dfe5755f98b93abe6a98e1e Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Wed, 1 Apr 2026 10:45:35 +0800
Subject: cpufreq: governor: fix double free in cpufreq_dbs_governor_init()
 error path

When kobject_init_and_add() fails, cpufreq_dbs_governor_init() calls
kobject_put(&dbs_data->attr_set.kobj).

The kobject release callback cpufreq_dbs_data_release() calls
gov->exit(dbs_data) and kfree(dbs_data), but the current error path
then calls gov->exit(dbs_data) and kfree(dbs_data) again, causing a
double free.

Keep the direct kfree(dbs_data) for the gov->init() failure path, but
after kobject_init_and_add() has been called, let kobject_put() handle
the cleanup through cpufreq_dbs_data_release().

Fixes: 4ebe36c94aed ("cpufreq: Fix kobject memleak")
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Reviewed-by: Zhongqiu Han <zhongqiu.han@oss.qualcomm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: All applicable <stable@vger.kernel.org>
Link: https://patch.msgid.link/20260401024535.1395801-1-lgs201920130244@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq_governor.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index acf101878733..86f35e451914 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -468,13 +468,13 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
 	/* Failure, so roll back. */
 	pr_err("initialization failed (dbs_data kobject init error %d)\n", ret);
 
-	kobject_put(&dbs_data->attr_set.kobj);
-
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
 		gov->gdbs_data = NULL;
-	gov->exit(dbs_data);
+
+	kobject_put(&dbs_data->attr_set.kobj);
+	goto free_policy_dbs_info;
 
 free_dbs_data:
 	kfree(dbs_data);
-- 
cgit v1.2.3


From 54ac9ff8f1196afc49d644a1625e0af1c9fcf7f5 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 31 Mar 2026 13:04:23 +0200
Subject: arm64: Use static call trampolines when kCFI is enabled

Implement arm64 support for the 'unoptimized' static call variety, which
routes all calls through a trampoline that performs a tail call to the
chosen function, and wire it up for use when kCFI is enabled. This works
around an issue with kCFI and generic static calls, where the prototypes
of default handlers such as __static_call_nop() and __static_call_ret0()
don't match the expected prototype of the call site, resulting in kCFI
false positives [0].

Since static call targets may be located in modules loaded out of direct
branching range, this needs an ADRP/LDR pair to load the branch target
into R16 and a branch-to-register (BR) instruction to perform an
indirect call.

Unlike on x86, there is no pressing need on arm64 to avoid indirect
calls at all cost, but hiding it from the compiler as is done here does
have some benefits:
- the literal is located in .rodata, which gives us the same robustness
  advantage that code patching does;
- no D-cache pollution from fetching hash values from .text sections.

From an execution speed PoV, this is unlikely to make any difference at
all.

Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will McVicker <willmcvicker@google.com>
Reported-by: Carlos Llamas <cmllamas@google.com>
Closes: https://lore.kernel.org/all/20260311225822.1565895-1-cmllamas@google.com/ [0]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/Kconfig                   |  1 +
 arch/arm64/include/asm/static_call.h | 31 +++++++++++++++++++++++++++++++
 arch/arm64/kernel/Makefile           |  1 +
 arch/arm64/kernel/static_call.c      | 23 +++++++++++++++++++++++
 arch/arm64/kernel/vmlinux.lds.S      |  1 +
 5 files changed, 57 insertions(+)
 create mode 100644 arch/arm64/include/asm/static_call.h
 create mode 100644 arch/arm64/kernel/static_call.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 38dba5f7e4d2..9ea19b74b6c3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -252,6 +252,7 @@ config ARM64
 	select HAVE_RSEQ
 	select HAVE_RUST if RUSTC_SUPPORTS_ARM64
 	select HAVE_STACKPROTECTOR
+	select HAVE_STATIC_CALL if CFI
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/arm64/include/asm/static_call.h b/arch/arm64/include/asm/static_call.h
new file mode 100644
index 000000000000..30f6a046de4f
--- /dev/null
+++ b/arch/arm64/include/asm/static_call.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_STATIC_CALL_H
+#define _ASM_STATIC_CALL_H
+
+#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, target)		    \
+	asm("	.pushsection .static_call.text, \"ax\"		\n" \
+	    "	.align	4					\n" \
+	    "	.globl	" name "				\n" \
+	    name ":						\n" \
+	    "	hint	34	/* BTI C */			\n" \
+	    "	adrp	x16, 1f					\n" \
+	    "	ldr	x16, [x16, :lo12:1f]			\n" \
+	    "	br	x16					\n" \
+	    "	.type	" name ", %function			\n" \
+	    "	.size	" name ", . - " name "			\n" \
+	    "	.popsection					\n" \
+	    "	.pushsection .rodata, \"a\"			\n" \
+	    "	.align	3					\n" \
+	    "1:	.quad	" target "				\n" \
+	    "	.popsection					\n")
+
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(STATIC_CALL_TRAMP_STR(name), #func)
+
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0)
+
+#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name)			\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0)
+
+#endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 76f32e424065..fe627100d199 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_MODULES)			+= module.o module-plts.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF)	+= watchdog_hld.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
+obj-$(CONFIG_HAVE_STATIC_CALL)		+= static_call.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_EFI)			+= efi.o efi-rt-wrapper.o
diff --git a/arch/arm64/kernel/static_call.c b/arch/arm64/kernel/static_call.c
new file mode 100644
index 000000000000..8b3a19e10871
--- /dev/null
+++ b/arch/arm64/kernel/static_call.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/static_call.h>
+#include <linux/memory.h>
+#include <asm/text-patching.h>
+
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
+{
+	u64 literal;
+	int ret;
+
+	if (!func)
+		func = __static_call_return0;
+
+	/* decode the instructions to discover the literal address */
+	literal = ALIGN_DOWN((u64)tramp + 4, SZ_4K) +
+		  aarch64_insn_adrp_get_offset(le32_to_cpup(tramp + 4)) +
+		  8 * aarch64_insn_decode_immediate(AARCH64_INSN_IMM_12,
+						    le32_to_cpup(tramp + 8));
+
+	ret = aarch64_insn_write_literal_u64((void *)literal, (u64)func);
+	WARN_ON_ONCE(ret);
+}
+EXPORT_SYMBOL_GPL(arch_static_call_transform);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ad6133b89e7a..af9e81f3818a 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -191,6 +191,7 @@ SECTIONS
 			LOCK_TEXT
 			KPROBES_TEXT
 			HYPERVISOR_TEXT
+			STATIC_CALL_TEXT
 			*(.gnu.warning)
 	}
 
-- 
cgit v1.2.3


From 61a11cf4812726aceaee17c96432e1c08f6ed6cb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 31 Mar 2026 07:07:47 -0600
Subject: io_uring: protect remaining lockless ctx->rings accesses with RCU

Commit 96189080265e addressed one case of ctx->rings being potentially
accessed while a resize is happening on the ring, but there are still
a few others that need handling. Add a helper for retrieving the
rings associated with an io_uring context, and add some sanity checking
to that to catch bad uses. ->rings_rcu is always valid, as long as it's
used within RCU read lock. Any use of ->rings_rcu or ->rings inside
either ->uring_lock or ->completion_lock is sane as well.

Do the minimum fix for the current kernel, but set it up such that this
basic infra can be extended for later kernels to make this harder to
mess up in the future.

Thanks to Junxi Qian for finding and debugging this issue.

Cc: stable@vger.kernel.org
Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS")
Reviewed-by: Junxi Qian <qjx1298677004@gmail.com>
Tested-by: Junxi Qian <qjx1298677004@gmail.com>
Link: https://lore.kernel.org/io-uring/20260330172348.89416-1-qjx1298677004@gmail.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c |  7 +++++--
 io_uring/io_uring.h | 34 +++++++++++++++++++++++++++++-----
 io_uring/wait.c     | 50 +++++++++++++++++++++++++++++++-------------------
 io_uring/wait.h     |  7 +++++--
 4 files changed, 70 insertions(+), 28 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 20ec8fdafcae..48f2f627319d 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2015,7 +2015,7 @@ int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	if (ctx->flags & IORING_SETUP_SQ_REWIND)
 		entries = ctx->sq_entries;
 	else
-		entries = io_sqring_entries(ctx);
+		entries = __io_sqring_entries(ctx);
 
 	entries = min(nr, entries);
 	if (unlikely(!entries))
@@ -2250,7 +2250,9 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	 */
 	poll_wait(file, &ctx->poll_wq, wait);
 
-	if (!io_sqring_full(ctx))
+	rcu_read_lock();
+
+	if (!__io_sqring_full(ctx))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	/*
@@ -2270,6 +2272,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	if (__io_cqring_events_user(ctx) || io_has_work(ctx))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
+	rcu_read_unlock();
 	return mask;
 }
 
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 0fa844faf287..ee24bc5d77b3 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -142,16 +142,28 @@ struct io_wait_queue {
 #endif
 };
 
+static inline struct io_rings *io_get_rings(struct io_ring_ctx *ctx)
+{
+	return rcu_dereference_check(ctx->rings_rcu,
+			lockdep_is_held(&ctx->uring_lock) ||
+			lockdep_is_held(&ctx->completion_lock));
+}
+
 static inline bool io_should_wake(struct io_wait_queue *iowq)
 {
 	struct io_ring_ctx *ctx = iowq->ctx;
-	int dist = READ_ONCE(ctx->rings->cq.tail) - (int) iowq->cq_tail;
+	struct io_rings *rings;
+	int dist;
+
+	guard(rcu)();
+	rings = io_get_rings(ctx);
 
 	/*
 	 * Wake up if we have enough events, or if a timeout occurred since we
 	 * started waiting. For timeouts, we always want to return to userspace,
 	 * regardless of event count.
 	 */
+	dist = READ_ONCE(rings->cq.tail) - (int) iowq->cq_tail;
 	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
 }
 
@@ -431,9 +443,9 @@ static inline void io_cqring_wake(struct io_ring_ctx *ctx)
 	__io_wq_wake(&ctx->cq_wait);
 }
 
-static inline bool io_sqring_full(struct io_ring_ctx *ctx)
+static inline bool __io_sqring_full(struct io_ring_ctx *ctx)
 {
-	struct io_rings *r = ctx->rings;
+	struct io_rings *r = io_get_rings(ctx);
 
 	/*
 	 * SQPOLL must use the actual sqring head, as using the cached_sq_head
@@ -445,9 +457,15 @@ static inline bool io_sqring_full(struct io_ring_ctx *ctx)
 	return READ_ONCE(r->sq.tail) - READ_ONCE(r->sq.head) == ctx->sq_entries;
 }
 
-static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+static inline bool io_sqring_full(struct io_ring_ctx *ctx)
 {
-	struct io_rings *rings = ctx->rings;
+	guard(rcu)();
+	return __io_sqring_full(ctx);
+}
+
+static inline unsigned int __io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	struct io_rings *rings = io_get_rings(ctx);
 	unsigned int entries;
 
 	/* make sure SQ entry isn't read before tail */
@@ -455,6 +473,12 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 	return min(entries, ctx->sq_entries);
 }
 
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	guard(rcu)();
+	return __io_sqring_entries(ctx);
+}
+
 /*
  * Don't complete immediately but use deferred completion infrastructure.
  * Protected by ->uring_lock and can only be used either with
diff --git a/io_uring/wait.c b/io_uring/wait.c
index 0581cadf20ee..91df86ce0d18 100644
--- a/io_uring/wait.c
+++ b/io_uring/wait.c
@@ -79,12 +79,15 @@ static enum hrtimer_restart io_cqring_min_timer_wakeup(struct hrtimer *timer)
 	if (io_has_work(ctx))
 		goto out_wake;
 	/* got events since we started waiting, min timeout is done */
-	if (iowq->cq_min_tail != READ_ONCE(ctx->rings->cq.tail))
-		goto out_wake;
-	/* if we have any events and min timeout expired, we're done */
-	if (io_cqring_events(ctx))
-		goto out_wake;
+	scoped_guard(rcu) {
+		struct io_rings *rings = io_get_rings(ctx);
 
+		if (iowq->cq_min_tail != READ_ONCE(rings->cq.tail))
+			goto out_wake;
+		/* if we have any events and min timeout expired, we're done */
+		if (io_cqring_events(ctx))
+			goto out_wake;
+	}
 	/*
 	 * If using deferred task_work running and application is waiting on
 	 * more than one request, ensure we reset it now where we are switching
@@ -186,9 +189,9 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 		   struct ext_arg *ext_arg)
 {
 	struct io_wait_queue iowq;
-	struct io_rings *rings = ctx->rings;
+	struct io_rings *rings;
 	ktime_t start_time;
-	int ret;
+	int ret, nr_wait;
 
 	min_events = min_t(int, min_events, ctx->cq_entries);
 
@@ -201,15 +204,23 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 
 	if (unlikely(test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)))
 		io_cqring_do_overflow_flush(ctx);
-	if (__io_cqring_events_user(ctx) >= min_events)
+
+	rcu_read_lock();
+	rings = io_get_rings(ctx);
+	if (__io_cqring_events_user(ctx) >= min_events) {
+		rcu_read_unlock();
 		return 0;
+	}
 
 	init_waitqueue_func_entry(&iowq.wq, io_wake_function);
 	iowq.wq.private = current;
 	INIT_LIST_HEAD(&iowq.wq.entry);
 	iowq.ctx = ctx;
-	iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
-	iowq.cq_min_tail = READ_ONCE(ctx->rings->cq.tail);
+	iowq.cq_tail = READ_ONCE(rings->cq.head) + min_events;
+	iowq.cq_min_tail = READ_ONCE(rings->cq.tail);
+	nr_wait = (int) iowq.cq_tail - READ_ONCE(rings->cq.tail);
+	rcu_read_unlock();
+	rings = NULL;
 	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
 	iowq.hit_timeout = 0;
 	iowq.min_timeout = ext_arg->min_time;
@@ -240,14 +251,6 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
 		unsigned long check_cq;
-		int nr_wait;
-
-		/* if min timeout has been hit, don't reset wait count */
-		if (!iowq.hit_timeout)
-			nr_wait = (int) iowq.cq_tail -
-					READ_ONCE(ctx->rings->cq.tail);
-		else
-			nr_wait = 1;
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
 			atomic_set(&ctx->cq_wait_nr, nr_wait);
@@ -298,11 +301,20 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags,
 			break;
 		}
 		cond_resched();
+
+		/* if min timeout has been hit, don't reset wait count */
+		if (!iowq.hit_timeout)
+			scoped_guard(rcu)
+				nr_wait = (int) iowq.cq_tail -
+						READ_ONCE(io_get_rings(ctx)->cq.tail);
+		else
+			nr_wait = 1;
 	} while (1);
 
 	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
 		finish_wait(&ctx->cq_wait, &iowq.wq);
 	restore_saved_sigmask_unless(ret == -EINTR);
 
-	return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
+	guard(rcu)();
+	return READ_ONCE(io_get_rings(ctx)->cq.head) == READ_ONCE(io_get_rings(ctx)->cq.tail) ? ret : 0;
 }
diff --git a/io_uring/wait.h b/io_uring/wait.h
index 5e236f74e1af..3a145fcfd3dd 100644
--- a/io_uring/wait.h
+++ b/io_uring/wait.h
@@ -28,12 +28,15 @@ void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx);
 
 static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
 {
-	return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
+	struct io_rings *rings = io_get_rings(ctx);
+	return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
 }
 
 static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx)
 {
-	return READ_ONCE(ctx->rings->cq.tail) - READ_ONCE(ctx->rings->cq.head);
+	struct io_rings *rings = io_get_rings(ctx);
+
+	return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
 }
 
 /*
-- 
cgit v1.2.3


From aa35dd6bdd033dea8aa3e20cbbbe10e06b2d044f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 31 Mar 2026 08:16:58 -0600
Subject: io_uring/bpf_filters: retain COW'ed settings on parse failures

If io_parse_restrictions() fails, it ends up clearing any restrictions
currently set. The intent is only to clear whatever it already applied,
but it ends up clearing everything, including whatever settings may have
been applied in a copy-on-write fashion already. Ensure that those are
retained.

Link: https://lore.kernel.org/io-uring/CAK8a0jzF-zaO5ZmdOrmfuxrhXuKg5m5+RDuO7tNvtj=kUYbW7Q@mail.gmail.com/
Reported-by: antonius <bluedragonsec2023@gmail.com>
Fixes: ed82f35b926b ("io_uring: allow registration of per-task restrictions")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/register.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/io_uring/register.c b/io_uring/register.c
index 5f3eb018fb32..837324bf0223 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -178,9 +178,17 @@ static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
 		return -EBUSY;
 
 	ret = io_parse_restrictions(arg, nr_args, &ctx->restrictions);
-	/* Reset all restrictions if an error happened */
+	/*
+	 * Reset all restrictions if an error happened, but retain any COW'ed
+	 * settings.
+	 */
 	if (ret < 0) {
+		struct io_bpf_filters *bpf = ctx->restrictions.bpf_filters;
+		bool cowed = ctx->restrictions.bpf_filters_cow;
+
 		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
+		ctx->restrictions.bpf_filters = bpf;
+		ctx->restrictions.bpf_filters_cow = cowed;
 		return ret;
 	}
 	if (ctx->restrictions.op_registered)
-- 
cgit v1.2.3


From cffff6df669a438ecac506dadd49a53d4475a796 Mon Sep 17 00:00:00 2001
From: Corey Hickey <bugfood-c@fatooh.org>
Date: Tue, 31 Mar 2026 14:49:06 -0700
Subject: hwmon: (asus-ec-sensors) Fix T_Sensor for PRIME X670E-PRO WIFI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the Asus PRIME X670E-PRO WIFI, the driver reports a constant value of
zero for T_Sensor. On this board, the register for T_Sensor is at a
different address, as found by experimentation and confirmed by
comparison to an independent temperature reading.

* sensor disconnected: -62.0°C
* ambient temperature: +22.0°C
* held between fingers: +30.0°C

Introduce SENSOR_TEMP_T_SENSOR_ALT1 to support the PRIME X670E-PRO WIFI
without causing a regression for other 600-series boards

Fixes: e0444758dd1b ("hwmon: (asus-ec-sensors) add PRIME X670E-PRO WIFI")
Signed-off-by: Corey Hickey <bugfood-c@fatooh.org>
Link: https://lore.kernel.org/r/20260331215414.368785-1-bugfood-ml@fatooh.org
[groeck: Fixed typo, updated Fixes: reference]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/asus-ec-sensors.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
index 86f444498650..adedaf0db10e 100644
--- a/drivers/hwmon/asus-ec-sensors.c
+++ b/drivers/hwmon/asus-ec-sensors.c
@@ -111,6 +111,8 @@ enum ec_sensors {
 	ec_sensor_temp_mb,
 	/* "T_Sensor" temperature sensor reading [℃] */
 	ec_sensor_temp_t_sensor,
+	/* like ec_sensor_temp_t_sensor, but at an alternate address [℃] */
+	ec_sensor_temp_t_sensor_alt1,
 	/* VRM temperature [℃] */
 	ec_sensor_temp_vrm,
 	/* VRM east (right) temperature [℃] */
@@ -160,6 +162,7 @@ enum ec_sensors {
 #define SENSOR_TEMP_CPU_PACKAGE BIT(ec_sensor_temp_cpu_package)
 #define SENSOR_TEMP_MB BIT(ec_sensor_temp_mb)
 #define SENSOR_TEMP_T_SENSOR BIT(ec_sensor_temp_t_sensor)
+#define SENSOR_TEMP_T_SENSOR_ALT1 BIT(ec_sensor_temp_t_sensor_alt1)
 #define SENSOR_TEMP_VRM BIT(ec_sensor_temp_vrm)
 #define SENSOR_TEMP_VRME BIT(ec_sensor_temp_vrme)
 #define SENSOR_TEMP_VRMW BIT(ec_sensor_temp_vrmw)
@@ -279,6 +282,8 @@ static const struct ec_sensor_info sensors_family_amd_600[] = {
 		EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x33),
 	[ec_sensor_temp_t_sensor] =
 		EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x36),
+	[ec_sensor_temp_t_sensor_alt1] =
+		EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x37),
 	[ec_sensor_fan_cpu_opt] =
 		EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xb0),
 	[ec_sensor_temp_water_in] =
@@ -519,7 +524,7 @@ static const struct ec_board_info board_info_prime_x570_pro = {
 static const struct ec_board_info board_info_prime_x670e_pro_wifi = {
 	.sensors = SENSOR_TEMP_CPU | SENSOR_TEMP_CPU_PACKAGE |
 		SENSOR_TEMP_MB | SENSOR_TEMP_VRM |
-		SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT,
+		SENSOR_TEMP_T_SENSOR_ALT1 | SENSOR_FAN_CPU_OPT,
 	.mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH,
 	.family = family_amd_600_series,
 };
-- 
cgit v1.2.3


From 328335a79487ec38d6b0e1aa807785b0f75e594d Mon Sep 17 00:00:00 2001
From: Gaurav Batra <gbatra@linux.ibm.com>
Date: Tue, 31 Mar 2026 17:30:22 -0500
Subject: powerpc/powernv/iommu: iommu incorrectly bypass DMA APIs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In a PowerNV environment, for devices that supports DMA mask less than
64 bit but larger than 32 bits, iommu is incorrectly bypassing DMA
APIs while allocating and mapping buffers for DMA operations.

Devices are failing with ENOMEN during probe with the following messages

amdgpu 0000:01:00.0: [drm] Detected VRAM RAM=4096M, BAR=4096M
amdgpu 0000:01:00.0: [drm] RAM width 128bits GDDR5
amdgpu 0000:01:00.0: iommu: 64-bit OK but direct DMA is limited by 0
amdgpu 0000:01:00.0: dma_iommu_get_required_mask: returning bypass mask 0xfffffffffffffff
amdgpu 0000:01:00.0:  4096M of VRAM memory ready
amdgpu 0000:01:00.0:  32570M of GTT memory ready.
amdgpu 0000:01:00.0: (-12) failed to allocate kernel bo
amdgpu 0000:01:00.0: [drm] Debug VRAM access will use slowpath MM access
amdgpu 0000:01:00.0: [drm] GART: num cpu pages 4096, num gpu pages 65536
amdgpu 0000:01:00.0: [drm] PCIE GART of 256M enabled (table at 0x000000F4FFF80000).
amdgpu 0000:01:00.0: (-12) failed to allocate kernel bo
amdgpu 0000:01:00.0: (-12) create WB bo failed
amdgpu 0000:01:00.0: amdgpu_device_wb_init failed -12
amdgpu 0000:01:00.0: amdgpu_device_ip_init failed
amdgpu 0000:01:00.0: Fatal error during GPU init
amdgpu 0000:01:00.0: finishing device.
amdgpu 0000:01:00.0: probe with driver amdgpu failed with error -12
amdgpu 0000:01:00.0:  ttm finalized

Fixes: 1471c517cf7d ("powerpc/iommu: bypass DMA APIs for coherent allocations for pre-mapped memory")
Suggested-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reported-by: Dan Horák <dan@danny.cz>
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5039
Tested-by: Dan Horak <dan@danny.cz>
Closes: https://lore.kernel.org/linuxppc-dev/20260313142351.609bc4c3efe1184f64ca5f44@danny.cz/
Signed-off-by: Gaurav Batra <gbatra@linux.ibm.com>
Closes: https://lore.kernel.org/linuxppc-dev/20260313142351.609bc4c3efe1184f64ca5f44@danny.cz/
[Maddy: Fixed tags]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260331223022.47488-1-gbatra@linux.ibm.com
---
 arch/powerpc/kernel/dma-iommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 73e10bd4d56d..8b4de508d2eb 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -67,7 +67,7 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 }
 bool arch_dma_alloc_direct(struct device *dev)
 {
-	if (dev->dma_ops_bypass)
+	if (dev->dma_ops_bypass && dev->bus_dma_limit)
 		return true;
 
 	return false;
@@ -75,7 +75,7 @@ bool arch_dma_alloc_direct(struct device *dev)
 
 bool arch_dma_free_direct(struct device *dev, dma_addr_t dma_handle)
 {
-	if (!dev->dma_ops_bypass)
+	if (!dev->dma_ops_bypass || !dev->bus_dma_limit)
 		return false;
 
 	return is_direct_handle(dev, dma_handle);
-- 
cgit v1.2.3


From 35d8945bf9b0c4d9586c7fa9fadeecf2cfc26c23 Mon Sep 17 00:00:00 2001
From: Rong Zhang <rongrong@oss.cipunited.com>
Date: Mon, 16 Mar 2026 01:28:22 +0800
Subject: MIPS: Loongson64: env: Check UARTs passed by LEFI cautiously

Some firmware does not set nr_uarts properly and passes empty items.
Iterate at most min(system->nr_uarts, MAX_UARTS) items to prevent
out-of-bounds access, and ignore UARTs with addr 0 silently.

Meanwhile, our DT only works with UPIO_MEM but theoretically firmware
may pass other IO types, so explicitly check against that.

Tested on Loongson-LS3A4000-7A1000-NUC-SE.

Fixes: 3989ed418483 ("MIPS: Loongson64: env: Fixup serial clock-frequency when using LEFI")
Cc: stable@vger.kernel.org
Reviewed-by: Yao Zi <me@ziyao.cc>
Signed-off-by: Rong Zhang <rongrong@oss.cipunited.com>
Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/loongson64/env.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index 11ddf02d6a15..7abcca7ab4ed 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -17,7 +17,9 @@
 #include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/libfdt.h>
+#include <linux/minmax.h>
 #include <linux/pci_ids.h>
+#include <linux/serial_core.h>
 #include <linux/string_choices.h>
 #include <asm/bootinfo.h>
 #include <loongson.h>
@@ -106,9 +108,23 @@ static void __init lefi_fixup_fdt(struct system_loongson *system)
 
 	is_loongson64g = (read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G;
 
-	for (i = 0; i < system->nr_uarts; i++) {
+	for (i = 0; i < min(system->nr_uarts, MAX_UARTS); i++) {
 		uartdev = &system->uarts[i];
 
+		/*
+		 * Some firmware does not set nr_uarts properly and passes empty
+		 * items. Ignore them silently.
+		 */
+		if (uartdev->uart_base == 0)
+			continue;
+
+		/* Our DT only works with UPIO_MEM. */
+		if (uartdev->iotype != UPIO_MEM) {
+			pr_warn("Ignore UART 0x%llx with iotype %u passed by firmware\n",
+				uartdev->uart_base, uartdev->iotype);
+			continue;
+		}
+
 		ret = lefi_fixup_fdt_serial(fdt_buf, uartdev->uart_base,
 					    uartdev->uartclk);
 		/*
-- 
cgit v1.2.3


From 43985a62bab9d35e5e9af41118ce2f44c01b97d2 Mon Sep 17 00:00:00 2001
From: Shiji Yang <yangshiji66@outlook.com>
Date: Tue, 24 Feb 2026 10:22:50 +0800
Subject: mips: ralink: update CPU clock index

Update CPU clock index to match the clock driver changes.

Fixes: d34db686a3d7 ("clk: ralink: mtmips: fix clocks probe order in oldest ralink SoCs")
Signed-off-by: Mieczyslaw Nalewaj <namiltd@yahoo.com>
Signed-off-by: Shiji Yang <yangshiji66@outlook.com>
Reviewed-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/ralink/clk.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/mips/ralink/clk.c b/arch/mips/ralink/clk.c
index 9db73fcac522..5c1eb46ef5d0 100644
--- a/arch/mips/ralink/clk.c
+++ b/arch/mips/ralink/clk.c
@@ -21,16 +21,16 @@ static const char *clk_cpu(int *idx)
 {
 	switch (ralink_soc) {
 	case RT2880_SOC:
-		*idx = 0;
+		*idx = 1;
 		return "ralink,rt2880-sysc";
 	case RT3883_SOC:
-		*idx = 0;
+		*idx = 1;
 		return "ralink,rt3883-sysc";
 	case RT305X_SOC_RT3050:
-		*idx = 0;
+		*idx = 1;
 		return "ralink,rt3050-sysc";
 	case RT305X_SOC_RT3052:
-		*idx = 0;
+		*idx = 1;
 		return "ralink,rt3052-sysc";
 	case RT305X_SOC_RT3350:
 		*idx = 1;
-- 
cgit v1.2.3


From d62cf1511743526f530a4c169424e50c757f5a5e Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Fri, 27 Mar 2026 11:38:06 +0000
Subject: MIPS: SiByte: Bring back cache initialisation

Bring back cache initialisation for Broadcom SiByte SB1 cores, which has
been removed causing the kernel to hang at bootstrap right after:

Dentry cache hash table entries: 524288 (order: 8, 4194304 bytes, linear)
Inode-cache hash table entries: 262144 (order: 7, 2097152 bytes, linear)

The cause of the problem is R4k cache handlers are also used by Broadcom
SiByte SB1 cores, however with a different cache error exception handler
and therefore not using CPU_R4K_CACHE_TLB:

obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
obj-$(CONFIG_CPU_SB1)           += c-r4k.o cerr-sb1.o cex-sb1.o tlb-r4k.o

(from arch/mips/mm/Makefile).

Fixes: bbe4f634f48c ("mips: fix r3k_cache_init build regression")
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Cc: stable@vger.kernel.org # v6.8+
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/cache.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index e3b4224c9a40..ad9b0430a28e 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -207,7 +207,8 @@ void cpu_cache_init(void)
 {
 	if (IS_ENABLED(CONFIG_CPU_R3000) && cpu_has_3k_cache)
 		r3k_cache_init();
-	if (IS_ENABLED(CONFIG_CPU_R4K_CACHE_TLB) && cpu_has_4k_cache)
+	if ((IS_ENABLED(CONFIG_CPU_R4K_CACHE_TLB) ||
+	     IS_ENABLED(CONFIG_CPU_SB1)) && cpu_has_4k_cache)
 		r4k_cache_init();
 
 	if (IS_ENABLED(CONFIG_CPU_CAVIUM_OCTEON) && cpu_has_octeon_cache)
-- 
cgit v1.2.3


From ec8bf18814915460d9c617b556bf024efef26613 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Mon, 30 Mar 2026 02:54:09 +0100
Subject: MIPS: Fix the GCC version check for `__multi3' workaround

It was only GCC 10 that fixed a MIPS64r6 code generation issue with a
`__multi3' libcall inefficiently produced to perform 64-bit widening
multiplication while suitable machine instructions exist to do such a
calculation.  The fix went in with GCC commit 48b2123f6336 ("re PR
target/82981 (unnecessary __multi3 call for mips64r6 linux kernel)").

Adjust our code accordingly, removing build failures such as:

mips64-linux-ld: lib/math/div64.o: in function `mul_u64_add_u64_div_u64':
div64.c:(.text+0x84): undefined reference to `__multi3'

with the GCC versions affected.

Fixes: ebabcf17bcd7 ("MIPS: Implement __multi3 for GCC7 MIPS64r6 builds")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601140146.hMLODc6v-lkp@intel.com/
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Cc: stable@vger.kernel.org # v4.15+
Reviewed-by: David Laight <david.laight.linux@gmail.com.
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/lib/multi3.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/lib/multi3.c b/arch/mips/lib/multi3.c
index 4c2483f410c2..92b3778bb56f 100644
--- a/arch/mips/lib/multi3.c
+++ b/arch/mips/lib/multi3.c
@@ -4,12 +4,12 @@
 #include "libgcc.h"
 
 /*
- * GCC 7 & older can suboptimally generate __multi3 calls for mips64r6, so for
+ * GCC 9 & older can suboptimally generate __multi3 calls for mips64r6, so for
  * that specific case only we implement that intrinsic here.
  *
  * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
  */
-#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ < 8)
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ < 10)
 
 /* multiply 64-bit values, low 64-bits returned */
 static inline long long notrace dmulu(long long a, long long b)
@@ -51,4 +51,4 @@ ti_type notrace __multi3(ti_type a, ti_type b)
 }
 EXPORT_SYMBOL(__multi3);
 
-#endif /* 64BIT && CPU_MIPSR6 && GCC7 */
+#endif /* 64BIT && CPU_MIPSR6 && GCC9 */
-- 
cgit v1.2.3


From 8374c2cb83b95b3c92f129fd56527225c20a058c Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Fri, 27 Mar 2026 18:57:18 +0000
Subject: MIPS: Always record SEGBITS in cpu_data.vmbits

With a 32-bit kernel running on 64-bit MIPS hardware the hardcoded value
of `cpu_vmbits' only records the size of compatibility useg and does not
reflect the size of native xuseg or the complete range of values allowed
in the VPN2 field of TLB entries.

An upcoming change will need the actual VPN2 value range permitted even
in 32-bit kernel configurations, so always include the `vmbits' member
in `struct cpuinfo_mips' and probe for SEGBITS when running on 64-bit
hardware and resorting to the currently hardcoded value of 31 on 32-bit
processors.  No functional change for users of `cpu_vmbits'.

Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/include/asm/cpu-features.h |  1 -
 arch/mips/include/asm/cpu-info.h     |  2 --
 arch/mips/include/asm/mipsregs.h     |  2 ++
 arch/mips/kernel/cpu-probe.c         | 13 ++++++++-----
 arch/mips/kernel/cpu-r3k-probe.c     |  2 ++
 5 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 404390bb87ea..3f11e5218e6c 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -484,7 +484,6 @@
 # endif
 # ifndef cpu_vmbits
 # define cpu_vmbits cpu_data[0].vmbits
-# define __NEED_VMBITS_PROBE
 # endif
 #endif
 
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index fd60837ce50b..211b578af6aa 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -80,9 +80,7 @@ struct cpuinfo_mips {
 	int			srsets; /* Shadow register sets */
 	int			package;/* physical package number */
 	unsigned int		globalnumber;
-#ifdef CONFIG_64BIT
 	int			vmbits; /* Virtual memory size in bits */
-#endif
 	void			*data;	/* Additional data */
 	unsigned int		watch_reg_count;   /* Number that exist */
 	unsigned int		watch_reg_use_cnt; /* Usable by ptrace */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index f799c0d723da..12a095dbf9e2 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1871,6 +1871,8 @@ do {									\
 
 #define read_c0_entryhi()	__read_ulong_c0_register($10, 0)
 #define write_c0_entryhi(val)	__write_ulong_c0_register($10, 0, val)
+#define read_c0_entryhi_64()	__read_64bit_c0_register($10, 0)
+#define write_c0_entryhi_64(val) __write_64bit_c0_register($10, 0, val)
 
 #define read_c0_guestctl1()	__read_32bit_c0_register($10, 4)
 #define write_c0_guestctl1(val)	__write_32bit_c0_register($10, 4, val)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 1e49e05ac8b1..489612ed9d49 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -210,11 +210,14 @@ static inline void set_elf_base_platform(const char *plat)
 
 static inline void cpu_probe_vmbits(struct cpuinfo_mips *c)
 {
-#ifdef __NEED_VMBITS_PROBE
-	write_c0_entryhi(0x3fffffffffffe000ULL);
-	back_to_back_c0_hazard();
-	c->vmbits = fls64(read_c0_entryhi() & 0x3fffffffffffe000ULL);
-#endif
+	int vmbits = 31;
+
+	if (cpu_has_64bits) {
+		write_c0_entryhi_64(0x3fffffffffffe000ULL);
+		back_to_back_c0_hazard();
+		vmbits = fls64(read_c0_entryhi_64() & 0x3fffffffffffe000ULL);
+	}
+	c->vmbits = vmbits;
 }
 
 static void set_isa(struct cpuinfo_mips *c, unsigned int isa)
diff --git a/arch/mips/kernel/cpu-r3k-probe.c b/arch/mips/kernel/cpu-r3k-probe.c
index 0c826f729f75..edcf04de0a6f 100644
--- a/arch/mips/kernel/cpu-r3k-probe.c
+++ b/arch/mips/kernel/cpu-r3k-probe.c
@@ -137,6 +137,8 @@ void cpu_probe(void)
 	else
 		cpu_set_nofpu_opts(c);
 
+	c->vmbits = 31;
+
 	reserve_exception_space(0, 0x400);
 }
 
-- 
cgit v1.2.3


From 74283cfe216392c7b776ebf6045b5b15ed9dffcd Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Fri, 27 Mar 2026 18:57:23 +0000
Subject: MIPS: mm: Suppress TLB uniquification on EHINV hardware

Hardware that supports the EHINV feature, mandatory for R6 ISA and FTLB
implementation, lets software mark TLB entries invalid, which eliminates
the need to ensure no duplicate matching entries are ever created.  This
feature is already used by local_flush_tlb_all(), via the UNIQUE_ENTRYHI
macro, making the preceding call to r4k_tlb_uniquify() superfluous.

The next change will also modify uniquification code such that it'll
become incompatible with the FTLB and MMID features, as well as MIPSr6
CPUs that do not implement 4KiB pages.

Therefore prevent r4k_tlb_uniquify() from being used on EHINV hardware,
as denoted by `cpu_has_tlbinv'.

Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/tlb-r4k.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 44a662536148..27bb64469604 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -640,7 +640,8 @@ static void r4k_tlb_configure(void)
 	temp_tlb_entry = current_cpu_data.tlbsize - 1;
 
 	/* From this point on the ARC firmware is dead.	 */
-	r4k_tlb_uniquify();
+	if (!cpu_has_tlbinv)
+		r4k_tlb_uniquify();
 	local_flush_tlb_all();
 
 	/* Did I tell you that ARC SUCKS?  */
-- 
cgit v1.2.3


From 540760b77b8fc49d39d1b2b76196e5ec57711a32 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@orcam.me.uk>
Date: Fri, 27 Mar 2026 18:57:30 +0000
Subject: MIPS: mm: Rewrite TLB uniquification for the hidden bit feature

Before the introduction of the EHINV feature, which lets software mark
TLB entries invalid, certain older implementations of the MIPS ISA were
equipped with an analogous bit, as a vendor extension, which however is
hidden from software and only ever set at reset, and then any software
write clears it, making the intended TLB entry valid.

This feature makes it unsafe to read a TLB entry with TLBR, modify the
page mask, and write the entry back with TLBWI, because this operation
will implicitly clear the hidden bit and this may create a duplicate
entry, as with the presence of the hidden bit there is no guarantee all
the entries across the TLB are unique each.

Usually the firmware has already uniquified TLB entries before handing
control over, in which case we only need to guarantee at bootstrap no
clash will happen with the VPN2 values chosen in local_flush_tlb_all().

However with systems such as Mikrotik RB532 we get handed the TLB as at
reset, with the hidden bit set across the entries and possibly duplicate
entries present.  This then causes a machine check exception when page
sizes are reset in r4k_tlb_uniquify() and prevents the system from
booting.

Rewrite the algorithm used in r4k_tlb_uniquify() then such as to avoid
the reuse of ASID/VPN values across the TLB.  Get rid of global entries
first as they may be blocking the entire address space, e.g. 16 256MiB
pages will exhaust the whole address space of a 32-bit CPU and a single
big page can exhaust the 32-bit compatibility space on a 64-bit CPU.

Details of the algorithm chosen are given across the code itself.

Fixes: 9f048fa48740 ("MIPS: mm: Prevent a TLB shutdown on initial uniquification")
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Cc: stable@vger.kernel.org # v6.18+
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/tlb-r4k.c | 282 +++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 228 insertions(+), 54 deletions(-)

diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 27bb64469604..08c3e65bf0f2 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -13,6 +13,7 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/memblock.h>
+#include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/export.h>
@@ -24,6 +25,7 @@
 #include <asm/hazards.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
+#include <asm/tlbdebug.h>
 #include <asm/tlbex.h>
 #include <asm/tlbmisc.h>
 #include <asm/setup.h>
@@ -511,87 +513,259 @@ static int __init set_ntlb(char *str)
 __setup("ntlb=", set_ntlb);
 
 
-/* Comparison function for EntryHi VPN fields.  */
-static int r4k_vpn_cmp(const void *a, const void *b)
+/* The start bit position of VPN2 and Mask in EntryHi/PageMask registers.  */
+#define VPN2_SHIFT 13
+
+/* Read full EntryHi even with CONFIG_32BIT.  */
+static inline unsigned long long read_c0_entryhi_native(void)
+{
+	return cpu_has_64bits ? read_c0_entryhi_64() : read_c0_entryhi();
+}
+
+/* Write full EntryHi even with CONFIG_32BIT.  */
+static inline void write_c0_entryhi_native(unsigned long long v)
 {
-	long v = *(unsigned long *)a - *(unsigned long *)b;
-	int s = sizeof(long) > sizeof(int) ? sizeof(long) * 8 - 1: 0;
-	return s ? (v != 0) | v >> s : v;
+	if (cpu_has_64bits)
+		write_c0_entryhi_64(v);
+	else
+		write_c0_entryhi(v);
 }
 
+/* TLB entry state for uniquification.  */
+struct tlbent {
+	unsigned long long wired:1;
+	unsigned long long global:1;
+	unsigned long long asid:10;
+	unsigned long long vpn:51;
+	unsigned long long pagesz:5;
+	unsigned long long index:14;
+};
+
 /*
- * Initialise all TLB entries with unique values that do not clash with
- * what we have been handed over and what we'll be using ourselves.
+ * Comparison function for TLB entry sorting.  Place wired entries first,
+ * then global entries, then order by the increasing VPN/ASID and the
+ * decreasing page size.  This lets us avoid clashes with wired entries
+ * easily and get entries for larger pages out of the way first.
+ *
+ * We could group bits so as to reduce the number of comparisons, but this
+ * is seldom executed and not performance-critical, so prefer legibility.
  */
-static void __ref r4k_tlb_uniquify(void)
+static int r4k_entry_cmp(const void *a, const void *b)
 {
-	int tlbsize = current_cpu_data.tlbsize;
-	bool use_slab = slab_is_available();
-	int start = num_wired_entries();
-	phys_addr_t tlb_vpn_size;
-	unsigned long *tlb_vpns;
-	unsigned long vpn_mask;
-	int cnt, ent, idx, i;
-
-	vpn_mask = GENMASK(cpu_vmbits - 1, 13);
-	vpn_mask |= IS_ENABLED(CONFIG_64BIT) ? 3ULL << 62 : 1 << 31;
+	struct tlbent ea = *(struct tlbent *)a, eb = *(struct tlbent *)b;
+
+	if (ea.wired > eb.wired)
+		return -1;
+	else if (ea.wired < eb.wired)
+		return 1;
+	else if (ea.global > eb.global)
+		return -1;
+	else if (ea.global < eb.global)
+		return 1;
+	else if (ea.vpn < eb.vpn)
+		return -1;
+	else if (ea.vpn > eb.vpn)
+		return 1;
+	else if (ea.asid < eb.asid)
+		return -1;
+	else if (ea.asid > eb.asid)
+		return 1;
+	else if (ea.pagesz > eb.pagesz)
+		return -1;
+	else if (ea.pagesz < eb.pagesz)
+		return 1;
+	else
+		return 0;
+}
 
-	tlb_vpn_size = tlbsize * sizeof(*tlb_vpns);
-	tlb_vpns = (use_slab ?
-		    kmalloc(tlb_vpn_size, GFP_KERNEL) :
-		    memblock_alloc_raw(tlb_vpn_size, sizeof(*tlb_vpns)));
-	if (WARN_ON(!tlb_vpns))
-		return; /* Pray local_flush_tlb_all() is good enough. */
+/*
+ * Fetch all the TLB entries.  Mask individual VPN values retrieved with
+ * the corresponding page mask and ignoring any 1KiB extension as we'll
+ * be using 4KiB pages for uniquification.
+ */
+static void __ref r4k_tlb_uniquify_read(struct tlbent *tlb_vpns, int tlbsize)
+{
+	int start = num_wired_entries();
+	unsigned long long vpn_mask;
+	bool global;
+	int i;
 
-	htw_stop();
+	vpn_mask = GENMASK(current_cpu_data.vmbits - 1, VPN2_SHIFT);
+	vpn_mask |= cpu_has_64bits ? 3ULL << 62 : 1 << 31;
 
-	for (i = start, cnt = 0; i < tlbsize; i++, cnt++) {
-		unsigned long vpn;
+	for (i = 0; i < tlbsize; i++) {
+		unsigned long long entryhi, vpn, mask, asid;
+		unsigned int pagesz;
 
 		write_c0_index(i);
 		mtc0_tlbr_hazard();
 		tlb_read();
 		tlb_read_hazard();
-		vpn = read_c0_entryhi();
-		vpn &= vpn_mask & PAGE_MASK;
-		tlb_vpns[cnt] = vpn;
 
-		/* Prevent any large pages from overlapping regular ones.  */
-		write_c0_pagemask(read_c0_pagemask() & PM_DEFAULT_MASK);
-		mtc0_tlbw_hazard();
-		tlb_write_indexed();
-		tlbw_use_hazard();
+		global = !!(read_c0_entrylo0() & ENTRYLO_G);
+		entryhi = read_c0_entryhi_native();
+		mask = read_c0_pagemask();
+
+		asid = entryhi & cpu_asid_mask(&current_cpu_data);
+		vpn = (entryhi & vpn_mask & ~mask) >> VPN2_SHIFT;
+		pagesz = ilog2((mask >> VPN2_SHIFT) + 1);
+
+		tlb_vpns[i].global = global;
+		tlb_vpns[i].asid = global ? 0 : asid;
+		tlb_vpns[i].vpn = vpn;
+		tlb_vpns[i].pagesz = pagesz;
+		tlb_vpns[i].wired = i < start;
+		tlb_vpns[i].index = i;
 	}
+}
 
-	sort(tlb_vpns, cnt, sizeof(tlb_vpns[0]), r4k_vpn_cmp, NULL);
+/*
+ * Write unique values to all but the wired TLB entries each, using
+ * the 4KiB page size.  This size might not be supported with R6, but
+ * EHINV is mandatory for R6, so we won't ever be called in that case.
+ *
+ * A sorted table is supplied with any wired entries at the beginning,
+ * followed by any global entries, and then finally regular entries.
+ * We start at the VPN and ASID values of zero and only assign user
+ * addresses, therefore guaranteeing no clash with addresses produced
+ * by UNIQUE_ENTRYHI.  We avoid any VPN values used by wired or global
+ * entries, by increasing the VPN value beyond the span of such entry.
+ *
+ * When a VPN/ASID clash is found with a regular entry we increment the
+ * ASID instead until no VPN/ASID clash has been found or the ASID space
+ * has been exhausted, in which case we increase the VPN value beyond
+ * the span of the largest clashing entry.
+ *
+ * We do not need to be concerned about FTLB or MMID configurations as
+ * those are required to implement the EHINV feature.
+ */
+static void __ref r4k_tlb_uniquify_write(struct tlbent *tlb_vpns, int tlbsize)
+{
+	unsigned long long asid, vpn, vpn_size, pagesz;
+	int widx, gidx, idx, sidx, lidx, i;
 
-	write_c0_pagemask(PM_DEFAULT_MASK);
+	vpn_size = 1ULL << (current_cpu_data.vmbits - VPN2_SHIFT);
+	pagesz = ilog2((PM_4K >> VPN2_SHIFT) + 1);
+
+	write_c0_pagemask(PM_4K);
 	write_c0_entrylo0(0);
 	write_c0_entrylo1(0);
 
-	idx = 0;
-	ent = tlbsize;
-	for (i = start; i < tlbsize; i++)
-		while (1) {
-			unsigned long entryhi, vpn;
+	asid = 0;
+	vpn = 0;
+	widx = 0;
+	gidx = 0;
+	for (sidx = 0; sidx < tlbsize && tlb_vpns[sidx].wired; sidx++)
+		;
+	for (lidx = sidx; lidx < tlbsize && tlb_vpns[lidx].global; lidx++)
+		;
+	idx = gidx = sidx + 1;
+	for (i = sidx; i < tlbsize; i++) {
+		unsigned long long entryhi, vpn_pagesz = 0;
 
-			entryhi = UNIQUE_ENTRYHI(ent);
-			vpn = entryhi & vpn_mask & PAGE_MASK;
+		while (1) {
+			if (WARN_ON(vpn >= vpn_size)) {
+				dump_tlb_all();
+				/* Pray local_flush_tlb_all() will cope.  */
+				return;
+			}
 
-			if (idx >= cnt || vpn < tlb_vpns[idx]) {
-				write_c0_entryhi(entryhi);
-				write_c0_index(i);
-				mtc0_tlbw_hazard();
-				tlb_write_indexed();
-				ent++;
-				break;
-			} else if (vpn == tlb_vpns[idx]) {
-				ent++;
-			} else {
+			/* VPN must be below the next wired entry.  */
+			if (widx < sidx && vpn >= tlb_vpns[widx].vpn) {
+				vpn = max(vpn,
+					  (tlb_vpns[widx].vpn +
+					   (1ULL << tlb_vpns[widx].pagesz)));
+				asid = 0;
+				widx++;
+				continue;
+			}
+			/* VPN must be below the next global entry.  */
+			if (gidx < lidx && vpn >= tlb_vpns[gidx].vpn) {
+				vpn = max(vpn,
+					  (tlb_vpns[gidx].vpn +
+					   (1ULL << tlb_vpns[gidx].pagesz)));
+				asid = 0;
+				gidx++;
+				continue;
+			}
+			/* Try to find a free ASID so as to conserve VPNs.  */
+			if (idx < tlbsize && vpn == tlb_vpns[idx].vpn &&
+			    asid == tlb_vpns[idx].asid) {
+				unsigned long long idx_pagesz;
+
+				idx_pagesz = tlb_vpns[idx].pagesz;
+				vpn_pagesz = max(vpn_pagesz, idx_pagesz);
+				do
+					idx++;
+				while (idx < tlbsize &&
+				       vpn == tlb_vpns[idx].vpn &&
+				       asid == tlb_vpns[idx].asid);
+				asid++;
+				if (asid > cpu_asid_mask(&current_cpu_data)) {
+					vpn += vpn_pagesz;
+					asid = 0;
+					vpn_pagesz = 0;
+				}
+				continue;
+			}
+			/* VPN mustn't be above the next regular entry.  */
+			if (idx < tlbsize && vpn > tlb_vpns[idx].vpn) {
+				vpn = max(vpn,
+					  (tlb_vpns[idx].vpn +
+					   (1ULL << tlb_vpns[idx].pagesz)));
+				asid = 0;
 				idx++;
+				continue;
 			}
+			break;
 		}
 
+		entryhi = (vpn << VPN2_SHIFT) | asid;
+		write_c0_entryhi_native(entryhi);
+		write_c0_index(tlb_vpns[i].index);
+		mtc0_tlbw_hazard();
+		tlb_write_indexed();
+
+		tlb_vpns[i].asid = asid;
+		tlb_vpns[i].vpn = vpn;
+		tlb_vpns[i].pagesz = pagesz;
+
+		asid++;
+		if (asid > cpu_asid_mask(&current_cpu_data)) {
+			vpn += 1ULL << pagesz;
+			asid = 0;
+		}
+	}
+}
+
+/*
+ * Initialise all TLB entries with unique values that do not clash with
+ * what we have been handed over and what we'll be using ourselves.
+ */
+static void __ref r4k_tlb_uniquify(void)
+{
+	int tlbsize = current_cpu_data.tlbsize;
+	bool use_slab = slab_is_available();
+	phys_addr_t tlb_vpn_size;
+	struct tlbent *tlb_vpns;
+
+	tlb_vpn_size = tlbsize * sizeof(*tlb_vpns);
+	tlb_vpns = (use_slab ?
+		    kmalloc(tlb_vpn_size, GFP_KERNEL) :
+		    memblock_alloc_raw(tlb_vpn_size, sizeof(*tlb_vpns)));
+	if (WARN_ON(!tlb_vpns))
+		return; /* Pray local_flush_tlb_all() is good enough. */
+
+	htw_stop();
+
+	r4k_tlb_uniquify_read(tlb_vpns, tlbsize);
+
+	sort(tlb_vpns, tlbsize, sizeof(*tlb_vpns), r4k_entry_cmp, NULL);
+
+	r4k_tlb_uniquify_write(tlb_vpns, tlbsize);
+
+	write_c0_pagemask(PM_DEFAULT_MASK);
+
 	tlbw_use_hazard();
 	htw_start();
 	flush_micro_tlb();
-- 
cgit v1.2.3


From 703ccb63ae9f7444d6ff876d024e17f628103c69 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 31 Mar 2026 18:07:39 -0700
Subject: workqueue: Add pool_workqueue to pending_pwqs list when unplugging
 multiple inactive works
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In unplug_oldest_pwq(), the first inactive work item on the
pool_workqueue is activated correctly. However, if multiple inactive
works exist on the same pool_workqueue, subsequent works fail to
activate because wq_node_nr_active.pending_pwqs is empty — the list
insertion is skipped when the pool_workqueue is plugged.

Fix this by checking for additional inactive works in
unplug_oldest_pwq() and updating wq_node_nr_active.pending_pwqs
accordingly.

Fixes: 4c065dbce1e8 ("workqueue: Enable unbound cpumask update on ordered workqueues")
Cc: stable@vger.kernel.org
Cc: Carlos Santa <carlos.santa@intel.com>
Cc: Ryan Neph <ryanneph@google.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Waiman Long <longman@redhat.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
---
 kernel/workqueue.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index eda756556341..c6ea96d5b716 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1849,8 +1849,20 @@ static void unplug_oldest_pwq(struct workqueue_struct *wq)
 	raw_spin_lock_irq(&pwq->pool->lock);
 	if (pwq->plugged) {
 		pwq->plugged = false;
-		if (pwq_activate_first_inactive(pwq, true))
+		if (pwq_activate_first_inactive(pwq, true)) {
+			/*
+			 * While plugged, queueing skips activation which
+			 * includes bumping the nr_active count and adding the
+			 * pwq to nna->pending_pwqs if the count can't be
+			 * obtained. We need to restore both for the pwq being
+			 * unplugged. The first call activates the first
+			 * inactive work item and the second, if there are more
+			 * inactive, puts the pwq on pending_pwqs.
+			 */
+			pwq_activate_first_inactive(pwq, false);
+
 			kick_pool(pwq->pool);
+		}
 	}
 	raw_spin_unlock_irq(&pwq->pool->lock);
 }
-- 
cgit v1.2.3


From 01cc50ea5167bb14117257ec084637abe9e5f691 Mon Sep 17 00:00:00 2001
From: Stefan Wiehler <stefan.wiehler@nokia.com>
Date: Tue, 10 Mar 2026 11:40:24 +0100
Subject: mips: mm: Allocate tlb_vpn array atomically

Found by DEBUG_ATOMIC_SLEEP:

  BUG: sleeping function called from invalid context at /include/linux/sched/mm.h:306
  in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 0, name: swapper/1
  preempt_count: 1, expected: 0
  RCU nest depth: 0, expected: 0
  no locks held by swapper/1/0.
  irq event stamp: 0
  hardirqs last  enabled at (0): [<0000000000000000>] 0x0
  hardirqs last disabled at (0): [<ffffffff801477fc>] copy_process+0x75c/0x1b68
  softirqs last  enabled at (0): [<ffffffff801477fc>] copy_process+0x75c/0x1b68
  softirqs last disabled at (0): [<0000000000000000>] 0x0
  CPU: 1 PID: 0 Comm: swapper/1 Not tainted 6.6.119-d79e757675ec-fct #1
  Stack : 800000000290bad8 0000000000000000 0000000000000008 800000000290bae8
          800000000290bae8 800000000290bc78 0000000000000000 0000000000000000
          ffffffff80c80000 0000000000000001 ffffffff80d8dee8 ffffffff810d09c0
          784bb2a7ec10647d 0000000000000010 ffffffff80a6fd60 8000000001d8a9c0
          0000000000000000 0000000000000000 ffffffff80d90000 0000000000000000
          ffffffff80c9e0e8 0000000007ffffff 0000000000000cc0 0000000000000400
          ffffffffffffffff 0000000000000001 0000000000000002 ffffffffc0149ed8
          fffffffffffffffe 8000000002908000 800000000290bae0 ffffffff80a81b74
          ffffffff80129fb0 0000000000000000 0000000000000000 0000000000000000
          0000000000000000 0000000000000000 ffffffff80129fd0 0000000000000000
          ...
  Call Trace:
  [<ffffffff80129fd0>] show_stack+0x60/0x158
  [<ffffffff80a7f894>] dump_stack_lvl+0x88/0xbc
  [<ffffffff8018d3c8>] __might_resched+0x268/0x288
  [<ffffffff803648b0>] __kmem_cache_alloc_node+0x2e0/0x330
  [<ffffffff80302788>] __kmalloc+0x58/0xd0
  [<ffffffff80a81b74>] r4k_tlb_uniquify+0x7c/0x428
  [<ffffffff80143e8c>] tlb_init+0x7c/0x110
  [<ffffffff8012bdb4>] per_cpu_trap_init+0x16c/0x1d0
  [<ffffffff80133258>] start_secondary+0x28/0x128

Fixes: 231ac951faba ("MIPS: mm: kmalloc tlb_vpn array to avoid stack overflow")
Signed-off-by: Stefan Wiehler <stefan.wiehler@nokia.com>
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/mm/tlb-r4k.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 08c3e65bf0f2..24fe85fa169d 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -751,7 +751,7 @@ static void __ref r4k_tlb_uniquify(void)
 
 	tlb_vpn_size = tlbsize * sizeof(*tlb_vpns);
 	tlb_vpns = (use_slab ?
-		    kmalloc(tlb_vpn_size, GFP_KERNEL) :
+		    kmalloc(tlb_vpn_size, GFP_ATOMIC) :
 		    memblock_alloc_raw(tlb_vpn_size, sizeof(*tlb_vpns)));
 	if (WARN_ON(!tlb_vpns))
 		return; /* Pray local_flush_tlb_all() is good enough. */
-- 
cgit v1.2.3


From a834a0b66ec6fb743377201a0f4229bb2503f4ce Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Wed, 25 Mar 2026 21:07:46 +0200
Subject: Bluetooth: hci_sync: call destroy in hci_cmd_sync_run if immediate

hci_cmd_sync_run() may run the work immediately if called from existing
sync work (otherwise it queues a new sync work). In this case it fails
to call the destroy() function.

On immediate run, make it behave same way as if item was queued
successfully: call destroy, and return 0.

The only callsite is hci_abort_conn() via hci_cmd_sync_run_once(), and
this changes its return value. However, its return value is not used
except as the return value for hci_disconnect(), and nothing uses the
return value of hci_disconnect(). Hence there should be no behavior
change anywhere.

Fixes: c898f6d7b093b ("Bluetooth: hci_sync: Introduce hci_cmd_sync_run/hci_cmd_sync_run_once")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 45d16639874a..6283a4df78b0 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -801,8 +801,15 @@ int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
 		return -ENETDOWN;
 
 	/* If on cmd_sync_work then run immediately otherwise queue */
-	if (current_work() == &hdev->cmd_sync_work)
-		return func(hdev, data);
+	if (current_work() == &hdev->cmd_sync_work) {
+		int err;
+
+		err = func(hdev, data);
+		if (destroy)
+			destroy(hdev, data, err);
+
+		return 0;
+	}
 
 	return hci_cmd_sync_submit(hdev, func, data, destroy);
 }
-- 
cgit v1.2.3


From 8a5b0135d4a5d9683203a3d9a12a711ccec5936b Mon Sep 17 00:00:00 2001
From: Cen Zhang <zzzccc427@gmail.com>
Date: Thu, 26 Mar 2026 23:16:45 +0800
Subject: Bluetooth: SCO: fix race conditions in sco_sock_connect()

sco_sock_connect() checks sk_state and sk_type without holding
the socket lock. Two concurrent connect() syscalls on the same
socket can both pass the check and enter sco_connect(), leading
to use-after-free.

The buggy scenario involves three participants and was confirmed
with additional logging instrumentation:

  Thread A (connect):    HCI disconnect:      Thread B (connect):

  sco_sock_connect(sk)                        sco_sock_connect(sk)
  sk_state==BT_OPEN                           sk_state==BT_OPEN
  (pass, no lock)                             (pass, no lock)
  sco_connect(sk):                            sco_connect(sk):
    hci_dev_lock                                hci_dev_lock
    hci_connect_sco                               <- blocked
      -> hcon1
    sco_conn_add->conn1
    lock_sock(sk)
    sco_chan_add:
      conn1->sk = sk
      sk->conn = conn1
    sk_state=BT_CONNECT
    release_sock
    hci_dev_unlock
                           hci_dev_lock
                           sco_conn_del:
                             lock_sock(sk)
                             sco_chan_del:
                               sk->conn=NULL
                               conn1->sk=NULL
                               sk_state=
                                 BT_CLOSED
                               SOCK_ZAPPED
                             release_sock
                           hci_dev_unlock
                                                  (unblocked)
                                                  hci_connect_sco
                                                    -> hcon2
                                                  sco_conn_add
                                                    -> conn2
                                                  lock_sock(sk)
                                                  sco_chan_add:
                                                    sk->conn=conn2
                                                  sk_state=
                                                    BT_CONNECT
                                                  // zombie sk!
                                                  release_sock
                                                  hci_dev_unlock

Thread B revives a BT_CLOSED + SOCK_ZAPPED socket back to
BT_CONNECT. Subsequent cleanup triggers double sock_put() and
use-after-free. Meanwhile conn1 is leaked as it was orphaned
when sco_conn_del() cleared the association.

Fix this by:
- Moving lock_sock() before the sk_state/sk_type checks in
  sco_sock_connect() to serialize concurrent connect attempts
- Fixing the sk_type != SOCK_SEQPACKET check to actually
  return the error instead of just assigning it
- Adding a state re-check in sco_connect() after lock_sock()
  to catch state changes during the window between the locks
- Adding sco_pi(sk)->conn check in sco_chan_add() to prevent
  double-attach of a socket to multiple connections
- Adding hci_conn_drop() on sco_chan_add failure to prevent
  HCI connection leaks

Fixes: 9a8ec9e8ebb5 ("Bluetooth: SCO: Fix possible circular locking dependency on sco_connect_cfm")
Signed-off-by: Cen Zhang <zzzccc427@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/sco.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 584e059de20a..b84587811ef4 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -298,7 +298,7 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk,
 	int err = 0;
 
 	sco_conn_lock(conn);
-	if (conn->sk)
+	if (conn->sk || sco_pi(sk)->conn)
 		err = -EBUSY;
 	else
 		__sco_chan_add(conn, sk, parent);
@@ -353,9 +353,20 @@ static int sco_connect(struct sock *sk)
 
 	lock_sock(sk);
 
+	/* Recheck state after reacquiring the socket lock, as another
+	 * thread may have changed it (e.g., closed the socket).
+	 */
+	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+		release_sock(sk);
+		hci_conn_drop(hcon);
+		err = -EBADFD;
+		goto unlock;
+	}
+
 	err = sco_chan_add(conn, sk, NULL);
 	if (err) {
 		release_sock(sk);
+		hci_conn_drop(hcon);
 		goto unlock;
 	}
 
@@ -656,13 +667,18 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr_unsized *addr,
 	    addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
-	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND)
+	lock_sock(sk);
+
+	if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
+		release_sock(sk);
 		return -EBADFD;
+	}
 
-	if (sk->sk_type != SOCK_SEQPACKET)
-		err = -EINVAL;
+	if (sk->sk_type != SOCK_SEQPACKET) {
+		release_sock(sk);
+		return -EINVAL;
+	}
 
-	lock_sock(sk);
 	/* Set destination address and psm */
 	bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr);
 	release_sock(sk);
-- 
cgit v1.2.3


From 2b2bf47cd75518c36fa2d41380e4a40641cc89cd Mon Sep 17 00:00:00 2001
From: Oleh Konko <security@1seal.org>
Date: Thu, 26 Mar 2026 17:31:24 +0000
Subject: Bluetooth: hci_event: move wake reason storage into validated event
 handlers

hci_store_wake_reason() is called from hci_event_packet() immediately
after stripping the HCI event header but before hci_event_func()
enforces the per-event minimum payload length from hci_ev_table.
This means a short HCI event frame can reach bacpy() before any bounds
check runs.

Rather than duplicating skb parsing and per-event length checks inside
hci_store_wake_reason(), move wake-address storage into the individual
event handlers after their existing event-length validation has
succeeded. Convert hci_store_wake_reason() into a small helper that only
stores an already-validated bdaddr while the caller holds hci_dev_lock().
Use the same helper after hci_event_func() with a NULL address to
preserve the existing unexpected-wake fallback semantics when no
validated event handler records a wake address.

Annotate the helper with __must_hold(&hdev->lock) and add
lockdep_assert_held(&hdev->lock) so future call paths keep the lock
contract explicit.

Call the helper from hci_conn_request_evt(), hci_conn_complete_evt(),
hci_sync_conn_complete_evt(), le_conn_complete_evt(),
hci_le_adv_report_evt(), hci_le_ext_adv_report_evt(),
hci_le_direct_adv_report_evt(), hci_le_pa_sync_established_evt(), and
hci_le_past_received_evt().

Fixes: 2f20216c1d6f ("Bluetooth: Emit controller suspend and resume events")
Cc: stable@vger.kernel.org
Signed-off-by: Oleh Konko <security@1seal.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 94 ++++++++++++++++++-----------------------------
 1 file changed, 35 insertions(+), 59 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 286529d2e554..81d2f9a3eec9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -80,6 +80,10 @@ static void *hci_le_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb,
 	return data;
 }
 
+static void hci_store_wake_reason(struct hci_dev *hdev,
+				  const bdaddr_t *bdaddr, u8 addr_type)
+	__must_hold(&hdev->lock);
+
 static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data,
 				struct sk_buff *skb)
 {
@@ -3111,6 +3115,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "status 0x%2.2x", status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
 
 	/* Check for existing connection:
 	 *
@@ -3274,6 +3279,10 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data,
 
 	bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type);
 
+	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
+	hci_dev_unlock(hdev);
+
 	/* Reject incoming connection from device with same BD ADDR against
 	 * CVE-2020-26555
 	 */
@@ -5021,6 +5030,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "status 0x%2.2x", status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, BDADDR_BREDR);
 
 	conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr);
 	if (!conn) {
@@ -5713,6 +5723,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
 	int err;
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, bdaddr, bdaddr_type);
 
 	/* All controllers implicitly stop advertising in the event of a
 	 * connection, so ensure that the state bit is cleared.
@@ -6005,6 +6016,7 @@ static void hci_le_past_received_evt(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type);
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
@@ -6403,6 +6415,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data,
 					info->length + 1))
 			break;
 
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
+
 		if (info->length <= max_adv_len(hdev)) {
 			rssi = info->data[info->length];
 			process_adv_report(hdev, info->type, &info->bdaddr,
@@ -6491,6 +6505,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data,
 					info->length))
 			break;
 
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
+
 		evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK;
 		legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type);
 
@@ -6536,6 +6552,7 @@ static void hci_le_pa_sync_established_evt(struct hci_dev *hdev, void *data,
 	bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
 
 	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, &ev->bdaddr, ev->bdaddr_type);
 
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
@@ -6834,6 +6851,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data,
 	for (i = 0; i < ev->num; i++) {
 		struct hci_ev_le_direct_adv_info *info = &ev->info[i];
 
+		hci_store_wake_reason(hdev, &info->bdaddr, info->bdaddr_type);
+
 		process_adv_report(hdev, info->type, &info->bdaddr,
 				   info->bdaddr_type, &info->direct_addr,
 				   info->direct_addr_type, HCI_ADV_PHY_1M, 0,
@@ -7517,73 +7536,29 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 	return true;
 }
 
-static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
-				  struct sk_buff *skb)
+static void hci_store_wake_reason(struct hci_dev *hdev,
+				  const bdaddr_t *bdaddr, u8 addr_type)
+	__must_hold(&hdev->lock)
 {
-	struct hci_ev_le_advertising_info *adv;
-	struct hci_ev_le_direct_adv_info *direct_adv;
-	struct hci_ev_le_ext_adv_info *ext_adv;
-	const struct hci_ev_conn_complete *conn_complete = (void *)skb->data;
-	const struct hci_ev_conn_request *conn_request = (void *)skb->data;
-
-	hci_dev_lock(hdev);
+	lockdep_assert_held(&hdev->lock);
 
 	/* If we are currently suspended and this is the first BT event seen,
 	 * save the wake reason associated with the event.
 	 */
 	if (!hdev->suspended || hdev->wake_reason)
-		goto unlock;
+		return;
+
+	if (!bdaddr) {
+		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
+		return;
+	}
 
 	/* Default to remote wake. Values for wake_reason are documented in the
 	 * Bluez mgmt api docs.
 	 */
 	hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE;
-
-	/* Once configured for remote wakeup, we should only wake up for
-	 * reconnections. It's useful to see which device is waking us up so
-	 * keep track of the bdaddr of the connection event that woke us up.
-	 */
-	if (event == HCI_EV_CONN_REQUEST) {
-		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
-		hdev->wake_addr_type = BDADDR_BREDR;
-	} else if (event == HCI_EV_CONN_COMPLETE) {
-		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
-		hdev->wake_addr_type = BDADDR_BREDR;
-	} else if (event == HCI_EV_LE_META) {
-		struct hci_ev_le_meta *le_ev = (void *)skb->data;
-		u8 subevent = le_ev->subevent;
-		u8 *ptr = &skb->data[sizeof(*le_ev)];
-		u8 num_reports = *ptr;
-
-		if ((subevent == HCI_EV_LE_ADVERTISING_REPORT ||
-		     subevent == HCI_EV_LE_DIRECT_ADV_REPORT ||
-		     subevent == HCI_EV_LE_EXT_ADV_REPORT) &&
-		    num_reports) {
-			adv = (void *)(ptr + 1);
-			direct_adv = (void *)(ptr + 1);
-			ext_adv = (void *)(ptr + 1);
-
-			switch (subevent) {
-			case HCI_EV_LE_ADVERTISING_REPORT:
-				bacpy(&hdev->wake_addr, &adv->bdaddr);
-				hdev->wake_addr_type = adv->bdaddr_type;
-				break;
-			case HCI_EV_LE_DIRECT_ADV_REPORT:
-				bacpy(&hdev->wake_addr, &direct_adv->bdaddr);
-				hdev->wake_addr_type = direct_adv->bdaddr_type;
-				break;
-			case HCI_EV_LE_EXT_ADV_REPORT:
-				bacpy(&hdev->wake_addr, &ext_adv->bdaddr);
-				hdev->wake_addr_type = ext_adv->bdaddr_type;
-				break;
-			}
-		}
-	} else {
-		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
-	}
-
-unlock:
-	hci_dev_unlock(hdev);
+	bacpy(&hdev->wake_addr, bdaddr);
+	hdev->wake_addr_type = addr_type;
 }
 
 #define HCI_EV_VL(_op, _func, _min_len, _max_len) \
@@ -7830,14 +7805,15 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
-	/* Store wake reason if we're suspended */
-	hci_store_wake_reason(hdev, event, skb);
-
 	bt_dev_dbg(hdev, "event 0x%2.2x", event);
 
 	hci_event_func(hdev, event, skb, &opcode, &status, &req_complete,
 		       &req_complete_skb);
 
+	hci_dev_lock(hdev);
+	hci_store_wake_reason(hdev, NULL, 0);
+	hci_dev_unlock(hdev);
+
 	if (req_complete) {
 		req_complete(hdev, status, opcode);
 	} else if (req_complete_skb) {
-- 
cgit v1.2.3


From 2969554bcfccb5c609f6b6cd4a014933f3a66dd0 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Wed, 25 Mar 2026 21:07:43 +0200
Subject: Bluetooth: hci_sync: hci_cmd_sync_queue_once() return -EEXIST if
 exists

hci_cmd_sync_queue_once() needs to indicate whether a queue item was
added, so caller can know if callbacks are called, so it can avoid
leaking resources.

Change the function to return -EEXIST if queue item already exists.

Modify all callsites to handle that.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 53 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 36 insertions(+), 17 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 6283a4df78b0..97745710e3ce 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -780,7 +780,7 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
 			    void *data, hci_cmd_sync_work_destroy_t destroy)
 {
 	if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy))
-		return 0;
+		return -EEXIST;
 
 	return hci_cmd_sync_queue(hdev, func, data, destroy);
 }
@@ -3262,6 +3262,8 @@ static int update_passive_scan_sync(struct hci_dev *hdev, void *data)
 
 int hci_update_passive_scan(struct hci_dev *hdev)
 {
+	int err;
+
 	/* Only queue if it would have any effect */
 	if (!test_bit(HCI_UP, &hdev->flags) ||
 	    test_bit(HCI_INIT, &hdev->flags) ||
@@ -3271,8 +3273,9 @@ int hci_update_passive_scan(struct hci_dev *hdev)
 	    hci_dev_test_flag(hdev, HCI_UNREGISTER))
 		return 0;
 
-	return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL,
-				       NULL);
+	err = hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL,
+				      NULL);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val)
@@ -6965,8 +6968,11 @@ static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data)
 
 int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn,
-				       NULL);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn,
+				      NULL);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err)
@@ -7002,8 +7008,11 @@ done:
 
 int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn,
-				       create_le_conn_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn,
+				      create_le_conn_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn)
@@ -7210,8 +7219,11 @@ done:
 
 int hci_connect_pa_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
-				       create_pa_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_pa_create_sync, conn,
+				      create_pa_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void create_big_complete(struct hci_dev *hdev, void *data, int err)
@@ -7273,8 +7285,11 @@ static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
 
 int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn)
 {
-	return hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
-				       create_big_complete);
+	int err;
+
+	err = hci_cmd_sync_queue_once(hdev, hci_le_big_create_sync, conn,
+				      create_big_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 struct past_data {
@@ -7366,7 +7381,7 @@ int hci_past_sync(struct hci_conn *conn, struct hci_conn *le)
 	if (err)
 		kfree(data);
 
-	return err;
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void le_read_features_complete(struct hci_dev *hdev, void *data, int err)
@@ -7453,7 +7468,7 @@ int hci_le_read_remote_features(struct hci_conn *conn)
 	else
 		err = -EOPNOTSUPP;
 
-	return err;
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void pkt_type_changed(struct hci_dev *hdev, void *data, int err)
@@ -7479,6 +7494,7 @@ int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type)
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_change_conn_ptype *cp;
+	int err;
 
 	cp = kmalloc_obj(*cp);
 	if (!cp)
@@ -7487,8 +7503,9 @@ int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type)
 	cp->handle = cpu_to_le16(conn->handle);
 	cp->pkt_type = cpu_to_le16(pkt_type);
 
-	return hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp,
-				       pkt_type_changed);
+	err = hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp,
+				      pkt_type_changed);
+	return (err == -EEXIST) ? 0 : err;
 }
 
 static void le_phy_update_complete(struct hci_dev *hdev, void *data, int err)
@@ -7514,6 +7531,7 @@ int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys)
 {
 	struct hci_dev *hdev = conn->hdev;
 	struct hci_cp_le_set_phy *cp;
+	int err;
 
 	cp = kmalloc_obj(*cp);
 	if (!cp)
@@ -7524,6 +7542,7 @@ int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys)
 	cp->tx_phys = tx_phys;
 	cp->rx_phys = rx_phys;
 
-	return hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp,
-				       le_phy_update_complete);
+	err = hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp,
+				      le_phy_update_complete);
+	return (err == -EEXIST) ? 0 : err;
 }
-- 
cgit v1.2.3


From aca377208e7f7322bf4e107cdec6e7d7e8aa7a88 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Wed, 25 Mar 2026 21:07:44 +0200
Subject: Bluetooth: hci_sync: fix leaks when hci_cmd_sync_queue_once fails

When hci_cmd_sync_queue_once() returns with error, the destroy callback
will not be called.

Fix leaking references / memory on these failures.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 97745710e3ce..8cbbba50e77e 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -7460,13 +7460,16 @@ int hci_le_read_remote_features(struct hci_conn *conn)
 	 * role is possible. Otherwise just transition into the
 	 * connected state without requesting the remote features.
 	 */
-	if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES))
+	if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) {
 		err = hci_cmd_sync_queue_once(hdev,
 					      hci_le_read_remote_features_sync,
 					      hci_conn_hold(conn),
 					      le_read_features_complete);
-	else
+		if (err)
+			hci_conn_drop(conn);
+	} else {
 		err = -EOPNOTSUPP;
+	}
 
 	return (err == -EEXIST) ? 0 : err;
 }
@@ -7505,6 +7508,9 @@ int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type)
 
 	err = hci_cmd_sync_queue_once(hdev, hci_change_conn_ptype_sync, cp,
 				      pkt_type_changed);
+	if (err)
+		kfree(cp);
+
 	return (err == -EEXIST) ? 0 : err;
 }
 
@@ -7544,5 +7550,8 @@ int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys)
 
 	err = hci_cmd_sync_queue_once(hdev, hci_le_set_phy_sync, cp,
 				      le_phy_update_complete);
+	if (err)
+		kfree(cp);
+
 	return (err == -EEXIST) ? 0 : err;
 }
-- 
cgit v1.2.3


From 035c25007c9e698bef3826070ee34bb6d778020c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 25 Mar 2026 11:11:46 -0400
Subject: Bluetooth: hci_sync: Fix UAF in le_read_features_complete

This fixes the following backtrace caused by hci_conn being freed
before le_read_features_complete but after
hci_le_read_remote_features_sync so hci_conn_del -> hci_cmd_sync_dequeue
is not able to prevent it:

==================================================================
BUG: KASAN: slab-use-after-free in instrument_atomic_read_write include/linux/instrumented.h:96 [inline]
BUG: KASAN: slab-use-after-free in atomic_dec_and_test include/linux/atomic/atomic-instrumented.h:1383 [inline]
BUG: KASAN: slab-use-after-free in hci_conn_drop include/net/bluetooth/hci_core.h:1688 [inline]
BUG: KASAN: slab-use-after-free in le_read_features_complete+0x5b/0x340 net/bluetooth/hci_sync.c:7344
Write of size 4 at addr ffff8880796b0010 by task kworker/u9:0/52

CPU: 0 UID: 0 PID: 52 Comm: kworker/u9:0 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/25/2025
Workqueue: hci0 hci_cmd_sync_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xcd/0x630 mm/kasan/report.c:482
 kasan_report+0xe0/0x110 mm/kasan/report.c:595
 check_region_inline mm/kasan/generic.c:194 [inline]
 kasan_check_range+0x100/0x1b0 mm/kasan/generic.c:200
 instrument_atomic_read_write include/linux/instrumented.h:96 [inline]
 atomic_dec_and_test include/linux/atomic/atomic-instrumented.h:1383 [inline]
 hci_conn_drop include/net/bluetooth/hci_core.h:1688 [inline]
 le_read_features_complete+0x5b/0x340 net/bluetooth/hci_sync.c:7344
 hci_cmd_sync_work+0x1ff/0x430 net/bluetooth/hci_sync.c:334
 process_one_work+0x9ba/0x1b20 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x6c8/0xf10 kernel/workqueue.c:3421
 kthread+0x3c5/0x780 kernel/kthread.c:463
 ret_from_fork+0x983/0xb10 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246
 </TASK>

Allocated by task 5932:
 kasan_save_stack+0x33/0x60 mm/kasan/common.c:56
 kasan_save_track+0x14/0x30 mm/kasan/common.c:77
 poison_kmalloc_redzone mm/kasan/common.c:400 [inline]
 __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:417
 kmalloc_noprof include/linux/slab.h:957 [inline]
 kzalloc_noprof include/linux/slab.h:1094 [inline]
 __hci_conn_add+0xf8/0x1c70 net/bluetooth/hci_conn.c:963
 hci_conn_add_unset+0x76/0x100 net/bluetooth/hci_conn.c:1084
 le_conn_complete_evt+0x639/0x1f20 net/bluetooth/hci_event.c:5714
 hci_le_enh_conn_complete_evt+0x23d/0x380 net/bluetooth/hci_event.c:5861
 hci_le_meta_evt+0x357/0x5e0 net/bluetooth/hci_event.c:7408
 hci_event_func net/bluetooth/hci_event.c:7716 [inline]
 hci_event_packet+0x685/0x11c0 net/bluetooth/hci_event.c:7773
 hci_rx_work+0x2c9/0xeb0 net/bluetooth/hci_core.c:4076
 process_one_work+0x9ba/0x1b20 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x6c8/0xf10 kernel/workqueue.c:3421
 kthread+0x3c5/0x780 kernel/kthread.c:463
 ret_from_fork+0x983/0xb10 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246

Freed by task 5932:
 kasan_save_stack+0x33/0x60 mm/kasan/common.c:56
 kasan_save_track+0x14/0x30 mm/kasan/common.c:77
 __kasan_save_free_info+0x3b/0x60 mm/kasan/generic.c:587
 kasan_save_free_info mm/kasan/kasan.h:406 [inline]
 poison_slab_object mm/kasan/common.c:252 [inline]
 __kasan_slab_free+0x5f/0x80 mm/kasan/common.c:284
 kasan_slab_free include/linux/kasan.h:234 [inline]
 slab_free_hook mm/slub.c:2540 [inline]
 slab_free mm/slub.c:6663 [inline]
 kfree+0x2f8/0x6e0 mm/slub.c:6871
 device_release+0xa4/0x240 drivers/base/core.c:2565
 kobject_cleanup lib/kobject.c:689 [inline]
 kobject_release lib/kobject.c:720 [inline]
 kref_put include/linux/kref.h:65 [inline]
 kobject_put+0x1e7/0x590 lib/kobject.c:737
 put_device drivers/base/core.c:3797 [inline]
 device_unregister+0x2f/0xc0 drivers/base/core.c:3920
 hci_conn_del_sysfs+0xb4/0x180 net/bluetooth/hci_sysfs.c:79
 hci_conn_cleanup net/bluetooth/hci_conn.c:173 [inline]
 hci_conn_del+0x657/0x1180 net/bluetooth/hci_conn.c:1234
 hci_disconn_complete_evt+0x410/0xa00 net/bluetooth/hci_event.c:3451
 hci_event_func net/bluetooth/hci_event.c:7719 [inline]
 hci_event_packet+0xa10/0x11c0 net/bluetooth/hci_event.c:7773
 hci_rx_work+0x2c9/0xeb0 net/bluetooth/hci_core.c:4076
 process_one_work+0x9ba/0x1b20 kernel/workqueue.c:3257
 process_scheduled_works kernel/workqueue.c:3340 [inline]
 worker_thread+0x6c8/0xf10 kernel/workqueue.c:3421
 kthread+0x3c5/0x780 kernel/kthread.c:463
 ret_from_fork+0x983/0xb10 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:246

The buggy address belongs to the object at ffff8880796b0000
 which belongs to the cache kmalloc-8k of size 8192
The buggy address is located 16 bytes inside of
 freed 8192-byte region [ffff8880796b0000, ffff8880796b2000)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x796b0
head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
anon flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff)
page_type: f5(slab)
raw: 00fff00000000040 ffff88813ff27280 0000000000000000 0000000000000001
raw: 0000000000000000 0000000000020002 00000000f5000000 0000000000000000
head: 00fff00000000040 ffff88813ff27280 0000000000000000 0000000000000001
head: 0000000000000000 0000000000020002 00000000f5000000 0000000000000000
head: 00fff00000000003 ffffea0001e5ac01 00000000ffffffff 00000000ffffffff
head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd2040(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 5657, tgid 5657 (dhcpcd-run-hook), ts 79819636908, free_ts 79814310558
 set_page_owner include/linux/page_owner.h:32 [inline]
 post_alloc_hook+0x1af/0x220 mm/page_alloc.c:1845
 prep_new_page mm/page_alloc.c:1853 [inline]
 get_page_from_freelist+0xd0b/0x31a0 mm/page_alloc.c:3879
 __alloc_frozen_pages_noprof+0x25f/0x2440 mm/page_alloc.c:5183
 alloc_pages_mpol+0x1fb/0x550 mm/mempolicy.c:2416
 alloc_slab_page mm/slub.c:3075 [inline]
 allocate_slab mm/slub.c:3248 [inline]
 new_slab+0x2c3/0x430 mm/slub.c:3302
 ___slab_alloc+0xe18/0x1c90 mm/slub.c:4651
 __slab_alloc.constprop.0+0x63/0x110 mm/slub.c:4774
 __slab_alloc_node mm/slub.c:4850 [inline]
 slab_alloc_node mm/slub.c:5246 [inline]
 __kmalloc_cache_noprof+0x477/0x800 mm/slub.c:5766
 kmalloc_noprof include/linux/slab.h:957 [inline]
 kzalloc_noprof include/linux/slab.h:1094 [inline]
 tomoyo_print_bprm security/tomoyo/audit.c:26 [inline]
 tomoyo_init_log+0xc8a/0x2140 security/tomoyo/audit.c:264
 tomoyo_supervisor+0x302/0x13b0 security/tomoyo/common.c:2198
 tomoyo_audit_env_log security/tomoyo/environ.c:36 [inline]
 tomoyo_env_perm+0x191/0x200 security/tomoyo/environ.c:63
 tomoyo_environ security/tomoyo/domain.c:672 [inline]
 tomoyo_find_next_domain+0xec1/0x20b0 security/tomoyo/domain.c:888
 tomoyo_bprm_check_security security/tomoyo/tomoyo.c:102 [inline]
 tomoyo_bprm_check_security+0x12d/0x1d0 security/tomoyo/tomoyo.c:92
 security_bprm_check+0x1b9/0x1e0 security/security.c:794
 search_binary_handler fs/exec.c:1659 [inline]
 exec_binprm fs/exec.c:1701 [inline]
 bprm_execve fs/exec.c:1753 [inline]
 bprm_execve+0x81e/0x1620 fs/exec.c:1729
 do_execveat_common.isra.0+0x4a5/0x610 fs/exec.c:1859
page last free pid 5657 tgid 5657 stack trace:
 reset_page_owner include/linux/page_owner.h:25 [inline]
 free_pages_prepare mm/page_alloc.c:1394 [inline]
 __free_frozen_pages+0x7df/0x1160 mm/page_alloc.c:2901
 discard_slab mm/slub.c:3346 [inline]
 __put_partials+0x130/0x170 mm/slub.c:3886
 qlink_free mm/kasan/quarantine.c:163 [inline]
 qlist_free_all+0x4c/0xf0 mm/kasan/quarantine.c:179
 kasan_quarantine_reduce+0x195/0x1e0 mm/kasan/quarantine.c:286
 __kasan_slab_alloc+0x69/0x90 mm/kasan/common.c:352
 kasan_slab_alloc include/linux/kasan.h:252 [inline]
 slab_post_alloc_hook mm/slub.c:4948 [inline]
 slab_alloc_node mm/slub.c:5258 [inline]
 __kmalloc_cache_noprof+0x274/0x800 mm/slub.c:5766
 kmalloc_noprof include/linux/slab.h:957 [inline]
 tomoyo_print_header security/tomoyo/audit.c:156 [inline]
 tomoyo_init_log+0x197/0x2140 security/tomoyo/audit.c:255
 tomoyo_supervisor+0x302/0x13b0 security/tomoyo/common.c:2198
 tomoyo_audit_env_log security/tomoyo/environ.c:36 [inline]
 tomoyo_env_perm+0x191/0x200 security/tomoyo/environ.c:63
 tomoyo_environ security/tomoyo/domain.c:672 [inline]
 tomoyo_find_next_domain+0xec1/0x20b0 security/tomoyo/domain.c:888
 tomoyo_bprm_check_security security/tomoyo/tomoyo.c:102 [inline]
 tomoyo_bprm_check_security+0x12d/0x1d0 security/tomoyo/tomoyo.c:92
 security_bprm_check+0x1b9/0x1e0 security/security.c:794
 search_binary_handler fs/exec.c:1659 [inline]
 exec_binprm fs/exec.c:1701 [inline]
 bprm_execve fs/exec.c:1753 [inline]
 bprm_execve+0x81e/0x1620 fs/exec.c:1729
 do_execveat_common.isra.0+0x4a5/0x610 fs/exec.c:1859
 do_execve fs/exec.c:1933 [inline]
 __do_sys_execve fs/exec.c:2009 [inline]
 __se_sys_execve fs/exec.c:2004 [inline]
 __x64_sys_execve+0x8e/0xb0 fs/exec.c:2004
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xcd/0xf80 arch/x86/entry/syscall_64.c:94

Memory state around the buggy address:
 ffff8880796aff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff8880796aff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff8880796b0000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                         ^
 ffff8880796b0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880796b0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

Fixes: a106e50be74b ("Bluetooth: HCI: Add support for LL Extended Feature Set")
Reported-by: syzbot+87badbb9094e008e0685@syzkaller.appspotmail.com
Tested-by: syzbot+87badbb9094e008e0685@syzkaller.appspotmail.com
Closes: https://syzbot.org/bug?extid=87badbb9094e008e0685
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Pauli Virtanen <pav@iki.fi>
---
 net/bluetooth/hci_sync.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 8cbbba50e77e..ffb0ceda6f7b 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -7390,10 +7390,8 @@ static void le_read_features_complete(struct hci_dev *hdev, void *data, int err)
 
 	bt_dev_dbg(hdev, "err %d", err);
 
-	if (err == -ECANCELED)
-		return;
-
 	hci_conn_drop(conn);
+	hci_conn_put(conn);
 }
 
 static int hci_le_read_all_remote_features_sync(struct hci_dev *hdev,
@@ -7463,10 +7461,12 @@ int hci_le_read_remote_features(struct hci_conn *conn)
 	if (conn->out || (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) {
 		err = hci_cmd_sync_queue_once(hdev,
 					      hci_le_read_remote_features_sync,
-					      hci_conn_hold(conn),
+					      hci_conn_hold(hci_conn_get(conn)),
 					      le_read_features_complete);
-		if (err)
+		if (err) {
 			hci_conn_drop(conn);
+			hci_conn_put(conn);
+		}
 	} else {
 		err = -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 0ffac654e95c1bdfe2d4edf28fb18d6ba1f103e6 Mon Sep 17 00:00:00 2001
From: Jonathan Rissanen <jonathan.rissanen@axis.com>
Date: Fri, 27 Mar 2026 11:47:21 +0100
Subject: Bluetooth: hci_h4: Fix race during initialization

Commit 5df5dafc171b ("Bluetooth: hci_uart: Fix another race during
initialization") fixed a race for hci commands sent during initialization.
However, there is still a race that happens if an hci event from one of
these commands is received before HCI_UART_REGISTERED has been set at
the end of hci_uart_register_dev(). The event will be ignored which
causes the command to fail with a timeout in the log:

"Bluetooth: hci0: command 0x1003 tx timeout"

This is because the hci event receive path (hci_uart_tty_receive ->
h4_recv) requires HCI_UART_REGISTERED to be set in h4_recv(), while the
hci command transmit path (hci_uart_send_frame -> h4_enqueue) only
requires HCI_UART_PROTO_INIT to be set in hci_uart_send_frame().

The check for HCI_UART_REGISTERED was originally added in commit
c2578202919a ("Bluetooth: Fix H4 crash from incoming UART packets")
to fix a crash caused by hu->hdev being null dereferenced. That can no
longer happen: once HCI_UART_PROTO_INIT is set in hci_uart_register_dev()
all pointers (hu, hu->priv and hu->hdev) are valid, and
hci_uart_tty_receive() already calls h4_recv() on HCI_UART_PROTO_INIT
or HCI_UART_PROTO_READY.

Remove the check for HCI_UART_REGISTERED in h4_recv() to fix the race
condition.

Fixes: 5df5dafc171b ("Bluetooth: hci_uart: Fix another race during initialization")
Signed-off-by: Jonathan Rissanen <jonathan.rissanen@axis.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_h4.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index 07cc2a79a77b..a889a66a326f 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -109,9 +109,6 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count)
 {
 	struct h4_struct *h4 = hu->priv;
 
-	if (!test_bit(HCI_UART_REGISTERED, &hu->flags))
-		return -EUNATCH;
-
 	h4->rx_skb = h4_recv_buf(hu, h4->rx_skb, data, count,
 				 h4_recv_pkts, ARRAY_SIZE(h4_recv_pkts));
 	if (IS_ERR(h4->rx_skb)) {
-- 
cgit v1.2.3


From b8dbe9648d69059cfe3a28917bfbf7e61efd7f15 Mon Sep 17 00:00:00 2001
From: Keenan Dong <keenanat2000@gmail.com>
Date: Sat, 28 Mar 2026 16:46:47 +0800
Subject: Bluetooth: MGMT: validate LTK enc_size on load

Load Long Term Keys stores the user-provided enc_size and later uses
it to size fixed-size stack operations when replying to LE LTK
requests. An enc_size larger than the 16-byte key buffer can therefore
overflow the reply stack buffer.

Reject oversized enc_size values while validating the management LTK
record so invalid keys never reach the stored key state.

Fixes: 346af67b8d11 ("Bluetooth: Add MGMT handlers for dealing with SMP LTK's")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index e5f9287fb826..adcd86c15b4e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7248,6 +7248,9 @@ static bool ltk_is_valid(struct mgmt_ltk_info *key)
 	if (key->initiator != 0x00 && key->initiator != 0x01)
 		return false;
 
+	if (key->enc_size > sizeof(key->val))
+		return false;
+
 	switch (key->addr.type) {
 	case BDADDR_LE_PUBLIC:
 		return true;
-- 
cgit v1.2.3


From a2639a7f0f5bf7d73f337f8f077c19415c62ed2c Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sun, 29 Mar 2026 16:43:01 +0300
Subject: Bluetooth: hci_conn: fix potential UAF in set_cig_params_sync

hci_conn lookup and field access must be covered by hdev lock in
set_cig_params_sync, otherwise it's possible it is freed concurrently.

Take hdev lock to prevent hci_conn from being deleted or modified
concurrently.  Just RCU lock is not suitable here, as we also want to
avoid "tearing" in the configuration.

Fixes: a091289218202 ("Bluetooth: hci_conn: Fix hci_le_set_cig_params")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index e6393f17576b..11d3ad8d2551 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1843,9 +1843,13 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data)
 	u8 aux_num_cis = 0;
 	u8 cis_id;
 
+	hci_dev_lock(hdev);
+
 	conn = hci_conn_hash_lookup_cig(hdev, cig_id);
-	if (!conn)
+	if (!conn) {
+		hci_dev_unlock(hdev);
 		return 0;
+	}
 
 	qos = &conn->iso_qos;
 	pdu->cig_id = cig_id;
@@ -1884,6 +1888,8 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data)
 	}
 	pdu->num_cis = aux_num_cis;
 
+	hci_dev_unlock(hdev);
+
 	if (!pdu->num_cis)
 		return 0;
 
-- 
cgit v1.2.3


From b255531b27da336571411248c2a72a350662bd09 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sun, 29 Mar 2026 16:43:02 +0300
Subject: Bluetooth: hci_event: fix potential UAF in
 hci_le_remote_conn_param_req_evt

hci_conn lookup and field access must be covered by hdev lock in
hci_le_remote_conn_param_req_evt, otherwise it's possible it is freed
concurrently.

Extend the hci_dev_lock critical section to cover all conn usage.

Fixes: 95118dd4edfec ("Bluetooth: hci_event: Use of a function table to handle LE subevents")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 81d2f9a3eec9..3ebc5e6d45d9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6784,25 +6784,31 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 	latency = le16_to_cpu(ev->latency);
 	timeout = le16_to_cpu(ev->timeout);
 
+	hci_dev_lock(hdev);
+
 	hcon = hci_conn_hash_lookup_handle(hdev, handle);
-	if (!hcon || hcon->state != BT_CONNECTED)
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_UNKNOWN_CONN_ID);
+	if (!hcon || hcon->state != BT_CONNECTED) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_UNKNOWN_CONN_ID);
+		goto unlock;
+	}
 
-	if (max > hcon->le_conn_max_interval)
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_INVALID_LL_PARAMS);
+	if (max > hcon->le_conn_max_interval) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_INVALID_LL_PARAMS);
+		goto unlock;
+	}
 
-	if (hci_check_conn_params(min, max, latency, timeout))
-		return send_conn_param_neg_reply(hdev, handle,
-						 HCI_ERROR_INVALID_LL_PARAMS);
+	if (hci_check_conn_params(min, max, latency, timeout)) {
+		send_conn_param_neg_reply(hdev, handle,
+					  HCI_ERROR_INVALID_LL_PARAMS);
+		goto unlock;
+	}
 
 	if (hcon->role == HCI_ROLE_MASTER) {
 		struct hci_conn_params *params;
 		u8 store_hint;
 
-		hci_dev_lock(hdev);
-
 		params = hci_conn_params_lookup(hdev, &hcon->dst,
 						hcon->dst_type);
 		if (params) {
@@ -6815,8 +6821,6 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 			store_hint = 0x00;
 		}
 
-		hci_dev_unlock(hdev);
-
 		mgmt_new_conn_param(hdev, &hcon->dst, hcon->dst_type,
 				    store_hint, min, max, latency, timeout);
 	}
@@ -6830,6 +6834,9 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, void *data,
 	cp.max_ce_len = 0;
 
 	hci_send_cmd(hdev, HCI_OP_LE_CONN_PARAM_REQ_REPLY, sizeof(cp), &cp);
+
+unlock:
+	hci_dev_unlock(hdev);
 }
 
 static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data,
-- 
cgit v1.2.3


From bda93eec78cdbfe5cda00785cefebd443e56b88b Mon Sep 17 00:00:00 2001
From: Keenan Dong <keenanat2000@gmail.com>
Date: Wed, 1 Apr 2026 22:25:26 +0800
Subject: Bluetooth: MGMT: validate mesh send advertising payload length

mesh_send() currently bounds MGMT_OP_MESH_SEND by total command
length, but it never verifies that the bytes supplied for the
flexible adv_data[] array actually match the embedded adv_data_len
field. MGMT_MESH_SEND_SIZE only covers the fixed header, so a
truncated command can still pass the existing 20..50 byte range
check and later drive the async mesh send path past the end of the
queued command buffer.

Keep rejecting zero-length and oversized advertising payloads, but
validate adv_data_len explicitly and require the command length to
exactly match the flexible array size before queueing the request.

Fixes: b338d91703fa ("Bluetooth: Implement support for Mesh")
Reported-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index adcd86c15b4e..b05bb380e5f8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2478,6 +2478,7 @@ static int mesh_send(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	struct mgmt_mesh_tx *mesh_tx;
 	struct mgmt_cp_mesh_send *send = data;
 	struct mgmt_rp_mesh_read_features rp;
+	u16 expected_len;
 	bool sending;
 	int err = 0;
 
@@ -2485,12 +2486,19 @@ static int mesh_send(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	    !hci_dev_test_flag(hdev, HCI_MESH_EXPERIMENTAL))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
 				       MGMT_STATUS_NOT_SUPPORTED);
-	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED) ||
-	    len <= MGMT_MESH_SEND_SIZE ||
-	    len > (MGMT_MESH_SEND_SIZE + 31))
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
+				       MGMT_STATUS_REJECTED);
+
+	if (!send->adv_data_len || send->adv_data_len > 31)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
 				       MGMT_STATUS_REJECTED);
 
+	expected_len = struct_size(send, adv_data, send->adv_data_len);
+	if (expected_len != len)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_MESH_SEND,
+				       MGMT_STATUS_INVALID_PARAMS);
+
 	hci_dev_lock(hdev);
 
 	memset(&rp, 0, sizeof(rp));
-- 
cgit v1.2.3


From d05111bfe37bfd8bd4d2dfe6675d6bdeef43f7c7 Mon Sep 17 00:00:00 2001
From: Oleh Konko <security@1seal.org>
Date: Tue, 31 Mar 2026 11:52:12 +0000
Subject: Bluetooth: SMP: force responder MITM requirements before building the
 pairing response

smp_cmd_pairing_req() currently builds the pairing response from the
initiator auth_req before enforcing the local BT_SECURITY_HIGH
requirement. If the initiator omits SMP_AUTH_MITM, the response can
also omit it even though the local side still requires MITM.

tk_request() then sees an auth value without SMP_AUTH_MITM and may
select JUST_CFM, making method selection inconsistent with the pairing
policy the responder already enforces.

When the local side requires HIGH security, first verify that MITM can
be achieved from the IO capabilities and then force SMP_AUTH_MITM in the
response in both rsp.auth_req and auth. This keeps the responder auth bits
and later method selection aligned.

Fixes: 2b64d153a0cc ("Bluetooth: Add MITM mechanism to LE-SMP")
Cc: stable@vger.kernel.org
Suggested-by: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Signed-off-by: Oleh Konko <security@1seal.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/smp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 485e3468bd26..deb8dd244b77 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1826,7 +1826,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (sec_level > conn->hcon->pending_sec_level)
 		conn->hcon->pending_sec_level = sec_level;
 
-	/* If we need MITM check that it can be achieved */
+	/* If we need MITM check that it can be achieved. */
 	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
 		u8 method;
 
@@ -1834,6 +1834,10 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 					 req->io_capability);
 		if (method == JUST_WORKS || method == JUST_CFM)
 			return SMP_AUTH_REQUIREMENTS;
+
+		/* Force MITM bit if it isn't set by the initiator. */
+		auth |= SMP_AUTH_MITM;
+		rsp.auth_req |= SMP_AUTH_MITM;
 	}
 
 	key_size = min(req->max_key_size, rsp.max_key_size);
-- 
cgit v1.2.3


From 20756fec2f0108cb88e815941f1ffff88dc286fe Mon Sep 17 00:00:00 2001
From: Oleh Konko <security@1seal.org>
Date: Tue, 31 Mar 2026 11:52:13 +0000
Subject: Bluetooth: SMP: derive legacy responder STK authentication from MITM
 state

The legacy responder path in smp_random() currently labels the stored
STK as authenticated whenever pending_sec_level is BT_SECURITY_HIGH.
That reflects what the local service requested, not what the pairing
flow actually achieved.

For Just Works/Confirm legacy pairing, SMP_FLAG_MITM_AUTH stays clear
and the resulting STK should remain unauthenticated even if the local
side requested HIGH security. Use the established MITM state when
storing the responder STK so the key metadata matches the pairing result.

This also keeps the legacy path aligned with the Secure Connections code,
which already treats JUST_WORKS/JUST_CFM as unauthenticated.

Fixes: fff3490f4781 ("Bluetooth: Fix setting correct authentication information for SMP STK")
Cc: stable@vger.kernel.org
Signed-off-by: Oleh Konko <security@1seal.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/smp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index deb8dd244b77..98f1da4f5f55 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1018,10 +1018,7 @@ static u8 smp_random(struct smp_chan *smp)
 
 		smp_s1(smp->tk, smp->prnd, smp->rrnd, stk);
 
-		if (hcon->pending_sec_level == BT_SECURITY_HIGH)
-			auth = 1;
-		else
-			auth = 0;
+		auth = test_bit(SMP_FLAG_MITM_AUTH, &smp->flags) ? 1 : 0;
 
 		/* Even though there's no _RESPONDER suffix this is the
 		 * responder STK we're adding for later lookup (the initiator
-- 
cgit v1.2.3


From bc39a094730ce062fa034a529c93147c096cb488 Mon Sep 17 00:00:00 2001
From: hkbinbin <hkbinbinbin@gmail.com>
Date: Tue, 31 Mar 2026 05:39:16 +0000
Subject: Bluetooth: hci_sync: fix stack buffer overflow in
 hci_le_big_create_sync
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

hci_le_big_create_sync() uses DEFINE_FLEX to allocate a
struct hci_cp_le_big_create_sync on the stack with room for 0x11 (17)
BIS entries.  However, conn->num_bis can hold up to HCI_MAX_ISO_BIS (31)
entries — validated against ISO_MAX_NUM_BIS (0x1f) in the caller
hci_conn_big_create_sync().  When conn->num_bis is between 18 and 31,
the memcpy that copies conn->bis into cp->bis writes up to 14 bytes
past the stack buffer, corrupting adjacent stack memory.

This is trivially reproducible: binding an ISO socket with
bc_num_bis = ISO_MAX_NUM_BIS (31) and calling listen() will
eventually trigger hci_le_big_create_sync() from the HCI command
sync worker, causing a KASAN-detectable stack-out-of-bounds write:

  BUG: KASAN: stack-out-of-bounds in hci_le_big_create_sync+0x256/0x3b0
  Write of size 31 at addr ffffc90000487b48 by task kworker/u9:0/71

Fix this by changing the DEFINE_FLEX count from the incorrect 0x11 to
HCI_MAX_ISO_BIS, which matches the maximum number of BIS entries that
conn->bis can actually carry.

Fixes: 42ecf1947135 ("Bluetooth: ISO: Do not emit LE BIG Create Sync if previous is pending")
Cc: stable@vger.kernel.org
Signed-off-by: hkbinbin <hkbinbinbin@gmail.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index ffb0ceda6f7b..919ec275dd23 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -7241,7 +7241,8 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err)
 
 static int hci_le_big_create_sync(struct hci_dev *hdev, void *data)
 {
-	DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis, 0x11);
+	DEFINE_FLEX(struct hci_cp_le_big_create_sync, cp, bis, num_bis,
+		    HCI_MAX_ISO_BIS);
 	struct hci_conn *conn = data;
 	struct bt_iso_qos *qos = &conn->iso_qos;
 	int err;
-- 
cgit v1.2.3


From 39ed7d89b973329cc5c764b65ba6302b17b1907e Mon Sep 17 00:00:00 2001
From: Anthony Pighin <anthony.pighin@nokia.com>
Date: Tue, 31 Mar 2026 14:26:32 -0400
Subject: i2c: imx: zero-initialize dma_slave_config for eDMA

commit 66d88e16f204 ("dmaengine: fsl-edma: read/write multiple registers
in cyclic transactions") causes fsl_edma_fill_tcd() to read
dst_port_window_size and src_port_window_size when building transfer
control descriptors.

Initialize the structure so unset fields are explicitly zero.

Fixes: 66d88e16f204 ("dmaengine: fsl-edma: read/write multiple registers in cyclic transactions")
Signed-off-by: Anthony Pighin <anthony.pighin@nokia.com>
Cc: <stable@vger.kernel.org> # v6.14+
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20260331182632.888110-1-anthony.pighin@nokia.com
---
 drivers/i2c/busses/i2c-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 452d120a210b..a208fefd3c3b 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -401,7 +401,7 @@ static void i2c_imx_reset_regs(struct imx_i2c_struct *i2c_imx)
 static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx, dma_addr_t phy_addr)
 {
 	struct imx_i2c_dma *dma;
-	struct dma_slave_config dma_sconfig;
+	struct dma_slave_config dma_sconfig = {};
 	struct device *dev = i2c_imx->adapter.dev.parent;
 	int ret;
 
-- 
cgit v1.2.3


From ffb5a4843c5bde702ed17cbcdbda98b37f7a6dad Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 31 Mar 2026 12:17:18 +0800
Subject: ipv6: fix data race in fib6_metric_set() using cmpxchg

fib6_metric_set() may be called concurrently from softirq context without
holding the FIB table lock. A typical path is:

  ndisc_router_discovery()
    spin_unlock_bh(&table->tb6_lock)        <- lock released
    fib6_metric_set(rt, RTAX_HOPLIMIT, ...) <- lockless call

When two CPUs process Router Advertisement packets for the same router
simultaneously, they can both arrive at fib6_metric_set() with the same
fib6_info pointer whose fib6_metrics still points to dst_default_metrics.

  if (f6i->fib6_metrics == &dst_default_metrics) {   /* both CPUs: true */
      struct dst_metrics *p = kzalloc_obj(*p, GFP_ATOMIC);
      refcount_set(&p->refcnt, 1);
      f6i->fib6_metrics = p;   /* CPU1 overwrites CPU0's p -> p0 leaked */
  }

The dst_metrics allocated by the losing CPU has refcnt=1 but no pointer
to it anywhere in memory, producing a kmemleak report:

  unreferenced object 0xff1100025aca1400 (size 96):
    comm "softirq", pid 0, jiffies 4299271239
    backtrace:
      kmalloc_trace+0x28a/0x380
      fib6_metric_set+0xcd/0x180
      ndisc_router_discovery+0x12dc/0x24b0
      icmpv6_rcv+0xc16/0x1360

Fix this by:
 - Set val for p->metrics before published via cmpxchg() so the metrics
   value is ready before the pointer becomes visible to other CPUs.
 - Replace the plain pointer store with cmpxchg() and free the allocation
   safely when competition failed.
 - Add READ_ONCE()/WRITE_ONCE() for metrics[] setting in the non-default
   metrics path to prevent compiler-based data races.

Fixes: d4ead6b34b67 ("net/ipv6: move metrics from dst to rt6_info")
Reported-by: Fei Liu <feliu@redhat.com>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260331-b4-fib6_metric_set-kmemleak-v3-1-88d27f4d8825@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_fib.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index dd26657b6a4a..45ef4d65dcbc 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -727,20 +727,28 @@ unlock:
 
 void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val)
 {
+	struct dst_metrics *m;
+
 	if (!f6i)
 		return;
 
-	if (f6i->fib6_metrics == &dst_default_metrics) {
+	if (READ_ONCE(f6i->fib6_metrics) == &dst_default_metrics) {
+		struct dst_metrics *dflt = (struct dst_metrics *)&dst_default_metrics;
 		struct dst_metrics *p = kzalloc_obj(*p, GFP_ATOMIC);
 
 		if (!p)
 			return;
 
+		p->metrics[metric - 1] = val;
 		refcount_set(&p->refcnt, 1);
-		f6i->fib6_metrics = p;
+		if (cmpxchg(&f6i->fib6_metrics, dflt, p) != dflt)
+			kfree(p);
+		else
+			return;
 	}
 
-	f6i->fib6_metrics->metrics[metric - 1] = val;
+	m = READ_ONCE(f6i->fib6_metrics);
+	WRITE_ONCE(m->metrics[metric - 1], val);
 }
 
 /*
-- 
cgit v1.2.3


From a54ecccfae62c5c85259ae5ea5d9c20009519049 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Tue, 31 Mar 2026 00:32:38 +0800
Subject: rds: ib: reject FRMR registration before IB connection is established

rds_ib_get_mr() extracts the rds_ib_connection from conn->c_transport_data
and passes it to rds_ib_reg_frmr() for FRWR memory registration. On a
fresh outgoing connection, ic is allocated in rds_ib_conn_alloc() with
i_cm_id = NULL because the connection worker has not yet called
rds_ib_conn_path_connect() to create the rdma_cm_id. When sendmsg() with
RDS_CMSG_RDMA_MAP is called on such a connection, the sendmsg path parses
the control message before any connection establishment, allowing
rds_ib_post_reg_frmr() to dereference ic->i_cm_id->qp and crash the
kernel.

The existing guard in rds_ib_reg_frmr() only checks for !ic (added in
commit 9e630bcb7701), which does not catch this case since ic is allocated
early and is always non-NULL once the connection object exists.

 KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
 RIP: 0010:rds_ib_post_reg_frmr+0x50e/0x920
 Call Trace:
  rds_ib_post_reg_frmr (net/rds/ib_frmr.c:167)
  rds_ib_map_frmr (net/rds/ib_frmr.c:252)
  rds_ib_reg_frmr (net/rds/ib_frmr.c:430)
  rds_ib_get_mr (net/rds/ib_rdma.c:615)
  __rds_rdma_map (net/rds/rdma.c:295)
  rds_cmsg_rdma_map (net/rds/rdma.c:860)
  rds_sendmsg (net/rds/send.c:1363)
  ____sys_sendmsg
  do_syscall_64

Add a check in rds_ib_get_mr() that verifies ic, i_cm_id, and qp are all
non-NULL before proceeding with FRMR registration, mirroring the guard
already present in rds_ib_post_inv(). Return -ENODEV when the connection
is not ready, which the existing error handling in rds_cmsg_send() converts
to -EAGAIN for userspace retry and triggers rds_conn_connect_if_down() to
start the connection worker.

Fixes: 1659185fb4d0 ("RDS: IB: Support Fastreg MR (FRMR) memory registration mode")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Reviewed-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260330163237.2752440-2-bestswngs@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rds/ib_rdma.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 077f7041df15..2cfec252eeac 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -604,8 +604,13 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		return ibmr;
 	}
 
-	if (conn)
+	if (conn) {
 		ic = conn->c_transport_data;
+		if (!ic || !ic->i_cm_id || !ic->i_cm_id->qp) {
+			ret = -ENODEV;
+			goto out;
+		}
+	}
 
 	if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) {
 		ret = -ENODEV;
-- 
cgit v1.2.3


From ad8391d37f334ee73ba91926f8b4e4cf6d31ea04 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 1 Apr 2026 00:54:15 +0000
Subject: bpf: sockmap: Fix use-after-free of sk->sk_socket in
 sk_psock_verdict_data_ready().

syzbot reported use-after-free of AF_UNIX socket's sk->sk_socket
in sk_psock_verdict_data_ready(). [0]

In unix_stream_sendmsg(), the peer socket's ->sk_data_ready() is
called after dropping its unix_state_lock().

Although the sender socket holds the peer's refcount, it does not
prevent the peer's sock_orphan(), and the peer's sk_socket might
be freed after one RCU grace period.

Let's fetch the peer's sk->sk_socket and sk->sk_socket->ops under
RCU in sk_psock_verdict_data_ready().

[0]:
BUG: KASAN: slab-use-after-free in sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278
Read of size 8 at addr ffff8880594da860 by task syz.4.1842/11013

CPU: 1 UID: 0 PID: 11013 Comm: syz.4.1842 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
Call Trace:
 <TASK>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xba/0x230 mm/kasan/report.c:482
 kasan_report+0x117/0x150 mm/kasan/report.c:595
 sk_psock_verdict_data_ready+0xec/0x590 net/core/skmsg.c:1278
 unix_stream_sendmsg+0x8a3/0xe80 net/unix/af_unix.c:2482
 sock_sendmsg_nosec net/socket.c:721 [inline]
 __sock_sendmsg net/socket.c:736 [inline]
 ____sys_sendmsg+0x972/0x9f0 net/socket.c:2585
 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2639
 __sys_sendmsg net/socket.c:2671 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7facf899c819
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007facf9827028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007facf8c15fa0 RCX: 00007facf899c819
RDX: 0000000000000000 RSI: 0000200000000500 RDI: 0000000000000004
RBP: 00007facf8a32c91 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007facf8c16038 R14: 00007facf8c15fa0 R15: 00007ffd41b01c78
 </TASK>

Allocated by task 11013:
 kasan_save_stack mm/kasan/common.c:57 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:78
 unpoison_slab_object mm/kasan/common.c:340 [inline]
 __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:366
 kasan_slab_alloc include/linux/kasan.h:253 [inline]
 slab_post_alloc_hook mm/slub.c:4538 [inline]
 slab_alloc_node mm/slub.c:4866 [inline]
 kmem_cache_alloc_lru_noprof+0x2b8/0x640 mm/slub.c:4885
 sock_alloc_inode+0x28/0xc0 net/socket.c:316
 alloc_inode+0x6a/0x1b0 fs/inode.c:347
 new_inode_pseudo include/linux/fs.h:3003 [inline]
 sock_alloc net/socket.c:631 [inline]
 __sock_create+0x12d/0x9d0 net/socket.c:1562
 sock_create net/socket.c:1656 [inline]
 __sys_socketpair+0x1c4/0x560 net/socket.c:1803
 __do_sys_socketpair net/socket.c:1856 [inline]
 __se_sys_socketpair net/socket.c:1853 [inline]
 __x64_sys_socketpair+0x9b/0xb0 net/socket.c:1853
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 15:
 kasan_save_stack mm/kasan/common.c:57 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:78
 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584
 poison_slab_object mm/kasan/common.c:253 [inline]
 __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:285
 kasan_slab_free include/linux/kasan.h:235 [inline]
 slab_free_hook mm/slub.c:2685 [inline]
 slab_free mm/slub.c:6165 [inline]
 kmem_cache_free+0x187/0x630 mm/slub.c:6295
 rcu_do_batch kernel/rcu/tree.c:2617 [inline]
 rcu_core+0x7cd/0x1070 kernel/rcu/tree.c:2869
 handle_softirqs+0x22a/0x870 kernel/softirq.c:622
 run_ksoftirqd+0x36/0x60 kernel/softirq.c:1063
 smpboot_thread_fn+0x541/0xa50 kernel/smpboot.c:160
 kthread+0x388/0x470 kernel/kthread.c:436
 ret_from_fork+0x51e/0xb90 arch/x86/kernel/process.c:158
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245

Fixes: c63829182c37 ("af_unix: Implement ->psock_update_sk_prot()")
Closes: https://lore.kernel.org/bpf/69cc6b9f.a70a0220.128fd0.004b.GAE@google.com/
Reported-by: syzbot+2184232f07e3677fbaef@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Link: https://patch.msgid.link/20260401005418.2452999-1-kuniyu@google.com
---
 net/core/skmsg.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 3261793abe83..6187a83bd741 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1267,17 +1267,20 @@ out:
 
 static void sk_psock_verdict_data_ready(struct sock *sk)
 {
-	struct socket *sock = sk->sk_socket;
-	const struct proto_ops *ops;
+	const struct proto_ops *ops = NULL;
+	struct socket *sock;
 	int copied;
 
 	trace_sk_data_ready(sk);
 
-	if (unlikely(!sock))
-		return;
-	ops = READ_ONCE(sock->ops);
+	rcu_read_lock();
+	sock = READ_ONCE(sk->sk_socket);
+	if (likely(sock))
+		ops = READ_ONCE(sock->ops);
+	rcu_read_unlock();
 	if (!ops || !ops->read_skb)
 		return;
+
 	copied = ops->read_skb(sk, sk_psock_verdict_recv);
 	if (copied >= 0) {
 		struct sk_psock *psock;
-- 
cgit v1.2.3


From d64cb81dcbd54927515a7f65e5e24affdc73c14b Mon Sep 17 00:00:00 2001
From: Yucheng Lu <kanolyc@gmail.com>
Date: Tue, 31 Mar 2026 16:00:21 +0800
Subject: net/sched: sch_netem: fix out-of-bounds access in packet corruption

In netem_enqueue(), the packet corruption logic uses
get_random_u32_below(skb_headlen(skb)) to select an index for
modifying skb->data. When an AF_PACKET TX_RING sends fully non-linear
packets over an IPIP tunnel, skb_headlen(skb) evaluates to 0.

Passing 0 to get_random_u32_below() takes the variable-ceil slow path
which returns an unconstrained 32-bit random integer. Using this
unconstrained value as an offset into skb->data results in an
out-of-bounds memory access.

Fix this by verifying skb_headlen(skb) is non-zero before attempting
to corrupt the linear data area. Fully non-linear packets will silently
bypass the corruption logic.

Fixes: c865e5d99e25 ("[PKT_SCHED] netem: packet corruption option")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Yuan Tan <tanyuan98@outlook.com>
Signed-off-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Yuhang Zheng <z1652074432@gmail.com>
Signed-off-by: Yucheng Lu <kanolyc@gmail.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Link: https://patch.msgid.link/45435c0935df877853a81e6d06205ac738ec65fa.1774941614.git.kanolyc@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_netem.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5de1c932944a..20df1c08b1e9 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -519,8 +519,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			goto finish_segs;
 		}
 
-		skb->data[get_random_u32_below(skb_headlen(skb))] ^=
-			1<<get_random_u32_below(8);
+		if (skb_headlen(skb))
+			skb->data[get_random_u32_below(skb_headlen(skb))] ^=
+				1 << get_random_u32_below(8);
 	}
 
 	if (unlikely(q->t_len >= sch->limit)) {
-- 
cgit v1.2.3


From b4e5f04c58a29c499faa85d12952ca9a4faf1cb9 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Thu, 26 Mar 2026 19:53:44 +0530
Subject: virtio_net: clamp rss_max_key_size to NETDEV_RSS_KEY_LEN

rss_max_key_size in the virtio spec is the maximum key size supported by
the device, not a mandatory size the driver must use. Also the value 40
is a spec minimum, not a spec maximum.

The current code rejects RSS and can fail probe when the device reports a
larger rss_max_key_size than the driver buffer limit. Instead, clamp the
effective key length to min(device rss_max_key_size, NETDEV_RSS_KEY_LEN)
and keep RSS enabled.

This keeps probe working on devices that advertise larger maximum key sizes
while respecting the netdev RSS key buffer size limit.

Fixes: 3f7d9c1964fc ("virtio_net: Add hash_key_length check")
Cc: stable@vger.kernel.org
Signed-off-by: Srujana Challa <schalla@marvell.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://patch.msgid.link/20260326142344.1171317-1-schalla@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ab2108ee206a..c0b9bc5574e2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -381,8 +381,6 @@ struct receive_queue {
 	struct xdp_buff **xsk_buffs;
 };
 
-#define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
-
 /* Control VQ buffers: protected by the rtnl lock */
 struct control_buf {
 	struct virtio_net_ctrl_hdr hdr;
@@ -486,7 +484,7 @@ struct virtnet_info {
 
 	/* Must be last as it ends in a flexible-array member. */
 	TRAILING_OVERLAP(struct virtio_net_rss_config_trailer, rss_trailer, hash_key_data,
-		u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+		u8 rss_hash_key_data[NETDEV_RSS_KEY_LEN];
 	);
 };
 static_assert(offsetof(struct virtnet_info, rss_trailer.hash_key_data) ==
@@ -6708,6 +6706,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	struct virtnet_info *vi;
 	u16 max_queue_pairs;
 	int mtu = 0;
+	u16 key_sz;
 
 	/* Find if host supports multiqueue/rss virtio_net device */
 	max_queue_pairs = 1;
@@ -6842,14 +6841,13 @@ static int virtnet_probe(struct virtio_device *vdev)
 	}
 
 	if (vi->has_rss || vi->has_rss_hash_report) {
-		vi->rss_key_size =
-			virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
-		if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) {
-			dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n",
-				vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE);
-			err = -EINVAL;
-			goto free;
-		}
+		key_sz = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
+
+		vi->rss_key_size = min_t(u16, key_sz, NETDEV_RSS_KEY_LEN);
+		if (key_sz > vi->rss_key_size)
+			dev_warn(&vdev->dev,
+				 "rss_max_key_size=%u exceeds driver limit %u, clamping\n",
+				 key_sz, vi->rss_key_size);
 
 		vi->rss_hash_types_supported =
 		    virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types));
-- 
cgit v1.2.3


From ce8fe5287b87e24e225c342f3b0ec04f0b3680fe Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 30 Mar 2026 21:45:40 +0300
Subject: net: macb: fix clk handling on PCI glue driver removal

platform_device_unregister() may still want to use the registered clks
during runtime resume callback.

Note that there is a commit d82d5303c4c5 ("net: macb: fix use after free
on rmmod") that addressed the similar problem of clk vs platform device
unregistration but just moved the bug to another place.

Save the pointers to clks into local variables for reuse after platform
device is unregistered.

BUG: KASAN: use-after-free in clk_prepare+0x5a/0x60
Read of size 8 at addr ffff888104f85e00 by task modprobe/597

CPU: 2 PID: 597 Comm: modprobe Not tainted 6.1.164+ #114
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.1-0-g3208b098f51a-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x8d/0xba
 print_report+0x17f/0x496
 kasan_report+0xd9/0x180
 clk_prepare+0x5a/0x60
 macb_runtime_resume+0x13d/0x410 [macb]
 pm_generic_runtime_resume+0x97/0xd0
 __rpm_callback+0xc8/0x4d0
 rpm_callback+0xf6/0x230
 rpm_resume+0xeeb/0x1a70
 __pm_runtime_resume+0xb4/0x170
 bus_remove_device+0x2e3/0x4b0
 device_del+0x5b3/0xdc0
 platform_device_del+0x4e/0x280
 platform_device_unregister+0x11/0x50
 pci_device_remove+0xae/0x210
 device_remove+0xcb/0x180
 device_release_driver_internal+0x529/0x770
 driver_detach+0xd4/0x1a0
 bus_remove_driver+0x135/0x260
 driver_unregister+0x72/0xb0
 pci_unregister_driver+0x26/0x220
 __do_sys_delete_module+0x32e/0x550
 do_syscall_64+0x35/0x80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
 </TASK>

Allocated by task 519:
 kasan_save_stack+0x2c/0x50
 kasan_set_track+0x21/0x30
 __kasan_kmalloc+0x8e/0x90
 __clk_register+0x458/0x2890
 clk_hw_register+0x1a/0x60
 __clk_hw_register_fixed_rate+0x255/0x410
 clk_register_fixed_rate+0x3c/0xa0
 macb_probe+0x1d8/0x42e [macb_pci]
 local_pci_probe+0xd7/0x190
 pci_device_probe+0x252/0x600
 really_probe+0x255/0x7f0
 __driver_probe_device+0x1ee/0x330
 driver_probe_device+0x4c/0x1f0
 __driver_attach+0x1df/0x4e0
 bus_for_each_dev+0x15d/0x1f0
 bus_add_driver+0x486/0x5e0
 driver_register+0x23a/0x3d0
 do_one_initcall+0xfd/0x4d0
 do_init_module+0x18b/0x5a0
 load_module+0x5663/0x7950
 __do_sys_finit_module+0x101/0x180
 do_syscall_64+0x35/0x80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Freed by task 597:
 kasan_save_stack+0x2c/0x50
 kasan_set_track+0x21/0x30
 kasan_save_free_info+0x2a/0x50
 __kasan_slab_free+0x106/0x180
 __kmem_cache_free+0xbc/0x320
 clk_unregister+0x6de/0x8d0
 macb_remove+0x73/0xc0 [macb_pci]
 pci_device_remove+0xae/0x210
 device_remove+0xcb/0x180
 device_release_driver_internal+0x529/0x770
 driver_detach+0xd4/0x1a0
 bus_remove_driver+0x135/0x260
 driver_unregister+0x72/0xb0
 pci_unregister_driver+0x26/0x220
 __do_sys_delete_module+0x32e/0x550
 do_syscall_64+0x35/0x80
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Fixes: d82d5303c4c5 ("net: macb: fix use after free on rmmod")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://patch.msgid.link/20260330184542.626619-1-pchelkin@ispras.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_pci.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index fc4f5aee6ab3..0ce5b736ea43 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -109,10 +109,12 @@ static void macb_remove(struct pci_dev *pdev)
 {
 	struct platform_device *plat_dev = pci_get_drvdata(pdev);
 	struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev);
+	struct clk *pclk = plat_data->pclk;
+	struct clk *hclk = plat_data->hclk;
 
-	clk_unregister(plat_data->pclk);
-	clk_unregister(plat_data->hclk);
 	platform_device_unregister(plat_dev);
+	clk_unregister(pclk);
+	clk_unregister(hclk);
 }
 
 static const struct pci_device_id dev_id_table[] = {
-- 
cgit v1.2.3


From f0f367a4f459cc8118aadc43c6bba53c60d93f8d Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Mon, 30 Mar 2026 21:45:41 +0300
Subject: net: macb: properly unregister fixed rate clocks

The additional resources allocated with clk_register_fixed_rate() need
to be released with clk_unregister_fixed_rate(), otherwise they are lost.

Fixes: 83a77e9ec415 ("net: macb: Added PCI wrapper for Platform Driver.")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Link: https://patch.msgid.link/20260330184542.626619-2-pchelkin@ispras.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_pci.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 0ce5b736ea43..b79dec17e6b0 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -96,10 +96,10 @@ static int macb_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return 0;
 
 err_plat_dev_register:
-	clk_unregister(plat_data.hclk);
+	clk_unregister_fixed_rate(plat_data.hclk);
 
 err_hclk_register:
-	clk_unregister(plat_data.pclk);
+	clk_unregister_fixed_rate(plat_data.pclk);
 
 err_pclk_register:
 	return err;
@@ -113,8 +113,8 @@ static void macb_remove(struct pci_dev *pdev)
 	struct clk *hclk = plat_data->hclk;
 
 	platform_device_unregister(plat_dev);
-	clk_unregister(pclk);
-	clk_unregister(hclk);
+	clk_unregister_fixed_rate(pclk);
+	clk_unregister_fixed_rate(hclk);
 }
 
 static const struct pci_device_id dev_id_table[] = {
-- 
cgit v1.2.3


From bf16bca6653679d8a514d6c1c5a2c67065033f14 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Mon, 30 Mar 2026 22:40:13 +0300
Subject: net/mlx5: lag: Check for LAG device before creating debugfs

__mlx5_lag_dev_add_mdev() may return 0 (success) even when an error
occurs that is handled gracefully. Consequently, the initialization
flow proceeds to call mlx5_ldev_add_debugfs() even when there is no
valid LAG context.

mlx5_ldev_add_debugfs() blindly created the debugfs directory and
attributes. This exposed interfaces (like the members file) that rely on
a valid ldev pointer, leading to potential NULL pointer dereferences if
accessed when ldev is NULL.

Add a check to verify that mlx5_lag_dev(dev) returns a valid pointer
before attempting to create the debugfs entries.

Fixes: 7f46a0b7327a ("net/mlx5: Lag, add debugfs to query hardware lag state")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260330194015.53585-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
index 62b6faa4276a..b8d5f6a44d26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -160,8 +160,11 @@ DEFINE_SHOW_ATTRIBUTE(members);
 
 void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev)
 {
+	struct mlx5_lag *ldev = mlx5_lag_dev(dev);
 	struct dentry *dbg;
 
+	if (!ldev)
+		return;
 	dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev));
 	dev->priv.dbg.lag_debugfs = dbg;
 
-- 
cgit v1.2.3


From 10dc35f6a443d488f219d1a1e3fb8f8dac422070 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Mon, 30 Mar 2026 22:40:14 +0300
Subject: net/mlx5: Avoid "No data available" when FW version queries fail

Avoid printing the misleading "kernel answers: No data available" devlink
output when querying firmware or pending firmware version fails
(e.g. MLX5 fw state errors / flash failures).

FW can fail on loading the pending flash image and get its version due
to various reasons, examples:

mlxfw: Firmware flash failed: key not applicable, err (7)
mlx5_fw_image_pending: can't read pending fw version while fw state is 1

and the resulting:
$ devlink dev info
kernel answers: No data available

Instead, just report 0 or 0xfff.. versions in case of failure to indicate
a problem, and let other information be shown.

after the fix:
$ devlink dev info
pci/0000:00:06.0:
  driver mlx5_core
  serial_number xxx...
  board.serial_number MT2225300179
  versions:
      fixed:
        fw.psid MT_0000000436
      running:
        fw.version 22.41.0188
        fw 22.41.0188
      stored:
        fw.version 255.255.65535
        fw 255.255.65535

Fixes: 9c86b07e3069 ("net/mlx5: Added fw version query command")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260330194015.53585-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c  |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/fw.c       | 53 ++++++++++++++--------
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  4 +-
 3 files changed, 37 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 6698ac55a4bf..73cf0321bb86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -107,9 +107,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	if (err)
 		return err;
 
-	err = mlx5_fw_version_query(dev, &running_fw, &stored_fw);
-	if (err)
-		return err;
+	mlx5_fw_version_query(dev, &running_fw, &stored_fw);
 
 	snprintf(version_str, sizeof(version_str), "%d.%d.%04d",
 		 mlx5_fw_ver_major(running_fw), mlx5_fw_ver_minor(running_fw),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index eeb4437975f2..c1f220e5fe18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -822,48 +822,63 @@ mlx5_fw_image_pending(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-int mlx5_fw_version_query(struct mlx5_core_dev *dev,
-			  u32 *running_ver, u32 *pending_ver)
+void mlx5_fw_version_query(struct mlx5_core_dev *dev,
+			   u32 *running_ver, u32 *pending_ver)
 {
 	u32 reg_mcqi_version[MLX5_ST_SZ_DW(mcqi_version)] = {};
 	bool pending_version_exists;
 	int component_index;
 	int err;
 
+	*running_ver = 0;
+	*pending_ver = 0;
+
 	if (!MLX5_CAP_GEN(dev, mcam_reg) || !MLX5_CAP_MCAM_REG(dev, mcqi) ||
 	    !MLX5_CAP_MCAM_REG(dev, mcqs)) {
 		mlx5_core_warn(dev, "fw query isn't supported by the FW\n");
-		return -EOPNOTSUPP;
+		return;
 	}
 
 	component_index = mlx5_get_boot_img_component_index(dev);
-	if (component_index < 0)
-		return component_index;
+	if (component_index < 0) {
+		mlx5_core_warn(dev, "fw query failed to find boot img component index, err %d\n",
+			       component_index);
+		return;
+	}
 
+	*running_ver = U32_MAX; /* indicate failure */
 	err = mlx5_reg_mcqi_version_query(dev, component_index,
 					  MCQI_FW_RUNNING_VERSION,
 					  reg_mcqi_version);
-	if (err)
-		return err;
-
-	*running_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
-
+	if (!err)
+		*running_ver = MLX5_GET(mcqi_version, reg_mcqi_version,
+					version);
+	else
+		mlx5_core_warn(dev, "failed to query running version, err %d\n",
+			       err);
+
+	*pending_ver = U32_MAX; /* indicate failure */
 	err = mlx5_fw_image_pending(dev, component_index, &pending_version_exists);
-	if (err)
-		return err;
+	if (err) {
+		mlx5_core_warn(dev, "failed to query pending image, err %d\n",
+			       err);
+		return;
+	}
 
 	if (!pending_version_exists) {
 		*pending_ver = 0;
-		return 0;
+		return;
 	}
 
 	err = mlx5_reg_mcqi_version_query(dev, component_index,
 					  MCQI_FW_STORED_VERSION,
 					  reg_mcqi_version);
-	if (err)
-		return err;
-
-	*pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
-
-	return 0;
+	if (!err)
+		*pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version,
+					version);
+	else
+		mlx5_core_warn(dev, "failed to query pending version, err %d\n",
+			       err);
+
+	return;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b635b423d972..1507e881d962 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -393,8 +393,8 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw,
 			struct netlink_ext_ack *extack);
-int mlx5_fw_version_query(struct mlx5_core_dev *dev,
-			  u32 *running_ver, u32 *stored_ver);
+void mlx5_fw_version_query(struct mlx5_core_dev *dev, u32 *running_ver,
+			   u32 *stored_ver);
 
 #ifdef CONFIG_MLX5_CORE_EN
 int mlx5e_init(void);
-- 
cgit v1.2.3


From 403186400a1a6166efe7031edc549c15fee4723f Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Mon, 30 Mar 2026 22:40:15 +0300
Subject: net/mlx5: Fix switchdev mode rollback in case of failure

If for some internal reason switchdev mode fails, we rollback to legacy
mode, before this patch, rollback will unregister the uplink netdev and
leave it unregistered causing the below kernel bug.

To fix this, we need to avoid netdev unregister by setting the proper
rollback flag 'MLX5_PRIV_FLAGS_SWITCH_LEGACY' to indicate legacy mode.

devlink (431) used greatest stack depth: 11048 bytes left
mlx5_core 0000:00:03.0: E-Switch: Disable: mode(LEGACY), nvfs(0), \
	necvfs(0), active vports(0)
mlx5_core 0000:00:03.0: E-Switch: Supported tc chains and prios offload
mlx5_core 0000:00:03.0: Loading uplink representor for vport 65535
mlx5_core 0000:00:03.0: mlx5_cmd_out_err:816:(pid 456): \
	QUERY_HCA_CAP(0x100) op_mod(0x0) failed, \
	status bad parameter(0x3), syndrome (0x3a3846), err(-22)
mlx5_core 0000:00:03.0 enp0s3np0 (unregistered): Unloading uplink \
	representor for vport 65535
 ------------[ cut here ]------------
kernel BUG at net/core/dev.c:12070!
Oops: invalid opcode: 0000 [#1] SMP NOPTI
CPU: 2 UID: 0 PID: 456 Comm: devlink Not tainted 6.16.0-rc3+ \
	#9 PREEMPT(voluntary)
RIP: 0010:unregister_netdevice_many_notify+0x123/0xae0
...
Call Trace:
[   90.923094]  unregister_netdevice_queue+0xad/0xf0
[   90.923323]  unregister_netdev+0x1c/0x40
[   90.923522]  mlx5e_vport_rep_unload+0x61/0xc6
[   90.923736]  esw_offloads_enable+0x8e6/0x920
[   90.923947]  mlx5_eswitch_enable_locked+0x349/0x430
[   90.924182]  ? is_mp_supported+0x57/0xb0
[   90.924376]  mlx5_devlink_eswitch_mode_set+0x167/0x350
[   90.924628]  devlink_nl_eswitch_set_doit+0x6f/0xf0
[   90.924862]  genl_family_rcv_msg_doit+0xe8/0x140
[   90.925088]  genl_rcv_msg+0x18b/0x290
[   90.925269]  ? __pfx_devlink_nl_pre_doit+0x10/0x10
[   90.925506]  ? __pfx_devlink_nl_eswitch_set_doit+0x10/0x10
[   90.925766]  ? __pfx_devlink_nl_post_doit+0x10/0x10
[   90.926001]  ? __pfx_genl_rcv_msg+0x10/0x10
[   90.926206]  netlink_rcv_skb+0x52/0x100
[   90.926393]  genl_rcv+0x28/0x40
[   90.926557]  netlink_unicast+0x27d/0x3d0
[   90.926749]  netlink_sendmsg+0x1f7/0x430
[   90.926942]  __sys_sendto+0x213/0x220
[   90.927127]  ? __sys_recvmsg+0x6a/0xd0
[   90.927312]  __x64_sys_sendto+0x24/0x30
[   90.927504]  do_syscall_64+0x50/0x1c0
[   90.927687]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   90.927929] RIP: 0033:0x7f7d0363e047

Fixes: 2a4f56fbcc47 ("net/mlx5e: Keep netdev when leave switchdev for devlink set legacy only")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260330194015.53585-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7a9ee36b8dca..01f6aecc4fcc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3761,6 +3761,8 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	return 0;
 
 err_vports:
+	/* rollback to legacy, indicates don't unregister the uplink netdev */
+	esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY;
 	mlx5_esw_offloads_rep_unload(esw, MLX5_VPORT_UPLINK);
 err_uplink:
 	esw_offloads_steering_cleanup(esw);
-- 
cgit v1.2.3


From ceee35e5674aa84cf9e504c2a9dae4587511556c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 30 Mar 2026 23:51:36 -0700
Subject: bnxt_en: Refactor some basic ring setup and adjustment logic

Refactor out the basic code that trims the default rings, sets up and
adjusts XDP TX rings and CP rings.  There is no change in behavior.
This is to prepare for the next bug fix patch.

Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260331065138.948205-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 53 ++++++++++++++++-------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  5 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c     |  5 +--
 4 files changed, 41 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7ed805713fbb..173f962fc2ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12992,6 +12992,21 @@ static int bnxt_tx_nr_rings_per_tc(struct bnxt *bp)
 	return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings;
 }
 
+static void bnxt_set_xdp_tx_rings(struct bnxt *bp)
+{
+	bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
+}
+
+static void bnxt_adj_tx_rings(struct bnxt *bp)
+{
+	/* Make adjustments if reserved TX rings are less than requested */
+	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	if (bp->tx_nr_rings_xdp)
+		bnxt_set_xdp_tx_rings(bp);
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -13009,13 +13024,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (rc)
 		return rc;
 
-	/* Make adjustments if reserved TX rings are less than requested */
-	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
-	if (bp->tx_nr_rings_xdp) {
-		bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
-		bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	}
+	bnxt_adj_tx_rings(bp);
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@@ -15436,11 +15445,19 @@ static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+void bnxt_set_cp_rings(struct bnxt *bp, bool sh)
+{
+	int tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
+
+	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
+			       tx_cp + bp->rx_nr_rings;
+}
+
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	bool sh = false;
-	int rc, tx_cp;
+	int rc;
 
 	if (tc > bp->max_tc) {
 		netdev_err(dev, "Too many traffic classes requested: %d. Max supported is %d.\n",
@@ -15473,9 +15490,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		bp->num_tc = 0;
 	}
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
-			       tx_cp + bp->rx_nr_rings;
+	bnxt_set_cp_rings(bp, sh);
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
@@ -16525,6 +16540,15 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp)
 	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 }
 
+static void bnxt_adj_dflt_rings(struct bnxt *bp, bool sh)
+{
+	if (sh)
+		bnxt_trim_dflt_sh_rings(bp);
+	else
+		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
+}
+
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 {
 	int dflt_rings, max_rx_rings, max_tx_rings, rc;
@@ -16550,11 +16574,8 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		return rc;
 	bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
 	bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings);
-	if (sh)
-		bnxt_trim_dflt_sh_rings(bp);
-	else
-		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
-	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
+
+	bnxt_adj_dflt_rings(bp, sh);
 
 	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
 	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a97d651130df..4bc7f7aeaab3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2985,6 +2985,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp);
 int bnxt_fw_init_one(struct bnxt *bp);
 bool bnxt_hwrm_reset_permitted(struct bnxt *bp);
+void bnxt_set_cp_rings(struct bnxt *bp, bool sh);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
 				struct bnxt_ntuple_filter *fltr, u32 idx);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 28d0ece2e7b1..0407aa1b3190 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -945,7 +945,6 @@ static int bnxt_set_channels(struct net_device *dev,
 	bool sh = false;
 	int tx_xdp = 0;
 	int rc = 0;
-	int tx_cp;
 
 	if (channel->other_count)
 		return -EINVAL;
@@ -1013,9 +1012,7 @@ static int bnxt_set_channels(struct net_device *dev,
 	if (tcs > 1)
 		bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tcs + tx_xdp;
 
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = sh ? max_t(int, tx_cp, bp->rx_nr_rings) :
-			       tx_cp + bp->rx_nr_rings;
+	bnxt_set_cp_rings(bp, sh);
 
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 85cbeb35681c..bebe37e139c9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -384,7 +384,7 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
-	int tx_xdp = 0, tx_cp, rc, tc;
+	int tx_xdp = 0, rc, tc;
 	struct bpf_prog *old;
 
 	netdev_assert_locked(dev);
@@ -431,8 +431,7 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	}
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
-	tx_cp = bnxt_num_tx_to_cp(bp, bp->tx_nr_rings);
-	bp->cp_nr_rings = max_t(int, tx_cp, bp->rx_nr_rings);
+	bnxt_set_cp_rings(bp, true);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 
-- 
cgit v1.2.3


From e4bf81dcad0a6fff2bbe5331d2c7fb30d45a788c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 30 Mar 2026 23:51:37 -0700
Subject: bnxt_en: Don't assume XDP is never enabled in
 bnxt_init_dflt_ring_mode()

The original code made the assumption that when we set up the initial
default ring mode, we must be just loading the driver and XDP cannot
be enabled yet.  This is not true when the FW goes through a resource
or capability change.  Resource reservations will be cancelled and
reinitialized with XDP already enabled.  devlink reload with XDP enabled
will also have the same issue.  This scenario will cause the ring
arithmetic to be all wrong in the bnxt_init_dflt_ring_mode() path
causing failure:

bnxt_en 0000:a1:00.0 ens2f0np0: bnxt_setup_int_mode err: ffffffea
bnxt_en 0000:a1:00.0 ens2f0np0: bnxt_request_irq err: ffffffea
bnxt_en 0000:a1:00.0 ens2f0np0: nic open fail (rc: ffffffea)

Fix it by properly accounting for XDP in the bnxt_init_dflt_ring_mode()
path by using the refactored helper functions in the previous patch.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Fixes: ec5d31e3c15d ("bnxt_en: Handle firmware reset status during IF_UP.")
Fixes: 228ea8c187d8 ("bnxt_en: implement devlink dev reload driver_reinit")
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260331065138.948205-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 173f962fc2ab..f11f3a704da5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -16547,6 +16547,10 @@ static void bnxt_adj_dflt_rings(struct bnxt *bp, bool sh)
 	else
 		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
 	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
+	if (sh && READ_ONCE(bp->xdp_prog)) {
+		bnxt_set_xdp_tx_rings(bp);
+		bnxt_set_cp_rings(bp, true);
+	}
 }
 
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
@@ -16588,16 +16592,17 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+
+	bnxt_adj_tx_rings(bp);
 	if (sh)
-		bnxt_trim_dflt_sh_rings(bp);
+		bnxt_adj_dflt_rings(bp, true);
 
 	/* Rings may have been trimmed, re-reserve the trimmed rings. */
 	if (bnxt_need_reserve_rings(bp)) {
 		rc = __bnxt_reserve_rings(bp);
 		if (rc && rc != -ENODEV)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
-		bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+		bnxt_adj_tx_rings(bp);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
@@ -16631,7 +16636,7 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp)
 	if (rc)
 		goto init_dflt_ring_err;
 
-	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	bnxt_adj_tx_rings(bp);
 
 	bnxt_set_dflt_rfs(bp);
 
-- 
cgit v1.2.3


From 071dbfa304e85a6b04a593e950d18fa170997288 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Mon, 30 Mar 2026 23:51:38 -0700
Subject: bnxt_en: Restore default stat ctxs for ULP when resource is available

During resource reservation, if the L2 driver does not have enough
MSIX vectors to provide to the RoCE driver, it sets the stat ctxs for
ULP also to 0 so that we don't have to reserve it unnecessarily.

However, subsequently the user may reduce L2 rings thereby freeing up
some resources that the L2 driver can now earmark for RoCE. In this
case, the driver should restore the default ULP stat ctxs to make
sure that all RoCE resources are ready for use.

The RoCE driver may fail to initialize in this scenario without this
fix.

Fixes: d630624ebd70 ("bnxt_en: Utilize ulp client resources if RoCE is not registered")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20260331065138.948205-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f11f3a704da5..3f775196ef81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8045,6 +8045,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		ulp_msix = bnxt_get_avail_msix(bp, bp->ulp_num_msix_want);
 		if (!ulp_msix)
 			bnxt_set_ulp_stat_ctxs(bp, 0);
+		else
+			bnxt_set_dflt_ulp_stat_ctxs(bp);
 
 		if (ulp_msix > bp->ulp_num_msix_want)
 			ulp_msix = bp->ulp_num_msix_want;
-- 
cgit v1.2.3


From 0179c6da0793ae03607002c284b53b6d584172d0 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Mon, 30 Mar 2026 17:02:42 +0200
Subject: usb: core: phy: avoid double use of 'usb3-phy'

Commit 53a2d95df836 ("usb: core: add phy notify connect and disconnect")
causes double use of the 'usb3-phy' in certain cases.

Since that commit, if a generic PHY named 'usb3-phy' is specified in
the device tree, that is getting added to the 'phy_roothub' list of the
secondary HCD by the usb_phy_roothub_alloc_usb3_phy() function. However,
that PHY is getting added also to the primary HCD's 'phy_roothub' list
by usb_phy_roothub_alloc() if there is no generic PHY specified with
'usb2-phy' name.

This causes that the usb_add_hcd() function executes each phy operations
twice on the 'usb3-phy'. Once when the primary HCD is added, then once
again when the secondary HCD is added.

The issue affects the Marvell Armada 3700 platform at least, where a
custom name is used for the USB2 PHY:

  $ git grep 'phy-names.*usb3' arch/arm64/boot/dts/marvell/armada-37xx.dtsi | tr '\t' ' '
  arch/arm64/boot/dts/marvell/armada-37xx.dtsi:    phy-names = "usb3-phy", "usb2-utmi-otg-phy";

Extend the usb_phy_roothub_alloc_usb3_phy() function to skip adding the
'usb3-phy' to the 'phy_roothub' list of the secondary HCD when 'usb2-phy'
is not specified in the device tree to avoid the double use.

Fixes: 53a2d95df836 ("usb: core: add phy notify connect and disconnect")
Cc: stable <stable@kernel.org>
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://patch.msgid.link/20260330-usb-avoid-usb3-phy-double-use-v1-1-d2113aecb535@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/phy.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/phy.c b/drivers/usb/core/phy.c
index 4bba1c275740..4d966cc9cdc9 100644
--- a/drivers/usb/core/phy.c
+++ b/drivers/usb/core/phy.c
@@ -114,7 +114,7 @@ EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc);
 struct usb_phy_roothub *usb_phy_roothub_alloc_usb3_phy(struct device *dev)
 {
 	struct usb_phy_roothub *phy_roothub;
-	int num_phys;
+	int num_phys, usb2_phy_index;
 
 	if (!IS_ENABLED(CONFIG_GENERIC_PHY))
 		return NULL;
@@ -124,6 +124,16 @@ struct usb_phy_roothub *usb_phy_roothub_alloc_usb3_phy(struct device *dev)
 	if (num_phys <= 0)
 		return NULL;
 
+	/*
+	 * If 'usb2-phy' is not present, usb_phy_roothub_alloc() added
+	 * all PHYs to the primary HCD's phy_roothub already, so skip
+	 * adding 'usb3-phy' here to avoid double use of that.
+	 */
+	usb2_phy_index = of_property_match_string(dev->of_node, "phy-names",
+						  "usb2-phy");
+	if (usb2_phy_index < 0)
+		return NULL;
+
 	phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL);
 	if (!phy_roothub)
 		return ERR_PTR(-ENOMEM);
-- 
cgit v1.2.3


From 7f6f127b9bc34bed35f56faf7ecb1561d6b39000 Mon Sep 17 00:00:00 2001
From: Yongchao Wu <yongchao.wu@autochips.com>
Date: Tue, 31 Mar 2026 08:04:07 +0800
Subject: usb: cdns3: gadget: fix NULL pointer dereference in ep_queue

When the gadget endpoint is disabled or not yet configured, the ep->desc
pointer can be NULL. This leads to a NULL pointer dereference when
__cdns3_gadget_ep_queue() is called, causing a kernel crash.

Add a check to return -ESHUTDOWN if ep->desc is NULL, which is the
standard return code for unconfigured endpoints.

This prevents potential crashes when ep_queue is called on endpoints
that are not ready.

Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Yongchao Wu <yongchao.wu@autochips.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://patch.msgid.link/20260331000407.613298-1-yongchao.wu@autochips.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index d59a60a16ec7..96d2a4c38b3f 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -2589,6 +2589,9 @@ static int __cdns3_gadget_ep_queue(struct usb_ep *ep,
 	struct cdns3_request *priv_req;
 	int ret = 0;
 
+	if (!ep->desc)
+		return -ESHUTDOWN;
+
 	request->actual = 0;
 	request->status = -EINPROGRESS;
 	priv_req = to_cdns3_request(request);
-- 
cgit v1.2.3


From 8b7a42ecdcdeb55580d9345412f7f8fc5aca3f6c Mon Sep 17 00:00:00 2001
From: JP Hein <jp@jphein.com>
Date: Mon, 30 Mar 2026 17:38:04 -0700
Subject: USB: core: add NO_LPM quirk for Razer Kiyo Pro webcam

The Razer Kiyo Pro (1532:0e05) is a USB 3.0 UVC webcam whose firmware
does not handle USB Link Power Management transitions reliably. When LPM
is active, the device can enter a state where it fails to respond to
control transfers, producing EPIPE (-32) errors on UVC probe control
SET_CUR requests. In the worst case, the stalled endpoint triggers an
xHCI stop-endpoint command that times out, causing the host controller
to be declared dead and every USB device on the bus to be disconnected.

This has been reported as Ubuntu Launchpad Bug #2061177. The failure
mode is:

  1. UVC probe control SET_CUR returns -32 (EPIPE)
  2. xHCI host not responding to stop endpoint command
  3. xHCI host controller not responding, assume dead
  4. All USB devices on the affected xHCI controller disconnect

Disabling LPM prevents the firmware from entering the problematic low-
power states that precede the stall. This is the same approach used for
other webcams with similar firmware issues (e.g., Logitech HD Webcam C270).

Cc: stable <stable@kernel.org>
Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2061177
Signed-off-by: JP Hein <jp@jphein.com>
Link: https://patch.msgid.link/20260331003806.212565-2-jp@jphein.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 26fed25da26e..0ffdaefba508 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -493,6 +493,8 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Razer - Razer Blade Keyboard */
 	{ USB_DEVICE(0x1532, 0x0116), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+	/* Razer - Razer Kiyo Pro Webcam */
+	{ USB_DEVICE(0x1532, 0x0e05), .driver_info = USB_QUIRK_NO_LPM },
 
 	/* Lenovo ThinkPad OneLink+ Dock twin hub controllers (VIA Labs VL812) */
 	{ USB_DEVICE(0x17ef, 0x1018), .driver_info = USB_QUIRK_RESET_RESUME },
-- 
cgit v1.2.3


From 33cfe0709b6bf1a7f1a16d5e8d65d003a71b6a21 Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Tue, 31 Mar 2026 20:05:08 +0800
Subject: usb: misc: usbio: Fix URB memory leak on submit failure

When usb_submit_urb() fails in usbio_probe(), the previously allocated
URB is never freed, causing a memory leak.

Fix this by jumping to err_free_urb label to properly release the URB
on the error path.

Fixes: 121a0f839dbb ("usb: misc: Add Intel USBIO bridge driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Oliver Neukum <oneukum@suse.com>
Reviewed-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Link: https://patch.msgid.link/20260331-usbio-v2-1-d8c48dad9463@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/usbio.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/misc/usbio.c b/drivers/usb/misc/usbio.c
index 2e68d48a2cc0..02d1e0760f0c 100644
--- a/drivers/usb/misc/usbio.c
+++ b/drivers/usb/misc/usbio.c
@@ -614,8 +614,10 @@ static int usbio_probe(struct usb_interface *intf, const struct usb_device_id *i
 	usb_fill_bulk_urb(usbio->urb, udev, usbio->rx_pipe, usbio->rxbuf,
 			  usbio->rxbuf_len, usbio_bulk_recv, usbio);
 	ret = usb_submit_urb(usbio->urb, GFP_KERNEL);
-	if (ret)
-		return dev_err_probe(dev, ret, "Submitting usb urb\n");
+	if (ret) {
+		dev_err_probe(dev, ret, "Submitting usb urb\n");
+		goto err_free_urb;
+	}
 
 	mutex_lock(&usbio->ctrl_mutex);
 
@@ -663,6 +665,7 @@ static int usbio_probe(struct usb_interface *intf, const struct usb_device_id *i
 err_unlock:
 	mutex_unlock(&usbio->ctrl_mutex);
 	usb_kill_urb(usbio->urb);
+err_free_urb:
 	usb_free_urb(usbio->urb);
 
 	return ret;
-- 
cgit v1.2.3


From 01af542392b5d41fd659d487015a71f627accce3 Mon Sep 17 00:00:00 2001
From: Guangshuo Li <lgs201920130244@gmail.com>
Date: Wed, 1 Apr 2026 10:51:42 +0800
Subject: usb: ulpi: fix double free in ulpi_register_interface() error path

When device_register() fails, ulpi_register() calls put_device() on
ulpi->dev.

The device release callback ulpi_dev_release() drops the OF node
reference and frees ulpi, but the current error path in
ulpi_register_interface() then calls kfree(ulpi) again, causing a
double free.

Let put_device() handle the cleanup through ulpi_dev_release() and
avoid freeing ulpi again in ulpi_register_interface().

Fixes: 289fcff4bcdb1 ("usb: add bus type for USB ULPI")
Cc: stable <stable@kernel.org>
Signed-off-by: Guangshuo Li <lgs201920130244@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://patch.msgid.link/20260401025142.1398996-1-lgs201920130244@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/common/ulpi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 56c9bfaf2ea3..b34fb65813c4 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -331,10 +331,9 @@ struct ulpi *ulpi_register_interface(struct device *dev,
 	ulpi->ops = ops;
 
 	ret = ulpi_register(dev, ulpi);
-	if (ret) {
-		kfree(ulpi);
+	if (ret)
 		return ERR_PTR(ret);
-	}
+
 
 	return ulpi;
 }
-- 
cgit v1.2.3


From 6e0e34d85cd46ceb37d16054e97a373a32770f6c Mon Sep 17 00:00:00 2001
From: Taegu Ha <hataegu0826@gmail.com>
Date: Thu, 2 Apr 2026 04:13:11 +0900
Subject: usb: gadget: f_uac1_legacy: validate control request size

f_audio_complete() copies req->length bytes into a 4-byte stack
variable:

  u32 data = 0;
  memcpy(&data, req->buf, req->length);

req->length is derived from the host-controlled USB request path,
which can lead to a stack out-of-bounds write.

Validate req->actual against the expected payload size for the
supported control selectors and decode only the expected amount
of data.

This avoids copying a host-influenced length into a fixed-size
stack object.

Signed-off-by: Taegu Ha <hataegu0826@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260401191311.3604898-1-hataegu0826@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_uac1_legacy.c | 47 +++++++++++++++++++++++------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/usb/gadget/function/f_uac1_legacy.c b/drivers/usb/gadget/function/f_uac1_legacy.c
index a0c953a99727..5d201a2e30e7 100644
--- a/drivers/usb/gadget/function/f_uac1_legacy.c
+++ b/drivers/usb/gadget/function/f_uac1_legacy.c
@@ -360,19 +360,46 @@ static int f_audio_out_ep_complete(struct usb_ep *ep, struct usb_request *req)
 static void f_audio_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct f_audio *audio = req->context;
-	int status = req->status;
-	u32 data = 0;
 	struct usb_ep *out_ep = audio->out_ep;
 
-	switch (status) {
-
-	case 0:				/* normal completion? */
-		if (ep == out_ep)
+	switch (req->status) {
+	case 0:
+		if (ep == out_ep) {
 			f_audio_out_ep_complete(ep, req);
-		else if (audio->set_con) {
-			memcpy(&data, req->buf, req->length);
-			audio->set_con->set(audio->set_con, audio->set_cmd,
-					le16_to_cpu(data));
+		} else if (audio->set_con) {
+			struct usb_audio_control *con = audio->set_con;
+			u8 type = con->type;
+			u32 data;
+			bool valid_request = false;
+
+			switch (type) {
+			case UAC_FU_MUTE: {
+				u8 value;
+
+				if (req->actual == sizeof(value)) {
+					memcpy(&value, req->buf, sizeof(value));
+					data = value;
+					valid_request = true;
+				}
+				break;
+			}
+			case UAC_FU_VOLUME: {
+				__le16 value;
+
+				if (req->actual == sizeof(value)) {
+					memcpy(&value, req->buf, sizeof(value));
+					data = le16_to_cpu(value);
+					valid_request = true;
+				}
+				break;
+			}
+			}
+
+			if (valid_request)
+				con->set(con, audio->set_cmd, data);
+			else
+				usb_ep_set_halt(ep);
+
 			audio->set_con = NULL;
 		}
 		break;
-- 
cgit v1.2.3


From 541288339b8cb8bb62be5ec0eab6c65e9dfc6055 Mon Sep 17 00:00:00 2001
From: Xiaolei Wang <xiaolei.wang@windriver.com>
Date: Wed, 1 Apr 2026 21:49:38 +0800
Subject: usb: dwc3: imx8mp: fix memory leak on probe failure path

When platform_get_drvdata() returns NULL and probe defers, the error
path jumps to the 'depopulate' label, skipping put_device() for the
reference acquired by of_find_device_by_node(). This extra reference
prevents the child platform device from being freed when
of_platform_depopulate() is called, resulting in memory leaks reported
by kmemleak:

  unreferenced object 0xffff0000c92c1480 (size 64):
    comm "kworker/u16:2", pid 50, jiffies 4294895789
    backtrace (crc 49d507d0):
      kmemleak_alloc+0x34/0x40
      __kmalloc_noprof+0x430/0x670
      of_device_alloc+0xec/0x26c
      of_platform_device_create_pdata+0x60/0x1f0
      of_platform_bus_create+0x290/0x610
      of_platform_populate+0x74/0x118
      dwc3_imx8mp_probe+0x228/0x734

Fixes: 86767625f525 ("usb: dwc3: imx8mp: disable auto suspend for host role")
Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://patch.msgid.link/20260401134938.686748-1-xiaolei.wang@windriver.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-imx8mp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c
index b3d7252bd910..1cf96540b66e 100644
--- a/drivers/usb/dwc3/dwc3-imx8mp.c
+++ b/drivers/usb/dwc3/dwc3-imx8mp.c
@@ -263,7 +263,7 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev)
 	dwc3 = platform_get_drvdata(dwc3_imx->dwc3_pdev);
 	if (!dwc3) {
 		err = dev_err_probe(dev, -EPROBE_DEFER, "failed to get dwc3 platform data\n");
-		goto depopulate;
+		goto put_dwc3;
 	}
 
 	dwc3->glue_ops = &dwc3_imx_glue_ops;
-- 
cgit v1.2.3


From c32f8748d70c8fc77676ad92ed76cede17bf2c48 Mon Sep 17 00:00:00 2001
From: Yongchao Wu <yongchao.wu@autochips.com>
Date: Wed, 1 Apr 2026 08:10:00 +0800
Subject: usb: cdns3: gadget: fix state inconsistency on gadget init failure

When cdns3_gadget_start() fails, the DRD hardware is left in gadget mode
while software state remains INACTIVE, creating hardware/software state
inconsistency.

When switching to host mode via sysfs:
  echo host > /sys/class/usb_role/13180000.usb-role-switch/role

The role state is not set to CDNS_ROLE_STATE_ACTIVE due to the error,
so cdns_role_stop() skips cleanup because state is still INACTIVE.
This violates the DRD controller design specification (Figure22),
which requires returning to idle state before switching roles.

This leads to a synchronous external abort in xhci_gen_setup() when
setting up the host controller:

[  516.440698] configfs-gadget 13180000.usb: failed to start g1: -19
[  516.442035] cdns-usb3 13180000.usb: Failed to add gadget
[  516.443278] cdns-usb3 13180000.usb: set role 2 has failed
...
[ 1301.375722] xhci-hcd xhci-hcd.1.auto: xHCI Host Controller
[ 1301.377716] Internal error: synchronous external abort: 96000010 [#1] PREEMPT SMP
[ 1301.382485] pc : xhci_gen_setup+0xa4/0x408
[ 1301.393391] backtrace:
    ...
    xhci_gen_setup+0xa4/0x408    <-- CRASH
    xhci_plat_setup+0x44/0x58
    usb_add_hcd+0x284/0x678
    ...
    cdns_role_set+0x9c/0xbc        <-- Role switch

Fix by calling cdns_drd_gadget_off() in the error path to properly
clean up the DRD gadget state.

Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Yongchao Wu <yongchao.wu@autochips.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://patch.msgid.link/20260401001000.5761-1-yongchao.wu@autochips.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-gadget.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 96d2a4c38b3f..8382231af357 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -3431,6 +3431,7 @@ static int __cdns3_gadget_init(struct cdns *cdns)
 	ret = cdns3_gadget_start(cdns);
 	if (ret) {
 		pm_runtime_put_sync(cdns->dev);
+		cdns_drd_gadget_off(cdns);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From bd3d245b0fef571f93504904df62b8865b1c0d34 Mon Sep 17 00:00:00 2001
From: Guan-Yu Lin <guanyulin@google.com>
Date: Wed, 1 Apr 2026 12:32:17 +0000
Subject: usb: core: use dedicated spinlock for offload state

Replace the coarse USB device lock with a dedicated offload_lock
spinlock to reduce contention during offload operations. Use
offload_pm_locked to synchronize with PM transitions and replace
the legacy offload_at_suspend flag.

Optimize usb_offload_get/put by switching from auto-resume/suspend
to pm_runtime_get_if_active(). This ensures offload state is only
modified when the device is already active, avoiding unnecessary
power transitions.

Cc: stable <stable@kernel.org>
Fixes: ef82a4803aab ("xhci: sideband: add api to trace sideband usage")
Signed-off-by: Guan-Yu Lin <guanyulin@google.com>
Tested-by: Hailong Liu <hailong.liu@oppo.com>
Acked-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260401123238.3790062-2-guanyulin@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/driver.c        |  23 +++++----
 drivers/usb/core/offload.c       | 102 ++++++++++++++++++++++-----------------
 drivers/usb/core/usb.c           |   1 +
 drivers/usb/host/xhci-sideband.c |   4 +-
 include/linux/usb.h              |  10 +++-
 5 files changed, 84 insertions(+), 56 deletions(-)

diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 2574e65bc640..f63004417058 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1415,14 +1415,16 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 	int			status = 0;
 	int			i = 0, n = 0;
 	struct usb_interface	*intf;
+	bool			offload_active = false;
 
 	if (udev->state == USB_STATE_NOTATTACHED ||
 			udev->state == USB_STATE_SUSPENDED)
 		goto done;
 
+	usb_offload_set_pm_locked(udev, true);
 	if (msg.event == PM_EVENT_SUSPEND && usb_offload_check(udev)) {
 		dev_dbg(&udev->dev, "device offloaded, skip suspend.\n");
-		udev->offload_at_suspend = 1;
+		offload_active = true;
 	}
 
 	/* Suspend all the interfaces and then udev itself */
@@ -1436,8 +1438,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 			 * interrupt urbs, allowing interrupt events to be
 			 * handled during system suspend.
 			 */
-			if (udev->offload_at_suspend &&
-			    intf->needs_remote_wakeup) {
+			if (offload_active && intf->needs_remote_wakeup) {
 				dev_dbg(&intf->dev,
 					"device offloaded, skip suspend.\n");
 				continue;
@@ -1452,7 +1453,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 		}
 	}
 	if (status == 0) {
-		if (!udev->offload_at_suspend)
+		if (!offload_active)
 			status = usb_suspend_device(udev, msg);
 
 		/*
@@ -1498,7 +1499,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 	 */
 	} else {
 		udev->can_submit = 0;
-		if (!udev->offload_at_suspend) {
+		if (!offload_active) {
 			for (i = 0; i < 16; ++i) {
 				usb_hcd_flush_endpoint(udev, udev->ep_out[i]);
 				usb_hcd_flush_endpoint(udev, udev->ep_in[i]);
@@ -1507,6 +1508,8 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 	}
 
  done:
+	if (status != 0)
+		usb_offload_set_pm_locked(udev, false);
 	dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status);
 	return status;
 }
@@ -1536,16 +1539,19 @@ static int usb_resume_both(struct usb_device *udev, pm_message_t msg)
 	int			status = 0;
 	int			i;
 	struct usb_interface	*intf;
+	bool			offload_active = false;
 
 	if (udev->state == USB_STATE_NOTATTACHED) {
 		status = -ENODEV;
 		goto done;
 	}
 	udev->can_submit = 1;
+	if (msg.event == PM_EVENT_RESUME)
+		offload_active = usb_offload_check(udev);
 
 	/* Resume the device */
 	if (udev->state == USB_STATE_SUSPENDED || udev->reset_resume) {
-		if (!udev->offload_at_suspend)
+		if (!offload_active)
 			status = usb_resume_device(udev, msg);
 		else
 			dev_dbg(&udev->dev,
@@ -1562,8 +1568,7 @@ static int usb_resume_both(struct usb_device *udev, pm_message_t msg)
 			 * pending interrupt urbs, allowing interrupt events
 			 * to be handled during system suspend.
 			 */
-			if (udev->offload_at_suspend &&
-			    intf->needs_remote_wakeup) {
+			if (offload_active && intf->needs_remote_wakeup) {
 				dev_dbg(&intf->dev,
 					"device offloaded, skip resume.\n");
 				continue;
@@ -1572,11 +1577,11 @@ static int usb_resume_both(struct usb_device *udev, pm_message_t msg)
 					udev->reset_resume);
 		}
 	}
-	udev->offload_at_suspend = 0;
 	usb_mark_last_busy(udev);
 
  done:
 	dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status);
+	usb_offload_set_pm_locked(udev, false);
 	if (!status)
 		udev->reset_resume = 0;
 	return status;
diff --git a/drivers/usb/core/offload.c b/drivers/usb/core/offload.c
index 7c699f1b8d2b..9db3cfedd29c 100644
--- a/drivers/usb/core/offload.c
+++ b/drivers/usb/core/offload.c
@@ -25,33 +25,30 @@
  */
 int usb_offload_get(struct usb_device *udev)
 {
-	int ret;
+	int ret = 0;
 
-	usb_lock_device(udev);
-	if (udev->state == USB_STATE_NOTATTACHED) {
-		usb_unlock_device(udev);
+	if (!usb_get_dev(udev))
 		return -ENODEV;
-	}
 
-	if (udev->state == USB_STATE_SUSPENDED ||
-		   udev->offload_at_suspend) {
-		usb_unlock_device(udev);
-		return -EBUSY;
+	if (pm_runtime_get_if_active(&udev->dev) != 1) {
+		ret = -EBUSY;
+		goto err_rpm;
 	}
 
-	/*
-	 * offload_usage could only be modified when the device is active, since
-	 * it will alter the suspend flow of the device.
-	 */
-	ret = usb_autoresume_device(udev);
-	if (ret < 0) {
-		usb_unlock_device(udev);
-		return ret;
+	spin_lock(&udev->offload_lock);
+
+	if (udev->offload_pm_locked) {
+		ret = -EAGAIN;
+		goto err;
 	}
 
 	udev->offload_usage++;
-	usb_autosuspend_device(udev);
-	usb_unlock_device(udev);
+
+err:
+	spin_unlock(&udev->offload_lock);
+	pm_runtime_put_autosuspend(&udev->dev);
+err_rpm:
+	usb_put_dev(udev);
 
 	return ret;
 }
@@ -69,35 +66,32 @@ EXPORT_SYMBOL_GPL(usb_offload_get);
  */
 int usb_offload_put(struct usb_device *udev)
 {
-	int ret;
+	int ret = 0;
 
-	usb_lock_device(udev);
-	if (udev->state == USB_STATE_NOTATTACHED) {
-		usb_unlock_device(udev);
+	if (!usb_get_dev(udev))
 		return -ENODEV;
-	}
 
-	if (udev->state == USB_STATE_SUSPENDED ||
-		   udev->offload_at_suspend) {
-		usb_unlock_device(udev);
-		return -EBUSY;
+	if (pm_runtime_get_if_active(&udev->dev) != 1) {
+		ret = -EBUSY;
+		goto err_rpm;
 	}
 
-	/*
-	 * offload_usage could only be modified when the device is active, since
-	 * it will alter the suspend flow of the device.
-	 */
-	ret = usb_autoresume_device(udev);
-	if (ret < 0) {
-		usb_unlock_device(udev);
-		return ret;
+	spin_lock(&udev->offload_lock);
+
+	if (udev->offload_pm_locked) {
+		ret = -EAGAIN;
+		goto err;
 	}
 
 	/* Drop the count when it wasn't 0, ignore the operation otherwise. */
 	if (udev->offload_usage)
 		udev->offload_usage--;
-	usb_autosuspend_device(udev);
-	usb_unlock_device(udev);
+
+err:
+	spin_unlock(&udev->offload_lock);
+	pm_runtime_put_autosuspend(&udev->dev);
+err_rpm:
+	usb_put_dev(udev);
 
 	return ret;
 }
@@ -112,25 +106,47 @@ EXPORT_SYMBOL_GPL(usb_offload_put);
  * management.
  *
  * The caller must hold @udev's device lock. In addition, the caller should
- * ensure downstream usb devices are all either suspended or marked as
- * "offload_at_suspend" to ensure the correctness of the return value.
+ * ensure the device itself and the downstream usb devices are all marked as
+ * "offload_pm_locked" to ensure the correctness of the return value.
  *
  * Returns true on any offload activity, false otherwise.
  */
 bool usb_offload_check(struct usb_device *udev) __must_hold(&udev->dev->mutex)
 {
 	struct usb_device *child;
-	bool active;
+	bool active = false;
 	int port1;
 
+	if (udev->offload_usage)
+		return true;
+
 	usb_hub_for_each_child(udev, port1, child) {
 		usb_lock_device(child);
 		active = usb_offload_check(child);
 		usb_unlock_device(child);
+
 		if (active)
-			return true;
+			break;
 	}
 
-	return !!udev->offload_usage;
+	return active;
 }
 EXPORT_SYMBOL_GPL(usb_offload_check);
+
+/**
+ * usb_offload_set_pm_locked - set the PM lock state of a USB device
+ * @udev: the USB device to modify
+ * @locked: the new lock state
+ *
+ * Setting @locked to true prevents offload_usage from being modified. This
+ * ensures that offload activities cannot be started or stopped during critical
+ * power management transitions, maintaining a stable state for the duration
+ * of the transition.
+ */
+void usb_offload_set_pm_locked(struct usb_device *udev, bool locked)
+{
+	spin_lock(&udev->offload_lock);
+	udev->offload_pm_locked = locked;
+	spin_unlock(&udev->offload_lock);
+}
+EXPORT_SYMBOL_GPL(usb_offload_set_pm_locked);
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index e9a10a33534c..df166cafe106 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -671,6 +671,7 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 	set_dev_node(&dev->dev, dev_to_node(bus->sysdev));
 	dev->state = USB_STATE_ATTACHED;
 	dev->lpm_disable_count = 1;
+	spin_lock_init(&dev->offload_lock);
 	dev->offload_usage = 0;
 	atomic_set(&dev->urbnum, 0);
 
diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c
index abbcc0e44f1b..54284d29d201 100644
--- a/drivers/usb/host/xhci-sideband.c
+++ b/drivers/usb/host/xhci-sideband.c
@@ -291,8 +291,8 @@ EXPORT_SYMBOL_GPL(xhci_sideband_get_event_buffer);
  * Allow other drivers, such as usb controller driver, to check if there are
  * any sideband activity on the host controller. This information could be used
  * for power management or other forms of resource management. The caller should
- * ensure downstream usb devices are all either suspended or marked as
- * "offload_at_suspend" to ensure the correctness of the return value.
+ * ensure downstream usb devices are all marked as "offload_pm_locked" to ensure
+ * the correctness of the return value.
  *
  * Returns true on any active sideband existence, false otherwise.
  */
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 04277af4bb9d..4aab20015851 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -21,6 +21,7 @@
 #include <linux/completion.h>	/* for struct completion */
 #include <linux/sched.h>	/* for current && schedule_timeout */
 #include <linux/mutex.h>	/* for struct mutex */
+#include <linux/spinlock.h>	/* for spinlock_t */
 #include <linux/pm_runtime.h>	/* for runtime PM */
 
 struct usb_device;
@@ -636,8 +637,9 @@ struct usb3_lpm_parameters {
  * @do_remote_wakeup:  remote wakeup should be enabled
  * @reset_resume: needs reset instead of resume
  * @port_is_suspended: the upstream port is suspended (L2 or U3)
- * @offload_at_suspend: offload activities during suspend is enabled.
+ * @offload_pm_locked: prevents offload_usage changes during PM transitions.
  * @offload_usage: number of offload activities happening on this usb device.
+ * @offload_lock: protects offload_usage and offload_pm_locked
  * @slot_id: Slot ID assigned by xHCI
  * @l1_params: best effor service latency for USB2 L1 LPM state, and L1 timeout.
  * @u1_params: exit latencies for USB3 U1 LPM state, and hub-initiated timeout.
@@ -726,8 +728,9 @@ struct usb_device {
 	unsigned do_remote_wakeup:1;
 	unsigned reset_resume:1;
 	unsigned port_is_suspended:1;
-	unsigned offload_at_suspend:1;
+	unsigned offload_pm_locked:1;
 	int offload_usage;
+	spinlock_t offload_lock;
 	enum usb_link_tunnel_mode tunnel_mode;
 	struct device_link *usb4_link;
 
@@ -849,6 +852,7 @@ static inline void usb_mark_last_busy(struct usb_device *udev)
 int usb_offload_get(struct usb_device *udev);
 int usb_offload_put(struct usb_device *udev);
 bool usb_offload_check(struct usb_device *udev);
+void usb_offload_set_pm_locked(struct usb_device *udev, bool locked);
 #else
 
 static inline int usb_offload_get(struct usb_device *udev)
@@ -857,6 +861,8 @@ static inline int usb_offload_put(struct usb_device *udev)
 { return 0; }
 static inline bool usb_offload_check(struct usb_device *udev)
 { return false; }
+static inline void usb_offload_set_pm_locked(struct usb_device *udev, bool locked)
+{ }
 #endif
 
 extern int usb_disable_lpm(struct usb_device *udev);
-- 
cgit v1.2.3


From 5abbe6ecc6203355c770bf232ade88e29c960049 Mon Sep 17 00:00:00 2001
From: Guan-Yu Lin <guanyulin@google.com>
Date: Wed, 1 Apr 2026 12:32:18 +0000
Subject: usb: host: xhci-sideband: delegate offload_usage tracking to class
 drivers

Remove usb_offload_get() and usb_offload_put() from the xHCI sideband
interrupter creation and removal paths.

The responsibility of manipulating offload_usage now lies entirely with
the USB class drivers. They have the precise context of when an offload
data stream actually starts and stops, ensuring a much more accurate
representation of offload activity for power management.

Cc: stable <stable@kernel.org>
Fixes: ef82a4803aab ("xhci: sideband: add api to trace sideband usage")
Signed-off-by: Guan-Yu Lin <guanyulin@google.com>
Tested-by: Hailong Liu <hailong.liu@oppo.com>
Tested-by: hailong.liu@oppo.com
Acked-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://patch.msgid.link/20260401123238.3790062-3-guanyulin@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-sideband.c  | 14 +-------------
 sound/usb/qcom/qc_audio_offload.c | 10 +++++++++-
 2 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/usb/host/xhci-sideband.c b/drivers/usb/host/xhci-sideband.c
index 54284d29d201..23153e136d4b 100644
--- a/drivers/usb/host/xhci-sideband.c
+++ b/drivers/usb/host/xhci-sideband.c
@@ -93,8 +93,6 @@ __xhci_sideband_remove_endpoint(struct xhci_sideband *sb, struct xhci_virt_ep *e
 static void
 __xhci_sideband_remove_interrupter(struct xhci_sideband *sb)
 {
-	struct usb_device *udev;
-
 	lockdep_assert_held(&sb->mutex);
 
 	if (!sb->ir)
@@ -102,10 +100,6 @@ __xhci_sideband_remove_interrupter(struct xhci_sideband *sb)
 
 	xhci_remove_secondary_interrupter(xhci_to_hcd(sb->xhci), sb->ir);
 	sb->ir = NULL;
-	udev = sb->vdev->udev;
-
-	if (udev->state != USB_STATE_NOTATTACHED)
-		usb_offload_put(udev);
 }
 
 /* sideband api functions */
@@ -328,9 +322,6 @@ int
 xhci_sideband_create_interrupter(struct xhci_sideband *sb, int num_seg,
 				 bool ip_autoclear, u32 imod_interval, int intr_num)
 {
-	int ret = 0;
-	struct usb_device *udev;
-
 	if (!sb || !sb->xhci)
 		return -ENODEV;
 
@@ -348,12 +339,9 @@ xhci_sideband_create_interrupter(struct xhci_sideband *sb, int num_seg,
 	if (!sb->ir)
 		return -ENOMEM;
 
-	udev = sb->vdev->udev;
-	ret = usb_offload_get(udev);
-
 	sb->ir->ip_autoclear = ip_autoclear;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(xhci_sideband_create_interrupter);
 
diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 510b68cced33..a8d313fa254a 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -699,6 +699,7 @@ static void uaudio_event_ring_cleanup_free(struct uaudio_dev *dev)
 		uaudio_iommu_unmap(MEM_EVENT_RING, IOVA_BASE, PAGE_SIZE,
 				   PAGE_SIZE);
 		xhci_sideband_remove_interrupter(uadev[dev->chip->card->number].sb);
+		usb_offload_put(dev->udev);
 	}
 }
 
@@ -1182,12 +1183,16 @@ static int uaudio_event_ring_setup(struct snd_usb_substream *subs,
 	dma_coherent = dev_is_dma_coherent(subs->dev->bus->sysdev);
 	er_pa = 0;
 
+	ret = usb_offload_get(subs->dev);
+	if (ret < 0)
+		goto exit;
+
 	/* event ring */
 	ret = xhci_sideband_create_interrupter(uadev[card_num].sb, 1, false,
 					       0, uaudio_qdev->data->intr_num);
 	if (ret < 0) {
 		dev_err(&subs->dev->dev, "failed to fetch interrupter\n");
-		goto exit;
+		goto put_offload;
 	}
 
 	sgt = xhci_sideband_get_event_buffer(uadev[card_num].sb);
@@ -1219,6 +1224,8 @@ clear_pa:
 	mem_info->dma = 0;
 remove_interrupter:
 	xhci_sideband_remove_interrupter(uadev[card_num].sb);
+put_offload:
+	usb_offload_put(subs->dev);
 exit:
 	return ret;
 }
@@ -1482,6 +1489,7 @@ unmap_er:
 	uaudio_iommu_unmap(MEM_EVENT_RING, IOVA_BASE, PAGE_SIZE, PAGE_SIZE);
 free_sec_ring:
 	xhci_sideband_remove_interrupter(uadev[card_num].sb);
+	usb_offload_put(subs->dev);
 drop_sync_ep:
 	if (subs->sync_endpoint) {
 		uaudio_iommu_unmap(MEM_XFER_RING,
-- 
cgit v1.2.3


From 4e0a88254ad59f6c53a34bf5fa241884ec09e8b2 Mon Sep 17 00:00:00 2001
From: Michael Zimmermann <sigmaepsilon92@gmail.com>
Date: Tue, 31 Mar 2026 20:48:44 +0200
Subject: usb: gadget: f_hid: move list and spinlock inits from bind to alloc

There was an issue when you did the following:
- setup and bind an hid gadget
- open /dev/hidg0
- use the resulting fd in EPOLL_CTL_ADD
- unbind the UDC
- bind the UDC
- use the fd in EPOLL_CTL_DEL

When CONFIG_DEBUG_LIST was enabled, a list_del corruption was reported
within remove_wait_queue (via ep_remove_wait_queue). After some
debugging I found out that the queues, which f_hid registers via
poll_wait were the problem. These were initialized using
init_waitqueue_head inside hidg_bind. So effectively, the bind function
re-initialized the queues while there were still items in them.

The solution is to move the initialization from hidg_bind to hidg_alloc
to extend their lifetimes to the lifetime of the function instance.

Additionally, I found many other possibly problematic init calls in the
bind function, which I moved as well.

Signed-off-by: Michael Zimmermann <sigmaepsilon92@gmail.com>
Cc: stable <stable@kernel.org>
Link: https://patch.msgid.link/20260331184844.2388761-1-sigmaepsilon92@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_hid.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 8812ebf33d14..e5ccaec7750c 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -1262,17 +1262,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f)
 	if (status)
 		goto fail;
 
-	spin_lock_init(&hidg->write_spinlock);
 	hidg->write_pending = 1;
 	hidg->req = NULL;
-	spin_lock_init(&hidg->read_spinlock);
-	spin_lock_init(&hidg->get_report_spinlock);
-	init_waitqueue_head(&hidg->write_queue);
-	init_waitqueue_head(&hidg->read_queue);
-	init_waitqueue_head(&hidg->get_queue);
-	init_waitqueue_head(&hidg->get_id_queue);
-	INIT_LIST_HEAD(&hidg->completed_out_req);
-	INIT_LIST_HEAD(&hidg->report_list);
 
 	INIT_WORK(&hidg->work, get_report_workqueue_handler);
 	hidg->workqueue = alloc_workqueue("report_work",
@@ -1608,6 +1599,16 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi)
 
 	mutex_lock(&opts->lock);
 
+	spin_lock_init(&hidg->write_spinlock);
+	spin_lock_init(&hidg->read_spinlock);
+	spin_lock_init(&hidg->get_report_spinlock);
+	init_waitqueue_head(&hidg->write_queue);
+	init_waitqueue_head(&hidg->read_queue);
+	init_waitqueue_head(&hidg->get_queue);
+	init_waitqueue_head(&hidg->get_id_queue);
+	INIT_LIST_HEAD(&hidg->completed_out_req);
+	INIT_LIST_HEAD(&hidg->report_list);
+
 	device_initialize(&hidg->dev);
 	hidg->dev.release = hidg_release;
 	hidg->dev.class = &hidg_class;
-- 
cgit v1.2.3


From 9e07e3b81807edd356e1f794cffa00a428eff443 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 1 Apr 2026 16:33:53 +0200
Subject: thermal: core: Fix thermal zone device registration error path

If thermal_zone_device_register_with_trips() fails after registering
a thermal zone device, it needs to wait for the tz->removal completion
like thermal_zone_device_unregister(), in case user space has managed
to take a reference to the thermal zone device's kobject, in which case
thermal_release() may not be called by the error path itself and tz may
be freed prematurely.

Add the missing wait_for_completion() call to the thermal zone device
registration error path.

Fixes: 04e6ccfc93c5 ("thermal: core: Fix NULL pointer dereference in zone registration error path")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: All applicable <stable@vger.kernel.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/2849815.mvXUDI8C0e@rafael.j.wysocki
---
 drivers/thermal/thermal_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5337612e484d..d1beee9e15f8 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1642,6 +1642,7 @@ unregister:
 	device_del(&tz->device);
 release_device:
 	put_device(&tz->device);
+	wait_for_completion(&tz->removal);
 remove_id:
 	ida_free(&thermal_tz_ida, id);
 free_tzp:
-- 
cgit v1.2.3


From d10a26aa4d072320530e6968ef945c8c575edf61 Mon Sep 17 00:00:00 2001
From: Martin Schiller <ms@dev.tdt.de>
Date: Tue, 31 Mar 2026 09:43:17 +0200
Subject: net/x25: Fix potential double free of skb

When alloc_skb fails in x25_queue_rx_frame it calls kfree_skb(skb) at
line 48 and returns 1 (error).
This error propagates back through the call chain:

x25_queue_rx_frame returns 1
    |
    v
x25_state3_machine receives the return value 1 and takes the else
branch at line 278, setting queued=0 and returning 0
    |
    v
x25_process_rx_frame returns queued=0
    |
    v
x25_backlog_rcv at line 452 sees queued=0 and calls kfree_skb(skb)
again

This would free the same skb twice. Looking at x25_backlog_rcv:

net/x25/x25_in.c:x25_backlog_rcv() {
    ...
    queued = x25_process_rx_frame(sk, skb);
    ...
    if (!queued)
        kfree_skb(skb);
}

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Link: https://patch.msgid.link/20260331-x25_fraglen-v4-1-3e69f18464b4@dev.tdt.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/x25/x25_in.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index b981a4828d08..0dbc73efab1c 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -44,10 +44,9 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more)
 	if (x25->fraglen > 0) {	/* End of fragment */
 		int len = x25->fraglen + skb->len;
 
-		if ((skbn = alloc_skb(len, GFP_ATOMIC)) == NULL){
-			kfree_skb(skb);
+		skbn = alloc_skb(len, GFP_ATOMIC);
+		if (!skbn)
 			return 1;
-		}
 
 		skb_queue_tail(&x25->fragment_queue, skb);
 
-- 
cgit v1.2.3


From a1822cb524e89b4cd2cf0b82e484a2335496a6d9 Mon Sep 17 00:00:00 2001
From: Martin Schiller <ms@dev.tdt.de>
Date: Tue, 31 Mar 2026 09:43:18 +0200
Subject: net/x25: Fix overflow when accumulating packets

Add a check to ensure that `x25_sock.fraglen` does not overflow.

The `fraglen` also needs to be resetted when purging `fragment_queue` in
`x25_clear_queues()`.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Suggested-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Link: https://patch.msgid.link/20260331-x25_fraglen-v4-2-3e69f18464b4@dev.tdt.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/x25/x25_in.c   | 4 ++++
 net/x25/x25_subr.c | 1 +
 2 files changed, 5 insertions(+)

diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index 0dbc73efab1c..e47ebd8acd21 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -34,6 +34,10 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more)
 	struct sk_buff *skbo, *skbn = skb;
 	struct x25_sock *x25 = x25_sk(sk);
 
+	/* make sure we don't overflow */
+	if (x25->fraglen + skb->len > USHRT_MAX)
+		return 1;
+
 	if (more) {
 		x25->fraglen += skb->len;
 		skb_queue_tail(&x25->fragment_queue, skb);
diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c
index 0285aaa1e93c..159708d9ad20 100644
--- a/net/x25/x25_subr.c
+++ b/net/x25/x25_subr.c
@@ -40,6 +40,7 @@ void x25_clear_queues(struct sock *sk)
 	skb_queue_purge(&x25->interrupt_in_queue);
 	skb_queue_purge(&x25->interrupt_out_queue);
 	skb_queue_purge(&x25->fragment_queue);
+	x25->fraglen = 0;
 }
 
 
-- 
cgit v1.2.3


From 1319ea57529e131822bab56bf417c8edc2db9ae8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Apr 2026 15:20:20 +0200
Subject: sched/fair: Fix zero_vruntime tracking fix

John reported that stress-ng-yield could make his machine unhappy and
managed to bisect it to commit b3d99f43c72b ("sched/fair: Fix
zero_vruntime tracking").

The combination of yield and that commit was specific enough to
hypothesize the following scenario:

Suppose we have 2 runnable tasks, both doing yield. Then one will be
eligible and one will not be, because the average position must be in
between these two entities.

Therefore, the runnable task will be eligible, and be promoted a full
slice (all the tasks do is yield after all). This causes it to jump over
the other task and now the other task is eligible and current is no
longer. So we schedule.

Since we are runnable, there is no {de,en}queue. All we have is the
__{en,de}queue_entity() from {put_prev,set_next}_task(). But per the
fingered commit, those two no longer move zero_vruntime.

All that moves zero_vruntime are tick and full {de,en}queue.

This means, that if the two tasks playing leapfrog can reach the
critical speed to reach the overflow point inside one tick's worth of
time, we're up a creek.

Additionally, when multiple cgroups are involved, there is no guarantee
the tick will in fact hit every cgroup in a timely manner. Statistically
speaking it will, but that same statistics does not rule out the
possibility of one cgroup not getting a tick for a significant amount of
time -- however unlikely.

Therefore, just like with the yield() case, force an update at the end
of every slice. This ensures the update is never more than a single
slice behind and the whole thing is within 2 lag bounds as per the
comment on entity_key().

Fixes: b3d99f43c72b ("sched/fair: Fix zero_vruntime tracking")
Reported-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: John Stultz <jstultz@google.com>
Link: https://patch.msgid.link/20260401132355.081530332@infradead.org
---
 kernel/sched/fair.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bf948db905ed..ab4114712be7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -707,7 +707,7 @@ void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta)
  * Called in:
  *  - place_entity()      -- before enqueue
  *  - update_entity_lag() -- before dequeue
- *  - entity_tick()
+ *  - update_deadline()   -- slice expiration
  *
  * This means it is one entry 'behind' but that puts it close enough to where
  * the bound on entity_key() is at most two lag bounds.
@@ -1131,6 +1131,7 @@ static bool update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * EEVDF: vd_i = ve_i + r_i / w_i
 	 */
 	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
+	avg_vruntime(cfs_rq);
 
 	/*
 	 * The task has consumed its request, reschedule.
@@ -5593,11 +5594,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	update_load_avg(cfs_rq, curr, UPDATE_TG);
 	update_cfs_group(curr);
 
-	/*
-	 * Pulls along cfs_rq::zero_vruntime.
-	 */
-	avg_vruntime(cfs_rq);
-
 #ifdef CONFIG_SCHED_HRTICK
 	/*
 	 * queued ticks are scheduled to match the slice, so don't bother
@@ -9128,7 +9124,7 @@ static void yield_task_fair(struct rq *rq)
 	 */
 	if (entity_eligible(cfs_rq, se)) {
 		se->vruntime = se->deadline;
-		se->deadline += calc_delta_fair(se->slice, se);
+		update_deadline(cfs_rq, se);
 	}
 }
 
-- 
cgit v1.2.3


From e08d007f9d813616ce7093600bc4fdb9c9d81d89 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 1 Apr 2026 15:20:21 +0200
Subject: sched/debug: Fix avg_vruntime() usage

John reported that stress-ng-yield could make his machine unhappy and
managed to bisect it to commit b3d99f43c72b ("sched/fair: Fix
zero_vruntime tracking").

The commit in question changes avg_vruntime() from a function that is
a pure reader, to a function that updates variables. This turns an
unlocked sched/debug usage of this function from a minor mistake into
a data corruptor.

Fixes: af4cf40470c2 ("sched/fair: Add cfs_rq::avg_vruntime")
Fixes: b3d99f43c72b ("sched/fair: Fix zero_vruntime tracking")
Reported-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: John Stultz <jstultz@google.com>
Link: https://patch.msgid.link/20260401132355.196370805@infradead.org
---
 kernel/sched/debug.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index b24f40f05019..15bf45b6f912 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -902,6 +902,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 left_vruntime = -1, zero_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+	u64 avruntime;
 	struct sched_entity *last, *first, *root;
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
@@ -925,6 +926,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	if (last)
 		right_vruntime = last->vruntime;
 	zero_vruntime = cfs_rq->zero_vruntime;
+	avruntime = avg_vruntime(cfs_rq);
 	raw_spin_rq_unlock_irqrestore(rq, flags);
 
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_deadline",
@@ -934,7 +936,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "zero_vruntime",
 			SPLIT_NS(zero_vruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "avg_vruntime",
-			SPLIT_NS(avg_vruntime(cfs_rq)));
+			SPLIT_NS(avruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "right_vruntime",
 			SPLIT_NS(right_vruntime));
 	spread = right_vruntime - left_vruntime;
-- 
cgit v1.2.3


From dbde07f06226438cd2cf1179745fa1bec5d8914a Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 12 Mar 2026 12:43:05 -0700
Subject: perf/x86: Fix potential bad container_of in intel_pmu_hw_config

Auto counter reload may have a group of events with software events
present within it. The software event PMU isn't the x86_hybrid_pmu and
a container_of operation in intel_pmu_set_acr_caused_constr (via the
hybrid helper) could cause out of bound memory reads. Avoid this by
guarding the call to intel_pmu_set_acr_caused_constr with an
is_x86_event check.

Fixes: ec980e4facef ("perf/x86/intel: Support auto counter reload")
Signed-off-by: Ian Rogers <irogers@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://patch.msgid.link/20260312194305.1834035-1-irogers@google.com
---
 arch/x86/events/intel/core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 36c68210d4d2..793335c3ce78 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4855,8 +4855,10 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask);
 
 		if (leader->nr_siblings) {
-			for_each_sibling_event(sibling, leader)
-				intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+			for_each_sibling_event(sibling, leader) {
+				if (is_x86_event(sibling))
+					intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+			}
 		}
 
 		if (leader != event)
-- 
cgit v1.2.3


From 579af7204d762587f9cce0d6236a710a771f1f6f Mon Sep 17 00:00:00 2001
From: Dave Penkler <dpenkler@gmail.com>
Date: Mon, 2 Feb 2026 10:47:55 +0100
Subject: gpib: Fix fluke driver s390 compile issue

The following errors were reported for a s390 randconfig build
of the fluke gpib driver:

>> drivers/gpib/eastwood/fluke_gpib.c:1002:23: error: call to undeclared function 'ioremap'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
    1002 |         nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start,
         |                              ^
>> drivers/gpib/eastwood/fluke_gpib.c:1002:21: error: incompatible integer to pointer conversion assigning to 'void *' from 'int' [-Wint-conversion]
    1002 |         nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start,
         |                            ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    1003 |                                      resource_size(e_priv->gpib_iomem_res));
         |                                      ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   drivers/gpib/eastwood/fluke_gpib.c:1036:33: error: incompatible integer to pointer conversion assigning to 'void *' from 'int' [-Wint-conversion]
    1036 |         e_priv->write_transfer_counter = ioremap(e_priv->write_transfer_counter_res->start,
         |                                        ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    1037 |                                                  resource_size(e_priv->write_transfer_counter_res));
         |                                                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Add HAS_IOMEM dependency to Kconfig for fluke driver option

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202601221748.AFAqHieJ-lkp@intel.com/
Fixes: baf8855c9160 ("staging: gpib: fix address space mixup")
Cc: stable <stable@kernel.org>
Signed-off-by: Dave Penkler <dpenkler@gmail.com>
Link: https://patch.msgid.link/20260202094755.4259-1-dpenkler@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpib/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpib/Kconfig b/drivers/gpib/Kconfig
index eeb50956ce85..d43a28c62ed7 100644
--- a/drivers/gpib/Kconfig
+++ b/drivers/gpib/Kconfig
@@ -122,6 +122,7 @@ config GPIB_FLUKE
 	depends on OF
        select GPIB_COMMON
        select GPIB_NEC7210
+       depends on HAS_IOMEM
        help
          GPIB driver for Fluke based cda devices.
 
-- 
cgit v1.2.3


From 5cefb52c1af6f69ea719e42788f6ec6a087eb74c Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 10 Mar 2026 11:51:27 +0100
Subject: gpib: lpvo_usb: fix memory leak on disconnect

The driver iterates over the registered USB interfaces during GPIB
attach and takes a reference to their USB devices until a match is
found. These references are never released which leads to a memory leak
when devices are disconnected.

Fix the leak by dropping the unnecessary references.

Fixes: fce79512a96a ("staging: gpib: Add LPVO DIY USB GPIB driver")
Cc: stable <stable@kernel.org> # 6.13
Cc: Dave Penkler <dpenkler@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://patch.msgid.link/20260310105127.17538-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
index ee781d2f0b8e..0f9d385bc50b 100644
--- a/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
+++ b/drivers/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
@@ -406,7 +406,7 @@ static int usb_gpib_attach(struct gpib_board *board, const struct gpib_board_con
 		for (j = 0 ; j < MAX_DEV ; j++) {
 			if ((assigned_usb_minors & 1 << j) == 0)
 				continue;
-			udev =	usb_get_dev(interface_to_usbdev(lpvo_usb_interfaces[j]));
+			udev = interface_to_usbdev(lpvo_usb_interfaces[j]);
 			device_path = kobject_get_path(&udev->dev.kobj, GFP_KERNEL);
 			match = gpib_match_device_path(&lpvo_usb_interfaces[j]->dev,
 						       config->device_path);
@@ -421,7 +421,7 @@ static int usb_gpib_attach(struct gpib_board *board, const struct gpib_board_con
 		for (j = 0 ; j < MAX_DEV ; j++) {
 			if ((assigned_usb_minors & 1 << j) == 0)
 				continue;
-			udev =	usb_get_dev(interface_to_usbdev(lpvo_usb_interfaces[j]));
+			udev = interface_to_usbdev(lpvo_usb_interfaces[j]);
 			DIA_LOG(1, "dev. %d: bus %d -> %d  dev: %d -> %d\n", j,
 				udev->bus->busnum, config->pci_bus, udev->devnum, config->pci_slot);
 			if (config->pci_bus == udev->bus->busnum &&
-- 
cgit v1.2.3


From d1857f8296dceb75d00ab857fc3c61bc00c7f5c6 Mon Sep 17 00:00:00 2001
From: Adam Crosser <adam.crosser@praetorian.com>
Date: Tue, 17 Mar 2026 19:25:28 +0700
Subject: gpib: fix use-after-free in IO ioctl handlers

The IBRD, IBWRT, IBCMD, and IBWAIT ioctl handlers use a gpib_descriptor
pointer after board->big_gpib_mutex has been released.  A concurrent
IBCLOSEDEV ioctl can free the descriptor via close_dev_ioctl() during
this window, causing a use-after-free.

The IO handlers (read_ioctl, write_ioctl, command_ioctl) explicitly
release big_gpib_mutex before calling their handler.  wait_ioctl() is
called with big_gpib_mutex held, but ibwait() releases it internally
when wait_mask is non-zero.  In all four cases, the descriptor pointer
obtained from handle_to_descriptor() becomes unprotected.

Fix this by introducing a kernel-only descriptor_busy reference count
in struct gpib_descriptor.  Each handler atomically increments
descriptor_busy under file_priv->descriptors_mutex before releasing the
lock, and decrements it when done.  close_dev_ioctl() checks
descriptor_busy under the same lock and rejects the close with -EBUSY
if the count is non-zero.

A reference count rather than a simple flag is necessary because
multiple handlers can operate on the same descriptor concurrently
(e.g. IBRD and IBWAIT on the same handle from different threads).

A separate counter is needed because io_in_progress can be cleared from
unprivileged userspace via the IBWAIT ioctl (through general_ibstatus()
with set_mask containing CMPL), which would allow an attacker to bypass
a check based solely on io_in_progress.  The new descriptor_busy
counter is only modified by the kernel IO paths.

The lock ordering is consistent (big_gpib_mutex -> descriptors_mutex)
and the handlers only hold descriptors_mutex briefly during the lookup,
so there is no deadlock risk and no impact on IO throughput.

Signed-off-by: Adam Crosser <adam.crosser@praetorian.com>
Cc: stable <stable@kernel.org>
Reviewed-by: Dave Penkler <dpenkler@gmail.com>
Tested-by: Dave Penkler <dpenkler@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpib/common/gpib_os.c     | 96 +++++++++++++++++++++++++++++----------
 drivers/gpib/include/gpib_types.h |  8 ++++
 2 files changed, 81 insertions(+), 23 deletions(-)

diff --git a/drivers/gpib/common/gpib_os.c b/drivers/gpib/common/gpib_os.c
index be757db993a5..97c98f0a7a43 100644
--- a/drivers/gpib/common/gpib_os.c
+++ b/drivers/gpib/common/gpib_os.c
@@ -888,10 +888,6 @@ static int read_ioctl(struct gpib_file_private *file_priv, struct gpib_board *bo
 	if (read_cmd.completed_transfer_count > read_cmd.requested_transfer_count)
 		return -EINVAL;
 
-	desc = handle_to_descriptor(file_priv, read_cmd.handle);
-	if (!desc)
-		return -EINVAL;
-
 	if (WARN_ON_ONCE(sizeof(userbuf) > sizeof(read_cmd.buffer_ptr)))
 		return -EFAULT;
 
@@ -904,6 +900,17 @@ static int read_ioctl(struct gpib_file_private *file_priv, struct gpib_board *bo
 	if (!access_ok(userbuf, remain))
 		return -EFAULT;
 
+	/* Lock descriptors to prevent concurrent close from freeing descriptor */
+	if (mutex_lock_interruptible(&file_priv->descriptors_mutex))
+		return -ERESTARTSYS;
+	desc = handle_to_descriptor(file_priv, read_cmd.handle);
+	if (!desc) {
+		mutex_unlock(&file_priv->descriptors_mutex);
+		return -EINVAL;
+	}
+	atomic_inc(&desc->descriptor_busy);
+	mutex_unlock(&file_priv->descriptors_mutex);
+
 	atomic_set(&desc->io_in_progress, 1);
 
 	/* Read buffer loads till we fill the user supplied buffer */
@@ -937,6 +944,7 @@ static int read_ioctl(struct gpib_file_private *file_priv, struct gpib_board *bo
 		retval = copy_to_user((void __user *)arg, &read_cmd, sizeof(read_cmd));
 
 	atomic_set(&desc->io_in_progress, 0);
+	atomic_dec(&desc->descriptor_busy);
 
 	wake_up_interruptible(&board->wait);
 	if (retval)
@@ -964,10 +972,6 @@ static int command_ioctl(struct gpib_file_private *file_priv,
 	if (cmd.completed_transfer_count > cmd.requested_transfer_count)
 		return -EINVAL;
 
-	desc = handle_to_descriptor(file_priv, cmd.handle);
-	if (!desc)
-		return -EINVAL;
-
 	userbuf = (u8 __user *)(unsigned long)cmd.buffer_ptr;
 	userbuf += cmd.completed_transfer_count;
 
@@ -980,6 +984,17 @@ static int command_ioctl(struct gpib_file_private *file_priv,
 	if (!access_ok(userbuf, remain))
 		return -EFAULT;
 
+	/* Lock descriptors to prevent concurrent close from freeing descriptor */
+	if (mutex_lock_interruptible(&file_priv->descriptors_mutex))
+		return -ERESTARTSYS;
+	desc = handle_to_descriptor(file_priv, cmd.handle);
+	if (!desc) {
+		mutex_unlock(&file_priv->descriptors_mutex);
+		return -EINVAL;
+	}
+	atomic_inc(&desc->descriptor_busy);
+	mutex_unlock(&file_priv->descriptors_mutex);
+
 	/*
 	 * Write buffer loads till we empty the user supplied buffer.
 	 * Call drivers at least once, even if remain is zero, in
@@ -1003,6 +1018,7 @@ static int command_ioctl(struct gpib_file_private *file_priv,
 		userbuf += bytes_written;
 		if (retval < 0) {
 			atomic_set(&desc->io_in_progress, 0);
+			atomic_dec(&desc->descriptor_busy);
 
 			wake_up_interruptible(&board->wait);
 			break;
@@ -1022,6 +1038,7 @@ static int command_ioctl(struct gpib_file_private *file_priv,
 	 */
 	if (!no_clear_io_in_prog || fault)
 		atomic_set(&desc->io_in_progress, 0);
+	atomic_dec(&desc->descriptor_busy);
 
 	wake_up_interruptible(&board->wait);
 	if (fault)
@@ -1047,10 +1064,6 @@ static int write_ioctl(struct gpib_file_private *file_priv, struct gpib_board *b
 	if (write_cmd.completed_transfer_count > write_cmd.requested_transfer_count)
 		return -EINVAL;
 
-	desc = handle_to_descriptor(file_priv, write_cmd.handle);
-	if (!desc)
-		return -EINVAL;
-
 	userbuf = (u8 __user *)(unsigned long)write_cmd.buffer_ptr;
 	userbuf += write_cmd.completed_transfer_count;
 
@@ -1060,6 +1073,17 @@ static int write_ioctl(struct gpib_file_private *file_priv, struct gpib_board *b
 	if (!access_ok(userbuf, remain))
 		return -EFAULT;
 
+	/* Lock descriptors to prevent concurrent close from freeing descriptor */
+	if (mutex_lock_interruptible(&file_priv->descriptors_mutex))
+		return -ERESTARTSYS;
+	desc = handle_to_descriptor(file_priv, write_cmd.handle);
+	if (!desc) {
+		mutex_unlock(&file_priv->descriptors_mutex);
+		return -EINVAL;
+	}
+	atomic_inc(&desc->descriptor_busy);
+	mutex_unlock(&file_priv->descriptors_mutex);
+
 	atomic_set(&desc->io_in_progress, 1);
 
 	/* Write buffer loads till we empty the user supplied buffer */
@@ -1094,6 +1118,7 @@ static int write_ioctl(struct gpib_file_private *file_priv, struct gpib_board *b
 		fault = copy_to_user((void __user *)arg, &write_cmd, sizeof(write_cmd));
 
 	atomic_set(&desc->io_in_progress, 0);
+	atomic_dec(&desc->descriptor_busy);
 
 	wake_up_interruptible(&board->wait);
 	if (fault)
@@ -1276,6 +1301,9 @@ static int close_dev_ioctl(struct file *filep, struct gpib_board *board, unsigne
 {
 	struct gpib_close_dev_ioctl cmd;
 	struct gpib_file_private *file_priv = filep->private_data;
+	struct gpib_descriptor *desc;
+	unsigned int pad;
+	int sad;
 	int retval;
 
 	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
@@ -1284,19 +1312,27 @@ static int close_dev_ioctl(struct file *filep, struct gpib_board *board, unsigne
 
 	if (cmd.handle >= GPIB_MAX_NUM_DESCRIPTORS)
 		return -EINVAL;
-	if (!file_priv->descriptors[cmd.handle])
-		return -EINVAL;
 
-	retval = decrement_open_device_count(board, &board->device_list,
-					     file_priv->descriptors[cmd.handle]->pad,
-					     file_priv->descriptors[cmd.handle]->sad);
-	if (retval < 0)
-		return retval;
-
-	kfree(file_priv->descriptors[cmd.handle]);
+	mutex_lock(&file_priv->descriptors_mutex);
+	desc = file_priv->descriptors[cmd.handle];
+	if (!desc) {
+		mutex_unlock(&file_priv->descriptors_mutex);
+		return -EINVAL;
+	}
+	if (atomic_read(&desc->descriptor_busy)) {
+		mutex_unlock(&file_priv->descriptors_mutex);
+		return -EBUSY;
+	}
+	/* Remove from table while holding lock to prevent new IO from starting */
 	file_priv->descriptors[cmd.handle] = NULL;
+	pad = desc->pad;
+	sad = desc->sad;
+	mutex_unlock(&file_priv->descriptors_mutex);
 
-	return 0;
+	retval = decrement_open_device_count(board, &board->device_list, pad, sad);
+
+	kfree(desc);
+	return retval;
 }
 
 static int serial_poll_ioctl(struct gpib_board *board, unsigned long arg)
@@ -1331,12 +1367,25 @@ static int wait_ioctl(struct gpib_file_private *file_priv, struct gpib_board *bo
 	if (retval)
 		return -EFAULT;
 
+	/*
+	 * Lock descriptors to prevent concurrent close from freeing
+	 * descriptor.  ibwait() releases big_gpib_mutex when wait_mask
+	 * is non-zero, so desc must be pinned with descriptor_busy.
+	 */
+	mutex_lock(&file_priv->descriptors_mutex);
 	desc = handle_to_descriptor(file_priv, wait_cmd.handle);
-	if (!desc)
+	if (!desc) {
+		mutex_unlock(&file_priv->descriptors_mutex);
 		return -EINVAL;
+	}
+	atomic_inc(&desc->descriptor_busy);
+	mutex_unlock(&file_priv->descriptors_mutex);
 
 	retval = ibwait(board, wait_cmd.wait_mask, wait_cmd.clear_mask,
 			wait_cmd.set_mask, &wait_cmd.ibsta, wait_cmd.usec_timeout, desc);
+
+	atomic_dec(&desc->descriptor_busy);
+
 	if (retval < 0)
 		return retval;
 
@@ -2035,6 +2084,7 @@ void init_gpib_descriptor(struct gpib_descriptor *desc)
 	desc->is_board = 0;
 	desc->autopoll_enabled = 0;
 	atomic_set(&desc->io_in_progress, 0);
+	atomic_set(&desc->descriptor_busy, 0);
 }
 
 int gpib_register_driver(struct gpib_interface *interface, struct module *provider_module)
diff --git a/drivers/gpib/include/gpib_types.h b/drivers/gpib/include/gpib_types.h
index 5a0978ae27e7..28b73157ffb7 100644
--- a/drivers/gpib/include/gpib_types.h
+++ b/drivers/gpib/include/gpib_types.h
@@ -364,6 +364,14 @@ struct gpib_descriptor {
 	unsigned int pad;	/* primary gpib address */
 	int sad;	/* secondary gpib address (negative means disabled) */
 	atomic_t io_in_progress;
+	/*
+	 * Kernel-only reference count to prevent descriptor from being
+	 * freed while IO handlers hold a pointer to it.  Incremented
+	 * before each IO operation, decremented when done.  Unlike
+	 * io_in_progress, this cannot be modified from userspace via
+	 * general_ibstatus().
+	 */
+	atomic_t descriptor_busy;
 	unsigned is_board : 1;
 	unsigned autopoll_enabled : 1;
 };
-- 
cgit v1.2.3


From 101ab946b79ad83b36d5cfd47de587492a80acf0 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Wed, 28 Jan 2026 15:00:10 +0000
Subject: comedi: ni_atmio16d: Fix invalid clean-up after failed attach

If the driver's COMEDI "attach" handler function (`atmio16d_attach()`)
returns an error, the COMEDI core will call the driver's "detach"
handler function (`atmio16d_detach()`) to clean up.  This calls
`reset_atmio16d()` unconditionally, but depending on where the error
occurred in the attach handler, the device may not have been
sufficiently initialized to call `reset_atmio16d()`.  It uses
`dev->iobase` as the I/O port base address and `dev->private` as the
pointer to the COMEDI device's private data structure.  `dev->iobase`
may still be set to its initial value of 0, which would result in
undesired writes to low I/O port addresses.  `dev->private` may still be
`NULL`, which would result in null pointer dereferences.

Fix `atmio16d_detach()` by checking that `dev->private` is valid
(non-null) before calling `reset_atmio16d()`.  This implies that
`dev->iobase` was set correctly since that is set up before
`dev->private`.

Fixes: 2323b276308a ("Staging: comedi: add ni_at_atmio16d driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://patch.msgid.link/20260128150011.5006-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers/ni_atmio16d.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/comedi/drivers/ni_atmio16d.c b/drivers/comedi/drivers/ni_atmio16d.c
index e5e7cc423c87..b057b3b3582e 100644
--- a/drivers/comedi/drivers/ni_atmio16d.c
+++ b/drivers/comedi/drivers/ni_atmio16d.c
@@ -698,7 +698,8 @@ static int atmio16d_attach(struct comedi_device *dev,
 
 static void atmio16d_detach(struct comedi_device *dev)
 {
-	reset_atmio16d(dev);
+	if (dev->private)
+		reset_atmio16d(dev);
 	comedi_legacy_detach(dev);
 }
 
-- 
cgit v1.2.3


From 3fb43a7a5b44713f892c58ead2e5f3a1bc9f4ee7 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Thu, 5 Feb 2026 13:39:49 +0000
Subject: comedi: me4000: Fix potential overrun of firmware buffer

`me4000_xilinx_download()` loads the firmware that was requested by
`request_firmware()`.  It is possible for it to overrun the source
buffer because it blindly trusts the file format.  It reads a data
stream length from the first 4 bytes into variable `file_length` and
reads the data stream contents of length `file_length` from offset 16
onwards.

Add a test to ensure that the supplied firmware is long enough to
contain the header and the data stream.  On failure, log an error and
return `-EINVAL`.

Note: The firmware loading was totally broken before commit ac584af59945
("staging: comedi: me4000: fix firmware downloading"), but that is the
most sensible target for this fix.

Fixes: ac584af59945 ("staging: comedi: me4000: fix firmware downloading")
Cc: stable <stable@kernel.org>
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://patch.msgid.link/20260205133949.71722-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers/me4000.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/comedi/drivers/me4000.c b/drivers/comedi/drivers/me4000.c
index 7dd3a0071863..effe9fdbbafe 100644
--- a/drivers/comedi/drivers/me4000.c
+++ b/drivers/comedi/drivers/me4000.c
@@ -315,6 +315,18 @@ static int me4000_xilinx_download(struct comedi_device *dev,
 	unsigned int val;
 	unsigned int i;
 
+	/* Get data stream length from header. */
+	if (size >= 4) {
+		file_length = (((unsigned int)data[0] & 0xff) << 24) +
+			      (((unsigned int)data[1] & 0xff) << 16) +
+			      (((unsigned int)data[2] & 0xff) << 8) +
+			      ((unsigned int)data[3] & 0xff);
+	}
+	if (size < 16 || file_length > size - 16) {
+		dev_err(dev->class_dev, "Firmware length inconsistency\n");
+		return -EINVAL;
+	}
+
 	if (!xilinx_iobase)
 		return -ENODEV;
 
@@ -346,10 +358,6 @@ static int me4000_xilinx_download(struct comedi_device *dev,
 	outl(val, devpriv->plx_regbase + PLX9052_CNTRL);
 
 	/* Download Xilinx firmware */
-	file_length = (((unsigned int)data[0] & 0xff) << 24) +
-		      (((unsigned int)data[1] & 0xff) << 16) +
-		      (((unsigned int)data[2] & 0xff) << 8) +
-		      ((unsigned int)data[3] & 0xff);
 	usleep_range(10, 1000);
 
 	for (i = 0; i < file_length; i++) {
-- 
cgit v1.2.3


From cc797d4821c754c701d9714b58bea947e31dbbe0 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Thu, 5 Feb 2026 14:01:30 +0000
Subject: comedi: me_daq: Fix potential overrun of firmware buffer

`me2600_xilinx_download()` loads the firmware that was requested by
`request_firmware()`.  It is possible for it to overrun the source
buffer because it blindly trusts the file format.  It reads a data
stream length from the first 4 bytes into variable `file_length` and
reads the data stream contents of length `file_length` from offset 16
onwards.  Although it checks that the supplied firmware is at least 16
bytes long, it does not check that it is long enough to contain the data
stream.

Add a test to ensure that the supplied firmware is long enough to
contain the header and the data stream.  On failure, log an error and
return `-EINVAL`.

Fixes: 85acac61096f9 ("Staging: comedi: add me_daq driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://patch.msgid.link/20260205140130.76697-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers/me_daq.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/drivers/comedi/drivers/me_daq.c b/drivers/comedi/drivers/me_daq.c
index 076b15097afd..2f2ea029cffc 100644
--- a/drivers/comedi/drivers/me_daq.c
+++ b/drivers/comedi/drivers/me_daq.c
@@ -344,6 +344,25 @@ static int me2600_xilinx_download(struct comedi_device *dev,
 	unsigned int file_length;
 	unsigned int i;
 
+	/*
+	 * Format of the firmware
+	 * Build longs from the byte-wise coded header
+	 * Byte 1-3:   length of the array
+	 * Byte 4-7:   version
+	 * Byte 8-11:  date
+	 * Byte 12-15: reserved
+	 */
+	if (size >= 4) {
+		file_length = (((unsigned int)data[0] & 0xff) << 24) +
+			      (((unsigned int)data[1] & 0xff) << 16) +
+			      (((unsigned int)data[2] & 0xff) << 8) +
+			      ((unsigned int)data[3] & 0xff);
+	}
+	if (size < 16 || file_length > size - 16) {
+		dev_err(dev->class_dev, "Firmware length inconsistency\n");
+		return -EINVAL;
+	}
+
 	/* disable irq's on PLX */
 	writel(0x00, devpriv->plx_regbase + PLX9052_INTCSR);
 
@@ -357,22 +376,6 @@ static int me2600_xilinx_download(struct comedi_device *dev,
 	writeb(0x00, dev->mmio + 0x0);
 	sleep(1);
 
-	/*
-	 * Format of the firmware
-	 * Build longs from the byte-wise coded header
-	 * Byte 1-3:   length of the array
-	 * Byte 4-7:   version
-	 * Byte 8-11:  date
-	 * Byte 12-15: reserved
-	 */
-	if (size < 16)
-		return -EINVAL;
-
-	file_length = (((unsigned int)data[0] & 0xff) << 24) +
-	    (((unsigned int)data[1] & 0xff) << 16) +
-	    (((unsigned int)data[2] & 0xff) << 8) +
-	    ((unsigned int)data[3] & 0xff);
-
 	/*
 	 * Loop for writing firmware byte by byte to xilinx
 	 * Firmware data start at offset 16
-- 
cgit v1.2.3


From 4b9a9a6d71e3e252032f959fb3895a33acb5865c Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Wed, 25 Feb 2026 13:24:27 +0000
Subject: comedi: Reinit dev->spinlock between attachments to low-level drivers

`struct comedi_device` is the main controlling structure for a COMEDI
device created by the COMEDI subsystem.  It contains a member `spinlock`
containing a spin-lock that is initialized by the COMEDI subsystem, but
is reserved for use by a low-level driver attached to the COMEDI device
(at least since commit 25436dc9d84f ("Staging: comedi: remove RT
code")).

Some COMEDI devices (those created on initialization of the COMEDI
subsystem when the "comedi.comedi_num_legacy_minors" parameter is
non-zero) can be attached to different low-level drivers over their
lifetime using the `COMEDI_DEVCONFIG` ioctl command.  This can result in
inconsistent lock states being reported when there is a mismatch in the
spin-lock locking levels used by each low-level driver to which the
COMEDI device has been attached.  Fix it by reinitializing
`dev->spinlock` before calling the low-level driver's `attach` function
pointer if `CONFIG_LOCKDEP` is enabled.

Reported-by: syzbot+cc9f7f4a7df09f53c4a4@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=cc9f7f4a7df09f53c4a4
Fixes: ed9eccbe8970 ("Staging: add comedi core")
Cc: stable <stable@kernel.org>
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://patch.msgid.link/20260225132427.86578-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c
index db225a3bf012..5ab96b5eefd1 100644
--- a/drivers/comedi/drivers.c
+++ b/drivers/comedi/drivers.c
@@ -1063,6 +1063,14 @@ int comedi_device_attach(struct comedi_device *dev, struct comedi_devconfig *it)
 		ret = -EIO;
 		goto out;
 	}
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		/*
+		 * dev->spinlock is for private use by the attached low-level
+		 * driver.  Reinitialize it to stop lock-dependency tracking
+		 * between attachments to different low-level drivers.
+		 */
+		spin_lock_init(&dev->spinlock);
+	}
 	dev->driver = driv;
 	dev->board_name = dev->board_ptr ? *(const char **)dev->board_ptr
 					 : dev->driver->driver_name;
-- 
cgit v1.2.3


From 29f644f14b89e6c4965e3c89251929e451190a66 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 10 Mar 2026 11:11:04 +0000
Subject: comedi: runflags cannot determine whether to reclaim chanlist

syzbot reported a memory leak [1], because commit 4e1da516debb ("comedi:
Add reference counting for Comedi command handling") did not consider
the exceptional exit case in do_cmd_ioctl() where runflags is not set.
This caused chanlist not to be properly freed by do_become_nonbusy(),
as it only frees chanlist when runflags is correctly set.

Added a check in do_become_nonbusy() for the case where runflags is not
set, to properly free the chanlist memory.

[1]
BUG: memory leak
  backtrace (crc 844a0efa):
    __comedi_get_user_chanlist drivers/comedi/comedi_fops.c:1815 [inline]
    do_cmd_ioctl.part.0+0x112/0x350 drivers/comedi/comedi_fops.c:1890
    do_cmd_ioctl drivers/comedi/comedi_fops.c:1858 [inline]

Fixes: 4e1da516debb ("comedi: Add reference counting for Comedi command handling")
Reported-by: syzbot+f238baf6ded841b5a82e@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f238baf6ded841b5a82e
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Cc: stable <stable@kernel.org> # 6.19
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://patch.msgid.link/20260310111104.70959-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/comedi_fops.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c
index 48a8a607a84c..0df9f4636fb6 100644
--- a/drivers/comedi/comedi_fops.c
+++ b/drivers/comedi/comedi_fops.c
@@ -793,13 +793,15 @@ static void do_become_nonbusy(struct comedi_device *dev,
 	__comedi_clear_subdevice_runflags(s, COMEDI_SRF_RUNNING |
 					     COMEDI_SRF_BUSY);
 	spin_unlock_irqrestore(&s->spin_lock, flags);
-	if (comedi_is_runflags_busy(runflags)) {
+	if (async) {
 		/*
 		 * "Run active" counter was set to 1 when setting up the
 		 * command.  Decrement it and wait for it to become 0.
 		 */
-		comedi_put_is_subdevice_running(s);
-		wait_for_completion(&async->run_complete);
+		if (comedi_is_runflags_busy(runflags)) {
+			comedi_put_is_subdevice_running(s);
+			wait_for_completion(&async->run_complete);
+		}
 		comedi_buf_reset(s);
 		async->inttrig = NULL;
 		kfree(async->cmd.chanlist);
-- 
cgit v1.2.3


From 93853512f565e625df2397f0d8050d6aafd7c3ad Mon Sep 17 00:00:00 2001
From: Deepanshu Kartikey <kartikey406@gmail.com>
Date: Mon, 9 Mar 2026 16:18:59 +0530
Subject: comedi: dt2815: add hardware detection to prevent crash

The dt2815 driver crashes when attached to I/O ports without actual
hardware present. This occurs because syzkaller or users can attach
the driver to arbitrary I/O addresses via COMEDI_DEVCONFIG ioctl.

When no hardware exists at the specified port, inb() operations return
0xff (floating bus), but outb() operations can trigger page faults due
to undefined behavior, especially under race conditions:

  BUG: unable to handle page fault for address: 000000007fffff90
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  RIP: 0010:dt2815_attach+0x6e0/0x1110

Add hardware detection by reading the status register before attempting
any write operations. If the read returns 0xff, assume no hardware is
present and fail the attach with -ENODEV. This prevents crashes from
outb() operations on non-existent hardware.

Reported-by: syzbot+72f94b474d6e50b71ffc@syzkaller.appspotmail.com
Cc: stable <stable@kernel.org>
Closes: https://syzkaller.appspot.com/bug?extid=72f94b474d6e50b71ffc
Tested-by: syzbot+72f94b474d6e50b71ffc@syzkaller.appspotmail.com
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Deepanshu Kartikey <kartikey406@gmail.com>
Link: [https://lore.kernel.org/all/20260126070458.10974-1-kartikey406@gmail.com/T/]
Link: [https://lore.kernel.org/all/20260126070458.10974-1-kartikey406@gmail.com/T/
Link: https://patch.msgid.link/20260309104859.503529-1-kartikey406@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers/dt2815.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/comedi/drivers/dt2815.c b/drivers/comedi/drivers/dt2815.c
index 03ba2fd18a21..d066dc303520 100644
--- a/drivers/comedi/drivers/dt2815.c
+++ b/drivers/comedi/drivers/dt2815.c
@@ -175,6 +175,18 @@ static int dt2815_attach(struct comedi_device *dev, struct comedi_devconfig *it)
 		    ? current_range_type : voltage_range_type;
 	}
 
+	/*
+	 * Check if hardware is present before attempting any I/O operations.
+	 * Reading 0xff from status register typically indicates no hardware
+	 * on the bus (floating bus reads as all 1s).
+	 */
+	if (inb(dev->iobase + DT2815_STATUS) == 0xff) {
+		dev_err(dev->class_dev,
+			"No hardware detected at I/O base 0x%lx\n",
+			dev->iobase);
+		return -ENODEV;
+	}
+
 	/* Init the 2815 */
 	outb(0x00, dev->iobase + DT2815_STATUS);
 	for (i = 0; i < 100; i++) {
-- 
cgit v1.2.3


From ba2c83167b215da30fa2aae56b140198cf8d8408 Mon Sep 17 00:00:00 2001
From: Xingjing Deng <micro6947@gmail.com>
Date: Fri, 30 Jan 2026 07:41:40 +0800
Subject: misc: fastrpc: possible double-free of cctx->remote_heap

fastrpc_init_create_static_process() may free cctx->remote_heap on the
err_map path but does not clear the pointer. Later, fastrpc_rpmsg_remove()
frees cctx->remote_heap again if it is non-NULL, which can lead to a
double-free if the INIT_CREATE_STATIC ioctl hits the error path and the rpmsg
device is subsequently removed/unbound.
Clear cctx->remote_heap after freeing it in the error path to prevent the
later cleanup from freeing it again.

This issue was found by an in-house analysis workflow that extracts AST-based
information and runs static checks, with LLM assistance for triage, and was
confirmed by manual code review.
No hardware testing was performed.

Fixes: 0871561055e66 ("misc: fastrpc: Add support for audiopd")
Cc: stable@vger.kernel.org # 6.2+
Signed-off-by: Xingjing Deng <xjdeng@buaa.edu.cn>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://patch.msgid.link/20260129234140.410983-1-xjdeng@buaa.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 47356a5d5804..19cfc487df7c 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -1401,6 +1401,7 @@ err_invoke:
 	}
 err_map:
 	fastrpc_buf_free(fl->cctx->remote_heap);
+	fl->cctx->remote_heap = NULL;
 err_name:
 	kfree(name);
 err:
-- 
cgit v1.2.3


From 6a502776f4a4f80fb839b22f12aeaf0267fca344 Mon Sep 17 00:00:00 2001
From: Xingjing Deng <micro6947@gmail.com>
Date: Sat, 31 Jan 2026 14:55:39 +0800
Subject: misc: fastrpc: check qcom_scm_assign_mem() return in rpmsg_probe

In the SDSP probe path, qcom_scm_assign_mem() is used to assign the
reserved memory to the configured VMIDs, but its return value was not checked.

Fail the probe if the SCM call fails to avoid continuing with an
unexpected/incorrect memory permission configuration.

This issue was found by an in-house analysis workflow that extracts AST-based
information and runs static checks, with LLM assistance for triage, and was
confirmed by manual code review.
No hardware testing was performed.

Fixes: c3c0363bc72d4 ("misc: fastrpc: support complete DMA pool access to the DSP")
Cc: stable@vger.kernel.org # 6.11-rc1
Signed-off-by: Xingjing Deng <xjdeng@buaa.edu.cn>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://patch.msgid.link/20260131065539.2124047-1-xjdeng@buaa.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 19cfc487df7c..1080f9acf70a 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -2390,8 +2390,10 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 		if (!err) {
 			src_perms = BIT(QCOM_SCM_VMID_HLOS);
 
-			qcom_scm_assign_mem(res.start, resource_size(&res), &src_perms,
+			err = qcom_scm_assign_mem(res.start, resource_size(&res), &src_perms,
 				    data->vmperms, data->vmcount);
+			if (err)
+				goto err_free_data;
 		}
 
 	}
-- 
cgit v1.2.3


From faeea8bbf6e958bf3c00cb08263109661975987c Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Mon, 30 Mar 2026 22:02:15 -0700
Subject: net/sched: cls_fw: fix NULL pointer dereference on shared blocks

The old-method path in fw_classify() calls tcf_block_q() and
dereferences q->handle.  Shared blocks leave block->q NULL, causing a
NULL deref when an empty cls_fw filter is attached to a shared block
and a packet with a nonzero major skb mark is classified.

Reject the configuration in fw_change() when the old method (no
TCA_OPTIONS) is used on a shared block, since fw_classify()'s
old-method path needs block->q which is NULL for shared blocks.

The fixed null-ptr-deref calling stack:
 KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f]
 RIP: 0010:fw_classify (net/sched/cls_fw.c:81)
 Call Trace:
  tcf_classify (./include/net/tc_wrapper.h:197 net/sched/cls_api.c:1764 net/sched/cls_api.c:1860)
  tc_run (net/core/dev.c:4401)
  __dev_queue_xmit (net/core/dev.c:4535 net/core/dev.c:4790)

Fixes: 1abf272022cf ("net: sched: tcindex, fw, flow: use tcf_block_q helper to get struct Qdisc")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260331050217.504278-1-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/cls_fw.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index be81c108179d..23884ef8b80c 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -247,8 +247,18 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	struct nlattr *tb[TCA_FW_MAX + 1];
 	int err;
 
-	if (!opt)
-		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
+	if (!opt) {
+		if (handle)
+			return -EINVAL;
+
+		if (tcf_block_shared(tp->chain->block)) {
+			NL_SET_ERR_MSG(extack,
+				       "Must specify mark when attaching fw filter to block");
+			return -EINVAL;
+		}
+
+		return 0; /* Succeed if it is old method. */
+	}
 
 	err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy,
 					  NULL);
-- 
cgit v1.2.3


From 1a280dd4bd1d616a01d6ffe0de284c907b555504 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Mon, 30 Mar 2026 22:02:16 -0700
Subject: net/sched: cls_flow: fix NULL pointer dereference on shared blocks

flow_change() calls tcf_block_q() and dereferences q->handle to derive
a default baseclass.  Shared blocks leave block->q NULL, causing a NULL
deref when a flow filter without a fully qualified baseclass is created
on a shared block.

Check tcf_block_shared() before accessing block->q and return -EINVAL
for shared blocks.  This avoids the null-deref shown below:

=======================================================================
KASAN: null-ptr-deref in range [0x0000000000000038-0x000000000000003f]
RIP: 0010:flow_change (net/sched/cls_flow.c:508)
Call Trace:
 tc_new_tfilter (net/sched/cls_api.c:2432)
 rtnetlink_rcv_msg (net/core/rtnetlink.c:6980)
 [...]
=======================================================================

Fixes: 1abf272022cf ("net: sched: tcindex, fw, flow: use tcf_block_q helper to get struct Qdisc")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20260331050217.504278-2-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/sched/cls_flow.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 339c664beff6..ab364e4e4686 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -503,8 +503,16 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 		}
 
 		if (TC_H_MAJ(baseclass) == 0) {
-			struct Qdisc *q = tcf_block_q(tp->chain->block);
+			struct tcf_block *block = tp->chain->block;
+			struct Qdisc *q;
 
+			if (tcf_block_shared(block)) {
+				NL_SET_ERR_MSG(extack,
+					       "Must specify baseclass when attaching flow filter to block");
+				goto err2;
+			}
+
+			q = tcf_block_q(block);
 			baseclass = TC_H_MAKE(q->handle, baseclass);
 		}
 		if (TC_H_MIN(baseclass) == 0)
-- 
cgit v1.2.3


From 70f73562d278d9f88e7095e327f2a50082a82c65 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Mon, 30 Mar 2026 22:02:17 -0700
Subject: selftests/tc-testing: add tests for cls_fw and cls_flow on shared
 blocks

Regression tests for the shared-block NULL derefs fixed in the previous
two patches:

  - fw: attempt to attach an empty fw filter to a shared block and
    verify the configuration is rejected with EINVAL.
  - flow: create a flow filter on a shared block without a baseclass
    and verify the configuration is rejected with EINVAL.

Signed-off-by: Xiang Mei <xmei5@asu.edu>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20260331050217.504278-3-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../tc-testing/tc-tests/infra/filter.json          | 44 ++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
index 8d10042b489b..dbce6436ed26 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/filter.json
@@ -22,5 +22,49 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY root handle 1: htb default 1"
         ]
+    },
+    {
+        "id": "b7e3",
+        "name": "Empty fw filter on shared block - rejected at config time",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 egress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "fw",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
+        "id": "c8f4",
+        "name": "Flow filter on shared block without baseclass - rejected at config time",
+        "category": [
+            "filter",
+            "flow"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress_block 1 clsact"
+        ],
+        "cmdUnderTest": "$TC filter add block 1 protocol ip prio 1 handle 1 flow map key dst",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show block 1",
+        "matchPattern": "flow",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
     }
 ]
-- 
cgit v1.2.3


From 48b5163c957548f5854f14c90bfdedc33afbea3c Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Fri, 27 Mar 2026 13:16:44 +0000
Subject: nvmem: imx: assign nvmem_cell_info::raw_len

Avoid getting error messages at startup like the following on i.MX6ULL:

nvmem imx-ocotp0: cell mac-addr raw len 6 unaligned to nvmem word size 4
nvmem imx-ocotp0: cell mac-addr raw len 6 unaligned to nvmem word size 4

This shouldn't cause any functional change as this alignment would
otherwise be done in nvmem_cell_info_to_nvmem_cell_entry_nodup().

Cc: stable@vger.kernel.org
Fixes: 13bcd440f2ff ("nvmem: core: verify cell's raw_len")
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Srinivas Kandagatla <srini@kernel.org>
Link: https://patch.msgid.link/20260327131645.3025781-2-srini@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/imx-ocotp-ele.c | 1 +
 drivers/nvmem/imx-ocotp.c     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 7cf7e809a8f5..a0d2985c6d03 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -131,6 +131,7 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index,
 static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
 					 struct nvmem_cell_info *cell)
 {
+	cell->raw_len = round_up(cell->bytes, 4);
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index 7bf7656d4f96..108d78d7f6cb 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -589,6 +589,7 @@ MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);
 static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
 					 struct nvmem_cell_info *cell)
 {
+	cell->raw_len = round_up(cell->bytes, 4);
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
-- 
cgit v1.2.3


From f9b88613ff402aa6fe8fd020573cb95867ae947e Mon Sep 17 00:00:00 2001
From: Ivan Vera <ivanverasantos@gmail.com>
Date: Fri, 27 Mar 2026 13:16:45 +0000
Subject: nvmem: zynqmp_nvmem: Fix buffer size in DMA and memcpy

Buffer size used in dma allocation and memcpy is wrong.
It can lead to undersized DMA buffer access and possible
memory corruption. use correct buffer size in dma_alloc_coherent
and memcpy.

Fixes: 737c0c8d07b5 ("nvmem: zynqmp_nvmem: Add support to access efuse")
Cc: stable@vger.kernel.org
Signed-off-by: Ivan Vera <ivanverasantos@gmail.com>
Signed-off-by: Harish Ediga <harish.ediga@amd.com>
Signed-off-by: Harsh Jain <h.jain@amd.com>
Signed-off-by: Srinivas Kandagatla <srini@kernel.org>
Link: https://patch.msgid.link/20260327131645.3025781-3-srini@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/zynqmp_nvmem.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/nvmem/zynqmp_nvmem.c b/drivers/nvmem/zynqmp_nvmem.c
index 7da717d6c7fa..d297ff150dc0 100644
--- a/drivers/nvmem/zynqmp_nvmem.c
+++ b/drivers/nvmem/zynqmp_nvmem.c
@@ -66,7 +66,7 @@ static int zynqmp_efuse_access(void *context, unsigned int offset,
 	dma_addr_t dma_buf;
 	size_t words = bytes / WORD_INBYTES;
 	int ret;
-	int value;
+	unsigned int value;
 	char *data;
 
 	if (bytes % WORD_INBYTES != 0) {
@@ -80,7 +80,7 @@ static int zynqmp_efuse_access(void *context, unsigned int offset,
 	}
 
 	if (pufflag == 1 && flag == EFUSE_WRITE) {
-		memcpy(&value, val, bytes);
+		memcpy(&value, val, sizeof(value));
 		if ((offset == EFUSE_PUF_START_OFFSET ||
 		     offset == EFUSE_PUF_MID_OFFSET) &&
 		    value & P_USER_0_64_UPPER_MASK) {
@@ -100,7 +100,7 @@ static int zynqmp_efuse_access(void *context, unsigned int offset,
 	if (!efuse)
 		return -ENOMEM;
 
-	data = dma_alloc_coherent(dev, sizeof(bytes),
+	data = dma_alloc_coherent(dev, bytes,
 				  &dma_buf, GFP_KERNEL);
 	if (!data) {
 		ret = -ENOMEM;
@@ -134,7 +134,7 @@ static int zynqmp_efuse_access(void *context, unsigned int offset,
 	if (flag == EFUSE_READ)
 		memcpy(val, data, bytes);
 efuse_access_err:
-	dma_free_coherent(dev, sizeof(bytes),
+	dma_free_coherent(dev, bytes,
 			  data, dma_buf);
 efuse_data_fail:
 	dma_free_coherent(dev, sizeof(struct xilinx_efuse),
-- 
cgit v1.2.3


From d78ceee1e6205ffcd84ff581ccb40a008d39136f Mon Sep 17 00:00:00 2001
From: Askar Safin <safinaskar@gmail.com>
Date: Tue, 24 Mar 2026 08:29:28 +0000
Subject: .get_maintainer.ignore: add myself

I don't want get_maintainer.pl to automatically print my email.

Signed-off-by: Askar Safin <safinaskar@gmail.com>
Link: https://patch.msgid.link/20260324082928.3473789-1-safinaskar@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .get_maintainer.ignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore
index e8d2269bad9d..60b6b2a374cd 100644
--- a/.get_maintainer.ignore
+++ b/.get_maintainer.ignore
@@ -1,6 +1,7 @@
 Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
 Alyssa Rosenzweig <alyssa@rosenzweig.io>
+Askar Safin <safinaskar@gmail.com>
 Christoph Hellwig <hch@lst.de>
 Jeff Kirsher <jeffrey.t.kirsher@intel.com>
 Marc Gonzalez <marc.w.gonzalez@free.fr>
-- 
cgit v1.2.3


From b18c833888742ca9de80c250f9d40d0e97caa9f6 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 1 Apr 2026 11:21:53 +0200
Subject: vsock: initialize child_ns_mode_locked in vsock_net_init()

The `child_ns_mode_locked` field lives in `struct net`, which persists
across vsock module reloads. When the module is unloaded and reloaded,
`vsock_net_init()` resets `mode` and `child_ns_mode` back to their
default values, but does not reset `child_ns_mode_locked`.

The stale lock from the previous module load causes subsequent writes
to `child_ns_mode` to silently fail: `vsock_net_set_child_mode()` sees
the old lock, skips updating the actual value, and returns success
when the requested mode matches the stale lock. The sysctl handler
reports no error, but `child_ns_mode` remains unchanged.

Steps to reproduce:
    $ modprobe vsock
    $ echo local > /proc/sys/net/vsock/child_ns_mode
    $ cat /proc/sys/net/vsock/child_ns_mode
    local
    $ modprobe -r vsock
    $ modprobe vsock
    $ echo local > /proc/sys/net/vsock/child_ns_mode
    $ cat /proc/sys/net/vsock/child_ns_mode
    global    <--- expected "local"

Fix this by initializing `child_ns_mode_locked` to 0 (unlocked) in
`vsock_net_init()`, so the write-once mechanism works correctly after
module reload.

Fixes: 102eab95f025 ("vsock: lock down child_ns_mode as write-once")
Reported-by: Jin Liu <jinl@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Bobby Eshleman <bobbyeshleman@meta.com>
Link: https://patch.msgid.link/20260401092153.28462-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2f7d94d682cb..d912ed2f012a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2928,6 +2928,7 @@ static void vsock_net_init(struct net *net)
 		net->vsock.mode = vsock_net_child_mode(current->nsproxy->net_ns);
 
 	net->vsock.child_ns_mode = net->vsock.mode;
+	net->vsock.child_ns_mode_locked = 0;
 }
 
 static __net_init int vsock_sysctl_init_net(struct net *net)
-- 
cgit v1.2.3


From f5df2990c364d1ac596d24b3118dbc56503f7cd4 Mon Sep 17 00:00:00 2001
From: Luka Gejak <luka.gejak@linux.dev>
Date: Wed, 1 Apr 2026 11:22:42 +0200
Subject: net: hsr: serialize seq_blocks merge across nodes

During node merging, hsr_handle_sup_frame() walks node_curr->seq_blocks
to update node_real without holding node_curr->seq_out_lock. This
allows concurrent mutations from duplicate registration paths, risking
inconsistent state or XArray/bitmap corruption.

Fix this by locking both nodes' seq_out_lock during the merge.
To prevent ABBA deadlocks, locks are acquired in order of memory
address.

Reviewed-by: Felix Maurer <fmaurer@redhat.com>
Fixes: 415e6367512b ("hsr: Implement more robust duplicate discard for PRP")
Signed-off-by: Luka Gejak <luka.gejak@linux.dev>
Link: https://patch.msgid.link/20260401092243.52121-2-luka.gejak@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_framereg.c | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 50996f4de7f9..d41863593674 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -123,6 +123,40 @@ static void hsr_free_node_rcu(struct rcu_head *rn)
 	hsr_free_node(node);
 }
 
+static void hsr_lock_seq_out_pair(struct hsr_node *node_a,
+				  struct hsr_node *node_b)
+{
+	if (node_a == node_b) {
+		spin_lock_bh(&node_a->seq_out_lock);
+		return;
+	}
+
+	if (node_a < node_b) {
+		spin_lock_bh(&node_a->seq_out_lock);
+		spin_lock_nested(&node_b->seq_out_lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock_bh(&node_b->seq_out_lock);
+		spin_lock_nested(&node_a->seq_out_lock, SINGLE_DEPTH_NESTING);
+	}
+}
+
+static void hsr_unlock_seq_out_pair(struct hsr_node *node_a,
+				    struct hsr_node *node_b)
+{
+	if (node_a == node_b) {
+		spin_unlock_bh(&node_a->seq_out_lock);
+		return;
+	}
+
+	if (node_a < node_b) {
+		spin_unlock(&node_b->seq_out_lock);
+		spin_unlock_bh(&node_a->seq_out_lock);
+	} else {
+		spin_unlock(&node_a->seq_out_lock);
+		spin_unlock_bh(&node_b->seq_out_lock);
+	}
+}
+
 void hsr_del_nodes(struct list_head *node_db)
 {
 	struct hsr_node *node;
@@ -432,7 +466,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame)
 	}
 
 	ether_addr_copy(node_real->macaddress_B, ethhdr->h_source);
-	spin_lock_bh(&node_real->seq_out_lock);
+	hsr_lock_seq_out_pair(node_real, node_curr);
 	for (i = 0; i < HSR_PT_PORTS; i++) {
 		if (!node_curr->time_in_stale[i] &&
 		    time_after(node_curr->time_in[i], node_real->time_in[i])) {
@@ -455,7 +489,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame)
 				  src_blk->seq_nrs[i], HSR_SEQ_BLOCK_SIZE);
 		}
 	}
-	spin_unlock_bh(&node_real->seq_out_lock);
+	hsr_unlock_seq_out_pair(node_real, node_curr);
 	node_real->addr_B_port = port_rcv->type;
 
 	spin_lock_bh(&hsr->list_lock);
-- 
cgit v1.2.3


From 2e3514e63bfb0e972b1f19668547a455d0129e88 Mon Sep 17 00:00:00 2001
From: Luka Gejak <luka.gejak@linux.dev>
Date: Wed, 1 Apr 2026 11:22:43 +0200
Subject: net: hsr: fix VLAN add unwind on slave errors

When vlan_vid_add() fails for a secondary slave, the error path calls
vlan_vid_del() on the failing port instead of the peer slave that had
already succeeded. This results in asymmetric VLAN state across the HSR
pair.

Fix this by switching to a centralized unwind path that removes the VID
from any slave device that was already programmed.

Fixes: 1a8a63a5305e ("net: hsr: Add VLAN CTAG filter support")
Signed-off-by: Luka Gejak <luka.gejak@linux.dev>
Link: https://patch.msgid.link/20260401092243.52121-3-luka.gejak@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_device.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index d1bfc49b5f01..fd2fea25eff0 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -532,8 +532,8 @@ static void hsr_change_rx_flags(struct net_device *dev, int change)
 static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
 				   __be16 proto, u16 vid)
 {
-	bool is_slave_a_added = false;
-	bool is_slave_b_added = false;
+	struct net_device *slave_a_dev = NULL;
+	struct net_device *slave_b_dev = NULL;
 	struct hsr_port *port;
 	struct hsr_priv *hsr;
 	int ret = 0;
@@ -549,33 +549,35 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
 		switch (port->type) {
 		case HSR_PT_SLAVE_A:
 			if (ret) {
-				/* clean up Slave-B */
 				netdev_err(dev, "add vid failed for Slave-A\n");
-				if (is_slave_b_added)
-					vlan_vid_del(port->dev, proto, vid);
-				return ret;
+				goto unwind;
 			}
-
-			is_slave_a_added = true;
+			slave_a_dev = port->dev;
 			break;
-
 		case HSR_PT_SLAVE_B:
 			if (ret) {
-				/* clean up Slave-A */
 				netdev_err(dev, "add vid failed for Slave-B\n");
-				if (is_slave_a_added)
-					vlan_vid_del(port->dev, proto, vid);
-				return ret;
+				goto unwind;
 			}
-
-			is_slave_b_added = true;
+			slave_b_dev = port->dev;
 			break;
 		default:
+			if (ret)
+				goto unwind;
 			break;
 		}
 	}
 
 	return 0;
+
+unwind:
+	if (slave_a_dev)
+		vlan_vid_del(slave_a_dev, proto, vid);
+
+	if (slave_b_dev)
+		vlan_vid_del(slave_b_dev, proto, vid);
+
+	return ret;
 }
 
 static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev,
-- 
cgit v1.2.3


From 4e453375561fc60820e6b9d8ebeb6b3ee177d42e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 1 Apr 2026 15:47:21 +0000
Subject: ipv6: avoid overflows in ip6_datagram_send_ctl()

Yiming Qian reported :
<quote>
 I believe I found a locally triggerable kernel bug in the IPv6 sendmsg
 ancillary-data path that can panic the kernel via `skb_under_panic()`
 (local DoS).

 The core issue is a mismatch between:

 - a 16-bit length accumulator (`struct ipv6_txoptions::opt_flen`, type
 `__u16`) and
 - a pointer to the *last* provided destination-options header (`opt->dst1opt`)

 when multiple `IPV6_DSTOPTS` control messages (cmsgs) are provided.

 - `include/net/ipv6.h`:
   - `struct ipv6_txoptions::opt_flen` is `__u16` (wrap possible).
 (lines 291-307, especially 298)
 - `net/ipv6/datagram.c:ip6_datagram_send_ctl()`:
   - Accepts repeated `IPV6_DSTOPTS` and accumulates into `opt_flen`
 without rejecting duplicates. (lines 909-933)
 - `net/ipv6/ip6_output.c:__ip6_append_data()`:
   - Uses `opt->opt_flen + opt->opt_nflen` to compute header
 sizes/headroom decisions. (lines 1448-1466, especially 1463-1465)
 - `net/ipv6/ip6_output.c:__ip6_make_skb()`:
   - Calls `ipv6_push_frag_opts()` if `opt->opt_flen` is non-zero.
 (lines 1930-1934)
 - `net/ipv6/exthdrs.c:ipv6_push_frag_opts()` / `ipv6_push_exthdr()`:
   - Push size comes from `ipv6_optlen(opt->dst1opt)` (based on the
 pointed-to header). (lines 1179-1185 and 1206-1211)

 1. `opt_flen` is a 16-bit accumulator:

 - `include/net/ipv6.h:298` defines `__u16 opt_flen; /* after fragment hdr */`.

 2. `ip6_datagram_send_ctl()` accepts *repeated* `IPV6_DSTOPTS` cmsgs
 and increments `opt_flen` each time:

 - In `net/ipv6/datagram.c:909-933`, for `IPV6_DSTOPTS`:
   - It computes `len = ((hdr->hdrlen + 1) << 3);`
   - It checks `CAP_NET_RAW` using `ns_capable(net->user_ns,
 CAP_NET_RAW)`. (line 922)
   - Then it does:
     - `opt->opt_flen += len;` (line 927)
     - `opt->dst1opt = hdr;` (line 928)

 There is no duplicate rejection here (unlike the legacy
 `IPV6_2292DSTOPTS` path which rejects duplicates at
 `net/ipv6/datagram.c:901-904`).

 If enough large `IPV6_DSTOPTS` cmsgs are provided, `opt_flen` wraps
 while `dst1opt` still points to a large (2048-byte)
 destination-options header.

 In the attached PoC (`poc.c`):

 - 32 cmsgs with `hdrlen=255` => `len = (255+1)*8 = 2048`
 - 1 cmsg with `hdrlen=0` => `len = 8`
 - Total increment: `32*2048 + 8 = 65544`, so `(__u16)opt_flen == 8`
 - The last cmsg is 2048 bytes, so `dst1opt` points to a 2048-byte header.

 3. The transmit path sizes headers using the wrapped `opt_flen`:

- In `net/ipv6/ip6_output.c:1463-1465`:
  - `headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen +
 opt->opt_nflen : 0) + ...;`

 With wrapped `opt_flen`, `headersize`/headroom decisions underestimate
 what will be pushed later.

 4. When building the final skb, the actual push length comes from
 `dst1opt` and is not limited by wrapped `opt_flen`:

 - In `net/ipv6/ip6_output.c:1930-1934`:
   - `if (opt->opt_flen) proto = ipv6_push_frag_opts(skb, opt, proto);`
 - In `net/ipv6/exthdrs.c:1206-1211`, `ipv6_push_frag_opts()` pushes
 `dst1opt` via `ipv6_push_exthdr()`.
 - In `net/ipv6/exthdrs.c:1179-1184`, `ipv6_push_exthdr()` does:
   - `skb_push(skb, ipv6_optlen(opt));`
   - `memcpy(h, opt, ipv6_optlen(opt));`

 With insufficient headroom, `skb_push()` underflows and triggers
 `skb_under_panic()` -> `BUG()`:

 - `net/core/skbuff.c:2669-2675` (`skb_push()` calls `skb_under_panic()`)
 - `net/core/skbuff.c:207-214` (`skb_panic()` ends in `BUG()`)

 - The `IPV6_DSTOPTS` cmsg path requires `CAP_NET_RAW` in the target
 netns user namespace (`ns_capable(net->user_ns, CAP_NET_RAW)`).
 - Root (or any task with `CAP_NET_RAW`) can trigger this without user
 namespaces.
 - An unprivileged `uid=1000` user can trigger this if unprivileged
 user namespaces are enabled and it can create a userns+netns to obtain
 namespaced `CAP_NET_RAW` (the attached PoC does this).

 - Local denial of service: kernel BUG/panic (system crash).
 - Reproducible with a small userspace PoC.
</quote>

This patch does not reject duplicated options, as this might break
some user applications.

Instead, it makes sure to adjust opt_flen and opt_nflen to correctly
reflect the size of the current option headers, preventing the overflows
and the potential for panics.

This applies to IPV6_DSTOPTS, IPV6_HOPOPTS, and IPV6_RTHDR.

Specifically:

When a new IPV6_DSTOPTS is processed, the length of the old opt->dst1opt
is subtracted from opt->opt_flen before adding the new length.

When a new IPV6_HOPOPTS is processed, the length of the old opt->dst0opt
is subtracted from opt->opt_nflen.

When a new Routing Header (IPV6_RTHDR or IPV6_2292RTHDR) is processed,
the length of the old opt->srcrt is subtracted from opt->opt_nflen.

In the special case within IPV6_2292RTHDR handling where dst1opt is moved
to dst0opt, the length of the old opt->dst0opt is subtracted from
opt->opt_nflen before the new one is added.

Fixes: 333fad5364d6 ("[IPV6]: Support several new sockopt / ancillary data in Advanced API (RFC3542).")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Closes: https://lore.kernel.org/netdev/CAL_bE8JNzawgr5OX5m+3jnQDHry2XxhQT5=jThW1zDPtUikRYA@mail.gmail.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260401154721.3740056-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/datagram.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index c564b68a0562..993e2d76fc1f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -763,6 +763,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
+	struct ipv6_rt_hdr *orthdr;
 	struct ipv6_rt_hdr *rthdr;
 	struct ipv6_opt_hdr *hdr;
 	struct ipv6_txoptions *opt = ipc6->opt;
@@ -924,9 +925,13 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				goto exit_f;
 			}
 			if (cmsg->cmsg_type == IPV6_DSTOPTS) {
+				if (opt->dst1opt)
+					opt->opt_flen -= ipv6_optlen(opt->dst1opt);
 				opt->opt_flen += len;
 				opt->dst1opt = hdr;
 			} else {
+				if (opt->dst0opt)
+					opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
 				opt->opt_nflen += len;
 				opt->dst0opt = hdr;
 			}
@@ -969,12 +974,17 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 				goto exit_f;
 			}
 
+			orthdr = opt->srcrt;
+			if (orthdr)
+				opt->opt_nflen -= ((orthdr->hdrlen + 1) << 3);
 			opt->opt_nflen += len;
 			opt->srcrt = rthdr;
 
 			if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) {
 				int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3);
 
+				if (opt->dst0opt)
+					opt->opt_nflen -= ipv6_optlen(opt->dst0opt);
 				opt->opt_nflen += dsthdrlen;
 				opt->dst0opt = opt->dst1opt;
 				opt->dst1opt = NULL;
-- 
cgit v1.2.3


From 3a359bf5c61d52e7f09754108309d637532164a6 Mon Sep 17 00:00:00 2001
From: Ruide Cao <caoruide123@gmail.com>
Date: Thu, 2 Apr 2026 23:12:31 +0800
Subject: batman-adv: reject oversized global TT response buffers

batadv_tt_prepare_tvlv_global_data() builds the allocation length for a
global TT response in 16-bit temporaries. When a remote originator
advertises a large enough global TT, the TT payload length plus the VLAN
header offset can exceed 65535 and wrap before kmalloc().

The full-table response path still uses the original TT payload length when
it fills tt_change, so the wrapped allocation is too small and
batadv_tt_prepare_tvlv_global_data() writes past the end of the heap object
before the later packet-size check runs.

Fix this by rejecting TT responses whose TVLV value length cannot fit in
the 16-bit TVLV payload length field.

Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific")
Cc: stable@vger.kernel.org
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Ruide Cao <caoruide123@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/translation-table.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 6e95e883c2bf..05cddcf994f6 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -798,8 +798,8 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 {
 	u16 num_vlan = 0;
 	u16 num_entries = 0;
-	u16 change_offset;
-	u16 tvlv_len;
+	u16 tvlv_len = 0;
+	unsigned int change_offset;
 	struct batadv_tvlv_tt_vlan_data *tt_vlan;
 	struct batadv_orig_node_vlan *vlan;
 	u8 *tt_change_ptr;
@@ -816,6 +816,11 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 	if (*tt_len < 0)
 		*tt_len = batadv_tt_len(num_entries);
 
+	if (change_offset > U16_MAX || *tt_len > U16_MAX - change_offset) {
+		*tt_len = 0;
+		goto out;
+	}
+
 	tvlv_len = *tt_len;
 	tvlv_len += change_offset;
 
-- 
cgit v1.2.3


From ec7067e661193403a7a00980bda8612db5954142 Mon Sep 17 00:00:00 2001
From: Dimitri Daskalakis <daskald@meta.com>
Date: Wed, 1 Apr 2026 09:28:48 -0700
Subject: eth: fbnic: Increase FBNIC_QUEUE_SIZE_MIN to 64

On systems with 64K pages, RX queues will be wedged if users set the
descriptor count to the current minimum (16). Fbnic fragments large
pages into 4K chunks, and scales down the ring size accordingly. With
64K pages and 16 descriptors, the ring size mask is 0 and will never
be filled.

32 descriptors is another special case that wedges the RX rings.
Internally, the rings track pages for the head/tail pointers, not page
fragments. So with 32 descriptors, there's only 1 usable page as one
ring slot is kept empty to disambiguate between an empty/full ring.
As a result, the head pointer never advances and the HW stalls after
consuming 16 page fragments.

Fixes: 0cb4c0a13723 ("eth: fbnic: Implement Rx queue alloc/start/stop/free")
Signed-off-by: Dimitri Daskalakis <daskald@meta.com>
Link: https://patch.msgid.link/20260401162848.2335350-1-dimitri.daskalakis1@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 980965274079..e03c9d2c38dc 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -38,7 +38,7 @@ struct fbnic_net;
 #define FBNIC_MAX_XDPQS			128u
 
 /* These apply to TWQs, TCQ, RCQ */
-#define FBNIC_QUEUE_SIZE_MIN		16u
+#define FBNIC_QUEUE_SIZE_MIN		64u
 #define FBNIC_QUEUE_SIZE_MAX		SZ_64K
 
 #define FBNIC_TXQ_SIZE_DEFAULT		1024
-- 
cgit v1.2.3


From b0db1accbc7395657c2b79db59fa9fae0d6656f3 Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Thu, 2 Apr 2026 17:29:22 +0800
Subject: bpf: reject direct access to nullable PTR_TO_BUF pointers

check_mem_access() matches PTR_TO_BUF via base_type() which strips
PTR_MAYBE_NULL, allowing direct dereference without a null check.

Map iterator ctx->key and ctx->value are PTR_TO_BUF | PTR_MAYBE_NULL.
On stop callbacks these are NULL, causing a kernel NULL dereference.

Add a type_may_be_null() guard to the PTR_TO_BUF branch, matching the
existing PTR_TO_BTF_ID pattern.

Fixes: 20b2aff4bc15 ("bpf: Introduce MEM_RDONLY flag")
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20260402092923.38357-2-tpluszz77@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a3388cb8fcbd..df04dccfc540 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7905,7 +7905,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	} else if (reg->type == CONST_PTR_TO_MAP) {
 		err = check_ptr_to_map_access(env, regs, regno, off, size, t,
 					      value_regno);
-	} else if (base_type(reg->type) == PTR_TO_BUF) {
+	} else if (base_type(reg->type) == PTR_TO_BUF &&
+		   !type_may_be_null(reg->type)) {
 		bool rdonly_mem = type_is_rdonly_mem(reg->type);
 		u32 *max_access;
 
-- 
cgit v1.2.3


From eb7024bfcc5f68ed11ed9dd4891a3073c15f04a8 Mon Sep 17 00:00:00 2001
From: Varun R Mallya <varunrmallya@gmail.com>
Date: Thu, 2 Apr 2026 00:41:25 +0530
Subject: bpf: Reject sleepable kprobe_multi programs at attach time

kprobe.multi programs run in atomic/RCU context and cannot sleep.
However, bpf_kprobe_multi_link_attach() did not validate whether the
program being attached had the sleepable flag set, allowing sleepable
helpers such as bpf_copy_from_user() to be invoked from a non-sleepable
context.

This causes a "sleeping function called from invalid context" splat:

  BUG: sleeping function called from invalid context at ./include/linux/uaccess.h:169
  in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1787, name: sudo
  preempt_count: 1, expected: 0
  RCU nest depth: 2, expected: 0

Fix this by rejecting sleepable programs early in
bpf_kprobe_multi_link_attach(), before any further processing.

Fixes: 0dcac2725406 ("bpf: Add multi kprobe link")
Signed-off-by: Varun R Mallya <varunrmallya@gmail.com>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Leon Hwang <leon.hwang@linux.dev>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20260401191126.440683-1-varunrmallya@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/trace/bpf_trace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0b040a417442..af7079aa0f36 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2752,6 +2752,10 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (!is_kprobe_multi(prog))
 		return -EINVAL;
 
+	/* kprobe_multi is not allowed to be sleepable. */
+	if (prog->sleepable)
+		return -EINVAL;
+
 	/* Writing to context is not allowed for kprobes. */
 	if (prog->aux->kprobe_write_ctx)
 		return -EINVAL;
-- 
cgit v1.2.3


From 179ee84a89114b854ac2dd1d293633a7f6c8dac1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 1 Apr 2026 00:20:19 +0200
Subject: bpf: Fix incorrect pruning due to atomic fetch precision tracking

When backtrack_insn encounters a BPF_STX instruction with BPF_ATOMIC
and BPF_FETCH, the src register (or r0 for BPF_CMPXCHG) also acts as
a destination, thus receiving the old value from the memory location.

The current backtracking logic does not account for this. It treats
atomic fetch operations the same as regular stores where the src
register is only an input. This leads the backtrack_insn to fail to
propagate precision to the stack location, which is then not marked
as precise!

Later, the verifier's path pruning can incorrectly consider two states
equivalent when they differ in terms of stack state. Meaning, two
branches can be treated as equivalent and thus get pruned when they
should not be seen as such.

Fix it as follows: Extend the BPF_LDX handling in backtrack_insn to
also cover atomic fetch operations via is_atomic_fetch_insn() helper.
When the fetch dst register is being tracked for precision, clear it,
and propagate precision over to the stack slot. For non-stack memory,
the precision walk stops at the atomic instruction, same as regular
BPF_LDX. This covers all fetch variants.

Before:

  0: (b7) r1 = 8                        ; R1=8
  1: (7b) *(u64 *)(r10 -8) = r1         ; R1=8 R10=fp0 fp-8=8
  2: (b7) r2 = 0                        ; R2=0
  3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)          ; R2=8 R10=fp0 fp-8=mmmmmmmm
  4: (bf) r3 = r10                      ; R3=fp0 R10=fp0
  5: (0f) r3 += r2
  mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1
  mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10
  mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)
  mark_precise: frame0: regs=r2 stack= before 2: (b7) r2 = 0
  6: R2=8 R3=fp8
  6: (b7) r0 = 0                        ; R0=0
  7: (95) exit

After:

  0: (b7) r1 = 8                        ; R1=8
  1: (7b) *(u64 *)(r10 -8) = r1         ; R1=8 R10=fp0 fp-8=8
  2: (b7) r2 = 0                        ; R2=0
  3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)          ; R2=8 R10=fp0 fp-8=mmmmmmmm
  4: (bf) r3 = r10                      ; R3=fp0 R10=fp0
  5: (0f) r3 += r2
  mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1
  mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10
  mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)
  mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0
  mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1
  mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8
  6: R2=8 R3=fp8
  6: (b7) r0 = 0                        ; R0=0
  7: (95) exit

Fixes: 5ffa25502b5a ("bpf: Add instructions for atomic_[cmp]xchg")
Fixes: 5ca419f2864a ("bpf: Add BPF_FETCH field / create atomic_fetch_add instruction")
Reported-by: STAR Labs SG <info@starlabs.sg>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20260331222020.401848-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index df04dccfc540..e3814152b52f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -617,6 +617,13 @@ static bool is_atomic_load_insn(const struct bpf_insn *insn)
 	       insn->imm == BPF_LOAD_ACQ;
 }
 
+static bool is_atomic_fetch_insn(const struct bpf_insn *insn)
+{
+	return BPF_CLASS(insn->code) == BPF_STX &&
+	       BPF_MODE(insn->code) == BPF_ATOMIC &&
+	       (insn->imm & BPF_FETCH);
+}
+
 static int __get_spi(s32 off)
 {
 	return (-off - 1) / BPF_REG_SIZE;
@@ -4447,10 +4454,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			   * dreg still needs precision before this insn
 			   */
 		}
-	} else if (class == BPF_LDX || is_atomic_load_insn(insn)) {
-		if (!bt_is_reg_set(bt, dreg))
+	} else if (class == BPF_LDX ||
+		   is_atomic_load_insn(insn) ||
+		   is_atomic_fetch_insn(insn)) {
+		u32 load_reg = dreg;
+
+		/*
+		 * Atomic fetch operation writes the old value into
+		 * a register (sreg or r0) and if it was tracked for
+		 * precision, propagate to the stack slot like we do
+		 * in regular ldx.
+		 */
+		if (is_atomic_fetch_insn(insn))
+			load_reg = insn->imm == BPF_CMPXCHG ?
+				   BPF_REG_0 : sreg;
+
+		if (!bt_is_reg_set(bt, load_reg))
 			return 0;
-		bt_clear_reg(bt, dreg);
+		bt_clear_reg(bt, load_reg);
 
 		/* scalars can only be spilled into stack w/o losing precision.
 		 * Load from any other memory can be zero extended.
-- 
cgit v1.2.3


From e1b5687a862a43429f1d9f69065b3bbc7780a97a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 1 Apr 2026 00:20:20 +0200
Subject: selftests/bpf: Add more precision tracking tests for atomics

Add verifier precision tracking tests for BPF atomic fetch operations.
Validate that backtrack_insn correctly propagates precision from the
fetch dst_reg to the stack slot for {fetch_add,xchg,cmpxchg} atomics.
For the first two src_reg gets the old memory value, and for the last
one r0. The fetched register is used for pointer arithmetic to trigger
backtracking. Also add coverage for fetch_{or,and,xor} flavors which
exercises the bitwise atomic fetch variants going through the same
insn->imm & BPF_FETCH check but with different imm values.

Add dual-precision regression tests for fetch_add and cmpxchg where
both the fetched value and a reread of the same stack slot are tracked
for precision. After the atomic operation, the stack slot is STACK_MISC,
so the ldx does not set INSN_F_STACK_ACCESS. These tests verify that
stack precision propagates solely through the atomic fetch's load side.

Add map-based tests for fetch_add and cmpxchg which validate that non-
stack atomic fetch completes precision tracking without falling back
to mark_all_scalars_precise. Lastly, add 32-bit variants for {fetch_add,
cmpxchg} on map values to cover the second valid atomic operand size.

  # LDLIBS=-static PKG_CONFIG='pkg-config --static' ./vmtest.sh -- ./test_progs -t verifier_precision
  [...]
  + /etc/rcS.d/S50-startup
  ./test_progs -t verifier_precision
  [    1.697105] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.700220] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  [    1.777043] tsc: Refined TSC clocksource calibration: 3407.986 MHz
  [    1.777619] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fc6d7268, max_idle_ns: 440795260133 ns
  [    1.778658] clocksource: Switched to clocksource tsc
  #633/1   verifier_precision/bpf_neg:OK
  #633/2   verifier_precision/bpf_end_to_le:OK
  #633/3   verifier_precision/bpf_end_to_be:OK
  #633/4   verifier_precision/bpf_end_bswap:OK
  #633/5   verifier_precision/bpf_load_acquire:OK
  #633/6   verifier_precision/bpf_store_release:OK
  #633/7   verifier_precision/state_loop_first_last_equal:OK
  #633/8   verifier_precision/bpf_cond_op_r10:OK
  #633/9   verifier_precision/bpf_cond_op_not_r10:OK
  #633/10  verifier_precision/bpf_atomic_fetch_add_precision:OK
  #633/11  verifier_precision/bpf_atomic_xchg_precision:OK
  #633/12  verifier_precision/bpf_atomic_fetch_or_precision:OK
  #633/13  verifier_precision/bpf_atomic_fetch_and_precision:OK
  #633/14  verifier_precision/bpf_atomic_fetch_xor_precision:OK
  #633/15  verifier_precision/bpf_atomic_cmpxchg_precision:OK
  #633/16  verifier_precision/bpf_atomic_fetch_add_dual_precision:OK
  #633/17  verifier_precision/bpf_atomic_cmpxchg_dual_precision:OK
  #633/18  verifier_precision/bpf_atomic_fetch_add_map_precision:OK
  #633/19  verifier_precision/bpf_atomic_cmpxchg_map_precision:OK
  #633/20  verifier_precision/bpf_atomic_fetch_add_32bit_precision:OK
  #633/21  verifier_precision/bpf_atomic_cmpxchg_32bit_precision:OK
  #633/22  verifier_precision/bpf_neg_2:OK
  #633/23  verifier_precision/bpf_neg_3:OK
  #633/24  verifier_precision/bpf_neg_4:OK
  #633/25  verifier_precision/bpf_neg_5:OK
  #633     verifier_precision:OK
  Summary: 1/25 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20260331222020.401848-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/verifier_precision.c       | 341 +++++++++++++++++++++
 1 file changed, 341 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 1fe090cd6744..4794903aec8e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -5,6 +5,13 @@
 #include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} precision_map SEC(".maps");
+
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
@@ -301,4 +308,338 @@ __naked int bpf_neg_5(void)
 	::: __clobber_all);
 }
 
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_add_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_add_insn];"	/* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_xchg((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_xchg_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[xchg_insn];"		/* r2 = atomic_xchg(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(xchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_or((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_or_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_or_insn];"	/* r2 = atomic_fetch_or(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_or_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_OR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_and((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_and_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_and_insn];"	/* r2 = atomic_fetch_and(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_and_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_xor((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_xor_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_xor_insn];"	/* r2 = atomic_fetch_xor(*(u64 *)(r10 - 8), r2) */
+	"r3 = r10;"
+	"r3 += r2;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_xor_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_XOR | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_cmpxchg_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r0 = 0;"
+	"r2 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */
+	"r3 = r10;"
+	"r3 += r0;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+/* Regression test for dual precision: Both the fetched value (r2) and
+ * a reread of the same stack slot (r3) are tracked for precision. After
+ * the atomic operation, the stack slot is STACK_MISC. Thus, the ldx at
+ * insn 4 does NOT set INSN_F_STACK_ACCESS. Precision for the stack slot
+ * propagates solely through the atomic fetch's load side (insn 3).
+ */
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2,r3 stack= before 4: (79) r3 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (db) r2 = atomic64_fetch_add((u64 *)(r10 -8), r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_fetch_add_dual_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = 0;"
+	".8byte %[fetch_add_insn];"	/* r2 = atomic_fetch_add(*(u64 *)(r10 - 8), r2) */
+	"r3 = *(u64 *)(r10 - 8);"
+	"r4 = r2;"
+	"r4 += r3;"
+	"r4 &= 7;"
+	"r5 = r10;"
+	"r5 += r4;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0,r3 stack= before 5: (79) r3 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r2)")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (b7) r2 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 2: (b7) r0 = 8")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_atomic_cmpxchg_dual_precision(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r0 = 8;"
+	"r2 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r10 - 8), r0, r2) */
+	"r3 = *(u64 *)(r10 - 8);"
+	"r4 = r0;"
+	"r4 += r3;"
+	"r4 &= 7;"
+	"r5 = r10;"
+	"r5 += r4;"			/* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7")
+__msg("mark_precise: frame0: regs=r1 stack= before 9: (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_fetch_add_map_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r1 = 0;"
+	".8byte %[fetch_add_insn];"	/* r1 = atomic_fetch_add(*(u64 *)(r0 + 0), r1) */
+	"r1 &= 7;"
+	"r2 = r10;"
+	"r2 += r1;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (db) r0 = atomic64_cmpxchg((u64 *)(r6 +0), r0, r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_cmpxchg_map_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r6 = r0;"
+	"r0 = 0;"
+	"r1 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u64 *)(r6 + 0), r0, r1) */
+	"r0 &= 7;"
+	"r2 = r10;"
+	"r2 += r0;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 10: (57) r1 &= 7")
+__msg("mark_precise: frame0: regs=r1 stack= before 9: (c3) r1 = atomic_fetch_add((u32 *)(r0 +0), r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_fetch_add_32bit_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r1 = 0;"
+	".8byte %[fetch_add_insn];"	/* r1 = atomic_fetch_add(*(u32 *)(r0 + 0), r1) */
+	"r1 &= 7;"
+	"r2 = r10;"
+	"r2 += r1;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(fetch_add_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_ADD | BPF_FETCH, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (57) r0 &= 7")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (c3) r0 = atomic_cmpxchg((u32 *)(r6 +0), r0, r1)")
+__not_msg("falling back to forcing all scalars precise")
+__naked int bpf_atomic_cmpxchg_32bit_precision(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[precision_map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto 1f;"
+	"r6 = r0;"
+	"r0 = 0;"
+	"r1 = 0;"
+	".8byte %[cmpxchg_insn];"	/* r0 = atomic_cmpxchg(*(u32 *)(r6 + 0), r0, r1) */
+	"r0 &= 7;"
+	"r2 = r10;"
+	"r2 += r0;"			/* mark_precise */
+	"1: r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(precision_map),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(cmpxchg_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_6, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From a4983968fa5b3179ab090407d325a71cdc96874e Mon Sep 17 00:00:00 2001
From: Ionut Nechita <ionut_n2001@yahoo.com>
Date: Mon, 23 Mar 2026 23:13:43 +0200
Subject: drm/amd/display: Wire up dcn10_dio_construct() for all pre-DCN401
 generations

Description:
 - Commit b82f0759346617b2 ("drm/amd/display: Migrate DIO registers access
   from hwseq to dio component") moved DIO_MEM_PWR_CTRL register access
   behind the new dio abstraction layer but only created the dio object for
   DCN 4.01. On all other generations (DCN 10/20/21/201/30/301/302/303/
   31/314/315/316/32/321/35/351/36), the dio pointer is NULL, causing the
   register write to be silently skipped.

   This results in AFMT HDMI memory not being powered on during init_hw,
   which can cause HDMI audio failures and display issues on affected
   hardware including Renoir/Cezanne (DCN 2.1) APUs that use dcn10_init_hw.

   Call dcn10_dio_construct() in each older DCN generation's resource.c
   to create the dio object, following the same pattern as DCN 4.01. This
   ensures the dio pointer is non-NULL and the mem_pwr_ctrl callback works
   through the dio abstraction for all DCN generations.

Fixes: b82f07593466 ("drm/amd/display: Migrate DIO registers access from hwseq to dio component.")
Reviewed-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Ionut Nechita <ionut_n2001@yahoo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/resource/dcn10/dcn10_resource.c | 41 +++++++++++++++++++++
 .../amd/display/dc/resource/dcn20/dcn20_resource.c | 42 +++++++++++++++++++++
 .../display/dc/resource/dcn201/dcn201_resource.c   | 41 +++++++++++++++++++++
 .../amd/display/dc/resource/dcn21/dcn21_resource.c | 34 +++++++++++++++++
 .../amd/display/dc/resource/dcn30/dcn30_resource.c | 42 +++++++++++++++++++++
 .../display/dc/resource/dcn301/dcn301_resource.c   | 42 +++++++++++++++++++++
 .../display/dc/resource/dcn302/dcn302_resource.c   | 41 +++++++++++++++++++++
 .../display/dc/resource/dcn303/dcn303_resource.c   | 41 +++++++++++++++++++++
 .../amd/display/dc/resource/dcn31/dcn31_resource.c | 40 ++++++++++++++++++++
 .../display/dc/resource/dcn314/dcn314_resource.c   | 40 ++++++++++++++++++++
 .../display/dc/resource/dcn315/dcn315_resource.c   | 40 ++++++++++++++++++++
 .../display/dc/resource/dcn316/dcn316_resource.c   | 40 ++++++++++++++++++++
 .../amd/display/dc/resource/dcn32/dcn32_resource.c | 43 ++++++++++++++++++++++
 .../display/dc/resource/dcn321/dcn321_resource.c   | 43 ++++++++++++++++++++++
 .../amd/display/dc/resource/dcn35/dcn35_resource.c | 43 ++++++++++++++++++++++
 .../display/dc/resource/dcn351/dcn351_resource.c   | 43 ++++++++++++++++++++++
 .../amd/display/dc/resource/dcn36/dcn36_resource.c | 43 ++++++++++++++++++++++
 17 files changed, 699 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
index bbe185e15eb6..4663456a736a 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
@@ -71,6 +71,7 @@
 #include "dce/dce_dmcu.h"
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
+#include "dio/dcn10/dcn10_dio.h"
 
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL		0x210f
@@ -444,6 +445,33 @@ static const struct dcn_hubbub_mask hubbub_mask = {
 		HUBBUB_MASK_SH_LIST_DCN10(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn10_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static int map_transmitter_id_to_phy_instance(
 	enum transmitter transmitter)
 {
@@ -917,6 +945,11 @@ static void dcn10_resource_destruct(struct dcn10_resource_pool *pool)
 	kfree(pool->base.hubbub);
 	pool->base.hubbub = NULL;
 
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.opps[i] != NULL)
 			pool->base.opps[i]->funcs->opp_destroy(&pool->base.opps[i]);
@@ -1653,6 +1686,14 @@ static bool dcn10_resource_construct(
 		goto fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn10_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto fail;
+	}
+
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
 		goto fail;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
index 8b555187ac75..74e8d229c9dd 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
@@ -82,6 +82,7 @@
 #include "dce/dce_dmcu.h"
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "vm_helper.h"
 
 #include "link_enc_cfg.h"
@@ -550,6 +551,33 @@ static const struct dcn_hubbub_mask hubbub_mask = {
 		HUBBUB_MASK_SH_LIST_DCN20(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn20_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 #define vmid_regs(id)\
 [id] = {\
 		DCN20_VMID_REG_LIST(id)\
@@ -1104,6 +1132,12 @@ static void dcn20_resource_destruct(struct dcn20_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn20_dpp_destroy(&pool->base.dpps[i]);
@@ -2692,6 +2726,14 @@ static bool dcn20_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn20_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn20_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c
index 4ea76e46ab15..e289be70efb5 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn201/dcn201_resource.c
@@ -56,6 +56,7 @@
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
 #include "dcn10/dcn10_resource.h"
+#include "dio/dcn10/dcn10_dio.h"
 
 #include "cyan_skillfish_ip_offset.h"
 
@@ -755,6 +756,33 @@ static struct hubbub *dcn201_hubbub_create(struct dc_context *ctx)
 	return &hubbub->base;
 }
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn201_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct timing_generator *dcn201_timing_generator_create(
 		struct dc_context *ctx,
 		uint32_t instance)
@@ -930,6 +958,11 @@ static void dcn201_resource_destruct(struct dcn201_resource_pool *pool)
 		pool->base.hubbub = NULL;
 	}
 
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn201_dpp_destroy(&pool->base.dpps[i]);
@@ -1276,6 +1309,14 @@ static bool dcn201_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn201_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
 		goto create_fail;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c
index 0f4307f8f3dd..4333baac96ad 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn21/dcn21_resource.c
@@ -84,6 +84,7 @@
 #include "dce/dce_dmcu.h"
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dcn21_resource.h"
 #include "vm_helper.h"
 #include "dcn20/dcn20_vmid.h"
@@ -329,6 +330,25 @@ static const struct dcn_hubbub_mask hubbub_mask = {
 		HUBBUB_MASK_SH_LIST_DCN21(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+static const struct dcn_dio_shift dio_shift = { 0 };
+
+static const struct dcn_dio_mask dio_mask = { 0 };
+
+static struct dio *dcn21_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
 
 #define vmid_regs(id)\
 [id] = {\
@@ -677,6 +697,12 @@ static void dcn21_resource_destruct(struct dcn21_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn20_dpp_destroy(&pool->base.dpps[i]);
@@ -1654,6 +1680,14 @@ static bool dcn21_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn21_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn21_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
index 2fa86b9587ed..87b7b4ee04c6 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
@@ -60,6 +60,7 @@
 #include "dml/display_mode_vba.h"
 #include "dcn30/dcn30_dccg.h"
 #include "dcn10/dcn10_resource.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "link_service.h"
 #include "dce/dce_panel_cntl.h"
 
@@ -886,6 +887,33 @@ static struct hubbub *dcn30_hubbub_create(struct dc_context *ctx)
 	return &hubbub3->base;
 }
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn30_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct timing_generator *dcn30_timing_generator_create(
 		struct dc_context *ctx,
 		uint32_t instance)
@@ -1095,6 +1123,12 @@ static void dcn30_resource_destruct(struct dcn30_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn30_dpp_destroy(&pool->base.dpps[i]);
@@ -2464,6 +2498,14 @@ static bool dcn30_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn30_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn30_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
index 7842bee57e63..6bb1c62124bb 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn301/dcn301_resource.c
@@ -59,6 +59,7 @@
 #include "dml/display_mode_vba.h"
 #include "dcn301/dcn301_dccg.h"
 #include "dcn10/dcn10_resource.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dcn30/dcn30_dio_stream_encoder.h"
 #include "dcn301/dcn301_dio_link_encoder.h"
 #include "dcn301/dcn301_panel_cntl.h"
@@ -843,6 +844,33 @@ static struct hubbub *dcn301_hubbub_create(struct dc_context *ctx)
 	return &hubbub3->base;
 }
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn301_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct timing_generator *dcn301_timing_generator_create(
 	struct dc_context *ctx, uint32_t instance)
 {
@@ -1066,6 +1094,12 @@ static void dcn301_destruct(struct dcn301_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn301_dpp_destroy(&pool->base.dpps[i]);
@@ -1582,6 +1616,14 @@ static bool dcn301_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn301_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	j = 0;
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c
index 1874d5d6b782..d02aafd06fd4 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn302/dcn302_resource.c
@@ -46,6 +46,7 @@
 #include "dml/dcn30/dcn30_fpu.h"
 
 #include "dcn10/dcn10_resource.h"
+#include "dio/dcn10/dcn10_dio.h"
 
 #include "link_service.h"
 
@@ -253,6 +254,33 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn302_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn302_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1022,6 +1050,11 @@ static void dcn302_resource_destruct(struct resource_pool *pool)
 		pool->hubbub = NULL;
 	}
 
+	if (pool->dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->dio));
+		pool->dio = NULL;
+	}
+
 	for (i = 0; i < pool->pipe_count; i++) {
 		if (pool->dpps[i] != NULL) {
 			kfree(TO_DCN20_DPP(pool->dpps[i]));
@@ -1372,6 +1405,14 @@ static bool dcn302_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->dio = dcn302_dio_create(ctx);
+	if (pool->dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->pipe_count; i++) {
 		pool->hubps[i] = dcn302_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c
index d52201cb359f..30b1403112c6 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn303/dcn303_resource.c
@@ -46,6 +46,7 @@
 #include "dml/dcn30/dcn30_fpu.h"
 
 #include "dcn10/dcn10_resource.h"
+#include "dio/dcn10/dcn10_dio.h"
 
 #include "link_service.h"
 
@@ -249,6 +250,33 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
+static struct dio *dcn303_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn303_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -966,6 +994,11 @@ static void dcn303_resource_destruct(struct resource_pool *pool)
 		pool->hubbub = NULL;
 	}
 
+	if (pool->dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->dio));
+		pool->dio = NULL;
+	}
+
 	for (i = 0; i < pool->pipe_count; i++) {
 		if (pool->dpps[i] != NULL) {
 			kfree(TO_DCN20_DPP(pool->dpps[i]));
@@ -1304,6 +1337,14 @@ static bool dcn303_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->dio = dcn303_dio_create(ctx);
+	if (pool->dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->pipe_count; i++) {
 		pool->hubps[i] = dcn303_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index 2055f1f8af65..4e9c041c707a 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -64,6 +64,7 @@
 #include "dce/dce_audio.h"
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dio/virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
@@ -810,6 +811,21 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn31 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -1021,6 +1037,18 @@ static struct mpc *dcn31_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn31_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn31_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1396,6 +1424,10 @@ static void dcn31_resource_destruct(struct dcn31_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn31_dpp_destroy(&pool->base.dpps[i]);
@@ -2063,6 +2095,14 @@ static bool dcn31_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn31_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn31_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index 1939f720ba29..e26a6427916a 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -66,6 +66,7 @@
 #include "dce/dce_audio.h"
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dio/virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
@@ -822,6 +823,21 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn314 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -1079,6 +1095,18 @@ static struct mpc *dcn31_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn314_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn31_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1455,6 +1483,10 @@ static void dcn314_resource_destruct(struct dcn314_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn31_dpp_destroy(&pool->base.dpps[i]);
@@ -1987,6 +2019,14 @@ static bool dcn314_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn314_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn31_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
index e8377c190f63..131a6cd4c735 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
@@ -63,6 +63,7 @@
 #include "dce/dce_audio.h"
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dio/virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
@@ -809,6 +810,21 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn31 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -1020,6 +1036,18 @@ static struct mpc *dcn31_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn315_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn31_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1397,6 +1425,10 @@ static void dcn315_resource_destruct(struct dcn315_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn31_dpp_destroy(&pool->base.dpps[i]);
@@ -2012,6 +2044,14 @@ static bool dcn315_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn315_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn31_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c
index 045ce01bd74e..c8c0ce6efcfd 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn316/dcn316_resource.c
@@ -63,6 +63,7 @@
 #include "dce/dce_audio.h"
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dio/virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
@@ -804,6 +805,21 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dcn_dio_registers dio_regs = {
+		DIO_REG_LIST_DCN10()
+};
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn31 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -1013,6 +1029,18 @@ static struct mpc *dcn31_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn316_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn31_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1392,6 +1420,10 @@ static void dcn316_resource_destruct(struct dcn316_resource_pool *pool)
 		kfree(pool->base.hubbub);
 		pool->base.hubbub = NULL;
 	}
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		if (pool->base.dpps[i] != NULL)
 			dcn31_dpp_destroy(&pool->base.dpps[i]);
@@ -1887,6 +1919,14 @@ static bool dcn316_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn316_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn31_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index c7fd604024d6..c3a6ae14de18 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -66,6 +66,7 @@
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
 #include "dio/virtual/virtual_stream_encoder.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dml/display_mode_vba.h"
 #include "dcn32/dcn32_dccg.h"
 #include "dcn10/dcn10_resource.h"
@@ -643,6 +644,19 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static struct dcn_dio_registers dio_regs;
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn32 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -833,6 +847,22 @@ static struct clock_source *dcn32_clock_source_create(
 	return NULL;
 }
 
+static struct dio *dcn32_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+#undef REG_STRUCT
+#define REG_STRUCT dio_regs
+	DIO_REG_LIST_DCN10();
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn32_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1494,6 +1524,11 @@ static void dcn32_resource_destruct(struct dcn32_resource_pool *pool)
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
 
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	if (pool->base.oem_device != NULL) {
 		struct dc *dc = pool->base.oem_device->ctx->dc;
 
@@ -2373,6 +2408,14 @@ static bool dcn32_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn32_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs, TGs, ABMs */
 	for (i = 0, j = 0; i < pool->base.res_cap->num_timing_generator; i++) {
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
index c1582c27ac87..990aec7eb3d0 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
@@ -69,6 +69,7 @@
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
 #include "dio/virtual/virtual_stream_encoder.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dml/display_mode_vba.h"
 #include "dcn32/dcn32_dccg.h"
 #include "dcn10/dcn10_resource.h"
@@ -639,6 +640,19 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static struct dcn_dio_registers dio_regs;
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn321 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -827,6 +841,22 @@ static struct clock_source *dcn321_clock_source_create(
 	return NULL;
 }
 
+static struct dio *dcn321_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+#undef REG_STRUCT
+#define REG_STRUCT dio_regs
+	DIO_REG_LIST_DCN10();
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn321_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1474,6 +1504,11 @@ static void dcn321_resource_destruct(struct dcn321_resource_pool *pool)
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
 
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
+
 	if (pool->base.oem_device != NULL) {
 		struct dc *dc = pool->base.oem_device->ctx->dc;
 
@@ -1872,6 +1907,14 @@ static bool dcn321_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn321_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs, TGs, ABMs */
 	for (i = 0, j = 0; i < pool->base.res_cap->num_timing_generator; i++) {
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 3494a40cea99..598b2f25881d 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -71,6 +71,7 @@
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
 #include "dio/virtual/virtual_stream_encoder.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
 #include "dcn35/dcn35_dccg.h"
@@ -664,6 +665,19 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static struct dcn_dio_registers dio_regs;
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn35 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -973,6 +987,22 @@ static struct mpc *dcn35_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn35_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+#undef REG_STRUCT
+#define REG_STRUCT dio_regs
+	DIO_REG_LIST_DCN10();
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn35_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1563,6 +1593,11 @@ static void dcn35_resource_destruct(struct dcn35_resource_pool *pool)
 
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 }
 
 static struct hubp *dcn35_hubp_create(
@@ -2033,6 +2068,14 @@ static bool dcn35_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn35_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn35_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 080bc7f24ffa..7e15d07df7a3 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -50,6 +50,7 @@
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
 #include "dio/virtual/virtual_stream_encoder.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
 #include "dcn35/dcn35_dccg.h"
@@ -644,6 +645,19 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static struct dcn_dio_registers dio_regs;
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn351 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -953,6 +967,22 @@ static struct mpc *dcn35_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn351_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+#undef REG_STRUCT
+#define REG_STRUCT dio_regs
+	DIO_REG_LIST_DCN10();
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn35_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1543,6 +1573,11 @@ static void dcn351_resource_destruct(struct dcn351_resource_pool *pool)
 
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 }
 
 static struct hubp *dcn35_hubp_create(
@@ -2005,6 +2040,14 @@ static bool dcn351_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn351_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn35_hubp_create(ctx, i);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
index af51ac4ea59e..83fee2ca61bf 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
@@ -50,6 +50,7 @@
 #include "dce/dce_hwseq.h"
 #include "clk_mgr.h"
 #include "dio/virtual/virtual_stream_encoder.h"
+#include "dio/dcn10/dcn10_dio.h"
 #include "dce110/dce110_resource.h"
 #include "dml/display_mode_vba.h"
 #include "dcn35/dcn35_dccg.h"
@@ -651,6 +652,19 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static struct dcn_dio_registers dio_regs;
+
+#define DIO_MASK_SH_LIST(mask_sh)\
+		HWS_SF(, DIO_MEM_PWR_CTRL, I2C_LIGHT_SLEEP_FORCE, mask_sh)
+
+static const struct dcn_dio_shift dio_shift = {
+		DIO_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dcn_dio_mask dio_mask = {
+		DIO_MASK_SH_LIST(_MASK)
+};
+
 static const struct resource_caps res_cap_dcn36 = {
 	.num_timing_generator = 4,
 	.num_opp = 4,
@@ -960,6 +974,22 @@ static struct mpc *dcn35_mpc_create(
 	return &mpc30->base;
 }
 
+static struct dio *dcn36_dio_create(struct dc_context *ctx)
+{
+	struct dcn10_dio *dio10 = kzalloc_obj(struct dcn10_dio);
+
+	if (!dio10)
+		return NULL;
+
+#undef REG_STRUCT
+#define REG_STRUCT dio_regs
+	DIO_REG_LIST_DCN10();
+
+	dcn10_dio_construct(dio10, ctx, &dio_regs, &dio_shift, &dio_mask);
+
+	return &dio10->base;
+}
+
 static struct hubbub *dcn35_hubbub_create(struct dc_context *ctx)
 {
 	int i;
@@ -1550,6 +1580,11 @@ static void dcn36_resource_destruct(struct dcn36_resource_pool *pool)
 
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
+
+	if (pool->base.dio != NULL) {
+		kfree(TO_DCN10_DIO(pool->base.dio));
+		pool->base.dio = NULL;
+	}
 }
 
 static struct hubp *dcn35_hubp_create(
@@ -2012,6 +2047,14 @@ static bool dcn36_resource_construct(
 		goto create_fail;
 	}
 
+	/* DIO */
+	pool->base.dio = dcn36_dio_create(ctx);
+	if (pool->base.dio == NULL) {
+		BREAK_TO_DEBUGGER();
+		dm_error("DC: failed to create dio!\n");
+		goto create_fail;
+	}
+
 	/* HUBPs, DPPs, OPPs and TGs */
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.hubps[i] = dcn35_hubp_create(ctx, i);
-- 
cgit v1.2.3


From 0c4a59df370bea245695c00aaae6ae75747139bd Mon Sep 17 00:00:00 2001
From: Changwoo Min <changwoo@igalia.com>
Date: Thu, 2 Apr 2026 11:31:50 +0900
Subject: sched_ext: Fix is_bpf_migration_disabled() false negative on
 non-PREEMPT_RCU

Since commit 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for
trampoline.c"), the BPF prolog (__bpf_prog_enter) calls migrate_disable()
only when CONFIG_PREEMPT_RCU is enabled, via rcu_read_lock_dont_migrate().
Without CONFIG_PREEMPT_RCU, the prolog never touches migration_disabled,
so migration_disabled == 1 always means the task is truly
migration-disabled regardless of whether it is the current task.

The old unconditional p == current check was a false negative in this
case, potentially allowing a migration-disabled task to be dispatched to
a remote CPU and triggering scx_error in task_can_run_on_remote_rq().

Only apply the p == current disambiguation when CONFIG_PREEMPT_RCU is
enabled, where the ambiguity with the BPF prolog still exists.

Fixes: 8e4f0b1ebcf2 ("bpf: use rcu_read_lock_dont_migrate() for trampoline.c")
Cc: stable@vger.kernel.org # v6.18+
Link: https://lore.kernel.org/lkml/20250821090609.42508-8-dongml2@chinatelecom.cn/
Signed-off-by: Changwoo Min <changwoo@igalia.com>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext_idle.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 0ae93cd64004..44c3a50c542c 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -860,25 +860,32 @@ static bool check_builtin_idle_enabled(struct scx_sched *sch)
  * code.
  *
  * We can't simply check whether @p->migration_disabled is set in a
- * sched_ext callback, because migration is always disabled for the current
- * task while running BPF code.
+ * sched_ext callback, because the BPF prolog (__bpf_prog_enter) may disable
+ * migration for the current task while running BPF code.
  *
- * The prolog (__bpf_prog_enter) and epilog (__bpf_prog_exit) respectively
- * disable and re-enable migration. For this reason, the current task
- * inside a sched_ext callback is always a migration-disabled task.
+ * Since the BPF prolog calls migrate_disable() only when CONFIG_PREEMPT_RCU
+ * is enabled (via rcu_read_lock_dont_migrate()), migration_disabled == 1 for
+ * the current task is ambiguous only in that case: it could be from the BPF
+ * prolog rather than a real migrate_disable() call.
  *
- * Therefore, when @p->migration_disabled == 1, check whether @p is the
- * current task or not: if it is, then migration was not disabled before
- * entering the callback, otherwise migration was disabled.
+ * Without CONFIG_PREEMPT_RCU, the BPF prolog never calls migrate_disable(),
+ * so migration_disabled == 1 always means the task is truly
+ * migration-disabled.
+ *
+ * Therefore, when migration_disabled == 1 and CONFIG_PREEMPT_RCU is enabled,
+ * check whether @p is the current task or not: if it is, then migration was
+ * not disabled before entering the callback, otherwise migration was disabled.
  *
  * Returns true if @p is migration-disabled, false otherwise.
  */
 static bool is_bpf_migration_disabled(const struct task_struct *p)
 {
-	if (p->migration_disabled == 1)
-		return p != current;
-	else
-		return p->migration_disabled;
+	if (p->migration_disabled == 1) {
+		if (IS_ENABLED(CONFIG_PREEMPT_RCU))
+			return p != current;
+		return true;
+	}
+	return p->migration_disabled;
 }
 
 static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
-- 
cgit v1.2.3


From 07712db80857d5d09ae08f3df85a708ecfc3b61f Mon Sep 17 00:00:00 2001
From: Nicholas Carlini <nicholas@carlini.com>
Date: Tue, 31 Mar 2026 15:25:32 +0200
Subject: eventpoll: defer struct eventpoll free to RCU grace period

In certain situations, ep_free() in eventpoll.c will kfree the epi->ep
eventpoll struct while it still being used by another concurrent thread.
Defer the kfree() to an RCU callback to prevent UAF.

Fixes: f2e467a48287 ("eventpoll: Fix semi-unbounded recursion")
Signed-off-by: Nicholas Carlini <nicholas@carlini.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventpoll.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 5714e900567c..4b43bf41296d 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -226,6 +226,9 @@ struct eventpoll {
 	 */
 	refcount_t refcount;
 
+	/* used to defer freeing past ep_get_upwards_depth_proc() RCU walk */
+	struct rcu_head rcu;
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* used to track busy poll napi_id */
 	unsigned int napi_id;
@@ -819,7 +822,8 @@ static void ep_free(struct eventpoll *ep)
 	mutex_destroy(&ep->mtx);
 	free_uid(ep->user);
 	wakeup_source_unregister(ep->ws);
-	kfree(ep);
+	/* ep_get_upwards_depth_proc() may still hold epi->ep under RCU */
+	kfree_rcu(ep, rcu);
 }
 
 /*
-- 
cgit v1.2.3


From 8eceab19eba9dcbfd2a0daec72e1bf48aa100170 Mon Sep 17 00:00:00 2001
From: Douya Le <ldy3087146292@gmail.com>
Date: Thu, 2 Apr 2026 23:34:55 +0800
Subject: crypto: af_alg - limit RX SG extraction by receive buffer budget

Make af_alg_get_rsgl() limit each RX scatterlist extraction to the
remaining receive buffer budget.

af_alg_get_rsgl() currently uses af_alg_readable() only as a gate
before extracting data into the RX scatterlist. Limit each extraction
to the remaining af_alg_rcvbuf(sk) budget so that receive-side
accounting matches the amount of data attached to the request.

If skcipher cannot obtain enough RX space for at least one chunk while
more data remains to be processed, reject the recvmsg call instead of
rounding the request length down to zero.

Fixes: e870456d8e7c8d57c059ea479b5aadbb55ff4c3a ("crypto: algif_skcipher - overhaul memory management")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Douya Le <ldy3087146292@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c         | 2 ++
 crypto/algif_skcipher.c | 5 +++++
 2 files changed, 7 insertions(+)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 8e0199394984..437f3e77c7e0 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1229,6 +1229,8 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 
 		seglen = min_t(size_t, (maxsize - len),
 			       msg_data_left(msg));
+		/* Never pin more pages than the remaining RX accounting budget. */
+		seglen = min_t(size_t, seglen, af_alg_rcvbuf(sk));
 
 		if (list_empty(&areq->rsgl_list)) {
 			rsgl = &areq->first_rsgl;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 82735e51be10..ba0a17fd95ac 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -130,6 +130,11 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * full block size buffers.
 	 */
 	if (ctx->more || len < ctx->used) {
+		if (len < bs) {
+			err = -EINVAL;
+			goto free;
+		}
+
 		len -= len % bs;
 		cflags |= CRYPTO_SKCIPHER_REQ_NOTFINAL;
 	}
-- 
cgit v1.2.3


From 2fd68c7ea2ae741a4446d54c8a461255022e2dc7 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Wed, 1 Apr 2026 10:28:39 +0800
Subject: MAINTAINERS: orphan PPP over Ethernet driver

We haven't seen activities from Michal Ostrowski for quite a long time.
The last commit from him is fb64bb560e18 ("PPPoE: Fix flush/close
races."), which was in 2009. Email to mostrows@earthlink.net also
bounces.

Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Link: https://patch.msgid.link/20260401022842.15082-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c3fe46d7c4bc..c6e226ae109d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21075,8 +21075,7 @@ F:	include/uapi/linux/atmppp.h
 F:	net/atm/pppoatm.c
 
 PPP OVER ETHERNET
-M:	Michal Ostrowski <mostrows@earthlink.net>
-S:	Maintained
+S:	Orphan
 F:	drivers/net/ppp/pppoe.c
 F:	drivers/net/ppp/pppox.c
 
-- 
cgit v1.2.3


From e9c9f084cd78a58e2331fbf83c3d5625fb86e33a Mon Sep 17 00:00:00 2001
From: Allison Henderson <achender@kernel.org>
Date: Wed, 1 Apr 2026 17:58:33 -0700
Subject: MAINTAINERS: Update email for Allison Henderson

Switch active email address to kernel.org alias

Signed-off-by: Allison Henderson <achender@kernel.org>
Link: https://patch.msgid.link/20260402005833.38376-1-achender@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c6e226ae109d..4601903a8f9b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22129,7 +22129,7 @@ S:	Supported
 F:	drivers/infiniband/sw/rdmavt
 
 RDS - RELIABLE DATAGRAM SOCKETS
-M:	Allison Henderson <allison.henderson@oracle.com>
+M:	Allison Henderson <achender@kernel.org>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 L:	rds-devel@oss.oracle.com (moderated for non-subscribers)
-- 
cgit v1.2.3


From 6dede3967619b5944003227a5d09fdc21ed57d10 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Wed, 1 Apr 2026 22:12:18 +0100
Subject: net: altera-tse: fix skb leak on DMA mapping error in
 tse_start_xmit()

When dma_map_single() fails in tse_start_xmit(), the function returns
NETDEV_TX_OK without freeing the skb. Since NETDEV_TX_OK tells the
stack the packet was consumed, the skb is never freed, leaking memory
on every DMA mapping failure.

Add dev_kfree_skb_any() before returning to properly free the skb.

Fixes: bbd2190ce96d ("Altera TSE: Add main and header file for Altera Ethernet Driver")
Cc: stable@vger.kernel.org
Signed-off-by: David Carlier <devnexen@gmail.com>
Link: https://patch.msgid.link/20260401211218.279185-1-devnexen@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/altera/altera_tse_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 4342e2d026f8..9eed0be4411e 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -570,6 +570,7 @@ static netdev_tx_t tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				  DMA_TO_DEVICE);
 	if (dma_mapping_error(priv->device, dma_addr)) {
 		netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
+		dev_kfree_skb_any(skb);
 		ret = NETDEV_TX_OK;
 		goto out;
 	}
-- 
cgit v1.2.3


From 51f4e090b9f87b40c21b6daadb5c06e6c0a07b67 Mon Sep 17 00:00:00 2001
From: Tyllis Xu <livelycarpet87@gmail.com>
Date: Tue, 31 Mar 2026 23:47:07 -0500
Subject: net: stmmac: fix integer underflow in chain mode

The jumbo_frm() chain-mode implementation unconditionally computes

    len = nopaged_len - bmax;

where nopaged_len = skb_headlen(skb) (linear bytes only) and bmax is
BUF_SIZE_8KiB or BUF_SIZE_2KiB.  However, the caller stmmac_xmit()
decides to invoke jumbo_frm() based on skb->len (total length including
page fragments):

    is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc);

When a packet has a small linear portion (nopaged_len <= bmax) but a
large total length due to page fragments (skb->len > bmax), the
subtraction wraps as an unsigned integer, producing a huge len value
(~0xFFFFxxxx).  This causes the while (len != 0) loop to execute
hundreds of thousands of iterations, passing skb->data + bmax * i
pointers far beyond the skb buffer to dma_map_single().  On IOMMU-less
SoCs (the typical deployment for stmmac), this maps arbitrary kernel
memory to the DMA engine, constituting a kernel memory disclosure and
potential memory corruption from hardware.

Fix this by introducing a buf_len local variable clamped to
min(nopaged_len, bmax).  Computing len = nopaged_len - buf_len is then
always safe: it is zero when the linear portion fits within a single
descriptor, causing the while (len != 0) loop to be skipped naturally,
and the fragment loop in stmmac_xmit() handles page fragments afterward.

Fixes: 286a83721720 ("stmmac: add CHAINED descriptor mode support (V4)")
Cc: stable@vger.kernel.org
Signed-off-by: Tyllis Xu <LivelyCarpet87@gmail.com>
Link: https://patch.msgid.link/20260401044708.1386919-1-LivelyCarpet87@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/chain_mode.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index 120a009c9992..37f9417c7c0e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -20,7 +20,7 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb,
 	unsigned int nopaged_len = skb_headlen(skb);
 	struct stmmac_priv *priv = tx_q->priv_data;
 	unsigned int entry = tx_q->cur_tx;
-	unsigned int bmax, des2;
+	unsigned int bmax, buf_len, des2;
 	unsigned int i = 1, len;
 	struct dma_desc *desc;
 
@@ -31,17 +31,18 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb,
 	else
 		bmax = BUF_SIZE_2KiB;
 
-	len = nopaged_len - bmax;
+	buf_len = min_t(unsigned int, nopaged_len, bmax);
+	len = nopaged_len - buf_len;
 
 	des2 = dma_map_single(priv->device, skb->data,
-			      bmax, DMA_TO_DEVICE);
+			      buf_len, DMA_TO_DEVICE);
 	desc->des2 = cpu_to_le32(des2);
 	if (dma_mapping_error(priv->device, des2))
 		return -1;
 	tx_q->tx_skbuff_dma[entry].buf = des2;
-	tx_q->tx_skbuff_dma[entry].len = bmax;
+	tx_q->tx_skbuff_dma[entry].len = buf_len;
 	/* do not close the descriptor and do not set own bit */
-	stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
+	stmmac_prepare_tx_desc(priv, desc, 1, buf_len, csum, STMMAC_CHAIN_MODE,
 			0, false, skb->len);
 
 	while (len != 0) {
-- 
cgit v1.2.3


From f2b1cbef153636fa498324b47e822e8b4d1774aa Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Fri, 3 Apr 2026 08:20:16 +0200
Subject: Documentation: minor updates to the security contacts

This clarifies the fact that the bug reporters must use a valid
e-mail address to send their report, and that the security team
assists developers working on a fix but doesn't always produce
fixes on its own.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://patch.msgid.link/20260403062018.31080-2-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index c0cf93e11565..da7937fd59df 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -8,6 +8,10 @@ like to know when a security bug is found so that it can be fixed and
 disclosed as quickly as possible.  Please report security bugs to the
 Linux kernel security team.
 
+Reports are to be sent over e-mail exclusively.  Please use a working e-mail
+address, preferably the same that you want to appear in ``Reported-by`` tags
+if any.  If unsure, send your report to yourself first.
+
 The security team and maintainers almost always require additional
 information beyond what was initially provided in a report and rely on
 active and efficient collaboration with the reporter to perform further
@@ -27,11 +31,9 @@ made public.
 
 The Linux kernel security team can be contacted by email at
 <security@kernel.org>.  This is a private list of security officers
-who will help verify the bug report and develop and release a fix.
-If you already have a fix, please include it with your report, as
-that can speed up the process considerably.  It is possible that the
-security team will bring in extra help from area maintainers to
-understand and fix the security vulnerability.
+who will help verify the bug report and assist developers working on a fix.
+It is possible that the security team will bring in extra help from area
+maintainers to understand and fix the security vulnerability.
 
 Please send **plain text** emails without attachments where possible.
 It is much harder to have a context-quoted discussion about a complex
-- 
cgit v1.2.3


From a72b832a482372001a158c8014d116b053089b5d Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Fri, 3 Apr 2026 08:20:17 +0200
Subject: Documentation: explain how to find maintainers addresses for security
 reports

These days, 80% of the work done by the security team consists in
locating the affected subsystem in a report, running get_maintainers on
it, forwarding the report to these persons and responding to the reporter
with them in Cc. This is a huge and unneeded overhead that we must try to
lower for a better overall efficiency. This patch adds a complete section
explaining how to figure the list of recipients to send the report to.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://patch.msgid.link/20260403062018.31080-3-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 76 +++++++++++++++++++++++++++++++--
 1 file changed, 73 insertions(+), 3 deletions(-)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index da7937fd59df..ac97fc78fecd 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -5,8 +5,75 @@ Security bugs
 
 Linux kernel developers take security very seriously.  As such, we'd
 like to know when a security bug is found so that it can be fixed and
-disclosed as quickly as possible.  Please report security bugs to the
-Linux kernel security team.
+disclosed as quickly as possible.
+
+Identifying contacts
+--------------------
+
+The most effective way to report a security bug is to send it directly to the
+affected subsystem's maintainers and Cc: the Linux kernel security team.  Do
+not send it to a public list at this stage, unless you have good reasons to
+consider the issue as being public or trivial to discover (e.g. result of a
+widely available automated vulnerability scanning tool that can be repeated by
+anyone).
+
+If you're sending a report for issues affecting multiple parts in the kernel,
+even if they're fairly similar issues, please send individual messages (think
+that maintainers will not all work on the issues at the same time). The only
+exception is when an issue concerns closely related parts maintained by the
+exact same subset of maintainers, and these parts are expected to be fixed all
+at once by the same commit, then it may be acceptable to report them at once.
+
+One difficulty for most first-time reporters is to figure the right list of
+recipients to send a report to.  In the Linux kernel, all official maintainers
+are trusted, so the consequences of accidentally including the wrong maintainer
+are essentially a bit more noise for that person, i.e. nothing dramatic.  As
+such, a suitable method to figure the list of maintainers (which kernel
+security officers use) is to rely on the get_maintainers.pl script, tuned to
+only report maintainers.  This script, when passed a file name, will look for
+its path in the MAINTAINERS file to figure a hierarchical list of relevant
+maintainers.  Calling it a first time with the finest level of filtering will
+most of the time return a short list of this specific file's maintainers::
+
+  $ ./scripts/get_maintainer.pl --no-l --no-r --pattern-depth 1 \
+    drivers/example.c
+  Developer One <dev1@example.com> (maintainer:example driver)
+  Developer Two <dev2@example.org> (maintainer:example driver)
+
+These two maintainers should then receive the message.  If the command does not
+return anything, it means the affected file is part of a wider subsystem, so we
+should be less specific::
+
+  $ ./scripts/get_maintainer.pl --no-l --no-r drivers/example.c
+  Developer One <dev1@example.com> (maintainer:example subsystem)
+  Developer Two <dev2@example.org> (maintainer:example subsystem)
+  Developer Three <dev3@example.com> (maintainer:example subsystem [GENERAL])
+  Developer Four <dev4@example.org> (maintainer:example subsystem [GENERAL])
+
+Here, picking the first, most specific ones, is sufficient.  When the list is
+long, it is possible to produce a comma-delimited e-mail address list on a
+single line suitable for use in the To: field of a mailer like this::
+
+  $ ./scripts/get_maintainer.pl --no-tree --no-l --no-r --no-n --m \
+    --no-git-fallback --no-substatus --no-rolestats --no-multiline \
+    --pattern-depth 1 drivers/example.c
+  dev1@example.com, dev2@example.org
+
+or this for the wider list::
+
+  $ ./scripts/get_maintainer.pl --no-tree --no-l --no-r --no-n --m \
+    --no-git-fallback --no-substatus --no-rolestats --no-multiline \
+    drivers/example.c
+  dev1@example.com, dev2@example.org, dev3@example.com, dev4@example.org
+
+If at this point you're still facing difficulties spotting the right
+maintainers, **and only in this case**, it's possible to send your report to
+the Linux kernel security team only.  Your message will be triaged, and you
+will receive instructions about whom to contact, if needed.  Your message may
+equally be forwarded as-is to the relevant maintainers.
+
+Sending the report
+------------------
 
 Reports are to be sent over e-mail exclusively.  Please use a working e-mail
 address, preferably the same that you want to appear in ``Reported-by`` tags
@@ -29,6 +96,7 @@ information is helpful.  Any exploit code is very helpful and will not
 be released without consent from the reporter unless it has already been
 made public.
 
+The report must be sent to maintainers, with the security team in ``Cc:``.
 The Linux kernel security team can be contacted by email at
 <security@kernel.org>.  This is a private list of security officers
 who will help verify the bug report and assist developers working on a fix.
@@ -44,7 +112,9 @@ reproduction steps, and follow it with a proposed fix, all in plain text.
 Markdown, HTML and RST formatted reports are particularly frowned upon since
 they're quite hard to read for humans and encourage to use dedicated viewers,
 sometimes online, which by definition is not acceptable for a confidential
-security report.
+security report. Note that some mailers tend to mangle formatting of plain
+text by default, please consult Documentation/process/email-clients.rst for
+more info.
 
 Disclosure and embargoed information
 ------------------------------------
-- 
cgit v1.2.3


From 496fa1befba1e8ff149af5120cd9c9616bb05120 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Fri, 3 Apr 2026 08:20:18 +0200
Subject: Documentation: clarify the mandatory and desirable info for security
 reports

A significant part of the effort of the security team consists in begging
reporters for patch proposals, or asking them to provide them in regular
format, and most of the time they're willing to provide this, they just
didn't know that it would help. So let's add a section detailing the
required and desirable contents in a security report to help reporters
write more actionable reports which do not require round trips.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://patch.msgid.link/20260403062018.31080-4-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 66 +++++++++++++++++++++++++++++----
 1 file changed, 59 insertions(+), 7 deletions(-)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index ac97fc78fecd..0b1f6d8e3cbe 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -7,6 +7,65 @@ Linux kernel developers take security very seriously.  As such, we'd
 like to know when a security bug is found so that it can be fixed and
 disclosed as quickly as possible.
 
+Preparing your report
+---------------------
+
+Like with any bug report, a security bug report requires a lot of analysis work
+from the developers, so the more information you can share about the issue, the
+better.  Please review the procedure outlined in
+Documentation/admin-guide/reporting-issues.rst if you are unclear about what
+information is helpful.  The following information are absolutely necessary in
+**any** security bug report:
+
+  * **affected kernel version range**: with no version indication, your report
+    will not be processed.  A significant part of reports are for bugs that
+    have already been fixed, so it is extremely important that vulnerabilities
+    are verified on recent versions (development tree or latest stable
+    version), at least by verifying that the code has not changed since the
+    version where it was detected.
+
+  * **description of the problem**: a detailed description of the problem, with
+    traces showing its manifestation, and why you consider that the observed
+    behavior as a problem in the kernel, is necessary.
+
+  * **reproducer**: developers will need to be able to reproduce the problem to
+    consider a fix as effective.  This includes both a way to trigger the issue
+    and a way to confirm it happens.  A reproducer with low complexity
+    dependencies will be needed (source code, shell script, sequence of
+    instructions, file-system image etc).  Binary-only executables are not
+    accepted.  Working exploits are extremely helpful and will not be released
+    without consent from the reporter, unless they are already public.  By
+    definition if an issue cannot be reproduced, it is not exploitable, thus it
+    is not a security bug.
+
+  * **conditions**: if the bug depends on certain configuration options,
+    sysctls, permissions, timing, code modifications etc, these should be
+    indicated.
+
+In addition, the following information are highly desirable:
+
+  * **suspected location of the bug**: the file names and functions where the
+    bug is suspected to be present are very important, at least to help forward
+    the report to the appropriate maintainers.  When not possible (for example,
+    "system freezes each time I run this command"), the security team will help
+    identify the source of the bug.
+
+  * **a proposed fix**: bug reporters who have analyzed the cause of a bug in
+    the source code almost always have an accurate idea on how to fix it,
+    because they spent a long time studying it and its implications.  Proposing
+    a tested fix will save maintainers a lot of time, even if the fix ends up
+    not being the right one, because it helps understand the bug.  When
+    proposing a tested fix, please always format it in a way that can be
+    immediately merged (see Documentation/process/submitting-patches.rst).
+    This will save some back-and-forth exchanges if it is accepted, and you
+    will be credited for finding and fixing this issue.  Note that in this case
+    only a ``Signed-off-by:`` tag is needed, without ``Reported-by:` when the
+    reporter and author are the same.
+
+  * **mitigations**: very often during a bug analysis, some ways of mitigating
+    the issue appear. It is useful to share them, as they can be helpful to
+    keep end users protected during the time it takes them to apply the fix.
+
 Identifying contacts
 --------------------
 
@@ -89,13 +148,6 @@ run additional tests.  Reports where the reporter does not respond promptly
 or cannot effectively discuss their findings may be abandoned if the
 communication does not quickly improve.
 
-As it is with any bug, the more information provided the easier it
-will be to diagnose and fix.  Please review the procedure outlined in
-'Documentation/admin-guide/reporting-issues.rst' if you are unclear about what
-information is helpful.  Any exploit code is very helpful and will not
-be released without consent from the reporter unless it has already been
-made public.
-
 The report must be sent to maintainers, with the security team in ``Cc:``.
 The Linux kernel security team can be contacted by email at
 <security@kernel.org>.  This is a private list of security officers
-- 
cgit v1.2.3


From 7e0ffb72de8aa3b25989c2d980e81b829c577010 Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Fri, 3 Apr 2026 08:57:20 +0200
Subject: sched_ext: Fix stale direct dispatch state in ddsp_dsq_id

@p->scx.ddsp_dsq_id can be left set (non-SCX_DSQ_INVALID) triggering a
spurious warning in mark_direct_dispatch() when the next wakeup's
ops.select_cpu() calls scx_bpf_dsq_insert(), such as:

 WARNING: kernel/sched/ext.c:1273 at scx_dsq_insert_commit+0xcd/0x140

The root cause is that ddsp_dsq_id was only cleared in dispatch_enqueue(),
which is not reached in all paths that consume or cancel a direct dispatch
verdict.

Fix it by clearing it at the right places:

 - direct_dispatch(): cache the direct dispatch state in local variables
   and clear it before dispatch_enqueue() on the synchronous path. For
   the deferred path, the direct dispatch state must remain set until
   process_ddsp_deferred_locals() consumes them.

 - process_ddsp_deferred_locals(): cache the dispatch state in local
   variables and clear it before calling dispatch_to_local_dsq(), which
   may migrate the task to another rq.

 - do_enqueue_task(): clear the dispatch state on the enqueue path
   (local/global/bypass fallbacks), where the direct dispatch verdict is
   ignored.

 - dequeue_task_scx(): clear the dispatch state after dispatch_dequeue()
   to handle both the deferred dispatch cancellation and the holding_cpu
   race, covering all cases where a pending direct dispatch is
   cancelled.

 - scx_disable_task(): clear the direct dispatch state when
   transitioning a task out of the current scheduler. Waking tasks may
   have had the direct dispatch state set by the outgoing scheduler's
   ops.select_cpu() and then been queued on a wake_list via
   ttwu_queue_wakelist(), when SCX_OPS_ALLOW_QUEUED_WAKEUP is set. Such
   tasks are not on the runqueue and are not iterated by scx_bypass(),
   so their direct dispatch state won't be cleared. Without this clear,
   any subsequent SCX scheduler that tries to direct dispatch the task
   will trigger the WARN_ON_ONCE() in mark_direct_dispatch().

Fixes: 5b26f7b920f7 ("sched_ext: Allow SCX_DSQ_LOCAL_ON for direct dispatches")
Cc: stable@vger.kernel.org # v6.12+
Cc: Daniel Hodges <hodgesd@meta.com>
Cc: Patrick Somaru <patsomaru@meta.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 49 +++++++++++++++++++++++++++++++++++--------------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index d5bdcdb3f700..064eaa76be4b 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1109,15 +1109,6 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	dsq_mod_nr(dsq, 1);
 	p->scx.dsq = dsq;
 
-	/*
-	 * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the
-	 * direct dispatch path, but we clear them here because the direct
-	 * dispatch verdict may be overridden on the enqueue path during e.g.
-	 * bypass.
-	 */
-	p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
-	p->scx.ddsp_enq_flags = 0;
-
 	/*
 	 * We're transitioning out of QUEUEING or DISPATCHING. store_release to
 	 * match waiters' load_acquire.
@@ -1283,12 +1274,34 @@ static void mark_direct_dispatch(struct scx_sched *sch,
 	p->scx.ddsp_enq_flags = enq_flags;
 }
 
+/*
+ * Clear @p direct dispatch state when leaving the scheduler.
+ *
+ * Direct dispatch state must be cleared in the following cases:
+ *  - direct_dispatch(): cleared on the synchronous enqueue path, deferred
+ *    dispatch keeps the state until consumed
+ *  - process_ddsp_deferred_locals(): cleared after consuming deferred state,
+ *  - do_enqueue_task(): cleared on enqueue fallbacks where the dispatch
+ *    verdict is ignored (local/global/bypass)
+ *  - dequeue_task_scx(): cleared after dispatch_dequeue(), covering deferred
+ *    cancellation and holding_cpu races
+ *  - scx_disable_task(): cleared for queued wakeup tasks, which are excluded by
+ *    the scx_bypass() loop, so that stale state is not reused by a subsequent
+ *    scheduler instance
+ */
+static inline void clear_direct_dispatch(struct task_struct *p)
+{
+	p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
+	p->scx.ddsp_enq_flags = 0;
+}
+
 static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
 			    u64 enq_flags)
 {
 	struct rq *rq = task_rq(p);
 	struct scx_dispatch_q *dsq =
 		find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
+	u64 ddsp_enq_flags;
 
 	touch_core_sched_dispatch(rq, p);
 
@@ -1329,8 +1342,10 @@ static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
 		return;
 	}
 
-	dispatch_enqueue(sch, dsq, p,
-			 p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
+	ddsp_enq_flags = p->scx.ddsp_enq_flags;
+	clear_direct_dispatch(p);
+
+	dispatch_enqueue(sch, dsq, p, ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
 }
 
 static bool scx_rq_online(struct rq *rq)
@@ -1439,6 +1454,7 @@ enqueue:
 	 */
 	touch_core_sched(rq, p);
 	refill_task_slice_dfl(sch, p);
+	clear_direct_dispatch(p);
 	dispatch_enqueue(sch, dsq, p, enq_flags);
 }
 
@@ -1610,6 +1626,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 	sub_nr_running(rq, 1);
 
 	dispatch_dequeue(rq, p);
+	clear_direct_dispatch(p);
 	return true;
 }
 
@@ -2293,13 +2310,15 @@ static void process_ddsp_deferred_locals(struct rq *rq)
 				struct task_struct, scx.dsq_list.node))) {
 		struct scx_sched *sch = scx_root;
 		struct scx_dispatch_q *dsq;
+		u64 dsq_id = p->scx.ddsp_dsq_id;
+		u64 enq_flags = p->scx.ddsp_enq_flags;
 
 		list_del_init(&p->scx.dsq_list.node);
+		clear_direct_dispatch(p);
 
-		dsq = find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
+		dsq = find_dsq_for_dispatch(sch, rq, dsq_id, p);
 		if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
-			dispatch_to_local_dsq(sch, rq, dsq, p,
-					      p->scx.ddsp_enq_flags);
+			dispatch_to_local_dsq(sch, rq, dsq, p, enq_flags);
 	}
 }
 
@@ -3015,6 +3034,8 @@ static void scx_disable_task(struct task_struct *p)
 	lockdep_assert_rq_held(rq);
 	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
 
+	clear_direct_dispatch(p);
+
 	if (SCX_HAS_OP(sch, disable))
 		SCX_CALL_OP_TASK(sch, SCX_KF_REST, disable, rq, p);
 	scx_set_task_state(p, SCX_TASK_READY);
-- 
cgit v1.2.3


From c842743d073bdd683606cb414eb0ca84465dd834 Mon Sep 17 00:00:00 2001
From: Ruide Cao <caoruide123@gmail.com>
Date: Thu, 2 Apr 2026 22:46:20 +0800
Subject: net: sched: act_csum: validate nested VLAN headers

tcf_csum_act() walks nested VLAN headers directly from skb->data when an
skb still carries in-payload VLAN tags. The current code reads
vlan->h_vlan_encapsulated_proto and then pulls VLAN_HLEN bytes without
first ensuring that the full VLAN header is present in the linear area.

If only part of an inner VLAN header is linearized, accessing
h_vlan_encapsulated_proto reads past the linear area, and the following
skb_pull(VLAN_HLEN) may violate skb invariants.

Fix this by requiring pskb_may_pull(skb, VLAN_HLEN) before accessing and
pulling each nested VLAN header. If the header still is not fully
available, drop the packet through the existing error path.

Fixes: 2ecba2d1e45b ("net: sched: act_csum: Fix csum calc for tagged packets")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Ruide Cao <caoruide123@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/22df2fcb49f410203eafa5d97963dd36089f4ecf.1774892775.git.caoruide123@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/act_csum.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 213e1ce9d2da..a9e4635d899e 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -604,8 +604,12 @@ again:
 			protocol = skb->protocol;
 			orig_vlan_tag_present = true;
 		} else {
-			struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data;
+			struct vlan_hdr *vlan;
 
+			if (!pskb_may_pull(skb, VLAN_HLEN))
+				goto drop;
+
+			vlan = (struct vlan_hdr *)skb->data;
 			protocol = vlan->h_vlan_encapsulated_proto;
 			skb_pull(skb, VLAN_HLEN);
 			skb_reset_network_header(skb);
-- 
cgit v1.2.3


From e16a0d36777b572196de4944aaa196adf828eb8e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 2 Apr 2026 16:10:40 +0200
Subject: net: fec: make FIXED_PHY dependency unconditional

When CONFIG_FIXED_PHY is in a loadable module, the fec driver cannot be
built-in any more:

x86_64-linux-ld: vmlinux.o: in function `fec_enet_mii_probe':
fec_main.c:(.text+0xc4f367): undefined reference to `fixed_phy_unregister'
x86_64-linux-ld: vmlinux.o: in function `fec_enet_close':
fec_main.c:(.text+0xc59591): undefined reference to `fixed_phy_unregister'
x86_64-linux-ld: vmlinux.o: in function `fec_enet_mii_probe.cold':

Select the fixed phy support on all targets to make this build
correctly, not just on coldfire.

Notat that Essentially the stub helpers in include/linux/phy_fixed.h
cannot be used correctly because of this build time dependency,
and we could just remove them to hit the build failure more often
when a driver uses them without the 'select FIXED_PHY'.

Fixes: dc86b621e1b4 ("net: fec: register a fixed phy using fixed_phy_register_100fd if needed")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260402141048.2713445-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index e2a591cf9601..11edbb46a118 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -28,7 +28,7 @@ config FEC
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select CRC32
 	select PHYLIB
-	select FIXED_PHY if M5272
+	select FIXED_PHY
 	select PAGE_POOL
 	imply PAGE_POOL_STATS
 	imply NET_SELFTESTS
-- 
cgit v1.2.3


From b120e4432f9f56c7103133d6a11245e617695adb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Apr 2026 10:35:19 +0000
Subject: net: lapbether: handle NETDEV_PRE_TYPE_CHANGE

lapbeth_data_transmit() expects the underlying device type
to be ARPHRD_ETHER.

Returning NOTIFY_BAD from lapbeth_device_event() makes sure
bonding driver can not break this expectation.

Fixes: 872254dd6b1f ("net/bonding: Enable bonding to enslave non ARPHRD_ETHER")
Reported-by: syzbot+d8c285748fa7292580a9@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69cd22a1.050a0220.70c3a.0002.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Martin Schiller <ms@dev.tdt.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260402103519.1201565-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/wan/lapbether.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index f357a7ac70ac..9861c99ea56c 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -446,33 +446,36 @@ static void lapbeth_free_device(struct lapbethdev *lapbeth)
 static int lapbeth_device_event(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
-	struct lapbethdev *lapbeth;
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct lapbethdev *lapbeth;
 
 	if (dev_net(dev) != &init_net)
 		return NOTIFY_DONE;
 
-	if (!dev_is_ethdev(dev) && !lapbeth_get_x25_dev(dev))
+	lapbeth = lapbeth_get_x25_dev(dev);
+	if (!dev_is_ethdev(dev) && !lapbeth)
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_UP:
 		/* New ethernet device -> new LAPB interface	 */
-		if (!lapbeth_get_x25_dev(dev))
+		if (!lapbeth)
 			lapbeth_new_device(dev);
 		break;
 	case NETDEV_GOING_DOWN:
 		/* ethernet device closes -> close LAPB interface */
-		lapbeth = lapbeth_get_x25_dev(dev);
 		if (lapbeth)
 			dev_close(lapbeth->axdev);
 		break;
 	case NETDEV_UNREGISTER:
 		/* ethernet device disappears -> remove LAPB interface */
-		lapbeth = lapbeth_get_x25_dev(dev);
 		if (lapbeth)
 			lapbeth_free_device(lapbeth);
 		break;
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Our underlying device type must not change. */
+		if (lapbeth)
+			return NOTIFY_BAD;
 	}
 
 	return NOTIFY_DONE;
-- 
cgit v1.2.3


From 285fa6b1e03cff78ead0383e1b259c44b95faf90 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 2 Apr 2026 14:57:10 +0200
Subject: net: airoha: Fix memory leak in airoha_qdma_rx_process()

If an error occurs on the subsequents buffers belonging to the
non-linear part of the skb (e.g. due to an error in the payload length
reported by the NIC or if we consumed all the available fragments for
the skb), the page_pool fragment will not be linked to the skb so it will
not return to the pool in the airoha_qdma_rx_process() error path. Fix the
memory leak partially reverting commit 'd6d2b0e1538d ("net: airoha: Fix
page recycling in airoha_qdma_rx_process()")' and always running
page_pool_put_full_page routine in the airoha_qdma_rx_process() error
path.

Fixes: d6d2b0e1538d ("net: airoha: Fix page recycling in airoha_qdma_rx_process()")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260402-airoha_qdma_rx_process-mem-leak-fix-v1-1-b5706f402d3c@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 95ba99b89428..91cb63a32d99 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -697,9 +697,8 @@ free_frag:
 		if (q->skb) {
 			dev_kfree_skb(q->skb);
 			q->skb = NULL;
-		} else {
-			page_pool_put_full_page(q->page_pool, page, true);
 		}
+		page_pool_put_full_page(q->page_pool, page, true);
 	}
 	airoha_qdma_fill_rx_queue(q);
 
-- 
cgit v1.2.3


From 4e65a8b8daa18d63255ec58964dd192c7fdd9f8b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 2 Apr 2026 10:17:32 +0000
Subject: ipv6: ioam: fix potential NULL dereferences in
 __ioam6_fill_trace_data()

We need to check __in6_dev_get() for possible NULL value, as
suggested by Yiming Qian.

Also add skb_dst_dev_rcu() instead of skb_dst_dev(),
and two missing READ_ONCE().

Note that @dev can't be NULL.

Fixes: 9ee11f0fff20 ("ipv6: ioam: Data plane support for Pre-allocated Trace")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Justin Iurman <justin.iurman@gmail.com>
Link: https://patch.msgid.link/20260402101732.1188059-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ioam6.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c
index 3978773bec42..05a0b7d7e2aa 100644
--- a/net/ipv6/ioam6.c
+++ b/net/ipv6/ioam6.c
@@ -710,7 +710,9 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 				    struct ioam6_schema *sc,
 				    unsigned int sclen, bool is_input)
 {
-	struct net_device *dev = skb_dst_dev(skb);
+	/* Note: skb_dst_dev_rcu() can't be NULL at this point. */
+	struct net_device *dev = skb_dst_dev_rcu(skb);
+	struct inet6_dev *i_skb_dev, *idev;
 	struct timespec64 ts;
 	ktime_t tstamp;
 	u64 raw64;
@@ -721,13 +723,16 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 
 	data = trace->data + trace->remlen * 4 - trace->nodelen * 4 - sclen * 4;
 
+	i_skb_dev = skb->dev ? __in6_dev_get(skb->dev) : NULL;
+	idev = __in6_dev_get(dev);
+
 	/* hop_lim and node_id */
 	if (trace->type.bit0) {
 		byte = ipv6_hdr(skb)->hop_limit;
 		if (is_input)
 			byte--;
 
-		raw32 = dev_net(dev)->ipv6.sysctl.ioam6_id;
+		raw32 = READ_ONCE(dev_net(dev)->ipv6.sysctl.ioam6_id);
 
 		*(__be32 *)data = cpu_to_be32((byte << 24) | raw32);
 		data += sizeof(__be32);
@@ -735,18 +740,18 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 
 	/* ingress_if_id and egress_if_id */
 	if (trace->type.bit1) {
-		if (!skb->dev)
+		if (!i_skb_dev)
 			raw16 = IOAM6_U16_UNAVAILABLE;
 		else
-			raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id);
+			raw16 = (__force u16)READ_ONCE(i_skb_dev->cnf.ioam6_id);
 
 		*(__be16 *)data = cpu_to_be16(raw16);
 		data += sizeof(__be16);
 
-		if (dev->flags & IFF_LOOPBACK)
+		if ((dev->flags & IFF_LOOPBACK) || !idev)
 			raw16 = IOAM6_U16_UNAVAILABLE;
 		else
-			raw16 = (__force u16)READ_ONCE(__in6_dev_get(dev)->cnf.ioam6_id);
+			raw16 = (__force u16)READ_ONCE(idev->cnf.ioam6_id);
 
 		*(__be16 *)data = cpu_to_be16(raw16);
 		data += sizeof(__be16);
@@ -822,7 +827,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 		if (is_input)
 			byte--;
 
-		raw64 = dev_net(dev)->ipv6.sysctl.ioam6_id_wide;
+		raw64 = READ_ONCE(dev_net(dev)->ipv6.sysctl.ioam6_id_wide);
 
 		*(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64);
 		data += sizeof(__be64);
@@ -830,18 +835,18 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 
 	/* ingress_if_id and egress_if_id (wide) */
 	if (trace->type.bit9) {
-		if (!skb->dev)
+		if (!i_skb_dev)
 			raw32 = IOAM6_U32_UNAVAILABLE;
 		else
-			raw32 = READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id_wide);
+			raw32 = READ_ONCE(i_skb_dev->cnf.ioam6_id_wide);
 
 		*(__be32 *)data = cpu_to_be32(raw32);
 		data += sizeof(__be32);
 
-		if (dev->flags & IFF_LOOPBACK)
+		if ((dev->flags & IFF_LOOPBACK) || !idev)
 			raw32 = IOAM6_U32_UNAVAILABLE;
 		else
-			raw32 = READ_ONCE(__in6_dev_get(dev)->cnf.ioam6_id_wide);
+			raw32 = READ_ONCE(idev->cnf.ioam6_id_wide);
 
 		*(__be32 *)data = cpu_to_be32(raw32);
 		data += sizeof(__be32);
-- 
cgit v1.2.3


From 1979645e1842cb7017525a61a0e0e0beb924d02a Mon Sep 17 00:00:00 2001
From: Zijing Yin <yzjaurora@gmail.com>
Date: Thu, 2 Apr 2026 07:01:53 -0700
Subject: bridge: guard local VLAN-0 FDB helpers against NULL vlan group

When CONFIG_BRIDGE_VLAN_FILTERING is not set, br_vlan_group() and
nbp_vlan_group() return NULL (br_private.h stub definitions). The
BR_BOOLOPT_FDB_LOCAL_VLAN_0 toggle code is compiled unconditionally and
reaches br_fdb_delete_locals_per_vlan_port() and
br_fdb_insert_locals_per_vlan_port(), where the NULL vlan group pointer
is dereferenced via list_for_each_entry(v, &vg->vlan_list, vlist).

The observed crash is in the delete path, triggered when creating a
bridge with IFLA_BR_MULTI_BOOLOPT containing BR_BOOLOPT_FDB_LOCAL_VLAN_0
via RTM_NEWLINK. The insert helper has the same bug pattern.

  Oops: general protection fault, probably for non-canonical address 0xdffffc0000000056: 0000 [#1] KASAN NOPTI
  KASAN: null-ptr-deref in range [0x00000000000002b0-0x00000000000002b7]
  RIP: 0010:br_fdb_delete_locals_per_vlan+0x2b9/0x310
  Call Trace:
   br_fdb_toggle_local_vlan_0+0x452/0x4c0
   br_toggle_fdb_local_vlan_0+0x31/0x80 net/bridge/br.c:276
   br_boolopt_toggle net/bridge/br.c:313
   br_boolopt_multi_toggle net/bridge/br.c:364
   br_changelink net/bridge/br_netlink.c:1542
   br_dev_newlink net/bridge/br_netlink.c:1575

Add NULL checks for the vlan group pointer in both helpers, returning
early when there are no VLANs to iterate. This matches the existing
pattern used by other bridge FDB functions such as br_fdb_add() and
br_fdb_delete().

Fixes: 21446c06b441 ("net: bridge: Introduce UAPI for BR_BOOLOPT_FDB_LOCAL_VLAN_0")
Signed-off-by: Zijing Yin <yzjaurora@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402140153.3925663-1-yzjaurora@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_fdb.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 0501ffcb8a3d..e2c17f620f00 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -597,6 +597,9 @@ static void br_fdb_delete_locals_per_vlan_port(struct net_bridge *br,
 		dev = br->dev;
 	}
 
+	if (!vg)
+		return;
+
 	list_for_each_entry(v, &vg->vlan_list, vlist)
 		br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid);
 }
@@ -630,6 +633,9 @@ static int br_fdb_insert_locals_per_vlan_port(struct net_bridge *br,
 		dev = br->dev;
 	}
 
+	if (!vg)
+		return 0;
+
 	list_for_each_entry(v, &vg->vlan_list, vlist) {
 		if (!br_vlan_should_use(v))
 			continue;
-- 
cgit v1.2.3


From 7b735ef81286007794a227ce2539419479c02a5f Mon Sep 17 00:00:00 2001
From: Nikolaos Gkarlis <nickgarlis@gmail.com>
Date: Thu, 2 Apr 2026 20:14:32 +0200
Subject: rtnetlink: add missing netlink_ns_capable() check for peer netns

rtnl_newlink() lacks a CAP_NET_ADMIN capability check on the peer
network namespace when creating paired devices (veth, vxcan,
netkit). This allows an unprivileged user with a user namespace
to create interfaces in arbitrary network namespaces, including
init_net.

Add a netlink_ns_capable() check for CAP_NET_ADMIN in the peer
namespace before allowing device creation to proceed.

Fixes: 81adee47dfb6 ("net: Support specifying the network namespace upon device creation.")
Signed-off-by: Nikolaos Gkarlis <nickgarlis@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260402181432.4126920-1-nickgarlis@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 40 +++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 13 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fae8034efbff..69daba3ddaf0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3894,28 +3894,42 @@ out_unregister:
 	goto out;
 }
 
-static struct net *rtnl_get_peer_net(const struct rtnl_link_ops *ops,
+static struct net *rtnl_get_peer_net(struct sk_buff *skb,
+				     const struct rtnl_link_ops *ops,
 				     struct nlattr *tbp[],
 				     struct nlattr *data[],
 				     struct netlink_ext_ack *extack)
 {
-	struct nlattr *tb[IFLA_MAX + 1];
+	struct nlattr *tb[IFLA_MAX + 1], **attrs;
+	struct net *net;
 	int err;
 
-	if (!data || !data[ops->peer_type])
-		return rtnl_link_get_net_ifla(tbp);
-
-	err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack);
-	if (err < 0)
-		return ERR_PTR(err);
-
-	if (ops->validate) {
-		err = ops->validate(tb, NULL, extack);
+	if (!data || !data[ops->peer_type]) {
+		attrs = tbp;
+	} else {
+		err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack);
 		if (err < 0)
 			return ERR_PTR(err);
+
+		if (ops->validate) {
+			err = ops->validate(tb, NULL, extack);
+			if (err < 0)
+				return ERR_PTR(err);
+		}
+
+		attrs = tb;
 	}
 
-	return rtnl_link_get_net_ifla(tb);
+	net = rtnl_link_get_net_ifla(attrs);
+	if (IS_ERR_OR_NULL(net))
+		return net;
+
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+		put_net(net);
+		return ERR_PTR(-EPERM);
+	}
+
+	return net;
 }
 
 static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4054,7 +4068,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 
 		if (ops->peer_type) {
-			peer_net = rtnl_get_peer_net(ops, tb, data, extack);
+			peer_net = rtnl_get_peer_net(skb, ops, tb, data, extack);
 			if (IS_ERR(peer_net)) {
 				ret = PTR_ERR(peer_net);
 				goto put_ops;
-- 
cgit v1.2.3


From 48a5fe38772b6f039522469ee6131a67838221a8 Mon Sep 17 00:00:00 2001
From: Oleh Konko <security@1seal.org>
Date: Thu, 2 Apr 2026 09:48:57 +0000
Subject: tipc: fix bc_ackers underflow on duplicate GRP_ACK_MSG

The GRP_ACK_MSG handler in tipc_group_proto_rcv() currently decrements
bc_ackers on every inbound group ACK, even when the same member has
already acknowledged the current broadcast round.

Because bc_ackers is a u16, a duplicate ACK received after the last
legitimate ACK wraps the counter to 65535. Once wrapped,
tipc_group_bc_cong() keeps reporting congestion and later group
broadcasts on the affected socket stay blocked until the group is
recreated.

Fix this by ignoring duplicate or stale ACKs before touching bc_acked or
bc_ackers. This makes repeated GRP_ACK_MSG handling idempotent and
prevents the underflow path.

Fixes: 2f487712b893 ("tipc: guarantee that group broadcast doesn't bypass group unicast")
Cc: stable@vger.kernel.org
Signed-off-by: Oleh Konko <security@1seal.org>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/41a4833f368641218e444fdcff822039.security@1seal.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/group.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index e0e6227b433b..14e6732624e2 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -746,6 +746,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
 	u32 port = msg_origport(hdr);
 	struct tipc_member *m, *pm;
 	u16 remitted, in_flight;
+	u16 acked;
 
 	if (!grp)
 		return;
@@ -798,7 +799,10 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
 	case GRP_ACK_MSG:
 		if (!m)
 			return;
-		m->bc_acked = msg_grp_bc_acked(hdr);
+		acked = msg_grp_bc_acked(hdr);
+		if (less_eq(acked, m->bc_acked))
+			return;
+		m->bc_acked = acked;
 		if (--grp->bc_ackers)
 			return;
 		list_del_init(&m->small_win);
-- 
cgit v1.2.3


From b76254c55dc8f23edc089027dd3f8792554c69fb Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Thu, 2 Apr 2026 15:12:07 +0800
Subject: net: qualcomm: qca_uart: report the consumed byte on RX skb
 allocation failure

qca_tty_receive() consumes each input byte before checking whether a
completed frame needs a fresh receive skb. When the current byte completes
a frame, the driver delivers that frame and then allocates a new skb for
the next one.

If that allocation fails, the current code returns i even though data[i]
has already been consumed and may already have completed the delivered
frame. Since serdev interprets the return value as the number of accepted
bytes, this under-reports progress by one byte and can replay the final
byte of the completed frame into a fresh parser state on the next call.

Return i + 1 in that failure path so the accepted-byte count matches the
actual receive-state progress.

Fixes: dfc768fbe618 ("net: qualcomm: add QCA7000 UART driver")
Cc: stable@vger.kernel.org
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260402071207.4036-1-pengpeng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qualcomm/qca_uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index 37efb1ea9fcd..847a5f928e41 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -100,7 +100,7 @@ qca_tty_receive(struct serdev_device *serdev, const u8 *data, size_t count)
 			if (!qca->rx_skb) {
 				netdev_dbg(netdev, "recv: out of RX resources\n");
 				n_stats->rx_errors++;
-				return i;
+				return i + 1;
 			}
 		}
 	}
-- 
cgit v1.2.3


From 06aaf04ca815f7a1f17762fd847b7bc14b8833fb Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Thu, 2 Apr 2026 09:26:12 +0200
Subject: ipv4: nexthop: avoid duplicate NHA_HW_STATS_ENABLE on nexthop group
 dump

Currently NHA_HW_STATS_ENABLE is included twice everytime a dump of
nexthop group is performed with NHA_OP_FLAG_DUMP_STATS. As all the stats
querying were moved to nla_put_nh_group_stats(), leave only that
instance of the attribute querying.

Fixes: 5072ae00aea4 ("net: nexthop: Expose nexthop group HW stats to user space")
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260402072613.25262-1-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index c942f1282236..a0c694583299 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -902,8 +902,7 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 		goto nla_put_failure;
 
 	if (op_flags & NHA_OP_FLAG_DUMP_STATS &&
-	    (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) ||
-	     nla_put_nh_group_stats(skb, nh, op_flags)))
+	    nla_put_nh_group_stats(skb, nh, op_flags))
 		goto nla_put_failure;
 
 	return 0;
-- 
cgit v1.2.3


From 14cf0cd35361f4e94824bf8a42f72713d7702a73 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Thu, 2 Apr 2026 09:26:13 +0200
Subject: ipv4: nexthop: allocate skb dynamically in rtm_get_nexthop()

When querying a nexthop object via RTM_GETNEXTHOP, the kernel currently
allocates a fixed-size skb using NLMSG_GOODSIZE. While sufficient for
single nexthops and small Equal-Cost Multi-Path groups, this fixed
allocation fails for large nexthop groups like 512 nexthops.

This results in the following warning splat:

 WARNING: net/ipv4/nexthop.c:3395 at rtm_get_nexthop+0x176/0x1c0, CPU#20: rep/4608
 [...]
 RIP: 0010:rtm_get_nexthop (net/ipv4/nexthop.c:3395)
 [...]
 Call Trace:
  <TASK>
  rtnetlink_rcv_msg (net/core/rtnetlink.c:6989)
  netlink_rcv_skb (net/netlink/af_netlink.c:2550)
  netlink_unicast (net/netlink/af_netlink.c:1319 net/netlink/af_netlink.c:1344)
  netlink_sendmsg (net/netlink/af_netlink.c:1894)
  ____sys_sendmsg (net/socket.c:721 net/socket.c:736 net/socket.c:2585)
  ___sys_sendmsg (net/socket.c:2641)
  __sys_sendmsg (net/socket.c:2671)
  do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
  entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
  </TASK>

Fix this by allocating the size dynamically using nh_nlmsg_size() and
using nlmsg_new(), this is consistent with nexthop_notify() behavior. In
addition, adjust nh_nlmsg_size_grp() so it calculates the size needed
based on flags passed. While at it, also add the size of NHA_FDB for
nexthop group size calculation as it was missing too.

This cannot be reproduced via iproute2 as the group size is currently
limited and the command fails as follows:

addattr_l ERROR: message exceeded bound of 1048

Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Reported-by: Yiming Qian <yimingqian591@gmail.com>
Closes: https://lore.kernel.org/netdev/CAL_bE8Li2h4KO+AQFXW4S6Yb_u5X4oSKnkywW+LPFjuErhqELA@mail.gmail.com/
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260402072613.25262-2-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/nexthop.c | 38 +++++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index a0c694583299..2c9036c719b6 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1003,16 +1003,32 @@ static size_t nh_nlmsg_size_grp_res(struct nh_group *nhg)
 		nla_total_size_64bit(8);/* NHA_RES_GROUP_UNBALANCED_TIME */
 }
 
-static size_t nh_nlmsg_size_grp(struct nexthop *nh)
+static size_t nh_nlmsg_size_grp(struct nexthop *nh, u32 op_flags)
 {
 	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
 	size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh;
 	size_t tot = nla_total_size(sz) +
-		nla_total_size(2); /* NHA_GROUP_TYPE */
+		nla_total_size(2) +	/* NHA_GROUP_TYPE */
+		nla_total_size(0);	/* NHA_FDB */
 
 	if (nhg->resilient)
 		tot += nh_nlmsg_size_grp_res(nhg);
 
+	if (op_flags & NHA_OP_FLAG_DUMP_STATS) {
+		tot += nla_total_size(0) +	  /* NHA_GROUP_STATS */
+		       nla_total_size(4);	  /* NHA_HW_STATS_ENABLE */
+		tot += nhg->num_nh *
+		       (nla_total_size(0) +	  /* NHA_GROUP_STATS_ENTRY */
+			nla_total_size(4) +	  /* NHA_GROUP_STATS_ENTRY_ID */
+			nla_total_size_64bit(8)); /* NHA_GROUP_STATS_ENTRY_PACKETS */
+
+		if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS) {
+			tot += nhg->num_nh *
+			       nla_total_size_64bit(8); /* NHA_GROUP_STATS_ENTRY_PACKETS_HW */
+			tot += nla_total_size(4);	/* NHA_HW_STATS_USED */
+		}
+	}
+
 	return tot;
 }
 
@@ -1047,14 +1063,14 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh)
 	return sz;
 }
 
-static size_t nh_nlmsg_size(struct nexthop *nh)
+static size_t nh_nlmsg_size(struct nexthop *nh, u32 op_flags)
 {
 	size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg));
 
 	sz += nla_total_size(4); /* NHA_ID */
 
 	if (nh->is_group)
-		sz += nh_nlmsg_size_grp(nh) +
+		sz += nh_nlmsg_size_grp(nh, op_flags) +
 		      nla_total_size(4) +	/* NHA_OP_FLAGS */
 		      0;
 	else
@@ -1070,7 +1086,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any());
+	skb = nlmsg_new(nh_nlmsg_size(nh, 0), gfp_any());
 	if (!skb)
 		goto errout;
 
@@ -3376,15 +3392,15 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
-	err = -ENOBUFS;
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb)
-		goto out;
-
 	err = -ENOENT;
 	nh = nexthop_find_by_id(net, id);
 	if (!nh)
-		goto errout_free;
+		goto out;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(nh_nlmsg_size(nh, op_flags), GFP_KERNEL);
+	if (!skb)
+		goto out;
 
 	err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid,
 			   nlh->nlmsg_seq, 0, op_flags);
-- 
cgit v1.2.3


From fde29fd9349327acc50d19a0b5f3d5a6c964dfd8 Mon Sep 17 00:00:00 2001
From: Yiqi Sun <sunyiqixm@gmail.com>
Date: Thu, 2 Apr 2026 15:04:19 +0800
Subject: ipv4: icmp: fix null-ptr-deref in icmp_build_probe()

ipv6_stub->ipv6_dev_find() may return ERR_PTR(-EAFNOSUPPORT) when the
IPv6 stack is not active (CONFIG_IPV6=m and not loaded), and passing
this error pointer to dev_hold() will cause a kernel crash with
null-ptr-deref.

Instead, silently discard the request. RFC 8335 does not appear to
define a specific response for the case where an IPv6 interface
identifier is syntactically valid but the implementation cannot perform
the lookup at runtime, and silently dropping the request may safer than
misreporting "No Such Interface".

Fixes: d329ea5bd884 ("icmp: add response to RFC 8335 PROBE messages")
Signed-off-by: Yiqi Sun <sunyiqixm@gmail.com>
Link: https://patch.msgid.link/20260402070419.2291578-1-sunyiqixm@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 568bd1e95d44..4e2a6c70dcd8 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1346,6 +1346,13 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
 			if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in6_addr))
 				goto send_mal_query;
 			dev = ipv6_stub->ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev);
+			/*
+			 * If IPv6 identifier lookup is unavailable, silently
+			 * discard the request instead of misreporting NO_IF.
+			 */
+			if (IS_ERR(dev))
+				return false;
+
 			dev_hold(dev);
 			break;
 #endif
-- 
cgit v1.2.3


From 77facb35227c421467cdb49268de433168c2dcef Mon Sep 17 00:00:00 2001
From: Chris J Arges <carges@cloudflare.com>
Date: Thu, 2 Apr 2026 17:23:16 -0500
Subject: net: increase IP_TUNNEL_RECURSION_LIMIT to 5

In configurations with multiple tunnel layers and MPLS lwtunnel routing, a
single tunnel hop can increment the counter beyond this limit. This causes
packets to be dropped with the "Dead loop on virtual device" message even
when a routing loop doesn't exist.

Increase IP_TUNNEL_RECURSION_LIMIT from 4 to 5 to handle this use-case.

Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions")
Link: https://lore.kernel.org/netdev/88deb91b-ef1b-403c-8eeb-0f971f27e34f@redhat.com/
Signed-off-by: Chris J Arges <carges@cloudflare.com>
Link: https://patch.msgid.link/20260402222401.3408368-1-carges@cloudflare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 1f577a4f8ce9..d708b66e55cd 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -32,7 +32,7 @@
  * recursion involves route lookups and full IP output, consuming much
  * more stack per level, so a lower limit is needed.
  */
-#define IP_TUNNEL_RECURSION_LIMIT	4
+#define IP_TUNNEL_RECURSION_LIMIT	5
 
 /* Keep error state on tunnel for 30 sec */
 #define IPTUNNEL_ERR_TIMEO	(30*HZ)
-- 
cgit v1.2.3


From 5c14a19d5b1645cce1cb1252833d70b23635b632 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Thu, 2 Apr 2026 12:21:48 +0800
Subject: nfc: s3fwrn5: allocate rx skb before consuming bytes

s3fwrn82_uart_read() reports the number of accepted bytes to the serdev
core. The current code consumes bytes into recv_skb and may already
deliver a complete frame before allocating a fresh receive buffer.

If that alloc_skb() fails, the callback returns 0 even though it has
already consumed bytes, and it leaves recv_skb as NULL for the next
receive callback. That breaks the receive_buf() accounting contract and
can also lead to a NULL dereference on the next skb_put_u8().

Allocate the receive skb lazily before consuming the next byte instead.
If allocation fails, return the number of bytes already accepted.

Fixes: 3f52c2cb7e3a ("nfc: s3fwrn5: Support a UART interface")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Link: https://patch.msgid.link/20260402042148.65236-1-pengpeng@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/s3fwrn5/uart.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/nfc/s3fwrn5/uart.c b/drivers/nfc/s3fwrn5/uart.c
index 9c09c10c2a46..4ee481bd7e96 100644
--- a/drivers/nfc/s3fwrn5/uart.c
+++ b/drivers/nfc/s3fwrn5/uart.c
@@ -58,6 +58,12 @@ static size_t s3fwrn82_uart_read(struct serdev_device *serdev,
 	size_t i;
 
 	for (i = 0; i < count; i++) {
+		if (!phy->recv_skb) {
+			phy->recv_skb = alloc_skb(NCI_SKB_BUFF_LEN, GFP_KERNEL);
+			if (!phy->recv_skb)
+				return i;
+		}
+
 		skb_put_u8(phy->recv_skb, *data++);
 
 		if (phy->recv_skb->len < S3FWRN82_NCI_HEADER)
@@ -69,9 +75,7 @@ static size_t s3fwrn82_uart_read(struct serdev_device *serdev,
 
 		s3fwrn5_recv_frame(phy->common.ndev, phy->recv_skb,
 				   phy->common.mode);
-		phy->recv_skb = alloc_skb(NCI_SKB_BUFF_LEN, GFP_KERNEL);
-		if (!phy->recv_skb)
-			return 0;
+		phy->recv_skb = NULL;
 	}
 
 	return i;
-- 
cgit v1.2.3


From 1345e9f4e3f3bc7d8a0a2138ae29e205a857a555 Mon Sep 17 00:00:00 2001
From: Jon Hunter <jonathanh@nvidia.com>
Date: Wed, 1 Apr 2026 11:29:39 +0100
Subject: net: stmmac: Fix PTP ref clock for Tegra234

Since commit 030ce919e114 ("net: stmmac: make sure that ptp_rate is not
0 before configuring timestamping") was added the following error is
observed on Tegra234:

 ERR KERN tegra-mgbe 6800000.ethernet eth0: Invalid PTP clock rate
 WARNING KERN tegra-mgbe 6800000.ethernet eth0: PTP init failed

It turns out that the Tegra234 device-tree binding defines the PTP ref
clock name as 'ptp-ref' and not 'ptp_ref' and the above commit now
exposes this and that the PTP clock is not configured correctly.

In order to update device-tree to use the correct 'ptp_ref' name, update
the Tegra MGBE driver to use 'ptp_ref' by default and fallback to using
'ptp-ref' if this clock name is present.

Fixes: d8ca113724e7 ("net: stmmac: tegra: Add MGBE support")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260401102941.17466-2-jonathanh@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
index d765acbe3754..21a0a11fc011 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c
@@ -9,7 +9,7 @@
 #include "stmmac_platform.h"
 
 static const char *const mgbe_clks[] = {
-	"rx-pcs", "tx", "tx-pcs", "mac-divider", "mac", "mgbe", "ptp-ref", "mac"
+	"rx-pcs", "tx", "tx-pcs", "mac-divider", "mac", "mgbe", "ptp_ref", "mac"
 };
 
 struct tegra_mgbe {
@@ -215,6 +215,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_resources res;
+	bool use_legacy_ptp = false;
 	struct tegra_mgbe *mgbe;
 	int irq, err, i;
 	u32 value;
@@ -257,9 +258,23 @@ static int tegra_mgbe_probe(struct platform_device *pdev)
 	if (!mgbe->clks)
 		return -ENOMEM;
 
-	for (i = 0; i <  ARRAY_SIZE(mgbe_clks); i++)
+	/* Older device-trees use 'ptp-ref' rather than 'ptp_ref'.
+	 * Fall back when the legacy name is present.
+	 */
+	if (of_property_match_string(pdev->dev.of_node, "clock-names",
+				     "ptp-ref") >= 0)
+		use_legacy_ptp = true;
+
+	for (i = 0; i < ARRAY_SIZE(mgbe_clks); i++) {
 		mgbe->clks[i].id = mgbe_clks[i];
 
+		if (use_legacy_ptp && !strcmp(mgbe_clks[i], "ptp_ref")) {
+			dev_warn(mgbe->dev,
+				 "Device-tree update needed for PTP clock!\n");
+			mgbe->clks[i].id = "ptp-ref";
+		}
+	}
+
 	err = devm_clk_bulk_get(mgbe->dev, ARRAY_SIZE(mgbe_clks), mgbe->clks);
 	if (err < 0)
 		return err;
-- 
cgit v1.2.3


From fb22b1fc5bca3c0aad95388933497ceb30f1fb26 Mon Sep 17 00:00:00 2001
From: Jon Hunter <jonathanh@nvidia.com>
Date: Wed, 1 Apr 2026 11:29:40 +0100
Subject: dt-bindings: net: Fix Tegra234 MGBE PTP clock

The PTP clock for the Tegra234 MGBE device is incorrectly named
'ptp-ref' and should be 'ptp_ref'. This is causing the following
warning to be observed on Tegra234 platforms that use this device:

 ERR KERN tegra-mgbe 6800000.ethernet eth0: Invalid PTP clock rate
 WARNING KERN tegra-mgbe 6800000.ethernet eth0: PTP init failed

Although this constitutes an ABI breakage in the binding for this
device, PTP support has clearly never worked and so fix this now
so we can correct the device-tree for this device. Note that the
MGBE driver still supports the legacy 'ptp-ref' clock name and so
older/existing device-trees will still work, but given that this
is not the correct name, there is no point to advertise this in the
binding.

Fixes: 189c2e5c7669 ("dt-bindings: net: Add Tegra234 MGBE")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260401102941.17466-3-jonathanh@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/nvidia,tegra234-mgbe.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/nvidia,tegra234-mgbe.yaml b/Documentation/devicetree/bindings/net/nvidia,tegra234-mgbe.yaml
index 2bd3efff2485..215f14d1897d 100644
--- a/Documentation/devicetree/bindings/net/nvidia,tegra234-mgbe.yaml
+++ b/Documentation/devicetree/bindings/net/nvidia,tegra234-mgbe.yaml
@@ -42,7 +42,7 @@ properties:
       - const: mgbe
       - const: mac
       - const: mac-divider
-      - const: ptp-ref
+      - const: ptp_ref
       - const: rx-input-m
       - const: rx-input
       - const: tx
@@ -133,7 +133,7 @@ examples:
                  <&bpmp TEGRA234_CLK_MGBE0_RX_PCS_M>,
                  <&bpmp TEGRA234_CLK_MGBE0_RX_PCS>,
                  <&bpmp TEGRA234_CLK_MGBE0_TX_PCS>;
-        clock-names = "mgbe", "mac", "mac-divider", "ptp-ref", "rx-input-m",
+        clock-names = "mgbe", "mac", "mac-divider", "ptp_ref", "rx-input-m",
                       "rx-input", "tx", "eee-pcs", "rx-pcs-input", "rx-pcs-m",
                       "rx-pcs", "tx-pcs";
         resets = <&bpmp TEGRA234_RESET_MGBE0_MAC>,
-- 
cgit v1.2.3


From b6422dff0e518245019233432b6bccfc30b73e2f Mon Sep 17 00:00:00 2001
From: Sahil Chandna <sahilchandna@linux.microsoft.com>
Date: Fri, 3 Apr 2026 05:09:29 -0700
Subject: PCI: hv: Fix double ida_free in hv_pci_probe error path

If hv_pci_probe() fails after storing the domain number in
hbus->bridge->domain_nr, there is a call to free this domain_nr via
pci_bus_release_emul_domain_nr(), however, during cleanup, the bridge
release callback pci_release_host_bridge_dev() also frees the domain_nr
causing ida_free to be called on same ID twice and triggering following
warning:

  ida_free called for id=28971 which is not allocated.
  WARNING: lib/idr.c:594 at ida_free+0xdf/0x160, CPU#0: kworker/0:2/198
  Call Trace:
   pci_bus_release_emul_domain_nr+0x17/0x20
   pci_release_host_bridge_dev+0x4b/0x60
   device_release+0x3b/0xa0
   kobject_put+0x8e/0x220
   devm_pci_alloc_host_bridge_release+0xe/0x20
   devres_release_all+0x9a/0xd0
   device_unbind_cleanup+0x12/0xa0
   really_probe+0x1c5/0x3f0
   vmbus_add_channel_work+0x135/0x1a0

Fix this by letting pci core handle the free domain_nr and remove
the explicit free called in pci-hyperv driver.

Fixes: bcce8c74f1ce ("PCI: Enable host bridge emulation for PCI_DOMAINS_GENERIC platforms")
Signed-off-by: Sahil Chandna <sahilchandna@linux.microsoft.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/pci/controller/pci-hyperv.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 38a790f642a1..49c0a2d51162 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -3786,7 +3786,7 @@ static int hv_pci_probe(struct hv_device *hdev,
 					   hbus->bridge->domain_nr);
 	if (!hbus->wq) {
 		ret = -ENOMEM;
-		goto free_dom;
+		goto free_bus;
 	}
 
 	hdev->channel->next_request_id_callback = vmbus_next_request_id;
@@ -3882,8 +3882,6 @@ close:
 	vmbus_close(hdev->channel);
 destroy_wq:
 	destroy_workqueue(hbus->wq);
-free_dom:
-	pci_bus_release_emul_domain_nr(hbus->bridge->domain_nr);
 free_bus:
 	kfree(hbus);
 	return ret;
-- 
cgit v1.2.3


From 16cbec24897624051b324aa3a85859c38ca65fde Mon Sep 17 00:00:00 2001
From: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Date: Tue, 24 Mar 2026 23:57:40 +0000
Subject: mshv: Fix infinite fault loop on permission-denied GPA intercepts

Prevent infinite fault loops when guests access memory regions without
proper permissions. Currently, mshv_handle_gpa_intercept() attempts to
remap pages for all faults on movable memory regions, regardless of
whether the access type is permitted. When a guest writes to a read-only
region, the remap succeeds but the region remains read-only, causing
immediate re-fault and spinning the vCPU indefinitely.

Validate intercept access type against region permissions before
attempting remaps. Reject writes to non-writable regions and executes to
non-executable regions early, returning false to let the VMM handle the
intercept appropriately.

This also closes a potential DoS vector where malicious guests could
intentionally trigger these fault loops to consume host resources.

Fixes: b9a66cd5ccbb ("mshv: Add support for movable memory regions")
Signed-off-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Reviewed-by: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/mshv_root_main.c | 15 ++++++++++++---
 include/hyperv/hvgdk_mini.h |  6 ++++++
 include/hyperv/hvhdk.h      |  4 ++--
 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 6f42423f7faa..c8e5523a52b6 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -630,7 +630,7 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp)
 {
 	struct mshv_partition *p = vp->vp_partition;
 	struct mshv_mem_region *region;
-	bool ret;
+	bool ret = false;
 	u64 gfn;
 #if defined(CONFIG_X86_64)
 	struct hv_x64_memory_intercept_message *msg =
@@ -641,6 +641,8 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp)
 		(struct hv_arm64_memory_intercept_message *)
 		vp->vp_intercept_msg_page->u.payload;
 #endif
+	enum hv_intercept_access_type access_type =
+		msg->header.intercept_access_type;
 
 	gfn = HVPFN_DOWN(msg->guest_physical_address);
 
@@ -648,12 +650,19 @@ static bool mshv_handle_gpa_intercept(struct mshv_vp *vp)
 	if (!region)
 		return false;
 
+	if (access_type == HV_INTERCEPT_ACCESS_WRITE &&
+	    !(region->hv_map_flags & HV_MAP_GPA_WRITABLE))
+		goto put_region;
+
+	if (access_type == HV_INTERCEPT_ACCESS_EXECUTE &&
+	    !(region->hv_map_flags & HV_MAP_GPA_EXECUTABLE))
+		goto put_region;
+
 	/* Only movable memory ranges are supported for GPA intercepts */
 	if (region->mreg_type == MSHV_REGION_TYPE_MEM_MOVABLE)
 		ret = mshv_region_handle_gfn_fault(region, gfn);
-	else
-		ret = false;
 
+put_region:
 	mshv_region_put(region);
 
 	return ret;
diff --git a/include/hyperv/hvgdk_mini.h b/include/hyperv/hvgdk_mini.h
index 1823a290a7b7..f9600f87186a 100644
--- a/include/hyperv/hvgdk_mini.h
+++ b/include/hyperv/hvgdk_mini.h
@@ -1533,4 +1533,10 @@ struct hv_mmio_write_input {
 	u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH];
 } __packed;
 
+enum hv_intercept_access_type {
+	HV_INTERCEPT_ACCESS_READ	= 0,
+	HV_INTERCEPT_ACCESS_WRITE	= 1,
+	HV_INTERCEPT_ACCESS_EXECUTE	= 2
+};
+
 #endif /* _HV_HVGDK_MINI_H */
diff --git a/include/hyperv/hvhdk.h b/include/hyperv/hvhdk.h
index 245f3db53bf1..5e83d3714966 100644
--- a/include/hyperv/hvhdk.h
+++ b/include/hyperv/hvhdk.h
@@ -779,7 +779,7 @@ struct hv_x64_intercept_message_header {
 	u32 vp_index;
 	u8 instruction_length:4;
 	u8 cr8:4; /* Only set for exo partitions */
-	u8 intercept_access_type;
+	u8 intercept_access_type; /* enum hv_intercept_access_type */
 	union hv_x64_vp_execution_state execution_state;
 	struct hv_x64_segment_register cs_segment;
 	u64 rip;
@@ -825,7 +825,7 @@ union hv_arm64_vp_execution_state {
 struct hv_arm64_intercept_message_header {
 	u32 vp_index;
 	u8 instruction_length;
-	u8 intercept_access_type;
+	u8 intercept_access_type; /* enum hv_intercept_access_type */
 	union hv_arm64_vp_execution_state execution_state;
 	u64 pc;
 	u64 cpsr;
-- 
cgit v1.2.3


From e2b0ae529db4766584e77647cefe3ec15c3d842e Mon Sep 17 00:00:00 2001
From: Zoltan Illes <zoliviragh@gmail.com>
Date: Fri, 3 Apr 2026 22:03:42 -0700
Subject: Input: xpad - add support for Razer Wolverine V3 Pro

Add device IDs for the Razer Wolverine V3 Pro controller in both
wired (0x0a57) and wireless 2.4 GHz dongle (0x0a59) modes.

The controller uses the Xbox 360 protocol (vendor-specific class,
subclass 93, protocol 1) on interface 0 with an identical 20-byte
input report layout, so no additional processing is needed.

Signed-off-by: Zoltan Illes <zoliviragh@gmail.com>
Link: https://patch.msgid.link/20260329220031.1325509-1-137647604+ZlordHUN@users.noreply.github.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 363d50949386..655226fe493d 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -313,6 +313,8 @@ static const struct xpad_device {
 	{ 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
 	{ 0x1532, 0x0a29, "Razer Wolverine V2", 0, XTYPE_XBOXONE },
+	{ 0x1532, 0x0a57, "Razer Wolverine V3 Pro (Wired)", 0, XTYPE_XBOX360 },
+	{ 0x1532, 0x0a59, "Razer Wolverine V3 Pro (2.4 GHz Dongle)", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
 	{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
-- 
cgit v1.2.3


From 0d9363a764d9d601a05591f9695cea8b429e9be3 Mon Sep 17 00:00:00 2001
From: Shengyu Qu <wiagn233@outlook.com>
Date: Fri, 3 Apr 2026 22:07:28 -0700
Subject: Input: xpad - add support for BETOP BTP-KP50B/C controller's wireless
 mode

BETOP's BTP-KP50B and BTP-KP50C controller's wireless dongles are both
working as standard Xbox 360 controllers. Add USB device IDs for them to
xpad driver.

Signed-off-by: Shengyu Qu <wiagn233@outlook.com>
Link: https://patch.msgid.link/TY4PR01MB14432B4B298EA186E5F86C46B9855A@TY4PR01MB14432.jpnprd01.prod.outlook.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 655226fe493d..627e8950e451 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -362,6 +362,8 @@ static const struct xpad_device {
 	{ 0x1bad, 0xfd00, "Razer Onza TE", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0xfd01, "Razer Onza", 0, XTYPE_XBOX360 },
 	{ 0x1ee9, 0x1590, "ZOTAC Gaming Zone", 0, XTYPE_XBOX360 },
+	{ 0x20bc, 0x5134, "BETOP BTP-KP50B Xinput Dongle", 0, XTYPE_XBOX360 },
+	{ 0x20bc, 0x514a, "BETOP BTP-KP50C Xinput Dongle", 0, XTYPE_XBOX360 },
 	{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x2064, "PowerA Wired Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE },
@@ -564,6 +566,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1a86),		/* Nanjing Qinheng Microelectronics (WCH) */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x1ee9),		/* ZOTAC Technology Limited */
+	XPAD_XBOX360_VENDOR(0x20bc),		/* BETOP wireless dongles */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOXONE_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOX360_VENDOR(0x2345),		/* Machenike Controllers */
-- 
cgit v1.2.3


From f387e2e2b9d302688dbdceebe9aade221c90f09e Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Sat, 4 Apr 2026 10:20:33 +0200
Subject: Documentation: fix two typos in latest update to the security report
 howto

In previous patch "Documentation: clarify the mandatory and desirable
info for security reports" I left two typos that I didn't detect in local
checks. One is "get_maintainers.pl" (no 's' in the script name), and the
other one is a missing closing quote after "Reported-by", which didn't
have effect here but I don't know if it can break rendering elsewhere
(e.g. on the public HTML page). Better fix it before it gets merged.

Signed-off-by: Willy Tarreau <w@1wt.eu>
Link: https://patch.msgid.link/20260404082033.5160-1-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 0b1f6d8e3cbe..27b028e85861 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -59,7 +59,7 @@ In addition, the following information are highly desirable:
     immediately merged (see Documentation/process/submitting-patches.rst).
     This will save some back-and-forth exchanges if it is accepted, and you
     will be credited for finding and fixing this issue.  Note that in this case
-    only a ``Signed-off-by:`` tag is needed, without ``Reported-by:` when the
+    only a ``Signed-off-by:`` tag is needed, without ``Reported-by:`` when the
     reporter and author are the same.
 
   * **mitigations**: very often during a bug analysis, some ways of mitigating
@@ -88,7 +88,7 @@ recipients to send a report to.  In the Linux kernel, all official maintainers
 are trusted, so the consequences of accidentally including the wrong maintainer
 are essentially a bit more noise for that person, i.e. nothing dramatic.  As
 such, a suitable method to figure the list of maintainers (which kernel
-security officers use) is to rely on the get_maintainers.pl script, tuned to
+security officers use) is to rely on the get_maintainer.pl script, tuned to
 only report maintainers.  This script, when passed a file name, will look for
 its path in the MAINTAINERS file to figure a hierarchical list of relevant
 maintainers.  Calling it a first time with the finest level of filtering will
-- 
cgit v1.2.3


From 834911eb8eef2501485d819b4eabebadc25c3497 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Mon, 23 Mar 2026 17:43:47 -0600
Subject: riscv: kgdb: fix several debug register assignment bugs

Fix several bugs in the RISC-V kgdb implementation:

- The element of dbg_reg_def[] that is supposed to pertain to the S1
  register embeds instead the struct pt_regs offset of the A1
  register.  Fix this to use the S1 register offset in struct pt_regs.

- The sleeping_thread_to_gdb_regs() function copies the value of the
  S10 register into the gdb_regs[] array element meant for the S9
  register, and copies the value of the S11 register into the array
  element meant for the S10 register.  It also neglects to copy the
  value of the S11 register.  Fix all of these issues.

Fixes: fe89bd2be8667 ("riscv: Add KGDB support")
Cc: Vincent Chen <vincent.chen@sifive.com>
Link: https://patch.msgid.link/fde376f8-bcfd-bfe4-e467-07d8f7608d05@kernel.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/kgdb.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index 15fec5d1e6de..0bf629204c76 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -175,7 +175,7 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
 	{DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)},
 	{DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)},
 	{DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)},
-	{DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
+	{DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, s1)},
 	{DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)},
 	{DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)},
 	{DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)},
@@ -244,8 +244,9 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 	gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6];
 	gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7];
 	gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8];
-	gdb_regs[DBG_REG_S9_OFF] = task->thread.s[10];
-	gdb_regs[DBG_REG_S10_OFF] = task->thread.s[11];
+	gdb_regs[DBG_REG_S9_OFF] = task->thread.s[9];
+	gdb_regs[DBG_REG_S10_OFF] = task->thread.s[10];
+	gdb_regs[DBG_REG_S11_OFF] = task->thread.s[11];
 	gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra;
 }
 
-- 
cgit v1.2.3


From 6b60a128c2f43180664a614830f3c529497e0394 Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Mon, 23 Mar 2026 17:43:47 -0600
Subject: riscv: patch: Avoid early phys_to_page()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similarly to commit 8d09e2d569f6 ("arm64: patching: avoid early
page_to_phys()"), avoid using phys_to_page() for the kernel address case
in patch_map().

Since this is called from apply_boot_alternatives() in setup_arch(), and
commit 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE
memory model") has moved sparse_init() to after setup_arch(),
phys_to_page() is not available there yet, and it panics on boot with
SPARSEMEM on RV32, which does not use SPARSEMEM_VMEMMAP.

Reported-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Closes: https://lore.kernel.org/r/20260223144108-dcace0b9-02e8-4b67-a7ce-f263bed36f26@linutronix.de/
Fixes: 4267739cabb8 ("arch, mm: consolidate initialization of SPARSE memory model")
Suggested-by: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Link: https://patch.msgid.link/20260310-riscv-sparsemem-alternatives-fix-v1-1-659d5dd257e2@iscas.ac.cn
[pjw@kernel.org: fix the subject line to align with the patch description]
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/patch.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index db13c9ddf9e3..16b243376f36 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -42,19 +42,20 @@ static inline bool is_kernel_exittext(uintptr_t addr)
 static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 {
 	uintptr_t uintaddr = (uintptr_t) addr;
-	struct page *page;
+	phys_addr_t phys;
 
-	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
-		page = phys_to_page(__pa_symbol(addr));
-	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
-		page = vmalloc_to_page(addr);
-	else
-		return addr;
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) {
+		phys = __pa_symbol(addr);
+	} else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) {
+		struct page *page = vmalloc_to_page(addr);
 
-	BUG_ON(!page);
+		BUG_ON(!page);
+		phys = page_to_phys(page) + offset_in_page(addr);
+	} else {
+		return addr;
+	}
 
-	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
-					 offset_in_page(addr));
+	return (void *)set_fixmap_offset(fixmap, phys);
 }
 
 static void patch_unmap(int fixmap)
-- 
cgit v1.2.3


From 57f0253bc1538446ee46a4550fe85d91235fb678 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Sat, 21 Feb 2026 10:37:31 +0800
Subject: riscv: make runtime const not usable by modules

Similar as commit 284922f4c563 ("x86: uaccess: don't use runtime-const
rewriting in modules") does, make riscv's runtime const not usable by
modules too, to "make sure this doesn't get forgotten the next time
somebody wants to do runtime constant optimizations". The reason is
well explained in the above commit: "The runtime-const infrastructure
was never designed to handle the modular case, because the constant
fixup is only done at boot time for core kernel code."

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://patch.msgid.link/20260221023731.3476-1-jszhang@kernel.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/runtime-const.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
index d766e2b9e6df..900db0a103d0 100644
--- a/arch/riscv/include/asm/runtime-const.h
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_RISCV_RUNTIME_CONST_H
 #define _ASM_RISCV_RUNTIME_CONST_H
 
+#ifdef MODULE
+  #error "Cannot use runtime-const infrastructure from modules"
+#endif
+
 #include <asm/asm.h>
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
-- 
cgit v1.2.3


From 3033b2b1e3949274f33a140e2a97571b5a307298 Mon Sep 17 00:00:00 2001
From: Zishun Yi <vulab@iscas.ac.cn>
Date: Mon, 23 Mar 2026 00:00:22 +0800
Subject: riscv: Reset pmm when PR_TAGGED_ADDR_ENABLE is not set

In set_tagged_addr_ctrl(), when PR_TAGGED_ADDR_ENABLE is not set, pmlen
is correctly set to 0, but it forgets to reset pmm. This results in the
CPU pmm state not corresponding to the software pmlen state.

Fix this by resetting pmm along with pmlen.

Fixes: 2e1743085887 ("riscv: Add support for the tagged address ABI")
Signed-off-by: Zishun Yi <vulab@iscas.ac.cn>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Link: https://patch.msgid.link/20260322160022.21908-1-vulab@iscas.ac.cn
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/process.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index aacb23978f93..5957effab57c 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -347,8 +347,10 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
 	if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen))
 		return -EINVAL;
 
-	if (!(arg & PR_TAGGED_ADDR_ENABLE))
+	if (!(arg & PR_TAGGED_ADDR_ENABLE)) {
 		pmlen = PMLEN_0;
+		pmm = ENVCFG_PMM_PMLEN_0;
+	}
 
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
-- 
cgit v1.2.3


From 87ad7cc9aa7f0a202189640c5015aa985e7e8f3b Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Thu, 2 Apr 2026 17:18:03 -0600
Subject: riscv: use _BITUL macro rather than BIT() in ptrace uapi and
 kselftests

Fix the build of non-kernel code that includes the RISC-V ptrace uapi
header, and the RISC-V validate_v_ptrace.c kselftest, by using the
_BITUL() macro rather than BIT().  BIT() is not available outside
the kernel.

Based on patches and comments from Charlie Jenkins, Michael Neuling,
and Andreas Schwab.

Fixes: 30eb191c895b ("selftests: riscv: verify ptrace rejects invalid vector csr inputs")
Fixes: 2af7c9cf021c ("riscv/ptrace: expose riscv CFI status and state via ptrace and in core files")
Cc: Andreas Schwab <schwab@suse.de>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Charlie Jenkins <thecharlesjenkins@gmail.com>
Link: https://patch.msgid.link/20260330024248.449292-1-mikey@neuling.org
Link: https://lore.kernel.org/linux-riscv/20260309-fix_selftests-v2-1-9d5a553a531e@gmail.com/
Link: https://lore.kernel.org/linux-riscv/20260309-fix_selftests-v2-3-9d5a553a531e@gmail.com/
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/uapi/asm/ptrace.h                     | 13 +++++++------
 tools/testing/selftests/riscv/vector/validate_v_ptrace.c |  4 ++--
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 18988a5f1a63..70a74adad914 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -9,6 +9,7 @@
 #ifndef __ASSEMBLER__
 
 #include <linux/types.h>
+#include <linux/const.h>
 
 #define PTRACE_GETFDPIC		33
 
@@ -138,12 +139,12 @@ struct __sc_riscv_cfi_state {
 #define PTRACE_CFI_SS_LOCK_BIT	4
 #define PTRACE_CFI_SS_PTR_BIT	5
 
-#define PTRACE_CFI_LP_EN_STATE		BIT(PTRACE_CFI_LP_EN_BIT)
-#define PTRACE_CFI_LP_LOCK_STATE	BIT(PTRACE_CFI_LP_LOCK_BIT)
-#define PTRACE_CFI_ELP_STATE		BIT(PTRACE_CFI_ELP_BIT)
-#define PTRACE_CFI_SS_EN_STATE		BIT(PTRACE_CFI_SS_EN_BIT)
-#define PTRACE_CFI_SS_LOCK_STATE	BIT(PTRACE_CFI_SS_LOCK_BIT)
-#define PTRACE_CFI_SS_PTR_STATE		BIT(PTRACE_CFI_SS_PTR_BIT)
+#define PTRACE_CFI_LP_EN_STATE		_BITUL(PTRACE_CFI_LP_EN_BIT)
+#define PTRACE_CFI_LP_LOCK_STATE	_BITUL(PTRACE_CFI_LP_LOCK_BIT)
+#define PTRACE_CFI_ELP_STATE		_BITUL(PTRACE_CFI_ELP_BIT)
+#define PTRACE_CFI_SS_EN_STATE		_BITUL(PTRACE_CFI_SS_EN_BIT)
+#define PTRACE_CFI_SS_LOCK_STATE	_BITUL(PTRACE_CFI_SS_LOCK_BIT)
+#define PTRACE_CFI_SS_PTR_STATE		_BITUL(PTRACE_CFI_SS_PTR_BIT)
 
 #define PRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_LP_EN_STATE | \
 					  PTRACE_CFI_LP_LOCK_STATE | \
diff --git a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
index 3589549f7228..7ae6fede496f 100644
--- a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
+++ b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
@@ -346,8 +346,8 @@ FIXTURE_TEARDOWN(v_csr_invalid)
 {
 }
 
-#define VECTOR_1_0		BIT(0)
-#define XTHEAD_VECTOR_0_7	BIT(1)
+#define VECTOR_1_0		_BITUL(0)
+#define XTHEAD_VECTOR_0_7	_BITUL(1)
 
 #define vector_test(x)		((x) & VECTOR_1_0)
 #define xthead_test(x)		((x) & XTHEAD_VECTOR_0_7)
-- 
cgit v1.2.3


From 511361fe7a8856e2f415010942808c237a1b8061 Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <thecharlesjenkins@gmail.com>
Date: Mon, 9 Mar 2026 18:52:11 -0700
Subject: selftests: riscv: Add braces around EXPECT_EQ()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

EXPECT_EQ() expands to multiple lines, breaking up one-line if
statements. This issue was not present in the patch on the mailing list
but was instead introduced by the maintainer when attempting to fix up
checkpatch warnings. Add braces around EXPECT_EQ() to avoid the error
even though checkpatch suggests them to be removed:

validate_v_ptrace.c:626:17: error: ‘else’ without a previous ‘if’

Fixes: 3789d5eecd5a ("selftests: riscv: verify syscalls discard vector context")
Fixes: 30eb191c895b ("selftests: riscv: verify ptrace rejects invalid vector csr inputs")
Fixes: 849f05ae1ea6 ("selftests: riscv: verify ptrace accepts valid vector csr values")
Signed-off-by: Charlie Jenkins <thecharlesjenkins@gmail.com>
Reviewed-and-tested-by: Sergey Matyukevich <geomatsi@gmail.com>
Link: https://patch.msgid.link/20260309-fix_selftests-v2-2-9d5a553a531e@gmail.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 tools/testing/selftests/riscv/vector/validate_v_ptrace.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
index 7ae6fede496f..74b6f6bcf067 100644
--- a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
+++ b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c
@@ -290,10 +290,11 @@ TEST(ptrace_v_syscall_clobbering)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
@@ -619,10 +620,11 @@ TEST_F(v_csr_invalid, ptrace_v_invalid_values)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
@@ -827,10 +829,11 @@ TEST_F(v_csr_valid, ptrace_v_valid_values)
 
 		/* verify initial vsetvli settings */
 
-		if (is_xtheadvector_supported())
+		if (is_xtheadvector_supported()) {
 			EXPECT_EQ(5UL, regset_data->vtype);
-		else
+		} else {
 			EXPECT_EQ(9UL, regset_data->vtype);
+		}
 
 		EXPECT_EQ(regset_data->vlenb, regset_data->vl);
 		EXPECT_EQ(vlenb, regset_data->vlenb);
-- 
cgit v1.2.3


From 9156585280f161fc1c3552cf1860559edb2bb7e3 Mon Sep 17 00:00:00 2001
From: Sunil V L <sunilvl@oss.qualcomm.com>
Date: Tue, 3 Mar 2026 11:46:05 +0530
Subject: ACPI: RIMT: Add dependency between iommu and devices

EPROBE_DEFER ensures IOMMU devices are probed before the devices that
depend on them. During shutdown, however, the IOMMU may be removed
first, leading to issues. To avoid this, a device link is added
which enforces the correct removal order.

Fixes: 8f7729552582 ("ACPI: RISC-V: Add support for RIMT")
Signed-off-by: Sunil V L <sunilvl@oss.qualcomm.com>
Link: https://patch.msgid.link/20260303061605.722949-1-sunilvl@oss.qualcomm.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 drivers/acpi/riscv/rimt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/riscv/rimt.c b/drivers/acpi/riscv/rimt.c
index 229c4a0d47a3..906282b0e63c 100644
--- a/drivers/acpi/riscv/rimt.c
+++ b/drivers/acpi/riscv/rimt.c
@@ -263,6 +263,13 @@ static int rimt_iommu_xlate(struct device *dev, struct acpi_rimt_node *node, u32
 	if (!rimt_fwnode)
 		return -EPROBE_DEFER;
 
+	/*
+	 * EPROBE_DEFER ensures IOMMU is probed before the devices that
+	 * depend on them. During shutdown, however, the IOMMU may be removed
+	 * first, leading to issues. To avoid this, a device link is added
+	 * which enforces the correct removal order.
+	 */
+	device_link_add(dev, rimt_fwnode->dev, DL_FLAG_AUTOREMOVE_CONSUMER);
 	return acpi_iommu_fwspec_init(dev, deviceid, rimt_fwnode);
 }
 
-- 
cgit v1.2.3


From a621d9cdc8d08bd2fe8dfe6fa6897d256de8248f Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Sat, 4 Apr 2026 18:40:57 -0600
Subject: riscv: ptrace: cfi: fix "PRACE" typo in uapi header

A CFI-related macro defined in arch/riscv/uapi/asm/ptrace.h misspells
"PTRACE" as "PRACE"; fix this.

Fixes: 2af7c9cf021c ("riscv/ptrace: expose riscv CFI status and state via ptrace and in core files")
Cc: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/uapi/asm/ptrace.h | 2 +-
 arch/riscv/kernel/ptrace.c           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 70a74adad914..69d71443e111 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -146,7 +146,7 @@ struct __sc_riscv_cfi_state {
 #define PTRACE_CFI_SS_LOCK_STATE	_BITUL(PTRACE_CFI_SS_LOCK_BIT)
 #define PTRACE_CFI_SS_PTR_STATE		_BITUL(PTRACE_CFI_SS_PTR_BIT)
 
-#define PRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_LP_EN_STATE | \
+#define PTRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_LP_EN_STATE | \
 					  PTRACE_CFI_LP_LOCK_STATE | \
 					  PTRACE_CFI_ELP_STATE | \
 					  PTRACE_CFI_SS_EN_STATE | \
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index e592bd6b7665..2704a532e916 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -351,7 +351,7 @@ static int riscv_cfi_set(struct task_struct *target,
 	if ((user_cfi.cfi_status.cfi_state &
 	     (PTRACE_CFI_LP_EN_STATE | PTRACE_CFI_LP_LOCK_STATE |
 	      PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) ||
-	     (user_cfi.cfi_status.cfi_state & PRACE_CFI_STATE_INVALID_MASK))
+	     (user_cfi.cfi_status.cfi_state & PTRACE_CFI_STATE_INVALID_MASK))
 		return -EINVAL;
 
 	/* If lpad is enabled on target and ptrace requests to set / clear elp, do that */
-- 
cgit v1.2.3


From a6ede084c4b7cd6ecd0d31d5292336e556901bd7 Mon Sep 17 00:00:00 2001
From: Zong Li <zong.li@sifive.com>
Date: Sat, 4 Apr 2026 18:40:58 -0600
Subject: riscv: cfi: clear CFI lock status in start_thread()

When libc locks the CFI status through the following prctl:
 - PR_LOCK_SHADOW_STACK_STATUS
 - PR_LOCK_INDIR_BR_LP_STATUS

A newly execd address space will inherit the lock status
if it does not clear the lock bits. Since the lock bits
remain set, libc will later fail to enable the landing
pad and shadow stack.

Signed-off-by: Zong Li <zong.li@sifive.com>
Link: https://patch.msgid.link/20260323065640.4045713-1-zong.li@sifive.com
[pjw@kernel.org: ensure we unlock before changing state; cleaned up subject line]
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/usercfi.h |  8 ++++----
 arch/riscv/kernel/process.c      |  2 ++
 arch/riscv/kernel/usercfi.c      | 12 ++++++------
 3 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h
index 7495baae1e3c..f56966edbf5c 100644
--- a/arch/riscv/include/asm/usercfi.h
+++ b/arch/riscv/include/asm/usercfi.h
@@ -39,7 +39,7 @@ void set_active_shstk(struct task_struct *task, unsigned long shstk_addr);
 bool is_shstk_enabled(struct task_struct *task);
 bool is_shstk_locked(struct task_struct *task);
 bool is_shstk_allocated(struct task_struct *task);
-void set_shstk_lock(struct task_struct *task);
+void set_shstk_lock(struct task_struct *task, bool lock);
 void set_shstk_status(struct task_struct *task, bool enable);
 unsigned long get_active_shstk(struct task_struct *task);
 int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr);
@@ -47,7 +47,7 @@ int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr);
 bool is_indir_lp_enabled(struct task_struct *task);
 bool is_indir_lp_locked(struct task_struct *task);
 void set_indir_lp_status(struct task_struct *task, bool enable);
-void set_indir_lp_lock(struct task_struct *task);
+void set_indir_lp_lock(struct task_struct *task, bool lock);
 
 #define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE)
 
@@ -69,7 +69,7 @@ void set_indir_lp_lock(struct task_struct *task);
 
 #define is_shstk_allocated(task) false
 
-#define set_shstk_lock(task) do {} while (0)
+#define set_shstk_lock(task, lock) do {} while (0)
 
 #define set_shstk_status(task, enable) do {} while (0)
 
@@ -79,7 +79,7 @@ void set_indir_lp_lock(struct task_struct *task);
 
 #define set_indir_lp_status(task, enable) do {} while (0)
 
-#define set_indir_lp_lock(task) do {} while (0)
+#define set_indir_lp_lock(task, lock) do {} while (0)
 
 #define restore_user_shstk(tsk, shstk_ptr) -EINVAL
 
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 5957effab57c..b2df7f72241a 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -160,6 +160,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 	 * clear shadow stack state on exec.
 	 * libc will set it later via prctl.
 	 */
+	set_shstk_lock(current, false);
 	set_shstk_status(current, false);
 	set_shstk_base(current, 0, 0);
 	set_active_shstk(current, 0);
@@ -167,6 +168,7 @@ void start_thread(struct pt_regs *regs, unsigned long pc,
 	 * disable indirect branch tracking on exec.
 	 * libc will enable it later via prctl.
 	 */
+	set_indir_lp_lock(current, false);
 	set_indir_lp_status(current, false);
 
 #ifdef CONFIG_64BIT
diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c
index 1adba746f164..9052171c1a8c 100644
--- a/arch/riscv/kernel/usercfi.c
+++ b/arch/riscv/kernel/usercfi.c
@@ -74,9 +74,9 @@ void set_shstk_status(struct task_struct *task, bool enable)
 	csr_write(CSR_ENVCFG, task->thread.envcfg);
 }
 
-void set_shstk_lock(struct task_struct *task)
+void set_shstk_lock(struct task_struct *task, bool lock)
 {
-	task->thread_info.user_cfi_state.ubcfi_locked = 1;
+	task->thread_info.user_cfi_state.ubcfi_locked = lock;
 }
 
 bool is_indir_lp_enabled(struct task_struct *task)
@@ -104,9 +104,9 @@ void set_indir_lp_status(struct task_struct *task, bool enable)
 	csr_write(CSR_ENVCFG, task->thread.envcfg);
 }
 
-void set_indir_lp_lock(struct task_struct *task)
+void set_indir_lp_lock(struct task_struct *task, bool lock)
 {
-	task->thread_info.user_cfi_state.ufcfi_locked = 1;
+	task->thread_info.user_cfi_state.ufcfi_locked = lock;
 }
 /*
  * If size is 0, then to be compatible with regular stack we want it to be as big as
@@ -452,7 +452,7 @@ int arch_lock_shadow_stack_status(struct task_struct *task,
 	    !is_shstk_enabled(task) || arg != 0)
 		return -EINVAL;
 
-	set_shstk_lock(task);
+	set_shstk_lock(task, true);
 
 	return 0;
 }
@@ -502,7 +502,7 @@ int arch_lock_indir_br_lp_status(struct task_struct *task,
 	    !is_indir_lp_enabled(task) || arg != 0)
 		return -EINVAL;
 
-	set_indir_lp_lock(task);
+	set_indir_lp_lock(task, true);
 
 	return 0;
 }
-- 
cgit v1.2.3


From ac4e61c730d778f8d8b8455da052952dbf8e0317 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Sat, 4 Apr 2026 18:40:58 -0600
Subject: riscv: ptrace: expand "LP" references to "branch landing pads" in
 uapi headers

Per Linus' comments about the unreadability of abbreviations such as
"LP", rename the RISC-V ptrace landing pad CFI macro names to be more
explicit.  This primarily involves expanding "LP" in the names to some
variant of "branch landing pad."

Link: https://lore.kernel.org/linux-riscv/CAHk-=whhSLGZAx3N5jJpb4GLFDqH_QvS07D+6BnkPWmCEzTAgw@mail.gmail.com/
Cc: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/uapi/asm/ptrace.h         | 20 +++++++++++---------
 arch/riscv/kernel/ptrace.c                   | 10 +++++-----
 tools/testing/selftests/riscv/cfi/cfitests.c |  5 +++--
 3 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 69d71443e111..9985bd58148e 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -132,23 +132,25 @@ struct __sc_riscv_cfi_state {
 	unsigned long ss_ptr;   /* shadow stack pointer */
 };
 
-#define PTRACE_CFI_LP_EN_BIT	0
-#define PTRACE_CFI_LP_LOCK_BIT	1
-#define PTRACE_CFI_ELP_BIT	2
+#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT		0
+#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT		1
+#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT	2
 #define PTRACE_CFI_SS_EN_BIT	3
 #define PTRACE_CFI_SS_LOCK_BIT	4
 #define PTRACE_CFI_SS_PTR_BIT	5
 
-#define PTRACE_CFI_LP_EN_STATE		_BITUL(PTRACE_CFI_LP_EN_BIT)
-#define PTRACE_CFI_LP_LOCK_STATE	_BITUL(PTRACE_CFI_LP_LOCK_BIT)
-#define PTRACE_CFI_ELP_STATE		_BITUL(PTRACE_CFI_ELP_BIT)
+#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE		_BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT)
+#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE	\
+	_BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT)
+#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE	\
+	_BITUL(PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT)
 #define PTRACE_CFI_SS_EN_STATE		_BITUL(PTRACE_CFI_SS_EN_BIT)
 #define PTRACE_CFI_SS_LOCK_STATE	_BITUL(PTRACE_CFI_SS_LOCK_BIT)
 #define PTRACE_CFI_SS_PTR_STATE		_BITUL(PTRACE_CFI_SS_PTR_BIT)
 
-#define PTRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_LP_EN_STATE | \
-					  PTRACE_CFI_LP_LOCK_STATE | \
-					  PTRACE_CFI_ELP_STATE | \
+#define PTRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | \
+					  PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | \
+					  PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE | \
 					  PTRACE_CFI_SS_EN_STATE | \
 					  PTRACE_CFI_SS_LOCK_STATE | \
 					  PTRACE_CFI_SS_PTR_STATE)
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2704a532e916..b6156625d6f8 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -303,11 +303,11 @@ static int riscv_cfi_get(struct task_struct *target,
 	regs = task_pt_regs(target);
 
 	if (is_indir_lp_enabled(target)) {
-		user_cfi.cfi_status.cfi_state |= PTRACE_CFI_LP_EN_STATE;
+		user_cfi.cfi_status.cfi_state |= PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE;
 		user_cfi.cfi_status.cfi_state |= is_indir_lp_locked(target) ?
-						 PTRACE_CFI_LP_LOCK_STATE : 0;
+						 PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE : 0;
 		user_cfi.cfi_status.cfi_state |= (regs->status & SR_ELP) ?
-						PTRACE_CFI_ELP_STATE : 0;
+						PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE : 0;
 	}
 
 	if (is_shstk_enabled(target)) {
@@ -349,7 +349,7 @@ static int riscv_cfi_set(struct task_struct *target,
 	 * rsvd field should be set to zero so that if those fields are needed in future
 	 */
 	if ((user_cfi.cfi_status.cfi_state &
-	     (PTRACE_CFI_LP_EN_STATE | PTRACE_CFI_LP_LOCK_STATE |
+	     (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE |
 	      PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) ||
 	     (user_cfi.cfi_status.cfi_state & PTRACE_CFI_STATE_INVALID_MASK))
 		return -EINVAL;
@@ -357,7 +357,7 @@ static int riscv_cfi_set(struct task_struct *target,
 	/* If lpad is enabled on target and ptrace requests to set / clear elp, do that */
 	if (is_indir_lp_enabled(target)) {
 		if (user_cfi.cfi_status.cfi_state &
-		    PTRACE_CFI_ELP_STATE) /* set elp state */
+		    PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE) /* set elp state */
 			regs->status |= SR_ELP;
 		else
 			regs->status &= ~SR_ELP; /* clear elp state */
diff --git a/tools/testing/selftests/riscv/cfi/cfitests.c b/tools/testing/selftests/riscv/cfi/cfitests.c
index 298544854415..68374a27ec81 100644
--- a/tools/testing/selftests/riscv/cfi/cfitests.c
+++ b/tools/testing/selftests/riscv/cfi/cfitests.c
@@ -94,7 +94,7 @@ bool cfi_ptrace_test(void)
 		}
 
 		switch (ptrace_test_num) {
-#define CFI_ENABLE_MASK (PTRACE_CFI_LP_EN_STATE |	\
+#define CFI_ENABLE_MASK (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE |	\
 			 PTRACE_CFI_SS_EN_STATE |	\
 			 PTRACE_CFI_SS_PTR_STATE)
 		case 0:
@@ -106,7 +106,8 @@ bool cfi_ptrace_test(void)
 						   __func__);
 			break;
 		case 1:
-			if (!(cfi_reg.cfi_status.cfi_state & PTRACE_CFI_ELP_STATE))
+			if (!(cfi_reg.cfi_status.cfi_state &
+			      PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE))
 				ksft_exit_fail_msg("%s: elp must have been set\n", __func__);
 			/* clear elp state. not interested in anything else */
 			cfi_reg.cfi_status.cfi_state = 0;
-- 
cgit v1.2.3


From adfc80dd0d7831335b5105fb3d8747094bf42878 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Sat, 4 Apr 2026 18:40:58 -0600
Subject: prctl: rename branch landing pad implementation functions to be more
 explicit

Per Linus' comments about the unreadability of abbreviations such as
"indir_br_lp", rename the three prctl() implementation functions to be more
explicit.  This involves renaming "indir_br_lp_status" in the function
names to "branch_landing_pad_state".

While here, add _prctl_ into the function names, following the
speculation control prctl implementation functions.

Link: https://lore.kernel.org/linux-riscv/CAHk-=whhSLGZAx3N5jJpb4GLFDqH_QvS07D+6BnkPWmCEzTAgw@mail.gmail.com/
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/usercfi.c | 16 ++++++++--------
 include/linux/cpu.h         |  6 +++---
 kernel/sys.c                | 15 ++++++++-------
 3 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c
index 9052171c1a8c..04ab1eb8df29 100644
--- a/arch/riscv/kernel/usercfi.c
+++ b/arch/riscv/kernel/usercfi.c
@@ -457,7 +457,8 @@ int arch_lock_shadow_stack_status(struct task_struct *task,
 	return 0;
 }
 
-int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status)
+int arch_prctl_get_branch_landing_pad_state(struct task_struct *t,
+					    unsigned long __user *state)
 {
 	unsigned long fcfi_status = 0;
 
@@ -467,10 +468,10 @@ int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *sta
 	/* indirect branch tracking is enabled on the task or not */
 	fcfi_status |= (is_indir_lp_enabled(t) ? PR_INDIR_BR_LP_ENABLE : 0);
 
-	return copy_to_user(status, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0;
+	return copy_to_user(state, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0;
 }
 
-int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status)
+int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state)
 {
 	bool enable_indir_lp = false;
 
@@ -482,24 +483,23 @@ int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status)
 		return -EINVAL;
 
 	/* Reject unknown flags */
-	if (status & ~PR_INDIR_BR_LP_ENABLE)
+	if (state & ~PR_INDIR_BR_LP_ENABLE)
 		return -EINVAL;
 
-	enable_indir_lp = (status & PR_INDIR_BR_LP_ENABLE);
+	enable_indir_lp = (state & PR_INDIR_BR_LP_ENABLE);
 	set_indir_lp_status(t, enable_indir_lp);
 
 	return 0;
 }
 
-int arch_lock_indir_br_lp_status(struct task_struct *task,
-				 unsigned long arg)
+int arch_prctl_lock_branch_landing_pad_state(struct task_struct *task)
 {
 	/*
 	 * If indirect branch tracking is not supported or not enabled on task,
 	 * nothing to lock here
 	 */
 	if (!is_user_lpad_enabled() ||
-	    !is_indir_lp_enabled(task) || arg != 0)
+	    !is_indir_lp_enabled(task))
 		return -EINVAL;
 
 	set_indir_lp_lock(task, true);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8239cd95a005..9b6b0d87fdb0 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -229,8 +229,8 @@ static inline bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v)
 #define smt_mitigations SMT_MITIGATIONS_OFF
 #endif
 
-int arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status);
-int arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status);
-int arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status);
+int arch_prctl_get_branch_landing_pad_state(struct task_struct *t, unsigned long __user *state);
+int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state);
+int arch_prctl_lock_branch_landing_pad_state(struct task_struct *t);
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/sys.c b/kernel/sys.c
index c86eba9aa7e9..a5e0c187bbbf 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2388,17 +2388,18 @@ int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long st
 	return -EINVAL;
 }
 
-int __weak arch_get_indir_br_lp_status(struct task_struct *t, unsigned long __user *status)
+int __weak arch_prctl_get_branch_landing_pad_state(struct task_struct *t,
+						   unsigned long __user *state)
 {
 	return -EINVAL;
 }
 
-int __weak arch_set_indir_br_lp_status(struct task_struct *t, unsigned long status)
+int __weak arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state)
 {
 	return -EINVAL;
 }
 
-int __weak arch_lock_indir_br_lp_status(struct task_struct *t, unsigned long status)
+int __weak arch_prctl_lock_branch_landing_pad_state(struct task_struct *t)
 {
 	return -EINVAL;
 }
@@ -2891,17 +2892,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_INDIR_BR_LP_STATUS:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = arch_get_indir_br_lp_status(me, (unsigned long __user *)arg2);
+		error = arch_prctl_get_branch_landing_pad_state(me, (unsigned long __user *)arg2);
 		break;
 	case PR_SET_INDIR_BR_LP_STATUS:
 		if (arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = arch_set_indir_br_lp_status(me, arg2);
+		error = arch_prctl_set_branch_landing_pad_state(me, arg2);
 		break;
 	case PR_LOCK_INDIR_BR_LP_STATUS:
-		if (arg3 || arg4 || arg5)
+		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		error = arch_lock_indir_br_lp_status(me, arg2);
+		error = arch_prctl_lock_branch_landing_pad_state(me);
 		break;
 	default:
 		trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
-- 
cgit v1.2.3


From e5342fe2c1bb5b4fab6ed531a0122c6417e57ecf Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Sat, 4 Apr 2026 18:40:58 -0600
Subject: riscv: ptrace: cfi: expand "SS" references to "shadow stack" in uapi
 headers

Similar to the recent change to expand "LP" to "branch landing pad",
let's expand "SS" in the ptrace uapi macros to "shadow stack" as well.
This aligns with the existing prctl() arguments, which use the
expanded "shadow stack" names, rather than just the abbreviation.

Link: https://lore.kernel.org/linux-riscv/CAHk-=whhSLGZAx3N5jJpb4GLFDqH_QvS07D+6BnkPWmCEzTAgw@mail.gmail.com/
Cc: Deepak Gupta <debug@rivosinc.com>
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/uapi/asm/ptrace.h         | 18 +++++++++---------
 arch/riscv/kernel/ptrace.c                   | 10 +++++-----
 tools/testing/selftests/riscv/cfi/cfitests.c |  4 ++--
 3 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h
index 9985bd58148e..3de2b7124aff 100644
--- a/arch/riscv/include/uapi/asm/ptrace.h
+++ b/arch/riscv/include/uapi/asm/ptrace.h
@@ -135,25 +135,25 @@ struct __sc_riscv_cfi_state {
 #define PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT		0
 #define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT		1
 #define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT	2
-#define PTRACE_CFI_SS_EN_BIT	3
-#define PTRACE_CFI_SS_LOCK_BIT	4
-#define PTRACE_CFI_SS_PTR_BIT	5
+#define PTRACE_CFI_SHADOW_STACK_EN_BIT			3
+#define PTRACE_CFI_SHADOW_STACK_LOCK_BIT		4
+#define PTRACE_CFI_SHADOW_STACK_PTR_BIT			5
 
 #define PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE		_BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT)
 #define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE	\
 	_BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT)
 #define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE	\
 	_BITUL(PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT)
-#define PTRACE_CFI_SS_EN_STATE		_BITUL(PTRACE_CFI_SS_EN_BIT)
-#define PTRACE_CFI_SS_LOCK_STATE	_BITUL(PTRACE_CFI_SS_LOCK_BIT)
-#define PTRACE_CFI_SS_PTR_STATE		_BITUL(PTRACE_CFI_SS_PTR_BIT)
+#define PTRACE_CFI_SHADOW_STACK_EN_STATE		_BITUL(PTRACE_CFI_SHADOW_STACK_EN_BIT)
+#define PTRACE_CFI_SHADOW_STACK_LOCK_STATE		_BITUL(PTRACE_CFI_SHADOW_STACK_LOCK_BIT)
+#define PTRACE_CFI_SHADOW_STACK_PTR_STATE		_BITUL(PTRACE_CFI_SHADOW_STACK_PTR_BIT)
 
 #define PTRACE_CFI_STATE_INVALID_MASK	~(PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | \
 					  PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | \
 					  PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE | \
-					  PTRACE_CFI_SS_EN_STATE | \
-					  PTRACE_CFI_SS_LOCK_STATE | \
-					  PTRACE_CFI_SS_PTR_STATE)
+					  PTRACE_CFI_SHADOW_STACK_EN_STATE | \
+					  PTRACE_CFI_SHADOW_STACK_LOCK_STATE | \
+					  PTRACE_CFI_SHADOW_STACK_PTR_STATE)
 
 struct __cfi_status {
 	__u64 cfi_state;
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index b6156625d6f8..93de2e7a3074 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -311,10 +311,10 @@ static int riscv_cfi_get(struct task_struct *target,
 	}
 
 	if (is_shstk_enabled(target)) {
-		user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SS_EN_STATE |
-						  PTRACE_CFI_SS_PTR_STATE);
+		user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SHADOW_STACK_EN_STATE |
+						  PTRACE_CFI_SHADOW_STACK_PTR_STATE);
 		user_cfi.cfi_status.cfi_state |= is_shstk_locked(target) ?
-						 PTRACE_CFI_SS_LOCK_STATE : 0;
+						 PTRACE_CFI_SHADOW_STACK_LOCK_STATE : 0;
 		user_cfi.shstk_ptr = get_active_shstk(target);
 	}
 
@@ -350,7 +350,7 @@ static int riscv_cfi_set(struct task_struct *target,
 	 */
 	if ((user_cfi.cfi_status.cfi_state &
 	     (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE |
-	      PTRACE_CFI_SS_EN_STATE | PTRACE_CFI_SS_LOCK_STATE)) ||
+	      PTRACE_CFI_SHADOW_STACK_EN_STATE | PTRACE_CFI_SHADOW_STACK_LOCK_STATE)) ||
 	     (user_cfi.cfi_status.cfi_state & PTRACE_CFI_STATE_INVALID_MASK))
 		return -EINVAL;
 
@@ -365,7 +365,7 @@ static int riscv_cfi_set(struct task_struct *target,
 
 	/* If shadow stack enabled on target, set new shadow stack pointer */
 	if (is_shstk_enabled(target) &&
-	    (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SS_PTR_STATE))
+	    (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SHADOW_STACK_PTR_STATE))
 		set_active_shstk(target, user_cfi.shstk_ptr);
 
 	return 0;
diff --git a/tools/testing/selftests/riscv/cfi/cfitests.c b/tools/testing/selftests/riscv/cfi/cfitests.c
index 68374a27ec81..0dac74b8553c 100644
--- a/tools/testing/selftests/riscv/cfi/cfitests.c
+++ b/tools/testing/selftests/riscv/cfi/cfitests.c
@@ -95,8 +95,8 @@ bool cfi_ptrace_test(void)
 
 		switch (ptrace_test_num) {
 #define CFI_ENABLE_MASK (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE |	\
-			 PTRACE_CFI_SS_EN_STATE |	\
-			 PTRACE_CFI_SS_PTR_STATE)
+			 PTRACE_CFI_SHADOW_STACK_EN_STATE |		\
+			 PTRACE_CFI_SHADOW_STACK_PTR_STATE)
 		case 0:
 			if ((cfi_reg.cfi_status.cfi_state & CFI_ENABLE_MASK) != CFI_ENABLE_MASK)
 				ksft_exit_fail_msg("%s: ptrace_getregset failed, %llu\n", __func__,
-- 
cgit v1.2.3


From 08ee1559052be302f1d3752f48360b89517d9f8d Mon Sep 17 00:00:00 2001
From: Paul Walmsley <pjw@kernel.org>
Date: Sat, 4 Apr 2026 18:40:58 -0600
Subject: prctl: cfi: change the branch landing pad prctl()s to be more
 descriptive

Per Linus' comments requesting the replacement of "INDIR_BR_LP" in the
indirect branch tracking prctl()s with something more readable, and
suggesting the use of the speculation control prctl()s as an exemplar,
reimplement the prctl()s and related constants that control per-task
forward-edge control flow integrity.

This primarily involves two changes.  First, the prctls are
restructured to resemble the style of the speculative execution
workaround control prctls PR_{GET,SET}_SPECULATION_CTRL, to make them
easier to extend in the future.  Second, the "indir_br_lp" abbrevation
is expanded to "branch_landing_pads" to be less telegraphic.  The
kselftest and documentation is adjusted accordingly.

Link: https://lore.kernel.org/linux-riscv/CAHk-=whhSLGZAx3N5jJpb4GLFDqH_QvS07D+6BnkPWmCEzTAgw@mail.gmail.com/
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 Documentation/arch/riscv/zicfilp.rst               | 63 +++++++++++++---------
 arch/riscv/kernel/usercfi.c                        | 15 +++---
 include/uapi/linux/prctl.h                         | 37 ++++++-------
 kernel/sys.c                                       | 23 ++++----
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 36 ++++++-------
 tools/testing/selftests/riscv/cfi/cfitests.c       |  4 +-
 6 files changed, 91 insertions(+), 87 deletions(-)

diff --git a/Documentation/arch/riscv/zicfilp.rst b/Documentation/arch/riscv/zicfilp.rst
index 78a3e01ff68c..ab7d8e62ddaf 100644
--- a/Documentation/arch/riscv/zicfilp.rst
+++ b/Documentation/arch/riscv/zicfilp.rst
@@ -76,34 +76,49 @@ the program.
 4. prctl() enabling
 --------------------
 
-:c:macro:`PR_SET_INDIR_BR_LP_STATUS` / :c:macro:`PR_GET_INDIR_BR_LP_STATUS` /
-:c:macro:`PR_LOCK_INDIR_BR_LP_STATUS` are three prctls added to manage indirect
-branch tracking.  These prctls are architecture-agnostic and return -EINVAL if
-the underlying functionality is not supported.
+Per-task indirect branch tracking state can be monitored and
+controlled via the :c:macro:`PR_GET_CFI` and :c:macro:`PR_SET_CFI`
+``prctl()` arguments (respectively), by supplying
+:c:macro:`PR_CFI_BRANCH_LANDING_PADS` as the second argument.  These
+are architecture-agnostic, and will return -EINVAL if the underlying
+functionality is not supported.
 
-* prctl(PR_SET_INDIR_BR_LP_STATUS, unsigned long arg)
+* prctl(:c:macro:`PR_SET_CFI`, :c:macro:`PR_CFI_BRANCH_LANDING_PADS`, unsigned long arg)
 
-If arg1 is :c:macro:`PR_INDIR_BR_LP_ENABLE` and if CPU supports
-``zicfilp`` then the kernel will enable indirect branch tracking for the
-task.  The dynamic loader can issue this :c:macro:`prctl` once it has
-determined that all the objects loaded in the address space support
-indirect branch tracking.  Additionally, if there is a `dlopen` to an
-object which wasn't compiled with ``zicfilp``, the dynamic loader can
-issue this prctl with arg1 set to 0 (i.e. :c:macro:`PR_INDIR_BR_LP_ENABLE`
-cleared).
-
-* prctl(PR_GET_INDIR_BR_LP_STATUS, unsigned long * arg)
+arg is a bitmask.
 
-Returns the current status of indirect branch tracking. If enabled
-it'll return :c:macro:`PR_INDIR_BR_LP_ENABLE`
-
-* prctl(PR_LOCK_INDIR_BR_LP_STATUS, unsigned long arg)
+If :c:macro:`PR_CFI_ENABLE` is set in arg, and the CPU supports
+``zicfilp``, then the kernel will enable indirect branch tracking for
+the task.  The dynamic loader can issue this ``prctl()`` once it has
+determined that all the objects loaded in the address space support
+indirect branch tracking.
+
+Indirect branch tracking state can also be locked once enabled.  This
+prevents the task from subsequently disabling it.  This is done by
+setting the bit :c:macro:`PR_CFI_LOCK` in arg.  Either indirect branch
+tracking must already be enabled for the task, or the bit
+:c:macro:`PR_CFI_ENABLE` must also be set in arg.  This is intended
+for environments that wish to run with a strict security posture that
+do not wish to load objects without ``zicfilp`` support.
+
+Indirect branch tracking can also be disabled for the task, assuming
+that it has not previously been enabled and locked.  If there is a
+``dlopen()`` to an object which wasn't compiled with ``zicfilp``, the
+dynamic loader can issue this ``prctl()`` with arg set to
+:c:macro:`PR_CFI_DISABLE`.  Disabling indirect branch tracking for the
+task is not possible if it has previously been enabled and locked.
+
+
+* prctl(:c:macro:`PR_GET_CFI`, :c:macro:`PR_CFI_BRANCH_LANDING_PADS`, unsigned long * arg)
+
+Returns the current status of indirect branch tracking into a bitmask
+stored into the memory location pointed to by arg.  The bitmask will
+have the :c:macro:`PR_CFI_ENABLE` bit set if indirect branch tracking
+is currently enabled for the task, and if it is locked, will
+additionally have the :c:macro:`PR_CFI_LOCK` bit set.  If indirect
+branch tracking is currently disabled for the task, the
+:c:macro:`PR_CFI_DISABLE` bit will be set.
 
-Locks the current status of indirect branch tracking on the task. User
-space may want to run with a strict security posture and wouldn't want
-loading of objects without ``zicfilp`` support in them, to disallow
-disabling of indirect branch tracking. In this case, user space can
-use this prctl to lock the current settings.
 
 5. violations related to indirect branch tracking
 --------------------------------------------------
diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c
index 04ab1eb8df29..2c535737511d 100644
--- a/arch/riscv/kernel/usercfi.c
+++ b/arch/riscv/kernel/usercfi.c
@@ -465,16 +465,14 @@ int arch_prctl_get_branch_landing_pad_state(struct task_struct *t,
 	if (!is_user_lpad_enabled())
 		return -EINVAL;
 
-	/* indirect branch tracking is enabled on the task or not */
-	fcfi_status |= (is_indir_lp_enabled(t) ? PR_INDIR_BR_LP_ENABLE : 0);
+	fcfi_status = (is_indir_lp_enabled(t) ? PR_CFI_ENABLE : PR_CFI_DISABLE);
+	fcfi_status |= (is_indir_lp_locked(t) ? PR_CFI_LOCK : 0);
 
 	return copy_to_user(state, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0;
 }
 
 int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state)
 {
-	bool enable_indir_lp = false;
-
 	if (!is_user_lpad_enabled())
 		return -EINVAL;
 
@@ -482,12 +480,13 @@ int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long
 	if (is_indir_lp_locked(t))
 		return -EINVAL;
 
-	/* Reject unknown flags */
-	if (state & ~PR_INDIR_BR_LP_ENABLE)
+	if (!(state & (PR_CFI_ENABLE | PR_CFI_DISABLE)))
+		return -EINVAL;
+
+	if (state & PR_CFI_ENABLE && state & PR_CFI_DISABLE)
 		return -EINVAL;
 
-	enable_indir_lp = (state & PR_INDIR_BR_LP_ENABLE);
-	set_indir_lp_status(t, enable_indir_lp);
+	set_indir_lp_status(t, !!(state & PR_CFI_ENABLE));
 
 	return 0;
 }
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 55b0446fff9d..b6ec6f693719 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -397,30 +397,23 @@ struct prctl_mm_map {
 # define PR_RSEQ_SLICE_EXT_ENABLE		0x01
 
 /*
- * Get the current indirect branch tracking configuration for the current
- * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS.
+ * Get or set the control flow integrity (CFI) configuration for the
+ * current thread.
+ *
+ * Some per-thread control flow integrity settings are not yet
+ * controlled through this prctl(); see for example
+ * PR_{GET,SET,LOCK}_SHADOW_STACK_STATUS
  */
-#define PR_GET_INDIR_BR_LP_STATUS      80
-
+#define PR_GET_CFI	80
+#define PR_SET_CFI	81
 /*
- * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will
- * enable cpu feature for user thread, to track all indirect branches and ensure
- * they land on arch defined landing pad instruction.
- * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction.
- * arch64 - If enabled, an indirect branch must land on a BTI instruction.
- * riscv - If enabled, an indirect branch must land on an lpad instruction.
- * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect
- * branches will no more be tracked by cpu to land on arch defined landing pad
- * instruction.
- */
-#define PR_SET_INDIR_BR_LP_STATUS      81
-# define PR_INDIR_BR_LP_ENABLE		   (1UL << 0)
-
-/*
- * Prevent further changes to the specified indirect branch tracking
- * configuration.  All bits may be locked via this call, including
- * undefined bits.
+ * Forward-edge CFI variants (excluding ARM64 BTI, which has its own
+ * prctl()s).
  */
-#define PR_LOCK_INDIR_BR_LP_STATUS      82
+#define PR_CFI_BRANCH_LANDING_PADS	0
+/* Return and control values for PR_{GET,SET}_CFI */
+# define PR_CFI_ENABLE		_BITUL(0)
+# define PR_CFI_DISABLE		_BITUL(1)
+# define PR_CFI_LOCK		_BITUL(2)
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index a5e0c187bbbf..62e842055cc9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2889,20 +2889,23 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = rseq_slice_extension_prctl(arg2, arg3);
 		break;
-	case PR_GET_INDIR_BR_LP_STATUS:
-		if (arg3 || arg4 || arg5)
+	case PR_GET_CFI:
+		if (arg2 != PR_CFI_BRANCH_LANDING_PADS)
 			return -EINVAL;
-		error = arch_prctl_get_branch_landing_pad_state(me, (unsigned long __user *)arg2);
-		break;
-	case PR_SET_INDIR_BR_LP_STATUS:
-		if (arg3 || arg4 || arg5)
+		if (arg4 || arg5)
 			return -EINVAL;
-		error = arch_prctl_set_branch_landing_pad_state(me, arg2);
+		error = arch_prctl_get_branch_landing_pad_state(me, (unsigned long __user *)arg3);
 		break;
-	case PR_LOCK_INDIR_BR_LP_STATUS:
-		if (arg2 || arg3 || arg4 || arg5)
+	case PR_SET_CFI:
+		if (arg2 != PR_CFI_BRANCH_LANDING_PADS)
 			return -EINVAL;
-		error = arch_prctl_lock_branch_landing_pad_state(me);
+		if (arg4 || arg5)
+			return -EINVAL;
+		error = arch_prctl_set_branch_landing_pad_state(me, arg3);
+		if (error)
+			break;
+		if (arg3 & PR_CFI_LOCK && !(arg3 & PR_CFI_DISABLE))
+			error = arch_prctl_lock_branch_landing_pad_state(me);
 		break;
 	default:
 		trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5);
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 55b0446fff9d..560f99bc4782 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -397,30 +397,24 @@ struct prctl_mm_map {
 # define PR_RSEQ_SLICE_EXT_ENABLE		0x01
 
 /*
- * Get the current indirect branch tracking configuration for the current
- * thread, this will be the value configured via PR_SET_INDIR_BR_LP_STATUS.
+ * Get or set the control flow integrity (CFI) configuration for the
+ * current thread.
+ *
+ * Some per-thread control flow integrity settings are not yet
+ * controlled through this prctl(); see for example
+ * PR_{GET,SET,LOCK}_SHADOW_STACK_STATUS
  */
-#define PR_GET_INDIR_BR_LP_STATUS      80
-
+#define PR_GET_CFI	80
+#define PR_SET_CFI	81
 /*
- * Set the indirect branch tracking configuration. PR_INDIR_BR_LP_ENABLE will
- * enable cpu feature for user thread, to track all indirect branches and ensure
- * they land on arch defined landing pad instruction.
- * x86 - If enabled, an indirect branch must land on an ENDBRANCH instruction.
- * arch64 - If enabled, an indirect branch must land on a BTI instruction.
- * riscv - If enabled, an indirect branch must land on an lpad instruction.
- * PR_INDIR_BR_LP_DISABLE will disable feature for user thread and indirect
- * branches will no more be tracked by cpu to land on arch defined landing pad
- * instruction.
+ * Forward-edge CFI variants (excluding ARM64 BTI, which has its own
+ * prctl()s).
  */
-#define PR_SET_INDIR_BR_LP_STATUS      81
-# define PR_INDIR_BR_LP_ENABLE		   (1UL << 0)
+#define PR_CFI_BRANCH_LANDING_PADS	0
+/* Return and control values for PR_{GET,SET}_CFI */
+# define PR_CFI_ENABLE		_BITUL(0)
+# define PR_CFI_DISABLE		_BITUL(1)
+# define PR_CFI_LOCK		_BITUL(2)
 
-/*
- * Prevent further changes to the specified indirect branch tracking
- * configuration.  All bits may be locked via this call, including
- * undefined bits.
- */
-#define PR_LOCK_INDIR_BR_LP_STATUS      82
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/testing/selftests/riscv/cfi/cfitests.c b/tools/testing/selftests/riscv/cfi/cfitests.c
index 0dac74b8553c..39d097b6881f 100644
--- a/tools/testing/selftests/riscv/cfi/cfitests.c
+++ b/tools/testing/selftests/riscv/cfi/cfitests.c
@@ -146,11 +146,11 @@ int main(int argc, char *argv[])
 	 * pads for user mode except lighting up a bit in senvcfg via a prctl.
 	 * Enable landing pad support throughout the execution of the test binary.
 	 */
-	ret = my_syscall5(__NR_prctl, PR_GET_INDIR_BR_LP_STATUS, &lpad_status, 0, 0, 0);
+	ret = my_syscall5(__NR_prctl, PR_GET_CFI, PR_CFI_BRANCH_LANDING_PADS, &lpad_status, 0, 0);
 	if (ret)
 		ksft_exit_fail_msg("Get landing pad status failed with %d\n", ret);
 
-	if (!(lpad_status & PR_INDIR_BR_LP_ENABLE))
+	if (!(lpad_status & PR_CFI_ENABLE))
 		ksft_exit_fail_msg("Landing pad is not enabled, should be enabled via glibc\n");
 
 	ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &ss_status, 0, 0, 0);
-- 
cgit v1.2.3


From 0422b07bc4c296b736e240d95d21fbfebbfaa2ca Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Sat, 28 Feb 2026 09:08:14 -0500
Subject: x86/mce/amd: Filter bogus hardware errors on Zen3 clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Users have been observing multiple L3 cache deferred errors after recent
kernel rework of deferred error handling.¹ ⁴

The errors are bogus due to inconsistent status values. Also, user verified
that bogus MCA_DESTAT values are present on the system even with an older
kernel.²

The errors seem to be garbage values present in the MCA_DESTAT of some L3
cache banks. These were implicitly ignored before the recent kernel rework
because these do not generate a deferred error interrupt.

A later revision of the rework patch was merged for v6.19. This naturally
filtered out most of the bogus error logs. However, a few signatures still
remain.³

Minimize the scope of the filter to the reported CPU
family/model/stepping and only for errors which don't have the Enabled
bit in the MCi status MSR.

¹ https://lore.kernel.org/20250915010010.3547-1-spasswolf@web.de
² https://lore.kernel.org/6e1eda7dd55f6fa30405edf7b0f75695cf55b237.camel@web.de
³ https://lore.kernel.org/21ba47fa8893b33b94370c2a42e5084cf0d2e975.camel@web.de
⁴ https://lore.kernel.org/r/CAKFB093B2k3sKsGJ_QNX1jVQsaXVFyy=wNwpzCGLOXa_vSDwXw@mail.gmail.com

  [ bp: Generalize the condition according to which errors are bogus. ]

Fixes: 7cb735d7c0cb ("x86/mce: Unify AMD DFR handler with MCA Polling")
Closes: https://lore.kernel.org/20250915010010.3547-1-spasswolf@web.de
Reported-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-By: Bert Karwatzki <spasswolf@web.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250915010010.3547-1-spasswolf@web.de
---
 arch/x86/kernel/cpu/mce/amd.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index a030ee4cecc2..28deaba08833 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -604,6 +604,14 @@ bool amd_filter_mce(struct mce *m)
 	enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
+	/* Bogus hw errors on Cezanne A0. */
+	if (c->x86 == 0x19 &&
+	    c->x86_model == 0x50 &&
+	    c->x86_stepping == 0x0) {
+		if (!(m->status & MCI_STATUS_EN))
+			return true;
+	}
+
 	/* See Family 17h Models 10h-2Fh Erratum #1114. */
 	if (c->x86 == 0x17 &&
 	    c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
-- 
cgit v1.2.3


From 51520e03e70d6c73e33ee7cbe0319767d05764fe Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Tue, 31 Mar 2026 14:16:23 +0200
Subject: EDAC/mc: Fix error path ordering in edac_mc_alloc()

When the mci->pvt_info allocation in edac_mc_alloc() fails, the error path
will call put_device() which will end up calling the device's release
function.

However, the init ordering is wrong such that device_initialize() happens
*after* the failed allocation and thus the device itself and the release
function pointer are not initialized yet when they're called:

  MCE: In-kernel MCE decoding enabled.
  ------------[ cut here ]------------
  kobject: '(null)': is not initialized, yet kobject_put() is being called.
  WARNING: lib/kobject.c:734 at kobject_put, CPU#22: systemd-udevd
  CPU: 22 UID: 0 PID: 538 Comm: systemd-udevd Not tainted 7.0.0-rc1+ #2 PREEMPT(full)
  RIP: 0010:kobject_put
  Call Trace:
   <TASK>
   edac_mc_alloc+0xbe/0xe0 [edac_core]
   amd64_edac_init+0x7a4/0xff0 [amd64_edac]
   ? __pfx_amd64_edac_init+0x10/0x10 [amd64_edac]
   do_one_initcall
   ...

Reorder the calling sequence so that the device is initialized and thus the
release function pointer is properly set before it can be used.

This was found by Claude while reviewing another EDAC patch.

Fixes: 0bbb265f7089 ("EDAC/mc: Get rid of silly one-shot struct allocation in edac_mc_alloc()")
Reported-by: Claude Code:claude-opus-4.5
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Cc: stable@kernel.org
Link: https://patch.msgid.link/20260331121623.4871-1-bp@kernel.org
---
 drivers/edac/edac_mc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 29e9828422bb..11d66333d93b 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -369,13 +369,13 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num,
 	if (!mci->layers)
 		goto error;
 
+	mci->dev.release = mci_release;
+	device_initialize(&mci->dev);
+
 	mci->pvt_info = kzalloc(sz_pvt, GFP_KERNEL);
 	if (!mci->pvt_info)
 		goto error;
 
-	mci->dev.release = mci_release;
-	device_initialize(&mci->dev);
-
 	/* setup index and various internal pointers */
 	mci->mc_idx = mc_num;
 	mci->tot_dimms = tot_dimms;
-- 
cgit v1.2.3


From 5401b9adebc9e5f68df58226f51493ef0e6ceb4d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 5 Apr 2026 12:42:25 -0700
Subject: i915: don't use a vma that didn't match the context VM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In eb_lookup_vma(), the code checks that the context vm matches before
incrementing the i915 vma usage count, but for the non-matching case it
didn't clear the non-matching vma pointer, so it would then mistakenly
be returned, causing potential UaF and refcount issues.

Reported-by: Yassine Mounir <sosohero200@gmail.com>
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index e7918f896a26..942f4eed817f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -898,6 +898,8 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
 		vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle);
 		if (likely(vma && vma->vm == vm))
 			vma = i915_vma_tryget(vma);
+		else
+			vma = NULL;
 		rcu_read_unlock();
 		if (likely(vma))
 			return vma;
-- 
cgit v1.2.3


From 591cd656a1bf5ea94a222af5ef2ee76df029c1d2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 5 Apr 2026 15:26:23 -0700
Subject: Linux 7.0-rc7

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 6b1d9fb1a6b4..4f54c5685638 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 4346be6577aaa04586167402ae87bbdbe32484a4 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Thu, 2 Apr 2026 00:03:15 +0800
Subject: tracing/probe: reject non-closed empty immediate strings

parse_probe_arg() accepts quoted immediate strings and passes the body
after the opening quote to __parse_imm_string(). That helper currently
computes strlen(str) and immediately dereferences str[len - 1], which
underflows when the body is empty and not closed with double-quotation.

Reject empty non-closed immediate strings before checking for the closing quote.

Link: https://lore.kernel.org/all/20260401160315.88518-1-pengpeng@iscas.ac.cn/

Fixes: a42e3c4de964 ("tracing/probe: Add immediate string parameter support")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_probe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index e0a5dc86c07e..e1c73065dae5 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1068,7 +1068,7 @@ static int __parse_imm_string(char *str, char **pbuf, int offs)
 {
 	size_t len = strlen(str);
 
-	if (str[len - 1] != '"') {
+	if (!len || str[len - 1] != '"') {
 		trace_probe_log_err(offs + len, IMMSTR_NO_CLOSE);
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From f0541edb2e7333f320642c7b491a67912c1f65db Mon Sep 17 00:00:00 2001
From: songxiebing <songxiebing@kylinos.cn>
Date: Sun, 5 Apr 2026 09:26:51 +0800
Subject: ALSA: hda/realtek: Add quirk for Lenovo Yoga Pro 7 14IAH10

The bass speakers are not working, and add the following entry
in /etc/modprobe.d/snd.conf:
options snd-sof-intel-hda-generic hda_model=alc287-yoga9-bass-spk-pin
Fixes the bass speakers.

So add the quick ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN here.

Reported-by: Fernando Garcia Corona <fgarcor@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221317
Signed-off-by: songxiebing <songxiebing@kylinos.cn>
Link: https://patch.msgid.link/20260405012651.133838-1-songxiebing@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 6db23ce8a5fe..45f9d6487388 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7680,6 +7680,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x3911, "Lenovo Yoga Pro 7 14IAH10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
 	SND_PCI_QUIRK(0x17aa, 0x391a, "Lenovo Yoga Slim 7 14AKP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TXNW2781_I2C),
-- 
cgit v1.2.3


From 5075d08e72af38b829fb71800c2a5be61d0b2e2c Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@nabladev.com>
Date: Mon, 6 Apr 2026 01:44:35 +0200
Subject: ASoC: dt-bindings: ti,tas2552: Add sound-dai-cells

Add missing sound-sai-cells for this codec into schema.
At the same time, drop trailing spaces from description.

Fixes: 506e0825a4c9 ("ASoC: dt-bindings: Convert ti,tas2552 to DT schema")
Signed-off-by: Marek Vasut <marex@nabladev.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Link: https://patch.msgid.link/20260405234502.154227-1-marex@nabladev.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/ti,tas2552.yaml | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/sound/ti,tas2552.yaml b/Documentation/devicetree/bindings/sound/ti,tas2552.yaml
index 10369aa5f0a8..85e3ebd2acd8 100644
--- a/Documentation/devicetree/bindings/sound/ti,tas2552.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,tas2552.yaml
@@ -12,8 +12,8 @@ maintainers:
   - Baojun Xu <baojun.xu@ti.com>
 
 description: >
-  The TAS2552 can receive its reference clock via MCLK, BCLK, IVCLKIN pin or 
-  use the internal 1.8MHz. This CLKIN is used by the PLL. In addition to PLL, 
+  The TAS2552 can receive its reference clock via MCLK, BCLK, IVCLKIN pin or
+  use the internal 1.8MHz. This CLKIN is used by the PLL. In addition to PLL,
   the PDM reference clock is also selectable: PLL, IVCLKIN, BCLK or MCLK.
 
   For system integration the dt-bindings/sound/tas2552.h header file provides
@@ -34,6 +34,9 @@ properties:
     maxItems: 1
     description: gpio pin to enable/disable the device
 
+  '#sound-dai-cells':
+    const: 0
+
 required:
   - compatible
   - reg
@@ -41,7 +44,10 @@ required:
   - iovdd-supply
   - avdd-supply
 
-additionalProperties: false
+allOf:
+  - $ref: dai-common.yaml#
+
+unevaluatedProperties: false
 
 examples:
   - |
@@ -54,6 +60,7 @@ examples:
         audio-codec@41 {
             compatible = "ti,tas2552";
             reg = <0x41>;
+            #sound-dai-cells = <0>;
             vbat-supply = <&reg_vbat>;
             iovdd-supply = <&reg_iovdd>;
             avdd-supply = <&reg_avdd>;
-- 
cgit v1.2.3


From 80a7916ca2d902b329a40e529c4c4131ae6ff273 Mon Sep 17 00:00:00 2001
From: Mark Pearson <mpearson-lenovo@squebb.ca>
Date: Thu, 2 Apr 2026 21:03:25 -0400
Subject: ASoC: amd: acp: add Lenovo P16s G5 AMD quirk for legacy SDW machine

Add a DMI quirk entry for Lenovo P16s G5 AMD to use ASOC_SDW_ACP_DMIC.
Needed to allow the microphone to work on this platform

Signed-off-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://patch.msgid.link/20260403010336.1223078-1-mpearson-lenovo@squebb.ca
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-sdw-legacy-mach.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
index 6388cd7cb28e..92749dc17df8 100644
--- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c
+++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
@@ -111,6 +111,22 @@ static const struct dmi_system_id soc_sdw_quirk_table[] = {
 		},
 		.driver_data = (void *)(ASOC_SDW_CODEC_SPKR),
 	},
+	{
+		.callback = soc_sdw_quirk_cb,
+		.matches = { /* Lenovo P16s G5 AMD */
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "21XG"),
+		},
+		.driver_data = (void *)(ASOC_SDW_ACP_DMIC),
+	},
+	{
+		.callback = soc_sdw_quirk_cb,
+		.matches = { /* Lenovo P16s G5 AMD */
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "21XH"),
+		},
+		.driver_data = (void *)(ASOC_SDW_ACP_DMIC),
+	},
 	{
 		.callback = soc_sdw_quirk_cb,
 		.matches = {
-- 
cgit v1.2.3


From 4e53116437e919c4b9a9d95fb73ae14fe0cfc8f9 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Mon, 16 Mar 2026 14:14:49 +0000
Subject: ASoC: SDCA: Fix errors in IRQ cleanup

IRQs are enabled through sdca_irq_populate() from component probe
using devm_request_threaded_irq(), this however means the IRQs can
persist if the sound card is torn down. Some of the IRQ handlers
store references to the card and the kcontrols which can then
fail. Some detail of the crash was explained in [1].

Generally it is not advised to use devm outside of bus probe, so
the code is updated to not use devm. The IRQ requests are not moved
to bus probe time as it makes passing the snd_soc_component into
the IRQs very awkward and would the require a second step once the
component is available, so it is simpler to just register the IRQs
at this point, even though that necessitates some manual cleanup.

Link: https://lore.kernel.org/linux-sound/20260310183829.2907805-1-gaggery.tsai@intel.com/ [1]
Fixes: b126394d9ec6 ("ASoC: SDCA: Generic interrupt support")
Reported-by: Gaggery Tsai <gaggery.tsai@intel.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260316141449.2950215-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sdca_interrupts.h      |  5 +++
 sound/soc/sdca/sdca_class_function.c |  9 +++++
 sound/soc/sdca/sdca_interrupts.c     | 77 ++++++++++++++++++++++++++++++++++--
 3 files changed, 87 insertions(+), 4 deletions(-)

diff --git a/include/sound/sdca_interrupts.h b/include/sound/sdca_interrupts.h
index 9bcb5d8fd592..b47003c3d26e 100644
--- a/include/sound/sdca_interrupts.h
+++ b/include/sound/sdca_interrupts.h
@@ -69,6 +69,8 @@ struct sdca_interrupt_info {
 int sdca_irq_request(struct device *dev, struct sdca_interrupt_info *interrupt_info,
 		     int sdca_irq, const char *name, irq_handler_t handler,
 		     void *data);
+void sdca_irq_free(struct device *dev, struct sdca_interrupt_info *interrupt_info,
+		   int sdca_irq, const char *name, void *data);
 int sdca_irq_data_populate(struct device *dev, struct regmap *function_regmap,
 			   struct snd_soc_component *component,
 			   struct sdca_function_data *function,
@@ -81,6 +83,9 @@ int sdca_irq_populate_early(struct device *dev, struct regmap *function_regmap,
 int sdca_irq_populate(struct sdca_function_data *function,
 		      struct snd_soc_component *component,
 		      struct sdca_interrupt_info *info);
+void sdca_irq_cleanup(struct sdca_function_data *function,
+		      struct snd_soc_component *component,
+		      struct sdca_interrupt_info *info);
 struct sdca_interrupt_info *sdca_irq_allocate(struct device *dev,
 					      struct regmap *regmap, int irq);
 
diff --git a/sound/soc/sdca/sdca_class_function.c b/sound/soc/sdca/sdca_class_function.c
index 98fd3fd1052b..fe404d769c78 100644
--- a/sound/soc/sdca/sdca_class_function.c
+++ b/sound/soc/sdca/sdca_class_function.c
@@ -198,6 +198,14 @@ static int class_function_component_probe(struct snd_soc_component *component)
 	return sdca_irq_populate(drv->function, component, core->irq_info);
 }
 
+static void class_function_component_remove(struct snd_soc_component *component)
+{
+	struct class_function_drv *drv = snd_soc_component_get_drvdata(component);
+	struct sdca_class_drv *core = drv->core;
+
+	sdca_irq_cleanup(drv->function, component, core->irq_info);
+}
+
 static int class_function_set_jack(struct snd_soc_component *component,
 				   struct snd_soc_jack *jack, void *d)
 {
@@ -209,6 +217,7 @@ static int class_function_set_jack(struct snd_soc_component *component,
 
 static const struct snd_soc_component_driver class_function_component_drv = {
 	.probe			= class_function_component_probe,
+	.remove			= class_function_component_remove,
 	.endianness		= 1,
 };
 
diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index 95b1ab4ba1b0..1838dabcdf60 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -252,8 +252,7 @@ static int sdca_irq_request_locked(struct device *dev,
 	if (irq < 0)
 		return irq;
 
-	ret = devm_request_threaded_irq(dev, irq, NULL, handler,
-					IRQF_ONESHOT, name, data);
+	ret = request_threaded_irq(irq, NULL, handler, IRQF_ONESHOT, name, data);
 	if (ret)
 		return ret;
 
@@ -264,6 +263,22 @@ static int sdca_irq_request_locked(struct device *dev,
 	return 0;
 }
 
+static void sdca_irq_free_locked(struct device *dev, struct sdca_interrupt_info *info,
+				 int sdca_irq, const char *name, void *data)
+{
+	int irq;
+
+	irq = regmap_irq_get_virq(info->irq_data, sdca_irq);
+	if (irq < 0)
+		return;
+
+	free_irq(irq, data);
+
+	info->irqs[sdca_irq].irq = 0;
+
+	dev_dbg(dev, "freed irq %d for %s\n", irq, name);
+}
+
 /**
  * sdca_irq_request - request an individual SDCA interrupt
  * @dev: Pointer to the struct device against which things should be allocated.
@@ -302,6 +317,30 @@ int sdca_irq_request(struct device *dev, struct sdca_interrupt_info *info,
 }
 EXPORT_SYMBOL_NS_GPL(sdca_irq_request, "SND_SOC_SDCA");
 
+/**
+ * sdca_irq_free - free an individual SDCA interrupt
+ * @dev: Pointer to the struct device.
+ * @info: Pointer to the interrupt information structure.
+ * @sdca_irq: SDCA interrupt position.
+ * @name: Name to be given to the IRQ.
+ * @data: Private data pointer that will be passed to the handler.
+ *
+ * Typically this is handled internally by sdca_irq_cleanup, however if
+ * a device requires custom IRQ handling this can be called manually before
+ * calling sdca_irq_cleanup, which will then skip that IRQ whilst processing.
+ */
+void sdca_irq_free(struct device *dev, struct sdca_interrupt_info *info,
+		   int sdca_irq, const char *name, void *data)
+{
+	if (sdca_irq < 0 || sdca_irq >= SDCA_MAX_INTERRUPTS)
+		return;
+
+	guard(mutex)(&info->irq_lock);
+
+	sdca_irq_free_locked(dev, info, sdca_irq, name, data);
+}
+EXPORT_SYMBOL_NS_GPL(sdca_irq_free, "SND_SOC_SDCA");
+
 /**
  * sdca_irq_data_populate - Populate common interrupt data
  * @dev: Pointer to the Function device.
@@ -328,8 +367,8 @@ int sdca_irq_data_populate(struct device *dev, struct regmap *regmap,
 	if (!dev)
 		return -ENODEV;
 
-	name = devm_kasprintf(dev, GFP_KERNEL, "%s %s %s", function->desc->name,
-			      entity->label, control->label);
+	name = kasprintf(GFP_KERNEL, "%s %s %s", function->desc->name,
+			 entity->label, control->label);
 	if (!name)
 		return -ENOMEM;
 
@@ -516,6 +555,36 @@ int sdca_irq_populate(struct sdca_function_data *function,
 }
 EXPORT_SYMBOL_NS_GPL(sdca_irq_populate, "SND_SOC_SDCA");
 
+/**
+ * sdca_irq_cleanup - Free all the individual IRQs for an SDCA Function
+ * @function: Pointer to the SDCA Function.
+ * @component: Pointer to the ASoC component for the Function.
+ * @info: Pointer to the SDCA interrupt info for this device.
+ *
+ * Typically this would be called from the driver for a single SDCA Function.
+ */
+void sdca_irq_cleanup(struct sdca_function_data *function,
+		      struct snd_soc_component *component,
+		      struct sdca_interrupt_info *info)
+{
+	struct device *dev = component->dev;
+	int i;
+
+	guard(mutex)(&info->irq_lock);
+
+	for (i = 0; i < SDCA_MAX_INTERRUPTS; i++) {
+		struct sdca_interrupt *interrupt = &info->irqs[i];
+
+		if (interrupt->function != function || !interrupt->irq)
+			continue;
+
+		sdca_irq_free_locked(dev, info, i, interrupt->name, interrupt);
+
+		kfree(interrupt->name);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(sdca_irq_cleanup, "SND_SOC_SDCA");
+
 /**
  * sdca_irq_allocate - allocate an SDCA interrupt structure for a device
  * @sdev: Device pointer against which things should be allocated.
-- 
cgit v1.2.3


From 86facd80a2a37536937f06de637abf9e8cabdb4b Mon Sep 17 00:00:00 2001
From: Maciej Strozek <mstrozek@opensource.cirrus.com>
Date: Thu, 2 Apr 2026 14:45:30 +0800
Subject: ASoC: SOF: Intel: Fix endpoint index if endpoints are missing

In case of missing endpoints, the sequential numbering will cause wrong
mapping. Instead, assign the original DAI index from codec_info_list.

Fixes: 5226d19d4cae ("ASoC: SOF: Intel: use sof_sdw as default SDW machine driver")
Signed-off-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20260402064531.2287261-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index c0cc7d3ce526..57632b464117 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1203,7 +1203,7 @@ static struct snd_soc_acpi_adr_device *find_acpi_adr_device(struct device *dev,
 						 codec_info_list[i].dais[j].dai_type))
 				continue;
 
-			endpoints[ep_index].num = ep_index;
+			endpoints[ep_index].num = j;
 			if (codec_info_list[i].dais[j].dai_type == SOC_SDW_DAI_TYPE_AMP) {
 				/* Assume all amp are aggregated */
 				endpoints[ep_index].aggregated = 1;
-- 
cgit v1.2.3


From 1de6ddcddc954a69f96b1c23205e03ddd603e3c8 Mon Sep 17 00:00:00 2001
From: Maciej Strozek <mstrozek@opensource.cirrus.com>
Date: Thu, 2 Apr 2026 14:45:31 +0800
Subject: ASoC: SOF: Intel: fix iteration in is_endpoint_present()

is_endpoint_present() iterates over sdca_data.num_functions, but checks
the dai_type according to codec info list, which will cause problems if
not all endpoints from the codec info list are present. Make sure the
type of actually present functions is compared against target dai_type.

Fixes: 5226d19d4cae ("ASoC: SOF: Intel: use sof_sdw as default SDW machine driver")
Signed-off-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20260402064531.2287261-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 57632b464117..8a240dcb7fcb 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1133,8 +1133,7 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev,
 
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_INTEL_SOUNDWIRE)
 
-static bool is_endpoint_present(struct sdw_slave *sdw_device,
-				struct asoc_sdw_codec_info *dai_info, int dai_type)
+static bool is_endpoint_present(struct sdw_slave *sdw_device, int dai_type)
 {
 	int i;
 
@@ -1145,7 +1144,7 @@ static bool is_endpoint_present(struct sdw_slave *sdw_device,
 	}
 
 	for (i = 0; i < sdw_device->sdca_data.num_functions; i++) {
-		if (dai_type == dai_info->dais[i].dai_type)
+		if (dai_type == asoc_sdw_get_dai_type(sdw_device->sdca_data.function[i].type))
 			return true;
 	}
 	dev_dbg(&sdw_device->dev, "Endpoint DAI type %d not found\n", dai_type);
@@ -1199,8 +1198,7 @@ static struct snd_soc_acpi_adr_device *find_acpi_adr_device(struct device *dev,
 		}
 		for (j = 0; j < codec_info_list[i].dai_num; j++) {
 			/* Check if the endpoint is present by the SDCA DisCo table */
-			if (!is_endpoint_present(sdw_device, &codec_info_list[i],
-						 codec_info_list[i].dais[j].dai_type))
+			if (!is_endpoint_present(sdw_device, codec_info_list[i].dais[j].dai_type))
 				continue;
 
 			endpoints[ep_index].num = j;
-- 
cgit v1.2.3


From 82d8701b2c930d0e96b0dbc9115a218d791cb0d2 Mon Sep 17 00:00:00 2001
From: Haoze Xie <royenheart@gmail.com>
Date: Mon, 6 Apr 2026 21:17:28 +0800
Subject: batman-adv: hold claim backbone gateways by reference

batadv_bla_add_claim() can replace claim->backbone_gw and drop the old
gateway's last reference while readers still follow the pointer.

The netlink claim dump path dereferences claim->backbone_gw->orig and
takes claim->backbone_gw->crc_lock without pinning the underlying
backbone gateway. batadv_bla_check_claim() still has the same naked
pointer access pattern.

Reuse batadv_bla_claim_get_backbone_gw() in both readers so they operate
on a stable gateway reference until the read-side work is complete.
This keeps the dump and claim-check paths aligned with the lifetime
rules introduced for the other BLA claim readers.

Fixes: 23721387c409 ("batman-adv: add basic bridge loop avoidance code")
Fixes: 04f3f5bf1883 ("batman-adv: add B.A.T.M.A.N. Dump BLA claims via netlink")
Cc: stable@vger.kernel.org
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Haoze Xie <royenheart@gmail.com>
Signed-off-by: Ao Zhou <n05ec@lzu.edu.cn>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bridge_loop_avoidance.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 3dc791c15bf7..648fa97ea913 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -2130,6 +2130,7 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid,
 			    struct batadv_bla_claim *claim)
 {
 	const u8 *primary_addr = primary_if->net_dev->dev_addr;
+	struct batadv_bla_backbone_gw *backbone_gw;
 	u16 backbone_crc;
 	bool is_own;
 	void *hdr;
@@ -2145,32 +2146,35 @@ batadv_bla_claim_dump_entry(struct sk_buff *msg, u32 portid,
 
 	genl_dump_check_consistent(cb, hdr);
 
-	is_own = batadv_compare_eth(claim->backbone_gw->orig,
-				    primary_addr);
+	backbone_gw = batadv_bla_claim_get_backbone_gw(claim);
+
+	is_own = batadv_compare_eth(backbone_gw->orig, primary_addr);
 
-	spin_lock_bh(&claim->backbone_gw->crc_lock);
-	backbone_crc = claim->backbone_gw->crc;
-	spin_unlock_bh(&claim->backbone_gw->crc_lock);
+	spin_lock_bh(&backbone_gw->crc_lock);
+	backbone_crc = backbone_gw->crc;
+	spin_unlock_bh(&backbone_gw->crc_lock);
 
 	if (is_own)
 		if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) {
 			genlmsg_cancel(msg, hdr);
-			goto out;
+			goto put_backbone_gw;
 		}
 
 	if (nla_put(msg, BATADV_ATTR_BLA_ADDRESS, ETH_ALEN, claim->addr) ||
 	    nla_put_u16(msg, BATADV_ATTR_BLA_VID, claim->vid) ||
 	    nla_put(msg, BATADV_ATTR_BLA_BACKBONE, ETH_ALEN,
-		    claim->backbone_gw->orig) ||
+		    backbone_gw->orig) ||
 	    nla_put_u16(msg, BATADV_ATTR_BLA_CRC,
 			backbone_crc)) {
 		genlmsg_cancel(msg, hdr);
-		goto out;
+		goto put_backbone_gw;
 	}
 
 	genlmsg_end(msg, hdr);
 	ret = 0;
 
+put_backbone_gw:
+	batadv_backbone_gw_put(backbone_gw);
 out:
 	return ret;
 }
@@ -2448,6 +2452,7 @@ out:
 bool batadv_bla_check_claim(struct batadv_priv *bat_priv,
 			    u8 *addr, unsigned short vid)
 {
+	struct batadv_bla_backbone_gw *backbone_gw;
 	struct batadv_bla_claim search_claim;
 	struct batadv_bla_claim *claim = NULL;
 	struct batadv_hard_iface *primary_if = NULL;
@@ -2470,9 +2475,13 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv,
 	 * return false.
 	 */
 	if (claim) {
-		if (!batadv_compare_eth(claim->backbone_gw->orig,
+		backbone_gw = batadv_bla_claim_get_backbone_gw(claim);
+
+		if (!batadv_compare_eth(backbone_gw->orig,
 					primary_if->net_dev->dev_addr))
 			ret = false;
+
+		batadv_backbone_gw_put(backbone_gw);
 		batadv_claim_put(claim);
 	}
 
-- 
cgit v1.2.3


From f58df566524ebcdfa394329c64f47e3c9257516e Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Tue, 17 Mar 2026 17:29:55 +0800
Subject: mm: filemap: fix nr_pages calculation overflow in filemap_map_pages()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When running stress-ng on my Arm64 machine with v7.0-rc3 kernel, I
encountered some very strange crash issues showing up as "Bad page state":

"
[  734.496287] BUG: Bad page state in process stress-ng-env  pfn:415735fb
[  734.496427] page: refcount:0 mapcount:1 mapping:0000000000000000 index:0x4cf316 pfn:0x415735fb
[  734.496434] flags: 0x57fffe000000800(owner_2|node=1|zone=2|lastcpupid=0x3ffff)
[  734.496439] raw: 057fffe000000800 0000000000000000 dead000000000122 0000000000000000
[  734.496440] raw: 00000000004cf316 0000000000000000 0000000000000000 0000000000000000
[  734.496442] page dumped because: nonzero mapcount
"

After analyzing this page’s state, it is hard to understand why the
mapcount is not 0 while the refcount is 0, since this page is not where
the issue first occurred.  By enabling the CONFIG_DEBUG_VM config, I can
reproduce the crash as well and captured the first warning where the issue
appears:

"
[  734.469226] page: refcount:33 mapcount:0 mapping:00000000bef2d187 index:0x81a0 pfn:0x415735c0
[  734.469304] head: order:5 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  734.469315] memcg:ffff000807a8ec00
[  734.469320] aops:ext4_da_aops ino:100b6f dentry name(?):"stress-ng-mmaptorture-9397-0-2736200540"
[  734.469335] flags: 0x57fffe400000069(locked|uptodate|lru|head|node=1|zone=2|lastcpupid=0x3ffff)
......
[  734.469364] page dumped because: VM_WARN_ON_FOLIO((_Generic((page + nr_pages - 1),
const struct page *: (const struct folio *)_compound_head(page + nr_pages - 1), struct page *:
(struct folio *)_compound_head(page + nr_pages - 1))) != folio)
[  734.469390] ------------[ cut here ]------------
[  734.469393] WARNING: ./include/linux/rmap.h:351 at folio_add_file_rmap_ptes+0x3b8/0x468,
CPU#90: stress-ng-mlock/9430
[  734.469551]  folio_add_file_rmap_ptes+0x3b8/0x468 (P)
[  734.469555]  set_pte_range+0xd8/0x2f8
[  734.469566]  filemap_map_folio_range+0x190/0x400
[  734.469579]  filemap_map_pages+0x348/0x638
[  734.469583]  do_fault_around+0x140/0x198
......
[  734.469640]  el0t_64_sync+0x184/0x188
"

The code that triggers the warning is: "VM_WARN_ON_FOLIO(page_folio(page +
nr_pages - 1) != folio, folio)", which indicates that set_pte_range()
tried to map beyond the large folio’s size.

By adding more debug information, I found that 'nr_pages' had overflowed
in filemap_map_pages(), causing set_pte_range() to establish mappings for
a range exceeding the folio size, potentially corrupting fields of pages
that do not belong to this folio (e.g., page->_mapcount).

After above analysis, I think the possible race is as follows:

CPU 0                                                  CPU 1
filemap_map_pages()                                   ext4_setattr()
   //get and lock folio with old inode->i_size
   next_uptodate_folio()

                                                          .......
                                                          //shrink the inode->i_size
                                                          i_size_write(inode, attr->ia_size);

   //calculate the end_pgoff with the new inode->i_size
   file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
   end_pgoff = min(end_pgoff, file_end);

   ......
   //nr_pages can be overflowed, cause xas.xa_index > end_pgoff
   end = folio_next_index(folio) - 1;
   nr_pages = min(end, end_pgoff) - xas.xa_index + 1;

   ......
   //map large folio
   filemap_map_folio_range()
                                                          ......
                                                          //truncate folios
                                                          truncate_pagecache(inode, inode->i_size);

To fix this issue, move the 'end_pgoff' calculation before
next_uptodate_folio(), so the retrieved folio stays consistent with the
file end to avoid 'nr_pages' calculation overflow.  After this patch, the
crash issue is gone.

Link: https://lkml.kernel.org/r/1cf1ac59018fc647a87b0dad605d4056a71c14e4.1773739704.git.baolin.wang@linux.alibaba.com
Fixes: 743a2753a02e ("filemap: cap PTE range to be created to allowed zero fill in folio_map_range()")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Yuanhe Shu <xiangzao@linux.alibaba.com>
Tested-by: Yuanhe Shu <xiangzao@linux.alibaba.com>
Acked-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Daniel Gomez <da.gomez@samsung.com>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Luis Chamberalin <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/filemap.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 406cef06b684..3c1e785542dd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3883,14 +3883,19 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	unsigned int nr_pages = 0, folio_type;
 	unsigned short mmap_miss = 0, mmap_miss_saved;
 
+	/*
+	 * Recalculate end_pgoff based on file_end before calling
+	 * next_uptodate_folio() to avoid races with concurrent
+	 * truncation.
+	 */
+	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+	end_pgoff = min(end_pgoff, file_end);
+
 	rcu_read_lock();
 	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
 	if (!folio)
 		goto out;
 
-	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
-	end_pgoff = min(end_pgoff, file_end);
-
 	/*
 	 * Do not allow to map with PMD across i_size to preserve
 	 * SIGBUS semantics.
-- 
cgit v1.2.3


From 307e0c5859b0aecc34180468b1aa76684adcf539 Mon Sep 17 00:00:00 2001
From: Leo Timmins <leotimmins1974@gmail.com>
Date: Wed, 25 Mar 2026 12:46:07 +0800
Subject: liveupdate: propagate file deserialization failures

luo_session_deserialize() ignored the return value from
luo_file_deserialize().  As a result, a session could be left partially
restored even though the /dev/liveupdate open path treats deserialization
failures as fatal.

Propagate the error so a failed file deserialization aborts session
deserialization instead of silently continuing.

Link: https://lkml.kernel.org/r/20260325044608.8407-1-leotimmins1974@gmail.com
Link: https://lkml.kernel.org/r/20260325044608.8407-2-leotimmins1974@gmail.com
Fixes: 16cec0d26521 ("liveupdate: luo_session: add ioctls for file preservation")
Signed-off-by: Leo Timmins <leotimmins1974@gmail.com>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/liveupdate/luo_session.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c
index 783677295640..25ae704d7787 100644
--- a/kernel/liveupdate/luo_session.c
+++ b/kernel/liveupdate/luo_session.c
@@ -558,8 +558,13 @@ int luo_session_deserialize(void)
 		}
 
 		scoped_guard(mutex, &session->mutex) {
-			luo_file_deserialize(&session->file_set,
-					     &sh->ser[i].file_set_ser);
+			err = luo_file_deserialize(&session->file_set,
+						   &sh->ser[i].file_set_ser);
+		}
+		if (err) {
+			pr_warn("Failed to deserialize files for session [%s] %pe\n",
+				session->name, ERR_PTR(err));
+			return err;
 		}
 	}
 
-- 
cgit v1.2.3


From cece9dc61daab6006d3ac9d36a0df2dd58fef18d Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 26 Mar 2026 14:51:27 -0700
Subject: mm: reinstate unconditional writeback start in balance_dirty_pages()

Commit 64dd89ae01f2 ("mm/block/fs: remove laptop_mode") removed this
unconditional writeback start from balance_dirty_pages():

       if (unlikely(!writeback_in_progress(wb)))
	       wb_start_background_writeback(wb);

This logic needs to be reinstated to prevent performance regressions for
strictlimited BDIs and memcg setups.  The problem occurs because:

a) For strictlimited BDIs, throttling is calculated using per-wb
   thresholds.  The per-wb threshold can be exceeded even when the global
   dirty threshold was not exceeded (nr_dirty < gdtc->bg_thresh)

b) For memcg-based throttling, memcg uses its own dirty count /
   thresholds and can trigger throttling even when the global threshold
   isn't exceeded

Without the unconditional writeback start, IO is throttled as it waits for
dirty pages to be written back but there is no writeback running.  This
leads to severe stalls.  On fuse, buffered write performance dropped from
1400 MiB/s to 2000 KiB/s.

Reinstate the unconditional writeback start so that writeback is
guaranteed to be running whenever IO needs to be throttled.

Link: https://lkml.kernel.org/r/20260326215127.3857682-2-joannelkoong@gmail.com
Fixes: 64dd89ae01f2 ("mm/block/fs: remove laptop_mode")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page-writeback.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 601a5e048d12..c1a4b32af1a7 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1858,6 +1858,27 @@ free_running:
 			break;
 		}
 
+		/*
+		 * Unconditionally start background writeback if it's not
+		 * already in progress. We need to do this because the global
+		 * dirty threshold check above (nr_dirty > gdtc->bg_thresh)
+		 * doesn't account for these cases:
+		 *
+		 * a) strictlimit BDIs: throttling is calculated using per-wb
+		 * thresholds. The per-wb threshold can be exceeded even when
+		 * nr_dirty < gdtc->bg_thresh
+		 *
+		 * b) memcg-based throttling: memcg uses its own dirty count and
+		 * thresholds and can trigger throttling even when global
+		 * nr_dirty < gdtc->bg_thresh
+		 *
+		 * Writeback needs to be started else the writer stalls in the
+		 * throttle loop waiting for dirty pages to be written back
+		 * while no writeback is running.
+		 */
+		if (unlikely(!writeback_in_progress(wb)))
+			wb_start_background_writeback(wb);
+
 		mem_cgroup_flush_foreign(wb);
 
 		/*
-- 
cgit v1.2.3


From 0199390a6b92fc21860e1b858abf525c7e73b956 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Thu, 26 Mar 2026 17:32:22 -0700
Subject: mm/damon/sysfs: dealloc repeat_call_control if damon_call() fails

damon_call() for repeat_call_control of DAMON_SYSFS could fail if somehow
the kdamond is stopped before the damon_call().  It could happen, for
example, when te damon context was made for monitroing of a virtual
address processes, and the process is terminated immediately, before the
damon_call() invocation.  In the case, the dyanmically allocated
repeat_call_control is not deallocated and leaked.

Fix the leak by deallocating the repeat_call_control under the
damon_call() failure.

This issue is discovered by sashiko [1].

Link: https://lkml.kernel.org/r/20260327003224.55752-1-sj@kernel.org
Link: https://lore.kernel.org/20260320020630.962-1-sj@kernel.org [1]
Fixes: 04a06b139ec0 ("mm/damon/sysfs: use dynamically allocated repeat mode damon_call_control")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.17+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 6a44a2f3d8fc..eefa959aa30a 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1670,7 +1670,8 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond)
 	repeat_call_control->data = kdamond;
 	repeat_call_control->repeat = true;
 	repeat_call_control->dealloc_on_cancel = true;
-	damon_call(ctx, repeat_call_control);
+	if (damon_call(ctx, repeat_call_control))
+		kfree(repeat_call_control);
 	return err;
 }
 
-- 
cgit v1.2.3


From 2ecbe06abf9bfb2261cd6464a6bc3a3615625402 Mon Sep 17 00:00:00 2001
From: Hao Li <hao.li@linux.dev>
Date: Mon, 30 Mar 2026 11:57:49 +0800
Subject: mm/memory_hotplug: maintain N_NORMAL_MEMORY during hotplug

N_NORMAL_MEMORY is initialized from zone population at boot, but memory
hotplug currently only updates N_MEMORY.  As a result, a node that gains
normal memory via hotplug can remain invisible to users iterating over
N_NORMAL_MEMORY, while a node that loses its last normal memory can stay
incorrectly marked as such.

The most visible effect is that
/sys/devices/system/node/has_normal_memory does not report a node even
after that node has gained normal memory via hotplug.

Also, list_lru-based shrinkers can undercount objects on such a node
and may skip reclaim on that node entirely, which can lead to a higher
memory footprint than expected.

Restore N_NORMAL_MEMORY maintenance directly in online_pages() and
offline_pages().  Set the bit when a node that currently lacks normal
memory onlines pages into a zone <= ZONE_NORMAL, and clear it when
offlining removes the last present pages from zones <= ZONE_NORMAL.

This restores the intended semantics without bringing back the old
status_change_nid_normal notifier plumbing which was removed in
8d2882a8edb8.

Current users that benefit include list_lru, zswap, nfsd filecache,
hugetlb_cgroup, and has_normal_memory sysfs reporting.

Link: https://lkml.kernel.org/r/20260330035941.518186-1-hao.li@linux.dev
Fixes: 8d2882a8edb8 ("mm,memory_hotplug: remove status_change_nid_normal and update documentation")
Signed-off-by: Hao Li <hao.li@linux.dev>
Reviewed-by: Harry Yoo (Oracle) <harry@kernel.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index bc805029da51..05a47953ef21 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1209,6 +1209,13 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 
 	if (node_arg.nid >= 0)
 		node_set_state(nid, N_MEMORY);
+	/*
+	 * Check whether we are adding normal memory to the node for the first
+	 * time.
+	 */
+	if (!node_state(nid, N_NORMAL_MEMORY) && zone_idx(zone) <= ZONE_NORMAL)
+		node_set_state(nid, N_NORMAL_MEMORY);
+
 	if (need_zonelists_rebuild)
 		build_all_zonelists(NULL);
 
@@ -1908,6 +1915,8 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	unsigned long flags;
 	char *reason;
 	int ret;
+	unsigned long normal_pages = 0;
+	enum zone_type zt;
 
 	/*
 	 * {on,off}lining is constrained to full memory sections (or more
@@ -2055,6 +2064,17 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	/* reinitialise watermarks and update pcp limits */
 	init_per_zone_wmark_min();
 
+	/*
+	 * Check whether this operation removes the last normal memory from
+	 * the node. We do this before clearing N_MEMORY to avoid the possible
+	 * transient "!N_MEMORY && N_NORMAL_MEMORY" state.
+	 */
+	if (zone_idx(zone) <= ZONE_NORMAL) {
+		for (zt = 0; zt <= ZONE_NORMAL; zt++)
+			normal_pages += pgdat->node_zones[zt].present_pages;
+		if (!normal_pages)
+			node_clear_state(node, N_NORMAL_MEMORY);
+	}
 	/*
 	 * Make sure to mark the node as memory-less before rebuilding the zone
 	 * list. Otherwise this node would still appear in the fallback lists.
-- 
cgit v1.2.3


From 894f99eb535edc4514f756818f3c4f688ba53a59 Mon Sep 17 00:00:00 2001
From: Sechang Lim <rhkrqnwk98@gmail.com>
Date: Tue, 31 Mar 2026 18:08:11 +0000
Subject: mm/vma: fix memory leak in __mmap_region()

commit 605f6586ecf7 ("mm/vma: do not leak memory when .mmap_prepare
swaps the file") handled the success path by skipping get_file() via
file_doesnt_need_get, but missed the error path.

When /dev/zero is mmap'd with MAP_SHARED, mmap_zero_prepare() calls
shmem_zero_setup_desc() which allocates a new shmem file to back the
mapping. If __mmap_new_vma() subsequently fails, this replacement
file is never fput()'d - the original is released by
ksys_mmap_pgoff(), but nobody releases the new one.

Add fput() for the swapped file in the error path.

Reproducible with fault injection.

FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 1
CPU: 2 UID: 0 PID: 366 Comm: syz.7.14 Not tainted 7.0.0-rc6 #2 PREEMPT(full)
Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x164/0x1f0
 should_fail_ex+0x525/0x650
 should_failslab+0xdf/0x140
 kmem_cache_alloc_noprof+0x78/0x630
 vm_area_alloc+0x24/0x160
 __mmap_region+0xf6b/0x2660
 mmap_region+0x2eb/0x3a0
 do_mmap+0xc79/0x1240
 vm_mmap_pgoff+0x252/0x4c0
 ksys_mmap_pgoff+0xf8/0x120
 __x64_sys_mmap+0x12a/0x190
 do_syscall_64+0xa9/0x580
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
 </TASK>

kmemleak: 1 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
BUG: memory leak
unreferenced object 0xffff8881118aca80 (size 360):
  comm "syz.7.14", pid 366, jiffies 4294913255
  hex dump (first 32 bytes):
    00 00 00 00 ad 4e ad de ff ff ff ff 00 00 00 00  .....N..........
    ff ff ff ff ff ff ff ff c0 28 4d ae ff ff ff ff  .........(M.....
  backtrace (crc db0f53bc):
    kmem_cache_alloc_noprof+0x3ab/0x630
    alloc_empty_file+0x5a/0x1e0
    alloc_file_pseudo+0x135/0x220
    __shmem_file_setup+0x274/0x420
    shmem_zero_setup_desc+0x9c/0x170
    mmap_zero_prepare+0x123/0x140
    __mmap_region+0xdda/0x2660
    mmap_region+0x2eb/0x3a0
    do_mmap+0xc79/0x1240
    vm_mmap_pgoff+0x252/0x4c0
    ksys_mmap_pgoff+0xf8/0x120
    __x64_sys_mmap+0x12a/0x190
    do_syscall_64+0xa9/0x580
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

Found by syzkaller.

Link: https://lkml.kernel.org/r/20260331180811.1333348-1-rhkrqnwk98@gmail.com
Fixes: 605f6586ecf7 ("mm/vma: do not leak memory when .mmap_prepare swaps the file")
Signed-off-by: Sechang Lim <rhkrqnwk98@gmail.com>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vma.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/vma.c b/mm/vma.c
index be64f781a3aa..c8df5f561ad7 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2781,6 +2781,13 @@ unacct_error:
 	if (map.charged)
 		vm_unacct_memory(map.charged);
 abort_munmap:
+	/*
+	 * This indicates that .mmap_prepare has set a new file, differing from
+	 * desc->vm_file. But since we're aborting the operation, only the
+	 * original file will be cleaned up. Ensure we clean up both.
+	 */
+	if (map.file_doesnt_need_get)
+		fput(map.file);
 	vms_abort_munmap_vmas(&map.vms, &map.mas_detach);
 	return error;
 }
-- 
cgit v1.2.3


From 4c04c6b47c361612b1d70cec8f7a60b1482d1400 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Thu, 2 Apr 2026 06:44:17 -0700
Subject: mm/damon/stat: deallocate damon_call() failure leaking damon_ctx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

damon_stat_start() always allocates the module's damon_ctx object
(damon_stat_context).  Meanwhile, if damon_call() in the function fails,
the damon_ctx object is not deallocated.  Hence, if the damon_call() is
failed, and the user writes Y to “enabled” again, the previously
allocated damon_ctx object is leaked.

This cannot simply be fixed by deallocating the damon_ctx object when
damon_call() fails.  That's because damon_call() failure doesn't guarantee
the kdamond main function, which accesses the damon_ctx object, is
completely finished.  In other words, if damon_stat_start() deallocates
the damon_ctx object after damon_call() failure, the not-yet-terminated
kdamond could access the freed memory (use-after-free).

Fix the leak while avoiding the use-after-free by keeping returning
damon_stat_start() without deallocating the damon_ctx object after
damon_call() failure, but deallocating it when the function is invoked
again and the kdamond is completely terminated.  If the kdamond is not yet
terminated, simply return -EAGAIN, as the kdamond will soon be terminated.

The issue was discovered [1] by sashiko.

Link: https://lkml.kernel.org/r/20260402134418.74121-1-sj@kernel.org
Link: https://lore.kernel.org/20260401012428.86694-1-sj@kernel.org [1]
Fixes: 405f61996d9d ("mm/damon/stat: use damon_call() repeat mode instead of damon_callback")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org> # 6.17.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/stat.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/damon/stat.c b/mm/damon/stat.c
index cf2c5a541eee..60351a719460 100644
--- a/mm/damon/stat.c
+++ b/mm/damon/stat.c
@@ -245,6 +245,12 @@ static int damon_stat_start(void)
 {
 	int err;
 
+	if (damon_stat_context) {
+		if (damon_is_running(damon_stat_context))
+			return -EAGAIN;
+		damon_destroy_ctx(damon_stat_context);
+	}
+
 	damon_stat_context = damon_stat_build_ctx();
 	if (!damon_stat_context)
 		return -ENOMEM;
@@ -261,6 +267,7 @@ static void damon_stat_stop(void)
 {
 	damon_stop(&damon_stat_context, 1);
 	damon_destroy_ctx(damon_stat_context);
+	damon_stat_context = NULL;
 }
 
 static int damon_stat_enabled_store(
-- 
cgit v1.2.3


From 7bc5da4842bed3252d26e742213741a4d0ac1b14 Mon Sep 17 00:00:00 2001
From: Joseph Qi <joseph.qi@linux.alibaba.com>
Date: Fri, 3 Apr 2026 14:38:30 +0800
Subject: ocfs2: fix out-of-bounds write in ocfs2_write_end_inline

KASAN reports a use-after-free write of 4086 bytes in
ocfs2_write_end_inline, called from ocfs2_write_end_nolock during a
copy_file_range splice fallback on a corrupted ocfs2 filesystem mounted on
a loop device.  The actual bug is an out-of-bounds write past the inode
block buffer, not a true use-after-free.  The write overflows into an
adjacent freed page, which KASAN reports as UAF.

The root cause is that ocfs2_try_to_write_inline_data trusts the on-disk
id_count field to determine whether a write fits in inline data.  On a
corrupted filesystem, id_count can exceed the physical maximum inline data
capacity, causing writes to overflow the inode block buffer.

Call trace (crash path):

   vfs_copy_file_range (fs/read_write.c:1634)
     do_splice_direct
       splice_direct_to_actor
         iter_file_splice_write
           ocfs2_file_write_iter
             generic_perform_write
               ocfs2_write_end
                 ocfs2_write_end_nolock (fs/ocfs2/aops.c:1949)
                   ocfs2_write_end_inline (fs/ocfs2/aops.c:1915)
                     memcpy_from_folio     <-- KASAN: write OOB

So add id_count upper bound check in ocfs2_validate_inode_block() to
alongside the existing i_size check to fix it.

Link: https://lkml.kernel.org/r/20260403063830.3662739-1-joseph.qi@linux.alibaba.com
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Reported-by: syzbot+62c1793956716ea8b28a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=62c1793956716ea8b28a
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Heming Zhao <heming.zhao@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/inode.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 03a51662ea8e..a2ccd8011706 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1505,6 +1505,16 @@ int ocfs2_validate_inode_block(struct super_block *sb,
 			goto bail;
 		}
 
+		if (le16_to_cpu(data->id_count) >
+		    ocfs2_max_inline_data_with_xattr(sb, di)) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode #%llu: inline data id_count %u exceeds max %d\n",
+					 (unsigned long long)bh->b_blocknr,
+					 le16_to_cpu(data->id_count),
+					 ocfs2_max_inline_data_with_xattr(sb, di));
+			goto bail;
+		}
+
 		if (le64_to_cpu(di->i_size) > le16_to_cpu(data->id_count)) {
 			rc = ocfs2_error(sb,
 					 "Invalid dinode #%llu: inline data i_size %llu exceeds id_count %u\n",
-- 
cgit v1.2.3


From 591478118293c1bd628de330a99eb1eb2ef8d76b Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Thu, 19 Mar 2026 14:13:33 -0700
Subject: idpf: fix PREEMPT_RT raw/bh spinlock nesting for async VC handling

Switch from using the completion's raw spinlock to a local lock in the
idpf_vc_xn struct. The conversion is safe because complete/_all() are
called outside the lock and there is no reason to share the completion
lock in the current logic. This avoids invalid wait context reported by
the kernel due to the async handler taking BH spinlock:

[  805.726977] =============================
[  805.726991] [ BUG: Invalid wait context ]
[  805.727006] 7.0.0-rc2-net-devq-031026+ #28 Tainted: G S         OE
[  805.727026] -----------------------------
[  805.727038] kworker/u261:0/572 is trying to lock:
[  805.727051] ff190da6a8dbb6a0 (&vport_config->mac_filter_list_lock){+...}-{3:3}, at: idpf_mac_filter_async_handler+0xe9/0x260 [idpf]
[  805.727099] other info that might help us debug this:
[  805.727111] context-{5:5}
[  805.727119] 3 locks held by kworker/u261:0/572:
[  805.727132]  #0: ff190da6db3e6148 ((wq_completion)idpf-0000:83:00.0-mbx){+.+.}-{0:0}, at: process_one_work+0x4b5/0x730
[  805.727163]  #1: ff3c6f0a6131fe50 ((work_completion)(&(&adapter->mbx_task)->work)){+.+.}-{0:0}, at: process_one_work+0x1e5/0x730
[  805.727191]  #2: ff190da765190020 (&x->wait#34){+.+.}-{2:2}, at: idpf_recv_mb_msg+0xc8/0x710 [idpf]
[  805.727218] stack backtrace:
...
[  805.727238] Workqueue: idpf-0000:83:00.0-mbx idpf_mbx_task [idpf]
[  805.727247] Call Trace:
[  805.727249]  <TASK>
[  805.727251]  dump_stack_lvl+0x77/0xb0
[  805.727259]  __lock_acquire+0xb3b/0x2290
[  805.727268]  ? __irq_work_queue_local+0x59/0x130
[  805.727275]  lock_acquire+0xc6/0x2f0
[  805.727277]  ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf]
[  805.727284]  ? _printk+0x5b/0x80
[  805.727290]  _raw_spin_lock_bh+0x38/0x50
[  805.727298]  ? idpf_mac_filter_async_handler+0xe9/0x260 [idpf]
[  805.727303]  idpf_mac_filter_async_handler+0xe9/0x260 [idpf]
[  805.727310]  idpf_recv_mb_msg+0x1c8/0x710 [idpf]
[  805.727317]  process_one_work+0x226/0x730
[  805.727322]  worker_thread+0x19e/0x340
[  805.727325]  ? __pfx_worker_thread+0x10/0x10
[  805.727328]  kthread+0xf4/0x130
[  805.727333]  ? __pfx_kthread+0x10/0x10
[  805.727336]  ret_from_fork+0x32c/0x410
[  805.727345]  ? __pfx_kthread+0x10/0x10
[  805.727347]  ret_from_fork_asm+0x1a/0x30
[  805.727354]  </TASK>

Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager")
Cc: stable@vger.kernel.org
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Ray Zhang <sgzhang@google.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 14 +++++---------
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.h |  5 +++--
 2 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 113ecfc16dd7..582e0c8e9dc0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -287,26 +287,21 @@ dma_mem_error:
 	return err;
 }
 
-/* API for virtchnl "transaction" support ("xn" for short).
- *
- * We are reusing the completion lock to serialize the accesses to the
- * transaction state for simplicity, but it could be its own separate synchro
- * as well. For now, this API is only used from within a workqueue context;
- * raw_spin_lock() is enough.
- */
+/* API for virtchnl "transaction" support ("xn" for short). */
+
 /**
  * idpf_vc_xn_lock - Request exclusive access to vc transaction
  * @xn: struct idpf_vc_xn* to access
  */
 #define idpf_vc_xn_lock(xn)			\
-	raw_spin_lock(&(xn)->completed.wait.lock)
+	spin_lock(&(xn)->lock)
 
 /**
  * idpf_vc_xn_unlock - Release exclusive access to vc transaction
  * @xn: struct idpf_vc_xn* to access
  */
 #define idpf_vc_xn_unlock(xn)		\
-	raw_spin_unlock(&(xn)->completed.wait.lock)
+	spin_unlock(&(xn)->lock)
 
 /**
  * idpf_vc_xn_release_bufs - Release reference to reply buffer(s) and
@@ -338,6 +333,7 @@ static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr)
 		xn->state = IDPF_VC_XN_IDLE;
 		xn->idx = i;
 		idpf_vc_xn_release_bufs(xn);
+		spin_lock_init(&xn->lock);
 		init_completion(&xn->completed);
 	}
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index fe065911ad5a..6876e3ed9d1b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -42,8 +42,8 @@ typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
  * struct idpf_vc_xn - Data structure representing virtchnl transactions
  * @completed: virtchnl event loop uses that to signal when a reply is
  *	       available, uses kernel completion API
- * @state: virtchnl event loop stores the data below, protected by the
- *	   completion's lock.
+ * @lock: protects the transaction state fields below
+ * @state: virtchnl event loop stores the data below, protected by @lock
  * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
  *	      truncated on its way to the receiver thread according to
  *	      reply_buf.iov_len.
@@ -58,6 +58,7 @@ typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
  */
 struct idpf_vc_xn {
 	struct completion completed;
+	spinlock_t lock;
 	enum idpf_vc_xn_state state;
 	size_t reply_sz;
 	struct kvec reply;
-- 
cgit v1.2.3


From d086fae65006368618104ba4c57779440eab2217 Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Thu, 19 Mar 2026 14:13:34 -0700
Subject: idpf: improve locking around idpf_vc_xn_push_free()

Protect the set_bit() operation for the free_xn bitmask in
idpf_vc_xn_push_free(), to make the locking consistent with rest of the
code and avoid potential races in that logic.

Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager")
Cc: stable@vger.kernel.org
Reported-by: Ray Zhang <sgzhang@google.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 582e0c8e9dc0..fbd5a15b015c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -402,7 +402,9 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr,
 				 struct idpf_vc_xn *xn)
 {
 	idpf_vc_xn_release_bufs(xn);
+	spin_lock_bh(&vcxn_mngr->xn_bm_lock);
 	set_bit(xn->idx, vcxn_mngr->free_xn_bm);
+	spin_unlock_bh(&vcxn_mngr->xn_bm_lock);
 }
 
 /**
-- 
cgit v1.2.3


From 8e2a2420e267a515f6db56a6e9570b5cacd92919 Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Thu, 19 Mar 2026 14:13:35 -0700
Subject: idpf: set the payload size before calling the async handler

Set the payload size before forwarding the reply to the async handler.
Without this, xn->reply_sz will be 0 and idpf_mac_filter_async_handler()
will never get past the size check.

Fixes: 34c21fa894a1 ("idpf: implement virtchnl transaction manager")
Cc: stable@vger.kernel.org
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Li Li <boolli@google.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index fbd5a15b015c..be66f9b2e101 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -615,6 +615,10 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter,
 		err = -ENXIO;
 		goto out_unlock;
 	case IDPF_VC_XN_ASYNC:
+		/* Set reply_sz from the actual payload so that async_handler
+		 * can evaluate the response.
+		 */
+		xn->reply_sz = ctlq_msg->data_len;
 		err = idpf_vc_xn_forward_async(adapter, xn, ctlq_msg);
 		idpf_vc_xn_unlock(xn);
 		return err;
-- 
cgit v1.2.3


From bb3f21edc7056cdf44a7f7bd7ba65af40741838c Mon Sep 17 00:00:00 2001
From: Kohei Enju <kohei@enjuk.jp>
Date: Sun, 1 Feb 2026 14:14:00 +0000
Subject: ice: ptp: don't WARN when controlling PF is unavailable

In VFIO passthrough setups, it is possible to pass through only a PF
which doesn't own the source timer. In that case the PTP controlling PF
(adapter->ctrl_pf) is never initialized in the VM, so ice_get_ctrl_ptp()
returns NULL and triggers WARN_ON() in ice_ptp_setup_pf().

Since this is an expected behavior in that configuration, replace
WARN_ON() with an informational message and return -EOPNOTSUPP.

Fixes: e800654e85b5 ("ice: Use ice_adapter for PTP shared data instead of auxdev")
Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 094e96219f45..a3c5f0a5e09b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -3080,7 +3080,13 @@ static int ice_ptp_setup_pf(struct ice_pf *pf)
 	struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf);
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN)
+	if (!ctrl_ptp) {
+		dev_info(ice_pf_to_dev(pf),
+			 "PTP unavailable: no controlling PF\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (pf->hw.mac_type == ICE_MAC_UNKNOWN)
 		return -ENODEV;
 
 	INIT_LIST_HEAD(&ptp->port.list_node);
-- 
cgit v1.2.3


From bf6dbadb72b997721e9b67348652926c076878d1 Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Fri, 27 Mar 2026 08:46:58 +0100
Subject: ice: fix PTP timestamping broken by SyncE code on E825C

The E825C SyncE support added in commit ad1df4f2d591 ("ice: dpll:
Support E825-C SyncE and dynamic pin discovery") introduced a SyncE
reconfiguration block in ice_ptp_link_change() that prevents
ice_ptp_port_phy_restart() from being called in several error paths.
Without the PHY restart, PTP timestamps stop working after any link
change event.

There are three ways the PHY restart gets blocked:

1. When DPLL initialization fails (e.g. missing ACPI firmware node
   properties), ICE_FLAG_DPLL is not set and the function returns early
   before reaching the PHY restart.

2. When ice_tspll_bypass_mux_active_e825c() fails to read the CGU
   register, WARN_ON_ONCE fires and the function returns early.

3. When ice_tspll_cfg_synce_ethdiv_e825c() fails to configure the
   clock divider for an active pin, same early return.

SyncE and PTP are independent features. SyncE reconfiguration failures
must not prevent the PTP PHY restart that is essential for timestamp
recovery after link changes.

Fix by making the entire SyncE block conditional on ICE_FLAG_DPLL
without an early return, and replacing the WARN_ON_ONCE + return error
handling inside the loop with dev_err_once + break. The function always
proceeds to ice_ptp_port_phy_restart() regardless of SyncE errors.

Fixes: ad1df4f2d591 ("ice: dpll: Support E825-C SyncE and dynamic pin discovery")
Signed-off-by: Petr Oros <poros@redhat.com>
Reviewed-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Sunitha Mekala <sunithax.d.mekala@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index a3c5f0a5e09b..6cb0cf7a9891 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1296,12 +1296,10 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 	if (pf->hw.reset_ongoing)
 		return;
 
-	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) {
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 &&
+	    test_bit(ICE_FLAG_DPLL, pf->flags)) {
 		int pin, err;
 
-		if (!test_bit(ICE_FLAG_DPLL, pf->flags))
-			return;
-
 		mutex_lock(&pf->dplls.lock);
 		for (pin = 0; pin < ICE_SYNCE_CLK_NUM; pin++) {
 			enum ice_synce_clk clk_pin;
@@ -1314,15 +1312,19 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 								port_num,
 								&active,
 								clk_pin);
-			if (WARN_ON_ONCE(err)) {
-				mutex_unlock(&pf->dplls.lock);
-				return;
+			if (err) {
+				dev_err_once(ice_pf_to_dev(pf),
+					     "Failed to read SyncE bypass mux for pin %d, err %d\n",
+					     pin, err);
+				break;
 			}
 
 			err = ice_tspll_cfg_synce_ethdiv_e825c(hw, clk_pin);
-			if (active && WARN_ON_ONCE(err)) {
-				mutex_unlock(&pf->dplls.lock);
-				return;
+			if (active && err) {
+				dev_err_once(ice_pf_to_dev(pf),
+					     "Failed to configure SyncE ETH divider for pin %d, err %d\n",
+					     pin, err);
+				break;
 			}
 		}
 		mutex_unlock(&pf->dplls.lock);
-- 
cgit v1.2.3


From d8ae40dc20cbd7bb6e6b36a928e2db2296060ad2 Mon Sep 17 00:00:00 2001
From: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Date: Wed, 4 Mar 2026 09:42:32 +0100
Subject: ixgbe: stop re-reading flash on every get_drvinfo for e610

ixgbe_get_drvinfo() calls ixgbe_refresh_fw_version() on every ethtool
query for e610 adapters.  That ends up in ixgbe_discover_flash_size(),
which bisects the full 16 MB NVM space issuing one ACI command per
step (~20 ms each, ~24 steps total = ~500 ms).

Profiling on an idle E610-XAT2 system with telegraf scraping ethtool
stats every 10 seconds:

  kretprobe:ixgbe_get_drvinfo took 527603 us
  kretprobe:ixgbe_get_drvinfo took 523978 us
  kretprobe:ixgbe_get_drvinfo took 552975 us
  kretprobe:ice_get_drvinfo   took       3 us
  kretprobe:igb_get_drvinfo   took       2 us
  kretprobe:i40e_get_drvinfo  took       5 us

The half-second stall happens under the RTNL lock, causing visible
latency on ip-link and friends.

The FW version can only change after an EMPR reset.  All flash data is
already populated at probe time and the cached adapter->eeprom_id is
what get_drvinfo should be returning.  The only place that needs to
trigger a re-read is ixgbe_devlink_reload_empr_finish(), right after
the EMPR completes and new firmware is running.  Additionally, refresh
the FW version in ixgbe_reinit_locked() so that any PF that undergoes a
reinit after an EMPR (e.g. triggered by another PF's devlink reload)
also picks up the new version in adapter->eeprom_id.

ixgbe_devlink_info_get() keeps its refresh call for explicit
"devlink dev info" queries, which is fine given those are user-initiated.

Fixes: c9e563cae19e ("ixgbe: add support for devlink reload")
Co-developed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/devlink/devlink.c |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe.h           |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c   | 13 +++++++------
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      | 10 ++++++++++
 4 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
index b0404f37271a..cf8908b82f8a 100644
--- a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c
@@ -474,7 +474,7 @@ static int ixgbe_devlink_reload_empr_finish(struct devlink *devlink,
 	adapter->flags2 &= ~(IXGBE_FLAG2_API_MISMATCH |
 			     IXGBE_FLAG2_FW_ROLLBACK);
 
-	return 0;
+	return ixgbe_refresh_fw_version(adapter);
 }
 
 static const struct devlink_ops ixgbe_devlink_ops = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index dce4936708eb..047f04045585 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -973,7 +973,7 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 			 u16 subdevice_id);
 void ixgbe_set_fw_version_e610(struct ixgbe_adapter *adapter);
-void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter);
+int ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter);
 #ifdef CONFIG_PCI_IOV
 void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter);
 #endif
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 56aabaa5caec..ba049b3a9609 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1155,12 +1155,17 @@ err:
 	return ret_val;
 }
 
-void ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter)
+int ixgbe_refresh_fw_version(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
+	int err;
+
+	err = ixgbe_get_flash_data(hw);
+	if (err)
+		return err;
 
-	ixgbe_get_flash_data(hw);
 	ixgbe_set_fw_version_e610(adapter);
+	return 0;
 }
 
 static void ixgbe_get_drvinfo(struct net_device *netdev,
@@ -1168,10 +1173,6 @@ static void ixgbe_get_drvinfo(struct net_device *netdev,
 {
 	struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
 
-	/* need to refresh info for e610 in case fw reloads in runtime */
-	if (adapter->hw.mac.type == ixgbe_mac_e610)
-		ixgbe_refresh_fw_version(adapter);
-
 	strscpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
 
 	strscpy(drvinfo->fw_version, adapter->eeprom_id,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e4101c59074d..59801187a839 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6289,6 +6289,16 @@ void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
 		msleep(2000);
 	ixgbe_up(adapter);
+
+	/* E610 has no FW event to notify all PFs of an EMPR reset, so
+	 * refresh the FW version here to pick up any new FW version after
+	 * a hardware reset (e.g. EMPR triggered by another PF's devlink
+	 * reload).  ixgbe_refresh_fw_version() updates both hw->flash and
+	 * adapter->eeprom_id so ethtool -i reports the correct string.
+	 */
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		(void)ixgbe_refresh_fw_version(adapter);
+
 	clear_bit(__IXGBE_RESETTING, &adapter->state);
 }
 
-- 
cgit v1.2.3


From 4821d563cd7f251ae728be1a6d04af82a294a5b9 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Fri, 13 Mar 2026 09:22:29 +0100
Subject: ixgbevf: add missing negotiate_features op to Hyper-V ops table

Commit a7075f501bd3 ("ixgbevf: fix mailbox API compatibility by
negotiating supported features") added the .negotiate_features callback
to ixgbe_mac_operations and populated it in ixgbevf_mac_ops, but forgot
to add it to ixgbevf_hv_mac_ops. This leaves the function pointer NULL
on Hyper-V VMs.

During probe, ixgbevf_negotiate_api() calls ixgbevf_set_features(),
which unconditionally dereferences hw->mac.ops.negotiate_features().
On Hyper-V this results in a NULL pointer dereference:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  [...]
  Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine [...]
  Workqueue: events work_for_cpu_fn
  RIP: 0010:0x0
  [...]
  Call Trace:
   ixgbevf_negotiate_api+0x66/0x160 [ixgbevf]
   ixgbevf_sw_init+0xe4/0x1f0 [ixgbevf]
   ixgbevf_probe+0x20f/0x4a0 [ixgbevf]
   local_pci_probe+0x50/0xa0
   work_for_cpu_fn+0x1a/0x30
   [...]

Add ixgbevf_hv_negotiate_features_vf() that returns -EOPNOTSUPP and
wire it into ixgbevf_hv_mac_ops. The caller already handles -EOPNOTSUPP
gracefully.

Fixes: a7075f501bd3 ("ixgbevf: fix mailbox API compatibility by negotiating supported features")
Reported-by: Xiaoqiang Xiong <xxiong@redhat.com>
Closes: https://issues.redhat.com/browse/RHEL-155455
Assisted-by: Claude:claude-4.6-opus-high Cursor
Tested-by: Xiaoqiang Xiong <xxiong@redhat.com>
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbevf/vf.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index b67b580f7f1c..f6df86d124b9 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -709,6 +709,12 @@ static int ixgbevf_negotiate_features_vf(struct ixgbe_hw *hw, u32 *pf_features)
 	return err;
 }
 
+static int ixgbevf_hv_negotiate_features_vf(struct ixgbe_hw *hw,
+					    u32 *pf_features)
+{
+	return -EOPNOTSUPP;
+}
+
 /**
  *  ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address
  *  @hw: pointer to the HW structure
@@ -1142,6 +1148,7 @@ static const struct ixgbe_mac_operations ixgbevf_hv_mac_ops = {
 	.setup_link		= ixgbevf_setup_mac_link_vf,
 	.check_link		= ixgbevf_hv_check_mac_link_vf,
 	.negotiate_api_version	= ixgbevf_hv_negotiate_api_version_vf,
+	.negotiate_features	= ixgbevf_hv_negotiate_features_vf,
 	.set_rar		= ixgbevf_hv_set_rar_vf,
 	.update_mc_addr_list	= ixgbevf_hv_update_mc_addr_list_vf,
 	.update_xcast_mode	= ixgbevf_hv_update_xcast_mode,
-- 
cgit v1.2.3


From b1e067240379f950a0022208e0685f3465c211cb Mon Sep 17 00:00:00 2001
From: Alex Dvoretsky <advoretsky@gmail.com>
Date: Thu, 12 Mar 2026 14:52:55 +0100
Subject: igb: remove napi_synchronize() in igb_down()

When an AF_XDP zero-copy application terminates abruptly (e.g., kill -9),
the XSK buffer pool is destroyed but NAPI polling continues.
igb_clean_rx_irq_zc() repeatedly returns the full budget, preventing
napi_complete_done() from clearing NAPI_STATE_SCHED.

igb_down() calls napi_synchronize() before napi_disable() for each queue
vector. napi_synchronize() spins waiting for NAPI_STATE_SCHED to clear,
which never happens. igb_down() blocks indefinitely, the TX watchdog
fires, and the TX queue remains permanently stalled.

napi_disable() already handles this correctly: it sets NAPI_STATE_DISABLE.
After a full-budget poll, __napi_poll() checks napi_disable_pending(). If
set, it forces completion and clears NAPI_STATE_SCHED, breaking the loop
that napi_synchronize() cannot.

napi_synchronize() was added in commit 41f149a285da ("igb: Fix possible
panic caused by Rx traffic arrival while interface is down").
napi_disable() provides stronger guarantees: it prevents further
scheduling and waits for any active poll to exit.
Other Intel drivers (ixgbe, ice, i40e) use napi_disable() without a
preceding napi_synchronize() in their down paths.

Remove redundant napi_synchronize() call and reorder napi_disable()
before igb_set_queue_napi() so the queue-to-NAPI mapping is only
cleared after polling has fully stopped.

Fixes: 2c6196013f84 ("igb: Add AF_XDP zero-copy Rx support")
Cc: stable@vger.kernel.org
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Alex Dvoretsky <advoretsky@gmail.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ee99fd8fd513..ce91dda00ec0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2203,9 +2203,8 @@ void igb_down(struct igb_adapter *adapter)
 
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
-			napi_synchronize(&adapter->q_vector[i]->napi);
-			igb_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
+			igb_set_queue_napi(adapter, i, NULL);
 		}
 	}
 
-- 
cgit v1.2.3


From d3baa34a470771399c1495bc04b1e26ac15d598e Mon Sep 17 00:00:00 2001
From: Agalakov Daniil <ade@amicon.ru>
Date: Wed, 18 Mar 2026 15:05:05 +0300
Subject: e1000: check return value of e1000_read_eeprom

[Why]
e1000_set_eeprom() performs a read-modify-write operation when the write
range is not word-aligned. This requires reading the first and last words
of the range from the EEPROM to preserve the unmodified bytes.

However, the code does not check the return value of e1000_read_eeprom().
If the read fails, the operation continues using uninitialized data from
eeprom_buff. This results in corrupted data being written back to the
EEPROM for the boundary words.

Add the missing error checks and abort the operation if reading fails.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Co-developed-by: Iskhakov Daniil <dish@amicon.ru>
Signed-off-by: Iskhakov Daniil <dish@amicon.ru>
Signed-off-by: Agalakov Daniil <ade@amicon.ru>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index ab232b3fbbd0..4dcbeabb3ad2 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -496,14 +496,19 @@ static int e1000_set_eeprom(struct net_device *netdev,
 		 */
 		ret_val = e1000_read_eeprom(hw, first_word, 1,
 					    &eeprom_buff[0]);
+		if (ret_val)
+			goto out;
+
 		ptr++;
 	}
-	if (((eeprom->offset + eeprom->len) & 1) && (ret_val == 0)) {
+	if ((eeprom->offset + eeprom->len) & 1) {
 		/* need read/modify/write of last changed EEPROM word
 		 * only the first byte of the word is being modified
 		 */
 		ret_val = e1000_read_eeprom(hw, last_word, 1,
 					    &eeprom_buff[last_word - first_word]);
+		if (ret_val)
+			goto out;
 	}
 
 	/* Device's eeprom is always little-endian, word addressable */
@@ -522,6 +527,7 @@ static int e1000_set_eeprom(struct net_device *netdev,
 	if ((ret_val == 0) && (first_word <= EEPROM_CHECKSUM_REG))
 		e1000_update_eeprom_checksum(hw);
 
+out:
 	kfree(eeprom_buff);
 	return ret_val;
 }
-- 
cgit v1.2.3


From a315e022a72d95ef5f1d4e58e903cb492b0ad931 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:51 +0200
Subject: xsk: tighten UMEM headroom validation to account for tailroom and min
 frame
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current headroom validation in xdp_umem_reg() could leave us with
insufficient space dedicated to even receive minimum-sized ethernet
frame. Furthermore if multi-buffer would come to play then
skb_shared_info stored at the end of XSK frame would be corrupted.

HW typically works with 128-aligned sizes so let us provide this value
as bare minimum.

Multi-buffer setting is known later in the configuration process so
besides accounting for 128 bytes, let us also take care of tailroom space
upfront.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Fixes: 99e3a236dd43 ("xsk: Add missing check on user supplied headroom size")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-2-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xdp/xdp_umem.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 066ce07c506d..58da2f4f4397 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -203,7 +203,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (!unaligned_chunks && chunks_rem)
 		return -EINVAL;
 
-	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
+	if (headroom > chunk_size - XDP_PACKET_HEADROOM -
+		       SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - 128)
 		return -EINVAL;
 
 	if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
-- 
cgit v1.2.3


From 1ee1605138fc94cc8f8f273321dd2471c64977f9 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:52 +0200
Subject: xsk: respect tailroom for ZC setups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Multi-buffer XDP stores information about frags in skb_shared_info that
sits at the tailroom of a packet. The storage space is reserved via
xdp_data_hard_end():

	((xdp)->data_hard_start + (xdp)->frame_sz -	\
	 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))

and then we refer to it via macro below:

static inline struct skb_shared_info *
xdp_get_shared_info_from_buff(const struct xdp_buff *xdp)
{
        return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}

Currently we do not respect this tailroom space in multi-buffer AF_XDP
ZC scenario. To address this, introduce xsk_pool_get_tailroom() and use
it within xsk_pool_get_rx_frame_size() which is used in ZC drivers to
configure length of HW Rx buffer.

Typically drivers on Rx Hw buffers side work on 128 byte alignment so
let us align the value returned by xsk_pool_get_rx_frame_size() in order
to avoid addressing this on driver's side. This addresses the fact that
idpf uses mentioned function *before* pool->dev being set so we were at
risk that after subtracting tailroom we would not provide 128-byte
aligned value to HW.

Since xsk_pool_get_rx_frame_size() is actively used in xsk_rcv_check()
and __xsk_rcv(), add a variant of this routine that will not include 128
byte alignment and therefore old behavior is preserved.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-3-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 23 ++++++++++++++++++++++-
 net/xdp/xsk.c              |  4 ++--
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 6b9ebae2dc95..46797645a0c2 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -41,16 +41,37 @@ static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
 	return XDP_PACKET_HEADROOM + pool->headroom;
 }
 
+static inline u32 xsk_pool_get_tailroom(bool mbuf)
+{
+	return mbuf ? SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : 0;
+}
+
 static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
 {
 	return pool->chunk_size;
 }
 
-static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
+static inline u32 __xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 {
 	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
+{
+	u32 frame_size =  __xsk_pool_get_rx_frame_size(pool);
+	struct xdp_umem *umem = pool->umem;
+	bool mbuf;
+
+	/* Reserve tailroom only for zero-copy pools that opted into
+	 * multi-buffer. The reserved area is used for skb_shared_info,
+	 * matching the XDP core's xdp_data_hard_end() layout.
+	 */
+	mbuf = pool->dev && (umem->flags & XDP_UMEM_SG_FLAG);
+	frame_size -= xsk_pool_get_tailroom(mbuf);
+
+	return ALIGN_DOWN(frame_size, 128);
+}
+
 static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool)
 {
 	return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 6149f6a79897..c8ef9e427c9c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -239,7 +239,7 @@ static u32 xsk_copy_xdp(void *to, void **from, u32 to_len,
 
 static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
-	u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool);
+	u32 frame_size = __xsk_pool_get_rx_frame_size(xs->pool);
 	void *copy_from = xsk_copy_xdp_start(xdp), *copy_to;
 	u32 from_len, meta_len, rem, num_desc;
 	struct xdp_buff_xsk *xskb;
@@ -338,7 +338,7 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
-	if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
+	if (len > __xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}
-- 
cgit v1.2.3


From 93e84fe45b752d17a5a46b306ed78f0133bbc719 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:53 +0200
Subject: xsk: fix XDP_UMEM_SG_FLAG issues
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently xp_assign_dev_shared() is missing XDP_USE_SG being propagated
to flags so set it in order to preserve mtu check that is supposed to be
done only when no multi-buffer setup is in picture.

Also, this flag has the same value as XDP_UMEM_TX_SW_CSUM so we could
get unexpected SG setups for software Tx checksums. Since csum flag is
UAPI, modify value of XDP_UMEM_SG_FLAG.

Fixes: d609f3d228a8 ("xsk: add multi-buffer support for sockets sharing umem")
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-4-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock.h  | 2 +-
 net/xdp/xsk_buff_pool.c | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 23e8861e8b25..ebac60a3d8a1 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -14,7 +14,7 @@
 #include <linux/mm.h>
 #include <net/sock.h>
 
-#define XDP_UMEM_SG_FLAG (1 << 1)
+#define XDP_UMEM_SG_FLAG BIT(3)
 
 struct net_device;
 struct xsk_queue;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 37b7a68b89b3..729602a3cec0 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -247,6 +247,10 @@ int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
 	struct xdp_umem *umem = umem_xs->umem;
 
 	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
+
+	if (umem->flags & XDP_UMEM_SG_FLAG)
+		flags |= XDP_USE_SG;
+
 	if (umem_xs->pool->uses_need_wakeup)
 		flags |= XDP_USE_NEED_WAKEUP;
 
-- 
cgit v1.2.3


From 36ee60b569ba0dfb6f961333b90d19ab5b323fa9 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:54 +0200
Subject: xsk: validate MTU against usable frame size on bind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AF_XDP bind currently accepts zero-copy pool configurations without
verifying that the device MTU fits into the usable frame space provided
by the UMEM chunk.

This becomes a problem since we started to respect tailroom which is
subtracted from chunk_size (among with headroom). 2k chunk size might
not provide enough space for standard 1500 MTU, so let us catch such
settings at bind time. Furthermore, validate whether underlying HW will
be able to satisfy configured MTU wrt XSK's frame size multiplied by
supported Rx buffer chain length (that is exposed via
net_device::xdp_zc_max_segs).

Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-5-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xdp/xsk_buff_pool.c | 28 +++++++++++++++++++++++++---
 1 file changed, 25 insertions(+), 3 deletions(-)

diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 729602a3cec0..cd7bc50872f6 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -10,6 +10,8 @@
 #include "xdp_umem.h"
 #include "xsk.h"
 
+#define ETH_PAD_LEN (ETH_HLEN + 2 * VLAN_HLEN  + ETH_FCS_LEN)
+
 void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 {
 	if (!xs->tx)
@@ -157,8 +159,12 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 int xp_assign_dev(struct xsk_buff_pool *pool,
 		  struct net_device *netdev, u16 queue_id, u16 flags)
 {
+	u32 needed = netdev->mtu + ETH_PAD_LEN;
+	u32 segs = netdev->xdp_zc_max_segs;
+	bool mbuf = flags & XDP_USE_SG;
 	bool force_zc, force_copy;
 	struct netdev_bpf bpf;
+	u32 frame_size;
 	int err = 0;
 
 	ASSERT_RTNL();
@@ -178,7 +184,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 	if (err)
 		return err;
 
-	if (flags & XDP_USE_SG)
+	if (mbuf)
 		pool->umem->flags |= XDP_UMEM_SG_FLAG;
 
 	if (flags & XDP_USE_NEED_WAKEUP)
@@ -200,8 +206,24 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 		goto err_unreg_pool;
 	}
 
-	if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) {
-		err = -EOPNOTSUPP;
+	if (mbuf) {
+		if (segs == 1) {
+			err = -EOPNOTSUPP;
+			goto err_unreg_pool;
+		}
+	} else {
+		segs = 1;
+	}
+
+	/* open-code xsk_pool_get_rx_frame_size() as pool->dev is not
+	 * set yet at this point; we are before getting down to driver
+	 */
+	frame_size = __xsk_pool_get_rx_frame_size(pool) -
+		     xsk_pool_get_tailroom(mbuf);
+	frame_size = ALIGN_DOWN(frame_size, 128);
+
+	if (needed > frame_size * segs) {
+		err = -EINVAL;
 		goto err_unreg_pool;
 	}
 
-- 
cgit v1.2.3


From c5866a6be47207b05c6eead6292c8551c8a91669 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:55 +0200
Subject: selftests: bpf: introduce a common routine for reading procfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parametrize current way of getting MAX_SKB_FRAGS value from {sys,proc}fs
so that it can be re-used to get cache line size of system's CPU. All
that just to mimic and compute size of kernel's struct skb_shared_info
which for xsk and test suite interpret as tailroom.

Introduce two variables to ifobject struct that will carry count of skb
frags and tailroom size. Do the reading and computing once, at the
beginning of test suite execution in xskxceiver, but for test_progs such
way is not possible as in this environment each test setups and torns
down ifobject structs.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-6-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/test_xsk.c | 25 +----------------------
 tools/testing/selftests/bpf/prog_tests/test_xsk.h | 23 +++++++++++++++++++++
 tools/testing/selftests/bpf/prog_tests/xsk.c      | 19 +++++++++++++++++
 tools/testing/selftests/bpf/xskxceiver.c          | 23 +++++++++++++++++++++
 4 files changed, 66 insertions(+), 24 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index 7e38ec6e656b..62118ffba661 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -179,25 +179,6 @@ int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem
 	return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg);
 }
 
-#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags"
-static unsigned int get_max_skb_frags(void)
-{
-	unsigned int max_skb_frags = 0;
-	FILE *file;
-
-	file = fopen(MAX_SKB_FRAGS_PATH, "r");
-	if (!file) {
-		ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH);
-		return 0;
-	}
-
-	if (fscanf(file, "%u", &max_skb_frags) != 1)
-		ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH);
-
-	fclose(file);
-	return max_skb_frags;
-}
-
 static int set_ring_size(struct ifobject *ifobj)
 {
 	int ret;
@@ -2242,11 +2223,7 @@ int testapp_too_many_frags(struct test_spec *test)
 	if (test->mode == TEST_MODE_ZC) {
 		max_frags = test->ifobj_tx->xdp_zc_max_segs;
 	} else {
-		max_frags = get_max_skb_frags();
-		if (!max_frags) {
-			ksft_print_msg("Can't get MAX_SKB_FRAGS from system, using default (17)\n");
-			max_frags = 17;
-		}
+		max_frags = test->ifobj_tx->max_skb_frags;
 		max_frags += 1;
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.h b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
index 8fc78a057de0..1ab8aee4ce56 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.h
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
@@ -31,6 +31,9 @@
 #define SOCK_RECONF_CTR			10
 #define USLEEP_MAX			10000
 
+#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags"
+#define SMP_CACHE_BYTES_PATH "/sys/devices/system/cpu/cpu0/cache/index0/coherency_line_size"
+
 extern bool opt_verbose;
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
 
@@ -45,6 +48,24 @@ static inline u64 ceil_u64(u64 a, u64 b)
 	return (a + b - 1) / b;
 }
 
+static inline unsigned int read_procfs_val(const char *path)
+{
+	unsigned int read_val = 0;
+	FILE *file;
+
+	file = fopen(path, "r");
+	if (!file) {
+		ksft_print_msg("Error opening %s\n", path);
+		return 0;
+	}
+
+	if (fscanf(file, "%u", &read_val) != 1)
+		ksft_print_msg("Error reading %s\n", path);
+
+	fclose(file);
+	return read_val;
+}
+
 /* Simple test */
 enum test_mode {
 	TEST_MODE_SKB,
@@ -115,6 +136,8 @@ struct ifobject {
 	int mtu;
 	u32 bind_flags;
 	u32 xdp_zc_max_segs;
+	u32 umem_tailroom;
+	u32 max_skb_frags;
 	bool tx_on;
 	bool rx_on;
 	bool use_poll;
diff --git a/tools/testing/selftests/bpf/prog_tests/xsk.c b/tools/testing/selftests/bpf/prog_tests/xsk.c
index dd4c35c0e428..6e2f63ee2a6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/xsk.c
@@ -62,6 +62,7 @@ int configure_ifobj(struct ifobject *tx, struct ifobject *rx)
 
 static void test_xsk(const struct test_spec *test_to_run, enum test_mode mode)
 {
+	u32 max_frags, umem_tailroom, cache_line_size;
 	struct ifobject *ifobj_tx, *ifobj_rx;
 	struct test_spec test;
 	int ret;
@@ -84,6 +85,24 @@ static void test_xsk(const struct test_spec *test_to_run, enum test_mode mode)
 		ifobj_tx->set_ring.default_rx = ifobj_tx->ring.rx_pending;
 	}
 
+	cache_line_size = read_procfs_val(SMP_CACHE_BYTES_PATH);
+	if (!cache_line_size)
+		cache_line_size = 64;
+
+	max_frags = read_procfs_val(MAX_SKB_FRAGS_PATH);
+	if (!max_frags)
+		max_frags = 17;
+
+	ifobj_tx->max_skb_frags = max_frags;
+	ifobj_rx->max_skb_frags = max_frags;
+
+	/* 48 bytes is a part of skb_shared_info w/o frags array;
+	 * 16 bytes is sizeof(skb_frag_t)
+	 */
+	umem_tailroom = ALIGN(48 + (max_frags * 16), cache_line_size);
+	ifobj_tx->umem_tailroom = umem_tailroom;
+	ifobj_rx->umem_tailroom = umem_tailroom;
+
 	if (!ASSERT_OK(init_iface(ifobj_rx, worker_testapp_validate_rx), "init RX"))
 		goto delete_rx;
 	if (!ASSERT_OK(init_iface(ifobj_tx, worker_testapp_validate_tx), "init TX"))
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 05b3cebc5ca9..7dad8556a722 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -80,6 +80,7 @@
 #include <linux/mman.h>
 #include <linux/netdev.h>
 #include <linux/ethtool.h>
+#include <linux/align.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <locale.h>
@@ -333,6 +334,7 @@ static void print_tests(void)
 int main(int argc, char **argv)
 {
 	const size_t total_tests = ARRAY_SIZE(tests) + ARRAY_SIZE(ci_skip_tests);
+	u32 cache_line_size, max_frags, umem_tailroom;
 	struct pkt_stream *rx_pkt_stream_default;
 	struct pkt_stream *tx_pkt_stream_default;
 	struct ifobject *ifobj_tx, *ifobj_rx;
@@ -354,6 +356,27 @@ int main(int argc, char **argv)
 
 	setlocale(LC_ALL, "");
 
+	cache_line_size = read_procfs_val(SMP_CACHE_BYTES_PATH);
+	if (!cache_line_size) {
+		ksft_print_msg("Can't get SMP_CACHE_BYTES from system, using default (64)\n");
+		cache_line_size = 64;
+	}
+
+	max_frags = read_procfs_val(MAX_SKB_FRAGS_PATH);
+	if (!max_frags) {
+		ksft_print_msg("Can't get MAX_SKB_FRAGS from system, using default (17)\n");
+		max_frags = 17;
+	}
+	ifobj_tx->max_skb_frags = max_frags;
+	ifobj_rx->max_skb_frags = max_frags;
+
+	/* 48 bytes is a part of skb_shared_info w/o frags array;
+	 * 16 bytes is sizeof(skb_frag_t)
+	 */
+	umem_tailroom = ALIGN(48 + (max_frags * 16), cache_line_size);
+	ifobj_tx->umem_tailroom = umem_tailroom;
+	ifobj_rx->umem_tailroom = umem_tailroom;
+
 	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
 
 	if (opt_print_tests) {
-- 
cgit v1.2.3


From 3197c51ce2fa00410f86f4829e4f9223553632f6 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:56 +0200
Subject: selftests: bpf: fix pkt grow tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Skip tail adjust tests in xskxceiver for SKB mode as it is not very
friendly for it. multi-buffer case does not work as xdp_rxq_info that is
registered for generic XDP does not report ::frag_size. The non-mbuf
path copies packet via skb_pp_cow_data() which only accounts for
headroom, leaving us with no tailroom and causing underlying XDP prog to
drop packets therefore.

For multi-buffer test on other modes, change the amount of bytes we use
for growth, assume worst-case scenario and take care of headroom and
tailroom.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-7-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/test_xsk.c | 24 ++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index 62118ffba661..ee60bcc22ee4 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -2528,16 +2528,34 @@ int testapp_adjust_tail_shrink_mb(struct test_spec *test)
 
 int testapp_adjust_tail_grow(struct test_spec *test)
 {
+	if (test->mode == TEST_MODE_SKB)
+		return TEST_SKIP;
+
 	/* Grow by 4 bytes for testing purpose */
 	return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2);
 }
 
 int testapp_adjust_tail_grow_mb(struct test_spec *test)
 {
+	u32 grow_size;
+
+	if (test->mode == TEST_MODE_SKB)
+		return TEST_SKIP;
+
+	/* worst case scenario is when underlying setup will work on 3k
+	 * buffers, let us account for it; given that we will use 6k as
+	 * pkt_len, expect that it will be broken down to 2 descs each
+	 * with 3k payload;
+	 *
+	 * 4k is truesize, 3k payload, 256 HR, 320 TR;
+	 */
+	grow_size = XSK_UMEM__MAX_FRAME_SIZE -
+		    XSK_UMEM__LARGE_FRAME_SIZE -
+		    XDP_PACKET_HEADROOM -
+		    test->ifobj_tx->umem_tailroom;
 	test->mtu = MAX_ETH_JUMBO_SIZE;
-	/* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */
-	return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1,
-				   XSK_UMEM__LARGE_FRAME_SIZE * 2);
+
+	return testapp_adjust_tail(test, grow_size, XSK_UMEM__LARGE_FRAME_SIZE * 2);
 }
 
 int testapp_tx_queue_consumer(struct test_spec *test)
-- 
cgit v1.2.3


From 16546954e117e65661109e788682891b15d4e3ce Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:57 +0200
Subject: selftests: bpf: have a separate variable for drop test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently two different XDP programs share a static variable for
different purposes (picking where to redirect on shared umem test &
whether to drop a packet). This can be a problem when running full test
suite - idx can be written by shared umem test and this value can cause
a false behavior within XDP drop half test.

Introduce a dedicated variable for drop half test so that these two
don't step on each other toes. There is no real need for using
__sync_fetch_and_add here as XSK tests are executed on single CPU.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-8-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/bpf/progs/xsk_xdp_progs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
index 683306db8594..023d8befd4ca 100644
--- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -26,8 +26,10 @@ SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp)
 
 SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp)
 {
+	static unsigned int drop_idx;
+
 	/* Drop every other packet */
-	if (idx++ % 2)
+	if (drop_idx++ % 2)
 		return XDP_DROP;
 
 	return bpf_redirect_map(&xsk, 0, XDP_DROP);
-- 
cgit v1.2.3


From 62838e363e4f0753d43b2b78e9d3f6ad3c9102ec Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 2 Apr 2026 17:49:58 +0200
Subject: selftests: bpf: adjust rx_dropped xskxceiver's test to respect
 tailroom
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since we have changed how big user defined headroom in umem can be,
change the logic in testapp_stats_rx_dropped() so we pass updated
headroom validation in xdp_umem_reg() and still drop half of frames.

Test works on non-mbuf setup so __xsk_pool_get_rx_frame_size() that is
called on xsk_rcv_check() will not account skb_shared_info size. Taking
the tailroom size into account in test being fixed is needed as
xdp_umem_reg() defaults to respect it.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-9-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/test_xsk.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index ee60bcc22ee4..7950c504ed28 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -1959,15 +1959,17 @@ int testapp_headroom(struct test_spec *test)
 
 int testapp_stats_rx_dropped(struct test_spec *test)
 {
+	u32 umem_tr = test->ifobj_tx->umem_tailroom;
+
 	if (test->mode == TEST_MODE_ZC) {
 		ksft_print_msg("Can not run RX_DROPPED test for ZC mode\n");
 		return TEST_SKIP;
 	}
 
-	if (pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0))
+	if (pkt_stream_replace_half(test, (MIN_PKT_SIZE * 3) + umem_tr, 0))
 		return TEST_FAILURE;
 	test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
-		XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3;
+		XDP_PACKET_HEADROOM - (MIN_PKT_SIZE * 2) - umem_tr;
 	if (pkt_stream_receive_half(test))
 		return TEST_FAILURE;
 	test->ifobj_rx->validation_func = validate_rx_dropped;
-- 
cgit v1.2.3


From 24ad7ff668896325591fa0b570f2cca6c55f136f Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 3 Apr 2026 11:32:51 +0200
Subject: vsock/test: fix send_buf()/recv_buf() EINTR handling

When send() or recv() returns -1 with errno == EINTR, the code skips
the break but still adds the return value to nwritten/nread, making it
decrease by 1. This leads to wrong buffer offsets and wrong bytes count.

Fix it by explicitly continuing the loop on EINTR, so the return value
is only added when it is positive.

Fixes: a8ed71a27ef5 ("vsock/test: add recv_buf() utility function")
Fixes: 12329bd51fdc ("vsock/test: add send_buf() utility function")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Luigi Leonardi <leonardi@redhat.com>
Link: https://patch.msgid.link/20260403093251.30662-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/vsock/util.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 9430ef5b8bc3..1fe1338c79cd 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -344,7 +344,9 @@ void send_buf(int fd, const void *buf, size_t len, int flags,
 		ret = send(fd, buf + nwritten, len - nwritten, flags);
 		timeout_check("send");
 
-		if (ret == 0 || (ret < 0 && errno != EINTR))
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
 			break;
 
 		nwritten += ret;
@@ -396,7 +398,9 @@ void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret)
 		ret = recv(fd, buf + nread, len - nread, flags);
 		timeout_check("recv");
 
-		if (ret == 0 || (ret < 0 && errno != EINTR))
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
 			break;
 
 		nread += ret;
-- 
cgit v1.2.3


From 0f42e3f4fe2a58394e37241d02d9ca6ab7b7d516 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@linux.dev>
Date: Fri, 3 Apr 2026 09:45:12 +0800
Subject: net: skb: fix cross-cache free of KFENCE-allocated skb head

SKB_SMALL_HEAD_CACHE_SIZE is intentionally set to a non-power-of-2
value (e.g. 704 on x86_64) to avoid collisions with generic kmalloc
bucket sizes. This ensures that skb_kfree_head() can reliably use
skb_end_offset to distinguish skb heads allocated from
skb_small_head_cache vs. generic kmalloc caches.

However, when KFENCE is enabled, kfence_ksize() returns the exact
requested allocation size instead of the slab bucket size. If a caller
(e.g. bpf_test_init) allocates skb head data via kzalloc() and the
requested size happens to equal SKB_SMALL_HEAD_CACHE_SIZE, then
slab_build_skb() -> ksize() returns that exact value. After subtracting
skb_shared_info overhead, skb_end_offset ends up matching
SKB_SMALL_HEAD_HEADROOM, causing skb_kfree_head() to incorrectly free
the object to skb_small_head_cache instead of back to the original
kmalloc cache, resulting in a slab cross-cache free:

  kmem_cache_free(skbuff_small_head): Wrong slab cache. Expected
  skbuff_small_head but got kmalloc-1k

Fix this by always calling kfree(head) in skb_kfree_head(). This keeps
the free path generic and avoids allocator-specific misclassification
for KFENCE objects.

Fixes: bf9f1baa279f ("net: add dedicated kmem_cache for typical/small skb->head")
Reported-by: Antonius <antonius@bluedragonsec.com>
Closes: https://lore.kernel.org/netdev/CAK8a0jxC5L5N7hq-DT2_NhUyjBxrPocoiDazzsBk4TGgT1r4-A@mail.gmail.com/
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260403014517.142550-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0e217041958a..43ee86dcf2ea 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1083,10 +1083,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
-	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
-		kmem_cache_free(net_hotdata.skb_small_head_cache, head);
-	else
-		kfree(head);
+	kfree(head);
 }
 
 static void skb_free_head(struct sk_buff *skb)
-- 
cgit v1.2.3


From a9d4f4f6e65e0bf9bbddedecc84d67249991979c Mon Sep 17 00:00:00 2001
From: Michael Guralnik <michaelgur@nvidia.com>
Date: Fri, 3 Apr 2026 12:17:56 +0300
Subject: net/mlx5: Update the list of the PCI supported devices

Add the upcoming ConnectX-10 NVLink-C2C device ID to the table of
supported PCI device IDs.

Cc: stable@vger.kernel.org
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260403091756.139583-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index fdc3ba20912e..3f73d9b1115d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2267,6 +2267,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x1023) },			/* ConnectX-8 */
 	{ PCI_VDEVICE(MELLANOX, 0x1025) },			/* ConnectX-9 */
 	{ PCI_VDEVICE(MELLANOX, 0x1027) },			/* ConnectX-10 */
+	{ PCI_VDEVICE(MELLANOX, 0x2101) },			/* ConnectX-10 NVLink-C2C */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
-- 
cgit v1.2.3


From e2a39d1a88f00ed83ebc7a19b7673d4ffd50b173 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Fri, 13 Mar 2026 10:40:47 -0700
Subject: perf/x86/intel/uncore: Fix iounmap() leak on global_init failure

Kernel test robot reported:

Unverified Error/Warning (likely false positive, kindly check if
interested):
    arch/x86/events/intel/uncore_discovery.c:293:2-8:
    ERROR: missing iounmap; ioremap on line 288 and execution via
    conditional on line 292

If domain->global_init() fails in __parse_discovery_table(), the
ioremap'ed MMIO region is not released before returning, resulting
in an MMIO mapping leak.

Fixes: b575fc0e3357 ("perf/x86/intel/uncore: Add domain global init callback")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20260313174050.171704-2-zide.chen@intel.com
---
 arch/x86/events/intel/uncore_discovery.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 12e259a988dd..427939be2fb4 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -264,6 +264,7 @@ static int __parse_discovery_table(struct uncore_discovery_domain *domain,
 	struct uncore_unit_discovery unit;
 	void __iomem *io_addr;
 	unsigned long size;
+	int ret = 0;
 	int i;
 
 	size = UNCORE_DISCOVERY_GLOBAL_MAP_SIZE;
@@ -273,21 +274,23 @@ static int __parse_discovery_table(struct uncore_discovery_domain *domain,
 
 	/* Read Global Discovery State */
 	memcpy_fromio(&global, io_addr, sizeof(struct uncore_global_discovery));
+	iounmap(io_addr);
+
 	if (uncore_discovery_invalid_unit(global)) {
 		pr_info("Invalid Global Discovery State: 0x%llx 0x%llx 0x%llx\n",
 			global.table1, global.ctl, global.table3);
-		iounmap(io_addr);
 		return -EINVAL;
 	}
-	iounmap(io_addr);
 
 	size = (1 + global.max_units) * global.stride * 8;
 	io_addr = ioremap(addr, size);
 	if (!io_addr)
 		return -ENOMEM;
 
-	if (domain->global_init && domain->global_init(global.ctl))
-		return -ENODEV;
+	if (domain->global_init && domain->global_init(global.ctl)) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	/* Parsing Unit Discovery State */
 	for (i = 0; i < global.max_units; i++) {
@@ -307,8 +310,10 @@ static int __parse_discovery_table(struct uncore_discovery_domain *domain,
 	}
 
 	*parsed = true;
+
+out:
 	iounmap(io_addr);
-	return 0;
+	return ret;
 }
 
 static int parse_discovery_table(struct uncore_discovery_domain *domain,
-- 
cgit v1.2.3


From 7b568e9eba2fad89a696f22f0413d44cf4a1f892 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Fri, 13 Mar 2026 10:40:48 -0700
Subject: perf/x86/intel/uncore: Skip discovery table for offline dies

This warning can be triggered if NUMA is disabled and the system
boots with fewer CPUs than the number of CPUs in die 0.

WARNING: CPU: 9 PID: 7257 at uncore.c:1157 uncore_pci_pmu_register+0x136/0x160 [intel_uncore]

Currently, the discovery table continues to be parsed even if all CPUs
in the associated die are offline.  This can lead to an array overflow
at "pmu->boxes[die] = box" in uncore_pci_pmu_register(), which may
trigger the warning above or cause other issues.

Fixes: edae1f06c2cd ("perf/x86/intel/uncore: Parse uncore discovery tables")
Reported-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://patch.msgid.link/20260313174050.171704-3-zide.chen@intel.com
---
 arch/x86/events/intel/uncore_discovery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 427939be2fb4..583cbd06b9b8 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -371,7 +371,7 @@ static bool uncore_discovery_pci(struct uncore_discovery_domain *domain)
 				     (val & UNCORE_DISCOVERY_DVSEC2_BIR_MASK) * UNCORE_DISCOVERY_BIR_STEP;
 
 			die = get_device_die_id(dev);
-			if (die < 0)
+			if ((die < 0) || (die >= uncore_max_dies()))
 				continue;
 
 			parse_discovery_table(domain, dev, die, bar_offset, &parsed);
-- 
cgit v1.2.3


From a16d1ec4dd0cdcf689f324adde6067083bce9099 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Fri, 13 Mar 2026 10:40:49 -0700
Subject: perf/x86/intel/uncore: Fix die ID init and look up bugs

In snbep_pci2phy_map_init(), in the nr_node_ids > 8 path,
uncore_device_to_die() may return -1 when all CPUs associated
with the UBOX device are offline.

Remove the WARN_ON_ONCE(die_id == -1) check for two reasons:

- The current code breaks out of the loop. This is incorrect because
  pci_get_device() does not guarantee iteration in domain or bus order,
  so additional UBOX devices may be skipped during the scan.

- Returning -EINVAL is incorrect, since marking offline buses with
  die_id == -1 is expected and should not be treated as an error.

Separately, when NUMA is disabled on a NUMA-capable platform,
pcibus_to_node() returns NUMA_NO_NODE, causing uncore_device_to_die()
to return -1 for all PCI devices.  As a result,
spr_update_device_location(), used on Intel SPR and EMR, ignores the
corresponding PMON units and does not add them to the RB tree.

Fix this by using uncore_pcibus_to_dieid(), which retrieves topology
from the UBOX GIDNIDMAP register and works regardless of whether NUMA
is enabled in Linux.  This requires snbep_pci2phy_map_init() to be
added in spr_uncore_pci_init().

Keep uncore_device_to_die() only for the nr_node_ids > 8 case, where
NUMA is expected to be enabled.

Fixes: 9a7832ce3d92 ("perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info")
Fixes: 65248a9a9ee1 ("perf/x86/uncore: Add a quirk for UPI on SPR")
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://patch.msgid.link/20260313174050.171704-4-zide.chen@intel.com
---
 arch/x86/events/intel/uncore.c       |  1 +
 arch/x86/events/intel/uncore_snbep.c | 13 ++++++-------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 786bd51a0d89..e9cc1ba921c5 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -67,6 +67,7 @@ int uncore_die_to_segment(int die)
 	return bus ? pci_domain_nr(bus) : -EINVAL;
 }
 
+/* Note: This API can only be used when NUMA information is available. */
 int uncore_device_to_die(struct pci_dev *dev)
 {
 	int node = pcibus_to_node(dev->bus);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 0a1d08136cc1..a4b337bf83c0 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1459,13 +1459,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 			}
 
 			map->pbus_to_dieid[bus] = die_id = uncore_device_to_die(ubox_dev);
-
 			raw_spin_unlock(&pci2phy_map_lock);
-
-			if (WARN_ON_ONCE(die_id == -1)) {
-				err = -EINVAL;
-				break;
-			}
 		}
 	}
 
@@ -6420,7 +6414,7 @@ static void spr_update_device_location(int type_id)
 
 	while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
 
-		die = uncore_device_to_die(dev);
+		die = uncore_pcibus_to_dieid(dev->bus);
 		if (die < 0)
 			continue;
 
@@ -6444,6 +6438,11 @@ static void spr_update_device_location(int type_id)
 
 int spr_uncore_pci_init(void)
 {
+	int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
+
+	if (ret)
+		return ret;
+
 	/*
 	 * The discovery table of UPI on some SPR variant is broken,
 	 * which impacts the detection of both UPI and M3UPI uncore PMON.
-- 
cgit v1.2.3


From 16bcbe6738bea7b4aee0a29324ce12c21c4b0ea0 Mon Sep 17 00:00:00 2001
From: Zide Chen <zide.chen@intel.com>
Date: Fri, 13 Mar 2026 10:40:50 -0700
Subject: perf/x86/intel/uncore: Remove extra double quote mark

The third argument in INTEL_UNCORE_FR_EVENT_DESC() is subject to
__stringify(), and the extra double quote marks can result in the
expansion "3.814697266e-6" in the sysfs knobs, instead of
3.814697266e-6.

This is incorrect, though it may still work for perf, e.g.
perf stat -e uncore_iio_free_running_0/bw_in_port0/

Fixes: d8987048f665 ("perf/x86/intel/uncore: Support IIO free-running counters on DMR")
Closes: https://lore.kernel.org/all/20251231224233.113839-1-zide.chen@intel.com/
Reported-by: Chun-Tse Shao <ctshao@google.com>
Signed-off-by: Zide Chen <zide.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Chun-Tse Shao <ctshao@google.com>
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Link: https://patch.msgid.link/20260313174050.171704-5-zide.chen@intel.com
---
 arch/x86/events/intel/uncore_snbep.c | 48 ++++++++++++++++++------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index a4b337bf83c0..215d33e260ed 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6934,34 +6934,34 @@ static struct freerunning_counters dmr_iio_freerunning[] = {
 
 static struct uncore_event_desc dmr_uncore_iio_freerunning_events[] = {
 	/*  ITC Free Running Data BW counter for inbound traffic */
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port0, 0x10, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port1, 0x11, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port2, 0x12, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port3, 0x13, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port4, 0x14, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port5, 0x15, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port6, 0x16, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port7, 0x17, "3.814697266e-6"),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port0, 0x10, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port1, 0x11, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port2, 0x12, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port3, 0x13, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port4, 0x14, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port5, 0x15, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port6, 0x16, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(inb_data_port7, 0x17, 3.814697266e-6),
 
 	/*  ITC Free Running BW IN counters */
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port0, 0x20, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port1, 0x21, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port2, 0x22, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port3, 0x23, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port4, 0x24, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port5, 0x25, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port6, 0x26, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port7, 0x27, "3.814697266e-6"),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port0, 0x20, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port1, 0x21, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port2, 0x22, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port3, 0x23, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port4, 0x24, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port5, 0x25, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port6, 0x26, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_in_port7, 0x27, 3.814697266e-6),
 
 	/*  ITC Free Running BW OUT counters */
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port0, 0x30, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port1, 0x31, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port2, 0x32, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port3, 0x33, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port4, 0x34, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port5, 0x35, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port6, 0x36, "3.814697266e-6"),
-	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port7, 0x37, "3.814697266e-6"),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port0, 0x30, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port1, 0x31, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port2, 0x32, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port3, 0x33, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port4, 0x34, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port5, 0x35, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port6, 0x36, 3.814697266e-6),
+	INTEL_UNCORE_FR_EVENT_DESC(bw_out_port7, 0x37, 3.814697266e-6),
 
 	/* Free Running Clock Counter */
 	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x40"),
-- 
cgit v1.2.3


From 105c42566a550e2d05fc14f763216a8765ee5d0e Mon Sep 17 00:00:00 2001
From: Arthur Husband <artmoty@gmail.com>
Date: Mon, 6 Apr 2026 15:23:35 -0700
Subject: ata: ahci: force 32-bit DMA for JMicron JMB582/JMB585

The JMicron JMB585 (and JMB582) SATA controllers advertise 64-bit DMA
support via the S64A bit in the AHCI CAP register, but their 64-bit DMA
implementation is defective. Under sustained I/O, DMA transfers targeting
addresses above 4GB silently corrupt data -- writes land at incorrect
memory addresses with no errors logged.

The failure pattern is similar to the ASMedia ASM1061
(commit 20730e9b2778 ("ahci: add 43-bit DMA address quirk for ASMedia
ASM1061 controllers")), which also falsely advertised full 64-bit DMA
support. However, the JMB585 requires a stricter 32-bit DMA mask rather
than 43-bit, as corruption occurs with any address above 4GB.

On the Minisforum N5 Pro specifically, the combination of the JMB585's
broken 64-bit DMA with the AMD Family 1Ah (Strix Point) IOMMU causes
silent data corruption that is only detectable via checksumming
filesystems (BTRFS/ZFS scrub). The corruption occurs when 32-bit IOVA
space is exhausted and the kernel transparently switches to 64-bit DMA
addresses.

Add device-specific PCI ID entries for the JMB582 (0x0582) and JMB585
(0x0585) before the generic JMicron class match, using a new board type
that combines AHCI_HFLAG_IGN_IRQ_IF_ERR (preserving existing behavior)
with AHCI_HFLAG_32BIT_ONLY to force 32-bit DMA masks.

Signed-off-by: Arthur Husband <artmoty@gmail.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 931d0081169b..1d73a53370cf 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -68,6 +68,7 @@ enum board_ids {
 	/* board IDs for specific chipsets in alphabetical order */
 	board_ahci_al,
 	board_ahci_avn,
+	board_ahci_jmb585,
 	board_ahci_mcp65,
 	board_ahci_mcp77,
 	board_ahci_mcp89,
@@ -212,6 +213,15 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_avn_ops,
 	},
+	/* JMicron JMB582/585: 64-bit DMA is broken, force 32-bit */
+	[board_ahci_jmb585] = {
+		AHCI_HFLAGS	(AHCI_HFLAG_IGN_IRQ_IF_ERR |
+				 AHCI_HFLAG_32BIT_ONLY),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 	[board_ahci_mcp65] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_FPDMA_AA | AHCI_HFLAG_NO_PMP |
 				 AHCI_HFLAG_YES_NCQ),
@@ -439,6 +449,10 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	/* Elkhart Lake IDs 0x4b60 & 0x4b62 https://sata-io.org/product/8803 not tested yet */
 	{ PCI_VDEVICE(INTEL, 0x4b63), board_ahci_pcs_quirk }, /* Elkhart Lake AHCI */
 
+	/* JMicron JMB582/585: force 32-bit DMA (broken 64-bit implementation) */
+	{ PCI_VDEVICE(JMICRON, 0x0582), board_ahci_jmb585 },
+	{ PCI_VDEVICE(JMICRON, 0x0585), board_ahci_jmb585 },
+
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
 	  PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff, board_ahci_ign_iferr },
-- 
cgit v1.2.3


From 75519f5df2a9b23f7bf305e12dc9a6e3e65c24b7 Mon Sep 17 00:00:00 2001
From: Jouni Högander <jouni.hogander@intel.com>
Date: Fri, 27 Mar 2026 13:45:53 +0200
Subject: drm/i915/psr: Do not use pipe_src as borders for SU area
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This far using crtc_state->pipe_src as borders for Selective Update area
haven't caused visible problems as drm_rect_width(crtc_state->pipe_src) ==
crtc_state->hw.adjusted_mode.crtc_hdisplay and
drm_rect_height(crtc_state->pipe_src) ==
crtc_state->hw.adjusted_mode.crtc_vdisplay when pipe scaling is not
used. On the other hand using pipe scaling is forcing full frame updates and all the
Selective Update area calculations are skipped. Now this improper usage of
crtc_state->pipe_src is causing following warnings:

<4> [7771.978166] xe 0000:00:02.0: [drm] drm_WARN_ON_ONCE(su_lines % vdsc_cfg->slice_height)

after WARN_ON_ONCE was added by commit:

"drm/i915/dsc: Add helper for writing DSC Selective Update ET parameters"

These warnings are seen when DSC and pipe scaling are enabled
simultaneously. This is because on full frame update SU area is improperly
set as pipe_src which is not aligned with DSC slice height.

Fix these by creating local rectangle using
crtc_state->hw.adjusted_mode.crtc_hdisplay and
crtc_state->hw.adjusted_mode.crtc_vdisplay. Use this local rectangle as
borders for SU area.

Fixes: d6774b8c3c58 ("drm/i915: Ensure damage clip area is within pipe area")
Cc: <stable@vger.kernel.org> # v6.0+
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://patch.msgid.link/20260327114553.195285-1-jouni.hogander@intel.com
(cherry picked from commit da0cdc1c329dd2ff09c41fbbe9fbd9c92c5d2c6e)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_psr.c | 30 +++++++++++++++++++-----------
 1 file changed, 19 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 3791944389db..097e18c1adb2 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2678,9 +2678,9 @@ static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state,
 
 static void clip_area_update(struct drm_rect *overlap_damage_area,
 			     struct drm_rect *damage_area,
-			     struct drm_rect *pipe_src)
+			     struct drm_rect *display_area)
 {
-	if (!drm_rect_intersect(damage_area, pipe_src))
+	if (!drm_rect_intersect(damage_area, display_area))
 		return;
 
 	if (overlap_damage_area->y1 == -1) {
@@ -2731,6 +2731,7 @@ static bool intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st
 static void
 intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state,
 				  struct intel_crtc *crtc,
+				  struct drm_rect *display_area,
 				  bool *cursor_in_su_area)
 {
 	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
@@ -2758,7 +2759,7 @@ intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state,
 			continue;
 
 		clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst,
-				 &crtc_state->pipe_src);
+				 display_area);
 		*cursor_in_su_area = true;
 	}
 }
@@ -2855,6 +2856,12 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 	struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_plane_state *new_plane_state, *old_plane_state;
 	struct intel_plane *plane;
+	struct drm_rect display_area = {
+		.x1 = 0,
+		.y1 = 0,
+		.x2 = crtc_state->hw.adjusted_mode.crtc_hdisplay,
+		.y2 = crtc_state->hw.adjusted_mode.crtc_vdisplay,
+	};
 	bool full_update = false, su_area_changed;
 	int i, ret;
 
@@ -2868,7 +2875,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 
 	crtc_state->psr2_su_area.x1 = 0;
 	crtc_state->psr2_su_area.y1 = -1;
-	crtc_state->psr2_su_area.x2 = drm_rect_width(&crtc_state->pipe_src);
+	crtc_state->psr2_su_area.x2 = drm_rect_width(&display_area);
 	crtc_state->psr2_su_area.y2 = -1;
 
 	/*
@@ -2906,14 +2913,14 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 				damaged_area.y1 = old_plane_state->uapi.dst.y1;
 				damaged_area.y2 = old_plane_state->uapi.dst.y2;
 				clip_area_update(&crtc_state->psr2_su_area, &damaged_area,
-						 &crtc_state->pipe_src);
+						 &display_area);
 			}
 
 			if (new_plane_state->uapi.visible) {
 				damaged_area.y1 = new_plane_state->uapi.dst.y1;
 				damaged_area.y2 = new_plane_state->uapi.dst.y2;
 				clip_area_update(&crtc_state->psr2_su_area, &damaged_area,
-						 &crtc_state->pipe_src);
+						 &display_area);
 			}
 			continue;
 		} else if (new_plane_state->uapi.alpha != old_plane_state->uapi.alpha) {
@@ -2921,7 +2928,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 			damaged_area.y1 = new_plane_state->uapi.dst.y1;
 			damaged_area.y2 = new_plane_state->uapi.dst.y2;
 			clip_area_update(&crtc_state->psr2_su_area, &damaged_area,
-					 &crtc_state->pipe_src);
+					 &display_area);
 			continue;
 		}
 
@@ -2937,7 +2944,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 		damaged_area.x1 += new_plane_state->uapi.dst.x1 - src.x1;
 		damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1;
 
-		clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src);
+		clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &display_area);
 	}
 
 	/*
@@ -2972,7 +2979,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 		 * cursor is added into affected planes even when
 		 * cursor is not updated by itself.
 		 */
-		intel_psr2_sel_fetch_et_alignment(state, crtc, &cursor_in_su_area);
+		intel_psr2_sel_fetch_et_alignment(state, crtc, &display_area,
+						  &cursor_in_su_area);
 
 		su_area_changed = intel_psr2_sel_fetch_pipe_alignment(crtc_state);
 
@@ -3048,8 +3056,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
 
 skip_sel_fetch_set_loop:
 	if (full_update)
-		clip_area_update(&crtc_state->psr2_su_area, &crtc_state->pipe_src,
-				 &crtc_state->pipe_src);
+		clip_area_update(&crtc_state->psr2_su_area, &display_area,
+				 &display_area);
 
 	psr2_man_trk_ctl_calc(crtc_state, full_update);
 	crtc_state->pipe_srcsz_early_tpt =
-- 
cgit v1.2.3


From 069daad4f2ae9c5c108131995529d5f02392c446 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Thu, 2 Apr 2026 13:31:04 +0200
Subject: xfrm: Wait for RCU readers during policy netns exit

xfrm_policy_fini() frees the policy_bydst hash tables after flushing the
policy work items and deleting all policies, but it does not wait for
concurrent RCU readers to leave their read-side critical sections first.

The policy_bydst tables are published via rcu_assign_pointer() and are
looked up through rcu_dereference_check(), so netns teardown must also
wait for an RCU grace period before freeing the table memory.

Fix this by adding synchronize_rcu() before freeing the policy hash tables.

Fixes: e1e551bc5630 ("xfrm: policy: prepare policy_bydst hash for rcu lookups")
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
---
 net/xfrm/xfrm_policy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 362939aa56cf..8f0188e763c7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4290,6 +4290,8 @@ static void xfrm_policy_fini(struct net *net)
 #endif
 	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
 
+	synchronize_rcu();
+
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
 	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-- 
cgit v1.2.3


From 1c428b03840094410c5fb6a5db30640486bbbfcb Mon Sep 17 00:00:00 2001
From: Qi Tang <tpluszz77@gmail.com>
Date: Thu, 2 Apr 2026 19:44:01 +0800
Subject: xfrm: hold dev ref until after transport_finish NF_HOOK

After async crypto completes, xfrm_input_resume() calls dev_put()
immediately on re-entry before the skb reaches transport_finish.
The skb->dev pointer is then used inside NF_HOOK and its okfn,
which can race with device teardown.

Remove the dev_put from the async resumption entry and instead
drop the reference after the NF_HOOK call in transport_finish,
using a saved device pointer since NF_HOOK may consume the skb.
This covers NF_DROP, NF_QUEUE and NF_STOLEN paths that skip
the okfn.

For non-transport exits (decaps, gro, drop) and secondary
async return points, release the reference inline when
async is set.

Suggested-by: Florian Westphal <fw@strlen.de>
Fixes: acf568ee859f ("xfrm: Reinject transport-mode packets through tasklet")
Cc: stable@vger.kernel.org
Signed-off-by: Qi Tang <tpluszz77@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/xfrm4_input.c |  5 ++++-
 net/ipv6/xfrm6_input.c |  5 ++++-
 net/xfrm/xfrm_input.c  | 18 ++++++++++++++----
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index f28cfd88eaf5..c2eac844bcdb 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -50,6 +50,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 {
 	struct xfrm_offload *xo = xfrm_offload(skb);
 	struct iphdr *iph = ip_hdr(skb);
+	struct net_device *dev = skb->dev;
 
 	iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;
 
@@ -73,8 +74,10 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	}
 
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
-		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm4_rcv_encap_finish);
+	if (async)
+		dev_put(dev);
 	return 0;
 }
 
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 9005fc156a20..699a001ac166 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -43,6 +43,7 @@ static int xfrm6_transport_finish2(struct net *net, struct sock *sk,
 int xfrm6_transport_finish(struct sk_buff *skb, int async)
 {
 	struct xfrm_offload *xo = xfrm_offload(skb);
+	struct net_device *dev = skb->dev;
 	int nhlen = -skb_network_offset(skb);
 
 	skb_network_header(skb)[IP6CB(skb)->nhoff] =
@@ -68,8 +69,10 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
 	}
 
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
-		dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+		dev_net(dev), NULL, skb, dev, NULL,
 		xfrm6_transport_finish2);
+	if (async)
+		dev_put(dev);
 	return 0;
 }
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index dc1312ed5a09..f65291eba1f6 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -506,7 +506,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
 			async = 1;
-			dev_put(skb->dev);
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
 			spin_lock(&x->lock);
 			goto resume;
@@ -659,8 +658,11 @@ process:
 			dev_hold(skb->dev);
 
 			nexthdr = x->type->input(x, skb);
-			if (nexthdr == -EINPROGRESS)
+			if (nexthdr == -EINPROGRESS) {
+				if (async)
+					dev_put(skb->dev);
 				return 0;
+			}
 
 			dev_put(skb->dev);
 			spin_lock(&x->lock);
@@ -695,9 +697,11 @@ resume:
 		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
 
 		err = xfrm_inner_mode_input(x, skb);
-		if (err == -EINPROGRESS)
+		if (err == -EINPROGRESS) {
+			if (async)
+				dev_put(skb->dev);
 			return 0;
-		else if (err) {
+		} else if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
 			goto drop;
 		}
@@ -734,6 +738,8 @@ resume_decapped:
 			sp->olen = 0;
 		if (skb_valid_dst(skb))
 			skb_dst_drop(skb);
+		if (async)
+			dev_put(skb->dev);
 		gro_cells_receive(&gro_cells, skb);
 		return 0;
 	} else {
@@ -753,6 +759,8 @@ resume_decapped:
 				sp->olen = 0;
 			if (skb_valid_dst(skb))
 				skb_dst_drop(skb);
+			if (async)
+				dev_put(skb->dev);
 			gro_cells_receive(&gro_cells, skb);
 			return err;
 		}
@@ -763,6 +771,8 @@ resume_decapped:
 drop_unlock:
 	spin_unlock(&x->lock);
 drop:
+	if (async)
+		dev_put(skb->dev);
 	xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1);
 	kfree_skb(skb);
 	return 0;
-- 
cgit v1.2.3


From 83317cce60a032c49480dcdabe146435bd689d03 Mon Sep 17 00:00:00 2001
From: Kotlyarov Mihail <mihailkotlyarow@gmail.com>
Date: Sat, 4 Apr 2026 12:05:20 +0300
Subject: xfrm: fix refcount leak in xfrm_migrate_policy_find

syzkaller reported a memory leak in xfrm_policy_alloc:

  BUG: memory leak
  unreferenced object 0xffff888114d79000 (size 1024):
    comm "syz.1.17", pid 931
    ...
    xfrm_policy_alloc+0xb3/0x4b0 net/xfrm/xfrm_policy.c:432

The root cause is a double call to xfrm_pol_hold_rcu() in
xfrm_migrate_policy_find(). The lookup function already returns
a policy with held reference, making the second call redundant.

Remove the redundant xfrm_pol_hold_rcu() call to fix the refcount
imbalance and prevent the memory leak.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 563d5ca93e88 ("xfrm: switch migrate to xfrm_policy_lookup_bytype")
Signed-off-by: Kotlyarov Mihail <mihailkotlyarow@gmail.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8f0188e763c7..a872af5610dc 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4528,9 +4528,6 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 	pol = xfrm_policy_lookup_bytype(net, type, &fl, sel->family, dir, if_id);
 	if (IS_ERR_OR_NULL(pol))
 		goto out_unlock;
-
-	if (!xfrm_pol_hold_rcu(pol))
-		pol = NULL;
 out_unlock:
 	rcu_read_unlock();
 	return pol;
-- 
cgit v1.2.3


From 1beb76b2053b68c491b78370794b8ff63c8f8c02 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 6 Apr 2026 17:33:03 +0200
Subject: xfrm_user: fix info leak in build_mapping()

struct xfrm_usersa_id has a one-byte padding hole after the proto
field, which ends up never getting set to zero before copying out to
userspace.  Fix that up by zeroing out the whole structure before
setting individual variables.

Fixes: 3a2dfbe8acb1 ("xfrm: Notify changes in UDP encapsulation via netlink")
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Assisted-by: gregkh_clanker_t1000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index a779590c985a..baa43c325da2 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -4172,6 +4172,7 @@ static int build_mapping(struct sk_buff *skb, struct xfrm_state *x,
 
 	um = nlmsg_data(nlh);
 
+	memset(&um->id, 0, sizeof(um->id));
 	memcpy(&um->id.daddr, &x->id.daddr, sizeof(um->id.daddr));
 	um->id.spi = x->id.spi;
 	um->id.family = x->props.family;
-- 
cgit v1.2.3


From d10119968d0e1f2b669604baf2a8b5fdb72fa6b4 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 6 Apr 2026 17:34:22 +0200
Subject: xfrm_user: fix info leak in build_report()

struct xfrm_user_report is a __u8 proto field followed by a struct
xfrm_selector which means there is three "empty" bytes of padding, but
the padding is never zeroed before copying to userspace.  Fix that up by
zeroing the structure before setting individual member variables.

Cc: stable <stable@kernel.org>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Assisted-by: gregkh_clanker_t1000
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_user.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index baa43c325da2..d56450f61669 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -4125,6 +4125,7 @@ static int build_report(struct sk_buff *skb, u8 proto,
 		return -EMSGSIZE;
 
 	ur = nlmsg_data(nlh);
+	memset(ur, 0, sizeof(*ur));
 	ur->proto = proto;
 	memcpy(&ur->sel, sel, sizeof(ur->sel));
 
-- 
cgit v1.2.3


From 426c355742f02cf743b347d9d7dbdc1bfbfa31ef Mon Sep 17 00:00:00 2001
From: Zhengchuan Liang <zcliangcn@gmail.com>
Date: Sun, 22 Mar 2026 11:46:08 -0700
Subject: net: af_key: zero aligned sockaddr tail in PF_KEY exports

PF_KEY export paths use `pfkey_sockaddr_size()` when reserving sockaddr
payload space, so IPv6 addresses occupy 32 bytes on the wire. However,
`pfkey_sockaddr_fill()` initializes only the first 28 bytes of
`struct sockaddr_in6`, leaving the final 4 aligned bytes uninitialized.

Not every PF_KEY message is affected. The state and policy dump builders
already zero the whole message buffer before filling the sockaddr
payloads. Keep the fix to the export paths that still append aligned
sockaddr payloads with plain `skb_put()`:

  - `SADB_ACQUIRE`
  - `SADB_X_NAT_T_NEW_MAPPING`
  - `SADB_X_MIGRATE`

Fix those paths by clearing only the aligned sockaddr tail after
`pfkey_sockaddr_fill()`.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Fixes: 08de61beab8a ("[PFKEYV2]: Extension for dynamic update of endpoint address(es)")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Xiao Liu <lx24@stu.ynu.edu.cn>
Signed-off-by: Zhengchuan Liang <zcliangcn@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/key/af_key.c | 52 ++++++++++++++++++++++++++++++++++------------------
 1 file changed, 34 insertions(+), 18 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 72ac2ace419d..5d480ae39405 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -757,6 +757,22 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port
 	return 0;
 }
 
+static unsigned int pfkey_sockaddr_fill_zero_tail(const xfrm_address_t *xaddr,
+						  __be16 port,
+						  struct sockaddr *sa,
+						  unsigned short family)
+{
+	unsigned int prefixlen;
+	int sockaddr_len = pfkey_sockaddr_len(family);
+	int sockaddr_size = pfkey_sockaddr_size(family);
+
+	prefixlen = pfkey_sockaddr_fill(xaddr, port, sa, family);
+	if (sockaddr_size > sockaddr_len)
+		memset((u8 *)sa + sockaddr_len, 0, sockaddr_size - sockaddr_len);
+
+	return prefixlen;
+}
+
 static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x,
 					      int add_keys, int hsc)
 {
@@ -3206,9 +3222,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 	addr->sadb_address_proto = 0;
 	addr->sadb_address_reserved = 0;
 	addr->sadb_address_prefixlen =
-		pfkey_sockaddr_fill(&x->props.saddr, 0,
-				    (struct sockaddr *) (addr + 1),
-				    x->props.family);
+		pfkey_sockaddr_fill_zero_tail(&x->props.saddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      x->props.family);
 	if (!addr->sadb_address_prefixlen)
 		BUG();
 
@@ -3221,9 +3237,9 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct
 	addr->sadb_address_proto = 0;
 	addr->sadb_address_reserved = 0;
 	addr->sadb_address_prefixlen =
-		pfkey_sockaddr_fill(&x->id.daddr, 0,
-				    (struct sockaddr *) (addr + 1),
-				    x->props.family);
+		pfkey_sockaddr_fill_zero_tail(&x->id.daddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      x->props.family);
 	if (!addr->sadb_address_prefixlen)
 		BUG();
 
@@ -3421,9 +3437,9 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	addr->sadb_address_proto = 0;
 	addr->sadb_address_reserved = 0;
 	addr->sadb_address_prefixlen =
-		pfkey_sockaddr_fill(&x->props.saddr, 0,
-				    (struct sockaddr *) (addr + 1),
-				    x->props.family);
+		pfkey_sockaddr_fill_zero_tail(&x->props.saddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      x->props.family);
 	if (!addr->sadb_address_prefixlen)
 		BUG();
 
@@ -3443,9 +3459,9 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	addr->sadb_address_proto = 0;
 	addr->sadb_address_reserved = 0;
 	addr->sadb_address_prefixlen =
-		pfkey_sockaddr_fill(ipaddr, 0,
-				    (struct sockaddr *) (addr + 1),
-				    x->props.family);
+		pfkey_sockaddr_fill_zero_tail(ipaddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      x->props.family);
 	if (!addr->sadb_address_prefixlen)
 		BUG();
 
@@ -3474,15 +3490,15 @@ static int set_sadb_address(struct sk_buff *skb, int sasize, int type,
 	switch (type) {
 	case SADB_EXT_ADDRESS_SRC:
 		addr->sadb_address_prefixlen = sel->prefixlen_s;
-		pfkey_sockaddr_fill(&sel->saddr, 0,
-				    (struct sockaddr *)(addr + 1),
-				    sel->family);
+		pfkey_sockaddr_fill_zero_tail(&sel->saddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      sel->family);
 		break;
 	case SADB_EXT_ADDRESS_DST:
 		addr->sadb_address_prefixlen = sel->prefixlen_d;
-		pfkey_sockaddr_fill(&sel->daddr, 0,
-				    (struct sockaddr *)(addr + 1),
-				    sel->family);
+		pfkey_sockaddr_fill_zero_tail(&sel->daddr, 0,
+					      (struct sockaddr *)(addr + 1),
+					      sel->family);
 		break;
 	default:
 		return -EINVAL;
-- 
cgit v1.2.3


From db5b8cecbdf479ad13156af750377e5b43853fab Mon Sep 17 00:00:00 2001
From: Francesco Lavra <flavra@baylibre.com>
Date: Mon, 30 Mar 2026 18:19:14 +0200
Subject: pinctrl: mcp23s08: Disable all pin interrupts during probe

A chip being probed may have the interrupt-on-change feature enabled on
some of its pins, for example after a reboot. This can cause the chip to
generate interrupts for pins that don't have a registered nested handler,
which leads to a kernel crash such as below:

[    7.928897] Unable to handle kernel read from unreadable memory at virtual address 00000000000000ac
[    7.932314] Mem abort info:
[    7.935081]   ESR = 0x0000000096000004
[    7.938808]   EC = 0x25: DABT (current EL), IL = 32 bits
[    7.944094]   SET = 0, FnV = 0
[    7.947127]   EA = 0, S1PTW = 0
[    7.950247]   FSC = 0x04: level 0 translation fault
[    7.955101] Data abort info:
[    7.957961]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[    7.963421]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[    7.968447]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[    7.973734] user pgtable: 4k pages, 48-bit VAs, pgdp=00000000089b7000
[    7.980148] [00000000000000ac] pgd=0000000000000000, p4d=0000000000000000
[    7.986913] Internal error: Oops: 0000000096000004 [#1]  SMP
[    7.992545] Modules linked in:
[    8.073678] CPU: 0 UID: 0 PID: 81 Comm: irq/18-4-0025 Not tainted 7.0.0-rc6-gd2b5a1f931c8-dirty #199
[    8.073689] Hardware name: Khadas VIM3 (DT)
[    8.073692] pstate: 604000c5 (nZCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    8.094639] pc : _raw_spin_lock_irq+0x40/0x80
[    8.098970] lr : handle_nested_irq+0x2c/0x168
[    8.098979] sp : ffff800082b2bd20
[    8.106599] x29: ffff800082b2bd20 x28: ffff800080107920 x27: ffff800080104d88
[    8.106611] x26: ffff000003298080 x25: 0000000000000001 x24: 000000000000ff00
[    8.113707] x23: 0000000000000001 x22: 0000000000000000 x21: 000000000000000e
[    8.120850] x20: 0000000000000000 x19: 00000000000000ac x18: 0000000000000000
[    8.135046] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
[    8.135062] x14: ffff800081567ea8 x13: ffffffffffffffff x12: 0000000000000000
[    8.135070] x11: 00000000000000c0 x10: 0000000000000b60 x9 : ffff800080109e0c
[    8.135078] x8 : 1fffe0000069dbc1 x7 : 0000000000000001 x6 : ffff0000034ede00
[    8.135086] x5 : 0000000000000000 x4 : ffff0000034ede08 x3 : 0000000000000001
[    8.163460] x2 : 0000000000000000 x1 : 0000000000000001 x0 : 00000000000000ac
[    8.170560] Call trace:
[    8.180094]  _raw_spin_lock_irq+0x40/0x80 (P)
[    8.184443]  mcp23s08_irq+0x248/0x358
[    8.184462]  irq_thread_fn+0x34/0xb8
[    8.184470]  irq_thread+0x1a4/0x310
[    8.195093]  kthread+0x13c/0x150
[    8.198309]  ret_from_fork+0x10/0x20
[    8.201850] Code: d65f03c0 d2800002 52800023 f9800011 (885ffc01)
[    8.207931] ---[ end trace 0000000000000000 ]---

This issue has always been present, but has been latent until commit
"f9f4fda15e72" ("pinctrl: mcp23s08: init reg_defaults from HW at probe and
switch cache type"), which correctly removed reg_defaults from the regmap
and as a side effect changed the behavior of the interrupt handler so that
the real value of the MCP_GPINTEN register is now being read from the chip
instead of using a bogus 0 default value; a non-zero value for this
register can trigger the invocation of a nested handler which may not exist
(yet).
Fix this issue by disabling all pin interrupts during initialization.

Fixes: f9f4fda15e72 ("pinctrl: mcp23s08: init reg_defaults from HW at probe and switch cache type")
Signed-off-by: Francesco Lavra <flavra@baylibre.com>
Signed-off-by: Linus Walleij <linusw@kernel.org>
---
 drivers/pinctrl/pinctrl-mcp23s08.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index 586f2f67c617..b89b3169e8be 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -664,6 +664,15 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	if (mcp->irq && mcp->irq_controller) {
 		struct gpio_irq_chip *girq = &mcp->chip.irq;
 
+		/*
+		 * Disable all pin interrupts, to prevent the interrupt handler from
+		 * calling nested handlers for any currently-enabled interrupts that
+		 * do not (yet) have an actual handler.
+		 */
+		ret = mcp_write(mcp, MCP_GPINTEN, 0);
+		if (ret < 0)
+			return dev_err_probe(dev, ret, "can't disable interrupts\n");
+
 		gpio_irq_chip_set_chip(girq, &mcp23s08_irq_chip);
 		/* This will let us handle the parent IRQ in the driver */
 		girq->parent_handler = NULL;
-- 
cgit v1.2.3


From 12cd7632757a54ce586e36040210b1a738a0fc53 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Wed, 18 Feb 2026 14:07:37 +0100
Subject: wifi: brcmsmac: Fix dma_free_coherent() size

dma_alloc_consistent() may change the size to align it. The new size is
saved in alloced.

Change the free size to match the allocation size.

Fixes: 5b435de0d786 ("net: wireless: add brcm80211 drivers")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20260218130741.46566-3-fourier.thomas@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
index 9f6ef7ce1b58..a329c20e92fb 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/dma.c
@@ -483,7 +483,7 @@ static void *dma_ringalloc(struct dma_info *di, u32 boundary, uint size,
 	if (((desc_strtaddr + size - 1) & boundary) != (desc_strtaddr
 							& boundary)) {
 		*alignbits = dma_align_sizetobits(size);
-		dma_free_coherent(di->dmadev, size, va, *descpa);
+		dma_free_coherent(di->dmadev, *alloced, va, *descpa);
 		va = dma_alloc_consistent(di, size, *alignbits,
 			alloced, descpa);
 	}
-- 
cgit v1.2.3


From 304950a467d83678bd0b0f46331882e2ac23b12d Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Mon, 23 Mar 2026 15:45:51 +0800
Subject: wifi: brcmfmac: validate bsscfg indices in IF events

brcmf_fweh_handle_if_event() validates the firmware-provided interface
index before it touches drvr->iflist[], but it still uses the raw
bsscfgidx field as an array index without a matching range check.

Reject IF events whose bsscfg index does not fit in drvr->iflist[]
before indexing the interface array.

Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20260323074551.93530-1-pengpeng@iscas.ac.cn
[add missing wifi prefix]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
index 984886481f4e..1cff4ba76943 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c
@@ -153,6 +153,11 @@ static void brcmf_fweh_handle_if_event(struct brcmf_pub *drvr,
 		bphy_err(drvr, "invalid interface index: %u\n", ifevent->ifidx);
 		return;
 	}
+	if (ifevent->bsscfgidx >= BRCMF_MAX_IFS) {
+		bphy_err(drvr, "invalid bsscfg index: %u\n",
+			 ifevent->bsscfgidx);
+		return;
+	}
 
 	ifp = drvr->iflist[ifevent->bsscfgidx];
 
-- 
cgit v1.2.3


From 25369b22223d1c56e42a0cd4ac9137349d5a898e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 27 Mar 2026 12:32:19 +0100
Subject: wifi: rt2x00usb: fix devres lifetime

USB drivers bind to USB interfaces and any device managed resources
should have their lifetime tied to the interface rather than parent USB
device. This avoids issues like memory leaks when drivers are unbound
without their devices being physically disconnected (e.g. on probe
deferral or configuration changes).

Fix the USB anchor lifetime so that it is released on driver unbind.

Fixes: 8b4c0009313f ("rt2x00usb: Use usb anchor to manage URB")
Cc: stable@vger.kernel.org	# 4.7
Cc: Vishal Thanki <vishalthanki@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20260327113219.1313748-1-johan@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00usb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
index 54599cad78f9..aa5ecade2a40 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
@@ -828,7 +828,7 @@ int rt2x00usb_probe(struct usb_interface *usb_intf,
 	if (retval)
 		goto exit_free_device;
 
-	rt2x00dev->anchor = devm_kmalloc(&usb_dev->dev,
+	rt2x00dev->anchor = devm_kmalloc(&usb_intf->dev,
 					sizeof(struct usb_anchor),
 					GFP_KERNEL);
 	if (!rt2x00dev->anchor) {
-- 
cgit v1.2.3


From ea245d78dec594372e27d8c79616baf49e98a4a1 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 30 Mar 2026 11:14:13 +0200
Subject: net: rfkill: prevent unlimited numbers of rfkill events from being
 created

Userspace can create an unlimited number of rfkill events if the system
is so configured, while not consuming them from the rfkill file
descriptor, causing a potential out of memory situation.  Prevent this
from bounding the number of pending rfkill events at a "large" number
(i.e. 1000) to prevent abuses like this.

Cc: Johannes Berg <johannes@sipsolutions.net>
Reported-by: Yuan Tan <yuantan098@gmail.com>
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Reported-by: Xin Liu <bird@lzu.edu.cn>
Cc: stable <stable@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/2026033013-disfigure-scroll-e25e@gregkh
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/rfkill/core.c | 35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 2444237bc36a..4827e1fb8804 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -73,11 +73,14 @@ struct rfkill_int_event {
 	struct rfkill_event_ext	ev;
 };
 
+/* Max rfkill events that can be "in-flight" for one data source */
+#define MAX_RFKILL_EVENT	1000
 struct rfkill_data {
 	struct list_head	list;
 	struct list_head	events;
 	struct mutex		mtx;
 	wait_queue_head_t	read_wait;
+	u32			event_count;
 	bool			input_handler;
 	u8			max_size;
 };
@@ -255,10 +258,12 @@ static void rfkill_global_led_trigger_unregister(void)
 }
 #endif /* CONFIG_RFKILL_LEDS */
 
-static void rfkill_fill_event(struct rfkill_event_ext *ev,
-			      struct rfkill *rfkill,
-			      enum rfkill_operation op)
+static int rfkill_fill_event(struct rfkill_int_event *int_ev,
+			     struct rfkill *rfkill,
+			     struct rfkill_data *data,
+			     enum rfkill_operation op)
 {
+	struct rfkill_event_ext *ev = &int_ev->ev;
 	unsigned long flags;
 
 	ev->idx = rfkill->idx;
@@ -271,6 +276,15 @@ static void rfkill_fill_event(struct rfkill_event_ext *ev,
 					RFKILL_BLOCK_SW_PREV));
 	ev->hard_block_reasons = rfkill->hard_block_reasons;
 	spin_unlock_irqrestore(&rfkill->lock, flags);
+
+	scoped_guard(mutex, &data->mtx) {
+		if (data->event_count++ > MAX_RFKILL_EVENT) {
+			data->event_count--;
+			return -ENOSPC;
+		}
+		list_add_tail(&int_ev->list, &data->events);
+	}
+	return 0;
 }
 
 static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op)
@@ -282,10 +296,10 @@ static void rfkill_send_events(struct rfkill *rfkill, enum rfkill_operation op)
 		ev = kzalloc_obj(*ev);
 		if (!ev)
 			continue;
-		rfkill_fill_event(&ev->ev, rfkill, op);
-		mutex_lock(&data->mtx);
-		list_add_tail(&ev->list, &data->events);
-		mutex_unlock(&data->mtx);
+		if (rfkill_fill_event(ev, rfkill, data, op)) {
+			kfree(ev);
+			continue;
+		}
 		wake_up_interruptible(&data->read_wait);
 	}
 }
@@ -1186,10 +1200,8 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
 		if (!ev)
 			goto free;
 		rfkill_sync(rfkill);
-		rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD);
-		mutex_lock(&data->mtx);
-		list_add_tail(&ev->list, &data->events);
-		mutex_unlock(&data->mtx);
+		if (rfkill_fill_event(ev, rfkill, data, RFKILL_OP_ADD))
+			kfree(ev);
 	}
 	list_add(&data->list, &rfkill_fds);
 	mutex_unlock(&rfkill_global_mutex);
@@ -1259,6 +1271,7 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf,
 		ret = -EFAULT;
 
 	list_del(&ev->list);
+	data->event_count--;
 	kfree(ev);
  out:
 	mutex_unlock(&data->mtx);
-- 
cgit v1.2.3


From 5a1140404cbf7ba40137dfb1fb96893aa9a67d68 Mon Sep 17 00:00:00 2001
From: Nathan Rebello <nathan.c.rebello@gmail.com>
Date: Tue, 7 Apr 2026 02:39:58 -0400
Subject: usb: typec: ucsi: skip connector validation before init

Notifications can arrive before ucsi_init() has populated
ucsi->cap.num_connectors via GET_CAPABILITY. At that point
num_connectors is still 0, causing all valid connector numbers to be
incorrectly rejected as bogus.

Skip the bounds check when num_connectors is 0 (not yet initialized).
Pre-init notifications are already handled safely by the early-event
guard in ucsi_connector_change().

Reported-by: Takashi Iwai <tiwai@suse.de>
Fixes: d2d8c17ac01a ("usb: typec: ucsi: validate connector number in ucsi_notify_common()")
Cc: stable@vger.kernel.org
Signed-off-by: Nathan Rebello <nathan.c.rebello@gmail.com>
Tested-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20260407063958.863-1-nathan.c.rebello@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 8333bdaf5566..46262ee0d192 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -44,7 +44,8 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci)
 		return;
 
 	if (UCSI_CCI_CONNECTOR(cci)) {
-		if (UCSI_CCI_CONNECTOR(cci) <= ucsi->cap.num_connectors)
+		if (!ucsi->cap.num_connectors ||
+		    UCSI_CCI_CONNECTOR(cci) <= ucsi->cap.num_connectors)
 			ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci));
 		else
 			dev_err(ucsi->dev, "bogus connector number in CCI: %lu\n",
-- 
cgit v1.2.3


From 1f8fd9490e3184e9a2394df2e682901a1d57ce71 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Tue, 7 Apr 2026 17:55:08 +0800
Subject: spi: zynq-qspi: Simplify clock handling with devm_clk_get_enabled()

Replace devm_clk_get() followed by clk_prepare_enable() with
devm_clk_get_enabled() for both "pclk" and "ref_clk". This removes
the need for explicit clock enable and disable calls, as the managed
API automatically disables the clocks on device removal or probe
failure.

Remove the now-unnecessary clk_disable_unprepare() calls from the
probe error paths and the remove callback. Simplify error handling
by jumping directly to the remove_ctlr label.

Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Acked-by: Michal Simek <michal.simek@amd.com>
Link: https://patch.msgid.link/24043625f89376da36feca2408f990a85be7ab36.1775555500.git.xiaopei01@kylinos.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-zynq-qspi.c | 42 ++++++------------------------------------
 1 file changed, 6 insertions(+), 36 deletions(-)

diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
index 5232483c4a3a..af252500195c 100644
--- a/drivers/spi/spi-zynq-qspi.c
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -381,21 +381,10 @@ static int zynq_qspi_setup_op(struct spi_device *spi)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct zynq_qspi *qspi = spi_controller_get_devdata(ctlr);
-	int ret;
 
 	if (ctlr->busy)
 		return -EBUSY;
 
-	ret = clk_enable(qspi->refclk);
-	if (ret)
-		return ret;
-
-	ret = clk_enable(qspi->pclk);
-	if (ret) {
-		clk_disable(qspi->refclk);
-		return ret;
-	}
-
 	zynq_qspi_write(qspi, ZYNQ_QSPI_ENABLE_OFFSET,
 			ZYNQ_QSPI_ENABLE_ENABLE_MASK);
 
@@ -661,7 +650,7 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 		goto remove_ctlr;
 	}
 
-	xqspi->pclk = devm_clk_get(&pdev->dev, "pclk");
+	xqspi->pclk = devm_clk_get_enabled(&pdev->dev, "pclk");
 	if (IS_ERR(xqspi->pclk)) {
 		dev_err(&pdev->dev, "pclk clock not found.\n");
 		ret = PTR_ERR(xqspi->pclk);
@@ -670,36 +659,24 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 
 	init_completion(&xqspi->data_completion);
 
-	xqspi->refclk = devm_clk_get(&pdev->dev, "ref_clk");
+	xqspi->refclk = devm_clk_get_enabled(&pdev->dev, "ref_clk");
 	if (IS_ERR(xqspi->refclk)) {
 		dev_err(&pdev->dev, "ref_clk clock not found.\n");
 		ret = PTR_ERR(xqspi->refclk);
 		goto remove_ctlr;
 	}
 
-	ret = clk_prepare_enable(xqspi->pclk);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to enable APB clock.\n");
-		goto remove_ctlr;
-	}
-
-	ret = clk_prepare_enable(xqspi->refclk);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to enable device clock.\n");
-		goto clk_dis_pclk;
-	}
-
 	xqspi->irq = platform_get_irq(pdev, 0);
 	if (xqspi->irq < 0) {
 		ret = xqspi->irq;
-		goto clk_dis_all;
+		goto remove_ctlr;
 	}
 	ret = devm_request_irq(&pdev->dev, xqspi->irq, zynq_qspi_irq,
 			       0, pdev->name, xqspi);
 	if (ret != 0) {
 		ret = -ENXIO;
 		dev_err(&pdev->dev, "request_irq failed\n");
-		goto clk_dis_all;
+		goto remove_ctlr;
 	}
 
 	ret = of_property_read_u32(np, "num-cs",
@@ -709,7 +686,7 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 	} else if (num_cs > ZYNQ_QSPI_MAX_NUM_CS) {
 		ret = -EINVAL;
 		dev_err(&pdev->dev, "only 2 chip selects are available\n");
-		goto clk_dis_all;
+		goto remove_ctlr;
 	} else {
 		ctlr->num_chipselect = num_cs;
 	}
@@ -728,15 +705,11 @@ static int zynq_qspi_probe(struct platform_device *pdev)
 	ret = devm_spi_register_controller(&pdev->dev, ctlr);
 	if (ret) {
 		dev_err(&pdev->dev, "devm_spi_register_controller failed\n");
-		goto clk_dis_all;
+		goto remove_ctlr;
 	}
 
 	return ret;
 
-clk_dis_all:
-	clk_disable_unprepare(xqspi->refclk);
-clk_dis_pclk:
-	clk_disable_unprepare(xqspi->pclk);
 remove_ctlr:
 	spi_controller_put(ctlr);
 
@@ -758,9 +731,6 @@ static void zynq_qspi_remove(struct platform_device *pdev)
 	struct zynq_qspi *xqspi = platform_get_drvdata(pdev);
 
 	zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET, 0);
-
-	clk_disable_unprepare(xqspi->refclk);
-	clk_disable_unprepare(xqspi->pclk);
 }
 
 static const struct of_device_id zynq_qspi_of_match[] = {
-- 
cgit v1.2.3


From c5408d818316061d6063c11a4f47f1ba25a3a708 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Tue, 7 Apr 2026 10:54:58 +0200
Subject: ASoC: Intel: avs: Fix memory leak in avs_register_i2s_test_boards()

Caller is responsible for freeing array allocated with
parse_int_array().

Found out by Coverity.

Fixes: 7d859189de13 ("ASoC: Intel: avs: Allow to specify custom configurations with i2s_test")
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://patch.msgid.link/20260407085459.400628-1-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/avs/board_selection.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/avs/board_selection.c b/sound/soc/intel/avs/board_selection.c
index 8a46285181fa..dd0e7cd5a7dd 100644
--- a/sound/soc/intel/avs/board_selection.c
+++ b/sound/soc/intel/avs/board_selection.c
@@ -520,7 +520,8 @@ static int avs_register_i2s_test_boards(struct avs_dev *adev)
 	if (num_elems > max_ssps) {
 		dev_err(adev->dev, "board supports only %d SSP, %d specified\n",
 			max_ssps, num_elems);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto exit;
 	}
 
 	for (ssp_port = 0; ssp_port < num_elems; ssp_port++) {
@@ -528,11 +529,13 @@ static int avs_register_i2s_test_boards(struct avs_dev *adev)
 		for_each_set_bit(tdm_slot, &tdm_slots, 16) {
 			ret = avs_register_i2s_test_board(adev, ssp_port, tdm_slot);
 			if (ret)
-				return ret;
+				goto exit;
 		}
 	}
 
-	return 0;
+exit:
+	kfree(array);
+	return ret;
 }
 
 static int avs_register_i2s_board(struct avs_dev *adev, struct snd_soc_acpi_mach *mach)
-- 
cgit v1.2.3


From c2812c0cb909211a1d2e7cec862406e32833b9de Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 7 Apr 2026 14:14:53 +0200
Subject: MAINTAINERS, mailmap: Change Ulf Hansson's email

Change my email in MAINTAINERS and add a few entries in mailmap to start
using ulfh@kernel.org.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 .mailmap    |  2 ++
 MAINTAINERS | 14 +++++++-------
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/.mailmap b/.mailmap
index 2d04aeba68b4..22c5ab1c5d55 100644
--- a/.mailmap
+++ b/.mailmap
@@ -849,6 +849,8 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko.ursulin@onelan.co.uk>
 Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
+Ulf Hansson <ulfh@kernel.org> <ulf.hansson@linaro.org>
+Ulf Hansson <ulfh@kernel.org> <ulf.hansson@stericsson.com>
 Umang Jain <uajain@igalia.com> <umang.jain@ideasonboard.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index c3fe46d7c4bc..7167dcea737d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6716,7 +6716,7 @@ F:	include/linux/platform_data/cpuidle-exynos.h
 CPUIDLE DRIVER - ARM PSCI
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
 M:	Sudeep Holla <sudeep.holla@kernel.org>
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-pm@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
@@ -6724,7 +6724,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm.git
 F:	drivers/cpuidle/cpuidle-psci.c
 
 CPUIDLE DRIVER - ARM PSCI PM DOMAIN
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-pm@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
@@ -6733,7 +6733,7 @@ F:	drivers/cpuidle/cpuidle-psci-domain.c
 F:	drivers/cpuidle/cpuidle-psci.h
 
 CPUIDLE DRIVER - DT IDLE PM DOMAIN
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/linux-pm.git
@@ -10729,7 +10729,7 @@ F:	Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.yaml
 F:	drivers/i2c/muxes/i2c-demux-pinctrl.c
 
 GENERIC PM DOMAINS
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/power/power?domain*
@@ -18089,7 +18089,7 @@ F:	drivers/mmc/host/mmc_spi.c
 F:	include/linux/spi/mmc_spi.h
 
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
@@ -24696,7 +24696,7 @@ F:	drivers/media/i2c/imx415.c
 SONY MEMORYSTICK SUBSYSTEM
 M:	Maxim Levitsky <maximlevitsky@gmail.com>
 M:	Alex Dubov <oakad@yahoo.com>
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc.git
@@ -27615,7 +27615,7 @@ F:	Documentation/fb/uvesafb.rst
 F:	drivers/video/fbdev/uvesafb.*
 
 Ux500 CLOCK DRIVERS
-M:	Ulf Hansson <ulf.hansson@linaro.org>
+M:	Ulf Hansson <ulfh@kernel.org>
 L:	linux-clk@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-- 
cgit v1.2.3


From 8508e9118649f13f7b857e9e10147b241db615d7 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 7 Apr 2026 14:33:17 +0200
Subject: Revert "ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix
 headphone"

This reverts commit 56fbbe096a89ff4b52af78a21a4afd9d94bdcc80.

It caused regressions on other Gigabyte models, and looking at the
bugzilla entry again, the suggested change appears rather dubious, as
incorrectly setting the front mic pin as the headphone.

Fixes: 56fbbe096a89 ("ALSA: hda/realtek: Add quirk for Gigabyte Technology to fix headphone")
Cc: <stable@vger.kernel.org>
Reported-by: Marcin Krycki <m.krycki@gmail.com>
Reported-by: Theodoros Orfanidis <teoulas@gmail.com>
Closes: https://lore.kernel.org/CAEfRphPU_ABuVFzaHhspxgp2WAqi7kKNGo4yOOt0zeVFPSj8+Q@mail.gmail.com
Link: https://patch.msgid.link/20260407123333.171130-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc662.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/sound/hda/codecs/realtek/alc662.c b/sound/hda/codecs/realtek/alc662.c
index 3a943adf9087..5073165d1f3c 100644
--- a/sound/hda/codecs/realtek/alc662.c
+++ b/sound/hda/codecs/realtek/alc662.c
@@ -313,7 +313,6 @@ enum {
 	ALC897_FIXUP_HEADSET_MIC_PIN2,
 	ALC897_FIXUP_UNIS_H3C_X500S,
 	ALC897_FIXUP_HEADSET_MIC_PIN3,
-	ALC897_FIXUP_H610M_HP_PIN,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -767,13 +766,6 @@ static const struct hda_fixup alc662_fixups[] = {
 			{ }
 		},
 	},
-	[ALC897_FIXUP_H610M_HP_PIN] = {
-		.type = HDA_FIXUP_PINS,
-		.v.pins = (const struct hda_pintbl[]) {
-			{ 0x19, 0x0321403f }, /* HP out */
-			{ }
-		},
-	},
 };
 
 static const struct hda_quirk alc662_fixup_tbl[] = {
@@ -823,7 +815,6 @@ static const struct hda_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
 	SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2),
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
-	SND_PCI_QUIRK(0x1458, 0xa194, "H610M H V2 DDR4", ALC897_FIXUP_H610M_HP_PIN),
 	SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS),
 	SND_PCI_QUIRK(0x17aa, 0x1057, "Lenovo P360", ALC897_FIXUP_HEADSET_MIC_PIN),
-- 
cgit v1.2.3


From a9b8b18364fffce4c451e6f6fd218fa4ab646705 Mon Sep 17 00:00:00 2001
From: Muhammad Alifa Ramdhan <ramdhan@starlabs.sg>
Date: Fri, 3 Apr 2026 09:36:17 +0800
Subject: net/tls: fix use-after-free in -EBUSY error path of tls_do_encryption

The -EBUSY handling in tls_do_encryption(), introduced by commit
859054147318 ("net: tls: handle backlogging of crypto requests"), has
a use-after-free due to double cleanup of encrypt_pending and the
scatterlist entry.

When crypto_aead_encrypt() returns -EBUSY, the request is enqueued to
the cryptd backlog and the async callback tls_encrypt_done() will be
invoked upon completion. That callback unconditionally restores the
scatterlist entry (sge->offset, sge->length) and decrements
ctx->encrypt_pending. However, if tls_encrypt_async_wait() returns an
error, the synchronous error path in tls_do_encryption() performs the
same cleanup again, double-decrementing encrypt_pending and
double-restoring the scatterlist.

The double-decrement corrupts the encrypt_pending sentinel (initialized
to 1), making tls_encrypt_async_wait() permanently skip the wait for
pending async callbacks. A subsequent sendmsg can then free the
tls_rec via bpf_exec_tx_verdict() while a cryptd callback is still
pending, resulting in a use-after-free when the callback fires on the
freed record.

Fix this by skipping the synchronous cleanup when the -EBUSY async
wait returns an error, since the callback has already handled
encrypt_pending and sge restoration.

Fixes: 859054147318 ("net: tls: handle backlogging of crypto requests")
Cc: stable@vger.kernel.org
Signed-off-by: Muhammad Alifa Ramdhan <ramdhan@starlabs.sg>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20260403013617.2838875-1-ramdhan@starlabs.sg
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/tls/tls_sw.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index dd9dda759bbb..83e78a3d1e65 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -584,6 +584,16 @@ static int tls_do_encryption(struct sock *sk,
 	if (rc == -EBUSY) {
 		rc = tls_encrypt_async_wait(ctx);
 		rc = rc ?: -EINPROGRESS;
+		/*
+		 * The async callback tls_encrypt_done() has already
+		 * decremented encrypt_pending and restored the sge on
+		 * both success and error. Skip the synchronous cleanup
+		 * below on error, just remove the record and return.
+		 */
+		if (rc != -EINPROGRESS) {
+			list_del(&rec->list);
+			return rc;
+		}
 	}
 	if (!rc || rc != -EINPROGRESS) {
 		atomic_dec(&ctx->encrypt_pending);
-- 
cgit v1.2.3


From 82b915051d32a68ea3bbe261c93f5620699ff047 Mon Sep 17 00:00:00 2001
From: Josh Snyder <josh@code406.com>
Date: Thu, 2 Apr 2026 16:23:38 -0700
Subject: tick/nohz: Fix inverted return value in check_tick_dependency() fast
 path

Commit 56534673cea7f ("tick/nohz: Optimize check_tick_dependency() with
early return") added a fast path that returns !val when the tick_stop
tracepoint is disabled.

This is inverted: the slow path returns true when a dependency IS found
(val != 0), but !val returns true when val is zero (no dependency).  The
result is that can_stop_full_tick() sees "dependency found" when there are
none, and the tick never stops on nohz_full CPUs.

Fix this by returning !!val instead of !val, matching the slow-path semantics.

Fixes: 56534673cea7f ("tick/nohz: Optimize check_tick_dependency() with early return")
Signed-off-by: Josh Snyder <josh@code406.com>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Assisted-by: Claude:claude-opus-4-6
Link: https://patch.msgid.link/20260402-fix-idle-tick2-v1-1-eecb589649d3@code406.com
---
 kernel/time/tick-sched.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f7907fadd63f..36449f0010a4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -345,7 +345,7 @@ static bool check_tick_dependency(atomic_t *dep)
 	int val = atomic_read(dep);
 
 	if (likely(!tracepoint_enabled(tick_stop)))
-		return !val;
+		return !!val;
 
 	if (val & TICK_DEP_MASK_POSIX_TIMER) {
 		trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
-- 
cgit v1.2.3


From b1baaff4e5231f0d7db209f72a43112cd2d29257 Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Tue, 7 Apr 2026 16:27:19 +0300
Subject: regulator: bd71828-regulator.c: Fix LDON-HEAD mode

The ROHM BD72720 supports so called LDON-HEAD -mode, in which the buck10
is expected to be supplying power for an LDO. In this mode, the buck10
voltage will follow what is set for the LDO, on order to lower the
power-loss in the LDO.

This hardware configuration can be adverticed via the device-tree. When
this is done, the Linux driver should omit registering the voltage
control operations for the buck10, because the voltage control is now
done by the hardware.

This is done by modifying the buck10 regulator descriptor, before
passing it to the regulator registration functions. There is an
off-by-one error when the regulator descriptor array is indexed, and
wrong descriptor is modified causing the LDO1 operations to be modified
instead of the BUCK10 operations.

Fix this by correcting the indexing.

Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Fixes: f16a9d76a71d ("regulator: bd71828: Support ROHM BD72720")
Link: https://patch.msgid.link/e7eef0bd407522ae5d9b7d0c4ec43f40b1dba833.1775565148.git.mazziesaccount@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd71828-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/bd71828-regulator.c b/drivers/regulator/bd71828-regulator.c
index c8f3343cfe23..473beb4399d9 100644
--- a/drivers/regulator/bd71828-regulator.c
+++ b/drivers/regulator/bd71828-regulator.c
@@ -785,7 +785,7 @@ static const struct bd71828_regulator_data bd71828_rdata[] = {
 	},
 };
 
-#define BD72720_BUCK10_DESC_INDEX 10
+#define BD72720_BUCK10_DESC_INDEX 9
 #define BD72720_NUM_BUCK_VOLTS 0x100
 #define BD72720_NUM_LDO_VOLTS 0x100
 #define BD72720_NUM_LDO12346_VOLTS 0x80
-- 
cgit v1.2.3


From 3ffe5eb4a5f248c0d4b849f050af973396656f85 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.ibm.com>
Date: Tue, 7 Apr 2026 18:17:21 +0200
Subject: KVM: s390: vsie: Fix races with partial gmap invalidations

Introduce a new boolean flag, used for shadow gmaps, to keep track of
whether the gmap has been invalidated, either partially or totally.

Use the new flag to check whether shadow gmap invalidations happened
during shadowing. In such cases, abort whatever was going on, return
-EAGAIN and let the caller try again.

Fixes: 19d6c5b80443 ("KVM: s390: vsie: Fix unshadowing while shadowing")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20260407161721.247044-1-imbrenda@linux.ibm.com>
---
 arch/s390/kvm/gaccess.c | 9 +++++----
 arch/s390/kvm/gmap.c    | 3 +++
 arch/s390/kvm/gmap.h    | 1 +
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 53a8550e7102..290e03a13a95 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -1449,7 +1449,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union
 	pgste_set_unlock(ptep_h, pgste);
 	if (rc)
 		return rc;
-	if (!sg->parent)
+	if (sg->invalidated)
 		return -EAGAIN;
 
 	newpte = _pte(f->pfn, 0, !p, 0);
@@ -1479,7 +1479,7 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 
 	do {
 		/* _gmap_crstep_xchg_atomic() could have unshadowed this shadow gmap */
-		if (!sg->parent)
+		if (sg->invalidated)
 			return -EAGAIN;
 		oldcrste = READ_ONCE(*host);
 		newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, f->writable, !p);
@@ -1492,7 +1492,7 @@ static int _do_shadow_crste(struct gmap *sg, gpa_t raddr, union crste *host, uni
 		if (!newcrste.h.p && !f->writable)
 			return -EOPNOTSUPP;
 	} while (!_gmap_crstep_xchg_atomic(sg->parent, host, oldcrste, newcrste, f->gfn, false));
-	if (!sg->parent)
+	if (sg->invalidated)
 		return -EAGAIN;
 
 	newcrste = _crste_fc1(f->pfn, oldcrste.h.tt, 0, !p);
@@ -1545,7 +1545,7 @@ static int _gaccess_do_shadow(struct kvm_s390_mmu_cache *mc, struct gmap *sg,
 				       entries[i].pfn, i + 1, entries[i].writable);
 		if (rc)
 			return rc;
-		if (!sg->parent)
+		if (sg->invalidated)
 			return -EAGAIN;
 	}
 
@@ -1601,6 +1601,7 @@ again:
 		scoped_guard(spinlock, &parent->children_lock) {
 			if (READ_ONCE(sg->parent) != parent)
 				return -EAGAIN;
+			sg->invalidated = false;
 			rc = _gaccess_do_shadow(vcpu->arch.mc, sg, saddr, walk);
 		}
 		if (rc == -ENOMEM)
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
index 645c32c767d2..0111d31e0386 100644
--- a/arch/s390/kvm/gmap.c
+++ b/arch/s390/kvm/gmap.c
@@ -181,6 +181,7 @@ void gmap_remove_child(struct gmap *child)
 
 	list_del(&child->list);
 	child->parent = NULL;
+	child->invalidated = true;
 }
 
 /**
@@ -1069,6 +1070,7 @@ static void gmap_unshadow_level(struct gmap *sg, gfn_t r_gfn, int level)
 	if (level > TABLE_TYPE_PAGE_TABLE)
 		align = 1UL << (11 * level + _SEGMENT_SHIFT);
 	kvm_s390_vsie_gmap_notifier(sg, ALIGN_DOWN(gaddr, align), ALIGN(gaddr + 1, align));
+	sg->invalidated = true;
 	if (dat_entry_walk(NULL, r_gfn, sg->asce, 0, level, &crstep, &ptep))
 		return;
 	if (ptep) {
@@ -1174,6 +1176,7 @@ static inline int __gmap_protect_asce_top_level(struct kvm_s390_mmu_cache *mc, s
 	scoped_guard(spinlock, &parent->children_lock) {
 		if (READ_ONCE(sg->parent) != parent)
 			return -EAGAIN;
+		sg->invalidated = false;
 		for (i = 0; i < CRST_TABLE_PAGES; i++) {
 			if (!context->f[i].valid)
 				continue;
diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h
index 579399ef5480..31ea13fda142 100644
--- a/arch/s390/kvm/gmap.h
+++ b/arch/s390/kvm/gmap.h
@@ -60,6 +60,7 @@ enum gmap_flags {
 struct gmap {
 	unsigned long flags;
 	unsigned char edat_level;
+	bool invalidated;
 	struct kvm *kvm;
 	union asce asce;
 	struct list_head list;
-- 
cgit v1.2.3


From 705355a82b8ea86e0afe44560e970eedc74c05d3 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Mon, 6 Apr 2026 14:40:42 +0530
Subject: MAINTAINERS: Update AMD SPI driver maintainers

Due to additional responsibilities, Raju Rangoju will no longer be
supporting AMD SPI driver. Maintenance will be handled by Krishnamoorthi
going forward.

Cc: Krishnamoorthi M <krishnamoorthi.m@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260406091042.4065767-1-Raju.Rangoju@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c3fe46d7c4bc..213f6a294a9f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1272,6 +1272,7 @@ F:	drivers/hid/amd-sfh-hid/
 
 AMD SPI DRIVER
 M:	Raju Rangoju <Raju.Rangoju@amd.com>
+M:	Krishnamoorthi M <krishnamoorthi.m@amd.com>
 L:	linux-spi@vger.kernel.org
 S:	Supported
 F:	drivers/spi/spi-amd-pci.c
-- 
cgit v1.2.3


From 7596459f3c93d8d45a1bf12d4d7526b50c15baa2 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Tue, 31 Mar 2026 18:27:10 -0700
Subject: drm/xe: Fix bug in idledly unit conversion

We only need to convert to picosecond units before writing to RING_IDLEDLY.

Fixes: 7c53ff050ba8 ("drm/xe: Apply Wa_16023105232")
Cc: Tangudu Tilak Tirumalesh <tilak.tirumalesh.tangudu@intel.com>
Acked-by: Tangudu Tilak Tirumalesh <tilak.tirumalesh.tangudu@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://patch.msgid.link/20260401012710.4165547-1-vinay.belgaumkar@intel.com
(cherry picked from commit 13743bd628bc9d9a0e2fe53488b2891aedf7cc74)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hw_engine.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 688d645e0e73..aa0b7a427f0b 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -595,9 +595,8 @@ static void adjust_idledly(struct xe_hw_engine *hwe)
 		maxcnt *= maxcnt_units_ns;
 
 		if (xe_gt_WARN_ON(gt, idledly >= maxcnt || inhibit_switch)) {
-			idledly = DIV_ROUND_CLOSEST(((maxcnt - 1) * maxcnt_units_ns),
+			idledly = DIV_ROUND_CLOSEST(((maxcnt - 1) * 1000),
 						    idledly_units_ps);
-			idledly = DIV_ROUND_CLOSEST(idledly, 1000);
 			xe_mmio_write32(&gt->mmio, RING_IDLEDLY(hwe->mmio_base), idledly);
 		}
 	}
-- 
cgit v1.2.3


From 95aca8602ef70ffd3d971675751c81826e124f90 Mon Sep 17 00:00:00 2001
From: John Pavlick <jspavlick@posteo.net>
Date: Mon, 6 Apr 2026 13:23:33 +0000
Subject: net: sfp: add quirks for Hisense and HSGQ GPON ONT SFP modules

Several GPON ONT SFP sticks based on Realtek RTL960x report
1000BASE-LX at 1300MBd in their EEPROM but can operate at 2500base-X.
On hosts capable of 2500base-X (e.g. Banana Pi R3 / MT7986), the
kernel negotiates only 1G because it trusts the incorrect EEPROM data.

Add quirks for:
- Hisense-Leox LXT-010S-H
- Hisense ZNID-GPON-2311NA
- HSGQ HSGQ-XPON-Stick

Each quirk advertises 2500base-X and ignores TX_FAULT during the
module's ~40s Linux boot time.

Tested on Banana Pi R3 (MT7986) with OpenWrt 25.12.1, confirmed
2.5Gbps link and full throughput with flow offloading.

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Suggested-by: Marcin Nita <marcin.nita@leolabs.pl>
Signed-off-by: John Pavlick <jspavlick@posteo.net>
Link: https://patch.msgid.link/20260406132321.72563-1-jspavlick@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index ce8924613363..6b7b8ae15d10 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -543,6 +543,22 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex,
 		  sfp_fixup_ignore_tx_fault_and_los),
 
+	// Hisense LXT-010S-H is a GPON ONT SFP (sold as LEOX LXT-010S-H) that
+	// can operate at 2500base-X, but reports 1000BASE-LX / 1300MBd in its
+	// EEPROM
+	SFP_QUIRK("Hisense-Leox", "LXT-010S-H", sfp_quirk_2500basex,
+		  sfp_fixup_ignore_tx_fault),
+
+	// Hisense ZNID-GPON-2311NA can operate at 2500base-X, but reports
+	// 1000BASE-LX / 1300MBd in its EEPROM
+	SFP_QUIRK("Hisense", "ZNID-GPON-2311NA", sfp_quirk_2500basex,
+		  sfp_fixup_ignore_tx_fault),
+
+	// HSGQ HSGQ-XPON-Stick can operate at 2500base-X, but reports
+	// 1000BASE-LX / 1300MBd in its EEPROM
+	SFP_QUIRK("HSGQ", "HSGQ-XPON-Stick", sfp_quirk_2500basex,
+		  sfp_fixup_ignore_tx_fault),
+
 	// Lantech 8330-262D-E and 8330-265D can operate at 2500base-X, but
 	// incorrectly report 2500MBd NRZ in their EEPROM.
 	// Some 8330-265D modules have inverted LOS, while all of them report
-- 
cgit v1.2.3


From f2777d5cb5c094e20f2323d953b1740baee5f8e8 Mon Sep 17 00:00:00 2001
From: Johan Alvarado <contact@c127.dev>
Date: Mon, 6 Apr 2026 07:44:25 +0000
Subject: net: stmmac: dwmac-motorcomm: fix eFUSE MAC address read failure

This patch fixes an issue where reading the MAC address from the eFUSE
fails due to a race condition.

The root cause was identified by comparing the driver's behavior with a
custom U-Boot port. In U-Boot, the MAC address was read successfully
every time because the driver was loaded later in the boot process, giving
the hardware ample time to initialize. In Linux, reading the eFUSE
immediately returns all zeros, resulting in a fallback to a random MAC address.

Hardware cold-boot testing revealed that the eFUSE controller requires a
short settling time to load its internal data. Adding a 2000-5000us
delay after the reset ensures the hardware is fully ready, allowing the
native MAC address to be read consistently.

Fixes: 02ff155ea281 ("net: stmmac: Add glue driver for Motorcomm YT6801 ethernet controller")
Reported-by: Georg Gottleuber <ggo@tuxedocomputers.com>
Closes: https://lore.kernel.org/24cfefff-1233-4745-8c47-812b502d5d19@tuxedocomputers.com
Signed-off-by: Johan Alvarado <contact@c127.dev>
Reviewed-by: Yao Zi <me@ziyao.cc>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/fc5992a4-9532-49c3-8ec1-c2f8c5b84ca1@smtp-relay.sendinblue.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-motorcomm.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-motorcomm.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-motorcomm.c
index 8b45b9cf7202..663d87ccfa0f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-motorcomm.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-motorcomm.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/bits.h>
+#include <linux/delay.h>
 #include <linux/dev_printk.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -334,6 +335,13 @@ static int motorcomm_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	motorcomm_reset(priv);
 
+	/*
+	 * After system reset, the eFuse controller needs time to load
+	 * its internal data. Without this delay, eFuse reads return
+	 * all zeros, causing MAC address detection to fail.
+	 */
+	usleep_range(2000, 5000);
+
 	ret = motorcomm_efuse_read_mac(&pdev->dev, priv, res.mac);
 	if (ret == -ENOENT) {
 		dev_warn(&pdev->dev, "eFuse contains no valid MAC address\n");
-- 
cgit v1.2.3


From 944b3b734cfbbe9502274c092bc3b8220764cc92 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 3 Apr 2026 17:19:38 -0700
Subject: net: avoid nul-deref trying to bind mp to incapable device

Sashiko points out that we use qops in __net_mp_open_rxq()
but never validate they are null. This was introduced when
check was moved from netdev_rx_queue_restart().

Look at ops directly instead of the locking config.
qops imply netdev_need_ops_lock(). We used netdev_need_ops_lock()
initially to signify that the real_num_rx_queues check below
is safe without rtnl_lock, but I'm not sure if this is actually
clear to most people, anyway.

Fixes: da7772a2b4ad ("net: move mp->rx_page_size validation to __net_mp_open_rxq()")
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20260404001938.2425670-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netdev_rx_queue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 668a90658f25..05fd2875d725 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -117,7 +117,7 @@ int __net_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 	struct netdev_rx_queue *rxq;
 	int ret;
 
-	if (!netdev_need_ops_lock(dev))
+	if (!qops)
 		return -EOPNOTSUPP;
 
 	if (rxq_idx >= dev->real_num_rx_queues) {
-- 
cgit v1.2.3


From efaa71faf212324ecbf6d5339e9717fe53254f58 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sun, 5 Apr 2026 22:29:19 +0100
Subject: selftests: net: bridge_vlan_mcast: wait for h1 before querier check

The querier-interval test adds h1 (currently a slave of the VRF created
by simple_if_init) to a temporary bridge br1 acting as an outside IGMP
querier. The kernel VRF driver (drivers/net/vrf.c) calls cycle_netdev()
on every slave add and remove, toggling the interface admin-down then up.
Phylink takes the PHY down during the admin-down half of that cycle.
Since h1 and swp1 are cable-connected, swp1 also loses its link may need
several seconds to re-negotiate.

Use setup_wait_dev $h1 0 which waits for h1 to return to UP state, so the
test can rely on the link being back up at this point.

Fixes: 4d8610ee8bd77 ("selftests: net: bridge: add vlan mcast_querier_interval tests")
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Link: https://patch.msgid.link/c830f130860fd2efae08bfb9e5b25fd028e58ce5.1775424423.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
index 72dfbeaf56b9..e8031f68200a 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh
@@ -414,6 +414,7 @@ vlmc_querier_intvl_test()
 	bridge vlan add vid 10 dev br1 self pvid untagged
 	ip link set dev $h1 master br1
 	ip link set dev br1 up
+	setup_wait_dev $h1 0
 	bridge vlan add vid 10 dev $h1 master
 	bridge vlan global set vid 10 dev br1 mcast_snooping 1 mcast_querier 1
 	sleep 2
-- 
cgit v1.2.3


From c3812651b522fe8437ebb7063b75ddb95b571643 Mon Sep 17 00:00:00 2001
From: Andrea Mayer <andrea.mayer@uniroma2.it>
Date: Sat, 4 Apr 2026 02:44:04 +0200
Subject: seg6: separate dst_cache for input and output paths in seg6 lwtunnel

The seg6 lwtunnel uses a single dst_cache per encap route, shared
between seg6_input_core() and seg6_output_core(). These two paths
can perform the post-encap SID lookup in different routing contexts
(e.g., ip rules matching on the ingress interface, or VRF table
separation). Whichever path runs first populates the cache, and the
other reuses it blindly, bypassing its own lookup.

Fix this by splitting the cache into cache_input and cache_output,
so each path maintains its own cached dst independently.

Fixes: 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and injection with lwtunnels")
Cc: stable@vger.kernel.org
Signed-off-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Justin Iurman <justin.iurman@gmail.com>
Link: https://patch.msgid.link/20260404004405.4057-2-andrea.mayer@uniroma2.it
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/seg6_iptunnel.c | 34 +++++++++++++++++++++++-----------
 1 file changed, 23 insertions(+), 11 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 3e1b9991131a..d6a0f7df9080 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -48,7 +48,8 @@ static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
 }
 
 struct seg6_lwt {
-	struct dst_cache cache;
+	struct dst_cache cache_input;
+	struct dst_cache cache_output;
 	struct seg6_iptunnel_encap tuninfo[];
 };
 
@@ -488,7 +489,7 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	slwt = seg6_lwt_lwtunnel(lwtst);
 
 	local_bh_disable();
-	dst = dst_cache_get(&slwt->cache);
+	dst = dst_cache_get(&slwt->cache_input);
 	local_bh_enable();
 
 	err = seg6_do_srh(skb, dst);
@@ -504,7 +505,7 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 		/* cache only if we don't create a dst reference loop */
 		if (!dst->error && lwtst != dst->lwtstate) {
 			local_bh_disable();
-			dst_cache_set_ip6(&slwt->cache, dst,
+			dst_cache_set_ip6(&slwt->cache_input, dst,
 					  &ipv6_hdr(skb)->saddr);
 			local_bh_enable();
 		}
@@ -564,7 +565,7 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
 
 	local_bh_disable();
-	dst = dst_cache_get(&slwt->cache);
+	dst = dst_cache_get(&slwt->cache_output);
 	local_bh_enable();
 
 	err = seg6_do_srh(skb, dst);
@@ -591,7 +592,7 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 		/* cache only if we don't create a dst reference loop */
 		if (orig_dst->lwtstate != dst->lwtstate) {
 			local_bh_disable();
-			dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+			dst_cache_set_ip6(&slwt->cache_output, dst, &fl6.saddr);
 			local_bh_enable();
 		}
 
@@ -701,11 +702,13 @@ static int seg6_build_state(struct net *net, struct nlattr *nla,
 
 	slwt = seg6_lwt_lwtunnel(newts);
 
-	err = dst_cache_init(&slwt->cache, GFP_ATOMIC);
-	if (err) {
-		kfree(newts);
-		return err;
-	}
+	err = dst_cache_init(&slwt->cache_input, GFP_ATOMIC);
+	if (err)
+		goto err_free_newts;
+
+	err = dst_cache_init(&slwt->cache_output, GFP_ATOMIC);
+	if (err)
+		goto err_destroy_input;
 
 	memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
 
@@ -720,11 +723,20 @@ static int seg6_build_state(struct net *net, struct nlattr *nla,
 	*ts = newts;
 
 	return 0;
+
+err_destroy_input:
+	dst_cache_destroy(&slwt->cache_input);
+err_free_newts:
+	kfree(newts);
+	return err;
 }
 
 static void seg6_destroy_state(struct lwtunnel_state *lwt)
 {
-	dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
+	struct seg6_lwt *slwt = seg6_lwt_lwtunnel(lwt);
+
+	dst_cache_destroy(&slwt->cache_input);
+	dst_cache_destroy(&slwt->cache_output);
 }
 
 static int seg6_fill_encap_info(struct sk_buff *skb,
-- 
cgit v1.2.3


From 32dfd742f06a68fac6499a58f52025990c854031 Mon Sep 17 00:00:00 2001
From: Andrea Mayer <andrea.mayer@uniroma2.it>
Date: Sat, 4 Apr 2026 02:44:05 +0200
Subject: selftests: seg6: add test for dst_cache isolation in seg6 lwtunnel

Add a selftest that verifies the dst_cache in seg6 lwtunnel is not
shared between the input (forwarding) and output (locally generated)
paths.

The test creates three namespaces (ns_src, ns_router, ns_dst)
connected in a line. An SRv6 encap route on ns_router encapsulates
traffic destined to cafe::1 with SID fc00::100. The SID is
reachable only for forwarded traffic (from ns_src) via an ip rule
matching the ingress interface (iif veth-r0 lookup 100), and
blackholed in the main table.

The test verifies that:

  1. A packet generated locally on ns_router does not reach
     ns_dst with an empty cache, since the SID is blackholed;
  2. A forwarded packet from ns_src populates the input cache
     from table 100 and reaches ns_dst;
  3. A packet generated locally on ns_router still does not
     reach ns_dst after the input cache is populated,
     confirming the output path does not reuse the input
     cache entry.

Both the forwarded and local packets are pinned to the same CPU
with taskset, since dst_cache is per-cpu.

Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Justin Iurman <justin.iurman@gmail.com>
Link: https://patch.msgid.link/20260404004405.4057-3-andrea.mayer@uniroma2.it
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile               |   1 +
 tools/testing/selftests/net/srv6_iptunnel_cache.sh | 197 +++++++++++++++++++++
 2 files changed, 198 insertions(+)
 create mode 100755 tools/testing/selftests/net/srv6_iptunnel_cache.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 605c54c0e8a3..c709523c99c6 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -89,6 +89,7 @@ TEST_PROGS := \
 	srv6_end_x_next_csid_l3vpn_test.sh \
 	srv6_hencap_red_l3vpn_test.sh \
 	srv6_hl2encap_red_l2vpn_test.sh \
+	srv6_iptunnel_cache.sh \
 	stress_reuseport_listen.sh \
 	tcp_fastopen_backup_key.sh \
 	test_bpf.sh \
diff --git a/tools/testing/selftests/net/srv6_iptunnel_cache.sh b/tools/testing/selftests/net/srv6_iptunnel_cache.sh
new file mode 100755
index 000000000000..62638ab679d9
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_iptunnel_cache.sh
@@ -0,0 +1,197 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+
+# This test verifies that the seg6 lwtunnel does not share the dst_cache
+# between the input (forwarding) and output (locally generated) paths.
+#
+# A shared dst_cache allows a forwarded packet to populate the cache and a
+# subsequent locally generated packet to silently reuse that entry, bypassing
+# its own route lookup. To expose this, the SID is made reachable only for
+# forwarded traffic (via an ip rule matching iif) and blackholed for everything
+# else. A local ping on ns_router must always hit the blackhole;
+# if it succeeds after a forwarded packet has populated the
+# cache, the bug is confirmed.
+#
+# Both forwarded and local packets are pinned to the same CPU with taskset,
+# since dst_cache is per-cpu.
+#
+#
+# +--------------------+                        +--------------------+
+# |      ns_src        |                        |      ns_dst        |
+# |                    |                        |                    |
+# |  veth-s0           |                        |           veth-d0  |
+# |  fd00::1/64        |                        |        fd01::2/64  |
+# +-------+------------+                        +----------+---------+
+#         |                                                |
+#         |            +--------------------+              |
+#         |            |     ns_router      |              |
+#         |            |                    |              |
+#         +------------+ veth-r0    veth-r1 +--------------+
+#                      | fd00::2    fd01::1 |
+#                      +--------------------+
+#
+#
+# ns_router: encap (main table)
+# +---------+---------------------------------------+
+# | dst     | action                                |
+# +---------+---------------------------------------+
+# | cafe::1 | encap seg6 mode encap segs fc00::100  |
+# +---------+---------------------------------------+
+#
+# ns_router: post-encap SID resolution
+# +-------+------------+----------------------------+
+# | table | dst        | action                     |
+# +-------+------------+----------------------------+
+# | 100   | fc00::100  | via fd01::2 dev veth-r1    |
+# +-------+------------+----------------------------+
+# | main  | fc00::100  | blackhole                  |
+# +-------+------------+----------------------------+
+#
+# ns_router: ip rule
+# +------------------+------------------------------+
+# | match            | action                       |
+# +------------------+------------------------------+
+# | iif veth-r0      | lookup 100                   |
+# +------------------+------------------------------+
+#
+# ns_dst: SRv6 decap (main table)
+# +--------------+----------------------------------+
+# | SID          | action                           |
+# +--------------+----------------------------------+
+# | fc00::100    | End.DT6 table 255 (local)        |
+# +--------------+----------------------------------+
+
+source lib.sh
+
+readonly SID="fc00::100"
+readonly DEST="cafe::1"
+
+readonly SRC_MAC="02:00:00:00:00:01"
+readonly RTR_R0_MAC="02:00:00:00:00:02"
+readonly RTR_R1_MAC="02:00:00:00:00:03"
+readonly DST_MAC="02:00:00:00:00:04"
+
+cleanup()
+{
+	cleanup_ns "${NS_SRC}" "${NS_RTR}" "${NS_DST}"
+}
+
+check_prerequisites()
+{
+	if ! command -v ip &>/dev/null; then
+		echo "SKIP: ip tool not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v ping &>/dev/null; then
+		echo "SKIP: ping not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v sysctl &>/dev/null; then
+		echo "SKIP: sysctl not found"
+		exit "${ksft_skip}"
+	fi
+
+	if ! command -v taskset &>/dev/null; then
+		echo "SKIP: taskset not found"
+		exit "${ksft_skip}"
+	fi
+}
+
+setup()
+{
+	setup_ns NS_SRC NS_RTR NS_DST
+
+	ip link add veth-s0 netns "${NS_SRC}" type veth \
+		peer name veth-r0 netns "${NS_RTR}"
+	ip link add veth-r1 netns "${NS_RTR}" type veth \
+		peer name veth-d0 netns "${NS_DST}"
+
+	ip -n "${NS_SRC}" link set veth-s0 address "${SRC_MAC}"
+	ip -n "${NS_RTR}" link set veth-r0 address "${RTR_R0_MAC}"
+	ip -n "${NS_RTR}" link set veth-r1 address "${RTR_R1_MAC}"
+	ip -n "${NS_DST}" link set veth-d0 address "${DST_MAC}"
+
+	# ns_src
+	ip -n "${NS_SRC}" link set veth-s0 up
+	ip -n "${NS_SRC}" addr add fd00::1/64 dev veth-s0 nodad
+	ip -n "${NS_SRC}" -6 route add "${DEST}"/128 via fd00::2
+
+	# ns_router
+	ip -n "${NS_RTR}" link set veth-r0 up
+	ip -n "${NS_RTR}" addr add fd00::2/64 dev veth-r0 nodad
+	ip -n "${NS_RTR}" link set veth-r1 up
+	ip -n "${NS_RTR}" addr add fd01::1/64 dev veth-r1 nodad
+	ip netns exec "${NS_RTR}" sysctl -qw net.ipv6.conf.all.forwarding=1
+
+	ip -n "${NS_RTR}" -6 route add "${DEST}"/128 \
+		encap seg6 mode encap segs "${SID}" dev veth-r0
+	ip -n "${NS_RTR}" -6 route add "${SID}"/128 table 100 \
+		via fd01::2 dev veth-r1
+	ip -n "${NS_RTR}" -6 route add blackhole "${SID}"/128
+	ip -n "${NS_RTR}" -6 rule add iif veth-r0 lookup 100
+
+	# ns_dst
+	ip -n "${NS_DST}" link set veth-d0 up
+	ip -n "${NS_DST}" addr add fd01::2/64 dev veth-d0 nodad
+	ip -n "${NS_DST}" addr add "${DEST}"/128 dev lo nodad
+	ip -n "${NS_DST}" -6 route add "${SID}"/128 \
+		encap seg6local action End.DT6 table 255 dev veth-d0
+	ip -n "${NS_DST}" -6 route add fd00::/64 via fd01::1
+
+	# static neighbors
+	ip -n "${NS_SRC}" -6 neigh add fd00::2 dev veth-s0 \
+		lladdr "${RTR_R0_MAC}" nud permanent
+	ip -n "${NS_RTR}" -6 neigh add fd00::1 dev veth-r0 \
+		lladdr "${SRC_MAC}" nud permanent
+	ip -n "${NS_RTR}" -6 neigh add fd01::2 dev veth-r1 \
+		lladdr "${DST_MAC}" nud permanent
+	ip -n "${NS_DST}" -6 neigh add fd01::1 dev veth-d0 \
+		lladdr "${RTR_R1_MAC}" nud permanent
+}
+
+test_cache_isolation()
+{
+	RET=0
+
+	# local ping with empty cache: must fail (SID is blackholed)
+	if ip netns exec "${NS_RTR}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "SKIP: local ping succeeded, topology broken"
+		exit "${ksft_skip}"
+	fi
+
+	# forward from ns_src to populate the input cache
+	if ! ip netns exec "${NS_SRC}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "SKIP: forwarded ping failed, topology broken"
+		exit "${ksft_skip}"
+	fi
+
+	# local ping again: must still fail; if the output path reuses
+	# the input cache, it bypasses the blackhole and the ping succeeds
+	if ip netns exec "${NS_RTR}" taskset -c 0 \
+			ping -c 1 -W 2 "${DEST}" &>/dev/null; then
+		echo "FAIL: output path used dst cached by input path"
+		RET="${ksft_fail}"
+	else
+		echo "PASS: output path dst_cache is independent"
+	fi
+
+	return "${RET}"
+}
+
+if [ "$(id -u)" -ne 0 ]; then
+	echo "SKIP: Need root privileges"
+	exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+check_prerequisites
+setup
+test_cache_isolation
+exit "${RET}"
-- 
cgit v1.2.3


From 4cda78d6f8bf2b700529f2fbccb994c3e826d7c2 Mon Sep 17 00:00:00 2001
From: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Date: Tue, 7 Apr 2026 12:50:31 +0500
Subject: Input: uinput - fix circular locking dependency with ff-core

A lockdep circular locking dependency warning can be triggered
reproducibly when using a force-feedback gamepad with uinput (for
example, playing ELDEN RING under Wine with a Flydigi Vader 5
controller):

  ff->mutex -> udev->mutex -> input_mutex -> dev->mutex -> ff->mutex

The cycle is caused by four lock acquisition paths:

1. ff upload: input_ff_upload() holds ff->mutex and calls
   uinput_dev_upload_effect() -> uinput_request_submit() ->
   uinput_request_send(), which acquires udev->mutex.

2. device create: uinput_ioctl_handler() holds udev->mutex and calls
   uinput_create_device() -> input_register_device(), which acquires
   input_mutex.

3. device register: input_register_device() holds input_mutex and
   calls kbd_connect() -> input_register_handle(), which acquires
   dev->mutex.

4. evdev release: evdev_release() calls input_flush_device() under
   dev->mutex, which calls input_ff_flush() acquiring ff->mutex.

Fix this by introducing a new state_lock spinlock to protect
udev->state and udev->dev access in uinput_request_send() instead of
acquiring udev->mutex.  The function only needs to atomically check
device state and queue an input event into the ring buffer via
uinput_dev_event() -- both operations are safe under a spinlock
(ktime_get_ts64() and wake_up_interruptible() do not sleep).  This
breaks the ff->mutex -> udev->mutex link since a spinlock is a leaf in
the lock ordering and cannot form cycles with mutexes.

To keep state transitions visible to uinput_request_send(), protect
writes to udev->state in uinput_create_device() and
uinput_destroy_device() with the same state_lock spinlock.

Additionally, move init_completion(&request->done) from
uinput_request_send() to uinput_request_submit() before
uinput_request_reserve_slot().  Once the slot is allocated,
uinput_flush_requests() may call complete() on it at any time from
the destroy path, so the completion must be initialised before the
request becomes visible.

Lock ordering after the fix:

  ff->mutex -> state_lock (spinlock, leaf)
  udev->mutex -> state_lock (spinlock, leaf)
  udev->mutex -> input_mutex -> dev->mutex -> ff->mutex (no back-edge)

Fixes: ff462551235d ("Input: uinput - switch to the new FF interface")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/CABXGCsMoxag+kEwHhb7KqhuyxfmGGd0P=tHZyb1uKE0pLr8Hkg@mail.gmail.com/
Signed-off-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Link: https://patch.msgid.link/20260407075031.38351-1-mikhail.v.gavrilov@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/uinput.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 13336a2fd49c..a973e82205b5 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -57,6 +57,7 @@ struct uinput_device {
 	struct input_dev	*dev;
 	struct mutex		mutex;
 	enum uinput_state	state;
+	spinlock_t		state_lock;
 	wait_queue_head_t	waitq;
 	unsigned char		ready;
 	unsigned char		head;
@@ -146,19 +147,15 @@ static void uinput_request_release_slot(struct uinput_device *udev,
 static int uinput_request_send(struct uinput_device *udev,
 			       struct uinput_request *request)
 {
-	int retval;
+	int retval = 0;
 
-	retval = mutex_lock_interruptible(&udev->mutex);
-	if (retval)
-		return retval;
+	spin_lock(&udev->state_lock);
 
 	if (udev->state != UIST_CREATED) {
 		retval = -ENODEV;
 		goto out;
 	}
 
-	init_completion(&request->done);
-
 	/*
 	 * Tell our userspace application about this new request
 	 * by queueing an input event.
@@ -166,7 +163,7 @@ static int uinput_request_send(struct uinput_device *udev,
 	uinput_dev_event(udev->dev, EV_UINPUT, request->code, request->id);
 
  out:
-	mutex_unlock(&udev->mutex);
+	spin_unlock(&udev->state_lock);
 	return retval;
 }
 
@@ -175,6 +172,13 @@ static int uinput_request_submit(struct uinput_device *udev,
 {
 	int retval;
 
+	/*
+	 * Initialize completion before allocating the request slot.
+	 * Once the slot is allocated, uinput_flush_requests() may
+	 * complete it at any time, so it must be initialized first.
+	 */
+	init_completion(&request->done);
+
 	retval = uinput_request_reserve_slot(udev, request);
 	if (retval)
 		return retval;
@@ -289,7 +293,14 @@ static void uinput_destroy_device(struct uinput_device *udev)
 	struct input_dev *dev = udev->dev;
 	enum uinput_state old_state = udev->state;
 
+	/*
+	 * Update state under state_lock so that concurrent
+	 * uinput_request_send() sees the state change before we
+	 * flush pending requests and tear down the device.
+	 */
+	spin_lock(&udev->state_lock);
 	udev->state = UIST_NEW_DEVICE;
+	spin_unlock(&udev->state_lock);
 
 	if (dev) {
 		name = dev->name;
@@ -366,7 +377,9 @@ static int uinput_create_device(struct uinput_device *udev)
 	if (error)
 		goto fail2;
 
+	spin_lock(&udev->state_lock);
 	udev->state = UIST_CREATED;
+	spin_unlock(&udev->state_lock);
 
 	return 0;
 
@@ -384,6 +397,7 @@ static int uinput_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	mutex_init(&newdev->mutex);
+	spin_lock_init(&newdev->state_lock);
 	spin_lock_init(&newdev->requests_lock);
 	init_waitqueue_head(&newdev->requests_waitq);
 	init_waitqueue_head(&newdev->waitq);
-- 
cgit v1.2.3


From 828ec7f803f41588a120e6d804297e74a482ab9d Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Tue, 7 Apr 2026 15:41:48 +0300
Subject: gpio: bd72720: handle missing regmap

Currently the probe does not check whether getting the regmap succeeded.
This can cause crash when regmap is used, if it wasn't successfully
obtained. Failing to get the regmap is unlikely, especially since this
driver is expected to be kicked by the MFD driver only after registering
the regmap - but it is still better to handle this gracefully.

Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Fixes: e7eef0bd4075 ("regulator: bd71828-regulator.c: Fix LDON-HEAD mode")
Link: https://patch.msgid.link/5bfffee380863bcf24f3062e48094c8eb7b1342f.1775565381.git.mazziesaccount@gmail.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpio-bd72720.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-bd72720.c b/drivers/gpio/gpio-bd72720.c
index 6549dbf4c7ad..d0f936ed80af 100644
--- a/drivers/gpio/gpio-bd72720.c
+++ b/drivers/gpio/gpio-bd72720.c
@@ -256,6 +256,8 @@ static int gpo_bd72720_probe(struct platform_device *pdev)
 	g->dev = dev;
 	g->chip.parent = parent;
 	g->regmap = dev_get_regmap(parent, NULL);
+	if (!g->regmap)
+		return -ENODEV;
 
 	return devm_gpiochip_add_data(dev, &g->chip, g);
 }
-- 
cgit v1.2.3


From 14a857056466be9d3d907a94e92a704ac1be149b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 4 Apr 2026 12:22:44 +0200
Subject: sched/deadline: Use revised wakeup rule for dl_server

John noted that commit 115135422562 ("sched/deadline: Fix 'stuck' dl_server")
unfixed the issue from commit a3a70caf7906 ("sched/deadline: Fix dl_server
behaviour").

The issue in commit 115135422562 was for wakeups of the server after the
deadline; in which case you *have* to start a new period. The case for
a3a70caf7906 is wakeups before the deadline.

Now, because the server is effectively running a least-laxity policy, it means
that any wakeup during the runnable phase means dl_entity_overflow() will be
true. This means we need to adjust the runtime to allow it to still run until
the existing deadline expires.

Use the revised wakeup rule for dl_defer entities.

Fixes: 115135422562 ("sched/deadline: Fix 'stuck' dl_server")
Reported-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Tested-by: John Stultz <jstultz@google.com>
Link: https://patch.msgid.link/20260404102244.GB22575@noisy.programming.kicks-ass.net
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d08b00429323..674de6a48551 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1027,7 +1027,7 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, rq_clock(rq))) {
 
-		if (unlikely(!dl_is_implicit(dl_se) &&
+		if (unlikely((!dl_is_implicit(dl_se) || dl_se->dl_defer) &&
 			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 			     !is_dl_boosted(dl_se))) {
 			update_dl_revised_wakeup(dl_se, rq);
-- 
cgit v1.2.3


From 4c71fd099513bfa8acab529b626e1f0097b76061 Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Wed, 1 Apr 2026 12:10:07 +0200
Subject: drm/i915/gt: fix refcount underflow in intel_engine_park_heartbeat

A use-after-free / refcount underflow is possible when the heartbeat
worker and intel_engine_park_heartbeat() race to release the same
engine->heartbeat.systole request.

The heartbeat worker reads engine->heartbeat.systole and calls
i915_request_put() on it when the request is complete, but clears
the pointer in a separate, non-atomic step. Concurrently, a request
retirement on another CPU can drop the engine wakeref to zero, triggering
__engine_park() -> intel_engine_park_heartbeat(). If the heartbeat
timer is pending at that point, cancel_delayed_work() returns true and
intel_engine_park_heartbeat() reads the stale non-NULL systole pointer
and calls i915_request_put() on it again, causing a refcount underflow:

```
<4> [487.221889] Workqueue: i915-unordered engine_retire [i915]
<4> [487.222640] RIP: 0010:refcount_warn_saturate+0x68/0xb0
...
<4> [487.222707] Call Trace:
<4> [487.222711]  <TASK>
<4> [487.222716]  intel_engine_park_heartbeat.part.0+0x6f/0x80 [i915]
<4> [487.223115]  intel_engine_park_heartbeat+0x25/0x40 [i915]
<4> [487.223566]  __engine_park+0xb9/0x650 [i915]
<4> [487.223973]  ____intel_wakeref_put_last+0x2e/0xb0 [i915]
<4> [487.224408]  __intel_wakeref_put_last+0x72/0x90 [i915]
<4> [487.224797]  intel_context_exit_engine+0x7c/0x80 [i915]
<4> [487.225238]  intel_context_exit+0xf1/0x1b0 [i915]
<4> [487.225695]  i915_request_retire.part.0+0x1b9/0x530 [i915]
<4> [487.226178]  i915_request_retire+0x1c/0x40 [i915]
<4> [487.226625]  engine_retire+0x122/0x180 [i915]
<4> [487.227037]  process_one_work+0x239/0x760
<4> [487.227060]  worker_thread+0x200/0x3f0
<4> [487.227068]  ? __pfx_worker_thread+0x10/0x10
<4> [487.227075]  kthread+0x10d/0x150
<4> [487.227083]  ? __pfx_kthread+0x10/0x10
<4> [487.227092]  ret_from_fork+0x3d4/0x480
<4> [487.227099]  ? __pfx_kthread+0x10/0x10
<4> [487.227107]  ret_from_fork_asm+0x1a/0x30
<4> [487.227141]  </TASK>
```

Fix this by replacing the non-atomic pointer read + separate clear with
xchg() in both racing paths. xchg() is a single indivisible hardware
instruction that atomically reads the old pointer and writes NULL. This
guarantees only one of the two concurrent callers obtains the non-NULL
pointer and performs the put, the other gets NULL and skips it.

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/15880
Fixes: 058179e72e09 ("drm/i915/gt: Replace hangcheck by heartbeats")
Cc: <stable@vger.kernel.org> # v5.5+
Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/d4c1c14255688dd07cc8044973c4f032a8d1559e.1775038106.git.sebastian.brzezinka@intel.com
(cherry picked from commit 13238dc0ee4f9ab8dafa2cca7295736191ae2f42)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c | 26 ++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index b279878dca29..6424ecce8bcb 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -148,10 +148,12 @@ static void heartbeat(struct work_struct *wrk)
 	/* Just in case everything has gone horribly wrong, give it a kick */
 	intel_engine_flush_submission(engine);
 
-	rq = engine->heartbeat.systole;
-	if (rq && i915_request_completed(rq)) {
-		i915_request_put(rq);
-		engine->heartbeat.systole = NULL;
+	rq = xchg(&engine->heartbeat.systole, NULL);
+	if (rq) {
+		if (i915_request_completed(rq))
+			i915_request_put(rq);
+		else
+			engine->heartbeat.systole = rq;
 	}
 
 	if (!intel_engine_pm_get_if_awake(engine))
@@ -232,8 +234,11 @@ static void heartbeat(struct work_struct *wrk)
 unlock:
 	mutex_unlock(&ce->timeline->mutex);
 out:
-	if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine))
-		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
+	if (!engine->i915->params.enable_hangcheck || !next_heartbeat(engine)) {
+		rq = xchg(&engine->heartbeat.systole, NULL);
+		if (rq)
+			i915_request_put(rq);
+	}
 	intel_engine_pm_put(engine);
 }
 
@@ -247,8 +252,13 @@ void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine)
 
 void intel_engine_park_heartbeat(struct intel_engine_cs *engine)
 {
-	if (cancel_delayed_work(&engine->heartbeat.work))
-		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
+	if (cancel_delayed_work(&engine->heartbeat.work)) {
+		struct i915_request *rq;
+
+		rq = xchg(&engine->heartbeat.systole, NULL);
+		if (rq)
+			i915_request_put(rq);
+	}
 }
 
 void intel_gt_unpark_heartbeats(struct intel_gt *gt)
-- 
cgit v1.2.3


From 9a91797e61d286805ae10a92cc48959c30800556 Mon Sep 17 00:00:00 2001
From: Weiming Shi <bestswngs@gmail.com>
Date: Wed, 1 Apr 2026 15:58:01 +0800
Subject: ipvs: fix NULL deref in ip_vs_add_service error path

When ip_vs_bind_scheduler() succeeds in ip_vs_add_service(), the local
variable sched is set to NULL.  If ip_vs_start_estimator() subsequently
fails, the out_err cleanup calls ip_vs_unbind_scheduler(svc, sched)
with sched == NULL.  ip_vs_unbind_scheduler() passes the cur_sched NULL
check (because svc->scheduler was set by the successful bind) but then
dereferences the NULL sched parameter at sched->done_service, causing a
kernel panic at offset 0x30 from NULL.

 Oops: general protection fault, [..] [#1] PREEMPT SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
 RIP: 0010:ip_vs_unbind_scheduler (net/netfilter/ipvs/ip_vs_sched.c:69)
 Call Trace:
  <TASK>
  ip_vs_add_service.isra.0 (net/netfilter/ipvs/ip_vs_ctl.c:1500)
  do_ip_vs_set_ctl (net/netfilter/ipvs/ip_vs_ctl.c:2809)
  nf_setsockopt (net/netfilter/nf_sockopt.c:102)
  [..]

Fix by simply not clearing the local sched variable after a successful
bind.  ip_vs_unbind_scheduler() already detects whether a scheduler is
installed via svc->scheduler, and keeping sched non-NULL ensures the
error path passes the correct pointer to both ip_vs_unbind_scheduler()
and ip_vs_scheduler_put().

While the bug is older, the problem popups in more recent kernels (6.2),
when the new error path is taken after the ip_vs_start_estimator() call.

Fixes: 705dd3444081 ("ipvs: use kthreads for stats estimation")
Reported-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
Acked-by: Simon Horman <horms@kernel.org>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 35642de2a0fe..2aaf50f52c8e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1452,7 +1452,6 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 		ret = ip_vs_bind_scheduler(svc, sched);
 		if (ret)
 			goto out_err;
-		sched = NULL;
 	}
 
 	ret = ip_vs_start_estimator(ipvs, &svc->stats);
-- 
cgit v1.2.3


From 1f3083aec8836213da441270cdb1ab612dd82cf4 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Wed, 1 Apr 2026 14:20:57 -0700
Subject: netfilter: nfnetlink_log: initialize nfgenmsg in NLMSG_DONE
 terminator

When batching multiple NFLOG messages (inst->qlen > 1), __nfulnl_send()
appends an NLMSG_DONE terminator with sizeof(struct nfgenmsg) payload via
nlmsg_put(), but never initializes the nfgenmsg bytes. The nlmsg_put()
helper only zeroes alignment padding after the payload, not the payload
itself, so four bytes of stale kernel heap data are leaked to userspace
in the NLMSG_DONE message body.

Use nfnl_msg_put() to build the NLMSG_DONE terminator, which initializes
the nfgenmsg payload via nfnl_fill_hdr(), consistent with how
__build_packet_message() already constructs NFULNL_MSG_PACKET headers.

Fixes: 29c5d4afba51 ("[NETFILTER]: nfnetlink_log: fix sending of multipart messages")
Reported-by: Weiming Shi <bestswngs@gmail.com>
Signed-off-by: Xiang Mei <xmei5@asu.edu>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nfnetlink_log.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index f80978c06fa0..0db908518b2f 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -361,10 +361,10 @@ static void
 __nfulnl_send(struct nfulnl_instance *inst)
 {
 	if (inst->qlen > 1) {
-		struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0,
-						 NLMSG_DONE,
-						 sizeof(struct nfgenmsg),
-						 0);
+		struct nlmsghdr *nlh = nfnl_msg_put(inst->skb, 0, 0,
+						    NLMSG_DONE, 0,
+						    AF_UNSPEC, NFNETLINK_V0,
+						    htons(inst->group_num));
 		if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n",
 			      inst->skb->len, skb_tailroom(inst->skb))) {
 			kfree_skb(inst->skb);
-- 
cgit v1.2.3


From ff64c5bfef12461df8450e0f50bb693b5269c720 Mon Sep 17 00:00:00 2001
From: Ren Wei <n05ec@lzu.edu.cn>
Date: Fri, 3 Apr 2026 23:52:52 +0800
Subject: netfilter: xt_multiport: validate range encoding in checkentry

ports_match_v1() treats any non-zero pflags entry as the start of a
port range and unconditionally consumes the next ports[] element as
the range end.

The checkentry path currently validates protocol, flags and count, but
it does not validate the range encoding itself. As a result, malformed
rules can mark the last slot as a range start or place two range starts
back to back, leaving ports_match_v1() to step past the last valid
ports[] element while interpreting the rule.

Reject malformed multiport v1 rules in checkentry by validating that
each range start has a following element and that the following element
is not itself marked as another range start.

Fixes: a89ecb6a2ef7 ("[NETFILTER]: x_tables: unify IPv4/IPv6 multiport match")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Yuhang Zheng <z1652074432@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/xt_multiport.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/xt_multiport.c b/net/netfilter/xt_multiport.c
index 44a00f5acde8..a1691ff405d3 100644
--- a/net/netfilter/xt_multiport.c
+++ b/net/netfilter/xt_multiport.c
@@ -105,6 +105,28 @@ multiport_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	return ports_match_v1(multiinfo, ntohs(pptr[0]), ntohs(pptr[1]));
 }
 
+static bool
+multiport_valid_ranges(const struct xt_multiport_v1 *multiinfo)
+{
+	unsigned int i;
+
+	for (i = 0; i < multiinfo->count; i++) {
+		if (!multiinfo->pflags[i])
+			continue;
+
+		if (++i >= multiinfo->count)
+			return false;
+
+		if (multiinfo->pflags[i])
+			return false;
+
+		if (multiinfo->ports[i - 1] > multiinfo->ports[i])
+			return false;
+	}
+
+	return true;
+}
+
 static inline bool
 check(u_int16_t proto,
       u_int8_t ip_invflags,
@@ -127,8 +149,10 @@ static int multiport_mt_check(const struct xt_mtchk_param *par)
 	const struct ipt_ip *ip = par->entryinfo;
 	const struct xt_multiport_v1 *multiinfo = par->matchinfo;
 
-	return check(ip->proto, ip->invflags, multiinfo->flags,
-		     multiinfo->count) ? 0 : -EINVAL;
+	if (!check(ip->proto, ip->invflags, multiinfo->flags, multiinfo->count))
+		return -EINVAL;
+
+	return multiport_valid_ranges(multiinfo) ? 0 : -EINVAL;
 }
 
 static int multiport_mt6_check(const struct xt_mtchk_param *par)
@@ -136,8 +160,10 @@ static int multiport_mt6_check(const struct xt_mtchk_param *par)
 	const struct ip6t_ip6 *ip = par->entryinfo;
 	const struct xt_multiport_v1 *multiinfo = par->matchinfo;
 
-	return check(ip->proto, ip->invflags, multiinfo->flags,
-		     multiinfo->count) ? 0 : -EINVAL;
+	if (!check(ip->proto, ip->invflags, multiinfo->flags, multiinfo->count))
+		return -EINVAL;
+
+	return multiport_valid_ranges(multiinfo) ? 0 : -EINVAL;
 }
 
 static struct xt_match multiport_mt_reg[] __read_mostly = {
-- 
cgit v1.2.3


From fdce0b3590f724540795b874b4c8850c90e6b0a8 Mon Sep 17 00:00:00 2001
From: Zhengchuan Liang <zcliangcn@gmail.com>
Date: Sat, 4 Apr 2026 17:39:47 +0800
Subject: netfilter: ip6t_eui64: reject invalid MAC header for all packets

`eui64_mt6()` derives a modified EUI-64 from the Ethernet source address
and compares it with the low 64 bits of the IPv6 source address.

The existing guard only rejects an invalid MAC header when
`par->fragoff != 0`. For packets with `par->fragoff == 0`, `eui64_mt6()`
can still reach `eth_hdr(skb)` even when the MAC header is not valid.

Fix this by removing the `par->fragoff != 0` condition so that packets
with an invalid MAC header are rejected before accessing `eth_hdr(skb)`.

Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Zhengchuan Liang <zcliangcn@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/ipv6/netfilter/ip6t_eui64.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c
index d704f7ed300c..da69a27e8332 100644
--- a/net/ipv6/netfilter/ip6t_eui64.c
+++ b/net/ipv6/netfilter/ip6t_eui64.c
@@ -22,8 +22,7 @@ eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 	unsigned char eui64[8];
 
 	if (!(skb_mac_header(skb) >= skb->head &&
-	      skb_mac_header(skb) + ETH_HLEN <= skb->data) &&
-	    par->fragoff != 0) {
+	      skb_mac_header(skb) + ETH_HLEN <= skb->data)) {
 		par->hotdrop = true;
 		return false;
 	}
-- 
cgit v1.2.3


From f8dca15a1b190787bbd03285304b569631160eda Mon Sep 17 00:00:00 2001
From: Tuan Do <tuan@calif.io>
Date: Fri, 3 Apr 2026 00:33:17 -0700
Subject: netfilter: nft_ct: fix use-after-free in timeout object destroy

nft_ct_timeout_obj_destroy() frees the timeout object with kfree()
immediately after nf_ct_untimeout(), without waiting for an RCU grace
period. Concurrent packet processing on other CPUs may still hold
RCU-protected references to the timeout object obtained via
rcu_dereference() in nf_ct_timeout_data().

Add an rcu_head to struct nf_ct_timeout and use kfree_rcu() to defer
freeing until after an RCU grace period, matching the approach already
used in nfnetlink_cttimeout.c.

KASAN report:
 BUG: KASAN: slab-use-after-free in nf_conntrack_tcp_packet+0x1381/0x29d0
 Read of size 4 at addr ffff8881035fe19c by task exploit/80

 Call Trace:
  nf_conntrack_tcp_packet+0x1381/0x29d0
  nf_conntrack_in+0x612/0x8b0
  nf_hook_slow+0x70/0x100
  __ip_local_out+0x1b2/0x210
  tcp_sendmsg_locked+0x722/0x1580
  __sys_sendto+0x2d8/0x320

 Allocated by task 75:
  nft_ct_timeout_obj_init+0xf6/0x290
  nft_obj_init+0x107/0x1b0
  nf_tables_newobj+0x680/0x9c0
  nfnetlink_rcv_batch+0xc29/0xe00

 Freed by task 26:
  nft_obj_destroy+0x3f/0xa0
  nf_tables_trans_destroy_work+0x51c/0x5c0
  process_one_work+0x2c4/0x5a0

Fixes: 7e0b2b57f01d ("netfilter: nft_ct: add ct timeout support")
Cc: stable@vger.kernel.org
Signed-off-by: Tuan Do <tuan@calif.io>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_conntrack_timeout.h | 1 +
 net/netfilter/nft_ct.c                       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 9fdaba911de6..3a66d4abb6d6 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -14,6 +14,7 @@
 struct nf_ct_timeout {
 	__u16			l3num;
 	const struct nf_conntrack_l4proto *l4proto;
+	struct rcu_head		rcu;
 	char			data[];
 };
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 128ff8155b5d..04c74ccf9b84 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1020,7 +1020,7 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx,
 	nf_queue_nf_hook_drop(ctx->net);
 	nf_ct_untimeout(ctx->net, timeout);
 	nf_ct_netns_put(ctx->net, ctx->family);
-	kfree(priv->timeout);
+	kfree_rcu(priv->timeout, rcu);
 }
 
 static int nft_ct_timeout_obj_dump(struct sk_buff *skb,
-- 
cgit v1.2.3


From 936206e3f6ff411581e615e930263d6f8b78df9d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 7 Apr 2026 17:00:01 +0200
Subject: netfilter: nfnetlink_queue: make hash table per queue

Sharing a global hash table among all queues is tempting, but
it can cause crash:

BUG: KASAN: slab-use-after-free in nfqnl_recv_verdict+0x11ac/0x15e0 [nfnetlink_queue]
[..]
 nfqnl_recv_verdict+0x11ac/0x15e0 [nfnetlink_queue]
 nfnetlink_rcv_msg+0x46a/0x930
 kmem_cache_alloc_node_noprof+0x11e/0x450

struct nf_queue_entry is freed via kfree, but parallel cpu can still
encounter such an nf_queue_entry when walking the list.

Alternative fix is to free the nf_queue_entry via kfree_rcu() instead,
but as we have to alloc/free for each skb this will cause more mem
pressure.

Cc: Scott Mitchell <scott.k.mitch1@gmail.com>
Fixes: e19079adcd26 ("netfilter: nfnetlink_queue: optimize verdict lookup with hash table")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_queue.h |   1 -
 net/netfilter/nfnetlink_queue.c  | 139 ++++++++++++++-------------------------
 2 files changed, 49 insertions(+), 91 deletions(-)

diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index 45eb26b2e95b..d17035d14d96 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -23,7 +23,6 @@ struct nf_queue_entry {
 	struct nf_hook_state	state;
 	bool			nf_ct_is_unconfirmed;
 	u16			size; /* sizeof(entry) + saved route keys */
-	u16			queue_num;
 
 	/* extra space to store route keys */
 };
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 47f7f62906e2..8e02f84784da 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -49,8 +49,8 @@
 #endif
 
 #define NFQNL_QMAX_DEFAULT 1024
-#define NFQNL_HASH_MIN     1024
-#define NFQNL_HASH_MAX     1048576
+#define NFQNL_HASH_MIN     8
+#define NFQNL_HASH_MAX     32768
 
 /* We're using struct nlattr which has 16bit nla_len. Note that nla_len
  * includes the header length. Thus, the maximum packet length that we
@@ -60,29 +60,10 @@
  */
 #define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN)
 
-/* Composite key for packet lookup: (net, queue_num, packet_id) */
-struct nfqnl_packet_key {
-	possible_net_t net;
-	u32 packet_id;
-	u16 queue_num;
-} __aligned(sizeof(u32));  /* jhash2 requires 32-bit alignment */
-
-/* Global rhashtable - one for entire system, all netns */
-static struct rhashtable nfqnl_packet_map __read_mostly;
-
-/* Helper to initialize composite key */
-static inline void nfqnl_init_key(struct nfqnl_packet_key *key,
-				  struct net *net, u32 packet_id, u16 queue_num)
-{
-	memset(key, 0, sizeof(*key));
-	write_pnet(&key->net, net);
-	key->packet_id = packet_id;
-	key->queue_num = queue_num;
-}
-
 struct nfqnl_instance {
 	struct hlist_node hlist;		/* global list of queues */
-	struct rcu_head rcu;
+	struct rhashtable nfqnl_packet_map;
+	struct rcu_work	rwork;
 
 	u32 peer_portid;
 	unsigned int queue_maxlen;
@@ -106,6 +87,7 @@ struct nfqnl_instance {
 
 typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long);
 
+static struct workqueue_struct *nfq_cleanup_wq __read_mostly;
 static unsigned int nfnl_queue_net_id __read_mostly;
 
 #define INSTANCE_BUCKETS	16
@@ -124,34 +106,10 @@ static inline u_int8_t instance_hashfn(u_int16_t queue_num)
 	return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS;
 }
 
-/* Extract composite key from nf_queue_entry for hashing */
-static u32 nfqnl_packet_obj_hashfn(const void *data, u32 len, u32 seed)
-{
-	const struct nf_queue_entry *entry = data;
-	struct nfqnl_packet_key key;
-
-	nfqnl_init_key(&key, entry->state.net, entry->id, entry->queue_num);
-
-	return jhash2((u32 *)&key, sizeof(key) / sizeof(u32), seed);
-}
-
-/* Compare stack-allocated key against entry */
-static int nfqnl_packet_obj_cmpfn(struct rhashtable_compare_arg *arg,
-				  const void *obj)
-{
-	const struct nfqnl_packet_key *key = arg->key;
-	const struct nf_queue_entry *entry = obj;
-
-	return !net_eq(entry->state.net, read_pnet(&key->net)) ||
-	       entry->queue_num != key->queue_num ||
-	       entry->id != key->packet_id;
-}
-
 static const struct rhashtable_params nfqnl_rhashtable_params = {
 	.head_offset = offsetof(struct nf_queue_entry, hash_node),
-	.key_len = sizeof(struct nfqnl_packet_key),
-	.obj_hashfn = nfqnl_packet_obj_hashfn,
-	.obj_cmpfn = nfqnl_packet_obj_cmpfn,
+	.key_offset = offsetof(struct nf_queue_entry, id),
+	.key_len = sizeof(u32),
 	.automatic_shrinking = true,
 	.min_size = NFQNL_HASH_MIN,
 	.max_size = NFQNL_HASH_MAX,
@@ -190,6 +148,10 @@ instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid)
 	spin_lock_init(&inst->lock);
 	INIT_LIST_HEAD(&inst->queue_list);
 
+	err = rhashtable_init(&inst->nfqnl_packet_map, &nfqnl_rhashtable_params);
+	if (err < 0)
+		goto out_free;
+
 	spin_lock(&q->instances_lock);
 	if (instance_lookup(q, queue_num)) {
 		err = -EEXIST;
@@ -210,6 +172,8 @@ instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid)
 
 out_unlock:
 	spin_unlock(&q->instances_lock);
+	rhashtable_destroy(&inst->nfqnl_packet_map);
+out_free:
 	kfree(inst);
 	return ERR_PTR(err);
 }
@@ -217,15 +181,18 @@ out_unlock:
 static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
 			unsigned long data);
 
-static void
-instance_destroy_rcu(struct rcu_head *head)
+static void instance_destroy_work(struct work_struct *work)
 {
-	struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance,
-						   rcu);
+	struct nfqnl_instance *inst;
 
+	inst = container_of(to_rcu_work(work), struct nfqnl_instance,
+			    rwork);
 	rcu_read_lock();
 	nfqnl_flush(inst, NULL, 0);
 	rcu_read_unlock();
+
+	rhashtable_destroy(&inst->nfqnl_packet_map);
+
 	kfree(inst);
 	module_put(THIS_MODULE);
 }
@@ -234,7 +201,9 @@ static void
 __instance_destroy(struct nfqnl_instance *inst)
 {
 	hlist_del_rcu(&inst->hlist);
-	call_rcu(&inst->rcu, instance_destroy_rcu);
+
+	INIT_RCU_WORK(&inst->rwork, instance_destroy_work);
+	queue_rcu_work(nfq_cleanup_wq, &inst->rwork);
 }
 
 static void
@@ -250,9 +219,7 @@ __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
 {
 	int err;
 
-	entry->queue_num = queue->queue_num;
-
-	err = rhashtable_insert_fast(&nfqnl_packet_map, &entry->hash_node,
+	err = rhashtable_insert_fast(&queue->nfqnl_packet_map, &entry->hash_node,
 				     nfqnl_rhashtable_params);
 	if (unlikely(err))
 		return err;
@@ -266,23 +233,19 @@ __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
 static void
 __dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
 {
-	rhashtable_remove_fast(&nfqnl_packet_map, &entry->hash_node,
+	rhashtable_remove_fast(&queue->nfqnl_packet_map, &entry->hash_node,
 			       nfqnl_rhashtable_params);
 	list_del(&entry->list);
 	queue->queue_total--;
 }
 
 static struct nf_queue_entry *
-find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id,
-		   struct net *net)
+find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id)
 {
-	struct nfqnl_packet_key key;
 	struct nf_queue_entry *entry;
 
-	nfqnl_init_key(&key, net, id, queue->queue_num);
-
 	spin_lock_bh(&queue->lock);
-	entry = rhashtable_lookup_fast(&nfqnl_packet_map, &key,
+	entry = rhashtable_lookup_fast(&queue->nfqnl_packet_map, &id,
 				       nfqnl_rhashtable_params);
 
 	if (entry)
@@ -1531,7 +1494,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info,
 
 	verdict = ntohl(vhdr->verdict);
 
-	entry = find_dequeue_entry(queue, ntohl(vhdr->id), info->net);
+	entry = find_dequeue_entry(queue, ntohl(vhdr->id));
 	if (entry == NULL)
 		return -ENOENT;
 
@@ -1880,40 +1843,38 @@ static int __init nfnetlink_queue_init(void)
 {
 	int status;
 
-	status = rhashtable_init(&nfqnl_packet_map, &nfqnl_rhashtable_params);
-	if (status < 0)
-		return status;
+	nfq_cleanup_wq = alloc_ordered_workqueue("nfq_workqueue", 0);
+	if (!nfq_cleanup_wq)
+		return -ENOMEM;
 
 	status = register_pernet_subsys(&nfnl_queue_net_ops);
-	if (status < 0) {
-		pr_err("failed to register pernet ops\n");
-		goto cleanup_rhashtable;
-	}
+	if (status < 0)
+		goto cleanup_pernet_subsys;
 
-	netlink_register_notifier(&nfqnl_rtnl_notifier);
-	status = nfnetlink_subsys_register(&nfqnl_subsys);
-	if (status < 0) {
-		pr_err("failed to create netlink socket\n");
-		goto cleanup_netlink_notifier;
-	}
+	status = netlink_register_notifier(&nfqnl_rtnl_notifier);
+	if (status < 0)
+	       goto cleanup_rtnl_notifier;
 
 	status = register_netdevice_notifier(&nfqnl_dev_notifier);
-	if (status < 0) {
-		pr_err("failed to register netdevice notifier\n");
-		goto cleanup_netlink_subsys;
-	}
+	if (status < 0)
+		goto cleanup_dev_notifier;
+
+	status = nfnetlink_subsys_register(&nfqnl_subsys);
+	if (status < 0)
+		goto cleanup_nfqnl_subsys;
 
 	nf_register_queue_handler(&nfqh);
 
 	return status;
 
-cleanup_netlink_subsys:
-	nfnetlink_subsys_unregister(&nfqnl_subsys);
-cleanup_netlink_notifier:
+cleanup_nfqnl_subsys:
+	unregister_netdevice_notifier(&nfqnl_dev_notifier);
+cleanup_dev_notifier:
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
+cleanup_rtnl_notifier:
 	unregister_pernet_subsys(&nfnl_queue_net_ops);
-cleanup_rhashtable:
-	rhashtable_destroy(&nfqnl_packet_map);
+cleanup_pernet_subsys:
+	destroy_workqueue(nfq_cleanup_wq);
 	return status;
 }
 
@@ -1924,9 +1885,7 @@ static void __exit nfnetlink_queue_fini(void)
 	nfnetlink_subsys_unregister(&nfqnl_subsys);
 	netlink_unregister_notifier(&nfqnl_rtnl_notifier);
 	unregister_pernet_subsys(&nfnl_queue_net_ops);
-
-	rhashtable_destroy(&nfqnl_packet_map);
-
+	destroy_workqueue(nfq_cleanup_wq);
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
-- 
cgit v1.2.3


From dde1a6084c5ca9d143a562540d5453454d79ea15 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <fmancera@suse.de>
Date: Mon, 6 Apr 2026 23:18:31 +0200
Subject: selftests: nft_queue.sh: add a parallel stress test

Introduce a new stress test to check for race conditions in the
nfnetlink_queue subsystem, where an entry is freed while another CPU is
concurrently walking the global rhashtable.

To trigger this, `nf_queue.c` is extended with two new flags:
  * -O (out-of-order): Buffers packet IDs and flushes them in reverse.
  * -b (bogus verdicts): Floods the kernel with non-existent packet IDs.

The bogus verdict loop forces the kernel's lookup function to perform
full rhashtable bucket traversals (-ENOENT). Combined with reverse-order
flushing and heavy parallel UDP/ping flooding across 8 queues, this puts
the nfnetlink_queue code under pressure.

Joint work with Florian Westphal.

Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 tools/testing/selftests/net/netfilter/nf_queue.c   | 50 +++++++++++--
 tools/testing/selftests/net/netfilter/nft_queue.sh | 83 ++++++++++++++++++----
 2 files changed, 115 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c
index 116c0ca0eabb..8bbec37f5356 100644
--- a/tools/testing/selftests/net/netfilter/nf_queue.c
+++ b/tools/testing/selftests/net/netfilter/nf_queue.c
@@ -19,6 +19,8 @@ struct options {
 	bool count_packets;
 	bool gso_enabled;
 	bool failopen;
+	bool out_of_order;
+	bool bogus_verdict;
 	int verbose;
 	unsigned int queue_num;
 	unsigned int timeout;
@@ -31,7 +33,7 @@ static struct options opts;
 
 static void help(const char *p)
 {
-	printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
+	printf("Usage: %s [-c|-v [-vv] ] [-o] [-O] [-b] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p);
 }
 
 static int parse_attr_cb(const struct nlattr *attr, void *data)
@@ -275,7 +277,9 @@ static int mainloop(void)
 	unsigned int buflen = 64 * 1024 + MNL_SOCKET_BUFFER_SIZE;
 	struct mnl_socket *nl;
 	struct nlmsghdr *nlh;
+	uint32_t ooo_ids[16];
 	unsigned int portid;
+	int ooo_count = 0;
 	char *buf;
 	int ret;
 
@@ -308,6 +312,9 @@ static int mainloop(void)
 
 		ret = mnl_cb_run(buf, ret, 0, portid, queue_cb, NULL);
 		if (ret < 0) {
+			/* bogus verdict mode will generate ENOENT error messages */
+			if (opts.bogus_verdict && errno == ENOENT)
+				continue;
 			perror("mnl_cb_run");
 			exit(EXIT_FAILURE);
 		}
@@ -316,10 +323,35 @@ static int mainloop(void)
 		if (opts.delay_ms)
 			sleep_ms(opts.delay_ms);
 
-		nlh = nfq_build_verdict(buf, id, opts.queue_num, opts.verdict);
-		if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
-			perror("mnl_socket_sendto");
-			exit(EXIT_FAILURE);
+		if (opts.bogus_verdict) {
+			for (int i = 0; i < 50; i++) {
+				nlh = nfq_build_verdict(buf, id + 0x7FFFFFFF + i,
+							opts.queue_num, opts.verdict);
+				mnl_socket_sendto(nl, nlh, nlh->nlmsg_len);
+			}
+		}
+
+		if (opts.out_of_order) {
+			ooo_ids[ooo_count] = id;
+			if (ooo_count >= 15) {
+				for (ooo_count; ooo_count >= 0; ooo_count--) {
+					nlh = nfq_build_verdict(buf, ooo_ids[ooo_count],
+								opts.queue_num, opts.verdict);
+					if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+						perror("mnl_socket_sendto");
+						exit(EXIT_FAILURE);
+					}
+				}
+				ooo_count = 0;
+			} else {
+				ooo_count++;
+			}
+		} else {
+			nlh = nfq_build_verdict(buf, id, opts.queue_num, opts.verdict);
+			if (mnl_socket_sendto(nl, nlh, nlh->nlmsg_len) < 0) {
+				perror("mnl_socket_sendto");
+				exit(EXIT_FAILURE);
+			}
 		}
 	}
 
@@ -332,7 +364,7 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) {
+	while ((c = getopt(argc, argv, "chvoObt:q:Q:d:G")) != -1) {
 		switch (c) {
 		case 'c':
 			opts.count_packets = true;
@@ -375,6 +407,12 @@ static void parse_opts(int argc, char **argv)
 		case 'v':
 			opts.verbose++;
 			break;
+		case 'O':
+			opts.out_of_order = true;
+			break;
+		case 'b':
+			opts.bogus_verdict = true;
+			break;
 		}
 	}
 
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index ea766bdc5d04..d80390848e85 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -11,6 +11,7 @@ ret=0
 timeout=5
 
 SCTP_TEST_TIMEOUT=60
+STRESS_TEST_TIMEOUT=30
 
 cleanup()
 {
@@ -719,6 +720,74 @@ EOF
 	fi
 }
 
+check_tainted()
+{
+	local msg="$1"
+
+	if [ "$tainted_then" -ne 0 ];then
+		return
+	fi
+
+	read tainted_now < /proc/sys/kernel/tainted
+	if [ "$tainted_now" -eq 0 ];then
+		echo "PASS: $msg"
+	else
+		echo "TAINT: $msg"
+		dmesg
+		ret=1
+	fi
+}
+
+test_queue_stress()
+{
+	read tainted_then < /proc/sys/kernel/tainted
+	local i
+
+        ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet t {
+	chain forward {
+		type filter hook forward priority 0; policy accept;
+
+		queue flags bypass to numgen random mod 8
+	}
+}
+EOF
+	timeout "$STRESS_TEST_TIMEOUT" ip netns exec "$ns2" \
+		socat -u UDP-LISTEN:12345,fork,pf=ipv4 STDOUT > /dev/null &
+
+	timeout "$STRESS_TEST_TIMEOUT" ip netns exec "$ns3" \
+		socat -u UDP-LISTEN:12345,fork,pf=ipv4 STDOUT > /dev/null &
+
+	for i in $(seq 0 7); do
+		ip netns exec "$nsrouter" timeout "$STRESS_TEST_TIMEOUT" \
+			./nf_queue -q $i -t 2 -O -b > /dev/null &
+	done
+
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f 10.0.2.99 > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f 10.0.3.99 > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f "dead:2::99" > /dev/null 2>&1 &
+	ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+		ping -q -f "dead:3::99" > /dev/null 2>&1 &
+
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns2" 12345
+	busywait "$BUSYWAIT_TIMEOUT" udp_listener_ready "$ns3" 12345
+
+	for i in $(seq 1 4);do
+		ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+			socat -u STDIN UDP-DATAGRAM:10.0.2.99:12345 < /dev/zero > /dev/null &
+		ip netns exec "$ns1" timeout "$STRESS_TEST_TIMEOUT" \
+			socat -u STDIN UDP-DATAGRAM:10.0.3.99:12345 < /dev/zero > /dev/null &
+	done
+
+	wait
+
+	check_tainted "concurrent queueing"
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -742,18 +811,7 @@ EOF
 
 	ip netns exec "$ns1" nft flush ruleset
 
-	if [ "$tainted_then" -ne 0 ];then
-		return
-	fi
-
-	read tainted_now < /proc/sys/kernel/tainted
-	if [ "$tainted_now" -eq 0 ];then
-		echo "PASS: queue program exiting while packets queued"
-	else
-		echo "TAINT: queue program exiting while packets queued"
-		dmesg
-		ret=1
-	fi
+	check_tainted "queue program exiting while packets queued"
 }
 
 ip netns exec "$nsrouter" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
@@ -799,6 +857,7 @@ test_sctp_forward
 test_sctp_output
 test_udp_nat_race
 test_udp_gro_ct
+test_queue_stress
 
 # should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
-- 
cgit v1.2.3


From f4c90fb761f696ebbcf1e8fb7f83d83cbb30cb0c Mon Sep 17 00:00:00 2001
From: Neo Chang <YLCHANG2@nuvoton.com>
Date: Wed, 8 Apr 2026 13:26:39 +0800
Subject: ASoC: nau8325: Add software reset during probe

Currently, the driver only performs a hardware reset during the I2C probe
sequence. To ensure all internal states of the codec are properly cleared
without affecting the configuration registers, a software reset is also
required.

According to the hardware specification, writing to the Software Reset
register (R01) twice will reset all internal states safely.

This patch adds the nau8325_software_reset() function, executes it right
after the hardware reset in the probe function, and marks the R01 register
as writeable in the regmap configuration.

Signed-off-by: Neo Chang <YLCHANG2@nuvoton.com>
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://patch.msgid.link/20260408052639.187149-1-YLCHANG2@nuvoton.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/nau8325.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/nau8325.c b/sound/soc/codecs/nau8325.c
index e651263a9812..58ef5c493835 100644
--- a/sound/soc/codecs/nau8325.c
+++ b/sound/soc/codecs/nau8325.c
@@ -142,7 +142,7 @@ static bool nau8325_readable_reg(struct device *dev, unsigned int reg)
 static bool nau8325_writeable_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
-	case NAU8325_R00_HARDWARE_RST:
+	case NAU8325_R00_HARDWARE_RST ... NAU8325_R01_SOFTWARE_RST:
 	case NAU8325_R03_CLK_CTRL ... NAU8325_R06_INT_CLR_STATUS:
 	case NAU8325_R09_IRQOUT ... NAU8325_R13_DAC_VOLUME:
 	case NAU8325_R29_DAC_CTRL1 ... NAU8325_R2A_DAC_CTRL2:
@@ -670,6 +670,12 @@ static void nau8325_reset_chip(struct regmap *regmap)
 	regmap_write(regmap, NAU8325_R00_HARDWARE_RST, 0x0000);
 }
 
+static void nau8325_software_reset(struct regmap *regmap)
+{
+	regmap_write(regmap, NAU8325_R01_SOFTWARE_RST, 0x0000);
+	regmap_write(regmap, NAU8325_R01_SOFTWARE_RST, 0x0000);
+}
+
 static void nau8325_init_regs(struct nau8325 *nau8325)
 {
 	struct regmap *regmap = nau8325->regmap;
@@ -856,6 +862,7 @@ static int nau8325_i2c_probe(struct i2c_client *i2c)
 	nau8325_print_device_properties(nau8325);
 
 	nau8325_reset_chip(nau8325->regmap);
+	nau8325_software_reset(nau8325->regmap);
 	ret = regmap_read(nau8325->regmap, NAU8325_R02_DEVICE_ID, &value);
 	if (ret) {
 		dev_dbg(dev, "Failed to read device id (%d)", ret);
-- 
cgit v1.2.3


From 082c192c0dd03f685514c9ce2eb0a80fd28e2175 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Wed, 8 Apr 2026 11:45:13 +0300
Subject: ALSA: hda/intel: enforce stricter period-size alignment for Intel NVL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Intel ACE4 based products set more strict constraints on HDA BDLE start
address and length alignment. Modify capability flags to drop
AZX_DCAPS_NO_ALIGN_BUFSIZE for Intel Nova Lake platforms.

Fixes: 7f428282fde3 ("ALSA: hda: controllers: intel: add support for Nova Lake")
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20260408084514.24325-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/controllers/intel.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c
index 8a7bd49e411f..a4104376523a 100644
--- a/sound/hda/controllers/intel.c
+++ b/sound/hda/controllers/intel.c
@@ -295,6 +295,9 @@ enum {
 #define AZX_DCAPS_INTEL_LNL \
 	(AZX_DCAPS_INTEL_SKYLAKE | AZX_DCAPS_PIO_COMMANDS)
 
+#define AZX_DCAPS_INTEL_NVL \
+	(AZX_DCAPS_INTEL_LNL & ~AZX_DCAPS_NO_ALIGN_BUFSIZE)
+
 /* quirks for ATI SB / AMD Hudson */
 #define AZX_DCAPS_PRESET_ATI_SB \
 	(AZX_DCAPS_NO_TCSEL | AZX_DCAPS_POSFIX_LPIB |\
@@ -2565,8 +2568,8 @@ static const struct pci_device_id azx_ids[] = {
 	/* Wildcat Lake */
 	{ PCI_DEVICE_DATA(INTEL, HDA_WCL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) },
 	/* Nova Lake */
-	{ PCI_DEVICE_DATA(INTEL, HDA_NVL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) },
-	{ PCI_DEVICE_DATA(INTEL, HDA_NVL_S, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) },
+	{ PCI_DEVICE_DATA(INTEL, HDA_NVL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_NVL) },
+	{ PCI_DEVICE_DATA(INTEL, HDA_NVL_S, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_NVL) },
 	/* Apollolake (Broxton-P) */
 	{ PCI_DEVICE_DATA(INTEL, HDA_APL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON) },
 	/* Gemini-Lake */
-- 
cgit v1.2.3


From 0f71866057262d669ed6a21246eaac0ad6d04d4e Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Wed, 8 Apr 2026 11:45:14 +0300
Subject: ASoC: SOF: Intel: hda: modify period size constraints for ACE4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Intel ACE4 based products set more strict constraints on HDA BDLE start
address and length alignment. Add a constraint to align period size to
128 bytes.

The commit removes the "minimum as per HDA spec" comment. This comment
was misleading as spec actually does allow a 2 byte BDLE length, and
more importantly, period size also directly impacts how the BDLE start
addresses are aligned, so it is not sufficient just to consider allowed
buffer length.

Fixes: d3df422f66e8 ("ASoC: SOF: Intel: add initial support for NVL-S")
Cc: stable@vger.kernel.org
Reported-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://patch.msgid.link/20260408084514.24325-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda-pcm.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c
index da6c1e7263cd..16a364072821 100644
--- a/sound/soc/sof/intel/hda-pcm.c
+++ b/sound/soc/sof/intel/hda-pcm.c
@@ -219,6 +219,7 @@ EXPORT_SYMBOL_NS(hda_dsp_pcm_pointer, "SND_SOC_SOF_INTEL_HDA_COMMON");
 int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
 		     struct snd_pcm_substream *substream)
 {
+	const struct sof_intel_dsp_desc *chip_info = get_chip_info(sdev->pdata);
 	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct snd_soc_component *scomp = sdev->component;
@@ -268,8 +269,17 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
 		return -ENODEV;
 	}
 
-	/* minimum as per HDA spec */
-	snd_pcm_hw_constraint_step(substream->runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 4);
+	/*
+	 * Set period size constraint to ensure BDLE buffer length and
+	 * start address alignment requirements are met. Align to 128
+	 * bytes for newer Intel platforms, with older ones using 4 byte alignment.
+	 */
+	if (chip_info->hw_ip_version >= SOF_INTEL_ACE_4_0)
+		snd_pcm_hw_constraint_step(substream->runtime, 0,
+					   SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 128);
+	else
+		snd_pcm_hw_constraint_step(substream->runtime, 0,
+					   SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 4);
 
 	/* avoid circular buffer wrap in middle of period */
 	snd_pcm_hw_constraint_integer(substream->runtime,
-- 
cgit v1.2.3


From 0669631dbccd41cf3ca7aa70213fcd8bb41c4b38 Mon Sep 17 00:00:00 2001
From: Tomasz Merta <tomasz.merta@arrow.com>
Date: Wed, 8 Apr 2026 10:40:56 +0200
Subject: ASoC: stm32_sai: fix incorrect BCLK polarity for DSP_A/B, LEFT_J

The STM32 SAI driver do not set the clock strobing bit (CKSTR) for DSP_A,
DSP_B and LEFT_J formats, causing data to be sampled on the wrong BCLK
edge when SND_SOC_DAIFMT_NB_NF is used.

Per ALSA convention, NB_NF requires sampling on the rising BCLK edge.
The STM32MP25 SAI reference manual states that CKSTR=1 is required for
signals received by the SAI to be sampled on the SCK rising edge.
Without setting CKSTR=1, the SAI samples on the falling edge, violating
the NB_NF convention. For comparison, the NXP FSL SAI driver correctly
sets FSL_SAI_CR2_BCP for DSP_A, DSP_B and LEFT_J, consistent with its
I2S handling.

This patch adds SAI_XCR1_CKSTR for DSP_A, DSP_B and LEFT_J in
stm32_sai_set_dai_fmt which was verified empirically with a cs47l35 codec.
RIGHT_J (LSB) is not investigated and addressed by this patch.

Note: the STM32 I2S driver (stm32_i2s_set_dai_fmt) may have the same issue
for DSP_A mode, as I2S_CGFR_CKPOL is not set. This has not been verified
and is left for a separate investigation.

Signed-off-by: Tomasz Merta <tommerta@gmail.com>
Link: https://patch.msgid.link/20260408084056.20588-1-tommerta@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/stm/stm32_sai_sub.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index 450e1585edee..3e82fa90e719 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -802,6 +802,7 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 		break;
 	/* Left justified */
 	case SND_SOC_DAIFMT_MSB:
+		cr1 |= SAI_XCR1_CKSTR;
 		frcr |= SAI_XFRCR_FSPOL | SAI_XFRCR_FSDEF;
 		break;
 	/* Right justified */
@@ -809,9 +810,11 @@ static int stm32_sai_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt)
 		frcr |= SAI_XFRCR_FSPOL | SAI_XFRCR_FSDEF;
 		break;
 	case SND_SOC_DAIFMT_DSP_A:
+		cr1 |= SAI_XCR1_CKSTR;
 		frcr |= SAI_XFRCR_FSPOL | SAI_XFRCR_FSOFF;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
+		cr1 |= SAI_XCR1_CKSTR;
 		frcr |= SAI_XFRCR_FSPOL;
 		break;
 	default:
-- 
cgit v1.2.3


From 5241c2ca33bb181bf7abb7cb4bba1cc67d1b6278 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Thu, 2 Apr 2026 11:09:16 +0200
Subject: firmware: efi: Never declare sysfb_primary_display on x86

The x86 architecture comes with its own instance of the global
state variable sysfb_primary_display. Never declare it in the EFI
subsystem. Fix the test for CONFIG_FIRMWARE_EDID accordingly.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: e65ca1646311 ("efi: export sysfb_primary_display for EDID")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index 5a595d026f58..6103b1a082d2 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -60,7 +60,7 @@ extern __weak const efi_config_table_type_t efi_arch_tables[];
  * x86 defines its own instance of sysfb_primary_display and uses
  * it even without EFI, everything else can get them from here.
  */
-#if !defined(CONFIG_X86) && (defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON)) || defined(CONFIG_FIRMWARE_EDID)
+#if !defined(CONFIG_X86) && (defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_FIRMWARE_EDID))
 struct sysfb_display_info sysfb_primary_display __section(".data");
 EXPORT_SYMBOL_GPL(sysfb_primary_display);
 #endif
-- 
cgit v1.2.3


From 23e0cbe55736de222ed975863cf06baf29bee5fe Mon Sep 17 00:00:00 2001
From: Maciej Strozek <mstrozek@opensource.cirrus.com>
Date: Wed, 8 Apr 2026 10:38:31 +0100
Subject: ASoC: SDCA: Fix overwritten var within for loop

mask variable should not be overwritten within the for loop or it will
skip certain bits. Change to using BIT() macro.

Fixes: b9ab3b618241 ("ASoC: SDCA: Add some initial IRQ handlers")
Signed-off-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260408093835.2881486-2-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdca/sdca_interrupts.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index 1838dabcdf60..9acb0be84674 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -117,9 +117,7 @@ static irqreturn_t function_status_handler(int irq, void *data)
 
 	status = val;
 	for_each_set_bit(mask, &status, BITS_PER_BYTE) {
-		mask = 1 << mask;
-
-		switch (mask) {
+		switch (BIT(mask)) {
 		case SDCA_CTL_ENTITY_0_FUNCTION_NEEDS_INITIALIZATION:
 			//FIXME: Add init writes
 			break;
-- 
cgit v1.2.3


From 58dec4fac4c46b42b8264f2d8aa6972ff951c18b Mon Sep 17 00:00:00 2001
From: Maciej Strozek <mstrozek@opensource.cirrus.com>
Date: Wed, 8 Apr 2026 10:38:32 +0100
Subject: ASoC: SDCA: mask Function_Status value

According to the SDCA specification [1], when writing Function_Status during
handling this control, the value should mask off bit 7.

[1] MIPI Specification for SoundWire Device Class for Audio, version
    1.1, section 7.14.1.3 (Host Software Handling of Function_Status)

Signed-off-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260408093835.2881486-3-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdca/sdca_interrupts.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index 9acb0be84674..0693209ffed1 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -138,7 +138,7 @@ static irqreturn_t function_status_handler(int irq, void *data)
 		}
 	}
 
-	ret = regmap_write(interrupt->function_regmap, reg, val);
+	ret = regmap_write(interrupt->function_regmap, reg, val & 0x7F);
 	if (ret < 0) {
 		dev_err(dev, "failed to clear function status: %d\n", ret);
 		goto error;
-- 
cgit v1.2.3


From 0b8757b220f94421bd4ff50cce03886387c4e71c Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 8 Apr 2026 10:38:34 +0100
Subject: ASoC: SDCA: Unregister IRQ handlers on module remove

Ensure that all interrupt handlers are unregistered before the parent
regmap_irq is unregistered.

sdca_irq_cleanup() was only called from the component_remove(). If the
module was loaded and removed without ever being component probed the
FDL interrupts would not be unregistered and this would hit a WARN
when devm called regmap_del_irq_chip() during the removal of the
parent IRQ.

Fixes: 4e53116437e9 ("ASoC: SDCA: Fix errors in IRQ cleanup")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20260408093835.2881486-5-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sdca_interrupts.h      |  4 ++--
 sound/soc/sdca/sdca_class_function.c | 10 +++++++++-
 sound/soc/sdca/sdca_interrupts.c     |  7 +++----
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/include/sound/sdca_interrupts.h b/include/sound/sdca_interrupts.h
index b47003c3d26e..a515cc3df097 100644
--- a/include/sound/sdca_interrupts.h
+++ b/include/sound/sdca_interrupts.h
@@ -83,8 +83,8 @@ int sdca_irq_populate_early(struct device *dev, struct regmap *function_regmap,
 int sdca_irq_populate(struct sdca_function_data *function,
 		      struct snd_soc_component *component,
 		      struct sdca_interrupt_info *info);
-void sdca_irq_cleanup(struct sdca_function_data *function,
-		      struct snd_soc_component *component,
+void sdca_irq_cleanup(struct device *dev,
+		      struct sdca_function_data *function,
 		      struct sdca_interrupt_info *info);
 struct sdca_interrupt_info *sdca_irq_allocate(struct device *dev,
 					      struct regmap *regmap, int irq);
diff --git a/sound/soc/sdca/sdca_class_function.c b/sound/soc/sdca/sdca_class_function.c
index fe404d769c78..730103120514 100644
--- a/sound/soc/sdca/sdca_class_function.c
+++ b/sound/soc/sdca/sdca_class_function.c
@@ -203,7 +203,7 @@ static void class_function_component_remove(struct snd_soc_component *component)
 	struct class_function_drv *drv = snd_soc_component_get_drvdata(component);
 	struct sdca_class_drv *core = drv->core;
 
-	sdca_irq_cleanup(drv->function, component, core->irq_info);
+	sdca_irq_cleanup(component->dev, drv->function, core->irq_info);
 }
 
 static int class_function_set_jack(struct snd_soc_component *component,
@@ -411,6 +411,13 @@ static int class_function_probe(struct auxiliary_device *auxdev,
 	return 0;
 }
 
+static void class_function_remove(struct auxiliary_device *auxdev)
+{
+	struct class_function_drv *drv = auxiliary_get_drvdata(auxdev);
+
+	sdca_irq_cleanup(drv->dev, drv->function, drv->core->irq_info);
+}
+
 static int class_function_runtime_suspend(struct device *dev)
 {
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
@@ -559,6 +566,7 @@ static struct auxiliary_driver class_function_drv = {
 	},
 
 	.probe		= class_function_probe,
+	.remove		= class_function_remove,
 	.id_table	= class_function_id_table
 };
 module_auxiliary_driver(class_function_drv);
diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c
index 0693209ffed1..5cdabf8ae9da 100644
--- a/sound/soc/sdca/sdca_interrupts.c
+++ b/sound/soc/sdca/sdca_interrupts.c
@@ -555,17 +555,16 @@ EXPORT_SYMBOL_NS_GPL(sdca_irq_populate, "SND_SOC_SDCA");
 
 /**
  * sdca_irq_cleanup - Free all the individual IRQs for an SDCA Function
+ * @sdev: Device pointer against which the sdca_interrupt_info was allocated.
  * @function: Pointer to the SDCA Function.
- * @component: Pointer to the ASoC component for the Function.
  * @info: Pointer to the SDCA interrupt info for this device.
  *
  * Typically this would be called from the driver for a single SDCA Function.
  */
-void sdca_irq_cleanup(struct sdca_function_data *function,
-		      struct snd_soc_component *component,
+void sdca_irq_cleanup(struct device *dev,
+		      struct sdca_function_data *function,
 		      struct sdca_interrupt_info *info)
 {
-	struct device *dev = component->dev;
 	int i;
 
 	guard(mutex)(&info->irq_lock);
-- 
cgit v1.2.3


From 6b6f7263d626886a96fce6352f94dfab7a24c339 Mon Sep 17 00:00:00 2001
From: Syed Saba Kareem <Syed.SabaKareem@amd.com>
Date: Wed, 8 Apr 2026 19:00:06 +0530
Subject: ASoC: amd: acp: update DMI quirk and add ACP DMIC for Lenovo
 platforms

Replace DMI_EXACT_MATCH with DMI_MATCH for Lenovo SKU entries (21YW,
21YX) so the quirk applies to all variants of these models, not just
exact SKU matches.

Add ASOC_SDW_ACP_DMIC flag alongside ASOC_SDW_CODEC_SPKR in driver_data
for these Lenovo platform entries, as these platforms use ACP PDM DMIC
instead of SoundWire DMIC for digital microphone support.

Fixes: 3acf517e1ae0 ("ASoC: amd: amd_sdw: add machine driver quirk for Lenovo models")
Tested-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Signed-off-by: Syed Saba Kareem <Syed.SabaKareem@amd.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://patch.msgid.link/20260408133029.1368317-1-syed.sabakareem@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp/acp-sdw-legacy-mach.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/amd/acp/acp-sdw-legacy-mach.c b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
index 92749dc17df8..cd7b1acc7216 100644
--- a/sound/soc/amd/acp/acp-sdw-legacy-mach.c
+++ b/sound/soc/amd/acp/acp-sdw-legacy-mach.c
@@ -99,17 +99,17 @@ static const struct dmi_system_id soc_sdw_quirk_table[] = {
 		.callback = soc_sdw_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "21YW"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "21YW"),
 		},
-		.driver_data = (void *)(ASOC_SDW_CODEC_SPKR),
+		.driver_data = (void *)((ASOC_SDW_CODEC_SPKR) | (ASOC_SDW_ACP_DMIC)),
 	},
 	{
 		.callback = soc_sdw_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "21YX"),
+			DMI_MATCH(DMI_PRODUCT_SKU, "21YX"),
 		},
-		.driver_data = (void *)(ASOC_SDW_CODEC_SPKR),
+		.driver_data = (void *)((ASOC_SDW_CODEC_SPKR) | (ASOC_SDW_ACP_DMIC)),
 	},
 	{
 		.callback = soc_sdw_quirk_cb,
-- 
cgit v1.2.3


From ff14dafde15c11403fac61367a34fea08926e9ee Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 7 Apr 2026 22:16:27 -0700
Subject: Input: uinput - take event lock when submitting FF request "event"

To avoid racing with FF playback events and corrupting device's event
queue take event_lock spinlock when calling uinput_dev_event() when
submitting a FF upload or erase "event".

Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Link: https://patch.msgid.link/adXkf6MWzlB8LA_s@google.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/uinput.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index a973e82205b5..0e9544a98e67 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -25,8 +25,10 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/lockdep.h>
 #include <linux/miscdevice.h>
 #include <linux/overflow.h>
+#include <linux/spinlock.h>
 #include <linux/input/mt.h>
 #include "../input-compat.h"
 
@@ -76,6 +78,8 @@ static int uinput_dev_event(struct input_dev *dev,
 	struct uinput_device	*udev = input_get_drvdata(dev);
 	struct timespec64	ts;
 
+	lockdep_assert_held(&dev->event_lock);
+
 	ktime_get_ts64(&ts);
 
 	udev->buff[udev->head] = (struct input_event) {
@@ -147,6 +151,7 @@ static void uinput_request_release_slot(struct uinput_device *udev,
 static int uinput_request_send(struct uinput_device *udev,
 			       struct uinput_request *request)
 {
+	unsigned long flags;
 	int retval = 0;
 
 	spin_lock(&udev->state_lock);
@@ -160,7 +165,9 @@ static int uinput_request_send(struct uinput_device *udev,
 	 * Tell our userspace application about this new request
 	 * by queueing an input event.
 	 */
+	spin_lock_irqsave(&udev->dev->event_lock, flags);
 	uinput_dev_event(udev->dev, EV_UINPUT, request->code, request->id);
+	spin_unlock_irqrestore(&udev->dev->event_lock, flags);
 
  out:
 	spin_unlock(&udev->state_lock);
-- 
cgit v1.2.3


From 52f657e34d7b21b47434d9d8b26fa7f6778b63a0 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 8 Apr 2026 13:18:57 -0700
Subject: x86: shadow stacks: proper error handling for mmap lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

김영민 reports that shstk_pop_sigframe() doesn't check for errors from
mmap_read_lock_killable(), which is a silly oversight, and also shows
that we haven't marked those functions with "__must_check", which would
have immediately caught it.

So let's fix both issues.

Reported-by: 김영민 <osori@hspace.io>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Acked-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/shstk.c   | 3 ++-
 include/linux/mmap_lock.h | 6 +++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 978232b6d48d..ff8edea8511b 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -351,7 +351,8 @@ static int shstk_pop_sigframe(unsigned long *ssp)
 	need_to_check_vma = PAGE_ALIGN(*ssp) == *ssp;
 
 	if (need_to_check_vma)
-		mmap_read_lock_killable(current->mm);
+		if (mmap_read_lock_killable(current->mm))
+			return -EINTR;
 
 	err = get_shstk_data(&token_addr, (unsigned long __user *)*ssp);
 	if (unlikely(err))
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 93eca48bc443..04b8f61ece5d 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -546,7 +546,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
 	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
-static inline int mmap_write_lock_killable(struct mm_struct *mm)
+static inline int __must_check mmap_write_lock_killable(struct mm_struct *mm)
 {
 	int ret;
 
@@ -593,7 +593,7 @@ static inline void mmap_read_lock(struct mm_struct *mm)
 	__mmap_lock_trace_acquire_returned(mm, false, true);
 }
 
-static inline int mmap_read_lock_killable(struct mm_struct *mm)
+static inline int __must_check mmap_read_lock_killable(struct mm_struct *mm)
 {
 	int ret;
 
@@ -603,7 +603,7 @@ static inline int mmap_read_lock_killable(struct mm_struct *mm)
 	return ret;
 }
 
-static inline bool mmap_read_trylock(struct mm_struct *mm)
+static inline bool __must_check mmap_read_trylock(struct mm_struct *mm)
 {
 	bool ret;
 
-- 
cgit v1.2.3


From c09ea768bdb975e828f8e17293c397c3d14ad85d Mon Sep 17 00:00:00 2001
From: Felix Gu <ustc.gu@gmail.com>
Date: Sun, 5 Apr 2026 14:51:52 +0800
Subject: net: mdio: realtek-rtl9300: use scoped device_for_each_child_node
 loop

Switch to device_for_each_child_node_scoped() to auto-release fwnode
references on early exit.

Fixes: 24e31e474769 ("net: mdio: Add RTL9300 MDIO driver")
Signed-off-by: Felix Gu <ustc.gu@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20260405-rtl9300-v1-1-08e4499cf944@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/mdio-realtek-rtl9300.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/mdio/mdio-realtek-rtl9300.c b/drivers/net/mdio/mdio-realtek-rtl9300.c
index 405a07075dd1..8d5fb014ca06 100644
--- a/drivers/net/mdio/mdio-realtek-rtl9300.c
+++ b/drivers/net/mdio/mdio-realtek-rtl9300.c
@@ -466,7 +466,6 @@ static int rtl9300_mdiobus_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct rtl9300_mdio_priv *priv;
-	struct fwnode_handle *child;
 	int err;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -487,7 +486,7 @@ static int rtl9300_mdiobus_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	device_for_each_child_node(dev, child) {
+	device_for_each_child_node_scoped(dev, child) {
 		err = rtl9300_mdiobus_probe_one(dev, priv, child);
 		if (err)
 			return err;
-- 
cgit v1.2.3


From bdbfead6d38979475df0c2f4bad2b19394fe9bdc Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:29 +0100
Subject: rxrpc: Fix key quota calculation for multitoken keys

In the rxrpc key preparsing, every token extracted sets the proposed quota
value, but for multitoken keys, this will overwrite the previous proposed
quota, losing it.

Fix this by adding to the proposed quota instead.

Fixes: 8a7a3eb4ddbe ("KEYS: RxRPC: Use key preparsing")
Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/key.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 85078114b2dd..af403f0ccab5 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -72,7 +72,7 @@ static int rxrpc_preparse_xdr_rxkad(struct key_preparsed_payload *prep,
 		return -EKEYREJECTED;
 
 	plen = sizeof(*token) + sizeof(*token->kad) + tktlen;
-	prep->quotalen = datalen + plen;
+	prep->quotalen += datalen + plen;
 
 	plen -= sizeof(*token);
 	token = kzalloc_obj(*token);
@@ -199,7 +199,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 	}
 
 	plen = sizeof(*token) + sizeof(*token->rxgk) + tktlen + keylen;
-	prep->quotalen = datalen + plen;
+	prep->quotalen += datalen + plen;
 
 	plen -= sizeof(*token);
 	token = kzalloc_obj(*token);
@@ -460,6 +460,7 @@ static int rxrpc_preparse(struct key_preparsed_payload *prep)
 	memcpy(&kver, prep->data, sizeof(kver));
 	prep->data += sizeof(kver);
 	prep->datalen -= sizeof(kver);
+	prep->quotalen = 0;
 
 	_debug("KEY I/F VERSION: %u", kver);
 
@@ -497,7 +498,7 @@ static int rxrpc_preparse(struct key_preparsed_payload *prep)
 		goto error;
 
 	plen = sizeof(*token->kad) + v1->ticket_length;
-	prep->quotalen = plen + sizeof(*token);
+	prep->quotalen += plen + sizeof(*token);
 
 	ret = -ENOMEM;
 	token = kzalloc_obj(*token);
-- 
cgit v1.2.3


From b555912b9b21075e8298015f888ffe3ff60b1a97 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:30 +0100
Subject: rxrpc: Fix key parsing memleak

In rxrpc_preparse_xdr_yfs_rxgk(), the memory attached to token->rxgk can be
leaked in a few error paths after it's allocated.

Fix this by freeing it in the "reject_token:" case.

Fixes: 0ca100ff4df6 ("rxrpc: Add YFS RxGK (GSSAPI) security class")
Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/key.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index af403f0ccab5..26d4336a4a02 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -274,6 +274,7 @@ nomem_token:
 nomem:
 	return -ENOMEM;
 reject_token:
+	kfree(token->rxgk);
 	kfree(token);
 reject:
 	return -EKEYREJECTED;
-- 
cgit v1.2.3


From 6a59d84b4fc2f27f7b40e348506cc686712e260b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:31 +0100
Subject: rxrpc: Fix anonymous key handling

In rxrpc_new_client_call_for_sendmsg(), a key with no payload is meant to
be substituted for a NULL key pointer, but the variable this is done with
is subsequently not used.

Fix this by using "key" rather than "rx->key" when filling in the
connection parameters.

Note that this only affects direct use of AF_RXRPC; the kAFS filesystem
doesn't use sendmsg() directly and so bypasses the issue.  Further,
AF_RXRPC passes a NULL key in if no key is set, so using an anonymous key
in that manner works.  Since this hasn't been noticed to this point, it
might be better just to remove the "key" variable and the code that sets it
- and, arguably, rxrpc_init_client_call_security() would be a better place
to handle it.

Fixes: 19ffa01c9c45 ("rxrpc: Use structs to hold connection params and protocol info")
Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-4-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/sendmsg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 04f9c5f2dc24..c35de4fd75e3 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -637,7 +637,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
 	cp.peer			= peer;
-	cp.key			= rx->key;
+	cp.key			= key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= rx->exclusive | p->exclusive;
 	cp.upgrade		= p->upgrade;
-- 
cgit v1.2.3


From 146d4ab94cf129ee06cd467cb5c71368a6b5bad6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:32 +0100
Subject: rxrpc: Fix call removal to use RCU safe deletion

Fix rxrpc call removal from the rxnet->calls list to use list_del_rcu()
rather than list_del_init() to prevent stuffing up reading
/proc/net/rxrpc/calls from potentially getting into an infinite loop.

This, however, means that list_empty() no longer works on an entry that's
been deleted from the list, making it harder to detect prior deletion.  Fix
this by:

Firstly, make rxrpc_destroy_all_calls() only dump the first ten calls that
are unexpectedly still on the list.  Limiting the number of steps means
there's no need to call cond_resched() or to remove calls from the list
here, thereby eliminating the need for rxrpc_put_call() to check for that.

rxrpc_put_call() can then be fixed to unconditionally delete the call from
the list as it is the only place that the deletion occurs.

Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing")
Closes: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-5-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/trace/events/rxrpc.h |  2 +-
 net/rxrpc/call_object.c      | 24 +++++++++---------------
 2 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 869f97c9bf73..a826cd80007b 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -347,7 +347,7 @@
 	EM(rxrpc_call_see_release,		"SEE release ") \
 	EM(rxrpc_call_see_userid_exists,	"SEE u-exists") \
 	EM(rxrpc_call_see_waiting_call,		"SEE q-conn  ") \
-	E_(rxrpc_call_see_zap,			"SEE zap     ")
+	E_(rxrpc_call_see_still_live,		"SEE !still-l")
 
 #define rxrpc_txqueue_traces \
 	EM(rxrpc_txqueue_await_reply,		"AWR") \
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 918f41d97a2f..59329cfe1532 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -654,11 +654,9 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
 	if (dead) {
 		ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
 
-		if (!list_empty(&call->link)) {
-			spin_lock(&rxnet->call_lock);
-			list_del_init(&call->link);
-			spin_unlock(&rxnet->call_lock);
-		}
+		spin_lock(&rxnet->call_lock);
+		list_del_rcu(&call->link);
+		spin_unlock(&rxnet->call_lock);
 
 		rxrpc_cleanup_call(call);
 	}
@@ -730,24 +728,20 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 	_enter("");
 
 	if (!list_empty(&rxnet->calls)) {
-		spin_lock(&rxnet->call_lock);
+		int shown = 0;
 
-		while (!list_empty(&rxnet->calls)) {
-			call = list_entry(rxnet->calls.next,
-					  struct rxrpc_call, link);
-			_debug("Zapping call %p", call);
+		spin_lock(&rxnet->call_lock);
 
-			rxrpc_see_call(call, rxrpc_call_see_zap);
-			list_del_init(&call->link);
+		list_for_each_entry(call, &rxnet->calls, link) {
+			rxrpc_see_call(call, rxrpc_call_see_still_live);
 
 			pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
 			       call, refcount_read(&call->ref),
 			       rxrpc_call_states[__rxrpc_call_state(call)],
 			       call->flags, call->events);
 
-			spin_unlock(&rxnet->call_lock);
-			cond_resched();
-			spin_lock(&rxnet->call_lock);
+			if (++shown >= 10)
+				break;
 		}
 
 		spin_unlock(&rxnet->call_lock);
-- 
cgit v1.2.3


From d179a868dd755b0cfcf7582e00943d702b9943b8 Mon Sep 17 00:00:00 2001
From: Oleh Konko <security@1seal.org>
Date: Wed, 8 Apr 2026 13:12:33 +0100
Subject: rxrpc: Fix RxGK token loading to check bounds

rxrpc_preparse_xdr_yfs_rxgk() reads the raw key length and ticket length
from the XDR token as u32 values and passes each through round_up(x, 4)
before using the rounded value for validation and allocation.  When the raw
length is >= 0xfffffffd, round_up() wraps to 0, so the bounds check and
kzalloc both use 0 while the subsequent memcpy still copies the original
~4 GiB value, producing a heap buffer overflow reachable from an
unprivileged add_key() call.

Fix this by:

 (1) Rejecting raw key lengths above AFSTOKEN_GK_KEY_MAX and raw ticket
     lengths above AFSTOKEN_GK_TOKEN_MAX before rounding, consistent with
     the caps that the RxKAD path already enforces via AFSTOKEN_RK_TIX_MAX.

 (2) Sizing the flexible-array allocation from the validated raw key
     length via struct_size_t() instead of the rounded value.

 (3) Caching the raw lengths so that the later field assignments and
     memcpy calls do not re-read from the token, eliminating a class of
     TOCTOU re-parse.

The control path (valid token with lengths within bounds) is unaffected.

Fixes: 0ca100ff4df6 ("rxrpc: Add YFS RxGK (GSSAPI) security class")
Signed-off-by: Oleh Konko <security@1seal.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-6-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/key.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 26d4336a4a02..77237a82be3b 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -13,6 +13,7 @@
 #include <crypto/skcipher.h>
 #include <linux/module.h>
 #include <linux/net.h>
+#include <linux/overflow.h>
 #include <linux/skbuff.h>
 #include <linux/key-type.h>
 #include <linux/ctype.h>
@@ -171,7 +172,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 	size_t plen;
 	const __be32 *ticket, *key;
 	s64 tmp;
-	u32 tktlen, keylen;
+	size_t raw_keylen, raw_tktlen, keylen, tktlen;
 
 	_enter(",{%x,%x,%x,%x},%x",
 	       ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
@@ -181,18 +182,22 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 		goto reject;
 
 	key = xdr + (6 * 2 + 1);
-	keylen = ntohl(key[-1]);
-	_debug("keylen: %x", keylen);
-	keylen = round_up(keylen, 4);
+	raw_keylen = ntohl(key[-1]);
+	_debug("keylen: %zx", raw_keylen);
+	if (raw_keylen > AFSTOKEN_GK_KEY_MAX)
+		goto reject;
+	keylen = round_up(raw_keylen, 4);
 	if ((6 * 2 + 2) * 4 + keylen > toklen)
 		goto reject;
 
 	ticket = xdr + (6 * 2 + 1 + (keylen / 4) + 1);
-	tktlen = ntohl(ticket[-1]);
-	_debug("tktlen: %x", tktlen);
-	tktlen = round_up(tktlen, 4);
+	raw_tktlen = ntohl(ticket[-1]);
+	_debug("tktlen: %zx", raw_tktlen);
+	if (raw_tktlen > AFSTOKEN_GK_TOKEN_MAX)
+		goto reject;
+	tktlen = round_up(raw_tktlen, 4);
 	if ((6 * 2 + 2) * 4 + keylen + tktlen != toklen) {
-		kleave(" = -EKEYREJECTED [%x!=%x, %x,%x]",
+		kleave(" = -EKEYREJECTED [%zx!=%x, %zx,%zx]",
 		       (6 * 2 + 2) * 4 + keylen + tktlen, toklen,
 		       keylen, tktlen);
 		goto reject;
@@ -206,7 +211,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 	if (!token)
 		goto nomem;
 
-	token->rxgk = kzalloc(sizeof(*token->rxgk) + keylen, GFP_KERNEL);
+	token->rxgk = kzalloc(struct_size_t(struct rxgk_key, _key, raw_keylen), GFP_KERNEL);
 	if (!token->rxgk)
 		goto nomem_token;
 
@@ -221,9 +226,9 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 	token->rxgk->enctype	= tmp = xdr_dec64(xdr + 5 * 2);
 	if (tmp < 0 || tmp > UINT_MAX)
 		goto reject_token;
-	token->rxgk->key.len	= ntohl(key[-1]);
+	token->rxgk->key.len	= raw_keylen;
 	token->rxgk->key.data	= token->rxgk->_key;
-	token->rxgk->ticket.len = ntohl(ticket[-1]);
+	token->rxgk->ticket.len = raw_tktlen;
 
 	if (token->rxgk->endtime != 0) {
 		expiry = rxrpc_s64_to_time64(token->rxgk->endtime);
@@ -236,8 +241,7 @@ static int rxrpc_preparse_xdr_yfs_rxgk(struct key_preparsed_payload *prep,
 	memcpy(token->rxgk->key.data, key, token->rxgk->key.len);
 
 	/* Pad the ticket so that we can use it directly in XDR */
-	token->rxgk->ticket.data = kzalloc(round_up(token->rxgk->ticket.len, 4),
-					   GFP_KERNEL);
+	token->rxgk->ticket.data = kzalloc(tktlen, GFP_KERNEL);
 	if (!token->rxgk->ticket.data)
 		goto nomem_yrxgk;
 	memcpy(token->rxgk->ticket.data, ticket, token->rxgk->ticket.len);
-- 
cgit v1.2.3


From b33f5741bb187db8ff32e8f5b96def77cc94dfca Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Wed, 8 Apr 2026 13:12:34 +0100
Subject: rxrpc: Fix use of wrong skb when comparing queued RESP challenge
 serial

In rxrpc_post_response(), the code should be comparing the challenge serial
number from the cached response before deciding to switch to a newer
response, but looks at the newer packet private data instead, rendering the
comparison always false.

Fix this by switching to look at the older packet.

Fix further[1] to substitute the new packet in place of the old one if
newer and also to release whichever we don't use.

Fixes: 5800b1cf3fd8 ("rxrpc: Allow CHALLENGEs to the passed to the app for a RESPONSE")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://sashiko.dev/#/patchset/20260319150150.4189381-1-dhowells%40redhat.com [1]
Link: https://patch.msgid.link/20260408121252.2249051-7-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/trace/events/rxrpc.h | 1 +
 net/rxrpc/conn_event.c       | 5 +++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a826cd80007b..f7f559204b87 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -185,6 +185,7 @@
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
 	EM(rxrpc_skb_put_oob,			"PUT oob      ") \
+	EM(rxrpc_skb_put_old_response,		"PUT old-resp ") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_purge_oob,		"PUT purge-oob") \
 	EM(rxrpc_skb_put_response,		"PUT response ") \
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 98ad9b51ca2c..c50cbfc5a313 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -557,11 +557,11 @@ void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb)
 	spin_lock_irq(&local->lock);
 	old = conn->tx_response;
 	if (old) {
-		struct rxrpc_skb_priv *osp = rxrpc_skb(skb);
+		struct rxrpc_skb_priv *osp = rxrpc_skb(old);
 
 		/* Always go with the response to the most recent challenge. */
 		if (after(sp->resp.challenge_serial, osp->resp.challenge_serial))
-			conn->tx_response = old;
+			conn->tx_response = skb;
 		else
 			old = skb;
 	} else {
@@ -569,4 +569,5 @@ void rxrpc_post_response(struct rxrpc_connection *conn, struct sk_buff *skb)
 	}
 	spin_unlock_irq(&local->lock);
 	rxrpc_poke_conn(conn, rxrpc_conn_get_poke_response);
+	rxrpc_free_skb(old, rxrpc_skb_put_old_response);
 }
-- 
cgit v1.2.3


From 65b3ffe0972ed023acc3981a0f7e1ae5d0208bd3 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Wed, 8 Apr 2026 13:12:35 +0100
Subject: rxrpc: Fix rack timer warning to report unexpected mode

rxrpc_rack_timer_expired() clears call->rack_timer_mode to OFF before
the switch. The default case warning therefore always prints OFF and
doesn't identify the unexpected timer mode.

Log the saved mode value instead so the warning reports the actual
unexpected rack timer mode.

Fixes: 7c482665931b ("rxrpc: Implement RACK/TLP to deal with transmission stalls [RFC8985]")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-8-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/input_rack.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/input_rack.c b/net/rxrpc/input_rack.c
index 13c371261e0a..9eb109ffba56 100644
--- a/net/rxrpc/input_rack.c
+++ b/net/rxrpc/input_rack.c
@@ -413,6 +413,6 @@ void rxrpc_rack_timer_expired(struct rxrpc_call *call, ktime_t overran_by)
 		break;
 	//case RXRPC_CALL_RACKTIMER_ZEROWIN:
 	default:
-		pr_warn("Unexpected rack timer %u", call->rack_timer_mode);
+		pr_warn("Unexpected rack timer %u", mode);
 	}
 }
-- 
cgit v1.2.3


From d666540d217e8d420544ebdfbadeedd623562733 Mon Sep 17 00:00:00 2001
From: Anderson Nascimento <anderson@allelesecurity.com>
Date: Wed, 8 Apr 2026 13:12:36 +0100
Subject: rxrpc: Fix key reference count leak from call->key

When creating a client call in rxrpc_alloc_client_call(), the code obtains
a reference to the key.  This is never cleaned up and gets leaked when the
call is destroyed.

Fix this by freeing call->key in rxrpc_destroy_call().

Before the patch, it shows the key reference counter elevated:

$ cat /proc/keys | grep afs@54321
1bffe9cd I--Q--i 8053480 4169w 3b010000  1000  1000 rxrpc     afs@54321: ka
$

After the patch, the invalidated key is removed when the code exits:

$ cat /proc/keys | grep afs@54321
$

Fixes: f3441d4125fc ("rxrpc: Copy client call parameters into rxrpc_call earlier")
Signed-off-by: Anderson Nascimento <anderson@allelesecurity.com>
Co-developed-by: David Howells <dhowells@redhat.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-9-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/call_object.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 59329cfe1532..f035f486c139 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -692,6 +692,7 @@ static void rxrpc_destroy_call(struct work_struct *work)
 	rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call);
 	rxrpc_put_peer(call->peer, rxrpc_peer_put_call);
 	rxrpc_put_local(call->local, rxrpc_local_put_call);
+	key_put(call->key);
 	call_rcu(&call->rcu, rxrpc_rcu_free_call);
 }
 
-- 
cgit v1.2.3


From 0cd3e3f3f2ec1a45aa559e2c0f3d57fac5eb3c25 Mon Sep 17 00:00:00 2001
From: Marc Dionne <marc.c.dionne@gmail.com>
Date: Wed, 8 Apr 2026 13:12:37 +0100
Subject: rxrpc: Fix to request an ack if window is limited

Peers may only send immediate acks for every 2 UDP packets received.
When sending a jumbogram, it is important to check that there is
sufficient window space to send another same sized jumbogram following
the current one, and request an ack if there isn't.  Failure to do so may
cause the call to stall waiting for an ack until the resend timer fires.

Where jumbograms are in use this causes a very significant drop in
performance.

Fixes: fe24a5494390 ("rxrpc: Send jumbo DATA packets")
Signed-off-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-10-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/trace/events/rxrpc.h | 1 +
 net/rxrpc/ar-internal.h      | 2 +-
 net/rxrpc/output.c           | 2 ++
 net/rxrpc/proc.c             | 5 +++--
 4 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index f7f559204b87..578b8038b211 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -521,6 +521,7 @@
 #define rxrpc_req_ack_traces \
 	EM(rxrpc_reqack_ack_lost,		"ACK-LOST  ")	\
 	EM(rxrpc_reqack_app_stall,		"APP-STALL ")	\
+	EM(rxrpc_reqack_jumbo_win,		"JUMBO-WIN ")	\
 	EM(rxrpc_reqack_more_rtt,		"MORE-RTT  ")	\
 	EM(rxrpc_reqack_no_srv_last,		"NO-SRVLAST")	\
 	EM(rxrpc_reqack_old_rtt,		"OLD-RTT   ")	\
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 36d6ca0d1089..96ecb83c9071 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -117,7 +117,7 @@ struct rxrpc_net {
 	atomic_t		stat_tx_jumbo[10];
 	atomic_t		stat_rx_jumbo[10];
 
-	atomic_t		stat_why_req_ack[8];
+	atomic_t		stat_why_req_ack[9];
 
 	atomic_t		stat_io_loop;
 };
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index d70db367e358..870e59bf06af 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -479,6 +479,8 @@ static size_t rxrpc_prepare_data_subpacket(struct rxrpc_call *call,
 		why = rxrpc_reqack_old_rtt;
 	else if (!last && !after(READ_ONCE(call->send_top), txb->seq))
 		why = rxrpc_reqack_app_stall;
+	else if (call->tx_winsize <= (2 * req->n) || call->cong_cwnd <= (2 * req->n))
+		why = rxrpc_reqack_jumbo_win;
 	else
 		goto dont_set_request_ack;
 
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 59292f7f9205..7755fca5beb8 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -518,11 +518,12 @@ int rxrpc_stats_show(struct seq_file *seq, void *v)
 		   atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE]),
 		   atomic_read(&rxnet->stat_rx_acks[0]));
 	seq_printf(seq,
-		   "Why-Req-A: acklost=%u mrtt=%u ortt=%u stall=%u\n",
+		   "Why-Req-A: acklost=%u mrtt=%u ortt=%u stall=%u jwin=%u\n",
 		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]),
 		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]),
 		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt]),
-		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_app_stall]));
+		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_app_stall]),
+		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_jumbo_win]));
 	seq_printf(seq,
 		   "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n",
 		   atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]),
-- 
cgit v1.2.3


From 6331f1b24a3e85465f6454e003a3e6c22005a5c5 Mon Sep 17 00:00:00 2001
From: Douya Le <ldy3087146292@gmail.com>
Date: Wed, 8 Apr 2026 13:12:38 +0100
Subject: rxrpc: Only put the call ref if one was acquired

rxrpc_input_packet_on_conn() can process a to-client packet after the
current client call on the channel has already been torn down.  In that
case chan->call is NULL, rxrpc_try_get_call() returns NULL and there is
no reference to drop.

The client-side implicit-end error path does not account for that and
unconditionally calls rxrpc_put_call().  This turns a protocol error
path into a kernel crash instead of rejecting the packet.

Only drop the call reference if one was actually acquired.  Keep the
existing protocol error handling unchanged.

Fixes: 5e6ef4f1017c ("rxrpc: Make the I/O thread take over the call and local processor work")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Signed-off-by: Douya Le <ldy3087146292@gmail.com>
Co-developed-by: Yuan Tan <tanyuan98@gmail.com>
Signed-off-by: Yuan Tan <tanyuan98@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Ao Zhou <n05ec@lzu.edu.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-11-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/io_thread.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index e939ecf417c4..697956931925 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -419,7 +419,8 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
 
 	if (sp->hdr.callNumber > chan->call_id) {
 		if (rxrpc_to_client(sp)) {
-			rxrpc_put_call(call, rxrpc_call_put_input);
+			if (call)
+				rxrpc_put_call(call, rxrpc_call_put_input);
 			return rxrpc_protocol_error(skb,
 						    rxrpc_eproto_unexpected_implicit_end);
 		}
-- 
cgit v1.2.3


From fe4447cd95623b1cfacc15f280aab73a6d7340b2 Mon Sep 17 00:00:00 2001
From: Yuqi Xu <xuyuqiabc@gmail.com>
Date: Wed, 8 Apr 2026 13:12:39 +0100
Subject: rxrpc: reject undecryptable rxkad response tickets

rxkad_decrypt_ticket() decrypts the RXKAD response ticket and then
parses the buffer as plaintext without checking whether
crypto_skcipher_decrypt() succeeded.

A malformed RESPONSE can therefore use a non-block-aligned ticket
length, make the decrypt operation fail, and still drive the ticket
parser with attacker-controlled bytes.

Check the decrypt result and abort the connection with RXKADBADTICKET
when ticket decryption fails.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Yuqi Xu <xuyuqiabc@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-12-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxkad.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index e923d6829008..0f79d694cb08 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -958,6 +958,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	struct in_addr addr;
 	unsigned int life;
 	time64_t issue, now;
+	int ret;
 	bool little_endian;
 	u8 *p, *q, *name, *end;
 
@@ -977,8 +978,11 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	sg_init_one(&sg[0], ticket, ticket_len);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, ticket_len, iv.x);
-	crypto_skcipher_decrypt(req);
+	ret = crypto_skcipher_decrypt(req);
 	skcipher_request_free(req);
+	if (ret < 0)
+		return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO,
+					rxkad_abort_resp_tkt_short);
 
 	p = ticket;
 	end = p + ticket_len;
-- 
cgit v1.2.3


From 3e3138007887504ee9206d0bfb5acb062c600025 Mon Sep 17 00:00:00 2001
From: Keenan Dong <keenanat2000@gmail.com>
Date: Wed, 8 Apr 2026 13:12:40 +0100
Subject: rxrpc: fix RESPONSE authenticator parser OOB read

rxgk_verify_authenticator() copies auth_len bytes into a temporary
buffer and then passes p + auth_len as the parser limit to
rxgk_do_verify_authenticator(). Since p is a __be32 *, that inflates the
parser end pointer by a factor of four and lets malformed RESPONSE
authenticators read past the kmalloc() buffer.

Decoded from the original latest-net reproduction logs with
scripts/decode_stacktrace.sh:

BUG: KASAN: slab-out-of-bounds in rxgk_verify_response()
Call Trace:
 dump_stack_lvl() [lib/dump_stack.c:123]
 print_report() [mm/kasan/report.c:379 mm/kasan/report.c:482]
 kasan_report() [mm/kasan/report.c:597]
 rxgk_verify_response()
   [net/rxrpc/rxgk.c:1103 net/rxrpc/rxgk.c:1167
    net/rxrpc/rxgk.c:1274]
 rxrpc_process_connection()
   [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364
    net/rxrpc/conn_event.c:386]
 process_one_work() [kernel/workqueue.c:3281]
 worker_thread()
   [kernel/workqueue.c:3353 kernel/workqueue.c:3440]
 kthread() [kernel/kthread.c:436]
 ret_from_fork() [arch/x86/kernel/process.c:164]

Allocated by task 54:
 rxgk_verify_response()
   [include/linux/slab.h:954 net/rxrpc/rxgk.c:1155
    net/rxrpc/rxgk.c:1274]
 rxrpc_process_connection()
   [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364
    net/rxrpc/conn_event.c:386]

Convert the byte count to __be32 units before constructing the parser
limit.

Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)")
Signed-off-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: Willy Tarreau <w@1wt.eu>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-13-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxgk.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index f9f5a2dc62ed..01dbdf0b5cf2 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -1164,7 +1164,8 @@ static int rxgk_verify_authenticator(struct rxrpc_connection *conn,
 	}
 
 	p = auth;
-	ret = rxgk_do_verify_authenticator(conn, krb5, skb, p, p + auth_len);
+	ret = rxgk_do_verify_authenticator(conn, krb5, skb, p,
+					   p + auth_len / sizeof(*p));
 error:
 	kfree(auth);
 	return ret;
-- 
cgit v1.2.3


From a2567217ade970ecc458144b6be469bc015b23e5 Mon Sep 17 00:00:00 2001
From: Keenan Dong <keenanat2000@gmail.com>
Date: Wed, 8 Apr 2026 13:12:41 +0100
Subject: rxrpc: fix oversized RESPONSE authenticator length check

rxgk_verify_response() decodes auth_len from the packet and is supposed
to verify that it fits in the remaining bytes. The existing check is
inverted, so oversized RESPONSE authenticators are accepted and passed
to rxgk_decrypt_skb(), which can later reach skb_to_sgvec() with an
impossible length and hit BUG_ON(len).

Decoded from the original latest-net reproduction logs with
scripts/decode_stacktrace.sh:

RIP: __skb_to_sgvec()
  [net/core/skbuff.c:5285 (discriminator 1)]
Call Trace:
 skb_to_sgvec() [net/core/skbuff.c:5305]
 rxgk_decrypt_skb() [net/rxrpc/rxgk_common.h:81]
 rxgk_verify_response() [net/rxrpc/rxgk.c:1268]
 rxrpc_process_connection()
   [net/rxrpc/conn_event.c:266 net/rxrpc/conn_event.c:364
    net/rxrpc/conn_event.c:386]
 process_one_work() [kernel/workqueue.c:3281]
 worker_thread()
   [kernel/workqueue.c:3353 kernel/workqueue.c:3440]
 kthread() [kernel/kthread.c:436]
 ret_from_fork() [arch/x86/kernel/process.c:164]

Reject authenticator lengths that exceed the remaining packet payload.

Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)")
Signed-off-by: Keenan Dong <keenanat2000@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: Willy Tarreau <w@1wt.eu>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-14-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxgk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index 01dbdf0b5cf2..9e4a4ff28913 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -1224,7 +1224,7 @@ static int rxgk_verify_response(struct rxrpc_connection *conn,
 
 	auth_offset	= offset;
 	auth_len	= ntohl(xauth_len);
-	if (auth_len < len)
+	if (auth_len > len)
 		goto short_packet;
 	if (auth_len & 3)
 		goto inconsistent;
-- 
cgit v1.2.3


From f125846ee79fcae537a964ce66494e96fa54a6de Mon Sep 17 00:00:00 2001
From: Luxiao Xu <rakukuip@gmail.com>
Date: Wed, 8 Apr 2026 13:12:42 +0100
Subject: rxrpc: fix reference count leak in rxrpc_server_keyring()

This patch fixes a reference count leak in rxrpc_server_keyring()
by checking if rx->securities is already set.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Luxiao Xu <rakukuip@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-15-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/server_key.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c
index 36b05fd842a7..27491f1e1273 100644
--- a/net/rxrpc/server_key.c
+++ b/net/rxrpc/server_key.c
@@ -125,6 +125,9 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
 
 	_enter("");
 
+	if (rx->securities)
+		return -EINVAL;
+
 	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 2afd86ccbb2082a3c4258aea8c07e5bb6267bc2f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:43 +0100
Subject: rxrpc: Fix key/keyring checks in
 setsockopt(RXRPC_SECURITY_KEY/KEYRING)

An AF_RXRPC socket can be both client and server at the same time.  When
sending new calls (ie. it's acting as a client), it uses rx->key to set the
security, and when accepting incoming calls (ie. it's acting as a server),
it uses rx->securities.

setsockopt(RXRPC_SECURITY_KEY) sets rx->key to point to an rxrpc-type key
and setsockopt(RXRPC_SECURITY_KEYRING) sets rx->securities to point to a
keyring of rxrpc_s-type keys.

Now, it should be possible to use both rx->key and rx->securities on the
same socket - but for userspace AF_RXRPC sockets rxrpc_setsockopt()
prevents that.

Fix this by:

 (1) Remove the incorrect check rxrpc_setsockopt(RXRPC_SECURITY_KEYRING)
     makes on rx->key.

 (2) Move the check that rxrpc_setsockopt(RXRPC_SECURITY_KEY) makes on
     rx->key down into rxrpc_request_key().

 (3) Remove rxrpc_request_key()'s check on rx->securities.

This (in combination with a previous patch) pushes the checks down into the
functions that set those pointers and removes the cross-checks that prevent
both key and keyring being set.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Anderson Nascimento <anderson@allelesecurity.com>
cc: Luxiao Xu <rakukuip@gmail.com>
cc: Yuan Tan <yuantan098@gmail.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-16-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/af_rxrpc.c | 6 ------
 net/rxrpc/key.c      | 2 +-
 2 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0f90272ac254..32ec91fa938f 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -654,9 +654,6 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			goto success;
 
 		case RXRPC_SECURITY_KEY:
-			ret = -EINVAL;
-			if (rx->key)
-				goto error;
 			ret = -EISCONN;
 			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
@@ -664,9 +661,6 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 			goto error;
 
 		case RXRPC_SECURITY_KEYRING:
-			ret = -EINVAL;
-			if (rx->key)
-				goto error;
 			ret = -EISCONN;
 			if (rx->sk.sk_state != RXRPC_UNBOUND)
 				goto error;
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 77237a82be3b..6301d79ee35a 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -622,7 +622,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
 
 	_enter("");
 
-	if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities)
+	if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->key)
 		return -EINVAL;
 
 	description = memdup_sockptr_nul(optval, optlen);
-- 
cgit v1.2.3


From f93af41b9f5f798823d0d0fb8765c2a936d76270 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:44 +0100
Subject: rxrpc: Fix missing error checks for rxkad encryption/decryption
 failure

Add error checking for failure of crypto_skcipher_en/decrypt() to various
rxkad function as the crypto functions can fail with ENOMEM at least.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-17-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxkad.c | 57 ++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 38 insertions(+), 19 deletions(-)

diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 0f79d694cb08..eb7f2769d2b1 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -197,6 +197,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
 	struct rxrpc_crypt iv;
 	__be32 *tmpbuf;
 	size_t tmpsize = 4 * sizeof(__be32);
+	int ret;
 
 	_enter("");
 
@@ -225,13 +226,13 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
 	skcipher_request_set_sync_tfm(req, ci);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x);
-	crypto_skcipher_encrypt(req);
+	ret = crypto_skcipher_encrypt(req);
 	skcipher_request_free(req);
 
 	memcpy(&conn->rxkad.csum_iv, tmpbuf + 2, sizeof(conn->rxkad.csum_iv));
 	kfree(tmpbuf);
-	_leave(" = 0");
-	return 0;
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
@@ -264,6 +265,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 	struct scatterlist sg;
 	size_t pad;
 	u16 check;
+	int ret;
 
 	_enter("");
 
@@ -286,11 +288,11 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
-	crypto_skcipher_encrypt(req);
+	ret = crypto_skcipher_encrypt(req);
 	skcipher_request_zero(req);
 
-	_leave(" = 0");
-	return 0;
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
@@ -345,7 +347,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	union {
 		__be32 buf[2];
 	} crypto __aligned(8);
-	u32 x, y;
+	u32 x, y = 0;
 	int ret;
 
 	_enter("{%d{%x}},{#%u},%u,",
@@ -376,8 +378,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
-	crypto_skcipher_encrypt(req);
+	ret = crypto_skcipher_encrypt(req);
 	skcipher_request_zero(req);
+	if (ret < 0)
+		goto out;
 
 	y = ntohl(crypto.buf[1]);
 	y = (y >> 16) & 0xffff;
@@ -413,6 +417,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 		memset(p + txb->pkt_len, 0, gap);
 	}
 
+out:
 	skcipher_request_free(req);
 	_leave(" = %d [set %x]", ret, y);
 	return ret;
@@ -453,8 +458,10 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, 8, iv.x);
-	crypto_skcipher_decrypt(req);
+	ret = crypto_skcipher_decrypt(req);
 	skcipher_request_zero(req);
+	if (ret < 0)
+		return ret;
 
 	/* Extract the decrypted packet length */
 	if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
@@ -531,10 +538,14 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x);
-	crypto_skcipher_decrypt(req);
+	ret = crypto_skcipher_decrypt(req);
 	skcipher_request_zero(req);
 	if (sg != _sg)
 		kfree(sg);
+	if (ret < 0) {
+		WARN_ON_ONCE(ret != -ENOMEM);
+		return ret;
+	}
 
 	/* Extract the decrypted packet length */
 	if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
@@ -602,8 +613,10 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
 	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
-	crypto_skcipher_encrypt(req);
+	ret = crypto_skcipher_encrypt(req);
 	skcipher_request_zero(req);
+	if (ret < 0)
+		goto out;
 
 	y = ntohl(crypto.buf[1]);
 	cksum = (y >> 16) & 0xffff;
@@ -1077,21 +1090,23 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 /*
  * decrypt the response packet
  */
-static void rxkad_decrypt_response(struct rxrpc_connection *conn,
-				   struct rxkad_response *resp,
-				   const struct rxrpc_crypt *session_key)
+static int rxkad_decrypt_response(struct rxrpc_connection *conn,
+				  struct rxkad_response *resp,
+				  const struct rxrpc_crypt *session_key)
 {
 	struct skcipher_request *req = rxkad_ci_req;
 	struct scatterlist sg[1];
 	struct rxrpc_crypt iv;
+	int ret;
 
 	_enter(",,%08x%08x",
 	       ntohl(session_key->n[0]), ntohl(session_key->n[1]));
 
 	mutex_lock(&rxkad_ci_mutex);
-	if (crypto_sync_skcipher_setkey(rxkad_ci, session_key->x,
-					sizeof(*session_key)) < 0)
-		BUG();
+	ret = crypto_sync_skcipher_setkey(rxkad_ci, session_key->x,
+					  sizeof(*session_key));
+	if (ret < 0)
+		goto unlock;
 
 	memcpy(&iv, session_key, sizeof(iv));
 
@@ -1100,12 +1115,14 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn,
 	skcipher_request_set_sync_tfm(req, rxkad_ci);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
-	crypto_skcipher_decrypt(req);
+	ret = crypto_skcipher_decrypt(req);
 	skcipher_request_zero(req);
 
+unlock:
 	mutex_unlock(&rxkad_ci_mutex);
 
 	_leave("");
+	return ret;
 }
 
 /*
@@ -1198,7 +1215,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 
 	/* use the session key from inside the ticket to decrypt the
 	 * response */
-	rxkad_decrypt_response(conn, response, &session_key);
+	ret = rxkad_decrypt_response(conn, response, &session_key);
+	if (ret < 0)
+		goto temporary_error_free_ticket;
 
 	if (ntohl(response->encrypted.epoch) != conn->proto.epoch ||
 	    ntohl(response->encrypted.cid) != conn->proto.cid ||
-- 
cgit v1.2.3


From 699e52180f4231c257821c037ed5c99d5eb0edb8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:45 +0100
Subject: rxrpc: Fix integer overflow in rxgk_verify_response()

In rxgk_verify_response(), there's a potential integer overflow due to
rounding up token_len before checking it, thereby allowing the length check to
be bypassed.

Fix this by checking the unrounded value against len too (len is limited as
the response must fit in a single UDP packet).

Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)")
Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-18-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxgk.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index 9e4a4ff28913..064c1531fc99 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -1209,7 +1209,8 @@ static int rxgk_verify_response(struct rxrpc_connection *conn,
 
 	token_offset	= offset;
 	token_len	= ntohl(rhdr.token_len);
-	if (xdr_round_up(token_len) + sizeof(__be32) > len)
+	if (token_len > len ||
+	    xdr_round_up(token_len) + sizeof(__be32) > len)
 		goto short_packet;
 
 	trace_rxrpc_rx_response(conn, sp->hdr.serial, 0, sp->hdr.cksum, token_len);
-- 
cgit v1.2.3


From 7e1876caa8363056f58a21d3b31b82c2daf7e608 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:46 +0100
Subject: rxrpc: Fix leak of rxgk context in rxgk_verify_response()

Fix rxgk_verify_response() to clean up the rxgk context it creates.

Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)")
Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-19-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxgk.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index 064c1531fc99..c67e3c2ca871 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -1270,16 +1270,18 @@ static int rxgk_verify_response(struct rxrpc_connection *conn,
 	if (ret < 0) {
 		rxrpc_abort_conn(conn, skb, RXGK_SEALEDINCON, ret,
 				 rxgk_abort_resp_auth_dec);
-		goto out;
+		goto out_gk;
 	}
 
 	ret = rxgk_verify_authenticator(conn, krb5, skb, auth_offset, auth_len);
 	if (ret < 0)
-		goto out;
+		goto out_gk;
 
 	conn->key = key;
 	key = NULL;
 	ret = 0;
+out_gk:
+	rxgk_put(gk);
 out:
 	key_put(key);
 	_leave(" = %d", ret);
-- 
cgit v1.2.3


From f564af387c8c28238f8ebc13314c589d7ba8475d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Apr 2026 13:12:47 +0100
Subject: rxrpc: Fix buffer overread in rxgk_do_verify_authenticator()

Fix rxgk_do_verify_authenticator() to check the buffer size before checking
the nonce.

Fixes: 9d1d2b59341f ("rxrpc: rxgk: Implement the yfs-rxgk security class (GSSAPI)")
Closes: https://sashiko.dev/#/patchset/20260401105614.1696001-10-dhowells@redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-20-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxgk.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c
index c67e3c2ca871..0d5e654da918 100644
--- a/net/rxrpc/rxgk.c
+++ b/net/rxrpc/rxgk.c
@@ -1085,6 +1085,9 @@ static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn,
 
 	_enter("");
 
+	if ((end - p) * sizeof(__be32) < 24)
+		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
+					rxgk_abort_resp_short_auth);
 	if (memcmp(p, conn->rxgk.nonce, 20) != 0)
 		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
 					rxgk_abort_resp_bad_nonce);
@@ -1098,7 +1101,7 @@ static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn,
 	p += xdr_round_up(app_len) / sizeof(__be32);
 	if (end - p < 4)
 		return rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO,
-					rxgk_abort_resp_short_applen);
+					rxgk_abort_resp_short_auth);
 
 	level	= ntohl(*p++);
 	epoch	= ntohl(*p++);
-- 
cgit v1.2.3


From c43ffdcfdbb5567b1f143556df8a04b4eeea041c Mon Sep 17 00:00:00 2001
From: Wang Jie <jiewang2024@lzu.edu.cn>
Date: Wed, 8 Apr 2026 13:12:48 +0100
Subject: rxrpc: only handle RESPONSE during service challenge

Only process RESPONSE packets while the service connection is still in
RXRPC_CONN_SERVICE_CHALLENGING. Check that state under state_lock before
running response verification and security initialization, then use a local
secured flag to decide whether to queue the secured-connection work after
the state transition. This keeps duplicate or late RESPONSE packets from
re-running the setup path and removes the unlocked post-transition state
test.

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Signed-off-by: Jie Wang <jiewang2024@lzu.edu.cn>
Signed-off-by: Yang Yang <n05ec@lzu.edu.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeffrey Altman <jaltman@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-21-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/conn_event.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index c50cbfc5a313..9a41ec708aeb 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -247,6 +247,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 			       struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	bool secured = false;
 	int ret;
 
 	if (conn->state == RXRPC_CONN_ABORTED)
@@ -262,6 +263,13 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		return ret;
 
 	case RXRPC_PACKET_TYPE_RESPONSE:
+		spin_lock_irq(&conn->state_lock);
+		if (conn->state != RXRPC_CONN_SERVICE_CHALLENGING) {
+			spin_unlock_irq(&conn->state_lock);
+			return 0;
+		}
+		spin_unlock_irq(&conn->state_lock);
+
 		ret = conn->security->verify_response(conn, skb);
 		if (ret < 0)
 			return ret;
@@ -272,11 +280,13 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 			return ret;
 
 		spin_lock_irq(&conn->state_lock);
-		if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING)
+		if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
 			conn->state = RXRPC_CONN_SERVICE;
+			secured = true;
+		}
 		spin_unlock_irq(&conn->state_lock);
 
-		if (conn->state == RXRPC_CONN_SERVICE) {
+		if (secured) {
 			/* Offload call state flipping to the I/O thread.  As
 			 * we've already received the packet, put it on the
 			 * front of the queue.
-- 
cgit v1.2.3


From a44ce6aa2efb61fe44f2cfab72bb01544bbca272 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Wed, 8 Apr 2026 13:12:49 +0100
Subject: rxrpc: proc: size address buffers for %pISpc output

The AF_RXRPC procfs helpers format local and remote socket addresses into
fixed 50-byte stack buffers with "%pISpc".

That is too small for the longest current-tree IPv6-with-port form the
formatter can produce. In lib/vsprintf.c, the compressed IPv6 path uses a
dotted-quad tail not only for v4mapped addresses, but also for ISATAP
addresses via ipv6_addr_is_isatap().

As a result, a case such as

  [ffff:ffff:ffff:ffff:0:5efe:255.255.255.255]:65535

is possible with the current formatter. That is 50 visible characters, so
51 bytes including the trailing NUL, which does not fit in the existing
char[50] buffers used by net/rxrpc/proc.c.

Size the buffers from the formatter's maximum textual form and switch the
call sites to scnprintf().

Changes since v1:
- correct the changelog to cite the actual maximum current-tree case
  explicitly
- frame the proof around the ISATAP formatting path instead of the earlier
  mapped-v4 example

Fixes: 75b54cb57ca3 ("rxrpc: Add IPv6 support")
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Anderson Nascimento <anderson@allelesecurity.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
cc: stable@kernel.org
Link: https://patch.msgid.link/20260408121252.2249051-22-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/proc.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 7755fca5beb8..e9a27fa7b25d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -10,6 +10,10 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
+#define RXRPC_PROC_ADDRBUF_SIZE \
+	(sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + \
+	 sizeof(":12345"))
+
 static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
 	[RXRPC_CONN_UNUSED]			= "Unused  ",
 	[RXRPC_CONN_CLIENT_UNSECURED]		= "ClUnsec ",
@@ -53,7 +57,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 	enum rxrpc_call_state state;
 	rxrpc_seq_t tx_bottom;
-	char lbuff[50], rbuff[50];
+	char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE];
 	long timeout = 0;
 
 	if (v == &rxnet->calls) {
@@ -69,11 +73,11 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 
 	local = call->local;
 	if (local)
-		sprintf(lbuff, "%pISpc", &local->srx.transport);
+		scnprintf(lbuff, sizeof(lbuff), "%pISpc", &local->srx.transport);
 	else
 		strcpy(lbuff, "no_local");
 
-	sprintf(rbuff, "%pISpc", &call->dest_srx.transport);
+	scnprintf(rbuff, sizeof(rbuff), "%pISpc", &call->dest_srx.transport);
 
 	state = rxrpc_call_state(call);
 	if (state != RXRPC_CALL_SERVER_PREALLOC)
@@ -142,7 +146,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 	struct rxrpc_connection *conn;
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
 	const char *state;
-	char lbuff[50], rbuff[50];
+	char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE];
 
 	if (v == &rxnet->conn_proc_list) {
 		seq_puts(seq,
@@ -161,8 +165,8 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 		goto print;
 	}
 
-	sprintf(lbuff, "%pISpc", &conn->local->srx.transport);
-	sprintf(rbuff, "%pISpc", &conn->peer->srx.transport);
+	scnprintf(lbuff, sizeof(lbuff), "%pISpc", &conn->local->srx.transport);
+	scnprintf(rbuff, sizeof(rbuff), "%pISpc", &conn->peer->srx.transport);
 print:
 	state = rxrpc_is_conn_aborted(conn) ?
 		rxrpc_call_completions[conn->completion] :
@@ -228,7 +232,7 @@ static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v)
 {
 	struct rxrpc_bundle *bundle;
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
-	char lbuff[50], rbuff[50];
+	char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE];
 
 	if (v == &rxnet->bundle_proc_list) {
 		seq_puts(seq,
@@ -242,8 +246,8 @@ static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v)
 
 	bundle = list_entry(v, struct rxrpc_bundle, proc_link);
 
-	sprintf(lbuff, "%pISpc", &bundle->local->srx.transport);
-	sprintf(rbuff, "%pISpc", &bundle->peer->srx.transport);
+	scnprintf(lbuff, sizeof(lbuff), "%pISpc", &bundle->local->srx.transport);
+	scnprintf(rbuff, sizeof(rbuff), "%pISpc", &bundle->peer->srx.transport);
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %4x %3u %3d"
 		   " %c%c%c %08x | %08x %08x %08x %08x %08x\n",
@@ -279,7 +283,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 {
 	struct rxrpc_peer *peer;
 	time64_t now;
-	char lbuff[50], rbuff[50];
+	char lbuff[RXRPC_PROC_ADDRBUF_SIZE], rbuff[RXRPC_PROC_ADDRBUF_SIZE];
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -290,9 +294,9 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v)
 
 	peer = list_entry(v, struct rxrpc_peer, hash_link);
 
-	sprintf(lbuff, "%pISpc", &peer->local->srx.transport);
+	scnprintf(lbuff, sizeof(lbuff), "%pISpc", &peer->local->srx.transport);
 
-	sprintf(rbuff, "%pISpc", &peer->srx.transport);
+	scnprintf(rbuff, sizeof(rbuff), "%pISpc", &peer->srx.transport);
 
 	now = ktime_get_seconds();
 	seq_printf(seq,
@@ -401,7 +405,7 @@ const struct seq_operations rxrpc_peer_seq_ops = {
 static int rxrpc_local_seq_show(struct seq_file *seq, void *v)
 {
 	struct rxrpc_local *local;
-	char lbuff[50];
+	char lbuff[RXRPC_PROC_ADDRBUF_SIZE];
 
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -412,7 +416,7 @@ static int rxrpc_local_seq_show(struct seq_file *seq, void *v)
 
 	local = hlist_entry(v, struct rxrpc_local, link);
 
-	sprintf(lbuff, "%pISpc", &local->srx.transport);
+	scnprintf(lbuff, sizeof(lbuff), "%pISpc", &local->srx.transport);
 
 	seq_printf(seq,
 		   "UDP   %-47.47s %3u %3u %3u\n",
-- 
cgit v1.2.3


From b30b1675aa2bcf0491fd3830b051df4e08a7c8ca Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@gmail.com>
Date: Sat, 4 Apr 2026 15:41:37 +0200
Subject: net: ioam6: fix OOB and missing lock

When trace->type.bit6 is set:

    if (trace->type.bit6) {
        ...
        queue = skb_get_tx_queue(dev, skb);
        qdisc = rcu_dereference(queue->qdisc);

This code can lead to an out-of-bounds access of the dev->_tx[] array
when is_input is true. In such a case, the packet is on the RX path and
skb->queue_mapping contains the RX queue index of the ingress device. If
the ingress device has more RX queues than the egress device (dev) has
TX queues, skb_get_queue_mapping(skb) will exceed dev->num_tx_queues.
Add a check to avoid this situation since skb_get_tx_queue() does not
clamp the index. This issue has also revealed that per queue visibility
cannot be accurate and will be replaced later as a new feature.

While at it, add missing lock around qdisc_qstats_qlen_backlog(). The
function __ioam6_fill_trace_data() is called from both softirq and
process contexts, hence the use of spin_lock_bh() here.

Fixes: b63c5478e9cb ("ipv6: ioam: Support for Queue depth data field")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20260403214418.2233266-2-kuba@kernel.org/
Signed-off-by: Justin Iurman <justin.iurman@gmail.com>
Link: https://patch.msgid.link/20260404134137.24553-1-justin.iurman@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ioam6.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c
index 05a0b7d7e2aa..e963a71858a7 100644
--- a/net/ipv6/ioam6.c
+++ b/net/ipv6/ioam6.c
@@ -803,12 +803,16 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb,
 		struct Qdisc *qdisc;
 		__u32 qlen, backlog;
 
-		if (dev->flags & IFF_LOOPBACK) {
+		if (dev->flags & IFF_LOOPBACK ||
+		    skb_get_queue_mapping(skb) >= dev->num_tx_queues) {
 			*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
 		} else {
 			queue = skb_get_tx_queue(dev, skb);
 			qdisc = rcu_dereference(queue->qdisc);
+
+			spin_lock_bh(qdisc_lock(qdisc));
 			qdisc_qstats_qlen_backlog(qdisc, &qlen, &backlog);
+			spin_unlock_bh(qdisc_lock(qdisc));
 
 			*(__be32 *)data = cpu_to_be32(backlog);
 		}
-- 
cgit v1.2.3


From 5a37d228799b0ec2c277459c83c814a59d310bc3 Mon Sep 17 00:00:00 2001
From: Fabio Baltieri <fabio.baltieri@gmail.com>
Date: Sun, 5 Apr 2026 23:20:13 +0100
Subject: net: txgbe: leave space for null terminators on property_entry

Lists of struct property_entry are supposed to be terminated with an
empty property, this driver currently seems to be allocating exactly the
amount of entry used.

Change the struct definition to leave an extra element for all
property_entry.

Fixes: c3e382ad6d15 ("net: txgbe: Add software nodes to support phylink")
Signed-off-by: Fabio Baltieri <fabio.baltieri@gmail.com>
Tested-by: Jiawen Wu <jiawenwu@trustnetic.com>
Link: https://patch.msgid.link/20260405222013.5347-1-fabio.baltieri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_type.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 82433e9cb0e3..6b05f32b4a01 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -424,10 +424,10 @@ struct txgbe_nodes {
 	char i2c_name[32];
 	char sfp_name[32];
 	char phylink_name[32];
-	struct property_entry gpio_props[1];
-	struct property_entry i2c_props[3];
-	struct property_entry sfp_props[8];
-	struct property_entry phylink_props[2];
+	struct property_entry gpio_props[2];
+	struct property_entry i2c_props[4];
+	struct property_entry sfp_props[9];
+	struct property_entry phylink_props[3];
 	struct software_node_ref_args i2c_ref[1];
 	struct software_node_ref_args gpio0_ref[1];
 	struct software_node_ref_args gpio1_ref[1];
-- 
cgit v1.2.3


From 9b55b253907e7431210483519c5ad711a37dafa1 Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@linux.dev>
Date: Mon, 6 Apr 2026 11:15:10 +0800
Subject: mptcp: fix slab-use-after-free in __inet_lookup_established

The ehash table lookups are lockless and rely on
SLAB_TYPESAFE_BY_RCU to guarantee socket memory stability
during RCU read-side critical sections. Both tcp_prot and
tcpv6_prot have their slab caches created with this flag
via proto_register().

However, MPTCP's mptcp_subflow_init() copies tcpv6_prot into
tcpv6_prot_override during inet_init() (fs_initcall, level 5),
before inet6_init() (module_init/device_initcall, level 6) has
called proto_register(&tcpv6_prot). At that point,
tcpv6_prot.slab is still NULL, so tcpv6_prot_override.slab
remains NULL permanently.

This causes MPTCP v6 subflow child sockets to be allocated via
kmalloc (falling into kmalloc-4k) instead of the TCPv6 slab
cache. The kmalloc-4k cache lacks SLAB_TYPESAFE_BY_RCU, so
when these sockets are freed without SOCK_RCU_FREE (which is
cleared for child sockets by design), the memory can be
immediately reused. Concurrent ehash lookups under
rcu_read_lock can then access freed memory, triggering a
slab-use-after-free in __inet_lookup_established.

Fix this by splitting the IPv6-specific initialization out of
mptcp_subflow_init() into a new mptcp_subflow_v6_init(), called
from mptcp_proto_v6_init() before protocol registration. This
ensures tcpv6_prot_override.slab correctly inherits the
SLAB_TYPESAFE_BY_RCU slab cache.

Fixes: b19bc2945b40 ("mptcp: implement delegated actions")
Cc: stable@vger.kernel.org
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260406031512.189159-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c |  2 ++
 net/mptcp/protocol.h |  1 +
 net/mptcp/subflow.c  | 15 +++++++++------
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 65c3bb8016f4..614c3f583ca0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -4660,6 +4660,8 @@ int __init mptcp_proto_v6_init(void)
 {
 	int err;
 
+	mptcp_subflow_v6_init();
+
 	mptcp_v6_prot = mptcp_prot;
 	strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name));
 	mptcp_v6_prot.slab = NULL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0bd1ee860316..ec15e503da8b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -875,6 +875,7 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
 void __init mptcp_proto_init(void);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 int __init mptcp_proto_v6_init(void);
+void __init mptcp_subflow_v6_init(void);
 #endif
 
 struct sock *mptcp_sk_clone_init(const struct sock *sk,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6716970693e9..4ff5863aa9fd 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -2165,7 +2165,15 @@ void __init mptcp_subflow_init(void)
 	tcp_prot_override.psock_update_sk_prot = NULL;
 #endif
 
+	mptcp_diag_subflow_init(&subflow_ulp_ops);
+
+	if (tcp_register_ulp(&subflow_ulp_ops) != 0)
+		panic("MPTCP: failed to register subflows to ULP\n");
+}
+
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
+void __init mptcp_subflow_v6_init(void)
+{
 	/* In struct mptcp_subflow_request_sock, we assume the TCP request sock
 	 * structures for v4 and v6 have the same size. It should not changed in
 	 * the future but better to make sure to be warned if it is no longer
@@ -2204,10 +2212,5 @@ void __init mptcp_subflow_init(void)
 	/* Disable sockmap processing for subflows */
 	tcpv6_prot_override.psock_update_sk_prot = NULL;
 #endif
-#endif
-
-	mptcp_diag_subflow_init(&subflow_ulp_ops);
-
-	if (tcp_register_ulp(&subflow_ulp_ops) != 0)
-		panic("MPTCP: failed to register subflows to ULP\n");
 }
+#endif
-- 
cgit v1.2.3


From 8e2760eaab778494fc1fa257031e0e1799647f46 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Tue, 7 Apr 2026 10:41:41 +0200
Subject: Revert "mptcp: add needs_id for netlink appending addr"

This commit was originally adding the ability to add MPTCP endpoints
with ID 0 by accident. The in-kernel PM, handling MPTCP endpoints at the
net namespace level, is not supposed to handle endpoints with such ID,
because this ID 0 is reserved to the initial subflow, as mentioned in
the MPTCPv1 protocol [1], a per-connection setting.

Note that 'ip mptcp endpoint add id 0' stops early with an error, but
other tools might still request the in-kernel PM to create MPTCP
endpoints with this restricted ID 0.

In other words, it was wrong to call the mptcp_pm_has_addr_attr_id
helper to check whether the address ID attribute is set: if it was set
to 0, a new MPTCP endpoint would be created with ID 0, which is not
expected, and might cause various issues later.

Fixes: 584f38942626 ("mptcp: add needs_id for netlink appending addr")
Cc: stable@vger.kernel.org
Link: https://datatracker.ietf.org/doc/html/rfc8684#section-3.2-9 [1]
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20260407-net-mptcp-revert-pm-needs-id-v2-1-7a25cbc324f8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_kernel.c | 24 +++++-------------------
 1 file changed, 5 insertions(+), 19 deletions(-)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 82e59f9c6dd9..0ebf43be9939 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -720,7 +720,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 					     struct mptcp_pm_addr_entry *entry,
-					     bool needs_id, bool replace)
+					     bool replace)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	int ret = -EINVAL;
@@ -779,7 +779,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 		}
 	}
 
-	if (!entry->addr.id && needs_id) {
+	if (!entry->addr.id) {
 find_next:
 		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
 						    MPTCP_PM_MAX_ADDR_ID + 1,
@@ -790,7 +790,7 @@ find_next:
 		}
 	}
 
-	if (!entry->addr.id && needs_id)
+	if (!entry->addr.id)
 		goto out;
 
 	__set_bit(entry->addr.id, pernet->id_bitmap);
@@ -923,7 +923,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 		return -ENOMEM;
 
 	entry->addr.port = 0;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, false);
 	if (ret < 0)
 		kfree(entry);
 
@@ -977,18 +977,6 @@ next:
 	return 0;
 }
 
-static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
-				      struct genl_info *info)
-{
-	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
-
-	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
-					 mptcp_pm_address_nl_policy, info->extack) &&
-	    tb[MPTCP_PM_ADDR_ATTR_ID])
-		return true;
-	return false;
-}
-
 /* Add an MPTCP endpoint */
 int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
@@ -1037,9 +1025,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 			goto out_free;
 		}
 	}
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
-						!mptcp_pm_has_addr_attr_id(attr, info),
-						true);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;
-- 
cgit v1.2.3


From 39897df386376912d561d4946499379effa1e7ef Mon Sep 17 00:00:00 2001
From: Jiexun Wang <wangjiexun2025@gmail.com>
Date: Tue, 7 Apr 2026 16:00:14 +0800
Subject: af_unix: read UNIX_DIAG_VFS data under unix_state_lock

Exact UNIX diag lookups hold a reference to the socket, but not to
u->path. Meanwhile, unix_release_sock() clears u->path under
unix_state_lock() and drops the path reference after unlocking.

Read the inode and device numbers for UNIX_DIAG_VFS while holding
unix_state_lock(), then emit the netlink attribute after dropping the
lock.

This keeps the VFS data stable while the reply is being built.

Fixes: 5f7b0569460b ("unix_diag: Unix inode info NLA")
Reported-by: Yifan Wu <yifanwucs@gmail.com>
Reported-by: Juefei Pu <tomapufckgml@gmail.com>
Co-developed-by: Yuan Tan <yuantan098@gmail.com>
Signed-off-by: Yuan Tan <yuantan098@gmail.com>
Suggested-by: Xin Liu <bird@lzu.edu.cn>
Tested-by: Ren Wei <enjou1224z@gmail.com>
Signed-off-by: Jiexun Wang <wangjiexun2025@gmail.com>
Signed-off-by: Ren Wei <n05ec@lzu.edu.cn>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260407080015.1744197-1-n05ec@lzu.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/diag.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/unix/diag.c b/net/unix/diag.c
index ca3473026151..c9c1e51c4419 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -28,18 +28,23 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 
 static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
 {
-	struct dentry *dentry = unix_sk(sk)->path.dentry;
+	struct unix_diag_vfs uv;
+	struct dentry *dentry;
+	bool have_vfs = false;
 
+	unix_state_lock(sk);
+	dentry = unix_sk(sk)->path.dentry;
 	if (dentry) {
-		struct unix_diag_vfs uv = {
-			.udiag_vfs_ino = d_backing_inode(dentry)->i_ino,
-			.udiag_vfs_dev = dentry->d_sb->s_dev,
-		};
-
-		return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
+		uv.udiag_vfs_ino = d_backing_inode(dentry)->i_ino;
+		uv.udiag_vfs_dev = dentry->d_sb->s_dev;
+		have_vfs = true;
 	}
+	unix_state_unlock(sk);
 
-	return 0;
+	if (!have_vfs)
+		return 0;
+
+	return nla_put(nlskb, UNIX_DIAG_VFS, sizeof(uv), &uv);
 }
 
 static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
-- 
cgit v1.2.3


From 0006c6f1091bbeea88b8a88a6548b9fb2f803c74 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Mon, 6 Apr 2026 22:27:30 -0400
Subject: devlink: Fix incorrect skb socket family dumping

The devlink_fmsg_dump_skb function was incorrectly using the socket
type (sk->sk_type) instead of the socket family (sk->sk_family)
when filling the "family" field in the fast message dump.

This patch fixes this to properly display the socket family.

Fixes: 3dbfde7f6bc7b8 ("devlink: add devlink_fmsg_dump_skb() function")
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://patch.msgid.link/20260407022730.2393-1-lirongqing@baidu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/devlink/health.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/devlink/health.c b/net/devlink/health.c
index 449c7611c640..ea7a334e939b 100644
--- a/net/devlink/health.c
+++ b/net/devlink/health.c
@@ -1327,7 +1327,7 @@ void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb)
 	if (sk) {
 		devlink_fmsg_pair_nest_start(fmsg, "sk");
 		devlink_fmsg_obj_nest_start(fmsg);
-		devlink_fmsg_put(fmsg, "family", sk->sk_type);
+		devlink_fmsg_put(fmsg, "family", sk->sk_family);
 		devlink_fmsg_put(fmsg, "type", sk->sk_type);
 		devlink_fmsg_put(fmsg, "proto", sk->sk_protocol);
 		devlink_fmsg_obj_nest_end(fmsg);
-- 
cgit v1.2.3


From 30f3b767aed45fdaf8f887e66e1f19bd0cbd4483 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Mon, 6 Apr 2026 13:08:16 +0530
Subject: MAINTAINERS: Add Prashanth as additional maintainer for amd-xgbe
 driver

Add Prashanth as an additional maintainer for the amd-xgbe Ethernet
driver to help with ongoing development and maintenance.

Cc: Prashanth Kumar K R <PrashanthKumar.K.R@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20260406073816.3218387-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4601903a8f9b..dc935838e516 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1291,6 +1291,7 @@ F:	include/uapi/drm/amdxdna_accel.h
 
 AMD XGBE DRIVER
 M:	Raju Rangoju <Raju.Rangoju@amd.com>
+M:	Prashanth Kumar K R <PrashanthKumar.K.R@amd.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi
-- 
cgit v1.2.3


From 9709b56d908acc120fe8b4ae250b3c9d749ea832 Mon Sep 17 00:00:00 2001
From: Alexander Koskovich <akoskovich@pm.me>
Date: Fri, 3 Apr 2026 18:43:47 +0200
Subject: net: ipa: fix GENERIC_CMD register field masks for IPA v5.0+

Fix the field masks to match the hardware layout documented in
downstream GSI (GSI_V3_0_EE_n_GSI_EE_GENERIC_CMD_*).

Notably this fixes a WARN I was seeing when I tried to send "stop"
to the MPSS remoteproc while IPA was up.

Fixes: faf0678ec8a0 ("net: ipa: add IPA v5.0 GSI register definitions")
Signed-off-by: Alexander Koskovich <akoskovich@pm.me>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260403-milos-ipa-v1-1-01e9e4e03d3e@fairphone.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ipa/reg/gsi_reg-v5.0.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c
index 36d1e65df71b..3334d8e20ad2 100644
--- a/drivers/net/ipa/reg/gsi_reg-v5.0.c
+++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c
@@ -156,9 +156,10 @@ REG_FIELDS(EV_CH_CMD, ev_ch_cmd, 0x00025010 + 0x12000 * GSI_EE_AP);
 
 static const u32 reg_generic_cmd_fmask[] = {
 	[GENERIC_OPCODE]				= GENMASK(4, 0),
-	[GENERIC_CHID]					= GENMASK(9, 5),
-	[GENERIC_EE]					= GENMASK(13, 10),
-						/* Bits 14-31 reserved */
+	[GENERIC_CHID]					= GENMASK(12, 5),
+	[GENERIC_EE]					= GENMASK(16, 13),
+						/* Bits 17-23 reserved */
+	[GENERIC_PARAMS]				= GENMASK(31, 24),
 };
 
 REG_FIELDS(GENERIC_CMD, generic_cmd, 0x00025018 + 0x12000 * GSI_EE_AP);
-- 
cgit v1.2.3


From 56007972c0b1e783ca714d6f1f4d6e66e531d21f Mon Sep 17 00:00:00 2001
From: Alexander Koskovich <akoskovich@pm.me>
Date: Fri, 3 Apr 2026 18:43:48 +0200
Subject: net: ipa: fix event ring index not programmed for IPA v5.0+

For IPA v5.0+, the event ring index field moved from CH_C_CNTXT_0 to
CH_C_CNTXT_1. The v5.0 register definition intended to define this
field in the CH_C_CNTXT_1 fmask array but used the old identifier of
ERINDEX instead of CH_ERINDEX.

Without a valid event ring, GSI channels could never signal transfer
completions. This caused gsi_channel_trans_quiesce() to block
forever in wait_for_completion().

At least for IPA v5.2 this resolves an issue seen where runtime
suspend, system suspend, and remoteproc stop all hanged forever. It
also meant the IPA data path was completely non functional.

Fixes: faf0678ec8a0 ("net: ipa: add IPA v5.0 GSI register definitions")
Signed-off-by: Alexander Koskovich <akoskovich@pm.me>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20260403-milos-ipa-v1-2-01e9e4e03d3e@fairphone.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ipa/reg/gsi_reg-v5.0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c
index 3334d8e20ad2..6c4a7fbe4de9 100644
--- a/drivers/net/ipa/reg/gsi_reg-v5.0.c
+++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c
@@ -30,7 +30,7 @@ REG_STRIDE_FIELDS(CH_C_CNTXT_0, ch_c_cntxt_0,
 
 static const u32 reg_ch_c_cntxt_1_fmask[] = {
 	[CH_R_LENGTH]					= GENMASK(23, 0),
-	[ERINDEX]					= GENMASK(31, 24),
+	[CH_ERINDEX]					= GENMASK(31, 24),
 };
 
 REG_STRIDE_FIELDS(CH_C_CNTXT_1, ch_c_cntxt_1,
-- 
cgit v1.2.3


From ebe560ea5f54134279356703e73b7f867c89db13 Mon Sep 17 00:00:00 2001
From: Alice Mikityanska <alice@isovalent.com>
Date: Fri, 3 Apr 2026 20:49:49 +0300
Subject: l2tp: Drop large packets with UDP encap

syzbot reported a WARN on my patch series [1]. The actual issue is an
overflow of 16-bit UDP length field, and it exists in the upstream code.
My series added a debug WARN with an overflow check that exposed the
issue, that's why syzbot tripped on my patches, rather than on upstream
code.

syzbot's repro:

r0 = socket$pppl2tp(0x18, 0x1, 0x1)
r1 = socket$inet6_udp(0xa, 0x2, 0x0)
connect$inet6(r1, &(0x7f00000000c0)={0xa, 0x0, 0x0, @loopback, 0xfffffffc}, 0x1c)
connect$pppl2tp(r0, &(0x7f0000000240)=@pppol2tpin6={0x18, 0x1, {0x0, r1, 0x4, 0x0, 0x0, 0x0, {0xa, 0x4e22, 0xffff, @ipv4={'\x00', '\xff\xff', @empty}}}}, 0x32)
writev(r0, &(0x7f0000000080)=[{&(0x7f0000000000)="ee", 0x34000}], 0x1)

It basically sends an oversized (0x34000 bytes) PPPoL2TP packet with UDP
encapsulation, and l2tp_xmit_core doesn't check for overflows when it
assigns the UDP length field. The value gets trimmed to 16 bites.

Add an overflow check that drops oversized packets and avoids sending
packets with trimmed UDP length to the wire.

syzbot's stack trace (with my patch applied):

len >= 65536u
WARNING: ./include/linux/udp.h:38 at udp_set_len_short include/linux/udp.h:38 [inline], CPU#1: syz.0.17/5957
WARNING: ./include/linux/udp.h:38 at l2tp_xmit_core net/l2tp/l2tp_core.c:1293 [inline], CPU#1: syz.0.17/5957
WARNING: ./include/linux/udp.h:38 at l2tp_xmit_skb+0x1204/0x18d0 net/l2tp/l2tp_core.c:1327, CPU#1: syz.0.17/5957
Modules linked in:
CPU: 1 UID: 0 PID: 5957 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
RIP: 0010:udp_set_len_short include/linux/udp.h:38 [inline]
RIP: 0010:l2tp_xmit_core net/l2tp/l2tp_core.c:1293 [inline]
RIP: 0010:l2tp_xmit_skb+0x1204/0x18d0 net/l2tp/l2tp_core.c:1327
Code: 0f 0b 90 e9 21 f9 ff ff e8 e9 05 ec f6 90 0f 0b 90 e9 8d f9 ff ff e8 db 05 ec f6 90 0f 0b 90 e9 cc f9 ff ff e8 cd 05 ec f6 90 <0f> 0b 90 e9 de fa ff ff 44 89 f1 80 e1 07 80 c1 03 38 c1 0f 8c 4f
RSP: 0018:ffffc90003d67878 EFLAGS: 00010293
RAX: ffffffff8ad985e3 RBX: ffff8881a6400090 RCX: ffff8881697f0000
RDX: 0000000000000000 RSI: 0000000000034010 RDI: 000000000000ffff
RBP: dffffc0000000000 R08: 0000000000000003 R09: 0000000000000004
R10: dffffc0000000000 R11: fffff520007acf00 R12: ffff8881baf20900
R13: 0000000000034010 R14: ffff8881a640008e R15: ffff8881760f7000
FS:  000055557e81f500(0000) GS:ffff8882a9467000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000200000033000 CR3: 00000001612f4000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 pppol2tp_sendmsg+0x40a/0x5f0 net/l2tp/l2tp_ppp.c:302
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg net/socket.c:742 [inline]
 sock_write_iter+0x503/0x550 net/socket.c:1195
 do_iter_readv_writev+0x619/0x8c0 fs/read_write.c:-1
 vfs_writev+0x33c/0x990 fs/read_write.c:1059
 do_writev+0x154/0x2e0 fs/read_write.c:1105
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f636479c629
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffffd4241c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00007f6364a15fa0 RCX: 00007f636479c629
RDX: 0000000000000001 RSI: 0000200000000080 RDI: 0000000000000003
RBP: 00007f6364832b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f6364a15fac R14: 00007f6364a15fa0 R15: 00007f6364a15fa0
 </TASK>

[1]: https://lore.kernel.org/all/20260226201600.222044-1-alice.kernel@fastmail.im/

Fixes: 3557baabf280 ("[L2TP]: PPP over L2TP driver core")
Reported-by: syzbot+ci3edea60a44225dec@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69a1dfba.050a0220.3a55be.0026.GAE@google.com/
Signed-off-by: Alice Mikityanska <alice@isovalent.com>
Link: https://patch.msgid.link/20260403174949.843941-1-alice.kernel@fastmail.im
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/l2tp/l2tp_core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c89ae52764b8..157fc23ce4e1 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1290,6 +1290,11 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
 		uh->source = inet->inet_sport;
 		uh->dest = inet->inet_dport;
 		udp_len = uhlen + session->hdr_len + data_len;
+		if (udp_len > U16_MAX) {
+			kfree_skb(skb);
+			ret = NET_XMIT_DROP;
+			goto out_unlock;
+		}
 		uh->len = htons(udp_len);
 
 		/* Calculate UDP checksum if configured to do so */
-- 
cgit v1.2.3


From 1561d96f5f55c1bca9ff047ace5813f4f244eea6 Mon Sep 17 00:00:00 2001
From: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Date: Tue, 7 Apr 2026 14:02:47 -0700
Subject: gpio: tegra: fix irq_release_resources calling enable instead of
 disable

tegra_gpio_irq_release_resources() erroneously calls tegra_gpio_enable()
instead of tegra_gpio_disable(). When IRQ resources are released, the
GPIO configuration bit (CNF) should be cleared to deconfigure the pin as
a GPIO. Leaving it enabled wastes power and can cause unexpected behavior
if the pin is later reused for an alternate function via pinctrl.

Fixes: 66fecef5bde0 ("gpio: tegra: Convert to gpio_irq_chip")
Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Link: https://patch.msgid.link/20260407210247.1737938-1-samasth.norway.ananda@oracle.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpio-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 15a5762a82c2..b14052fe64ac 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -595,7 +595,7 @@ static void tegra_gpio_irq_release_resources(struct irq_data *d)
 	struct tegra_gpio_info *tgi = gpiochip_get_data(chip);
 
 	gpiochip_relres_irq(chip, d->hwirq);
-	tegra_gpio_enable(tgi, d->hwirq);
+	tegra_gpio_disable(tgi, d->hwirq);
 }
 
 static void tegra_gpio_irq_print_chip(struct irq_data *d, struct seq_file *s)
-- 
cgit v1.2.3


From a13edf9b92fc4700b3020d7ea547a3d64dd33b63 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Thu, 9 Apr 2026 08:31:11 +0300
Subject: drm/i915/gem: Drop check for changed VM in EXECBUF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the introduction of d4433c7600f7 ("drm/i915/gem: Use the proto-context
to handle create parameters (v5)") it has not been possible for VM to change
after context creation so the check will never fail.

Sima's analysis:

  This check was added in f7ce8639f6ff ("drm/i915/gem: Split the context's
  obj:vma lut into its own mutex") but without any hint in the commit
  message as to why. In another hunk of that commit there's a hint though in
  __eb_add_lut:

          /* user racing with ctx set-vm */

  This would mean that this bug was introduced in e0695db7298e ("drm/i915:
  Create/destroy VM (ppGTT) for use with contexts"), which allowed to change
  the gem_ctx->vm at runtime, opening up the race that was partially fixed
  in the earlier referenced commit about a year later.

  But it cannot be exploited anymore in anything remotely recent because
  with the introduction of proto-contexts we've made gem_ctx->vm invariant
  again, exactly to preemptively close all these potential issues.
  Specifically d4433c7600f7 ("drm/i915/gem: Use the proto-context to handle
  create parameters (v5)") is the vm specific part of the proto-context
  work.

v3:
- Include Sima's analysis and WARN_ON_ONCE

v4:
- Focus only on latest mainline codebase

References: https://lore.kernel.org/all/20260324151741.29338-1-sosohero200@gmail.com/
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Simona Vetter <simona.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tursulin@ursulin.net>
Cc: Andi Shyti <andi.shyti@kernel.org>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://patch.msgid.link/20260409053111.8914-1-joonas.lahtinen@linux.intel.com
(cherry picked from commit f6d4afc9ec6a0bc326151b35a7a3369369180079)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 942f4eed817f..65ce54b20ec2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -896,7 +896,7 @@ static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
 
 		rcu_read_lock();
 		vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle);
-		if (likely(vma && vma->vm == vm))
+		if (likely(vma))
 			vma = i915_vma_tryget(vma);
 		else
 			vma = NULL;
-- 
cgit v1.2.3


From c71ba669b570c7b3f86ec875be222ea11dacb352 Mon Sep 17 00:00:00 2001
From: Pengpeng Hou <pengpeng@iscas.ac.cn>
Date: Sun, 5 Apr 2026 08:40:00 +0800
Subject: nfc: pn533: allocate rx skb before consuming bytes

pn532_receive_buf() reports the number of accepted bytes to the serdev
core. The current code consumes bytes into recv_skb and may already hand
a complete frame to pn533_recv_frame() before allocating a fresh receive
buffer.

If that alloc_skb() fails, the callback returns 0 even though it has
already consumed bytes, and it leaves recv_skb as NULL for the next
receive callback. That breaks the receive_buf() accounting contract and
can also lead to a NULL dereference on the next skb_put_u8().

Allocate the receive skb lazily before consuming the next byte instead.
If allocation fails, return the number of bytes already accepted.

Fixes: c656aa4c27b1 ("nfc: pn533: add UART phy driver")
Cc: stable@vger.kernel.org
Signed-off-by: Pengpeng Hou <pengpeng@iscas.ac.cn>
Link: https://patch.msgid.link/20260405094003.3-pn533-v2-pengpeng@iscas.ac.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/nfc/pn533/uart.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index 1b82b7b2a5fa..e0d67cd2ac9b 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -211,6 +211,13 @@ static size_t pn532_receive_buf(struct serdev_device *serdev,
 
 	timer_delete(&dev->cmd_timeout);
 	for (i = 0; i < count; i++) {
+		if (!dev->recv_skb) {
+			dev->recv_skb = alloc_skb(PN532_UART_SKB_BUFF_LEN,
+						  GFP_KERNEL);
+			if (!dev->recv_skb)
+				return i;
+		}
+
 		if (unlikely(!skb_tailroom(dev->recv_skb)))
 			skb_trim(dev->recv_skb, 0);
 
@@ -219,9 +226,7 @@ static size_t pn532_receive_buf(struct serdev_device *serdev,
 			continue;
 
 		pn533_recv_frame(dev->priv, dev->recv_skb, 0);
-		dev->recv_skb = alloc_skb(PN532_UART_SKB_BUFF_LEN, GFP_KERNEL);
-		if (!dev->recv_skb)
-			return 0;
+		dev->recv_skb = NULL;
 	}
 
 	return i;
-- 
cgit v1.2.3


From 7e0548525abd2bff9694e016b6a469ccd2d5a053 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 8 Apr 2026 15:40:57 +0100
Subject: iommu: Ensure .iotlb_sync is called correctly

Many drivers have no reason to use the iotlb_gather mechanism, but do
still depend on .iotlb_sync being called to properly complete an unmap.
Since the core code is now relying on the gather to detect when there
is legitimately something to sync, it should also take care of encoding
a successful unmap when the driver does not touch the gather itself.

Fixes: 90c5def10bea ("iommu: Do not call drivers for empty gathers")
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Closes: https://lore.kernel.org/r/8800a38b-8515-4bbe-af15-0dae81274bf7@nvidia.com
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/iommu.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 50718ab810a4..ee83850c7060 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2717,6 +2717,12 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 
 		pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
 			 iova, unmapped_page);
+		/*
+		 * If the driver itself isn't using the gather, make sure
+		 * it looks non-empty so iotlb_sync will still be called.
+		 */
+		if (iotlb_gather->start >= iotlb_gather->end)
+			iommu_iotlb_gather_add_range(iotlb_gather, iova, size);
 
 		iova += unmapped_page;
 		unmapped += unmapped_page;
-- 
cgit v1.2.3


From e3b2cf6e5dba416a03152f299d99982dfe1e861d Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Apr 2026 12:15:58 +0200
Subject: kernfs: pass struct ns_common instead of const void * for namespace
 tags

kernfs has historically used const void * to pass around namespace tags
used for directory-level namespace filtering. The only current user of
this is sysfs network namespace tagging where struct net pointers are
cast to void *.

Replace all const void * namespace parameters with const struct
ns_common * throughout the kernfs, sysfs, and kobject namespace layers.
This includes the kobj_ns_type_operations callbacks, kobject_namespace(),
and all sysfs/kernfs APIs that accept or return namespace tags.

Passing struct ns_common is needed because various codepaths require
access to the underlying namespace. A struct ns_common can always be
converted back to the concrete namespace type (e.g., struct net) via
container_of() or to_ns_common() in the reverse direction.

This is a preparatory change for switching to ns_id-based directory
iteration to prevent a KASLR pointer leak through the current use of
raw namespace pointers as hash seeds and comparison keys.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/base/class.c                |  4 +--
 drivers/base/core.c                 |  7 +++---
 drivers/infiniband/core/device.c    |  5 ++--
 drivers/infiniband/ulp/srp/ib_srp.c |  7 +++---
 drivers/net/bonding/bond_sysfs.c    |  4 +--
 drivers/net/ipvlan/ipvtap.c         |  5 ++--
 drivers/net/macvtap.c               |  5 ++--
 fs/kernfs/dir.c                     | 30 ++++++++++++----------
 fs/kernfs/file.c                    |  2 +-
 fs/kernfs/kernfs-internal.h         |  2 +-
 fs/kernfs/mount.c                   |  2 +-
 fs/nfs/sysfs.c                      | 16 +++++++-----
 fs/sysfs/dir.c                      |  6 ++---
 fs/sysfs/file.c                     |  8 +++---
 fs/sysfs/mount.c                    | 10 +++++---
 fs/sysfs/symlink.c                  |  7 +++---
 fs/sysfs/sysfs.h                    |  4 +--
 include/linux/device/class.h        |  6 ++---
 include/linux/kernfs.h              | 40 +++++++++++++++++------------
 include/linux/kobject.h             |  4 +--
 include/linux/kobject_ns.h          | 13 +++++-----
 include/linux/netdevice.h           |  4 +--
 include/linux/sysfs.h               | 24 +++++++++---------
 include/net/net_namespace.h         |  8 +++---
 lib/kobject.c                       |  8 +++---
 lib/kobject_uevent.c                | 13 ++++++----
 net/core/net-sysfs.c                | 50 ++++++++++++++++++-------------------
 net/core/net_namespace.c            |  8 +++---
 net/sunrpc/sysfs.c                  | 17 +++++++------
 net/wireless/sysfs.c                |  4 +--
 30 files changed, 175 insertions(+), 148 deletions(-)

diff --git a/drivers/base/class.c b/drivers/base/class.c
index 827fc7adacc7..ffab0a9c8ccb 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -127,7 +127,7 @@ static const struct kobj_type class_ktype = {
 };
 
 int class_create_file_ns(const struct class *cls, const struct class_attribute *attr,
-			 const void *ns)
+			 const struct ns_common *ns)
 {
 	struct subsys_private *sp = class_to_subsys(cls);
 	int error;
@@ -143,7 +143,7 @@ int class_create_file_ns(const struct class *cls, const struct class_attribute *
 EXPORT_SYMBOL_GPL(class_create_file_ns);
 
 void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr,
-			  const void *ns)
+			  const struct ns_common *ns)
 {
 	struct subsys_private *sp = class_to_subsys(cls);
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 09b98f02f559..0613de0fbe44 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2570,15 +2570,14 @@ static void device_release(struct kobject *kobj)
 	kfree(p);
 }
 
-static const void *device_namespace(const struct kobject *kobj)
+static const struct ns_common *device_namespace(const struct kobject *kobj)
 {
 	const struct device *dev = kobj_to_dev(kobj);
-	const void *ns = NULL;
 
 	if (dev->class && dev->class->namespace)
-		ns = dev->class->namespace(dev);
+		return dev->class->namespace(dev);
 
-	return ns;
+	return NULL;
 }
 
 static void device_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 558b73940d66..7945614be36d 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -509,12 +509,13 @@ static int ib_device_uevent(const struct device *device,
 	return 0;
 }
 
-static const void *net_namespace(const struct device *d)
+static const struct ns_common *net_namespace(const struct device *d)
 {
 	const struct ib_core_device *coredev =
 			container_of(d, struct ib_core_device, dev);
+	struct net *net = read_pnet(&coredev->rdma_net);
 
-	return read_pnet(&coredev->rdma_net);
+	return net ? to_ns_common(net) : NULL;
 }
 
 static struct class ib_class = {
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 30339dcabb4d..b58868e1cf11 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -43,6 +43,7 @@
 #include <linux/jiffies.h>
 #include <linux/lockdep.h>
 #include <linux/inet.h>
+#include <net/net_namespace.h>
 #include <rdma/ib_cache.h>
 
 #include <linux/atomic.h>
@@ -1048,7 +1049,7 @@ static void srp_remove_target(struct srp_target_port *target)
 	scsi_remove_host(target->scsi_host);
 	srp_stop_rport_timers(target->rport);
 	srp_disconnect_target(target);
-	kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net);
+	kobj_ns_drop(KOBJ_NS_TYPE_NET, to_ns_common(target->net));
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
 		srp_free_ch_ib(target, ch);
@@ -3713,7 +3714,7 @@ static ssize_t add_target_store(struct device *dev,
 
 	target = host_to_target(target_host);
 
-	target->net		= kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	target->net		= to_net_ns(kobj_ns_grab_current(KOBJ_NS_TYPE_NET));
 	target->io_class	= SRP_REV16A_IB_IO_CLASS;
 	target->scsi_host	= target_host;
 	target->srp_host	= host;
@@ -3905,7 +3906,7 @@ put:
 		 * earlier in this function.
 		 */
 		if (target->state != SRP_TARGET_REMOVED)
-			kobj_ns_drop(KOBJ_NS_TYPE_NET, target->net);
+			kobj_ns_drop(KOBJ_NS_TYPE_NET, to_ns_common(target->net));
 		scsi_host_put(target->scsi_host);
 	}
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 9a75ad3181ab..eaba44c76a5e 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -808,7 +808,7 @@ int __net_init bond_create_sysfs(struct bond_net *bn)
 	sysfs_attr_init(&bn->class_attr_bonding_masters.attr);
 
 	ret = netdev_class_create_file_ns(&bn->class_attr_bonding_masters,
-					  bn->net);
+					  to_ns_common(bn->net));
 	/* Permit multiple loads of the module by ignoring failures to
 	 * create the bonding_masters sysfs file.  Bonding devices
 	 * created by second or subsequent loads of the module will
@@ -835,7 +835,7 @@ int __net_init bond_create_sysfs(struct bond_net *bn)
 /* Remove /sys/class/net/bonding_masters. */
 void __net_exit bond_destroy_sysfs(struct bond_net *bn)
 {
-	netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net);
+	netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, to_ns_common(bn->net));
 }
 
 /* Initialize sysfs for each bond.  This sets up and registers
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index edd13916831a..2d6bbddd1edd 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -30,10 +30,11 @@
 static dev_t ipvtap_major;
 static struct cdev ipvtap_cdev;
 
-static const void *ipvtap_net_namespace(const struct device *d)
+static const struct ns_common *ipvtap_net_namespace(const struct device *d)
 {
 	const struct net_device *dev = to_net_dev(d->parent);
-	return dev_net(dev);
+
+	return to_ns_common(dev_net(dev));
 }
 
 static struct class ipvtap_class = {
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index b391a0f740a3..cc975dfb7380 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -35,10 +35,11 @@ struct macvtap_dev {
  */
 static dev_t macvtap_major;
 
-static const void *macvtap_net_namespace(const struct device *d)
+static const struct ns_common *macvtap_net_namespace(const struct device *d)
 {
 	const struct net_device *dev = to_net_dev(d->parent);
-	return dev_net(dev);
+
+	return to_ns_common(dev_net(dev));
 }
 
 static struct class macvtap_class = {
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8d40c4b1db9f..be262145ae08 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -313,7 +313,8 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
  *
  *	Return: 31-bit hash of ns + name (so it fits in an off_t)
  */
-static unsigned int kernfs_name_hash(const char *name, const void *ns)
+static unsigned int kernfs_name_hash(const char *name,
+				     const struct ns_common *ns)
 {
 	unsigned long hash = init_name_hash(ns);
 	unsigned int len = strlen(name);
@@ -330,7 +331,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns)
 }
 
 static int kernfs_name_compare(unsigned int hash, const char *name,
-			       const void *ns, const struct kernfs_node *kn)
+			       const struct ns_common *ns, const struct kernfs_node *kn)
 {
 	if (hash < kn->hash)
 		return -1;
@@ -856,7 +857,7 @@ out_unlock:
  */
 static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 					  const unsigned char *name,
-					  const void *ns)
+					  const struct ns_common *ns)
 {
 	struct rb_node *node = parent->dir.children.rb_node;
 	bool has_ns = kernfs_ns_enabled(parent);
@@ -889,7 +890,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 
 static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
-					  const void *ns)
+					  const struct ns_common *ns)
 {
 	ssize_t len;
 	char *p, *name;
@@ -930,7 +931,8 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
  * Return: pointer to the found kernfs_node on success, %NULL on failure.
  */
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
-					   const char *name, const void *ns)
+					   const char *name,
+					   const struct ns_common *ns)
 {
 	struct kernfs_node *kn;
 	struct kernfs_root *root = kernfs_root(parent);
@@ -956,7 +958,8 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
  * Return: pointer to the found kernfs_node on success, %NULL on failure.
  */
 struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
-					   const char *path, const void *ns)
+					   const char *path,
+					   const struct ns_common *ns)
 {
 	struct kernfs_node *kn;
 	struct kernfs_root *root = kernfs_root(parent);
@@ -1079,7 +1082,8 @@ struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root)
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 kuid_t uid, kgid_t gid,
-					 void *priv, const void *ns)
+					 void *priv,
+					 const struct ns_common *ns)
 {
 	struct kernfs_node *kn;
 	int rc;
@@ -1221,7 +1225,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 	struct kernfs_node *kn;
 	struct kernfs_root *root;
 	struct inode *inode = NULL;
-	const void *ns = NULL;
+	const struct ns_common *ns = NULL;
 
 	root = kernfs_root(parent);
 	down_read(&root->kernfs_rwsem);
@@ -1702,7 +1706,7 @@ bool kernfs_remove_self(struct kernfs_node *kn)
  * Return: %0 on success, -ENOENT if such entry doesn't exist.
  */
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
-			     const void *ns)
+			     const struct ns_common *ns)
 {
 	struct kernfs_node *kn;
 	struct kernfs_root *root;
@@ -1741,7 +1745,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
  * Return: %0 on success, -errno on failure.
  */
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
-		     const char *new_name, const void *new_ns)
+		     const char *new_name, const struct ns_common *new_ns)
 {
 	struct kernfs_node *old_parent;
 	struct kernfs_root *root;
@@ -1832,7 +1836,7 @@ static int kernfs_dir_fop_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static struct kernfs_node *kernfs_dir_pos(const void *ns,
+static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns,
 	struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
 {
 	if (pos) {
@@ -1867,7 +1871,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
 	return pos;
 }
 
-static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
+static struct kernfs_node *kernfs_dir_next_pos(const struct ns_common *ns,
 	struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
 {
 	pos = kernfs_dir_pos(ns, parent, ino, pos);
@@ -1889,7 +1893,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 	struct kernfs_node *parent = kernfs_dentry_node(dentry);
 	struct kernfs_node *pos = file->private_data;
 	struct kernfs_root *root;
-	const void *ns = NULL;
+	const struct ns_common *ns = NULL;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e32406d62c0d..1163aa769738 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -1045,7 +1045,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 umode_t mode, kuid_t uid, kgid_t gid,
 					 loff_t size,
 					 const struct kernfs_ops *ops,
-					 void *priv, const void *ns,
+					 void *priv, const struct ns_common *ns,
 					 struct lock_class_key *key)
 {
 	struct kernfs_node *kn;
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 6061b6f70d2a..b1fd9622a5e3 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -97,7 +97,7 @@ struct kernfs_super_info {
 	 * instance.  If multiple tags become necessary, make the following
 	 * an array and compare kernfs_node tag against every entry.
 	 */
-	const void		*ns;
+	const struct ns_common	*ns;
 
 	/* anchored at kernfs_root->supers, protected by kernfs_rwsem */
 	struct list_head	node;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 048f00b73b71..6e3217b6e481 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -345,7 +345,7 @@ static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
  *
  * Return: the namespace tag associated with kernfs super_block @sb.
  */
-const void *kernfs_super_ns(struct super_block *sb)
+const struct ns_common *kernfs_super_ns(struct super_block *sb)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
 
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 7d8921f524a6..1da4f707f9ef 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/string.h>
 #include <linux/nfs_fs.h>
+#include <net/net_namespace.h>
 #include <linux/rcupdate.h>
 #include <linux/lockd/lockd.h>
 
@@ -127,9 +128,10 @@ static void nfs_netns_client_release(struct kobject *kobj)
 	kfree(rcu_dereference_raw(c->identifier));
 }
 
-static const void *nfs_netns_client_namespace(const struct kobject *kobj)
+static const struct ns_common *nfs_netns_client_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct nfs_netns_client, kobject)->net;
+	return to_ns_common(container_of(kobj, struct nfs_netns_client,
+					 kobject)->net);
 }
 
 static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier,
@@ -156,9 +158,10 @@ static void nfs_netns_object_release(struct kobject *kobj)
 	kfree(c);
 }
 
-static const void *nfs_netns_namespace(const struct kobject *kobj)
+static const struct ns_common *nfs_netns_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct nfs_netns_client, nfs_net_kobj)->net;
+	return to_ns_common(container_of(kobj, struct nfs_netns_client,
+					 nfs_net_kobj)->net);
 }
 
 static struct kobj_type nfs_netns_object_type = {
@@ -350,9 +353,10 @@ static void nfs_sysfs_sb_release(struct kobject *kobj)
 	/* no-op: why? see lib/kobject.c kobject_cleanup() */
 }
 
-static const void *nfs_netns_server_namespace(const struct kobject *kobj)
+static const struct ns_common *nfs_netns_server_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct nfs_server, kobj)->nfs_client->cl_net;
+	return to_ns_common(container_of(kobj, struct nfs_server,
+					 kobj)->nfs_client->cl_net);
 }
 
 static struct kobj_type nfs_sb_ktype = {
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 94e12efd92f2..ffdcd4153c58 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -37,7 +37,7 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
  * @kobj: object we're creating directory for
  * @ns: the namespace tag to use
  */
-int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
+int sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns)
 {
 	struct kernfs_node *parent, *kn;
 	kuid_t uid;
@@ -103,7 +103,7 @@ void sysfs_remove_dir(struct kobject *kobj)
 }
 
 int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
-			const void *new_ns)
+			const struct ns_common *new_ns)
 {
 	struct kernfs_node *parent;
 	int ret;
@@ -115,7 +115,7 @@ int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
 }
 
 int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
-		      const void *new_ns)
+		      const struct ns_common *new_ns)
 {
 	struct kernfs_node *kn = kobj->sd;
 	struct kernfs_node *new_parent;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index a8176c875f55..5709cede1d75 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -272,7 +272,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
 
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 		const struct attribute *attr, umode_t mode, kuid_t uid,
-		kgid_t gid, const void *ns)
+		kgid_t gid, const struct ns_common *ns)
 {
 	struct kobject *kobj = parent->priv;
 	const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;
@@ -322,7 +322,7 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 
 int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
 		const struct bin_attribute *battr, umode_t mode, size_t size,
-		kuid_t uid, kgid_t gid, const void *ns)
+		kuid_t uid, kgid_t gid, const struct ns_common *ns)
 {
 	const struct attribute *attr = &battr->attr;
 	struct lock_class_key *key = NULL;
@@ -362,7 +362,7 @@ int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
  * @ns: namespace the new file should belong to
  */
 int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
-			 const void *ns)
+			 const struct ns_common *ns)
 {
 	kuid_t uid;
 	kgid_t gid;
@@ -505,7 +505,7 @@ EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection);
  * Hash the attribute name and namespace tag and kill the victim.
  */
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
-			  const void *ns)
+			  const struct ns_common *ns)
 {
 	struct kernfs_node *parent = kobj->sd;
 
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index e65c60158a04..b199e8ff79b1 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -55,7 +55,7 @@ static const struct fs_context_operations sysfs_fs_context_ops = {
 static int sysfs_init_fs_context(struct fs_context *fc)
 {
 	struct kernfs_fs_context *kfc;
-	struct net *netns;
+	struct ns_common *ns;
 
 	if (!(fc->sb_flags & SB_KERNMOUNT)) {
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
@@ -66,12 +66,14 @@ static int sysfs_init_fs_context(struct fs_context *fc)
 	if (!kfc)
 		return -ENOMEM;
 
-	kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	kfc->ns_tag = ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
 	kfc->root = sysfs_root;
 	kfc->magic = SYSFS_MAGIC;
 	fc->fs_private = kfc;
 	fc->ops = &sysfs_fs_context_ops;
-	if (netns) {
+	if (ns) {
+		struct net *netns = to_net_ns(ns);
+
 		put_user_ns(fc->user_ns);
 		fc->user_ns = get_user_ns(netns->user_ns);
 	}
@@ -81,7 +83,7 @@ static int sysfs_init_fs_context(struct fs_context *fc)
 
 static void sysfs_kill_sb(struct super_block *sb)
 {
-	void *ns = (void *)kernfs_super_ns(sb);
+	struct ns_common *ns = (struct ns_common *)kernfs_super_ns(sb);
 
 	kernfs_kill_sb(sb);
 	kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 5603530a1a52..5f9c05fb1394 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -121,7 +121,7 @@ EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn);
 void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
 			const char *name)
 {
-	const void *ns = NULL;
+	const struct ns_common *ns = NULL;
 
 	/*
 	 * We don't own @target and it may be removed at any time.
@@ -164,10 +164,11 @@ EXPORT_SYMBOL_GPL(sysfs_remove_link);
  *	A helper function for the common rename symlink idiom.
  */
 int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
-			 const char *old, const char *new, const void *new_ns)
+			 const char *old, const char *new,
+			 const struct ns_common *new_ns)
 {
 	struct kernfs_node *parent, *kn = NULL;
-	const void *old_ns = NULL;
+	const struct ns_common *old_ns = NULL;
 	int result;
 
 	if (!kobj)
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 8e012f25e1c0..f4583dcafcd1 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -29,10 +29,10 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name);
  */
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 		const struct attribute *attr, umode_t amode, kuid_t uid,
-		kgid_t gid, const void *ns);
+		kgid_t gid, const struct ns_common *ns);
 int sysfs_add_bin_file_mode_ns(struct kernfs_node *parent,
 		const struct bin_attribute *battr, umode_t mode, size_t size,
-		kuid_t uid, kgid_t gid, const void *ns);
+		kuid_t uid, kgid_t gid, const struct ns_common *ns);
 
 /*
  * symlink.c
diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index 65880e60c720..021da0d61796 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -62,7 +62,7 @@ struct class {
 	int (*shutdown_pre)(struct device *dev);
 
 	const struct kobj_ns_type_operations *ns_type;
-	const void *(*namespace)(const struct device *dev);
+	const struct ns_common *(*namespace)(const struct device *dev);
 
 	void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid);
 
@@ -180,9 +180,9 @@ struct class_attribute {
 	struct class_attribute class_attr_##_name = __ATTR_WO(_name)
 
 int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr,
-				      const void *ns);
+				      const struct ns_common *ns);
 void class_remove_file_ns(const struct class *class, const struct class_attribute *attr,
-			  const void *ns);
+			  const struct ns_common *ns);
 
 static inline int __must_check class_create_file(const struct class *class,
 						 const struct class_attribute *attr)
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index b5a5f32fdfd1..4f0ab88a1b31 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -23,6 +23,7 @@
 struct file;
 struct dentry;
 struct iattr;
+struct ns_common;
 struct seq_file;
 struct vm_area_struct;
 struct vm_operations_struct;
@@ -209,7 +210,7 @@ struct kernfs_node {
 
 	struct rb_node		rb;
 
-	const void		*ns;	/* namespace tag */
+	const struct ns_common	*ns;	/* namespace tag */
 	unsigned int		hash;	/* ns + name hash */
 	unsigned short		flags;
 	umode_t			mode;
@@ -331,7 +332,7 @@ struct kernfs_ops {
  */
 struct kernfs_fs_context {
 	struct kernfs_root	*root;		/* Root of the hierarchy being mounted */
-	void			*ns_tag;	/* Namespace tag of the mount (or NULL) */
+	struct ns_common	*ns_tag;	/* Namespace tag of the mount (or NULL) */
 	unsigned long		magic;		/* File system specific magic number */
 
 	/* The following are set/used by kernfs_mount() */
@@ -406,9 +407,11 @@ void pr_cont_kernfs_name(struct kernfs_node *kn);
 void pr_cont_kernfs_path(struct kernfs_node *kn);
 struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
-					   const char *name, const void *ns);
+					   const char *name,
+					   const struct ns_common *ns);
 struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
-					   const char *path, const void *ns);
+					   const char *path,
+					   const struct ns_common *ns);
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
@@ -426,7 +429,8 @@ unsigned int kernfs_root_flags(struct kernfs_node *kn);
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 kuid_t uid, kgid_t gid,
-					 void *priv, const void *ns);
+					 void *priv,
+					 const struct ns_common *ns);
 struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 					    const char *name);
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
@@ -434,7 +438,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 kuid_t uid, kgid_t gid,
 					 loff_t size,
 					 const struct kernfs_ops *ops,
-					 void *priv, const void *ns,
+					 void *priv,
+					 const struct ns_common *ns,
 					 struct lock_class_key *key);
 struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
@@ -446,9 +451,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn);
 void kernfs_unbreak_active_protection(struct kernfs_node *kn);
 bool kernfs_remove_self(struct kernfs_node *kn);
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
-			     const void *ns);
+			     const struct ns_common *ns);
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
-		     const char *new_name, const void *new_ns);
+		     const char *new_name, const struct ns_common *new_ns);
 int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
 __poll_t kernfs_generic_poll(struct kernfs_open_file *of,
 			     struct poll_table_struct *pt);
@@ -459,7 +464,7 @@ int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
 int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
 		     const void *value, size_t size, int flags);
 
-const void *kernfs_super_ns(struct super_block *sb);
+const struct ns_common *kernfs_super_ns(struct super_block *sb);
 int kernfs_get_tree(struct fs_context *fc);
 void kernfs_free_fs_context(struct fs_context *fc);
 void kernfs_kill_sb(struct super_block *sb);
@@ -494,11 +499,11 @@ static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
 
 static inline struct kernfs_node *
 kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
-		       const void *ns)
+		       const struct ns_common *ns)
 { return NULL; }
 static inline struct kernfs_node *
 kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path,
-		       const void *ns)
+		       const struct ns_common *ns)
 { return NULL; }
 
 static inline void kernfs_get(struct kernfs_node *kn) { }
@@ -526,14 +531,15 @@ static inline unsigned int kernfs_root_flags(struct kernfs_node *kn)
 static inline struct kernfs_node *
 kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
 		     umode_t mode, kuid_t uid, kgid_t gid,
-		     void *priv, const void *ns)
+		     void *priv, const struct ns_common *ns)
 { return ERR_PTR(-ENOSYS); }
 
 static inline struct kernfs_node *
 __kernfs_create_file(struct kernfs_node *parent, const char *name,
 		     umode_t mode, kuid_t uid, kgid_t gid,
 		     loff_t size, const struct kernfs_ops *ops,
-		     void *priv, const void *ns, struct lock_class_key *key)
+		     void *priv, const struct ns_common *ns,
+		     struct lock_class_key *key)
 { return ERR_PTR(-ENOSYS); }
 
 static inline struct kernfs_node *
@@ -549,12 +555,14 @@ static inline bool kernfs_remove_self(struct kernfs_node *kn)
 { return false; }
 
 static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn,
-					   const char *name, const void *ns)
+					   const char *name,
+					   const struct ns_common *ns)
 { return -ENOSYS; }
 
 static inline int kernfs_rename_ns(struct kernfs_node *kn,
 				   struct kernfs_node *new_parent,
-				   const char *new_name, const void *new_ns)
+				   const char *new_name,
+				   const struct ns_common *new_ns)
 { return -ENOSYS; }
 
 static inline int kernfs_setattr(struct kernfs_node *kn,
@@ -575,7 +583,7 @@ static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
 				   const void *value, size_t size, int flags)
 { return -ENOSYS; }
 
-static inline const void *kernfs_super_ns(struct super_block *sb)
+static inline const struct ns_common *kernfs_super_ns(struct super_block *sb)
 { return NULL; }
 
 static inline int kernfs_get_tree(struct fs_context *fc)
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index c8219505a79f..bcb5d4e32001 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -109,7 +109,7 @@ struct kobject *kobject_get(struct kobject *kobj);
 struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj);
 void kobject_put(struct kobject *kobj);
 
-const void *kobject_namespace(const struct kobject *kobj);
+const struct ns_common *kobject_namespace(const struct kobject *kobj);
 void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid);
 char *kobject_get_path(const struct kobject *kobj, gfp_t flag);
 
@@ -118,7 +118,7 @@ struct kobj_type {
 	const struct sysfs_ops *sysfs_ops;
 	const struct attribute_group **default_groups;
 	const struct kobj_ns_type_operations *(*child_ns_type)(const struct kobject *kobj);
-	const void *(*namespace)(const struct kobject *kobj);
+	const struct ns_common *(*namespace)(const struct kobject *kobj);
 	void (*get_ownership)(const struct kobject *kobj, kuid_t *uid, kgid_t *gid);
 };
 
diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h
index 150fe2ae1b6b..4f0990e09b93 100644
--- a/include/linux/kobject_ns.h
+++ b/include/linux/kobject_ns.h
@@ -16,6 +16,7 @@
 #ifndef _LINUX_KOBJECT_NS_H
 #define _LINUX_KOBJECT_NS_H
 
+struct ns_common;
 struct sock;
 struct kobject;
 
@@ -39,10 +40,10 @@ enum kobj_ns_type {
 struct kobj_ns_type_operations {
 	enum kobj_ns_type type;
 	bool (*current_may_mount)(void);
-	void *(*grab_current_ns)(void);
-	const void *(*netlink_ns)(struct sock *sk);
-	const void *(*initial_ns)(void);
-	void (*drop_ns)(void *);
+	struct ns_common *(*grab_current_ns)(void);
+	const struct ns_common *(*netlink_ns)(struct sock *sk);
+	const struct ns_common *(*initial_ns)(void);
+	void (*drop_ns)(struct ns_common *);
 };
 
 int kobj_ns_type_register(const struct kobj_ns_type_operations *ops);
@@ -51,7 +52,7 @@ const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *pa
 const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj);
 
 bool kobj_ns_current_may_mount(enum kobj_ns_type type);
-void *kobj_ns_grab_current(enum kobj_ns_type type);
-void kobj_ns_drop(enum kobj_ns_type type, void *ns);
+struct ns_common *kobj_ns_grab_current(enum kobj_ns_type type);
+void kobj_ns_drop(enum kobj_ns_type type, struct ns_common *ns);
 
 #endif /* _LINUX_KOBJECT_NS_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ca01eb3f7d2..85c20bdd36fb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5339,9 +5339,9 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi
 }
 
 int netdev_class_create_file_ns(const struct class_attribute *class_attr,
-				const void *ns);
+				const struct ns_common *ns);
 void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
-				 const void *ns);
+				 const struct ns_common *ns);
 
 extern const struct kobj_ns_type_operations net_ns_type_operations;
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 99b775f3ff46..468259fb6049 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -396,13 +396,13 @@ struct sysfs_ops {
 
 #ifdef CONFIG_SYSFS
 
-int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
+int __must_check sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns);
 void sysfs_remove_dir(struct kobject *kobj);
 int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
-				     const void *new_ns);
+				     const struct ns_common *new_ns);
 int __must_check sysfs_move_dir_ns(struct kobject *kobj,
 				   struct kobject *new_parent_kobj,
-				   const void *new_ns);
+				   const struct ns_common *new_ns);
 int __must_check sysfs_create_mount_point(struct kobject *parent_kobj,
 					  const char *name);
 void sysfs_remove_mount_point(struct kobject *parent_kobj,
@@ -410,7 +410,7 @@ void sysfs_remove_mount_point(struct kobject *parent_kobj,
 
 int __must_check sysfs_create_file_ns(struct kobject *kobj,
 				      const struct attribute *attr,
-				      const void *ns);
+				      const struct ns_common *ns);
 int __must_check sysfs_create_files(struct kobject *kobj,
 				   const struct attribute * const *attr);
 int __must_check sysfs_chmod_file(struct kobject *kobj,
@@ -419,7 +419,7 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj,
 						  const struct attribute *attr);
 void sysfs_unbreak_active_protection(struct kernfs_node *kn);
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
-			  const void *ns);
+			  const struct ns_common *ns);
 bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr);
 void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *attr);
 
@@ -437,7 +437,7 @@ void sysfs_remove_link(struct kobject *kobj, const char *name);
 
 int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *target,
 			 const char *old_name, const char *new_name,
-			 const void *new_ns);
+			 const struct ns_common *new_ns);
 
 void sysfs_delete_link(struct kobject *dir, struct kobject *targ,
 			const char *name);
@@ -502,7 +502,7 @@ ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj,
 
 #else /* CONFIG_SYSFS */
 
-static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
+static inline int sysfs_create_dir_ns(struct kobject *kobj, const struct ns_common *ns)
 {
 	return 0;
 }
@@ -512,14 +512,14 @@ static inline void sysfs_remove_dir(struct kobject *kobj)
 }
 
 static inline int sysfs_rename_dir_ns(struct kobject *kobj,
-				      const char *new_name, const void *new_ns)
+				      const char *new_name, const struct ns_common *new_ns)
 {
 	return 0;
 }
 
 static inline int sysfs_move_dir_ns(struct kobject *kobj,
 				    struct kobject *new_parent_kobj,
-				    const void *new_ns)
+				    const struct ns_common *new_ns)
 {
 	return 0;
 }
@@ -537,7 +537,7 @@ static inline void sysfs_remove_mount_point(struct kobject *parent_kobj,
 
 static inline int sysfs_create_file_ns(struct kobject *kobj,
 				       const struct attribute *attr,
-				       const void *ns)
+				       const struct ns_common *ns)
 {
 	return 0;
 }
@@ -567,7 +567,7 @@ static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn)
 
 static inline void sysfs_remove_file_ns(struct kobject *kobj,
 					const struct attribute *attr,
-					const void *ns)
+					const struct ns_common *ns)
 {
 }
 
@@ -612,7 +612,7 @@ static inline void sysfs_remove_link(struct kobject *kobj, const char *name)
 
 static inline int sysfs_rename_link_ns(struct kobject *k, struct kobject *t,
 				       const char *old_name,
-				       const char *new_name, const void *ns)
+				       const char *new_name, const struct ns_common *ns)
 {
 	return 0;
 }
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index d7bec49ee9ea..80de5e98a66d 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -264,14 +264,14 @@ void ipx_unregister_sysctl(void);
 #define ipx_unregister_sysctl()
 #endif
 
-#ifdef CONFIG_NET_NS
-void __put_net(struct net *net);
-
 static inline struct net *to_net_ns(struct ns_common *ns)
 {
 	return container_of(ns, struct net, ns);
 }
 
+#ifdef CONFIG_NET_NS
+void __put_net(struct net *net);
+
 /* Try using get_net_track() instead */
 static inline struct net *get_net(struct net *net)
 {
@@ -309,7 +309,7 @@ static inline int check_net(const struct net *net)
 	return ns_ref_read(net) != 0;
 }
 
-void net_drop_ns(void *);
+void net_drop_ns(struct ns_common *);
 void net_passive_dec(struct net *net);
 
 #else
diff --git a/lib/kobject.c b/lib/kobject.c
index cfdb2c3f20a2..9c9ff0f5175f 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -27,7 +27,7 @@
  * and thus @kobj should have a namespace tag associated with it.  Returns
  * %NULL otherwise.
  */
-const void *kobject_namespace(const struct kobject *kobj)
+const struct ns_common *kobject_namespace(const struct kobject *kobj)
 {
 	const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj);
 
@@ -1083,9 +1083,9 @@ bool kobj_ns_current_may_mount(enum kobj_ns_type type)
 	return may_mount;
 }
 
-void *kobj_ns_grab_current(enum kobj_ns_type type)
+struct ns_common *kobj_ns_grab_current(enum kobj_ns_type type)
 {
-	void *ns = NULL;
+	struct ns_common *ns = NULL;
 
 	spin_lock(&kobj_ns_type_lock);
 	if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type])
@@ -1096,7 +1096,7 @@ void *kobj_ns_grab_current(enum kobj_ns_type type)
 }
 EXPORT_SYMBOL_GPL(kobj_ns_grab_current);
 
-void kobj_ns_drop(enum kobj_ns_type type, void *ns)
+void kobj_ns_drop(enum kobj_ns_type type, struct ns_common *ns)
 {
 	spin_lock(&kobj_ns_type_lock);
 	if (kobj_ns_type_is_valid(type) &&
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 871941c9830c..ddbc4d7482d2 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -238,7 +238,7 @@ static int kobj_usermode_filter(struct kobject *kobj)
 
 	ops = kobj_ns_ops(kobj);
 	if (ops) {
-		const void *init_ns, *ns;
+		const struct ns_common *init_ns, *ns;
 
 		ns = kobj->ktype->namespace(kobj);
 		init_ns = ops->initial_ns();
@@ -388,7 +388,7 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj,
 
 #ifdef CONFIG_NET
 	const struct kobj_ns_type_operations *ops;
-	const struct net *net = NULL;
+	const struct ns_common *ns = NULL;
 
 	ops = kobj_ns_ops(kobj);
 	if (!ops && kobj->kset) {
@@ -404,14 +404,17 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj,
 	 */
 	if (ops && ops->netlink_ns && kobj->ktype->namespace)
 		if (ops->type == KOBJ_NS_TYPE_NET)
-			net = kobj->ktype->namespace(kobj);
+			ns = kobj->ktype->namespace(kobj);
 
-	if (!net)
+	if (!ns)
 		ret = uevent_net_broadcast_untagged(env, action_string,
 						    devpath);
-	else
+	else {
+		const struct net *net = container_of(ns, struct net, ns);
+
 		ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env,
 						  action_string, devpath);
+	}
 #endif
 
 	return ret;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 07624b682b08..b9740a397f55 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1181,24 +1181,24 @@ static void rx_queue_release(struct kobject *kobj)
 	netdev_put(queue->dev, &queue->dev_tracker);
 }
 
-static const void *rx_queue_namespace(const struct kobject *kobj)
+static const struct ns_common *rx_queue_namespace(const struct kobject *kobj)
 {
 	struct netdev_rx_queue *queue = to_rx_queue(kobj);
 	struct device *dev = &queue->dev->dev;
-	const void *ns = NULL;
 
 	if (dev->class && dev->class->namespace)
-		ns = dev->class->namespace(dev);
+		return dev->class->namespace(dev);
 
-	return ns;
+	return NULL;
 }
 
 static void rx_queue_get_ownership(const struct kobject *kobj,
 				   kuid_t *uid, kgid_t *gid)
 {
-	const struct net *net = rx_queue_namespace(kobj);
+	const struct ns_common *ns = rx_queue_namespace(kobj);
 
-	net_ns_get_ownership(net, uid, gid);
+	net_ns_get_ownership(ns ? container_of(ns, struct net, ns) : NULL,
+			     uid, gid);
 }
 
 static const struct kobj_type rx_queue_ktype = {
@@ -1931,24 +1931,24 @@ static void netdev_queue_release(struct kobject *kobj)
 	netdev_put(queue->dev, &queue->dev_tracker);
 }
 
-static const void *netdev_queue_namespace(const struct kobject *kobj)
+static const struct ns_common *netdev_queue_namespace(const struct kobject *kobj)
 {
 	struct netdev_queue *queue = to_netdev_queue(kobj);
 	struct device *dev = &queue->dev->dev;
-	const void *ns = NULL;
 
 	if (dev->class && dev->class->namespace)
-		ns = dev->class->namespace(dev);
+		return dev->class->namespace(dev);
 
-	return ns;
+	return NULL;
 }
 
 static void netdev_queue_get_ownership(const struct kobject *kobj,
 				       kuid_t *uid, kgid_t *gid)
 {
-	const struct net *net = netdev_queue_namespace(kobj);
+	const struct ns_common *ns = netdev_queue_namespace(kobj);
 
-	net_ns_get_ownership(net, uid, gid);
+	net_ns_get_ownership(ns ? container_of(ns, struct net, ns) : NULL,
+			     uid, gid);
 }
 
 static const struct kobj_type netdev_queue_ktype = {
@@ -2185,24 +2185,24 @@ static bool net_current_may_mount(void)
 	return ns_capable(net->user_ns, CAP_SYS_ADMIN);
 }
 
-static void *net_grab_current_ns(void)
+static struct ns_common *net_grab_current_ns(void)
 {
-	struct net *ns = current->nsproxy->net_ns;
+	struct net *net = current->nsproxy->net_ns;
 #ifdef CONFIG_NET_NS
-	if (ns)
-		refcount_inc(&ns->passive);
+	if (net)
+		refcount_inc(&net->passive);
 #endif
-	return ns;
+	return net ? to_ns_common(net) : NULL;
 }
 
-static const void *net_initial_ns(void)
+static const struct ns_common *net_initial_ns(void)
 {
-	return &init_net;
+	return to_ns_common(&init_net);
 }
 
-static const void *net_netlink_ns(struct sock *sk)
+static const struct ns_common *net_netlink_ns(struct sock *sk)
 {
-	return sock_net(sk);
+	return to_ns_common(sock_net(sk));
 }
 
 const struct kobj_ns_type_operations net_ns_type_operations = {
@@ -2252,11 +2252,11 @@ static void netdev_release(struct device *d)
 	kvfree(dev);
 }
 
-static const void *net_namespace(const struct device *d)
+static const struct ns_common *net_namespace(const struct device *d)
 {
 	const struct net_device *dev = to_net_dev(d);
 
-	return dev_net(dev);
+	return to_ns_common(dev_net(dev));
 }
 
 static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid)
@@ -2402,14 +2402,14 @@ int netdev_change_owner(struct net_device *ndev, const struct net *net_old,
 }
 
 int netdev_class_create_file_ns(const struct class_attribute *class_attr,
-				const void *ns)
+				const struct ns_common *ns)
 {
 	return class_create_file_ns(&net_class, class_attr, ns);
 }
 EXPORT_SYMBOL(netdev_class_create_file_ns);
 
 void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
-				 const void *ns)
+				 const struct ns_common *ns)
 {
 	class_remove_file_ns(&net_class, class_attr, ns);
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 1057d16d5dd2..24aa10a1d0ea 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -540,12 +540,10 @@ void net_passive_dec(struct net *net)
 	}
 }
 
-void net_drop_ns(void *p)
+void net_drop_ns(struct ns_common *ns)
 {
-	struct net *net = (struct net *)p;
-
-	if (net)
-		net_passive_dec(net);
+	if (ns)
+		net_passive_dec(to_net_ns(ns));
 }
 
 struct net *copy_net_ns(u64 flags,
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index af8fac9cedd4..a90480f80154 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -6,6 +6,7 @@
 #include <linux/kobject.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/xprtsock.h>
+#include <net/net_namespace.h>
 
 #include "sysfs.h"
 
@@ -553,20 +554,22 @@ static void rpc_sysfs_xprt_release(struct kobject *kobj)
 	kfree(xprt);
 }
 
-static const void *rpc_sysfs_client_namespace(const struct kobject *kobj)
+static const struct ns_common *rpc_sysfs_client_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct rpc_sysfs_client, kobject)->net;
+	return to_ns_common(container_of(kobj, struct rpc_sysfs_client,
+					 kobject)->net);
 }
 
-static const void *rpc_sysfs_xprt_switch_namespace(const struct kobject *kobj)
+static const struct ns_common *rpc_sysfs_xprt_switch_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct rpc_sysfs_xprt_switch, kobject)->net;
+	return to_ns_common(container_of(kobj, struct rpc_sysfs_xprt_switch,
+					 kobject)->net);
 }
 
-static const void *rpc_sysfs_xprt_namespace(const struct kobject *kobj)
+static const struct ns_common *rpc_sysfs_xprt_namespace(const struct kobject *kobj)
 {
-	return container_of(kobj, struct rpc_sysfs_xprt,
-			    kobject)->xprt->xprt_net;
+	return to_ns_common(container_of(kobj, struct rpc_sysfs_xprt,
+					 kobject)->xprt->xprt_net);
 }
 
 static struct kobj_attribute rpc_sysfs_clnt_version = __ATTR(rpc_version,
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 2e0ea69b9604..0b9abe70d39d 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -154,11 +154,11 @@ static SIMPLE_DEV_PM_OPS(wiphy_pm_ops, wiphy_suspend, wiphy_resume);
 #define WIPHY_PM_OPS NULL
 #endif
 
-static const void *wiphy_namespace(const struct device *d)
+static const struct ns_common *wiphy_namespace(const struct device *d)
 {
 	struct wiphy *wiphy = container_of(d, struct wiphy, dev);
 
-	return wiphy_net(wiphy);
+	return to_ns_common(wiphy_net(wiphy));
 }
 
 struct class ieee80211_class = {
-- 
cgit v1.2.3


From 1fe989e1c42a315c7e7918e7b812377137085036 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 1 Apr 2026 12:21:16 +0200
Subject: kernfs: use namespace id instead of pointer for hashing and
 comparison

kernfs uses the namespace tag as both a hash seed (via init_name_hash())
and a comparison key in the rbtree. The resulting hash values are exposed
to userspace through directory seek positions (ctx->pos), and the raw
pointer comparisons in kernfs_name_compare() encode kernel pointer
ordering into the rbtree layout.

This constitutes a KASLR information leak since the hash and ordering
derived from kernel pointers can be observed from userspace.

Fix this by using the 64-bit namespace id (ns_common::ns_id) instead of
the raw pointer value for both hashing and comparison. The namespace id
is a stable, non-secret identifier that is already exposed to userspace
through other interfaces (e.g., /proc/pid/ns/, ioctl NS_GET_NSID).

Introduce kernfs_ns_id() as a helper that extracts the namespace id from
a potentially-NULL ns_common pointer, returning 0 for the no-namespace
case.

All namespace equality checks in the directory iteration and dentry
revalidation paths are also switched from pointer comparison to ns_id
comparison for consistency.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/kernfs/dir.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index be262145ae08..f5cf1d74b5f1 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <linux/hash.h>
+#include <linux/ns_common.h>
 
 #include "kernfs-internal.h"
 
@@ -306,6 +307,18 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
 	return parent;
 }
 
+/*
+ * kernfs_ns_id - return the namespace id for a given namespace
+ * @ns: namespace tag (may be NULL)
+ *
+ * Use the 64-bit namespace id instead of raw pointers for hashing
+ * and comparison to avoid leaking kernel addresses to userspace.
+ */
+static u64 kernfs_ns_id(const struct ns_common *ns)
+{
+	return ns ? ns->ns_id : 0;
+}
+
 /**
  *	kernfs_name_hash - calculate hash of @ns + @name
  *	@name: Null terminated string to hash
@@ -316,7 +329,7 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
 static unsigned int kernfs_name_hash(const char *name,
 				     const struct ns_common *ns)
 {
-	unsigned long hash = init_name_hash(ns);
+	unsigned long hash = init_name_hash(kernfs_ns_id(ns));
 	unsigned int len = strlen(name);
 	while (len--)
 		hash = partial_name_hash(*name++, hash);
@@ -333,13 +346,16 @@ static unsigned int kernfs_name_hash(const char *name,
 static int kernfs_name_compare(unsigned int hash, const char *name,
 			       const struct ns_common *ns, const struct kernfs_node *kn)
 {
+	u64 ns_id = kernfs_ns_id(ns);
+	u64 kn_ns_id = kernfs_ns_id(kn->ns);
+
 	if (hash < kn->hash)
 		return -1;
 	if (hash > kn->hash)
 		return 1;
-	if (ns < kn->ns)
+	if (ns_id < kn_ns_id)
 		return -1;
-	if (ns > kn->ns)
+	if (ns_id > kn_ns_id)
 		return 1;
 	return strcmp(name, kernfs_rcu_name(kn));
 }
@@ -1203,7 +1219,7 @@ static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name,
 
 	/* The kernfs node has been moved to a different namespace */
 	if (parent && kernfs_ns_enabled(parent) &&
-	    kernfs_info(dentry->d_sb)->ns != kn->ns)
+	    kernfs_ns_id(kernfs_info(dentry->d_sb)->ns) != kernfs_ns_id(kn->ns))
 		goto out_bad;
 
 	up_read(&root->kernfs_rwsem);
@@ -1775,7 +1791,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	old_name = kernfs_rcu_name(kn);
 	if (!new_name)
 		new_name = old_name;
-	if ((old_parent == new_parent) && (kn->ns == new_ns) &&
+	if ((old_parent == new_parent) &&
+	    (kernfs_ns_id(kn->ns) == kernfs_ns_id(new_ns)) &&
 	    (strcmp(old_name, new_name) == 0))
 		goto out;	/* nothing to rename */
 
@@ -1861,7 +1878,8 @@ static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns,
 		}
 	}
 	/* Skip over entries which are dying/dead or in the wrong namespace */
-	while (pos && (!kernfs_active(pos) || pos->ns != ns)) {
+	while (pos && (!kernfs_active(pos) ||
+		       kernfs_ns_id(pos->ns) != kernfs_ns_id(ns))) {
 		struct rb_node *node = rb_next(&pos->rb);
 		if (!node)
 			pos = NULL;
@@ -1882,7 +1900,8 @@ static struct kernfs_node *kernfs_dir_next_pos(const struct ns_common *ns,
 				pos = NULL;
 			else
 				pos = rb_to_kn(node);
-		} while (pos && (!kernfs_active(pos) || pos->ns != ns));
+		} while (pos && (!kernfs_active(pos) ||
+			kernfs_ns_id(pos->ns) != kernfs_ns_id(ns)));
 	}
 	return pos;
 }
-- 
cgit v1.2.3


From cb76a81c7cec37bdf525164561b02665cd763421 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 2 Apr 2026 09:12:11 +0200
Subject: kernfs: make directory seek namespace-aware

The rbtree backing kernfs directories is ordered by (hash, ns_id, name)
but kernfs_dir_pos() only searches by hash when seeking to a position
during readdir. When two nodes from different namespaces share the same
hash value, the binary search can land on a node in the wrong namespace.
The subsequent skip-forward loop walks rb_next() and may overshoot the
correct node, silently dropping an entry from the readdir results.

With the recent switch from raw namespace pointers to public namespace
ids as hash seeds, computing hash collisions became an offline operation.
An unprivileged user could unshare into a new network namespace, create
a single interface whose name-hash collides with a target entry in
init_net, and cause a victim's seekdir/readdir on /sys/class/net to miss
that entry.

Fix this by extending the rbtree search in kernfs_dir_pos() to also
compare namespace ids when hashes match. Since the rbtree is already
ordered by (hash, ns_id, name), this makes the seek land directly in the
correct namespace's range, eliminating the wrong-namespace overshoot.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/kernfs/dir.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index f5cf1d74b5f1..22a4dff2a3af 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1866,6 +1866,7 @@ static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns,
 	}
 	if (!pos && (hash > 1) && (hash < INT_MAX)) {
 		struct rb_node *node = parent->dir.children.rb_node;
+		u64 ns_id = kernfs_ns_id(ns);
 		while (node) {
 			pos = rb_to_kn(node);
 
@@ -1873,6 +1874,10 @@ static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns,
 				node = node->rb_left;
 			else if (hash > pos->hash)
 				node = node->rb_right;
+			else if (ns_id < kernfs_ns_id(pos->ns))
+				node = node->rb_left;
+			else if (ns_id > kernfs_ns_id(pos->ns))
+				node = node->rb_right;
 			else
 				break;
 		}
-- 
cgit v1.2.3


From 3fd0da4fd8851a7e62d009b7db6c4a05b092bc19 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Sun, 5 Apr 2026 06:52:39 +0100
Subject: net: lan966x: fix page_pool error handling in
 lan966x_fdma_rx_alloc_page_pool()

page_pool_create() can return an ERR_PTR on failure. The return value
is used unconditionally in the loop that follows, passing the error
pointer through xdp_rxq_info_reg_mem_model() into page_pool_use_xdp_mem(),
which dereferences it, causing a kernel oops.

Add an IS_ERR check after page_pool_create() to return early on failure.

Fixes: 11871aba1974 ("net: lan96x: Use page_pool API")
Cc: stable@vger.kernel.org
Signed-off-by: David Carlier <devnexen@gmail.com>
Link: https://patch.msgid.link/20260405055241.35767-2-devnexen@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 7b6369e43451..74851c63e46a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -91,6 +91,8 @@ static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
 		pp_params.dma_dir = DMA_BIDIRECTIONAL;
 
 	rx->page_pool = page_pool_create(&pp_params);
+	if (unlikely(IS_ERR(rx->page_pool)))
+		return PTR_ERR(rx->page_pool);
 
 	for (int i = 0; i < lan966x->num_phys_ports; ++i) {
 		struct lan966x_port *port;
-- 
cgit v1.2.3


From 076344a6ad9d1308faaed1402fdcfdda68b604ab Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Sun, 5 Apr 2026 06:52:40 +0100
Subject: net: lan966x: fix page pool leak in error paths

lan966x_fdma_rx_alloc() creates a page pool but does not destroy it if
the subsequent fdma_alloc_coherent() call fails, leaking the pool.

Similarly, lan966x_fdma_init() frees the coherent DMA memory when
lan966x_fdma_tx_alloc() fails but does not destroy the page pool that
was successfully created by lan966x_fdma_rx_alloc(), leaking it.

Add the missing page_pool_destroy() calls in both error paths.

Fixes: 11871aba1974 ("net: lan96x: Use page_pool API")
Cc: stable@vger.kernel.org
Signed-off-by: David Carlier <devnexen@gmail.com>
Link: https://patch.msgid.link/20260405055241.35767-3-devnexen@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 74851c63e46a..10773fe93d4d 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -119,8 +119,10 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 		return PTR_ERR(rx->page_pool);
 
 	err = fdma_alloc_coherent(lan966x->dev, fdma);
-	if (err)
+	if (err) {
+		page_pool_destroy(rx->page_pool);
 		return err;
+	}
 
 	fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size),
 		       FDMA_DCB_STATUS_INTR);
@@ -957,6 +959,7 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 	err = lan966x_fdma_tx_alloc(&lan966x->tx);
 	if (err) {
 		fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma);
+		page_pool_destroy(lan966x->rx.page_pool);
 		return err;
 	}
 
-- 
cgit v1.2.3


From 59c3d55a946cacdb4181600723c20ac4f4c20c84 Mon Sep 17 00:00:00 2001
From: David Carlier <devnexen@gmail.com>
Date: Sun, 5 Apr 2026 06:52:41 +0100
Subject: net: lan966x: fix use-after-free and leak in lan966x_fdma_reload()

When lan966x_fdma_reload() fails to allocate new RX buffers, the restore
path restarts DMA using old descriptors whose pages were already freed
via lan966x_fdma_rx_free_pages(). Since page_pool_put_full_page() can
release pages back to the buddy allocator, the hardware may DMA into
memory now owned by other kernel subsystems.

Additionally, on the restore path, the newly created page pool (if
allocation partially succeeded) is overwritten without being destroyed,
leaking it.

Fix both issues by deferring the release of old pages until after the
new allocation succeeds. Save the old page array before the allocation
so old pages can be freed on the success path. On the failure path, the
old descriptors, pages and page pool are all still valid, making the
restore safe. Also ensure the restore path re-enables NAPI and wakes
the netdev, matching the success path.

Fixes: 89ba464fcf54 ("net: lan966x: refactor buffer reload function")
Cc: stable@vger.kernel.org
Signed-off-by: David Carlier <devnexen@gmail.com>
Link: https://patch.msgid.link/20260405055241.35767-4-devnexen@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c   | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 10773fe93d4d..f8ce735a7fc0 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -812,9 +812,15 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x)
 
 static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 {
+	struct page *(*old_pages)[FDMA_RX_DCB_MAX_DBS];
 	struct page_pool *page_pool;
 	struct fdma fdma_rx_old;
-	int err;
+	int err, i, j;
+
+	old_pages = kmemdup(lan966x->rx.page, sizeof(lan966x->rx.page),
+			   GFP_KERNEL);
+	if (!old_pages)
+		return -ENOMEM;
 
 	/* Store these for later to free them */
 	memcpy(&fdma_rx_old, &lan966x->rx.fdma, sizeof(struct fdma));
@@ -825,7 +831,6 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 	lan966x_fdma_stop_netdev(lan966x);
 
 	lan966x_fdma_rx_disable(&lan966x->rx);
-	lan966x_fdma_rx_free_pages(&lan966x->rx);
 	lan966x->rx.page_order = round_up(new_mtu, PAGE_SIZE) / PAGE_SIZE - 1;
 	lan966x->rx.max_mtu = new_mtu;
 	err = lan966x_fdma_rx_alloc(&lan966x->rx);
@@ -833,6 +838,11 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 		goto restore;
 	lan966x_fdma_rx_start(&lan966x->rx);
 
+	for (i = 0; i < fdma_rx_old.n_dcbs; ++i)
+		for (j = 0; j < fdma_rx_old.n_dbs; ++j)
+			page_pool_put_full_page(page_pool,
+						old_pages[i][j], false);
+
 	fdma_free_coherent(lan966x->dev, &fdma_rx_old);
 
 	page_pool_destroy(page_pool);
@@ -840,12 +850,17 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 	lan966x_fdma_wakeup_netdev(lan966x);
 	napi_enable(&lan966x->napi);
 
-	return err;
+	kfree(old_pages);
+	return 0;
 restore:
 	lan966x->rx.page_pool = page_pool;
 	memcpy(&lan966x->rx.fdma, &fdma_rx_old, sizeof(struct fdma));
 	lan966x_fdma_rx_start(&lan966x->rx);
 
+	lan966x_fdma_wakeup_netdev(lan966x);
+	napi_enable(&lan966x->napi);
+
+	kfree(old_pages);
 	return err;
 }
 
-- 
cgit v1.2.3


From 57df6923ca53b524d06d2347b896d9de74b3bc86 Mon Sep 17 00:00:00 2001
From: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Date: Thu, 9 Apr 2026 11:58:53 -0700
Subject: gpio: tegra: return -ENOMEM on allocation failure in probe

devm_kzalloc() failure in tegra_gpio_probe() returns -ENODEV, which
indicates "no such device". The correct error code for a memory
allocation failure is -ENOMEM.

Signed-off-by: Samasth Norway Ananda <samasth.norway.ananda@oracle.com>
Link: https://patch.msgid.link/20260409185853.2163034-1-samasth.norway.ananda@oracle.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
---
 drivers/gpio/gpio-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index b14052fe64ac..df06b56a2ade 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -698,7 +698,7 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 
 	tgi = devm_kzalloc(&pdev->dev, sizeof(*tgi), GFP_KERNEL);
 	if (!tgi)
-		return -ENODEV;
+		return -ENOMEM;
 
 	tgi->soc = of_device_get_match_data(&pdev->dev);
 	tgi->dev = &pdev->dev;
-- 
cgit v1.2.3


From ba893caead54745595e29953f0531cf3651610aa Mon Sep 17 00:00:00 2001
From: David Arcari <darcari@redhat.com>
Date: Thu, 19 Mar 2026 10:03:07 -0400
Subject: tools/power turbostat: Allow execution to continue after
 perf_l2_init() failure

Currently, if perf_l2_init() fails turbostat exits after issuing the
following error (which was encountered on AlderLake):

turbostat: perf_l2_init(cpu0, 0x0, 0xff24) REFS: Invalid argument

This occurs because perf_l2_init() calls err(). However, the code has been
written in such a manner that it is able to perform cleanup and continue.
Therefore, this issue can be addressed by changing the appropriate calls
to err() to warnx().

Additionally, correct the PMU type arguments passed to the warning strings
in the ecore and lcore blocks so the logs accurately reflect the failing
counter type.

Signed-off-by: David Arcari <darcari@redhat.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 tools/power/x86/turbostat/turbostat.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 34e2143cd4b3..e9e8ef72395a 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -9405,13 +9405,13 @@ void perf_l2_init(void)
 		if (!is_hybrid) {
 			fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP);
 			if (fd_l2_percpu[cpu] == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.refs);
 				free_fd_l2_percpu();
 				return;
 			}
 			retval = open_perf_counter(cpu, perf_pmu_types.uniform, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
 			if (retval == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.uniform, perf_model_support->first.hits);
 				free_fd_l2_percpu();
 				return;
 			}
@@ -9420,39 +9420,39 @@ void perf_l2_init(void)
 		if (perf_pcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_pcore_set)) {
 			fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.refs, -1, PERF_FORMAT_GROUP);
 			if (fd_l2_percpu[cpu] == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.refs);
 				free_fd_l2_percpu();
 				return;
 			}
 			retval = open_perf_counter(cpu, perf_pmu_types.pcore, perf_model_support->first.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
 			if (retval == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->first.hits);
 				free_fd_l2_percpu();
 				return;
 			}
 		} else if (perf_ecore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_ecore_set)) {
 			fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.refs, -1, PERF_FORMAT_GROUP);
 			if (fd_l2_percpu[cpu] == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.refs);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.refs);
 				free_fd_l2_percpu();
 				return;
 			}
 			retval = open_perf_counter(cpu, perf_pmu_types.ecore, perf_model_support->second.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
 			if (retval == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->second.hits);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.ecore, perf_model_support->second.hits);
 				free_fd_l2_percpu();
 				return;
 			}
 		} else if (perf_lcore_set && CPU_ISSET_S(cpu, cpu_possible_setsize, perf_lcore_set)) {
 			fd_l2_percpu[cpu] = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.refs, -1, PERF_FORMAT_GROUP);
 			if (fd_l2_percpu[cpu] == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.refs);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) REFS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.refs);
 				free_fd_l2_percpu();
 				return;
 			}
 			retval = open_perf_counter(cpu, perf_pmu_types.lcore, perf_model_support->third.hits, fd_l2_percpu[cpu], PERF_FORMAT_GROUP);
 			if (retval == -1) {
-				err(-1, "%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.pcore, perf_model_support->third.hits);
+				warnx("%s(cpu%d, 0x%x, 0x%llx) HITS", __func__, cpu, perf_pmu_types.lcore, perf_model_support->third.hits);
 				free_fd_l2_percpu();
 				return;
 			}
-- 
cgit v1.2.3


From d6e152d905bdb1f32f9d99775e2f453350399a6a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@kernel.org>
Date: Tue, 7 Apr 2026 10:54:17 +0200
Subject: clockevents: Prevent timer interrupt starvation

Calvin reported an odd NMI watchdog lockup which claims that the CPU locked
up in user space. He provided a reproducer, which sets up a timerfd based
timer and then rearms it in a loop with an absolute expiry time of 1ns.

As the expiry time is in the past, the timer ends up as the first expiring
timer in the per CPU hrtimer base and the clockevent device is programmed
with the minimum delta value. If the machine is fast enough, this ends up
in a endless loop of programming the delta value to the minimum value
defined by the clock event device, before the timer interrupt can fire,
which starves the interrupt and consequently triggers the lockup detector
because the hrtimer callback of the lockup mechanism is never invoked.

As a first step to prevent this, avoid reprogramming the clock event device
when:
     - a forced minimum delta event is pending
     - the new expiry delta is less then or equal to the minimum delta

Thanks to Calvin for providing the reproducer and to Borislav for testing
and providing data from his Zen5 machine.

The problem is not limited to Zen5, but depending on the underlying
clock event device (e.g. TSC deadline timer on Intel) and the CPU speed
not necessarily observable.

This change serves only as the last resort and further changes will be made
to prevent this scenario earlier in the call chain as far as possible.

[ tglx: Updated to restore the old behaviour vs. !force and delta <= 0 and
  	fixed up the tick-broadcast handlers as pointed out by Borislav ]

Fixes: d316c57ff6bf ("[PATCH] clockevents: add core functionality")
Reported-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Thomas Gleixner <tglx@kernel.org>
Tested-by: Calvin Owens <calvin@wbinvd.org>
Tested-by: Borislav Petkov <bp@alien8.de>
Link: https://lore.kernel.org/lkml/acMe-QZUel-bBYUh@mozart.vkv.me/
Link: https://patch.msgid.link/20260407083247.562657657@kernel.org
---
 include/linux/clockchips.h   |  2 ++
 kernel/time/clockevents.c    | 27 +++++++++++++++++++--------
 kernel/time/hrtimer.c        |  1 +
 kernel/time/tick-broadcast.c |  8 +++++++-
 kernel/time/tick-common.c    |  1 +
 kernel/time/tick-sched.c     |  1 +
 6 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index b0df28ddd394..50cdc9da8d32 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -80,6 +80,7 @@ enum clock_event_state {
  * @shift:		nanoseconds to cycles divisor (power of two)
  * @state_use_accessors:current state of the device, assigned by the core code
  * @features:		features
+ * @next_event_forced:	True if the last programming was a forced event
  * @retries:		number of forced programming retries
  * @set_state_periodic:	switch state to periodic
  * @set_state_oneshot:	switch state to oneshot
@@ -108,6 +109,7 @@ struct clock_event_device {
 	u32			shift;
 	enum clock_event_state	state_use_accessors;
 	unsigned int		features;
+	unsigned int		next_event_forced;
 	unsigned long		retries;
 
 	int			(*set_state_periodic)(struct clock_event_device *);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index eaae1ce9f060..38570998a19b 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -172,6 +172,7 @@ void clockevents_shutdown(struct clock_event_device *dev)
 {
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 }
 
 /**
@@ -305,7 +306,6 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 {
 	unsigned long long clc;
 	int64_t delta;
-	int rc;
 
 	if (WARN_ON_ONCE(expires < 0))
 		return -ETIME;
@@ -324,16 +324,27 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires,
 		return dev->set_next_ktime(expires, dev);
 
 	delta = ktime_to_ns(ktime_sub(expires, ktime_get()));
-	if (delta <= 0)
-		return force ? clockevents_program_min_delta(dev) : -ETIME;
 
-	delta = min(delta, (int64_t) dev->max_delta_ns);
-	delta = max(delta, (int64_t) dev->min_delta_ns);
+	/* Required for tick_periodic() during early boot */
+	if (delta <= 0 && !force)
+		return -ETIME;
+
+	if (delta > (int64_t)dev->min_delta_ns) {
+		delta = min(delta, (int64_t) dev->max_delta_ns);
+		clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
+		if (!dev->set_next_event((unsigned long) clc, dev))
+			return 0;
+	}
 
-	clc = ((unsigned long long) delta * dev->mult) >> dev->shift;
-	rc = dev->set_next_event((unsigned long) clc, dev);
+	if (dev->next_event_forced)
+		return 0;
 
-	return (rc && force) ? clockevents_program_min_delta(dev) : rc;
+	if (dev->set_next_event(dev->min_delta_ticks, dev)) {
+		if (!force || clockevents_program_min_delta(dev))
+			return -ETIME;
+	}
+	dev->next_event_forced = 1;
+	return 0;
 }
 
 /*
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 860af7a58428..1e37142fe52f 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1888,6 +1888,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 	entry_time = now = hrtimer_update_base(cpu_base);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f63c65881364..7e57fa31ee26 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -76,8 +76,10 @@ const struct clock_event_device *tick_get_wakeup_device(int cpu)
  */
 static void tick_broadcast_start_periodic(struct clock_event_device *bc)
 {
-	if (bc)
+	if (bc) {
+		bc->next_event_forced = 0;
 		tick_setup_periodic(bc, 1);
+	}
 }
 
 /*
@@ -403,6 +405,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+	tick_broadcast_device.evtdev->next_event_forced = 0;
 
 	/* Handle spurious interrupts gracefully */
 	if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) {
@@ -696,6 +699,7 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 
 	raw_spin_lock(&tick_broadcast_lock);
 	dev->next_event = KTIME_MAX;
+	tick_broadcast_device.evtdev->next_event_forced = 0;
 	next_event = KTIME_MAX;
 	cpumask_clear(tmpmask);
 	now = ktime_get();
@@ -1063,6 +1067,7 @@ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc,
 
 
 	bc->event_handler = tick_handle_oneshot_broadcast;
+	bc->next_event_forced = 0;
 	bc->next_event = KTIME_MAX;
 
 	/*
@@ -1175,6 +1180,7 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 		}
 
 		/* This moves the broadcast assignment to this CPU: */
+		bc->next_event_forced = 0;
 		clockevents_program_event(bc, bc->next_event, 1);
 	}
 	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index d305d8521896..6a9198a4279b 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -110,6 +110,7 @@ void tick_handle_periodic(struct clock_event_device *dev)
 	int cpu = smp_processor_id();
 	ktime_t next = dev->next_event;
 
+	dev->next_event_forced = 0;
 	tick_periodic(cpu);
 
 	/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 36449f0010a4..d1f27df1e60e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1513,6 +1513,7 @@ static void tick_nohz_lowres_handler(struct clock_event_device *dev)
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
 
 	dev->next_event = KTIME_MAX;
+	dev->next_event_forced = 0;
 
 	if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART))
 		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
-- 
cgit v1.2.3


From 31d00156e50ecad37f2cb6cbf04aaa9a260505ef Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 4 Apr 2026 08:29:58 +0800
Subject: crypto: af_alg - Fix page reassignment overflow in af_alg_pull_tsgl

When page reassignment was added to af_alg_pull_tsgl the original
loop wasn't updated so it may try to reassign one more page than
necessary.

Add the check to the reassignment so that this does not happen.

Also update the comment which still refers to the obsolete offset
argument.

Reported-by: syzbot+d23888375c2737c17ba5@syzkaller.appspotmail.com
Fixes: e870456d8e7c ("crypto: algif_skcipher - overhaul memory management")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 437f3e77c7e0..dd0e5be4d8c0 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -705,8 +705,8 @@ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst)
 			 * Assumption: caller created af_alg_count_tsgl(len)
 			 * SG entries in dst.
 			 */
-			if (dst) {
-				/* reassign page to dst after offset */
+			if (dst && plen) {
+				/* reassign page to dst */
 				get_page(page);
 				sg_set_page(dst + j, page, plen, sg[i].offset);
 				j++;
-- 
cgit v1.2.3


From d702c3408213bb12bd570bb97204d8340d141c51 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Tue, 7 Apr 2026 12:58:18 +0200
Subject: X.509: Fix out-of-bounds access when parsing extensions

Leo reports an out-of-bounds access when parsing a certificate with
empty Basic Constraints or Key Usage extension because the first byte of
the extension is read before checking its length.  Fix it.

The bug can be triggered by an unprivileged user by submitting a
specially crafted certificate to the kernel through the keyrings(7) API.
Leo has demonstrated this with a proof-of-concept program responsibly
disclosed off-list.

Fixes: 30eae2b037af ("KEYS: X.509: Parse Basic Constraints for CA")
Fixes: 567671281a75 ("KEYS: X.509: Parse Key Usage")
Reported-by: Leo Lin <leo@depthfirst.com> # off-list
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Ignat Korchagin <ignat@linux.win>
Cc: stable@vger.kernel.org # v6.4+
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/asymmetric_keys/x509_cert_parser.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 37e4fb9da106..bfd10f0195e0 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -609,10 +609,10 @@ int x509_process_extension(void *context, size_t hdrlen,
 		 *   0x04 is where keyCertSign lands in this bit string
 		 *   0x80 is where digitalSignature lands in this bit string
 		 */
-		if (v[0] != ASN1_BTS)
-			return -EBADMSG;
 		if (vlen < 4)
 			return -EBADMSG;
+		if (v[0] != ASN1_BTS)
+			return -EBADMSG;
 		if (v[2] >= 8)
 			return -EBADMSG;
 		if (v[3] & 0x80)
@@ -645,10 +645,10 @@ int x509_process_extension(void *context, size_t hdrlen,
 		 *	(Expect 0xFF if the CA is TRUE)
 		 * vlen should match the entire extension size
 		 */
-		if (v[0] != (ASN1_CONS_BIT | ASN1_SEQ))
-			return -EBADMSG;
 		if (vlen < 2)
 			return -EBADMSG;
+		if (v[0] != (ASN1_CONS_BIT | ASN1_SEQ))
+			return -EBADMSG;
 		if (v[1] != vlen - 2)
 			return -EBADMSG;
 		/* Empty SEQUENCE means CA:FALSE (default value omitted per DER) */
-- 
cgit v1.2.3


From 3d14bd48e3a77091cbce637a12c2ae31b4a1687c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 12 Apr 2026 13:32:21 +0800
Subject: crypto: algif_aead - Fix minimum RX size check for decryption

The check for the minimum receive buffer size did not take the
tag size into account during decryption.  Fix this by adding the
required extra length.

Reported-by: syzbot+aa11561819dc42ebbc7c@syzkaller.appspotmail.com
Reported-by: Daniel Pouzzner <douzzer@mega.nu>
Fixes: d887c52d6ae4 ("crypto: algif_aead - overhaul memory management")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/algif_aead.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index dda15bb05e89..f8bd45f7dc83 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -144,7 +144,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
 	if (usedpages < outlen) {
 		size_t less = outlen - usedpages;
 
-		if (used < less) {
+		if (used < less + (ctx->enc ? 0 : as)) {
 			err = -EINVAL;
 			goto free;
 		}
-- 
cgit v1.2.3


From 028ef9c96e96197026887c0f092424679298aae8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 12 Apr 2026 13:48:06 -0700
Subject: Linux 7.0

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 4f54c5685638..36d0a32fbe49 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 7
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3